Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/QwQ-32B-Preview
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: original
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# original
+
+This model is a fine-tuned version of [Qwen/QwQ-32B-Preview](https://huggingface.co/Qwen/QwQ-32B-Preview) on the MOS-v1 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 96
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 223704105418752.0,
+    "train_loss": 0.4401542440255483,
+    "train_runtime": 59266.2263,
+    "train_samples_per_second": 0.607,
+    "train_steps_per_second": 0.006
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/QwQ-32B-Preview",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39416500e1822bb432adc139df2e22821e0d55911284f94eace12e729b4d7e17
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5765b95edd33c738573d577652b63ff8ee330b26568f8f382a75566c2716348a
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15748eafcdac2c1b99a2faa31b6a48b9dec8f6a1751aee51891f9ed5814f2b5d
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8b408ef14bf329d53efb1d7736486d3aa4fb37dca22fa9c7d81f9e79d6d9b89
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764540a155bbdb9e925bf6b51f34e68f4277795bd4e4dd4441b226ca43fa324c
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb44efdddfe74c7f92dc310d97d08f741f4d1e5003065de5f0b3daeb4adc01a5
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53762413d900d995554b53f71cb6f574cef0b399e648b405f8121d0f514ffcda
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c999e3b59cb6c8c95ce35753a223a9e1b50396995ba38e8a2726666880c24a
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba4d310c2b2212dc1d0f4fcde0d8d20c7a58012f00756954e4f7b4e7fdc7023
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac105a054b11f78d04549bf1f87f824618c9dadb4ae914fbc2f062ce373952c
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f30863569265759145290073731790b372eca7cb62561ba2578f2c348138e1
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10d244d115ba9bc5b8197ef55248611b9d61dcecccc0687cffc145ffc3dfd54
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d89a2c7f67049be2bc254d818691479b9a58addd8c9449e413803dac4f2734a
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dddfdd3c94d6e26606d7eb524d05da3ff4dbfd92b57ea261a06abe0c955ecf0a
+size 2123397800

model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 223704105418752.0,
+    "train_loss": 0.4401542440255483,
+    "train_runtime": 59266.2263,
+    "train_samples_per_second": 0.607,
+    "train_steps_per_second": 0.006
+}

trainer_log.jsonl

@@ -0,0 +1,376 @@
+{"current_steps": 1, "total_steps": 375, "loss": 0.8339, "lr": 2.6315789473684213e-07, "epoch": 0.008, "percentage": 0.27, "elapsed_time": "0:02:55", "remaining_time": "18:16:12"}
+{"current_steps": 2, "total_steps": 375, "loss": 0.8732, "lr": 5.263157894736843e-07, "epoch": 0.016, "percentage": 0.53, "elapsed_time": "0:05:34", "remaining_time": "17:18:43"}
+{"current_steps": 3, "total_steps": 375, "loss": 0.894, "lr": 7.894736842105263e-07, "epoch": 0.024, "percentage": 0.8, "elapsed_time": "0:08:09", "remaining_time": "16:50:49"}
+{"current_steps": 4, "total_steps": 375, "loss": 0.8509, "lr": 1.0526315789473685e-06, "epoch": 0.032, "percentage": 1.07, "elapsed_time": "0:10:51", "remaining_time": "16:47:07"}
+{"current_steps": 5, "total_steps": 375, "loss": 0.8362, "lr": 1.3157894736842106e-06, "epoch": 0.04, "percentage": 1.33, "elapsed_time": "0:13:29", "remaining_time": "16:38:28"}
+{"current_steps": 6, "total_steps": 375, "loss": 0.8653, "lr": 1.5789473684210526e-06, "epoch": 0.048, "percentage": 1.6, "elapsed_time": "0:16:03", "remaining_time": "16:27:55"}
+{"current_steps": 7, "total_steps": 375, "loss": 0.8321, "lr": 1.8421052631578948e-06, "epoch": 0.056, "percentage": 1.87, "elapsed_time": "0:18:41", "remaining_time": "16:22:32"}
+{"current_steps": 8, "total_steps": 375, "loss": 0.8143, "lr": 2.105263157894737e-06, "epoch": 0.064, "percentage": 2.13, "elapsed_time": "0:21:19", "remaining_time": "16:18:10"}
+{"current_steps": 9, "total_steps": 375, "loss": 0.7905, "lr": 2.368421052631579e-06, "epoch": 0.072, "percentage": 2.4, "elapsed_time": "0:23:54", "remaining_time": "16:12:06"}
+{"current_steps": 10, "total_steps": 375, "loss": 0.7129, "lr": 2.631578947368421e-06, "epoch": 0.08, "percentage": 2.67, "elapsed_time": "0:26:28", "remaining_time": "16:06:12"}
+{"current_steps": 11, "total_steps": 375, "loss": 0.7227, "lr": 2.8947368421052634e-06, "epoch": 0.088, "percentage": 2.93, "elapsed_time": "0:28:59", "remaining_time": "15:59:23"}
+{"current_steps": 12, "total_steps": 375, "loss": 0.6972, "lr": 3.157894736842105e-06, "epoch": 0.096, "percentage": 3.2, "elapsed_time": "0:31:33", "remaining_time": "15:54:45"}
+{"current_steps": 13, "total_steps": 375, "loss": 0.678, "lr": 3.421052631578948e-06, "epoch": 0.104, "percentage": 3.47, "elapsed_time": "0:34:10", "remaining_time": "15:51:49"}
+{"current_steps": 14, "total_steps": 375, "loss": 0.667, "lr": 3.6842105263157896e-06, "epoch": 0.112, "percentage": 3.73, "elapsed_time": "0:36:49", "remaining_time": "15:49:38"}
+{"current_steps": 15, "total_steps": 375, "loss": 0.6192, "lr": 3.947368421052632e-06, "epoch": 0.12, "percentage": 4.0, "elapsed_time": "0:39:25", "remaining_time": "15:46:04"}
+{"current_steps": 16, "total_steps": 375, "loss": 0.6118, "lr": 4.210526315789474e-06, "epoch": 0.128, "percentage": 4.27, "elapsed_time": "0:41:57", "remaining_time": "15:41:24"}
+{"current_steps": 17, "total_steps": 375, "loss": 0.5681, "lr": 4.473684210526316e-06, "epoch": 0.136, "percentage": 4.53, "elapsed_time": "0:44:29", "remaining_time": "15:36:49"}
+{"current_steps": 18, "total_steps": 375, "loss": 0.607, "lr": 4.736842105263158e-06, "epoch": 0.144, "percentage": 4.8, "elapsed_time": "0:47:06", "remaining_time": "15:34:22"}
+{"current_steps": 19, "total_steps": 375, "loss": 0.5273, "lr": 5e-06, "epoch": 0.152, "percentage": 5.07, "elapsed_time": "0:49:41", "remaining_time": "15:31:07"}
+{"current_steps": 20, "total_steps": 375, "loss": 0.5578, "lr": 5.263157894736842e-06, "epoch": 0.16, "percentage": 5.33, "elapsed_time": "0:52:20", "remaining_time": "15:29:07"}
+{"current_steps": 21, "total_steps": 375, "loss": 0.5794, "lr": 5.526315789473685e-06, "epoch": 0.168, "percentage": 5.6, "elapsed_time": "0:54:57", "remaining_time": "15:26:19"}
+{"current_steps": 22, "total_steps": 375, "loss": 0.5229, "lr": 5.789473684210527e-06, "epoch": 0.176, "percentage": 5.87, "elapsed_time": "0:57:37", "remaining_time": "15:24:41"}
+{"current_steps": 23, "total_steps": 375, "loss": 0.5292, "lr": 6.0526315789473685e-06, "epoch": 0.184, "percentage": 6.13, "elapsed_time": "1:00:14", "remaining_time": "15:21:55"}
+{"current_steps": 24, "total_steps": 375, "loss": 0.5271, "lr": 6.31578947368421e-06, "epoch": 0.192, "percentage": 6.4, "elapsed_time": "1:02:51", "remaining_time": "15:19:15"}
+{"current_steps": 25, "total_steps": 375, "loss": 0.5155, "lr": 6.578947368421054e-06, "epoch": 0.2, "percentage": 6.67, "elapsed_time": "1:05:30", "remaining_time": "15:17:13"}
+{"current_steps": 26, "total_steps": 375, "loss": 0.5287, "lr": 6.842105263157896e-06, "epoch": 0.208, "percentage": 6.93, "elapsed_time": "1:08:14", "remaining_time": "15:16:04"}
+{"current_steps": 27, "total_steps": 375, "loss": 0.4791, "lr": 7.1052631578947375e-06, "epoch": 0.216, "percentage": 7.2, "elapsed_time": "1:10:51", "remaining_time": "15:13:11"}
+{"current_steps": 28, "total_steps": 375, "loss": 0.5329, "lr": 7.368421052631579e-06, "epoch": 0.224, "percentage": 7.47, "elapsed_time": "1:13:26", "remaining_time": "15:10:09"}
+{"current_steps": 29, "total_steps": 375, "loss": 0.5294, "lr": 7.631578947368423e-06, "epoch": 0.232, "percentage": 7.73, "elapsed_time": "1:16:02", "remaining_time": "15:07:19"}
+{"current_steps": 30, "total_steps": 375, "loss": 0.4842, "lr": 7.894736842105265e-06, "epoch": 0.24, "percentage": 8.0, "elapsed_time": "1:18:39", "remaining_time": "15:04:36"}
+{"current_steps": 31, "total_steps": 375, "loss": 0.5348, "lr": 8.157894736842106e-06, "epoch": 0.248, "percentage": 8.27, "elapsed_time": "1:21:22", "remaining_time": "15:02:55"}
+{"current_steps": 32, "total_steps": 375, "loss": 0.5382, "lr": 8.421052631578948e-06, "epoch": 0.256, "percentage": 8.53, "elapsed_time": "1:24:04", "remaining_time": "15:01:13"}
+{"current_steps": 33, "total_steps": 375, "loss": 0.5039, "lr": 8.68421052631579e-06, "epoch": 0.264, "percentage": 8.8, "elapsed_time": "1:26:39", "remaining_time": "14:58:04"}
+{"current_steps": 34, "total_steps": 375, "loss": 0.5037, "lr": 8.947368421052632e-06, "epoch": 0.272, "percentage": 9.07, "elapsed_time": "1:29:19", "remaining_time": "14:55:51"}
+{"current_steps": 35, "total_steps": 375, "loss": 0.5017, "lr": 9.210526315789474e-06, "epoch": 0.28, "percentage": 9.33, "elapsed_time": "1:31:56", "remaining_time": "14:53:11"}
+{"current_steps": 36, "total_steps": 375, "loss": 0.4469, "lr": 9.473684210526315e-06, "epoch": 0.288, "percentage": 9.6, "elapsed_time": "1:34:31", "remaining_time": "14:50:08"}
+{"current_steps": 37, "total_steps": 375, "loss": 0.478, "lr": 9.736842105263159e-06, "epoch": 0.296, "percentage": 9.87, "elapsed_time": "1:37:03", "remaining_time": "14:46:42"}
+{"current_steps": 38, "total_steps": 375, "loss": 0.5392, "lr": 1e-05, "epoch": 0.304, "percentage": 10.13, "elapsed_time": "1:39:34", "remaining_time": "14:43:07"}
+{"current_steps": 39, "total_steps": 375, "loss": 0.5022, "lr": 9.99978274148479e-06, "epoch": 0.312, "percentage": 10.4, "elapsed_time": "1:42:05", "remaining_time": "14:39:35"}
+{"current_steps": 40, "total_steps": 375, "loss": 0.5057, "lr": 9.999130984819662e-06, "epoch": 0.32, "percentage": 10.67, "elapsed_time": "1:44:35", "remaining_time": "14:35:56"}
+{"current_steps": 41, "total_steps": 375, "loss": 0.4718, "lr": 9.998044786644492e-06, "epoch": 0.328, "percentage": 10.93, "elapsed_time": "1:47:03", "remaining_time": "14:32:04"}
+{"current_steps": 42, "total_steps": 375, "loss": 0.5049, "lr": 9.9965242413536e-06, "epoch": 0.336, "percentage": 11.2, "elapsed_time": "1:49:32", "remaining_time": "14:28:30"}
+{"current_steps": 43, "total_steps": 375, "loss": 0.5203, "lr": 9.994569481087552e-06, "epoch": 0.344, "percentage": 11.47, "elapsed_time": "1:52:03", "remaining_time": "14:25:07"}
+{"current_steps": 44, "total_steps": 375, "loss": 0.4967, "lr": 9.992180675721671e-06, "epoch": 0.352, "percentage": 11.73, "elapsed_time": "1:54:32", "remaining_time": "14:21:37"}
+{"current_steps": 45, "total_steps": 375, "loss": 0.5188, "lr": 9.989358032851283e-06, "epoch": 0.36, "percentage": 12.0, "elapsed_time": "1:56:55", "remaining_time": "14:17:30"}
+{"current_steps": 46, "total_steps": 375, "loss": 0.4864, "lr": 9.986101797773667e-06, "epoch": 0.368, "percentage": 12.27, "elapsed_time": "1:59:25", "remaining_time": "14:14:06"}
+{"current_steps": 47, "total_steps": 375, "loss": 0.4883, "lr": 9.98241225346674e-06, "epoch": 0.376, "percentage": 12.53, "elapsed_time": "2:01:55", "remaining_time": "14:10:52"}
+{"current_steps": 48, "total_steps": 375, "loss": 0.5121, "lr": 9.978289720564471e-06, "epoch": 0.384, "percentage": 12.8, "elapsed_time": "2:04:33", "remaining_time": "14:08:30"}
+{"current_steps": 49, "total_steps": 375, "loss": 0.4975, "lr": 9.97373455732901e-06, "epoch": 0.392, "percentage": 13.07, "elapsed_time": "2:07:11", "remaining_time": "14:06:13"}
+{"current_steps": 50, "total_steps": 375, "loss": 0.4944, "lr": 9.968747159619556e-06, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "2:09:37", "remaining_time": "14:02:35"}
+{"current_steps": 51, "total_steps": 375, "loss": 0.5209, "lr": 9.963327960857962e-06, "epoch": 0.408, "percentage": 13.6, "elapsed_time": "2:19:08", "remaining_time": "14:44:00"}
+{"current_steps": 52, "total_steps": 375, "loss": 0.514, "lr": 9.957477431991053e-06, "epoch": 0.416, "percentage": 13.87, "elapsed_time": "2:21:35", "remaining_time": "14:39:29"}
+{"current_steps": 53, "total_steps": 375, "loss": 0.526, "lr": 9.95119608144972e-06, "epoch": 0.424, "percentage": 14.13, "elapsed_time": "2:24:01", "remaining_time": "14:35:01"}
+{"current_steps": 54, "total_steps": 375, "loss": 0.4806, "lr": 9.944484455104716e-06, "epoch": 0.432, "percentage": 14.4, "elapsed_time": "2:26:27", "remaining_time": "14:30:35"}
+{"current_steps": 55, "total_steps": 375, "loss": 0.5273, "lr": 9.937343136219234e-06, "epoch": 0.44, "percentage": 14.67, "elapsed_time": "2:28:53", "remaining_time": "14:26:18"}
+{"current_steps": 56, "total_steps": 375, "loss": 0.5745, "lr": 9.929772745398207e-06, "epoch": 0.448, "percentage": 14.93, "elapsed_time": "2:31:21", "remaining_time": "14:22:09"}
+{"current_steps": 57, "total_steps": 375, "loss": 0.5082, "lr": 9.921773940534382e-06, "epoch": 0.456, "percentage": 15.2, "elapsed_time": "2:33:47", "remaining_time": "14:17:57"}
+{"current_steps": 58, "total_steps": 375, "loss": 0.5244, "lr": 9.913347416751148e-06, "epoch": 0.464, "percentage": 15.47, "elapsed_time": "2:36:12", "remaining_time": "14:13:46"}
+{"current_steps": 59, "total_steps": 375, "loss": 0.5117, "lr": 9.904493906342124e-06, "epoch": 0.472, "percentage": 15.73, "elapsed_time": "2:38:39", "remaining_time": "14:09:47"}
+{"current_steps": 60, "total_steps": 375, "loss": 0.4942, "lr": 9.895214178707516e-06, "epoch": 0.48, "percentage": 16.0, "elapsed_time": "2:41:06", "remaining_time": "14:05:49"}
+{"current_steps": 61, "total_steps": 375, "loss": 0.5165, "lr": 9.885509040287267e-06, "epoch": 0.488, "percentage": 16.27, "elapsed_time": "2:43:34", "remaining_time": "14:02:00"}
+{"current_steps": 62, "total_steps": 375, "loss": 0.5218, "lr": 9.875379334490962e-06, "epoch": 0.496, "percentage": 16.53, "elapsed_time": "2:46:01", "remaining_time": "13:58:10"}
+{"current_steps": 63, "total_steps": 375, "loss": 0.4986, "lr": 9.864825941624538e-06, "epoch": 0.504, "percentage": 16.8, "elapsed_time": "2:48:28", "remaining_time": "13:54:18"}
+{"current_steps": 64, "total_steps": 375, "loss": 0.5127, "lr": 9.853849778813777e-06, "epoch": 0.512, "percentage": 17.07, "elapsed_time": "2:50:53", "remaining_time": "13:50:27"}
+{"current_steps": 65, "total_steps": 375, "loss": 0.5158, "lr": 9.842451799924616e-06, "epoch": 0.52, "percentage": 17.33, "elapsed_time": "2:53:22", "remaining_time": "13:46:51"}
+{"current_steps": 66, "total_steps": 375, "loss": 0.5006, "lr": 9.830632995480243e-06, "epoch": 0.528, "percentage": 17.6, "elapsed_time": "2:55:54", "remaining_time": "13:43:32"}
+{"current_steps": 67, "total_steps": 375, "loss": 0.5126, "lr": 9.818394392575018e-06, "epoch": 0.536, "percentage": 17.87, "elapsed_time": "2:58:22", "remaining_time": "13:40:00"}
+{"current_steps": 68, "total_steps": 375, "loss": 0.5394, "lr": 9.805737054785223e-06, "epoch": 0.544, "percentage": 18.13, "elapsed_time": "3:00:50", "remaining_time": "13:36:24"}
+{"current_steps": 69, "total_steps": 375, "loss": 0.5224, "lr": 9.792662082076618e-06, "epoch": 0.552, "percentage": 18.4, "elapsed_time": "3:03:17", "remaining_time": "13:32:51"}
+{"current_steps": 70, "total_steps": 375, "loss": 0.5125, "lr": 9.779170610708872e-06, "epoch": 0.56, "percentage": 18.67, "elapsed_time": "3:05:45", "remaining_time": "13:29:23"}
+{"current_steps": 71, "total_steps": 375, "loss": 0.5081, "lr": 9.765263813136796e-06, "epoch": 0.568, "percentage": 18.93, "elapsed_time": "3:08:16", "remaining_time": "13:26:07"}
+{"current_steps": 72, "total_steps": 375, "loss": 0.4958, "lr": 9.750942897908468e-06, "epoch": 0.576, "percentage": 19.2, "elapsed_time": "3:10:44", "remaining_time": "13:22:40"}
+{"current_steps": 73, "total_steps": 375, "loss": 0.5279, "lr": 9.736209109560201e-06, "epoch": 0.584, "percentage": 19.47, "elapsed_time": "3:13:10", "remaining_time": "13:19:09"}
+{"current_steps": 74, "total_steps": 375, "loss": 0.5136, "lr": 9.721063728508384e-06, "epoch": 0.592, "percentage": 19.73, "elapsed_time": "3:15:38", "remaining_time": "13:15:46"}
+{"current_steps": 75, "total_steps": 375, "loss": 0.474, "lr": 9.705508070938219e-06, "epoch": 0.6, "percentage": 20.0, "elapsed_time": "3:18:04", "remaining_time": "13:12:17"}
+{"current_steps": 76, "total_steps": 375, "loss": 0.4994, "lr": 9.689543488689332e-06, "epoch": 0.608, "percentage": 20.27, "elapsed_time": "3:20:31", "remaining_time": "13:08:54"}
+{"current_steps": 77, "total_steps": 375, "loss": 0.5183, "lr": 9.673171369138297e-06, "epoch": 0.616, "percentage": 20.53, "elapsed_time": "3:22:59", "remaining_time": "13:05:37"}
+{"current_steps": 78, "total_steps": 375, "loss": 0.493, "lr": 9.656393135078067e-06, "epoch": 0.624, "percentage": 20.8, "elapsed_time": "3:25:27", "remaining_time": "13:02:20"}
+{"current_steps": 79, "total_steps": 375, "loss": 0.4635, "lr": 9.639210244594335e-06, "epoch": 0.632, "percentage": 21.07, "elapsed_time": "3:27:55", "remaining_time": "12:59:02"}
+{"current_steps": 80, "total_steps": 375, "loss": 0.5312, "lr": 9.621624190938802e-06, "epoch": 0.64, "percentage": 21.33, "elapsed_time": "3:30:23", "remaining_time": "12:55:50"}
+{"current_steps": 81, "total_steps": 375, "loss": 0.4524, "lr": 9.603636502399436e-06, "epoch": 0.648, "percentage": 21.6, "elapsed_time": "3:32:52", "remaining_time": "12:52:38"}
+{"current_steps": 82, "total_steps": 375, "loss": 0.4648, "lr": 9.585248742167638e-06, "epoch": 0.656, "percentage": 21.87, "elapsed_time": "3:35:19", "remaining_time": "12:49:24"}
+{"current_steps": 83, "total_steps": 375, "loss": 0.4911, "lr": 9.566462508202403e-06, "epoch": 0.664, "percentage": 22.13, "elapsed_time": "3:37:46", "remaining_time": "12:46:09"}
+{"current_steps": 84, "total_steps": 375, "loss": 0.4968, "lr": 9.547279433091446e-06, "epoch": 0.672, "percentage": 22.4, "elapsed_time": "3:40:13", "remaining_time": "12:42:55"}
+{"current_steps": 85, "total_steps": 375, "loss": 0.4879, "lr": 9.527701183909336e-06, "epoch": 0.68, "percentage": 22.67, "elapsed_time": "3:42:41", "remaining_time": "12:39:45"}
+{"current_steps": 86, "total_steps": 375, "loss": 0.4577, "lr": 9.507729462072615e-06, "epoch": 0.688, "percentage": 22.93, "elapsed_time": "3:45:09", "remaining_time": "12:36:38"}
+{"current_steps": 87, "total_steps": 375, "loss": 0.4922, "lr": 9.48736600319193e-06, "epoch": 0.696, "percentage": 23.2, "elapsed_time": "3:47:37", "remaining_time": "12:33:31"}
+{"current_steps": 88, "total_steps": 375, "loss": 0.4915, "lr": 9.466612576921223e-06, "epoch": 0.704, "percentage": 23.47, "elapsed_time": "3:50:02", "remaining_time": "12:30:16"}
+{"current_steps": 89, "total_steps": 375, "loss": 0.4711, "lr": 9.445470986803922e-06, "epoch": 0.712, "percentage": 23.73, "elapsed_time": "3:52:27", "remaining_time": "12:26:58"}
+{"current_steps": 90, "total_steps": 375, "loss": 0.5108, "lr": 9.423943070116219e-06, "epoch": 0.72, "percentage": 24.0, "elapsed_time": "3:54:54", "remaining_time": "12:23:51"}
+{"current_steps": 91, "total_steps": 375, "loss": 0.5128, "lr": 9.402030697707398e-06, "epoch": 0.728, "percentage": 24.27, "elapsed_time": "3:57:19", "remaining_time": "12:20:38"}
+{"current_steps": 92, "total_steps": 375, "loss": 0.4823, "lr": 9.37973577383726e-06, "epoch": 0.736, "percentage": 24.53, "elapsed_time": "3:59:43", "remaining_time": "12:17:25"}
+{"current_steps": 93, "total_steps": 375, "loss": 0.4985, "lr": 9.357060236010626e-06, "epoch": 0.744, "percentage": 24.8, "elapsed_time": "4:02:13", "remaining_time": "12:14:28"}
+{"current_steps": 94, "total_steps": 375, "loss": 0.4484, "lr": 9.334006054808966e-06, "epoch": 0.752, "percentage": 25.07, "elapsed_time": "4:04:36", "remaining_time": "12:11:13"}
+{"current_steps": 95, "total_steps": 375, "loss": 0.5047, "lr": 9.310575233719155e-06, "epoch": 0.76, "percentage": 25.33, "elapsed_time": "4:07:02", "remaining_time": "12:08:05"}
+{"current_steps": 96, "total_steps": 375, "loss": 0.5064, "lr": 9.28676980895935e-06, "epoch": 0.768, "percentage": 25.6, "elapsed_time": "4:09:24", "remaining_time": "12:04:51"}
+{"current_steps": 97, "total_steps": 375, "loss": 0.4604, "lr": 9.262591849302049e-06, "epoch": 0.776, "percentage": 25.87, "elapsed_time": "4:11:47", "remaining_time": "12:01:38"}
+{"current_steps": 98, "total_steps": 375, "loss": 0.5295, "lr": 9.238043455894294e-06, "epoch": 0.784, "percentage": 26.13, "elapsed_time": "4:14:09", "remaining_time": "11:58:22"}
+{"current_steps": 99, "total_steps": 375, "loss": 0.4977, "lr": 9.213126762075088e-06, "epoch": 0.792, "percentage": 26.4, "elapsed_time": "4:16:30", "remaining_time": "11:55:07"}
+{"current_steps": 100, "total_steps": 375, "loss": 0.4732, "lr": 9.187843933189994e-06, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "4:18:51", "remaining_time": "11:51:52"}
+{"current_steps": 101, "total_steps": 375, "loss": 0.5175, "lr": 9.162197166402957e-06, "epoch": 0.808, "percentage": 26.93, "elapsed_time": "4:28:30", "remaining_time": "12:08:25"}
+{"current_steps": 102, "total_steps": 375, "loss": 0.5087, "lr": 9.136188690505363e-06, "epoch": 0.816, "percentage": 27.2, "elapsed_time": "4:30:59", "remaining_time": "12:05:16"}
+{"current_steps": 103, "total_steps": 375, "loss": 0.4835, "lr": 9.109820765722357e-06, "epoch": 0.824, "percentage": 27.47, "elapsed_time": "4:33:30", "remaining_time": "12:02:17"}
+{"current_steps": 104, "total_steps": 375, "loss": 0.5349, "lr": 9.083095683516414e-06, "epoch": 0.832, "percentage": 27.73, "elapsed_time": "4:36:05", "remaining_time": "11:59:26"}
+{"current_steps": 105, "total_steps": 375, "loss": 0.4567, "lr": 9.056015766388205e-06, "epoch": 0.84, "percentage": 28.0, "elapsed_time": "4:38:38", "remaining_time": "11:56:30"}
+{"current_steps": 106, "total_steps": 375, "loss": 0.5166, "lr": 9.028583367674767e-06, "epoch": 0.848, "percentage": 28.27, "elapsed_time": "4:41:10", "remaining_time": "11:53:33"}
+{"current_steps": 107, "total_steps": 375, "loss": 0.4526, "lr": 9.00080087134498e-06, "epoch": 0.856, "percentage": 28.53, "elapsed_time": "4:43:41", "remaining_time": "11:50:34"}
+{"current_steps": 108, "total_steps": 375, "loss": 0.4893, "lr": 8.972670691792409e-06, "epoch": 0.864, "percentage": 28.8, "elapsed_time": "4:46:08", "remaining_time": "11:47:25"}
+{"current_steps": 109, "total_steps": 375, "loss": 0.4924, "lr": 8.944195273625472e-06, "epoch": 0.872, "percentage": 29.07, "elapsed_time": "4:48:40", "remaining_time": "11:44:27"}
+{"current_steps": 110, "total_steps": 375, "loss": 0.4981, "lr": 8.915377091454992e-06, "epoch": 0.88, "percentage": 29.33, "elapsed_time": "4:51:11", "remaining_time": "11:41:29"}
+{"current_steps": 111, "total_steps": 375, "loss": 0.5134, "lr": 8.886218649679162e-06, "epoch": 0.888, "percentage": 29.6, "elapsed_time": "4:53:37", "remaining_time": "11:38:21"}
+{"current_steps": 112, "total_steps": 375, "loss": 0.461, "lr": 8.856722482265886e-06, "epoch": 0.896, "percentage": 29.87, "elapsed_time": "4:56:02", "remaining_time": "11:35:10"}
+{"current_steps": 113, "total_steps": 375, "loss": 0.505, "lr": 8.826891152532579e-06, "epoch": 0.904, "percentage": 30.13, "elapsed_time": "4:58:29", "remaining_time": "11:32:03"}
+{"current_steps": 114, "total_steps": 375, "loss": 0.4716, "lr": 8.796727252923403e-06, "epoch": 0.912, "percentage": 30.4, "elapsed_time": "5:00:57", "remaining_time": "11:29:01"}
+{"current_steps": 115, "total_steps": 375, "loss": 0.5296, "lr": 8.766233404783975e-06, "epoch": 0.92, "percentage": 30.67, "elapsed_time": "5:03:21", "remaining_time": "11:25:52"}
+{"current_steps": 116, "total_steps": 375, "loss": 0.5045, "lr": 8.735412258133562e-06, "epoch": 0.928, "percentage": 30.93, "elapsed_time": "5:05:47", "remaining_time": "11:22:44"}
+{"current_steps": 117, "total_steps": 375, "loss": 0.472, "lr": 8.704266491434787e-06, "epoch": 0.936, "percentage": 31.2, "elapsed_time": "5:08:16", "remaining_time": "11:19:46"}
+{"current_steps": 118, "total_steps": 375, "loss": 0.5026, "lr": 8.672798811360863e-06, "epoch": 0.944, "percentage": 31.47, "elapsed_time": "5:10:45", "remaining_time": "11:16:49"}
+{"current_steps": 119, "total_steps": 375, "loss": 0.484, "lr": 8.641011952560372e-06, "epoch": 0.952, "percentage": 31.73, "elapsed_time": "5:13:14", "remaining_time": "11:13:52"}
+{"current_steps": 120, "total_steps": 375, "loss": 0.4997, "lr": 8.608908677419606e-06, "epoch": 0.96, "percentage": 32.0, "elapsed_time": "5:15:41", "remaining_time": "11:10:49"}
+{"current_steps": 121, "total_steps": 375, "loss": 0.4804, "lr": 8.576491775822527e-06, "epoch": 0.968, "percentage": 32.27, "elapsed_time": "5:18:03", "remaining_time": "11:07:39"}
+{"current_steps": 122, "total_steps": 375, "loss": 0.4887, "lr": 8.543764064908295e-06, "epoch": 0.976, "percentage": 32.53, "elapsed_time": "5:20:27", "remaining_time": "11:04:33"}
+{"current_steps": 123, "total_steps": 375, "loss": 0.4453, "lr": 8.510728388826464e-06, "epoch": 0.984, "percentage": 32.8, "elapsed_time": "5:22:55", "remaining_time": "11:01:35"}
+{"current_steps": 124, "total_steps": 375, "loss": 0.5123, "lr": 8.477387618489808e-06, "epoch": 0.992, "percentage": 33.07, "elapsed_time": "5:25:23", "remaining_time": "10:58:38"}
+{"current_steps": 125, "total_steps": 375, "loss": 0.4633, "lr": 8.443744651324828e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "5:27:54", "remaining_time": "10:55:49"}
+{"current_steps": 126, "total_steps": 375, "loss": 0.427, "lr": 8.409802411019962e-06, "epoch": 1.008, "percentage": 33.6, "elapsed_time": "5:30:28", "remaining_time": "10:53:04"}
+{"current_steps": 127, "total_steps": 375, "loss": 0.4324, "lr": 8.375563847271506e-06, "epoch": 1.016, "percentage": 33.87, "elapsed_time": "5:32:57", "remaining_time": "10:50:11"}
+{"current_steps": 128, "total_steps": 375, "loss": 0.4387, "lr": 8.341031935527267e-06, "epoch": 1.024, "percentage": 34.13, "elapsed_time": "5:35:24", "remaining_time": "10:47:14"}
+{"current_steps": 129, "total_steps": 375, "loss": 0.4469, "lr": 8.306209676727994e-06, "epoch": 1.032, "percentage": 34.4, "elapsed_time": "5:37:53", "remaining_time": "10:44:21"}
+{"current_steps": 130, "total_steps": 375, "loss": 0.4226, "lr": 8.271100097046585e-06, "epoch": 1.04, "percentage": 34.67, "elapsed_time": "5:40:23", "remaining_time": "10:41:30"}
+{"current_steps": 131, "total_steps": 375, "loss": 0.3729, "lr": 8.235706247625098e-06, "epoch": 1.048, "percentage": 34.93, "elapsed_time": "5:42:53", "remaining_time": "10:38:39"}
+{"current_steps": 132, "total_steps": 375, "loss": 0.4627, "lr": 8.200031204309604e-06, "epoch": 1.056, "percentage": 35.2, "elapsed_time": "5:45:21", "remaining_time": "10:35:46"}
+{"current_steps": 133, "total_steps": 375, "loss": 0.4347, "lr": 8.16407806738288e-06, "epoch": 1.064, "percentage": 35.47, "elapsed_time": "5:47:50", "remaining_time": "10:32:54"}
+{"current_steps": 134, "total_steps": 375, "loss": 0.402, "lr": 8.127849961294984e-06, "epoch": 1.072, "percentage": 35.73, "elapsed_time": "5:50:18", "remaining_time": "10:30:02"}
+{"current_steps": 135, "total_steps": 375, "loss": 0.4203, "lr": 8.091350034391732e-06, "epoch": 1.08, "percentage": 36.0, "elapsed_time": "5:52:50", "remaining_time": "10:27:16"}
+{"current_steps": 136, "total_steps": 375, "loss": 0.4521, "lr": 8.05458145864109e-06, "epoch": 1.088, "percentage": 36.27, "elapsed_time": "5:55:17", "remaining_time": "10:24:22"}
+{"current_steps": 137, "total_steps": 375, "loss": 0.4321, "lr": 8.017547429357532e-06, "epoch": 1.096, "percentage": 36.53, "elapsed_time": "5:57:47", "remaining_time": "10:21:34"}
+{"current_steps": 138, "total_steps": 375, "loss": 0.4591, "lr": 7.980251164924342e-06, "epoch": 1.104, "percentage": 36.8, "elapsed_time": "6:00:16", "remaining_time": "10:18:44"}
+{"current_steps": 139, "total_steps": 375, "loss": 0.4322, "lr": 7.94269590651393e-06, "epoch": 1.112, "percentage": 37.07, "elapsed_time": "6:02:42", "remaining_time": "10:15:50"}
+{"current_steps": 140, "total_steps": 375, "loss": 0.4612, "lr": 7.904884917806174e-06, "epoch": 1.12, "percentage": 37.33, "elapsed_time": "6:05:12", "remaining_time": "10:13:02"}
+{"current_steps": 141, "total_steps": 375, "loss": 0.4353, "lr": 7.866821484704777e-06, "epoch": 1.1280000000000001, "percentage": 37.6, "elapsed_time": "6:07:37", "remaining_time": "10:10:06"}
+{"current_steps": 142, "total_steps": 375, "loss": 0.4323, "lr": 7.828508915051724e-06, "epoch": 1.1360000000000001, "percentage": 37.87, "elapsed_time": "6:10:04", "remaining_time": "10:07:14"}
+{"current_steps": 143, "total_steps": 375, "loss": 0.4352, "lr": 7.789950538339813e-06, "epoch": 1.144, "percentage": 38.13, "elapsed_time": "6:12:31", "remaining_time": "10:04:22"}
+{"current_steps": 144, "total_steps": 375, "loss": 0.3971, "lr": 7.751149705423313e-06, "epoch": 1.152, "percentage": 38.4, "elapsed_time": "6:14:52", "remaining_time": "10:01:22"}
+{"current_steps": 145, "total_steps": 375, "loss": 0.4566, "lr": 7.712109788226763e-06, "epoch": 1.16, "percentage": 38.67, "elapsed_time": "6:17:13", "remaining_time": "9:58:21"}
+{"current_steps": 146, "total_steps": 375, "loss": 0.446, "lr": 7.672834179451943e-06, "epoch": 1.168, "percentage": 38.93, "elapsed_time": "6:19:34", "remaining_time": "9:55:21"}
+{"current_steps": 147, "total_steps": 375, "loss": 0.4759, "lr": 7.633326292283028e-06, "epoch": 1.176, "percentage": 39.2, "elapsed_time": "6:22:03", "remaining_time": "9:52:35"}
+{"current_steps": 148, "total_steps": 375, "loss": 0.4239, "lr": 7.593589560089984e-06, "epoch": 1.184, "percentage": 39.47, "elapsed_time": "6:24:30", "remaining_time": "9:49:44"}
+{"current_steps": 149, "total_steps": 375, "loss": 0.4053, "lr": 7.553627436130183e-06, "epoch": 1.192, "percentage": 39.73, "elapsed_time": "6:26:56", "remaining_time": "9:46:53"}
+{"current_steps": 150, "total_steps": 375, "loss": 0.4521, "lr": 7.513443393248312e-06, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "6:29:23", "remaining_time": "9:44:04"}
+{"current_steps": 151, "total_steps": 375, "loss": 0.3883, "lr": 7.473040923574567e-06, "epoch": 1.208, "percentage": 40.27, "elapsed_time": "6:38:49", "remaining_time": "9:51:37"}
+{"current_steps": 152, "total_steps": 375, "loss": 0.4322, "lr": 7.432423538221179e-06, "epoch": 1.216, "percentage": 40.53, "elapsed_time": "6:41:18", "remaining_time": "9:48:45"}
+{"current_steps": 153, "total_steps": 375, "loss": 0.4105, "lr": 7.391594766977277e-06, "epoch": 1.224, "percentage": 40.8, "elapsed_time": "6:43:46", "remaining_time": "9:45:52"}
+{"current_steps": 154, "total_steps": 375, "loss": 0.4103, "lr": 7.350558158002154e-06, "epoch": 1.232, "percentage": 41.07, "elapsed_time": "6:46:15", "remaining_time": "9:43:00"}
+{"current_steps": 155, "total_steps": 375, "loss": 0.4312, "lr": 7.3093172775169e-06, "epoch": 1.24, "percentage": 41.33, "elapsed_time": "6:48:45", "remaining_time": "9:40:10"}
+{"current_steps": 156, "total_steps": 375, "loss": 0.4325, "lr": 7.2678757094945e-06, "epoch": 1.248, "percentage": 41.6, "elapsed_time": "6:51:14", "remaining_time": "9:37:19"}
+{"current_steps": 157, "total_steps": 375, "loss": 0.4232, "lr": 7.226237055348369e-06, "epoch": 1.256, "percentage": 41.87, "elapsed_time": "6:53:44", "remaining_time": "9:34:29"}
+{"current_steps": 158, "total_steps": 375, "loss": 0.4359, "lr": 7.184404933619377e-06, "epoch": 1.264, "percentage": 42.13, "elapsed_time": "6:56:09", "remaining_time": "9:31:33"}
+{"current_steps": 159, "total_steps": 375, "loss": 0.4158, "lr": 7.142382979661386e-06, "epoch": 1.272, "percentage": 42.4, "elapsed_time": "6:58:32", "remaining_time": "9:28:35"}
+{"current_steps": 160, "total_steps": 375, "loss": 0.4035, "lr": 7.100174845325327e-06, "epoch": 1.28, "percentage": 42.67, "elapsed_time": "7:01:00", "remaining_time": "9:25:43"}
+{"current_steps": 161, "total_steps": 375, "loss": 0.3862, "lr": 7.057784198641835e-06, "epoch": 1.288, "percentage": 42.93, "elapsed_time": "7:03:30", "remaining_time": "9:22:54"}
+{"current_steps": 162, "total_steps": 375, "loss": 0.4347, "lr": 7.015214723502496e-06, "epoch": 1.296, "percentage": 43.2, "elapsed_time": "7:06:04", "remaining_time": "9:20:12"}
+{"current_steps": 163, "total_steps": 375, "loss": 0.4183, "lr": 6.972470119339692e-06, "epoch": 1.304, "percentage": 43.47, "elapsed_time": "7:08:39", "remaining_time": "9:17:30"}
+{"current_steps": 164, "total_steps": 375, "loss": 0.4459, "lr": 6.929554100805118e-06, "epoch": 1.312, "percentage": 43.73, "elapsed_time": "7:11:07", "remaining_time": "9:14:40"}
+{"current_steps": 165, "total_steps": 375, "loss": 0.4249, "lr": 6.886470397446958e-06, "epoch": 1.32, "percentage": 44.0, "elapsed_time": "7:13:34", "remaining_time": "9:11:49"}
+{"current_steps": 166, "total_steps": 375, "loss": 0.4376, "lr": 6.843222753385785e-06, "epoch": 1.328, "percentage": 44.27, "elapsed_time": "7:16:01", "remaining_time": "9:08:58"}
+{"current_steps": 167, "total_steps": 375, "loss": 0.4017, "lr": 6.799814926989171e-06, "epoch": 1.336, "percentage": 44.53, "elapsed_time": "7:18:26", "remaining_time": "9:06:04"}
+{"current_steps": 168, "total_steps": 375, "loss": 0.4145, "lr": 6.756250690545079e-06, "epoch": 1.3439999999999999, "percentage": 44.8, "elapsed_time": "7:20:52", "remaining_time": "9:03:13"}
+{"current_steps": 169, "total_steps": 375, "loss": 0.4373, "lr": 6.712533829934042e-06, "epoch": 1.3519999999999999, "percentage": 45.07, "elapsed_time": "7:23:18", "remaining_time": "9:00:21"}
+{"current_steps": 170, "total_steps": 375, "loss": 0.4272, "lr": 6.6686681443001485e-06, "epoch": 1.3599999999999999, "percentage": 45.33, "elapsed_time": "7:25:44", "remaining_time": "8:57:31"}
+{"current_steps": 171, "total_steps": 375, "loss": 0.4628, "lr": 6.62465744572089e-06, "epoch": 1.3679999999999999, "percentage": 45.6, "elapsed_time": "7:28:06", "remaining_time": "8:54:35"}
+{"current_steps": 172, "total_steps": 375, "loss": 0.481, "lr": 6.580505558875878e-06, "epoch": 1.376, "percentage": 45.87, "elapsed_time": "7:30:28", "remaining_time": "8:51:39"}
+{"current_steps": 173, "total_steps": 375, "loss": 0.4285, "lr": 6.536216320714466e-06, "epoch": 1.384, "percentage": 46.13, "elapsed_time": "7:32:50", "remaining_time": "8:48:45"}
+{"current_steps": 174, "total_steps": 375, "loss": 0.3997, "lr": 6.491793580122301e-06, "epoch": 1.392, "percentage": 46.4, "elapsed_time": "7:35:21", "remaining_time": "8:46:00"}
+{"current_steps": 175, "total_steps": 375, "loss": 0.4332, "lr": 6.447241197586847e-06, "epoch": 1.4, "percentage": 46.67, "elapsed_time": "7:37:49", "remaining_time": "8:43:13"}
+{"current_steps": 176, "total_steps": 375, "loss": 0.4236, "lr": 6.402563044861899e-06, "epoch": 1.408, "percentage": 46.93, "elapsed_time": "7:40:21", "remaining_time": "8:40:31"}
+{"current_steps": 177, "total_steps": 375, "loss": 0.4349, "lr": 6.357763004631104e-06, "epoch": 1.416, "percentage": 47.2, "elapsed_time": "7:42:51", "remaining_time": "8:37:46"}
+{"current_steps": 178, "total_steps": 375, "loss": 0.4089, "lr": 6.312844970170551e-06, "epoch": 1.424, "percentage": 47.47, "elapsed_time": "7:45:16", "remaining_time": "8:34:56"}
+{"current_steps": 179, "total_steps": 375, "loss": 0.4298, "lr": 6.267812845010431e-06, "epoch": 1.432, "percentage": 47.73, "elapsed_time": "7:47:37", "remaining_time": "8:32:02"}
+{"current_steps": 180, "total_steps": 375, "loss": 0.4517, "lr": 6.2226705425958e-06, "epoch": 1.44, "percentage": 48.0, "elapsed_time": "7:50:01", "remaining_time": "8:29:11"}
+{"current_steps": 181, "total_steps": 375, "loss": 0.4393, "lr": 6.177421985946499e-06, "epoch": 1.448, "percentage": 48.27, "elapsed_time": "7:52:26", "remaining_time": "8:26:22"}
+{"current_steps": 182, "total_steps": 375, "loss": 0.4225, "lr": 6.132071107316221e-06, "epoch": 1.456, "percentage": 48.53, "elapsed_time": "7:54:51", "remaining_time": "8:23:33"}
+{"current_steps": 183, "total_steps": 375, "loss": 0.4579, "lr": 6.0866218478507875e-06, "epoch": 1.464, "percentage": 48.8, "elapsed_time": "7:57:16", "remaining_time": "8:20:44"}
+{"current_steps": 184, "total_steps": 375, "loss": 0.4036, "lr": 6.041078157245649e-06, "epoch": 1.472, "percentage": 49.07, "elapsed_time": "7:59:39", "remaining_time": "8:17:54"}
+{"current_steps": 185, "total_steps": 375, "loss": 0.451, "lr": 5.995443993402647e-06, "epoch": 1.48, "percentage": 49.33, "elapsed_time": "8:02:01", "remaining_time": "8:15:03"}
+{"current_steps": 186, "total_steps": 375, "loss": 0.3881, "lr": 5.949723322086053e-06, "epoch": 1.488, "percentage": 49.6, "elapsed_time": "8:04:25", "remaining_time": "8:12:14"}
+{"current_steps": 187, "total_steps": 375, "loss": 0.4036, "lr": 5.9039201165779315e-06, "epoch": 1.496, "percentage": 49.87, "elapsed_time": "8:06:50", "remaining_time": "8:09:26"}
+{"current_steps": 188, "total_steps": 375, "loss": 0.4048, "lr": 5.858038357332851e-06, "epoch": 1.504, "percentage": 50.13, "elapsed_time": "8:09:16", "remaining_time": "8:06:40"}
+{"current_steps": 189, "total_steps": 375, "loss": 0.4464, "lr": 5.812082031631966e-06, "epoch": 1.512, "percentage": 50.4, "elapsed_time": "8:11:41", "remaining_time": "8:03:53"}
+{"current_steps": 190, "total_steps": 375, "loss": 0.4485, "lr": 5.766055133236513e-06, "epoch": 1.52, "percentage": 50.67, "elapsed_time": "8:14:06", "remaining_time": "8:01:05"}
+{"current_steps": 191, "total_steps": 375, "loss": 0.4522, "lr": 5.7199616620407325e-06, "epoch": 1.528, "percentage": 50.93, "elapsed_time": "8:16:30", "remaining_time": "7:58:18"}
+{"current_steps": 192, "total_steps": 375, "loss": 0.4752, "lr": 5.673805623724272e-06, "epoch": 1.536, "percentage": 51.2, "elapsed_time": "8:18:56", "remaining_time": "7:55:33"}
+{"current_steps": 193, "total_steps": 375, "loss": 0.4021, "lr": 5.627591029404072e-06, "epoch": 1.544, "percentage": 51.47, "elapsed_time": "8:21:22", "remaining_time": "7:52:48"}
+{"current_steps": 194, "total_steps": 375, "loss": 0.4396, "lr": 5.581321895285787e-06, "epoch": 1.552, "percentage": 51.73, "elapsed_time": "8:23:45", "remaining_time": "7:50:00"}
+{"current_steps": 195, "total_steps": 375, "loss": 0.4227, "lr": 5.535002242314772e-06, "epoch": 1.56, "percentage": 52.0, "elapsed_time": "8:26:12", "remaining_time": "7:47:15"}
+{"current_steps": 196, "total_steps": 375, "loss": 0.4512, "lr": 5.488636095826636e-06, "epoch": 1.568, "percentage": 52.27, "elapsed_time": "8:28:39", "remaining_time": "7:44:32"}
+{"current_steps": 197, "total_steps": 375, "loss": 0.4767, "lr": 5.4422274851974356e-06, "epoch": 1.576, "percentage": 52.53, "elapsed_time": "8:31:05", "remaining_time": "7:41:47"}
+{"current_steps": 198, "total_steps": 375, "loss": 0.4035, "lr": 5.395780443493508e-06, "epoch": 1.584, "percentage": 52.8, "elapsed_time": "8:33:31", "remaining_time": "7:39:03"}
+{"current_steps": 199, "total_steps": 375, "loss": 0.4329, "lr": 5.34929900712098e-06, "epoch": 1.592, "percentage": 53.07, "elapsed_time": "8:35:57", "remaining_time": "7:36:19"}
+{"current_steps": 200, "total_steps": 375, "loss": 0.3965, "lr": 5.302787215474992e-06, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "8:38:22", "remaining_time": "7:33:34"}
+{"current_steps": 201, "total_steps": 375, "loss": 0.4272, "lr": 5.256249110588659e-06, "epoch": 1.608, "percentage": 53.6, "elapsed_time": "8:47:44", "remaining_time": "7:36:51"}
+{"current_steps": 202, "total_steps": 375, "loss": 0.4409, "lr": 5.209688736781811e-06, "epoch": 1.616, "percentage": 53.87, "elapsed_time": "8:50:16", "remaining_time": "7:34:08"}
+{"current_steps": 203, "total_steps": 375, "loss": 0.4419, "lr": 5.163110140309518e-06, "epoch": 1.624, "percentage": 54.13, "elapsed_time": "8:52:43", "remaining_time": "7:31:22"}
+{"current_steps": 204, "total_steps": 375, "loss": 0.398, "lr": 5.116517369010467e-06, "epoch": 1.6320000000000001, "percentage": 54.4, "elapsed_time": "8:55:12", "remaining_time": "7:28:37"}
+{"current_steps": 205, "total_steps": 375, "loss": 0.4229, "lr": 5.069914471955179e-06, "epoch": 1.6400000000000001, "percentage": 54.67, "elapsed_time": "8:57:44", "remaining_time": "7:25:56"}
+{"current_steps": 206, "total_steps": 375, "loss": 0.4153, "lr": 5.023305499094145e-06, "epoch": 1.6480000000000001, "percentage": 54.93, "elapsed_time": "9:00:11", "remaining_time": "7:23:09"}
+{"current_steps": 207, "total_steps": 375, "loss": 0.443, "lr": 4.976694500905858e-06, "epoch": 1.6560000000000001, "percentage": 55.2, "elapsed_time": "9:02:33", "remaining_time": "7:20:20"}
+{"current_steps": 208, "total_steps": 375, "loss": 0.4541, "lr": 4.930085528044823e-06, "epoch": 1.6640000000000001, "percentage": 55.47, "elapsed_time": "9:04:54", "remaining_time": "7:17:29"}
+{"current_steps": 209, "total_steps": 375, "loss": 0.4069, "lr": 4.883482630989536e-06, "epoch": 1.6720000000000002, "percentage": 55.73, "elapsed_time": "9:07:16", "remaining_time": "7:14:40"}
+{"current_steps": 210, "total_steps": 375, "loss": 0.3964, "lr": 4.8368898596904834e-06, "epoch": 1.6800000000000002, "percentage": 56.0, "elapsed_time": "9:09:42", "remaining_time": "7:11:54"}
+{"current_steps": 211, "total_steps": 375, "loss": 0.4339, "lr": 4.790311263218191e-06, "epoch": 1.688, "percentage": 56.27, "elapsed_time": "9:12:07", "remaining_time": "7:09:08"}
+{"current_steps": 212, "total_steps": 375, "loss": 0.426, "lr": 4.743750889411342e-06, "epoch": 1.696, "percentage": 56.53, "elapsed_time": "9:14:36", "remaining_time": "7:06:24"}
+{"current_steps": 213, "total_steps": 375, "loss": 0.4338, "lr": 4.697212784525009e-06, "epoch": 1.704, "percentage": 56.8, "elapsed_time": "9:17:07", "remaining_time": "7:03:43"}
+{"current_steps": 214, "total_steps": 375, "loss": 0.4083, "lr": 4.65070099287902e-06, "epoch": 1.712, "percentage": 57.07, "elapsed_time": "9:19:37", "remaining_time": "7:01:01"}
+{"current_steps": 215, "total_steps": 375, "loss": 0.4658, "lr": 4.604219556506492e-06, "epoch": 1.72, "percentage": 57.33, "elapsed_time": "9:22:07", "remaining_time": "6:58:19"}
+{"current_steps": 216, "total_steps": 375, "loss": 0.4248, "lr": 4.557772514802564e-06, "epoch": 1.728, "percentage": 57.6, "elapsed_time": "9:24:39", "remaining_time": "6:55:39"}
+{"current_steps": 217, "total_steps": 375, "loss": 0.4482, "lr": 4.511363904173366e-06, "epoch": 1.736, "percentage": 57.87, "elapsed_time": "9:27:12", "remaining_time": "6:52:59"}
+{"current_steps": 218, "total_steps": 375, "loss": 0.4391, "lr": 4.46499775768523e-06, "epoch": 1.744, "percentage": 58.13, "elapsed_time": "9:29:45", "remaining_time": "6:50:20"}
+{"current_steps": 219, "total_steps": 375, "loss": 0.4087, "lr": 4.418678104714214e-06, "epoch": 1.752, "percentage": 58.4, "elapsed_time": "9:32:13", "remaining_time": "6:47:37"}
+{"current_steps": 220, "total_steps": 375, "loss": 0.418, "lr": 4.372408970595931e-06, "epoch": 1.76, "percentage": 58.67, "elapsed_time": "9:34:42", "remaining_time": "6:44:54"}
+{"current_steps": 221, "total_steps": 375, "loss": 0.4009, "lr": 4.326194376275729e-06, "epoch": 1.768, "percentage": 58.93, "elapsed_time": "9:37:12", "remaining_time": "6:42:13"}
+{"current_steps": 222, "total_steps": 375, "loss": 0.4119, "lr": 4.280038337959268e-06, "epoch": 1.776, "percentage": 59.2, "elapsed_time": "9:39:40", "remaining_time": "6:39:30"}
+{"current_steps": 223, "total_steps": 375, "loss": 0.4364, "lr": 4.2339448667634885e-06, "epoch": 1.784, "percentage": 59.47, "elapsed_time": "9:42:13", "remaining_time": "6:36:50"}
+{"current_steps": 224, "total_steps": 375, "loss": 0.3943, "lr": 4.187917968368036e-06, "epoch": 1.792, "percentage": 59.73, "elapsed_time": "9:44:44", "remaining_time": "6:34:10"}
+{"current_steps": 225, "total_steps": 375, "loss": 0.4447, "lr": 4.141961642667152e-06, "epoch": 1.8, "percentage": 60.0, "elapsed_time": "9:47:13", "remaining_time": "6:31:29"}
+{"current_steps": 226, "total_steps": 375, "loss": 0.4397, "lr": 4.09607988342207e-06, "epoch": 1.808, "percentage": 60.27, "elapsed_time": "9:49:44", "remaining_time": "6:28:48"}
+{"current_steps": 227, "total_steps": 375, "loss": 0.3881, "lr": 4.0502766779139485e-06, "epoch": 1.8159999999999998, "percentage": 60.53, "elapsed_time": "9:52:14", "remaining_time": "6:26:07"}
+{"current_steps": 228, "total_steps": 375, "loss": 0.4673, "lr": 4.0045560065973535e-06, "epoch": 1.8239999999999998, "percentage": 60.8, "elapsed_time": "9:54:43", "remaining_time": "6:23:26"}
+{"current_steps": 229, "total_steps": 375, "loss": 0.4156, "lr": 3.958921842754351e-06, "epoch": 1.8319999999999999, "percentage": 61.07, "elapsed_time": "9:57:16", "remaining_time": "6:20:47"}
+{"current_steps": 230, "total_steps": 375, "loss": 0.4044, "lr": 3.913378152149214e-06, "epoch": 1.8399999999999999, "percentage": 61.33, "elapsed_time": "9:59:46", "remaining_time": "6:18:06"}
+{"current_steps": 231, "total_steps": 375, "loss": 0.4387, "lr": 3.86792889268378e-06, "epoch": 1.8479999999999999, "percentage": 61.6, "elapsed_time": "10:02:10", "remaining_time": "6:15:22"}
+{"current_steps": 232, "total_steps": 375, "loss": 0.3976, "lr": 3.8225780140535025e-06, "epoch": 1.8559999999999999, "percentage": 61.87, "elapsed_time": "10:04:35", "remaining_time": "6:12:39"}
+{"current_steps": 233, "total_steps": 375, "loss": 0.4062, "lr": 3.777329457404202e-06, "epoch": 1.8639999999999999, "percentage": 62.13, "elapsed_time": "10:07:05", "remaining_time": "6:09:59"}
+{"current_steps": 234, "total_steps": 375, "loss": 0.4458, "lr": 3.7321871549895715e-06, "epoch": 1.8719999999999999, "percentage": 62.4, "elapsed_time": "10:09:35", "remaining_time": "6:07:18"}
+{"current_steps": 235, "total_steps": 375, "loss": 0.3947, "lr": 3.68715502982945e-06, "epoch": 1.88, "percentage": 62.67, "elapsed_time": "10:12:05", "remaining_time": "6:04:39"}
+{"current_steps": 236, "total_steps": 375, "loss": 0.4294, "lr": 3.6422369953688973e-06, "epoch": 1.888, "percentage": 62.93, "elapsed_time": "10:14:33", "remaining_time": "6:01:57"}
+{"current_steps": 237, "total_steps": 375, "loss": 0.4498, "lr": 3.5974369551381023e-06, "epoch": 1.896, "percentage": 63.2, "elapsed_time": "10:17:01", "remaining_time": "5:59:16"}
+{"current_steps": 238, "total_steps": 375, "loss": 0.4312, "lr": 3.5527588024131542e-06, "epoch": 1.904, "percentage": 63.47, "elapsed_time": "10:19:31", "remaining_time": "5:56:36"}
+{"current_steps": 239, "total_steps": 375, "loss": 0.4772, "lr": 3.5082064198777e-06, "epoch": 1.912, "percentage": 63.73, "elapsed_time": "10:21:59", "remaining_time": "5:53:56"}
+{"current_steps": 240, "total_steps": 375, "loss": 0.4101, "lr": 3.463783679285535e-06, "epoch": 1.92, "percentage": 64.0, "elapsed_time": "10:24:30", "remaining_time": "5:51:16"}
+{"current_steps": 241, "total_steps": 375, "loss": 0.4222, "lr": 3.4194944411241213e-06, "epoch": 1.928, "percentage": 64.27, "elapsed_time": "10:27:00", "remaining_time": "5:48:37"}
+{"current_steps": 242, "total_steps": 375, "loss": 0.4322, "lr": 3.3753425542791106e-06, "epoch": 1.936, "percentage": 64.53, "elapsed_time": "10:29:29", "remaining_time": "5:45:57"}
+{"current_steps": 243, "total_steps": 375, "loss": 0.4553, "lr": 3.3313318556998523e-06, "epoch": 1.944, "percentage": 64.8, "elapsed_time": "10:31:57", "remaining_time": "5:43:17"}
+{"current_steps": 244, "total_steps": 375, "loss": 0.4541, "lr": 3.2874661700659586e-06, "epoch": 1.952, "percentage": 65.07, "elapsed_time": "10:34:30", "remaining_time": "5:40:39"}
+{"current_steps": 245, "total_steps": 375, "loss": 0.4164, "lr": 3.2437493094549223e-06, "epoch": 1.96, "percentage": 65.33, "elapsed_time": "10:37:02", "remaining_time": "5:38:01"}
+{"current_steps": 246, "total_steps": 375, "loss": 0.4151, "lr": 3.200185073010831e-06, "epoch": 1.968, "percentage": 65.6, "elapsed_time": "10:39:34", "remaining_time": "5:35:22"}
+{"current_steps": 247, "total_steps": 375, "loss": 0.3739, "lr": 3.1567772466142156e-06, "epoch": 1.976, "percentage": 65.87, "elapsed_time": "10:41:59", "remaining_time": "5:32:41"}
+{"current_steps": 248, "total_steps": 375, "loss": 0.4892, "lr": 3.1135296025530426e-06, "epoch": 1.984, "percentage": 66.13, "elapsed_time": "10:44:28", "remaining_time": "5:30:02"}
+{"current_steps": 249, "total_steps": 375, "loss": 0.4132, "lr": 3.070445899194885e-06, "epoch": 1.992, "percentage": 66.4, "elapsed_time": "10:46:57", "remaining_time": "5:27:22"}
+{"current_steps": 250, "total_steps": 375, "loss": 0.4463, "lr": 3.0275298806603102e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "10:49:28", "remaining_time": "5:24:44"}
+{"current_steps": 251, "total_steps": 375, "loss": 0.3639, "lr": 2.984785276497507e-06, "epoch": 2.008, "percentage": 66.93, "elapsed_time": "10:59:05", "remaining_time": "5:25:36"}
+{"current_steps": 252, "total_steps": 375, "loss": 0.3535, "lr": 2.9422158013581658e-06, "epoch": 2.016, "percentage": 67.2, "elapsed_time": "11:01:31", "remaining_time": "5:22:53"}
+{"current_steps": 253, "total_steps": 375, "loss": 0.3835, "lr": 2.899825154674674e-06, "epoch": 2.024, "percentage": 67.47, "elapsed_time": "11:03:56", "remaining_time": "5:20:09"}
+{"current_steps": 254, "total_steps": 375, "loss": 0.3412, "lr": 2.8576170203386144e-06, "epoch": 2.032, "percentage": 67.73, "elapsed_time": "11:06:21", "remaining_time": "5:17:26"}
+{"current_steps": 255, "total_steps": 375, "loss": 0.3863, "lr": 2.8155950663806234e-06, "epoch": 2.04, "percentage": 68.0, "elapsed_time": "11:08:47", "remaining_time": "5:14:43"}
+{"current_steps": 256, "total_steps": 375, "loss": 0.3514, "lr": 2.7737629446516325e-06, "epoch": 2.048, "percentage": 68.27, "elapsed_time": "11:11:13", "remaining_time": "5:12:00"}
+{"current_steps": 257, "total_steps": 375, "loss": 0.3528, "lr": 2.732124290505501e-06, "epoch": 2.056, "percentage": 68.53, "elapsed_time": "11:13:42", "remaining_time": "5:09:19"}
+{"current_steps": 258, "total_steps": 375, "loss": 0.3296, "lr": 2.6906827224831024e-06, "epoch": 2.064, "percentage": 68.8, "elapsed_time": "11:16:10", "remaining_time": "5:06:38"}
+{"current_steps": 259, "total_steps": 375, "loss": 0.3416, "lr": 2.6494418419978485e-06, "epoch": 2.072, "percentage": 69.07, "elapsed_time": "11:18:40", "remaining_time": "5:03:57"}
+{"current_steps": 260, "total_steps": 375, "loss": 0.3793, "lr": 2.608405233022724e-06, "epoch": 2.08, "percentage": 69.33, "elapsed_time": "11:21:11", "remaining_time": "5:01:17"}
+{"current_steps": 261, "total_steps": 375, "loss": 0.3298, "lr": 2.5675764617788233e-06, "epoch": 2.088, "percentage": 69.6, "elapsed_time": "11:23:40", "remaining_time": "4:58:37"}
+{"current_steps": 262, "total_steps": 375, "loss": 0.3427, "lr": 2.526959076425434e-06, "epoch": 2.096, "percentage": 69.87, "elapsed_time": "11:26:10", "remaining_time": "4:55:56"}
+{"current_steps": 263, "total_steps": 375, "loss": 0.3709, "lr": 2.4865566067516896e-06, "epoch": 2.104, "percentage": 70.13, "elapsed_time": "11:28:39", "remaining_time": "4:53:16"}
+{"current_steps": 264, "total_steps": 375, "loss": 0.3255, "lr": 2.4463725638698182e-06, "epoch": 2.112, "percentage": 70.4, "elapsed_time": "11:31:02", "remaining_time": "4:50:33"}
+{"current_steps": 265, "total_steps": 375, "loss": 0.3928, "lr": 2.406410439910017e-06, "epoch": 2.12, "percentage": 70.67, "elapsed_time": "11:33:29", "remaining_time": "4:47:52"}
+{"current_steps": 266, "total_steps": 375, "loss": 0.3497, "lr": 2.366673707716973e-06, "epoch": 2.128, "percentage": 70.93, "elapsed_time": "11:35:56", "remaining_time": "4:45:10"}
+{"current_steps": 267, "total_steps": 375, "loss": 0.3653, "lr": 2.327165820548059e-06, "epoch": 2.136, "percentage": 71.2, "elapsed_time": "11:38:27", "remaining_time": "4:42:31"}
+{"current_steps": 268, "total_steps": 375, "loss": 0.3628, "lr": 2.287890211773238e-06, "epoch": 2.144, "percentage": 71.47, "elapsed_time": "11:40:59", "remaining_time": "4:39:52"}
+{"current_steps": 269, "total_steps": 375, "loss": 0.3681, "lr": 2.2488502945766893e-06, "epoch": 2.152, "percentage": 71.73, "elapsed_time": "11:43:29", "remaining_time": "4:37:12"}
+{"current_steps": 270, "total_steps": 375, "loss": 0.3542, "lr": 2.210049461660189e-06, "epoch": 2.16, "percentage": 72.0, "elapsed_time": "11:45:57", "remaining_time": "4:34:32"}
+{"current_steps": 271, "total_steps": 375, "loss": 0.3618, "lr": 2.1714910849482777e-06, "epoch": 2.168, "percentage": 72.27, "elapsed_time": "11:48:30", "remaining_time": "4:31:53"}
+{"current_steps": 272, "total_steps": 375, "loss": 0.3533, "lr": 2.1331785152952243e-06, "epoch": 2.176, "percentage": 72.53, "elapsed_time": "11:50:59", "remaining_time": "4:29:14"}
+{"current_steps": 273, "total_steps": 375, "loss": 0.3761, "lr": 2.0951150821938278e-06, "epoch": 2.184, "percentage": 72.8, "elapsed_time": "11:53:21", "remaining_time": "4:26:31"}
+{"current_steps": 274, "total_steps": 375, "loss": 0.3776, "lr": 2.0573040934860717e-06, "epoch": 2.192, "percentage": 73.07, "elapsed_time": "11:55:46", "remaining_time": "4:23:50"}
+{"current_steps": 275, "total_steps": 375, "loss": 0.326, "lr": 2.0197488350756618e-06, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "11:58:15", "remaining_time": "4:21:11"}
+{"current_steps": 276, "total_steps": 375, "loss": 0.3596, "lr": 1.98245257064247e-06, "epoch": 2.208, "percentage": 73.6, "elapsed_time": "12:00:42", "remaining_time": "4:18:31"}
+{"current_steps": 277, "total_steps": 375, "loss": 0.3443, "lr": 1.945418541358911e-06, "epoch": 2.216, "percentage": 73.87, "elapsed_time": "12:03:12", "remaining_time": "4:15:51"}
+{"current_steps": 278, "total_steps": 375, "loss": 0.3469, "lr": 1.9086499656082685e-06, "epoch": 2.224, "percentage": 74.13, "elapsed_time": "12:05:41", "remaining_time": "4:13:12"}
+{"current_steps": 279, "total_steps": 375, "loss": 0.3494, "lr": 1.872150038705015e-06, "epoch": 2.232, "percentage": 74.4, "elapsed_time": "12:08:09", "remaining_time": "4:10:33"}
+{"current_steps": 280, "total_steps": 375, "loss": 0.3614, "lr": 1.835921932617119e-06, "epoch": 2.24, "percentage": 74.67, "elapsed_time": "12:10:38", "remaining_time": "4:07:53"}
+{"current_steps": 281, "total_steps": 375, "loss": 0.3678, "lr": 1.7999687956903955e-06, "epoch": 2.248, "percentage": 74.93, "elapsed_time": "12:13:03", "remaining_time": "4:05:13"}
+{"current_steps": 282, "total_steps": 375, "loss": 0.3514, "lr": 1.7642937523749038e-06, "epoch": 2.2560000000000002, "percentage": 75.2, "elapsed_time": "12:15:27", "remaining_time": "4:02:32"}
+{"current_steps": 283, "total_steps": 375, "loss": 0.3349, "lr": 1.7288999029534177e-06, "epoch": 2.2640000000000002, "percentage": 75.47, "elapsed_time": "12:17:54", "remaining_time": "3:59:53"}
+{"current_steps": 284, "total_steps": 375, "loss": 0.3655, "lr": 1.6937903232720076e-06, "epoch": 2.2720000000000002, "percentage": 75.73, "elapsed_time": "12:20:21", "remaining_time": "3:57:13"}
+{"current_steps": 285, "total_steps": 375, "loss": 0.3446, "lr": 1.6589680644727347e-06, "epoch": 2.2800000000000002, "percentage": 76.0, "elapsed_time": "12:22:47", "remaining_time": "3:54:34"}
+{"current_steps": 286, "total_steps": 375, "loss": 0.3473, "lr": 1.6244361527284953e-06, "epoch": 2.288, "percentage": 76.27, "elapsed_time": "12:25:12", "remaining_time": "3:51:53"}
+{"current_steps": 287, "total_steps": 375, "loss": 0.3614, "lr": 1.5901975889800387e-06, "epoch": 2.296, "percentage": 76.53, "elapsed_time": "12:27:36", "remaining_time": "3:49:14"}
+{"current_steps": 288, "total_steps": 375, "loss": 0.3417, "lr": 1.556255348675174e-06, "epoch": 2.304, "percentage": 76.8, "elapsed_time": "12:30:03", "remaining_time": "3:46:34"}
+{"current_steps": 289, "total_steps": 375, "loss": 0.348, "lr": 1.522612381510195e-06, "epoch": 2.312, "percentage": 77.07, "elapsed_time": "12:32:36", "remaining_time": "3:43:57"}
+{"current_steps": 290, "total_steps": 375, "loss": 0.3587, "lr": 1.489271611173538e-06, "epoch": 2.32, "percentage": 77.33, "elapsed_time": "12:35:02", "remaining_time": "3:41:18"}
+{"current_steps": 291, "total_steps": 375, "loss": 0.3479, "lr": 1.4562359350917054e-06, "epoch": 2.328, "percentage": 77.6, "elapsed_time": "12:37:29", "remaining_time": "3:38:39"}
+{"current_steps": 292, "total_steps": 375, "loss": 0.3678, "lr": 1.423508224177474e-06, "epoch": 2.336, "percentage": 77.87, "elapsed_time": "12:39:55", "remaining_time": "3:36:00"}
+{"current_steps": 293, "total_steps": 375, "loss": 0.3321, "lr": 1.3910913225803946e-06, "epoch": 2.344, "percentage": 78.13, "elapsed_time": "12:42:22", "remaining_time": "3:33:21"}
+{"current_steps": 294, "total_steps": 375, "loss": 0.3748, "lr": 1.35898804743963e-06, "epoch": 2.352, "percentage": 78.4, "elapsed_time": "12:44:48", "remaining_time": "3:30:42"}
+{"current_steps": 295, "total_steps": 375, "loss": 0.3489, "lr": 1.3272011886391368e-06, "epoch": 2.36, "percentage": 78.67, "elapsed_time": "12:47:14", "remaining_time": "3:28:03"}
+{"current_steps": 296, "total_steps": 375, "loss": 0.3427, "lr": 1.295733508565213e-06, "epoch": 2.368, "percentage": 78.93, "elapsed_time": "12:49:42", "remaining_time": "3:25:25"}
+{"current_steps": 297, "total_steps": 375, "loss": 0.3484, "lr": 1.2645877418664394e-06, "epoch": 2.376, "percentage": 79.2, "elapsed_time": "12:52:10", "remaining_time": "3:22:47"}
+{"current_steps": 298, "total_steps": 375, "loss": 0.3486, "lr": 1.2337665952160266e-06, "epoch": 2.384, "percentage": 79.47, "elapsed_time": "12:54:35", "remaining_time": "3:20:08"}
+{"current_steps": 299, "total_steps": 375, "loss": 0.3345, "lr": 1.2032727470765982e-06, "epoch": 2.392, "percentage": 79.73, "elapsed_time": "12:56:58", "remaining_time": "3:17:29"}
+{"current_steps": 300, "total_steps": 375, "loss": 0.3695, "lr": 1.1731088474674235e-06, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "12:59:24", "remaining_time": "3:14:51"}
+{"current_steps": 301, "total_steps": 375, "loss": 0.3605, "lr": 1.1432775177341165e-06, "epoch": 2.408, "percentage": 80.27, "elapsed_time": "13:08:46", "remaining_time": "3:13:55"}
+{"current_steps": 302, "total_steps": 375, "loss": 0.3328, "lr": 1.11378135032084e-06, "epoch": 2.416, "percentage": 80.53, "elapsed_time": "13:11:14", "remaining_time": "3:11:15"}
+{"current_steps": 303, "total_steps": 375, "loss": 0.3592, "lr": 1.08462290854501e-06, "epoch": 2.424, "percentage": 80.8, "elapsed_time": "13:13:46", "remaining_time": "3:08:37"}
+{"current_steps": 304, "total_steps": 375, "loss": 0.3653, "lr": 1.0558047263745297e-06, "epoch": 2.432, "percentage": 81.07, "elapsed_time": "13:16:17", "remaining_time": "3:05:58"}
+{"current_steps": 305, "total_steps": 375, "loss": 0.3317, "lr": 1.0273293082075914e-06, "epoch": 2.44, "percentage": 81.33, "elapsed_time": "13:18:48", "remaining_time": "3:03:19"}
+{"current_steps": 306, "total_steps": 375, "loss": 0.3417, "lr": 9.991991286550207e-07, "epoch": 2.448, "percentage": 81.6, "elapsed_time": "13:21:19", "remaining_time": "3:00:41"}
+{"current_steps": 307, "total_steps": 375, "loss": 0.3634, "lr": 9.71416632325235e-07, "epoch": 2.456, "percentage": 81.87, "elapsed_time": "13:23:51", "remaining_time": "2:58:03"}
+{"current_steps": 308, "total_steps": 375, "loss": 0.3428, "lr": 9.439842336117954e-07, "epoch": 2.464, "percentage": 82.13, "elapsed_time": "13:26:21", "remaining_time": "2:55:24"}
+{"current_steps": 309, "total_steps": 375, "loss": 0.3336, "lr": 9.169043164835867e-07, "epoch": 2.472, "percentage": 82.4, "elapsed_time": "13:28:50", "remaining_time": "2:52:45"}
+{"current_steps": 310, "total_steps": 375, "loss": 0.4171, "lr": 8.901792342776439e-07, "epoch": 2.48, "percentage": 82.67, "elapsed_time": "13:31:21", "remaining_time": "2:50:07"}
+{"current_steps": 311, "total_steps": 375, "loss": 0.3123, "lr": 8.638113094946382e-07, "epoch": 2.488, "percentage": 82.93, "elapsed_time": "13:33:51", "remaining_time": "2:47:28"}
+{"current_steps": 312, "total_steps": 375, "loss": 0.3784, "lr": 8.378028335970451e-07, "epoch": 2.496, "percentage": 83.2, "elapsed_time": "13:36:18", "remaining_time": "2:44:49"}
+{"current_steps": 313, "total_steps": 375, "loss": 0.3631, "lr": 8.121560668100065e-07, "epoch": 2.504, "percentage": 83.47, "elapsed_time": "13:38:44", "remaining_time": "2:42:10"}
+{"current_steps": 314, "total_steps": 375, "loss": 0.3319, "lr": 7.868732379249122e-07, "epoch": 2.512, "percentage": 83.73, "elapsed_time": "13:41:11", "remaining_time": "2:39:31"}
+{"current_steps": 315, "total_steps": 375, "loss": 0.3517, "lr": 7.619565441057075e-07, "epoch": 2.52, "percentage": 84.0, "elapsed_time": "13:43:41", "remaining_time": "2:36:53"}
+{"current_steps": 316, "total_steps": 375, "loss": 0.3702, "lr": 7.37408150697953e-07, "epoch": 2.528, "percentage": 84.27, "elapsed_time": "13:46:09", "remaining_time": "2:34:15"}
+{"current_steps": 317, "total_steps": 375, "loss": 0.3759, "lr": 7.132301910406503e-07, "epoch": 2.536, "percentage": 84.53, "elapsed_time": "13:48:40", "remaining_time": "2:31:37"}
+{"current_steps": 318, "total_steps": 375, "loss": 0.322, "lr": 6.894247662808456e-07, "epoch": 2.544, "percentage": 84.8, "elapsed_time": "13:51:10", "remaining_time": "2:28:59"}
+{"current_steps": 319, "total_steps": 375, "loss": 0.3343, "lr": 6.659939451910341e-07, "epoch": 2.552, "percentage": 85.07, "elapsed_time": "13:53:42", "remaining_time": "2:26:21"}
+{"current_steps": 320, "total_steps": 375, "loss": 0.3813, "lr": 6.429397639893758e-07, "epoch": 2.56, "percentage": 85.33, "elapsed_time": "13:56:14", "remaining_time": "2:23:43"}
+{"current_steps": 321, "total_steps": 375, "loss": 0.368, "lr": 6.202642261627411e-07, "epoch": 2.568, "percentage": 85.6, "elapsed_time": "13:58:44", "remaining_time": "2:21:05"}
+{"current_steps": 322, "total_steps": 375, "loss": 0.4142, "lr": 5.979693022926025e-07, "epoch": 2.576, "percentage": 85.87, "elapsed_time": "14:01:13", "remaining_time": "2:18:27"}
+{"current_steps": 323, "total_steps": 375, "loss": 0.3717, "lr": 5.760569298837825e-07, "epoch": 2.584, "percentage": 86.13, "elapsed_time": "14:03:42", "remaining_time": "2:15:49"}
+{"current_steps": 324, "total_steps": 375, "loss": 0.352, "lr": 5.54529013196079e-07, "epoch": 2.592, "percentage": 86.4, "elapsed_time": "14:06:13", "remaining_time": "2:13:12"}
+{"current_steps": 325, "total_steps": 375, "loss": 0.3661, "lr": 5.333874230787772e-07, "epoch": 2.6, "percentage": 86.67, "elapsed_time": "14:08:43", "remaining_time": "2:10:34"}
+{"current_steps": 326, "total_steps": 375, "loss": 0.3616, "lr": 5.126339968080696e-07, "epoch": 2.608, "percentage": 86.93, "elapsed_time": "14:11:16", "remaining_time": "2:07:57"}
+{"current_steps": 327, "total_steps": 375, "loss": 0.3645, "lr": 4.922705379273862e-07, "epoch": 2.616, "percentage": 87.2, "elapsed_time": "14:13:46", "remaining_time": "2:05:19"}
+{"current_steps": 328, "total_steps": 375, "loss": 0.3307, "lr": 4.7229881609066387e-07, "epoch": 2.624, "percentage": 87.47, "elapsed_time": "14:16:15", "remaining_time": "2:02:41"}
+{"current_steps": 329, "total_steps": 375, "loss": 0.3624, "lr": 4.5272056690855494e-07, "epoch": 2.632, "percentage": 87.73, "elapsed_time": "14:18:43", "remaining_time": "2:00:03"}
+{"current_steps": 330, "total_steps": 375, "loss": 0.3242, "lr": 4.335374917975982e-07, "epoch": 2.64, "percentage": 88.0, "elapsed_time": "14:21:11", "remaining_time": "1:57:26"}
+{"current_steps": 331, "total_steps": 375, "loss": 0.3808, "lr": 4.147512578323615e-07, "epoch": 2.648, "percentage": 88.27, "elapsed_time": "14:23:38", "remaining_time": "1:54:48"}
+{"current_steps": 332, "total_steps": 375, "loss": 0.3389, "lr": 3.9636349760056427e-07, "epoch": 2.656, "percentage": 88.53, "elapsed_time": "14:26:07", "remaining_time": "1:52:10"}
+{"current_steps": 333, "total_steps": 375, "loss": 0.3336, "lr": 3.783758090611983e-07, "epoch": 2.664, "percentage": 88.8, "elapsed_time": "14:28:34", "remaining_time": "1:49:32"}
+{"current_steps": 334, "total_steps": 375, "loss": 0.3482, "lr": 3.6078975540566716e-07, "epoch": 2.672, "percentage": 89.07, "elapsed_time": "14:31:01", "remaining_time": "1:46:55"}
+{"current_steps": 335, "total_steps": 375, "loss": 0.3077, "lr": 3.4360686492193263e-07, "epoch": 2.68, "percentage": 89.33, "elapsed_time": "14:33:27", "remaining_time": "1:44:17"}
+{"current_steps": 336, "total_steps": 375, "loss": 0.3906, "lr": 3.268286308617041e-07, "epoch": 2.6879999999999997, "percentage": 89.6, "elapsed_time": "14:35:54", "remaining_time": "1:41:40"}
+{"current_steps": 337, "total_steps": 375, "loss": 0.342, "lr": 3.104565113106689e-07, "epoch": 2.6959999999999997, "percentage": 89.87, "elapsed_time": "14:38:20", "remaining_time": "1:39:02"}
+{"current_steps": 338, "total_steps": 375, "loss": 0.3491, "lr": 2.9449192906178205e-07, "epoch": 2.7039999999999997, "percentage": 90.13, "elapsed_time": "14:40:48", "remaining_time": "1:36:25"}
+{"current_steps": 339, "total_steps": 375, "loss": 0.3875, "lr": 2.789362714916172e-07, "epoch": 2.7119999999999997, "percentage": 90.4, "elapsed_time": "14:43:19", "remaining_time": "1:33:48"}
+{"current_steps": 340, "total_steps": 375, "loss": 0.32, "lr": 2.6379089043980064e-07, "epoch": 2.7199999999999998, "percentage": 90.67, "elapsed_time": "14:45:46", "remaining_time": "1:31:10"}
+{"current_steps": 341, "total_steps": 375, "loss": 0.3451, "lr": 2.4905710209153224e-07, "epoch": 2.7279999999999998, "percentage": 90.93, "elapsed_time": "14:48:14", "remaining_time": "1:28:33"}
+{"current_steps": 342, "total_steps": 375, "loss": 0.3861, "lr": 2.3473618686320477e-07, "epoch": 2.7359999999999998, "percentage": 91.2, "elapsed_time": "14:50:44", "remaining_time": "1:25:56"}
+{"current_steps": 343, "total_steps": 375, "loss": 0.3469, "lr": 2.208293892911284e-07, "epoch": 2.7439999999999998, "percentage": 91.47, "elapsed_time": "14:53:13", "remaining_time": "1:23:20"}
+{"current_steps": 344, "total_steps": 375, "loss": 0.3761, "lr": 2.0733791792338197e-07, "epoch": 2.752, "percentage": 91.73, "elapsed_time": "14:55:44", "remaining_time": "1:20:43"}
+{"current_steps": 345, "total_steps": 375, "loss": 0.3504, "lr": 1.9426294521477874e-07, "epoch": 2.76, "percentage": 92.0, "elapsed_time": "14:58:11", "remaining_time": "1:18:06"}
+{"current_steps": 346, "total_steps": 375, "loss": 0.3652, "lr": 1.8160560742498223e-07, "epoch": 2.768, "percentage": 92.27, "elapsed_time": "15:00:40", "remaining_time": "1:15:29"}
+{"current_steps": 347, "total_steps": 375, "loss": 0.3259, "lr": 1.6936700451975818e-07, "epoch": 2.776, "percentage": 92.53, "elapsed_time": "15:03:08", "remaining_time": "1:12:52"}
+{"current_steps": 348, "total_steps": 375, "loss": 0.3555, "lr": 1.5754820007538473e-07, "epoch": 2.784, "percentage": 92.8, "elapsed_time": "15:05:36", "remaining_time": "1:10:15"}
+{"current_steps": 349, "total_steps": 375, "loss": 0.3451, "lr": 1.461502211862237e-07, "epoch": 2.792, "percentage": 93.07, "elapsed_time": "15:08:05", "remaining_time": "1:07:39"}
+{"current_steps": 350, "total_steps": 375, "loss": 0.3481, "lr": 1.3517405837546404e-07, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "15:10:34", "remaining_time": "1:05:02"}
+{"current_steps": 351, "total_steps": 375, "loss": 0.3324, "lr": 1.2462066550903818e-07, "epoch": 2.808, "percentage": 93.6, "elapsed_time": "15:19:52", "remaining_time": "1:02:53"}
+{"current_steps": 352, "total_steps": 375, "loss": 0.3304, "lr": 1.1449095971273305e-07, "epoch": 2.816, "percentage": 93.87, "elapsed_time": "15:22:23", "remaining_time": "1:00:16"}
+{"current_steps": 353, "total_steps": 375, "loss": 0.3655, "lr": 1.0478582129248516e-07, "epoch": 2.824, "percentage": 94.13, "elapsed_time": "15:24:56", "remaining_time": "0:57:38"}
+{"current_steps": 354, "total_steps": 375, "loss": 0.3815, "lr": 9.550609365787888e-08, "epoch": 2.832, "percentage": 94.4, "elapsed_time": "15:27:29", "remaining_time": "0:55:01"}
+{"current_steps": 355, "total_steps": 375, "loss": 0.3656, "lr": 8.66525832488535e-08, "epoch": 2.84, "percentage": 94.67, "elapsed_time": "15:30:00", "remaining_time": "0:52:23"}
+{"current_steps": 356, "total_steps": 375, "loss": 0.3437, "lr": 7.822605946561923e-08, "epoch": 2.848, "percentage": 94.93, "elapsed_time": "15:32:34", "remaining_time": "0:49:46"}
+{"current_steps": 357, "total_steps": 375, "loss": 0.3697, "lr": 7.022725460179459e-08, "epoch": 2.856, "percentage": 95.2, "elapsed_time": "15:35:07", "remaining_time": "0:47:08"}
+{"current_steps": 358, "total_steps": 375, "loss": 0.3595, "lr": 6.265686378076729e-08, "epoch": 2.864, "percentage": 95.47, "elapsed_time": "15:37:40", "remaining_time": "0:44:31"}
+{"current_steps": 359, "total_steps": 375, "loss": 0.3706, "lr": 5.5515544895284324e-08, "epoch": 2.872, "percentage": 95.73, "elapsed_time": "15:40:12", "remaining_time": "0:41:54"}
+{"current_steps": 360, "total_steps": 375, "loss": 0.3524, "lr": 4.880391855028088e-08, "epoch": 2.88, "percentage": 96.0, "elapsed_time": "15:42:43", "remaining_time": "0:39:16"}
+{"current_steps": 361, "total_steps": 375, "loss": 0.3407, "lr": 4.252256800894694e-08, "epoch": 2.888, "percentage": 96.27, "elapsed_time": "15:45:13", "remaining_time": "0:36:39"}
+{"current_steps": 362, "total_steps": 375, "loss": 0.3292, "lr": 3.6672039142039426e-08, "epoch": 2.896, "percentage": 96.53, "elapsed_time": "15:47:45", "remaining_time": "0:34:02"}
+{"current_steps": 363, "total_steps": 375, "loss": 0.3429, "lr": 3.125284038044407e-08, "epoch": 2.904, "percentage": 96.8, "elapsed_time": "15:50:15", "remaining_time": "0:31:24"}
+{"current_steps": 364, "total_steps": 375, "loss": 0.3428, "lr": 2.6265442670991293e-08, "epoch": 2.912, "percentage": 97.07, "elapsed_time": "15:52:48", "remaining_time": "0:28:47"}
+{"current_steps": 365, "total_steps": 375, "loss": 0.3448, "lr": 2.1710279435530058e-08, "epoch": 2.92, "percentage": 97.33, "elapsed_time": "15:55:13", "remaining_time": "0:26:10"}
+{"current_steps": 366, "total_steps": 375, "loss": 0.3519, "lr": 1.7587746533260786e-08, "epoch": 2.928, "percentage": 97.6, "elapsed_time": "15:57:40", "remaining_time": "0:23:32"}
+{"current_steps": 367, "total_steps": 375, "loss": 0.3739, "lr": 1.3898202226333424e-08, "epoch": 2.936, "percentage": 97.87, "elapsed_time": "16:00:09", "remaining_time": "0:20:55"}
+{"current_steps": 368, "total_steps": 375, "loss": 0.3628, "lr": 1.0641967148716236e-08, "epoch": 2.944, "percentage": 98.13, "elapsed_time": "16:02:41", "remaining_time": "0:18:18"}
+{"current_steps": 369, "total_steps": 375, "loss": 0.3411, "lr": 7.819324278328099e-09, "epoch": 2.952, "percentage": 98.4, "elapsed_time": "16:05:14", "remaining_time": "0:15:41"}
+{"current_steps": 370, "total_steps": 375, "loss": 0.3326, "lr": 5.430518912448169e-09, "epoch": 2.96, "percentage": 98.67, "elapsed_time": "16:07:46", "remaining_time": "0:13:04"}
+{"current_steps": 371, "total_steps": 375, "loss": 0.3696, "lr": 3.4757586464001513e-09, "epoch": 2.968, "percentage": 98.93, "elapsed_time": "16:10:17", "remaining_time": "0:10:27"}
+{"current_steps": 372, "total_steps": 375, "loss": 0.3661, "lr": 1.9552133555084117e-09, "epoch": 2.976, "percentage": 99.2, "elapsed_time": "16:12:46", "remaining_time": "0:07:50"}
+{"current_steps": 373, "total_steps": 375, "loss": 0.3421, "lr": 8.690151803386615e-10, "epoch": 2.984, "percentage": 99.47, "elapsed_time": "16:15:18", "remaining_time": "0:05:13"}
+{"current_steps": 374, "total_steps": 375, "loss": 0.3395, "lr": 2.1725851521103847e-10, "epoch": 2.992, "percentage": 99.73, "elapsed_time": "16:17:53", "remaining_time": "0:02:36"}
+{"current_steps": 375, "total_steps": 375, "loss": 0.3399, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "16:20:24", "remaining_time": "0:00:00"}
+{"current_steps": 375, "total_steps": 375, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "16:27:44", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2667 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008,
+      "grad_norm": 14.56950855255127,
+      "learning_rate": 2.6315789473684213e-07,
+      "loss": 0.8339,
+      "step": 1
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 13.73933219909668,
+      "learning_rate": 5.263157894736843e-07,
+      "loss": 0.8732,
+      "step": 2
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 14.081198692321777,
+      "learning_rate": 7.894736842105263e-07,
+      "loss": 0.894,
+      "step": 3
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 14.026392936706543,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 0.8509,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 14.380779266357422,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 0.8362,
+      "step": 5
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 12.984580993652344,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.8653,
+      "step": 6
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 10.433991432189941,
+      "learning_rate": 1.8421052631578948e-06,
+      "loss": 0.8321,
+      "step": 7
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 9.493083000183105,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 0.8143,
+      "step": 8
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 7.640753746032715,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.7905,
+      "step": 9
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.019260883331299,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.7129,
+      "step": 10
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 3.2670819759368896,
+      "learning_rate": 2.8947368421052634e-06,
+      "loss": 0.7227,
+      "step": 11
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 2.992112398147583,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 0.6972,
+      "step": 12
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 2.052677869796753,
+      "learning_rate": 3.421052631578948e-06,
+      "loss": 0.678,
+      "step": 13
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 1.920199990272522,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 0.667,
+      "step": 14
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.706879734992981,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 0.6192,
+      "step": 15
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 1.6659389734268188,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 0.6118,
+      "step": 16
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 1.3653850555419922,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 0.5681,
+      "step": 17
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 1.4679189920425415,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 0.607,
+      "step": 18
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 1.2237054109573364,
+      "learning_rate": 5e-06,
+      "loss": 0.5273,
+      "step": 19
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.9686553478240967,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 0.5578,
+      "step": 20
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.7895737290382385,
+      "learning_rate": 5.526315789473685e-06,
+      "loss": 0.5794,
+      "step": 21
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 0.8087520599365234,
+      "learning_rate": 5.789473684210527e-06,
+      "loss": 0.5229,
+      "step": 22
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 0.7652890086174011,
+      "learning_rate": 6.0526315789473685e-06,
+      "loss": 0.5292,
+      "step": 23
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.9132710695266724,
+      "learning_rate": 6.31578947368421e-06,
+      "loss": 0.5271,
+      "step": 24
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.8860102295875549,
+      "learning_rate": 6.578947368421054e-06,
+      "loss": 0.5155,
+      "step": 25
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.8902170062065125,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.5287,
+      "step": 26
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.8824247121810913,
+      "learning_rate": 7.1052631578947375e-06,
+      "loss": 0.4791,
+      "step": 27
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 1.2683454751968384,
+      "learning_rate": 7.368421052631579e-06,
+      "loss": 0.5329,
+      "step": 28
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.7248997092247009,
+      "learning_rate": 7.631578947368423e-06,
+      "loss": 0.5294,
+      "step": 29
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.7209534645080566,
+      "learning_rate": 7.894736842105265e-06,
+      "loss": 0.4842,
+      "step": 30
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.7555510401725769,
+      "learning_rate": 8.157894736842106e-06,
+      "loss": 0.5348,
+      "step": 31
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.6169366240501404,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 0.5382,
+      "step": 32
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.6152195930480957,
+      "learning_rate": 8.68421052631579e-06,
+      "loss": 0.5039,
+      "step": 33
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.631288468837738,
+      "learning_rate": 8.947368421052632e-06,
+      "loss": 0.5037,
+      "step": 34
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.5909512042999268,
+      "learning_rate": 9.210526315789474e-06,
+      "loss": 0.5017,
+      "step": 35
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.5489953756332397,
+      "learning_rate": 9.473684210526315e-06,
+      "loss": 0.4469,
+      "step": 36
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.565674901008606,
+      "learning_rate": 9.736842105263159e-06,
+      "loss": 0.478,
+      "step": 37
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.680474579334259,
+      "learning_rate": 1e-05,
+      "loss": 0.5392,
+      "step": 38
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.607657253742218,
+      "learning_rate": 9.99978274148479e-06,
+      "loss": 0.5022,
+      "step": 39
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.5720808506011963,
+      "learning_rate": 9.999130984819662e-06,
+      "loss": 0.5057,
+      "step": 40
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.5648075938224792,
+      "learning_rate": 9.998044786644492e-06,
+      "loss": 0.4718,
+      "step": 41
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.5617280006408691,
+      "learning_rate": 9.9965242413536e-06,
+      "loss": 0.5049,
+      "step": 42
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.6486408114433289,
+      "learning_rate": 9.994569481087552e-06,
+      "loss": 0.5203,
+      "step": 43
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.5352612733840942,
+      "learning_rate": 9.992180675721671e-06,
+      "loss": 0.4967,
+      "step": 44
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5438513159751892,
+      "learning_rate": 9.989358032851283e-06,
+      "loss": 0.5188,
+      "step": 45
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.5454742908477783,
+      "learning_rate": 9.986101797773667e-06,
+      "loss": 0.4864,
+      "step": 46
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.536598265171051,
+      "learning_rate": 9.98241225346674e-06,
+      "loss": 0.4883,
+      "step": 47
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.4659676253795624,
+      "learning_rate": 9.978289720564471e-06,
+      "loss": 0.5121,
+      "step": 48
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.5836896300315857,
+      "learning_rate": 9.97373455732901e-06,
+      "loss": 0.4975,
+      "step": 49
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5226072669029236,
+      "learning_rate": 9.968747159619556e-06,
+      "loss": 0.4944,
+      "step": 50
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 0.5444321632385254,
+      "learning_rate": 9.963327960857962e-06,
+      "loss": 0.5209,
+      "step": 51
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.5670180320739746,
+      "learning_rate": 9.957477431991053e-06,
+      "loss": 0.514,
+      "step": 52
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 0.511341392993927,
+      "learning_rate": 9.95119608144972e-06,
+      "loss": 0.526,
+      "step": 53
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 0.5060410499572754,
+      "learning_rate": 9.944484455104716e-06,
+      "loss": 0.4806,
+      "step": 54
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.487128347158432,
+      "learning_rate": 9.937343136219234e-06,
+      "loss": 0.5273,
+      "step": 55
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.5598118305206299,
+      "learning_rate": 9.929772745398207e-06,
+      "loss": 0.5745,
+      "step": 56
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.5080751180648804,
+      "learning_rate": 9.921773940534382e-06,
+      "loss": 0.5082,
+      "step": 57
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.5492854118347168,
+      "learning_rate": 9.913347416751148e-06,
+      "loss": 0.5244,
+      "step": 58
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.5565740466117859,
+      "learning_rate": 9.904493906342124e-06,
+      "loss": 0.5117,
+      "step": 59
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.5090964436531067,
+      "learning_rate": 9.895214178707516e-06,
+      "loss": 0.4942,
+      "step": 60
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 0.5151892304420471,
+      "learning_rate": 9.885509040287267e-06,
+      "loss": 0.5165,
+      "step": 61
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 0.5298195481300354,
+      "learning_rate": 9.875379334490962e-06,
+      "loss": 0.5218,
+      "step": 62
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 0.5165826082229614,
+      "learning_rate": 9.864825941624538e-06,
+      "loss": 0.4986,
+      "step": 63
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.506293773651123,
+      "learning_rate": 9.853849778813777e-06,
+      "loss": 0.5127,
+      "step": 64
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.5140017867088318,
+      "learning_rate": 9.842451799924616e-06,
+      "loss": 0.5158,
+      "step": 65
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.5674154162406921,
+      "learning_rate": 9.830632995480243e-06,
+      "loss": 0.5006,
+      "step": 66
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.5346920490264893,
+      "learning_rate": 9.818394392575018e-06,
+      "loss": 0.5126,
+      "step": 67
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.5248146653175354,
+      "learning_rate": 9.805737054785223e-06,
+      "loss": 0.5394,
+      "step": 68
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.5473419427871704,
+      "learning_rate": 9.792662082076618e-06,
+      "loss": 0.5224,
+      "step": 69
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.5517472624778748,
+      "learning_rate": 9.779170610708872e-06,
+      "loss": 0.5125,
+      "step": 70
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.4769006669521332,
+      "learning_rate": 9.765263813136796e-06,
+      "loss": 0.5081,
+      "step": 71
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.5075954794883728,
+      "learning_rate": 9.750942897908468e-06,
+      "loss": 0.4958,
+      "step": 72
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.5006887316703796,
+      "learning_rate": 9.736209109560201e-06,
+      "loss": 0.5279,
+      "step": 73
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.5326476693153381,
+      "learning_rate": 9.721063728508384e-06,
+      "loss": 0.5136,
+      "step": 74
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5512110590934753,
+      "learning_rate": 9.705508070938219e-06,
+      "loss": 0.474,
+      "step": 75
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.5133175253868103,
+      "learning_rate": 9.689543488689332e-06,
+      "loss": 0.4994,
+      "step": 76
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.5255376696586609,
+      "learning_rate": 9.673171369138297e-06,
+      "loss": 0.5183,
+      "step": 77
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.5707758665084839,
+      "learning_rate": 9.656393135078067e-06,
+      "loss": 0.493,
+      "step": 78
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.5201893448829651,
+      "learning_rate": 9.639210244594335e-06,
+      "loss": 0.4635,
+      "step": 79
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.5058737397193909,
+      "learning_rate": 9.621624190938802e-06,
+      "loss": 0.5312,
+      "step": 80
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 0.43761327862739563,
+      "learning_rate": 9.603636502399436e-06,
+      "loss": 0.4524,
+      "step": 81
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 0.5335831642150879,
+      "learning_rate": 9.585248742167638e-06,
+      "loss": 0.4648,
+      "step": 82
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 0.5373964309692383,
+      "learning_rate": 9.566462508202403e-06,
+      "loss": 0.4911,
+      "step": 83
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.5256152153015137,
+      "learning_rate": 9.547279433091446e-06,
+      "loss": 0.4968,
+      "step": 84
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.5257714986801147,
+      "learning_rate": 9.527701183909336e-06,
+      "loss": 0.4879,
+      "step": 85
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 0.5462167859077454,
+      "learning_rate": 9.507729462072615e-06,
+      "loss": 0.4577,
+      "step": 86
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 0.5356786847114563,
+      "learning_rate": 9.48736600319193e-06,
+      "loss": 0.4922,
+      "step": 87
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.5588122010231018,
+      "learning_rate": 9.466612576921223e-06,
+      "loss": 0.4915,
+      "step": 88
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 0.5467613935470581,
+      "learning_rate": 9.445470986803922e-06,
+      "loss": 0.4711,
+      "step": 89
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.5490957498550415,
+      "learning_rate": 9.423943070116219e-06,
+      "loss": 0.5108,
+      "step": 90
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.4839731752872467,
+      "learning_rate": 9.402030697707398e-06,
+      "loss": 0.5128,
+      "step": 91
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.5173898935317993,
+      "learning_rate": 9.37973577383726e-06,
+      "loss": 0.4823,
+      "step": 92
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.563199520111084,
+      "learning_rate": 9.357060236010626e-06,
+      "loss": 0.4985,
+      "step": 93
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.513721227645874,
+      "learning_rate": 9.334006054808966e-06,
+      "loss": 0.4484,
+      "step": 94
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.5133054256439209,
+      "learning_rate": 9.310575233719155e-06,
+      "loss": 0.5047,
+      "step": 95
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5787802338600159,
+      "learning_rate": 9.28676980895935e-06,
+      "loss": 0.5064,
+      "step": 96
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 0.4748121500015259,
+      "learning_rate": 9.262591849302049e-06,
+      "loss": 0.4604,
+      "step": 97
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 0.556131899356842,
+      "learning_rate": 9.238043455894294e-06,
+      "loss": 0.5295,
+      "step": 98
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 0.5900002717971802,
+      "learning_rate": 9.213126762075088e-06,
+      "loss": 0.4977,
+      "step": 99
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5788969397544861,
+      "learning_rate": 9.187843933189994e-06,
+      "loss": 0.4732,
+      "step": 100
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 0.5433998107910156,
+      "learning_rate": 9.162197166402957e-06,
+      "loss": 0.5175,
+      "step": 101
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 0.5408159494400024,
+      "learning_rate": 9.136188690505363e-06,
+      "loss": 0.5087,
+      "step": 102
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 0.5552597045898438,
+      "learning_rate": 9.109820765722357e-06,
+      "loss": 0.4835,
+      "step": 103
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.5368766188621521,
+      "learning_rate": 9.083095683516414e-06,
+      "loss": 0.5349,
+      "step": 104
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.46206405758857727,
+      "learning_rate": 9.056015766388205e-06,
+      "loss": 0.4567,
+      "step": 105
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 0.5309408903121948,
+      "learning_rate": 9.028583367674767e-06,
+      "loss": 0.5166,
+      "step": 106
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 0.528049886226654,
+      "learning_rate": 9.00080087134498e-06,
+      "loss": 0.4526,
+      "step": 107
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.5379208326339722,
+      "learning_rate": 8.972670691792409e-06,
+      "loss": 0.4893,
+      "step": 108
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 0.5074729919433594,
+      "learning_rate": 8.944195273625472e-06,
+      "loss": 0.4924,
+      "step": 109
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.5556723475456238,
+      "learning_rate": 8.915377091454992e-06,
+      "loss": 0.4981,
+      "step": 110
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 0.5345364212989807,
+      "learning_rate": 8.886218649679162e-06,
+      "loss": 0.5134,
+      "step": 111
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.511635959148407,
+      "learning_rate": 8.856722482265886e-06,
+      "loss": 0.461,
+      "step": 112
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 0.49792084097862244,
+      "learning_rate": 8.826891152532579e-06,
+      "loss": 0.505,
+      "step": 113
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 0.4829058051109314,
+      "learning_rate": 8.796727252923403e-06,
+      "loss": 0.4716,
+      "step": 114
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.5941436886787415,
+      "learning_rate": 8.766233404783975e-06,
+      "loss": 0.5296,
+      "step": 115
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.5134578943252563,
+      "learning_rate": 8.735412258133562e-06,
+      "loss": 0.5045,
+      "step": 116
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 0.5325246453285217,
+      "learning_rate": 8.704266491434787e-06,
+      "loss": 0.472,
+      "step": 117
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 0.538865327835083,
+      "learning_rate": 8.672798811360863e-06,
+      "loss": 0.5026,
+      "step": 118
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 0.48347458243370056,
+      "learning_rate": 8.641011952560372e-06,
+      "loss": 0.484,
+      "step": 119
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.5306034684181213,
+      "learning_rate": 8.608908677419606e-06,
+      "loss": 0.4997,
+      "step": 120
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 0.5399216413497925,
+      "learning_rate": 8.576491775822527e-06,
+      "loss": 0.4804,
+      "step": 121
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 0.5183812975883484,
+      "learning_rate": 8.543764064908295e-06,
+      "loss": 0.4887,
+      "step": 122
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 0.4991128444671631,
+      "learning_rate": 8.510728388826464e-06,
+      "loss": 0.4453,
+      "step": 123
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.5225016474723816,
+      "learning_rate": 8.477387618489808e-06,
+      "loss": 0.5123,
+      "step": 124
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.46465304493904114,
+      "learning_rate": 8.443744651324828e-06,
+      "loss": 0.4633,
+      "step": 125
+    },
+    {
+      "epoch": 1.008,
+      "grad_norm": 0.5113005638122559,
+      "learning_rate": 8.409802411019962e-06,
+      "loss": 0.427,
+      "step": 126
+    },
+    {
+      "epoch": 1.016,
+      "grad_norm": 0.5328509211540222,
+      "learning_rate": 8.375563847271506e-06,
+      "loss": 0.4324,
+      "step": 127
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.519523024559021,
+      "learning_rate": 8.341031935527267e-06,
+      "loss": 0.4387,
+      "step": 128
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.506823718547821,
+      "learning_rate": 8.306209676727994e-06,
+      "loss": 0.4469,
+      "step": 129
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.4721229374408722,
+      "learning_rate": 8.271100097046585e-06,
+      "loss": 0.4226,
+      "step": 130
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.4656391739845276,
+      "learning_rate": 8.235706247625098e-06,
+      "loss": 0.3729,
+      "step": 131
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.4901474118232727,
+      "learning_rate": 8.200031204309604e-06,
+      "loss": 0.4627,
+      "step": 132
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.606958270072937,
+      "learning_rate": 8.16407806738288e-06,
+      "loss": 0.4347,
+      "step": 133
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.4573584496974945,
+      "learning_rate": 8.127849961294984e-06,
+      "loss": 0.402,
+      "step": 134
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.4766193926334381,
+      "learning_rate": 8.091350034391732e-06,
+      "loss": 0.4203,
+      "step": 135
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.5167376399040222,
+      "learning_rate": 8.05458145864109e-06,
+      "loss": 0.4521,
+      "step": 136
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.52271968126297,
+      "learning_rate": 8.017547429357532e-06,
+      "loss": 0.4321,
+      "step": 137
+    },
+    {
+      "epoch": 1.104,
+      "grad_norm": 0.49505582451820374,
+      "learning_rate": 7.980251164924342e-06,
+      "loss": 0.4591,
+      "step": 138
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 0.6967505216598511,
+      "learning_rate": 7.94269590651393e-06,
+      "loss": 0.4322,
+      "step": 139
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.46629568934440613,
+      "learning_rate": 7.904884917806174e-06,
+      "loss": 0.4612,
+      "step": 140
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.49921801686286926,
+      "learning_rate": 7.866821484704777e-06,
+      "loss": 0.4353,
+      "step": 141
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.5447902083396912,
+      "learning_rate": 7.828508915051724e-06,
+      "loss": 0.4323,
+      "step": 142
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 0.5017483830451965,
+      "learning_rate": 7.789950538339813e-06,
+      "loss": 0.4352,
+      "step": 143
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.49647992849349976,
+      "learning_rate": 7.751149705423313e-06,
+      "loss": 0.3971,
+      "step": 144
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.5001079440116882,
+      "learning_rate": 7.712109788226763e-06,
+      "loss": 0.4566,
+      "step": 145
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 0.4786428213119507,
+      "learning_rate": 7.672834179451943e-06,
+      "loss": 0.446,
+      "step": 146
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 0.5244361758232117,
+      "learning_rate": 7.633326292283028e-06,
+      "loss": 0.4759,
+      "step": 147
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 0.4763104319572449,
+      "learning_rate": 7.593589560089984e-06,
+      "loss": 0.4239,
+      "step": 148
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.4974442422389984,
+      "learning_rate": 7.553627436130183e-06,
+      "loss": 0.4053,
+      "step": 149
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.5250166654586792,
+      "learning_rate": 7.513443393248312e-06,
+      "loss": 0.4521,
+      "step": 150
+    },
+    {
+      "epoch": 1.208,
+      "grad_norm": 0.4822094440460205,
+      "learning_rate": 7.473040923574567e-06,
+      "loss": 0.3883,
+      "step": 151
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.4862370491027832,
+      "learning_rate": 7.432423538221179e-06,
+      "loss": 0.4322,
+      "step": 152
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.482036828994751,
+      "learning_rate": 7.391594766977277e-06,
+      "loss": 0.4105,
+      "step": 153
+    },
+    {
+      "epoch": 1.232,
+      "grad_norm": 0.5110259056091309,
+      "learning_rate": 7.350558158002154e-06,
+      "loss": 0.4103,
+      "step": 154
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.5026330351829529,
+      "learning_rate": 7.3093172775169e-06,
+      "loss": 0.4312,
+      "step": 155
+    },
+    {
+      "epoch": 1.248,
+      "grad_norm": 0.4886966943740845,
+      "learning_rate": 7.2678757094945e-06,
+      "loss": 0.4325,
+      "step": 156
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.4985504150390625,
+      "learning_rate": 7.226237055348369e-06,
+      "loss": 0.4232,
+      "step": 157
+    },
+    {
+      "epoch": 1.264,
+      "grad_norm": 0.47912245988845825,
+      "learning_rate": 7.184404933619377e-06,
+      "loss": 0.4359,
+      "step": 158
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 0.48068177700042725,
+      "learning_rate": 7.142382979661386e-06,
+      "loss": 0.4158,
+      "step": 159
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.4839794933795929,
+      "learning_rate": 7.100174845325327e-06,
+      "loss": 0.4035,
+      "step": 160
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.5554186105728149,
+      "learning_rate": 7.057784198641835e-06,
+      "loss": 0.3862,
+      "step": 161
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.5477203726768494,
+      "learning_rate": 7.015214723502496e-06,
+      "loss": 0.4347,
+      "step": 162
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.48494377732276917,
+      "learning_rate": 6.972470119339692e-06,
+      "loss": 0.4183,
+      "step": 163
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.4876761734485626,
+      "learning_rate": 6.929554100805118e-06,
+      "loss": 0.4459,
+      "step": 164
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.4854036867618561,
+      "learning_rate": 6.886470397446958e-06,
+      "loss": 0.4249,
+      "step": 165
+    },
+    {
+      "epoch": 1.328,
+      "grad_norm": 0.4709065556526184,
+      "learning_rate": 6.843222753385785e-06,
+      "loss": 0.4376,
+      "step": 166
+    },
+    {
+      "epoch": 1.336,
+      "grad_norm": 0.4834536910057068,
+      "learning_rate": 6.799814926989171e-06,
+      "loss": 0.4017,
+      "step": 167
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.4833991527557373,
+      "learning_rate": 6.756250690545079e-06,
+      "loss": 0.4145,
+      "step": 168
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.5171043872833252,
+      "learning_rate": 6.712533829934042e-06,
+      "loss": 0.4373,
+      "step": 169
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5456111431121826,
+      "learning_rate": 6.6686681443001485e-06,
+      "loss": 0.4272,
+      "step": 170
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 0.5275494456291199,
+      "learning_rate": 6.62465744572089e-06,
+      "loss": 0.4628,
+      "step": 171
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 0.46399417519569397,
+      "learning_rate": 6.580505558875878e-06,
+      "loss": 0.481,
+      "step": 172
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.4880594313144684,
+      "learning_rate": 6.536216320714466e-06,
+      "loss": 0.4285,
+      "step": 173
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 0.48990365862846375,
+      "learning_rate": 6.491793580122301e-06,
+      "loss": 0.3997,
+      "step": 174
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.49995189905166626,
+      "learning_rate": 6.447241197586847e-06,
+      "loss": 0.4332,
+      "step": 175
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.4638576805591583,
+      "learning_rate": 6.402563044861899e-06,
+      "loss": 0.4236,
+      "step": 176
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.49920183420181274,
+      "learning_rate": 6.357763004631104e-06,
+      "loss": 0.4349,
+      "step": 177
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 0.5193583965301514,
+      "learning_rate": 6.312844970170551e-06,
+      "loss": 0.4089,
+      "step": 178
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 0.47679874300956726,
+      "learning_rate": 6.267812845010431e-06,
+      "loss": 0.4298,
+      "step": 179
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.49884992837905884,
+      "learning_rate": 6.2226705425958e-06,
+      "loss": 0.4517,
+      "step": 180
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.48136106133461,
+      "learning_rate": 6.177421985946499e-06,
+      "loss": 0.4393,
+      "step": 181
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.5779682397842407,
+      "learning_rate": 6.132071107316221e-06,
+      "loss": 0.4225,
+      "step": 182
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.5509202480316162,
+      "learning_rate": 6.0866218478507875e-06,
+      "loss": 0.4579,
+      "step": 183
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.5101506114006042,
+      "learning_rate": 6.041078157245649e-06,
+      "loss": 0.4036,
+      "step": 184
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.623524010181427,
+      "learning_rate": 5.995443993402647e-06,
+      "loss": 0.451,
+      "step": 185
+    },
+    {
+      "epoch": 1.488,
+      "grad_norm": 0.4368286728858948,
+      "learning_rate": 5.949723322086053e-06,
+      "loss": 0.3881,
+      "step": 186
+    },
+    {
+      "epoch": 1.496,
+      "grad_norm": 0.4305906295776367,
+      "learning_rate": 5.9039201165779315e-06,
+      "loss": 0.4036,
+      "step": 187
+    },
+    {
+      "epoch": 1.504,
+      "grad_norm": 0.4749639630317688,
+      "learning_rate": 5.858038357332851e-06,
+      "loss": 0.4048,
+      "step": 188
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.48530155420303345,
+      "learning_rate": 5.812082031631966e-06,
+      "loss": 0.4464,
+      "step": 189
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.555038571357727,
+      "learning_rate": 5.766055133236513e-06,
+      "loss": 0.4485,
+      "step": 190
+    },
+    {
+      "epoch": 1.528,
+      "grad_norm": 0.4892346262931824,
+      "learning_rate": 5.7199616620407325e-06,
+      "loss": 0.4522,
+      "step": 191
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.5365411639213562,
+      "learning_rate": 5.673805623724272e-06,
+      "loss": 0.4752,
+      "step": 192
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.5186147689819336,
+      "learning_rate": 5.627591029404072e-06,
+      "loss": 0.4021,
+      "step": 193
+    },
+    {
+      "epoch": 1.552,
+      "grad_norm": 0.48625391721725464,
+      "learning_rate": 5.581321895285787e-06,
+      "loss": 0.4396,
+      "step": 194
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.5071629285812378,
+      "learning_rate": 5.535002242314772e-06,
+      "loss": 0.4227,
+      "step": 195
+    },
+    {
+      "epoch": 1.568,
+      "grad_norm": 0.5189520120620728,
+      "learning_rate": 5.488636095826636e-06,
+      "loss": 0.4512,
+      "step": 196
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.5435962677001953,
+      "learning_rate": 5.4422274851974356e-06,
+      "loss": 0.4767,
+      "step": 197
+    },
+    {
+      "epoch": 1.584,
+      "grad_norm": 0.4914834797382355,
+      "learning_rate": 5.395780443493508e-06,
+      "loss": 0.4035,
+      "step": 198
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 0.5276004672050476,
+      "learning_rate": 5.34929900712098e-06,
+      "loss": 0.4329,
+      "step": 199
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.4546476900577545,
+      "learning_rate": 5.302787215474992e-06,
+      "loss": 0.3965,
+      "step": 200
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.48372510075569153,
+      "learning_rate": 5.256249110588659e-06,
+      "loss": 0.4272,
+      "step": 201
+    },
+    {
+      "epoch": 1.616,
+      "grad_norm": 0.49213626980781555,
+      "learning_rate": 5.209688736781811e-06,
+      "loss": 0.4409,
+      "step": 202
+    },
+    {
+      "epoch": 1.624,
+      "grad_norm": 0.4945046603679657,
+      "learning_rate": 5.163110140309518e-06,
+      "loss": 0.4419,
+      "step": 203
+    },
+    {
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.4468039274215698,
+      "learning_rate": 5.116517369010467e-06,
+      "loss": 0.398,
+      "step": 204
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.4727765917778015,
+      "learning_rate": 5.069914471955179e-06,
+      "loss": 0.4229,
+      "step": 205
+    },
+    {
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.5005367398262024,
+      "learning_rate": 5.023305499094145e-06,
+      "loss": 0.4153,
+      "step": 206
+    },
+    {
+      "epoch": 1.6560000000000001,
+      "grad_norm": 0.4818647801876068,
+      "learning_rate": 4.976694500905858e-06,
+      "loss": 0.443,
+      "step": 207
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.47024303674697876,
+      "learning_rate": 4.930085528044823e-06,
+      "loss": 0.4541,
+      "step": 208
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.47553378343582153,
+      "learning_rate": 4.883482630989536e-06,
+      "loss": 0.4069,
+      "step": 209
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.44939181208610535,
+      "learning_rate": 4.8368898596904834e-06,
+      "loss": 0.3964,
+      "step": 210
+    },
+    {
+      "epoch": 1.688,
+      "grad_norm": 0.46793460845947266,
+      "learning_rate": 4.790311263218191e-06,
+      "loss": 0.4339,
+      "step": 211
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.45191749930381775,
+      "learning_rate": 4.743750889411342e-06,
+      "loss": 0.426,
+      "step": 212
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.45308157801628113,
+      "learning_rate": 4.697212784525009e-06,
+      "loss": 0.4338,
+      "step": 213
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 0.4543735384941101,
+      "learning_rate": 4.65070099287902e-06,
+      "loss": 0.4083,
+      "step": 214
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.49145424365997314,
+      "learning_rate": 4.604219556506492e-06,
+      "loss": 0.4658,
+      "step": 215
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.4785975515842438,
+      "learning_rate": 4.557772514802564e-06,
+      "loss": 0.4248,
+      "step": 216
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.5019366145133972,
+      "learning_rate": 4.511363904173366e-06,
+      "loss": 0.4482,
+      "step": 217
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.4578736126422882,
+      "learning_rate": 4.46499775768523e-06,
+      "loss": 0.4391,
+      "step": 218
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 0.46869972348213196,
+      "learning_rate": 4.418678104714214e-06,
+      "loss": 0.4087,
+      "step": 219
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.480589359998703,
+      "learning_rate": 4.372408970595931e-06,
+      "loss": 0.418,
+      "step": 220
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.5114148855209351,
+      "learning_rate": 4.326194376275729e-06,
+      "loss": 0.4009,
+      "step": 221
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.4714803099632263,
+      "learning_rate": 4.280038337959268e-06,
+      "loss": 0.4119,
+      "step": 222
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.4820714592933655,
+      "learning_rate": 4.2339448667634885e-06,
+      "loss": 0.4364,
+      "step": 223
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.45575451850891113,
+      "learning_rate": 4.187917968368036e-06,
+      "loss": 0.3943,
+      "step": 224
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.4869477152824402,
+      "learning_rate": 4.141961642667152e-06,
+      "loss": 0.4447,
+      "step": 225
+    },
+    {
+      "epoch": 1.808,
+      "grad_norm": 0.4546818435192108,
+      "learning_rate": 4.09607988342207e-06,
+      "loss": 0.4397,
+      "step": 226
+    },
+    {
+      "epoch": 1.8159999999999998,
+      "grad_norm": 0.5653818249702454,
+      "learning_rate": 4.0502766779139485e-06,
+      "loss": 0.3881,
+      "step": 227
+    },
+    {
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.484779953956604,
+      "learning_rate": 4.0045560065973535e-06,
+      "loss": 0.4673,
+      "step": 228
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.48289933800697327,
+      "learning_rate": 3.958921842754351e-06,
+      "loss": 0.4156,
+      "step": 229
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.43402060866355896,
+      "learning_rate": 3.913378152149214e-06,
+      "loss": 0.4044,
+      "step": 230
+    },
+    {
+      "epoch": 1.8479999999999999,
+      "grad_norm": 0.47271519899368286,
+      "learning_rate": 3.86792889268378e-06,
+      "loss": 0.4387,
+      "step": 231
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.5104248523712158,
+      "learning_rate": 3.8225780140535025e-06,
+      "loss": 0.3976,
+      "step": 232
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.44085070490837097,
+      "learning_rate": 3.777329457404202e-06,
+      "loss": 0.4062,
+      "step": 233
+    },
+    {
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.5098981857299805,
+      "learning_rate": 3.7321871549895715e-06,
+      "loss": 0.4458,
+      "step": 234
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.42704570293426514,
+      "learning_rate": 3.68715502982945e-06,
+      "loss": 0.3947,
+      "step": 235
+    },
+    {
+      "epoch": 1.888,
+      "grad_norm": 0.46332859992980957,
+      "learning_rate": 3.6422369953688973e-06,
+      "loss": 0.4294,
+      "step": 236
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.4884559214115143,
+      "learning_rate": 3.5974369551381023e-06,
+      "loss": 0.4498,
+      "step": 237
+    },
+    {
+      "epoch": 1.904,
+      "grad_norm": 0.5290793180465698,
+      "learning_rate": 3.5527588024131542e-06,
+      "loss": 0.4312,
+      "step": 238
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 0.48744434118270874,
+      "learning_rate": 3.5082064198777e-06,
+      "loss": 0.4772,
+      "step": 239
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.4615407884120941,
+      "learning_rate": 3.463783679285535e-06,
+      "loss": 0.4101,
+      "step": 240
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.49090084433555603,
+      "learning_rate": 3.4194944411241213e-06,
+      "loss": 0.4222,
+      "step": 241
+    },
+    {
+      "epoch": 1.936,
+      "grad_norm": 0.4603979289531708,
+      "learning_rate": 3.3753425542791106e-06,
+      "loss": 0.4322,
+      "step": 242
+    },
+    {
+      "epoch": 1.944,
+      "grad_norm": 0.4630926847457886,
+      "learning_rate": 3.3313318556998523e-06,
+      "loss": 0.4553,
+      "step": 243
+    },
+    {
+      "epoch": 1.952,
+      "grad_norm": 0.5014007091522217,
+      "learning_rate": 3.2874661700659586e-06,
+      "loss": 0.4541,
+      "step": 244
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.5217999815940857,
+      "learning_rate": 3.2437493094549223e-06,
+      "loss": 0.4164,
+      "step": 245
+    },
+    {
+      "epoch": 1.968,
+      "grad_norm": 0.5072699785232544,
+      "learning_rate": 3.200185073010831e-06,
+      "loss": 0.4151,
+      "step": 246
+    },
+    {
+      "epoch": 1.976,
+      "grad_norm": 0.4602278172969818,
+      "learning_rate": 3.1567772466142156e-06,
+      "loss": 0.3739,
+      "step": 247
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.5061410069465637,
+      "learning_rate": 3.1135296025530426e-06,
+      "loss": 0.4892,
+      "step": 248
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.5533497333526611,
+      "learning_rate": 3.070445899194885e-06,
+      "loss": 0.4132,
+      "step": 249
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.52688068151474,
+      "learning_rate": 3.0275298806603102e-06,
+      "loss": 0.4463,
+      "step": 250
+    },
+    {
+      "epoch": 2.008,
+      "grad_norm": 0.5126904249191284,
+      "learning_rate": 2.984785276497507e-06,
+      "loss": 0.3639,
+      "step": 251
+    },
+    {
+      "epoch": 2.016,
+      "grad_norm": 0.5104655623435974,
+      "learning_rate": 2.9422158013581658e-06,
+      "loss": 0.3535,
+      "step": 252
+    },
+    {
+      "epoch": 2.024,
+      "grad_norm": 0.5136793255805969,
+      "learning_rate": 2.899825154674674e-06,
+      "loss": 0.3835,
+      "step": 253
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.45347532629966736,
+      "learning_rate": 2.8576170203386144e-06,
+      "loss": 0.3412,
+      "step": 254
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.4745730757713318,
+      "learning_rate": 2.8155950663806234e-06,
+      "loss": 0.3863,
+      "step": 255
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.5067371129989624,
+      "learning_rate": 2.7737629446516325e-06,
+      "loss": 0.3514,
+      "step": 256
+    },
+    {
+      "epoch": 2.056,
+      "grad_norm": 0.45462149381637573,
+      "learning_rate": 2.732124290505501e-06,
+      "loss": 0.3528,
+      "step": 257
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 0.46529221534729004,
+      "learning_rate": 2.6906827224831024e-06,
+      "loss": 0.3296,
+      "step": 258
+    },
+    {
+      "epoch": 2.072,
+      "grad_norm": 0.5160210728645325,
+      "learning_rate": 2.6494418419978485e-06,
+      "loss": 0.3416,
+      "step": 259
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.505672037601471,
+      "learning_rate": 2.608405233022724e-06,
+      "loss": 0.3793,
+      "step": 260
+    },
+    {
+      "epoch": 2.088,
+      "grad_norm": 0.44298309087753296,
+      "learning_rate": 2.5675764617788233e-06,
+      "loss": 0.3298,
+      "step": 261
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 0.4680778682231903,
+      "learning_rate": 2.526959076425434e-06,
+      "loss": 0.3427,
+      "step": 262
+    },
+    {
+      "epoch": 2.104,
+      "grad_norm": 0.4816036820411682,
+      "learning_rate": 2.4865566067516896e-06,
+      "loss": 0.3709,
+      "step": 263
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.47969356179237366,
+      "learning_rate": 2.4463725638698182e-06,
+      "loss": 0.3255,
+      "step": 264
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.5166645646095276,
+      "learning_rate": 2.406410439910017e-06,
+      "loss": 0.3928,
+      "step": 265
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.523476243019104,
+      "learning_rate": 2.366673707716973e-06,
+      "loss": 0.3497,
+      "step": 266
+    },
+    {
+      "epoch": 2.136,
+      "grad_norm": 0.5414285063743591,
+      "learning_rate": 2.327165820548059e-06,
+      "loss": 0.3653,
+      "step": 267
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 0.4763210713863373,
+      "learning_rate": 2.287890211773238e-06,
+      "loss": 0.3628,
+      "step": 268
+    },
+    {
+      "epoch": 2.152,
+      "grad_norm": 0.5000659227371216,
+      "learning_rate": 2.2488502945766893e-06,
+      "loss": 0.3681,
+      "step": 269
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.48179784417152405,
+      "learning_rate": 2.210049461660189e-06,
+      "loss": 0.3542,
+      "step": 270
+    },
+    {
+      "epoch": 2.168,
+      "grad_norm": 0.4680255651473999,
+      "learning_rate": 2.1714910849482777e-06,
+      "loss": 0.3618,
+      "step": 271
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.4781685173511505,
+      "learning_rate": 2.1331785152952243e-06,
+      "loss": 0.3533,
+      "step": 272
+    },
+    {
+      "epoch": 2.184,
+      "grad_norm": 0.508620023727417,
+      "learning_rate": 2.0951150821938278e-06,
+      "loss": 0.3761,
+      "step": 273
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.48846498131752014,
+      "learning_rate": 2.0573040934860717e-06,
+      "loss": 0.3776,
+      "step": 274
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.48690298199653625,
+      "learning_rate": 2.0197488350756618e-06,
+      "loss": 0.326,
+      "step": 275
+    },
+    {
+      "epoch": 2.208,
+      "grad_norm": 0.5058321356773376,
+      "learning_rate": 1.98245257064247e-06,
+      "loss": 0.3596,
+      "step": 276
+    },
+    {
+      "epoch": 2.216,
+      "grad_norm": 0.5168304443359375,
+      "learning_rate": 1.945418541358911e-06,
+      "loss": 0.3443,
+      "step": 277
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 0.4696882367134094,
+      "learning_rate": 1.9086499656082685e-06,
+      "loss": 0.3469,
+      "step": 278
+    },
+    {
+      "epoch": 2.232,
+      "grad_norm": 0.46734338998794556,
+      "learning_rate": 1.872150038705015e-06,
+      "loss": 0.3494,
+      "step": 279
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.4970659017562866,
+      "learning_rate": 1.835921932617119e-06,
+      "loss": 0.3614,
+      "step": 280
+    },
+    {
+      "epoch": 2.248,
+      "grad_norm": 0.4725131094455719,
+      "learning_rate": 1.7999687956903955e-06,
+      "loss": 0.3678,
+      "step": 281
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.48716068267822266,
+      "learning_rate": 1.7642937523749038e-06,
+      "loss": 0.3514,
+      "step": 282
+    },
+    {
+      "epoch": 2.2640000000000002,
+      "grad_norm": 0.4228149950504303,
+      "learning_rate": 1.7288999029534177e-06,
+      "loss": 0.3349,
+      "step": 283
+    },
+    {
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.47141751646995544,
+      "learning_rate": 1.6937903232720076e-06,
+      "loss": 0.3655,
+      "step": 284
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 0.44692301750183105,
+      "learning_rate": 1.6589680644727347e-06,
+      "loss": 0.3446,
+      "step": 285
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 0.46537840366363525,
+      "learning_rate": 1.6244361527284953e-06,
+      "loss": 0.3473,
+      "step": 286
+    },
+    {
+      "epoch": 2.296,
+      "grad_norm": 0.4578072428703308,
+      "learning_rate": 1.5901975889800387e-06,
+      "loss": 0.3614,
+      "step": 287
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.4702107012271881,
+      "learning_rate": 1.556255348675174e-06,
+      "loss": 0.3417,
+      "step": 288
+    },
+    {
+      "epoch": 2.312,
+      "grad_norm": 0.49962151050567627,
+      "learning_rate": 1.522612381510195e-06,
+      "loss": 0.348,
+      "step": 289
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.514380156993866,
+      "learning_rate": 1.489271611173538e-06,
+      "loss": 0.3587,
+      "step": 290
+    },
+    {
+      "epoch": 2.328,
+      "grad_norm": 0.4479122459888458,
+      "learning_rate": 1.4562359350917054e-06,
+      "loss": 0.3479,
+      "step": 291
+    },
+    {
+      "epoch": 2.336,
+      "grad_norm": 0.48699259757995605,
+      "learning_rate": 1.423508224177474e-06,
+      "loss": 0.3678,
+      "step": 292
+    },
+    {
+      "epoch": 2.344,
+      "grad_norm": 0.46162307262420654,
+      "learning_rate": 1.3910913225803946e-06,
+      "loss": 0.3321,
+      "step": 293
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 0.4586437940597534,
+      "learning_rate": 1.35898804743963e-06,
+      "loss": 0.3748,
+      "step": 294
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.479818195104599,
+      "learning_rate": 1.3272011886391368e-06,
+      "loss": 0.3489,
+      "step": 295
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.44310837984085083,
+      "learning_rate": 1.295733508565213e-06,
+      "loss": 0.3427,
+      "step": 296
+    },
+    {
+      "epoch": 2.376,
+      "grad_norm": 0.4900333881378174,
+      "learning_rate": 1.2645877418664394e-06,
+      "loss": 0.3484,
+      "step": 297
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.6010957360267639,
+      "learning_rate": 1.2337665952160266e-06,
+      "loss": 0.3486,
+      "step": 298
+    },
+    {
+      "epoch": 2.392,
+      "grad_norm": 0.44970938563346863,
+      "learning_rate": 1.2032727470765982e-06,
+      "loss": 0.3345,
+      "step": 299
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.46644240617752075,
+      "learning_rate": 1.1731088474674235e-06,
+      "loss": 0.3695,
+      "step": 300
+    },
+    {
+      "epoch": 2.408,
+      "grad_norm": 0.4730045199394226,
+      "learning_rate": 1.1432775177341165e-06,
+      "loss": 0.3605,
+      "step": 301
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 0.4608900845050812,
+      "learning_rate": 1.11378135032084e-06,
+      "loss": 0.3328,
+      "step": 302
+    },
+    {
+      "epoch": 2.424,
+      "grad_norm": 0.47910159826278687,
+      "learning_rate": 1.08462290854501e-06,
+      "loss": 0.3592,
+      "step": 303
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.5008491277694702,
+      "learning_rate": 1.0558047263745297e-06,
+      "loss": 0.3653,
+      "step": 304
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.45120254158973694,
+      "learning_rate": 1.0273293082075914e-06,
+      "loss": 0.3317,
+      "step": 305
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 0.44771674275398254,
+      "learning_rate": 9.991991286550207e-07,
+      "loss": 0.3417,
+      "step": 306
+    },
+    {
+      "epoch": 2.456,
+      "grad_norm": 0.47719165682792664,
+      "learning_rate": 9.71416632325235e-07,
+      "loss": 0.3634,
+      "step": 307
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 0.5096871256828308,
+      "learning_rate": 9.439842336117954e-07,
+      "loss": 0.3428,
+      "step": 308
+    },
+    {
+      "epoch": 2.472,
+      "grad_norm": 0.43439558148384094,
+      "learning_rate": 9.169043164835867e-07,
+      "loss": 0.3336,
+      "step": 309
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.4950801730155945,
+      "learning_rate": 8.901792342776439e-07,
+      "loss": 0.4171,
+      "step": 310
+    },
+    {
+      "epoch": 2.488,
+      "grad_norm": 0.4548616409301758,
+      "learning_rate": 8.638113094946382e-07,
+      "loss": 0.3123,
+      "step": 311
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.5122199058532715,
+      "learning_rate": 8.378028335970451e-07,
+      "loss": 0.3784,
+      "step": 312
+    },
+    {
+      "epoch": 2.504,
+      "grad_norm": 0.452438622713089,
+      "learning_rate": 8.121560668100065e-07,
+      "loss": 0.3631,
+      "step": 313
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 0.43378862738609314,
+      "learning_rate": 7.868732379249122e-07,
+      "loss": 0.3319,
+      "step": 314
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.4786088466644287,
+      "learning_rate": 7.619565441057075e-07,
+      "loss": 0.3517,
+      "step": 315
+    },
+    {
+      "epoch": 2.528,
+      "grad_norm": 0.5133551955223083,
+      "learning_rate": 7.37408150697953e-07,
+      "loss": 0.3702,
+      "step": 316
+    },
+    {
+      "epoch": 2.536,
+      "grad_norm": 0.4935527741909027,
+      "learning_rate": 7.132301910406503e-07,
+      "loss": 0.3759,
+      "step": 317
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 0.4293310344219208,
+      "learning_rate": 6.894247662808456e-07,
+      "loss": 0.322,
+      "step": 318
+    },
+    {
+      "epoch": 2.552,
+      "grad_norm": 0.46054044365882874,
+      "learning_rate": 6.659939451910341e-07,
+      "loss": 0.3343,
+      "step": 319
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.5166534185409546,
+      "learning_rate": 6.429397639893758e-07,
+      "loss": 0.3813,
+      "step": 320
+    },
+    {
+      "epoch": 2.568,
+      "grad_norm": 0.4581873118877411,
+      "learning_rate": 6.202642261627411e-07,
+      "loss": 0.368,
+      "step": 321
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.5063138008117676,
+      "learning_rate": 5.979693022926025e-07,
+      "loss": 0.4142,
+      "step": 322
+    },
+    {
+      "epoch": 2.584,
+      "grad_norm": 0.47579020261764526,
+      "learning_rate": 5.760569298837825e-07,
+      "loss": 0.3717,
+      "step": 323
+    },
+    {
+      "epoch": 2.592,
+      "grad_norm": 0.4639912545681,
+      "learning_rate": 5.54529013196079e-07,
+      "loss": 0.352,
+      "step": 324
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.4613383710384369,
+      "learning_rate": 5.333874230787772e-07,
+      "loss": 0.3661,
+      "step": 325
+    },
+    {
+      "epoch": 2.608,
+      "grad_norm": 0.42720070481300354,
+      "learning_rate": 5.126339968080696e-07,
+      "loss": 0.3616,
+      "step": 326
+    },
+    {
+      "epoch": 2.616,
+      "grad_norm": 0.4943825304508209,
+      "learning_rate": 4.922705379273862e-07,
+      "loss": 0.3645,
+      "step": 327
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.4619237780570984,
+      "learning_rate": 4.7229881609066387e-07,
+      "loss": 0.3307,
+      "step": 328
+    },
+    {
+      "epoch": 2.632,
+      "grad_norm": 0.47587689757347107,
+      "learning_rate": 4.5272056690855494e-07,
+      "loss": 0.3624,
+      "step": 329
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.45437976717948914,
+      "learning_rate": 4.335374917975982e-07,
+      "loss": 0.3242,
+      "step": 330
+    },
+    {
+      "epoch": 2.648,
+      "grad_norm": 0.5222877264022827,
+      "learning_rate": 4.147512578323615e-07,
+      "loss": 0.3808,
+      "step": 331
+    },
+    {
+      "epoch": 2.656,
+      "grad_norm": 0.46543389558792114,
+      "learning_rate": 3.9636349760056427e-07,
+      "loss": 0.3389,
+      "step": 332
+    },
+    {
+      "epoch": 2.664,
+      "grad_norm": 0.4624124765396118,
+      "learning_rate": 3.783758090611983e-07,
+      "loss": 0.3336,
+      "step": 333
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 0.45994681119918823,
+      "learning_rate": 3.6078975540566716e-07,
+      "loss": 0.3482,
+      "step": 334
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.45068469643592834,
+      "learning_rate": 3.4360686492193263e-07,
+      "loss": 0.3077,
+      "step": 335
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.5126630663871765,
+      "learning_rate": 3.268286308617041e-07,
+      "loss": 0.3906,
+      "step": 336
+    },
+    {
+      "epoch": 2.6959999999999997,
+      "grad_norm": 0.4749516546726227,
+      "learning_rate": 3.104565113106689e-07,
+      "loss": 0.342,
+      "step": 337
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.43455156683921814,
+      "learning_rate": 2.9449192906178205e-07,
+      "loss": 0.3491,
+      "step": 338
+    },
+    {
+      "epoch": 2.7119999999999997,
+      "grad_norm": 0.46082979440689087,
+      "learning_rate": 2.789362714916172e-07,
+      "loss": 0.3875,
+      "step": 339
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.44106754660606384,
+      "learning_rate": 2.6379089043980064e-07,
+      "loss": 0.32,
+      "step": 340
+    },
+    {
+      "epoch": 2.7279999999999998,
+      "grad_norm": 0.46814629435539246,
+      "learning_rate": 2.4905710209153224e-07,
+      "loss": 0.3451,
+      "step": 341
+    },
+    {
+      "epoch": 2.7359999999999998,
+      "grad_norm": 0.5077950358390808,
+      "learning_rate": 2.3473618686320477e-07,
+      "loss": 0.3861,
+      "step": 342
+    },
+    {
+      "epoch": 2.7439999999999998,
+      "grad_norm": 0.49315568804740906,
+      "learning_rate": 2.208293892911284e-07,
+      "loss": 0.3469,
+      "step": 343
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.4634096920490265,
+      "learning_rate": 2.0733791792338197e-07,
+      "loss": 0.3761,
+      "step": 344
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.4556006193161011,
+      "learning_rate": 1.9426294521477874e-07,
+      "loss": 0.3504,
+      "step": 345
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 0.48851218819618225,
+      "learning_rate": 1.8160560742498223e-07,
+      "loss": 0.3652,
+      "step": 346
+    },
+    {
+      "epoch": 2.776,
+      "grad_norm": 0.45232683420181274,
+      "learning_rate": 1.6936700451975818e-07,
+      "loss": 0.3259,
+      "step": 347
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 0.4734852910041809,
+      "learning_rate": 1.5754820007538473e-07,
+      "loss": 0.3555,
+      "step": 348
+    },
+    {
+      "epoch": 2.792,
+      "grad_norm": 0.46094757318496704,
+      "learning_rate": 1.461502211862237e-07,
+      "loss": 0.3451,
+      "step": 349
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.45597511529922485,
+      "learning_rate": 1.3517405837546404e-07,
+      "loss": 0.3481,
+      "step": 350
+    },
+    {
+      "epoch": 2.808,
+      "grad_norm": 0.44162362813949585,
+      "learning_rate": 1.2462066550903818e-07,
+      "loss": 0.3324,
+      "step": 351
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 0.4328787326812744,
+      "learning_rate": 1.1449095971273305e-07,
+      "loss": 0.3304,
+      "step": 352
+    },
+    {
+      "epoch": 2.824,
+      "grad_norm": 0.472141832113266,
+      "learning_rate": 1.0478582129248516e-07,
+      "loss": 0.3655,
+      "step": 353
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 0.4979706406593323,
+      "learning_rate": 9.550609365787888e-08,
+      "loss": 0.3815,
+      "step": 354
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.49750280380249023,
+      "learning_rate": 8.66525832488535e-08,
+      "loss": 0.3656,
+      "step": 355
+    },
+    {
+      "epoch": 2.848,
+      "grad_norm": 0.46096086502075195,
+      "learning_rate": 7.822605946561923e-08,
+      "loss": 0.3437,
+      "step": 356
+    },
+    {
+      "epoch": 2.856,
+      "grad_norm": 0.5005020499229431,
+      "learning_rate": 7.022725460179459e-08,
+      "loss": 0.3697,
+      "step": 357
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 0.4813578426837921,
+      "learning_rate": 6.265686378076729e-08,
+      "loss": 0.3595,
+      "step": 358
+    },
+    {
+      "epoch": 2.872,
+      "grad_norm": 0.4750673472881317,
+      "learning_rate": 5.5515544895284324e-08,
+      "loss": 0.3706,
+      "step": 359
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.48565149307250977,
+      "learning_rate": 4.880391855028088e-08,
+      "loss": 0.3524,
+      "step": 360
+    },
+    {
+      "epoch": 2.888,
+      "grad_norm": 0.4671759307384491,
+      "learning_rate": 4.252256800894694e-08,
+      "loss": 0.3407,
+      "step": 361
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 0.4376312494277954,
+      "learning_rate": 3.6672039142039426e-08,
+      "loss": 0.3292,
+      "step": 362
+    },
+    {
+      "epoch": 2.904,
+      "grad_norm": 0.4908435344696045,
+      "learning_rate": 3.125284038044407e-08,
+      "loss": 0.3429,
+      "step": 363
+    },
+    {
+      "epoch": 2.912,
+      "grad_norm": 0.44629916548728943,
+      "learning_rate": 2.6265442670991293e-08,
+      "loss": 0.3428,
+      "step": 364
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 0.465819388628006,
+      "learning_rate": 2.1710279435530058e-08,
+      "loss": 0.3448,
+      "step": 365
+    },
+    {
+      "epoch": 2.928,
+      "grad_norm": 0.4819665253162384,
+      "learning_rate": 1.7587746533260786e-08,
+      "loss": 0.3519,
+      "step": 366
+    },
+    {
+      "epoch": 2.936,
+      "grad_norm": 0.4784250855445862,
+      "learning_rate": 1.3898202226333424e-08,
+      "loss": 0.3739,
+      "step": 367
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.495050847530365,
+      "learning_rate": 1.0641967148716236e-08,
+      "loss": 0.3628,
+      "step": 368
+    },
+    {
+      "epoch": 2.952,
+      "grad_norm": 0.4823502004146576,
+      "learning_rate": 7.819324278328099e-09,
+      "loss": 0.3411,
+      "step": 369
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.41492488980293274,
+      "learning_rate": 5.430518912448169e-09,
+      "loss": 0.3326,
+      "step": 370
+    },
+    {
+      "epoch": 2.968,
+      "grad_norm": 0.47112229466438293,
+      "learning_rate": 3.4757586464001513e-09,
+      "loss": 0.3696,
+      "step": 371
+    },
+    {
+      "epoch": 2.976,
+      "grad_norm": 0.46793392300605774,
+      "learning_rate": 1.9552133555084117e-09,
+      "loss": 0.3661,
+      "step": 372
+    },
+    {
+      "epoch": 2.984,
+      "grad_norm": 0.4385625720024109,
+      "learning_rate": 8.690151803386615e-10,
+      "loss": 0.3421,
+      "step": 373
+    },
+    {
+      "epoch": 2.992,
+      "grad_norm": 0.43801286816596985,
+      "learning_rate": 2.1725851521103847e-10,
+      "loss": 0.3395,
+      "step": 374
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.44443294405937195,
+      "learning_rate": 0.0,
+      "loss": 0.3399,
+      "step": 375
+    },
+    {
+      "epoch": 3.0,
+      "step": 375,
+      "total_flos": 223704105418752.0,
+      "train_loss": 0.4401542440255483,
+      "train_runtime": 59266.2263,
+      "train_samples_per_second": 0.607,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 223704105418752.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c978379f7d4e15fce1781f29f6355c4384a55beb86301f88c3590d3cf994bf18
+size 7416