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/Qwen2.5-32B-Instruct
+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/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the Sky-T1 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: 2e-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: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0a0+f70bd71a48.nv24.06
+- 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": 1.9952038369304557,
+    "total_flos": 716120051679232.0,
+    "train_loss": 0.4522540926073606,
+    "train_runtime": 71993.7308,
+    "train_samples_per_second": 0.278,
+    "train_steps_per_second": 0.003
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "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": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "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 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "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 sha256:7b367df5e952cbd6eeff8a22029ece027953df6a13e507473de61858b8395c62
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56829089c167c338ea13a81d6fee15469a3b48856b8a1d78ff0d27f1ba3c0732
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebcab05e30ee007224c4908b2a444790d05cb7e1c6835e751c9bd4c8b417c08e
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67af141ba3fb1b1838e5326811bbf3e3bdf7605084390af7e7a34f4b840fb0e1
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f64be31f15de14c406ff32d9e8ee971ac0735f3c90f302e792d8682394c53b7
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29723db0b41eeebd9e51d862ab2029429ab6117df03438290d6d75d2fbdea4b
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:752bb49d912df49bb55f893cceeef814d9a5b341ffa1c8d5ecce1d4792436fa4
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8ded533af2e8f2bdb29b8bf3aa30c7e768ff1996231e40b1e52f30e1f9d01f
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbdbbc3516a45094a892a0ec3247e67201c65326aa29f4e0fc61c874ae2eed3
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa36fdd1e86185d999255584e0dbcb1ca3019d650004b3f3b318cc033cf181d
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cbf0ab5e3fbb107bfab23c38e68aee19fb9682130029c1c231f93979ba0f0c7
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05419f19a55284a34285e221d200cf7df53fbb28aef7ed3a0a7381965283a2f0
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c55ffbae0705090908b7972e1b2758c305e6df6fa949f453eeea9d51f8632e
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a28c9c4d6fb114b33e580083d1bd856b0e1464d44ce66783a665fad64e65049
+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 Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\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 Qwen, created by Alibaba Cloud. You are a helpful assistant.<|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": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9952038369304557,
+    "total_flos": 716120051679232.0,
+    "train_loss": 0.4522540926073606,
+    "train_runtime": 71993.7308,
+    "train_samples_per_second": 0.278,
+    "train_steps_per_second": 0.003
+}

trainer_log.jsonl

@@ -0,0 +1,300 @@
+{"current_steps": 1, "total_steps": 208, "loss": 0.7408, "lr": 9.523809523809525e-07, "epoch": 0.009592326139088728, "percentage": 0.48, "elapsed_time": "0:05:17", "remaining_time": "18:15:41"}
+{"current_steps": 2, "total_steps": 208, "loss": 0.7838, "lr": 1.904761904761905e-06, "epoch": 0.019184652278177457, "percentage": 0.96, "elapsed_time": "0:10:32", "remaining_time": "18:05:21"}
+{"current_steps": 3, "total_steps": 208, "loss": 0.7864, "lr": 2.8571428571428573e-06, "epoch": 0.02877697841726619, "percentage": 1.44, "elapsed_time": "0:16:16", "remaining_time": "18:31:56"}
+{"current_steps": 4, "total_steps": 208, "loss": 0.7749, "lr": 3.80952380952381e-06, "epoch": 0.03836930455635491, "percentage": 1.92, "elapsed_time": "0:22:25", "remaining_time": "19:03:52"}
+{"current_steps": 5, "total_steps": 208, "loss": 0.7393, "lr": 4.761904761904762e-06, "epoch": 0.047961630695443645, "percentage": 2.4, "elapsed_time": "0:27:34", "remaining_time": "18:39:19"}
+{"current_steps": 6, "total_steps": 208, "loss": 0.7485, "lr": 5.7142857142857145e-06, "epoch": 0.05755395683453238, "percentage": 2.88, "elapsed_time": "0:34:20", "remaining_time": "19:16:22"}
+{"current_steps": 7, "total_steps": 208, "loss": 0.7022, "lr": 6.666666666666667e-06, "epoch": 0.0671462829736211, "percentage": 3.37, "elapsed_time": "0:39:34", "remaining_time": "18:56:25"}
+{"current_steps": 8, "total_steps": 208, "loss": 0.6913, "lr": 7.61904761904762e-06, "epoch": 0.07673860911270983, "percentage": 3.85, "elapsed_time": "0:44:30", "remaining_time": "18:32:39"}
+{"current_steps": 9, "total_steps": 208, "loss": 0.7048, "lr": 8.571428571428571e-06, "epoch": 0.08633093525179857, "percentage": 4.33, "elapsed_time": "0:50:35", "remaining_time": "18:38:43"}
+{"current_steps": 10, "total_steps": 208, "loss": 0.6192, "lr": 9.523809523809525e-06, "epoch": 0.09592326139088729, "percentage": 4.81, "elapsed_time": "0:56:22", "remaining_time": "18:36:11"}
+{"current_steps": 11, "total_steps": 208, "loss": 0.6308, "lr": 1.0476190476190477e-05, "epoch": 0.10551558752997602, "percentage": 5.29, "elapsed_time": "1:01:59", "remaining_time": "18:30:20"}
+{"current_steps": 12, "total_steps": 208, "loss": 0.608, "lr": 1.1428571428571429e-05, "epoch": 0.11510791366906475, "percentage": 5.77, "elapsed_time": "1:07:23", "remaining_time": "18:20:40"}
+{"current_steps": 13, "total_steps": 208, "loss": 0.6213, "lr": 1.2380952380952383e-05, "epoch": 0.12470023980815348, "percentage": 6.25, "elapsed_time": "1:14:00", "remaining_time": "18:30:14"}
+{"current_steps": 14, "total_steps": 208, "loss": 0.6082, "lr": 1.3333333333333333e-05, "epoch": 0.1342925659472422, "percentage": 6.73, "elapsed_time": "1:19:47", "remaining_time": "18:25:37"}
+{"current_steps": 15, "total_steps": 208, "loss": 0.5867, "lr": 1.4285714285714287e-05, "epoch": 0.14388489208633093, "percentage": 7.21, "elapsed_time": "1:25:14", "remaining_time": "18:16:50"}
+{"current_steps": 16, "total_steps": 208, "loss": 0.584, "lr": 1.523809523809524e-05, "epoch": 0.15347721822541965, "percentage": 7.69, "elapsed_time": "1:31:26", "remaining_time": "18:17:21"}
+{"current_steps": 17, "total_steps": 208, "loss": 0.5702, "lr": 1.6190476190476193e-05, "epoch": 0.1630695443645084, "percentage": 8.17, "elapsed_time": "1:36:32", "remaining_time": "18:04:41"}
+{"current_steps": 18, "total_steps": 208, "loss": 0.5572, "lr": 1.7142857142857142e-05, "epoch": 0.17266187050359713, "percentage": 8.65, "elapsed_time": "1:41:11", "remaining_time": "17:48:08"}
+{"current_steps": 19, "total_steps": 208, "loss": 0.5825, "lr": 1.8095238095238097e-05, "epoch": 0.18225419664268586, "percentage": 9.13, "elapsed_time": "1:46:45", "remaining_time": "17:41:59"}
+{"current_steps": 20, "total_steps": 208, "loss": 0.5305, "lr": 1.904761904761905e-05, "epoch": 0.19184652278177458, "percentage": 9.62, "elapsed_time": "1:52:38", "remaining_time": "17:38:47"}
+{"current_steps": 21, "total_steps": 208, "loss": 0.5454, "lr": 2e-05, "epoch": 0.2014388489208633, "percentage": 10.1, "elapsed_time": "1:58:42", "remaining_time": "17:37:05"}
+{"current_steps": 22, "total_steps": 208, "loss": 0.5611, "lr": 1.9998588839790777e-05, "epoch": 0.21103117505995203, "percentage": 10.58, "elapsed_time": "2:05:12", "remaining_time": "17:38:32"}
+{"current_steps": 23, "total_steps": 208, "loss": 0.5204, "lr": 1.999435575743774e-05, "epoch": 0.22062350119904076, "percentage": 11.06, "elapsed_time": "2:11:10", "remaining_time": "17:35:07"}
+{"current_steps": 24, "total_steps": 208, "loss": 0.5457, "lr": 1.9987301947652354e-05, "epoch": 0.2302158273381295, "percentage": 11.54, "elapsed_time": "2:17:54", "remaining_time": "17:37:17"}
+{"current_steps": 25, "total_steps": 208, "loss": 0.5501, "lr": 1.9977429401245764e-05, "epoch": 0.23980815347721823, "percentage": 12.02, "elapsed_time": "2:24:11", "remaining_time": "17:35:29"}
+{"current_steps": 26, "total_steps": 208, "loss": 0.5222, "lr": 1.9964740904566903e-05, "epoch": 0.24940047961630696, "percentage": 12.5, "elapsed_time": "2:30:04", "remaining_time": "17:30:28"}
+{"current_steps": 27, "total_steps": 208, "loss": 0.5043, "lr": 1.9949240038716092e-05, "epoch": 0.2589928057553957, "percentage": 12.98, "elapsed_time": "2:35:04", "remaining_time": "17:19:34"}
+{"current_steps": 28, "total_steps": 208, "loss": 0.5106, "lr": 1.9930931178534353e-05, "epoch": 0.2685851318944844, "percentage": 13.46, "elapsed_time": "2:40:09", "remaining_time": "17:09:38"}
+{"current_steps": 29, "total_steps": 208, "loss": 0.5057, "lr": 1.9909819491368677e-05, "epoch": 0.27817745803357313, "percentage": 13.94, "elapsed_time": "2:45:03", "remaining_time": "16:58:48"}
+{"current_steps": 30, "total_steps": 208, "loss": 0.52, "lr": 1.988591093561364e-05, "epoch": 0.28776978417266186, "percentage": 14.42, "elapsed_time": "2:50:16", "remaining_time": "16:50:18"}
+{"current_steps": 31, "total_steps": 208, "loss": 0.5166, "lr": 1.985921225902975e-05, "epoch": 0.2973621103117506, "percentage": 14.9, "elapsed_time": "2:56:07", "remaining_time": "16:45:38"}
+{"current_steps": 32, "total_steps": 208, "loss": 0.4923, "lr": 1.982973099683902e-05, "epoch": 0.3069544364508393, "percentage": 15.38, "elapsed_time": "3:01:17", "remaining_time": "16:37:03"}
+{"current_steps": 33, "total_steps": 208, "loss": 0.499, "lr": 1.9797475469598267e-05, "epoch": 0.31654676258992803, "percentage": 15.87, "elapsed_time": "3:07:49", "remaining_time": "16:36:04"}
+{"current_steps": 34, "total_steps": 208, "loss": 0.4931, "lr": 1.9762454780850807e-05, "epoch": 0.3261390887290168, "percentage": 16.35, "elapsed_time": "3:12:50", "remaining_time": "16:26:55"}
+{"current_steps": 35, "total_steps": 208, "loss": 0.5057, "lr": 1.972467881455713e-05, "epoch": 0.33573141486810554, "percentage": 16.83, "elapsed_time": "3:19:06", "remaining_time": "16:24:11"}
+{"current_steps": 36, "total_steps": 208, "loss": 0.4971, "lr": 1.968415823230534e-05, "epoch": 0.34532374100719426, "percentage": 17.31, "elapsed_time": "3:24:16", "remaining_time": "16:15:57"}
+{"current_steps": 37, "total_steps": 208, "loss": 0.4742, "lr": 1.96409044703021e-05, "epoch": 0.354916067146283, "percentage": 17.79, "elapsed_time": "3:30:10", "remaining_time": "16:11:21"}
+{"current_steps": 38, "total_steps": 208, "loss": 0.515, "lr": 1.9594929736144978e-05, "epoch": 0.3645083932853717, "percentage": 18.27, "elapsed_time": "3:35:10", "remaining_time": "16:02:36"}
+{"current_steps": 39, "total_steps": 208, "loss": 0.4816, "lr": 1.9546247005377065e-05, "epoch": 0.37410071942446044, "percentage": 18.75, "elapsed_time": "3:40:46", "remaining_time": "15:56:43"}
+{"current_steps": 40, "total_steps": 208, "loss": 0.4672, "lr": 1.9494870017824877e-05, "epoch": 0.38369304556354916, "percentage": 19.23, "elapsed_time": "3:46:04", "remaining_time": "15:49:30"}
+{"current_steps": 41, "total_steps": 208, "loss": 0.4622, "lr": 1.9440813273720504e-05, "epoch": 0.3932853717026379, "percentage": 19.71, "elapsed_time": "3:51:08", "remaining_time": "15:41:30"}
+{"current_steps": 42, "total_steps": 208, "loss": 0.4589, "lr": 1.938409202960922e-05, "epoch": 0.4028776978417266, "percentage": 20.19, "elapsed_time": "3:56:33", "remaining_time": "15:34:58"}
+{"current_steps": 43, "total_steps": 208, "loss": 0.4918, "lr": 1.932472229404356e-05, "epoch": 0.41247002398081534, "percentage": 20.67, "elapsed_time": "4:02:01", "remaining_time": "15:28:43"}
+{"current_steps": 44, "total_steps": 208, "loss": 0.4958, "lr": 1.9262720823065217e-05, "epoch": 0.42206235011990406, "percentage": 21.15, "elapsed_time": "4:08:10", "remaining_time": "15:25:01"}
+{"current_steps": 45, "total_steps": 208, "loss": 0.4773, "lr": 1.9198105115475946e-05, "epoch": 0.4316546762589928, "percentage": 21.63, "elapsed_time": "4:13:28", "remaining_time": "15:18:08"}
+{"current_steps": 46, "total_steps": 208, "loss": 0.4827, "lr": 1.9130893407898834e-05, "epoch": 0.4412470023980815, "percentage": 22.12, "elapsed_time": "4:19:00", "remaining_time": "15:12:09"}
+{"current_steps": 47, "total_steps": 208, "loss": 0.4686, "lr": 1.9061104669631343e-05, "epoch": 0.45083932853717024, "percentage": 22.6, "elapsed_time": "4:24:55", "remaining_time": "15:07:32"}
+{"current_steps": 48, "total_steps": 208, "loss": 0.4884, "lr": 1.8988758597291577e-05, "epoch": 0.460431654676259, "percentage": 23.08, "elapsed_time": "4:30:36", "remaining_time": "15:02:01"}
+{"current_steps": 49, "total_steps": 208, "loss": 0.4587, "lr": 1.8913875609259246e-05, "epoch": 0.47002398081534774, "percentage": 23.56, "elapsed_time": "4:36:26", "remaining_time": "14:57:01"}
+{"current_steps": 50, "total_steps": 208, "loss": 0.4726, "lr": 1.8836476839912967e-05, "epoch": 0.47961630695443647, "percentage": 24.04, "elapsed_time": "4:41:39", "remaining_time": "14:50:01"}
+{"current_steps": 51, "total_steps": 208, "loss": 0.4889, "lr": 1.8756584133665447e-05, "epoch": 0.4892086330935252, "percentage": 24.52, "elapsed_time": "4:46:57", "remaining_time": "14:43:24"}
+{"current_steps": 52, "total_steps": 208, "loss": 0.4841, "lr": 1.86742200387983e-05, "epoch": 0.4988009592326139, "percentage": 25.0, "elapsed_time": "4:52:47", "remaining_time": "14:38:23"}
+{"current_steps": 53, "total_steps": 208, "loss": 0.4365, "lr": 1.8589407801098192e-05, "epoch": 0.5083932853717026, "percentage": 25.48, "elapsed_time": "4:58:18", "remaining_time": "14:32:24"}
+{"current_steps": 54, "total_steps": 208, "loss": 0.47, "lr": 1.8502171357296144e-05, "epoch": 0.5179856115107914, "percentage": 25.96, "elapsed_time": "5:04:03", "remaining_time": "14:27:07"}
+{"current_steps": 55, "total_steps": 208, "loss": 0.4816, "lr": 1.8412535328311813e-05, "epoch": 0.5275779376498801, "percentage": 26.44, "elapsed_time": "5:09:33", "remaining_time": "14:21:06"}
+{"current_steps": 56, "total_steps": 208, "loss": 0.4528, "lr": 1.8320525012304685e-05, "epoch": 0.5371702637889688, "percentage": 26.92, "elapsed_time": "5:15:04", "remaining_time": "14:15:12"}
+{"current_steps": 57, "total_steps": 208, "loss": 0.458, "lr": 1.8226166377534113e-05, "epoch": 0.5467625899280576, "percentage": 27.4, "elapsed_time": "5:20:54", "remaining_time": "14:10:08"}
+{"current_steps": 58, "total_steps": 208, "loss": 0.486, "lr": 1.8129486055030255e-05, "epoch": 0.5563549160671463, "percentage": 27.88, "elapsed_time": "5:26:59", "remaining_time": "14:05:40"}
+{"current_steps": 59, "total_steps": 208, "loss": 0.4246, "lr": 1.8030511331077945e-05, "epoch": 0.565947242206235, "percentage": 28.37, "elapsed_time": "5:32:17", "remaining_time": "13:59:10"}
+{"current_steps": 60, "total_steps": 208, "loss": 0.4579, "lr": 1.7929270139515606e-05, "epoch": 0.5755395683453237, "percentage": 28.85, "elapsed_time": "5:38:15", "remaining_time": "13:54:22"}
+{"current_steps": 61, "total_steps": 208, "loss": 0.4381, "lr": 1.782579105385145e-05, "epoch": 0.5851318944844125, "percentage": 29.33, "elapsed_time": "5:42:09", "remaining_time": "13:44:32"}
+{"current_steps": 62, "total_steps": 208, "loss": 0.4807, "lr": 1.772010327919912e-05, "epoch": 0.5947242206235012, "percentage": 29.81, "elapsed_time": "5:49:00", "remaining_time": "13:41:51"}
+{"current_steps": 63, "total_steps": 208, "loss": 0.4685, "lr": 1.761223664403505e-05, "epoch": 0.60431654676259, "percentage": 30.29, "elapsed_time": "5:55:24", "remaining_time": "13:38:00"}
+{"current_steps": 64, "total_steps": 208, "loss": 0.4591, "lr": 1.7502221591779932e-05, "epoch": 0.6139088729016786, "percentage": 30.77, "elapsed_time": "6:01:15", "remaining_time": "13:32:49"}
+{"current_steps": 65, "total_steps": 208, "loss": 0.4744, "lr": 1.7390089172206594e-05, "epoch": 0.6235011990407674, "percentage": 31.25, "elapsed_time": "6:07:29", "remaining_time": "13:28:28"}
+{"current_steps": 66, "total_steps": 208, "loss": 0.4703, "lr": 1.727587103267677e-05, "epoch": 0.6330935251798561, "percentage": 31.73, "elapsed_time": "6:13:00", "remaining_time": "13:22:31"}
+{"current_steps": 67, "total_steps": 208, "loss": 0.5017, "lr": 1.7159599409209194e-05, "epoch": 0.6426858513189448, "percentage": 32.21, "elapsed_time": "6:18:58", "remaining_time": "13:17:32"}
+{"current_steps": 68, "total_steps": 208, "loss": 0.4193, "lr": 1.704130711738157e-05, "epoch": 0.6522781774580336, "percentage": 32.69, "elapsed_time": "6:23:05", "remaining_time": "13:08:43"}
+{"current_steps": 69, "total_steps": 208, "loss": 0.4605, "lr": 1.692102754306895e-05, "epoch": 0.6618705035971223, "percentage": 33.17, "elapsed_time": "6:29:19", "remaining_time": "13:04:17"}
+{"current_steps": 70, "total_steps": 208, "loss": 0.4636, "lr": 1.6798794633021192e-05, "epoch": 0.6714628297362111, "percentage": 33.65, "elapsed_time": "6:35:49", "remaining_time": "13:00:20"}
+{"current_steps": 71, "total_steps": 208, "loss": 0.467, "lr": 1.667464288528207e-05, "epoch": 0.6810551558752997, "percentage": 34.13, "elapsed_time": "6:41:26", "remaining_time": "12:54:37"}
+{"current_steps": 72, "total_steps": 208, "loss": 0.4526, "lr": 1.6548607339452853e-05, "epoch": 0.6906474820143885, "percentage": 34.62, "elapsed_time": "6:47:16", "remaining_time": "12:49:17"}
+{"current_steps": 73, "total_steps": 208, "loss": 0.4513, "lr": 1.6420723566802982e-05, "epoch": 0.7002398081534772, "percentage": 35.1, "elapsed_time": "6:52:38", "remaining_time": "12:43:05"}
+{"current_steps": 74, "total_steps": 208, "loss": 0.4644, "lr": 1.6291027660230735e-05, "epoch": 0.709832134292566, "percentage": 35.58, "elapsed_time": "6:57:38", "remaining_time": "12:36:15"}
+{"current_steps": 75, "total_steps": 208, "loss": 0.4416, "lr": 1.6159556224076637e-05, "epoch": 0.7194244604316546, "percentage": 36.06, "elapsed_time": "7:03:00", "remaining_time": "12:30:08"}
+{"current_steps": 76, "total_steps": 208, "loss": 0.4761, "lr": 1.6026346363792565e-05, "epoch": 0.7290167865707434, "percentage": 36.54, "elapsed_time": "7:09:27", "remaining_time": "12:25:54"}
+{"current_steps": 77, "total_steps": 208, "loss": 0.4758, "lr": 1.5891435675469376e-05, "epoch": 0.7386091127098321, "percentage": 37.02, "elapsed_time": "7:15:13", "remaining_time": "12:20:27"}
+{"current_steps": 78, "total_steps": 208, "loss": 0.4735, "lr": 1.57548622352261e-05, "epoch": 0.7482014388489209, "percentage": 37.5, "elapsed_time": "7:20:37", "remaining_time": "12:14:22"}
+{"current_steps": 79, "total_steps": 208, "loss": 0.4592, "lr": 1.561666458846365e-05, "epoch": 0.7577937649880095, "percentage": 37.98, "elapsed_time": "7:27:30", "remaining_time": "12:10:44"}
+{"current_steps": 80, "total_steps": 208, "loss": 0.4714, "lr": 1.5476881738986037e-05, "epoch": 0.7673860911270983, "percentage": 38.46, "elapsed_time": "7:33:15", "remaining_time": "12:05:12"}
+{"current_steps": 81, "total_steps": 208, "loss": 0.425, "lr": 1.5335553137992286e-05, "epoch": 0.7769784172661871, "percentage": 38.94, "elapsed_time": "7:38:17", "remaining_time": "11:58:33"}
+{"current_steps": 82, "total_steps": 208, "loss": 0.444, "lr": 1.519271867294203e-05, "epoch": 0.7865707434052758, "percentage": 39.42, "elapsed_time": "7:44:32", "remaining_time": "11:53:47"}
+{"current_steps": 83, "total_steps": 208, "loss": 0.4902, "lr": 1.504841865629799e-05, "epoch": 0.7961630695443646, "percentage": 39.9, "elapsed_time": "7:50:33", "remaining_time": "11:48:40"}
+{"current_steps": 84, "total_steps": 208, "loss": 0.4916, "lr": 1.490269381414849e-05, "epoch": 0.8057553956834532, "percentage": 40.38, "elapsed_time": "7:56:16", "remaining_time": "11:43:04"}
+{"current_steps": 85, "total_steps": 208, "loss": 0.445, "lr": 1.4755585274713289e-05, "epoch": 0.815347721822542, "percentage": 40.87, "elapsed_time": "8:02:20", "remaining_time": "11:37:58"}
+{"current_steps": 86, "total_steps": 208, "loss": 0.4239, "lr": 1.4607134556735836e-05, "epoch": 0.8249400479616307, "percentage": 41.35, "elapsed_time": "8:07:12", "remaining_time": "11:31:10"}
+{"current_steps": 87, "total_steps": 208, "loss": 0.4797, "lr": 1.4457383557765385e-05, "epoch": 0.8345323741007195, "percentage": 41.83, "elapsed_time": "8:12:59", "remaining_time": "11:25:39"}
+{"current_steps": 88, "total_steps": 208, "loss": 0.4588, "lr": 1.4306374542332141e-05, "epoch": 0.8441247002398081, "percentage": 42.31, "elapsed_time": "8:18:11", "remaining_time": "11:19:20"}
+{"current_steps": 89, "total_steps": 208, "loss": 0.4472, "lr": 1.4154150130018867e-05, "epoch": 0.8537170263788969, "percentage": 42.79, "elapsed_time": "8:23:30", "remaining_time": "11:13:14"}
+{"current_steps": 90, "total_steps": 208, "loss": 0.4767, "lr": 1.4000753283432267e-05, "epoch": 0.8633093525179856, "percentage": 43.27, "elapsed_time": "8:29:33", "remaining_time": "11:08:04"}
+{"current_steps": 91, "total_steps": 208, "loss": 0.4641, "lr": 1.3846227296077568e-05, "epoch": 0.8729016786570744, "percentage": 43.75, "elapsed_time": "8:35:13", "remaining_time": "11:02:26"}
+{"current_steps": 1, "total_steps": 208, "loss": 0.7408, "lr": 9.523809523809525e-07, "epoch": 0.009592326139088728, "percentage": 0.48, "elapsed_time": "0:05:16", "remaining_time": "18:11:52"}
+{"current_steps": 2, "total_steps": 208, "loss": 0.7838, "lr": 1.904761904761905e-06, "epoch": 0.019184652278177457, "percentage": 0.96, "elapsed_time": "0:10:32", "remaining_time": "18:05:40"}
+{"current_steps": 3, "total_steps": 208, "loss": 0.7863, "lr": 2.8571428571428573e-06, "epoch": 0.02877697841726619, "percentage": 1.44, "elapsed_time": "0:16:16", "remaining_time": "18:31:38"}
+{"current_steps": 4, "total_steps": 208, "loss": 0.775, "lr": 3.80952380952381e-06, "epoch": 0.03836930455635491, "percentage": 1.92, "elapsed_time": "0:22:23", "remaining_time": "19:02:11"}
+{"current_steps": 5, "total_steps": 208, "loss": 0.7394, "lr": 4.761904761904762e-06, "epoch": 0.047961630695443645, "percentage": 2.4, "elapsed_time": "0:27:33", "remaining_time": "18:38:44"}
+{"current_steps": 6, "total_steps": 208, "loss": 0.7485, "lr": 5.7142857142857145e-06, "epoch": 0.05755395683453238, "percentage": 2.88, "elapsed_time": "0:34:19", "remaining_time": "19:15:41"}
+{"current_steps": 7, "total_steps": 208, "loss": 0.7022, "lr": 6.666666666666667e-06, "epoch": 0.0671462829736211, "percentage": 3.37, "elapsed_time": "0:39:34", "remaining_time": "18:56:20"}
+{"current_steps": 8, "total_steps": 208, "loss": 0.6913, "lr": 7.61904761904762e-06, "epoch": 0.07673860911270983, "percentage": 3.85, "elapsed_time": "0:44:33", "remaining_time": "18:33:55"}
+{"current_steps": 9, "total_steps": 208, "loss": 0.7041, "lr": 8.571428571428571e-06, "epoch": 0.08633093525179857, "percentage": 4.33, "elapsed_time": "0:50:40", "remaining_time": "18:40:32"}
+{"current_steps": 10, "total_steps": 208, "loss": 0.6186, "lr": 9.523809523809525e-06, "epoch": 0.09592326139088729, "percentage": 4.81, "elapsed_time": "0:56:27", "remaining_time": "18:37:53"}
+{"current_steps": 11, "total_steps": 208, "loss": 0.6306, "lr": 1.0476190476190477e-05, "epoch": 0.10551558752997602, "percentage": 5.29, "elapsed_time": "1:02:09", "remaining_time": "18:33:20"}
+{"current_steps": 12, "total_steps": 208, "loss": 0.6073, "lr": 1.1428571428571429e-05, "epoch": 0.11510791366906475, "percentage": 5.77, "elapsed_time": "1:07:33", "remaining_time": "18:23:35"}
+{"current_steps": 13, "total_steps": 208, "loss": 0.6209, "lr": 1.2380952380952383e-05, "epoch": 0.12470023980815348, "percentage": 6.25, "elapsed_time": "1:14:13", "remaining_time": "18:33:25"}
+{"current_steps": 14, "total_steps": 208, "loss": 0.6077, "lr": 1.3333333333333333e-05, "epoch": 0.1342925659472422, "percentage": 6.73, "elapsed_time": "1:20:02", "remaining_time": "18:29:03"}
+{"current_steps": 15, "total_steps": 208, "loss": 0.5864, "lr": 1.4285714285714287e-05, "epoch": 0.14388489208633093, "percentage": 7.21, "elapsed_time": "1:25:28", "remaining_time": "18:19:49"}
+{"current_steps": 16, "total_steps": 208, "loss": 0.5837, "lr": 1.523809523809524e-05, "epoch": 0.15347721822541965, "percentage": 7.69, "elapsed_time": "1:31:43", "remaining_time": "18:20:38"}
+{"current_steps": 17, "total_steps": 208, "loss": 0.5701, "lr": 1.6190476190476193e-05, "epoch": 0.1630695443645084, "percentage": 8.17, "elapsed_time": "1:36:51", "remaining_time": "18:08:13"}
+{"current_steps": 18, "total_steps": 208, "loss": 0.5569, "lr": 1.7142857142857142e-05, "epoch": 0.17266187050359713, "percentage": 8.65, "elapsed_time": "1:41:32", "remaining_time": "17:51:49"}
+{"current_steps": 19, "total_steps": 208, "loss": 0.5824, "lr": 1.8095238095238097e-05, "epoch": 0.18225419664268586, "percentage": 9.13, "elapsed_time": "1:47:11", "remaining_time": "17:46:12"}
+{"current_steps": 20, "total_steps": 208, "loss": 0.5305, "lr": 1.904761904761905e-05, "epoch": 0.19184652278177458, "percentage": 9.62, "elapsed_time": "1:53:03", "remaining_time": "17:42:40"}
+{"current_steps": 21, "total_steps": 208, "loss": 0.5451, "lr": 2e-05, "epoch": 0.2014388489208633, "percentage": 10.1, "elapsed_time": "1:59:06", "remaining_time": "17:40:38"}
+{"current_steps": 22, "total_steps": 208, "loss": 0.5611, "lr": 1.9998588839790777e-05, "epoch": 0.21103117505995203, "percentage": 10.58, "elapsed_time": "2:05:36", "remaining_time": "17:41:55"}
+{"current_steps": 23, "total_steps": 208, "loss": 0.5204, "lr": 1.999435575743774e-05, "epoch": 0.22062350119904076, "percentage": 11.06, "elapsed_time": "2:11:31", "remaining_time": "17:37:52"}
+{"current_steps": 24, "total_steps": 208, "loss": 0.5459, "lr": 1.9987301947652354e-05, "epoch": 0.2302158273381295, "percentage": 11.54, "elapsed_time": "2:18:16", "remaining_time": "17:40:03"}
+{"current_steps": 25, "total_steps": 208, "loss": 0.5501, "lr": 1.9977429401245764e-05, "epoch": 0.23980815347721823, "percentage": 12.02, "elapsed_time": "2:24:35", "remaining_time": "17:38:22"}
+{"current_steps": 26, "total_steps": 208, "loss": 0.5219, "lr": 1.9964740904566903e-05, "epoch": 0.24940047961630696, "percentage": 12.5, "elapsed_time": "2:30:28", "remaining_time": "17:33:17"}
+{"current_steps": 27, "total_steps": 208, "loss": 0.5043, "lr": 1.9949240038716092e-05, "epoch": 0.2589928057553957, "percentage": 12.98, "elapsed_time": "2:35:28", "remaining_time": "17:22:14"}
+{"current_steps": 28, "total_steps": 208, "loss": 0.5106, "lr": 1.9930931178534353e-05, "epoch": 0.2685851318944844, "percentage": 13.46, "elapsed_time": "2:40:32", "remaining_time": "17:12:06"}
+{"current_steps": 29, "total_steps": 208, "loss": 0.5059, "lr": 1.9909819491368677e-05, "epoch": 0.27817745803357313, "percentage": 13.94, "elapsed_time": "2:45:27", "remaining_time": "17:01:16"}
+{"current_steps": 30, "total_steps": 208, "loss": 0.5209, "lr": 1.988591093561364e-05, "epoch": 0.28776978417266186, "percentage": 14.42, "elapsed_time": "2:50:44", "remaining_time": "16:53:01"}
+{"current_steps": 31, "total_steps": 208, "loss": 0.5173, "lr": 1.985921225902975e-05, "epoch": 0.2973621103117506, "percentage": 14.9, "elapsed_time": "2:56:36", "remaining_time": "16:48:21"}
+{"current_steps": 32, "total_steps": 208, "loss": 0.4928, "lr": 1.982973099683902e-05, "epoch": 0.3069544364508393, "percentage": 15.38, "elapsed_time": "3:01:44", "remaining_time": "16:39:37"}
+{"current_steps": 33, "total_steps": 208, "loss": 0.4993, "lr": 1.9797475469598267e-05, "epoch": 0.31654676258992803, "percentage": 15.87, "elapsed_time": "3:08:16", "remaining_time": "16:38:27"}
+{"current_steps": 34, "total_steps": 208, "loss": 0.4934, "lr": 1.9762454780850807e-05, "epoch": 0.3261390887290168, "percentage": 16.35, "elapsed_time": "3:13:16", "remaining_time": "16:29:05"}
+{"current_steps": 35, "total_steps": 208, "loss": 0.5058, "lr": 1.972467881455713e-05, "epoch": 0.33573141486810554, "percentage": 16.83, "elapsed_time": "3:19:35", "remaining_time": "16:26:34"}
+{"current_steps": 36, "total_steps": 208, "loss": 0.4971, "lr": 1.968415823230534e-05, "epoch": 0.34532374100719426, "percentage": 17.31, "elapsed_time": "3:24:53", "remaining_time": "16:18:54"}
+{"current_steps": 37, "total_steps": 208, "loss": 0.4743, "lr": 1.96409044703021e-05, "epoch": 0.354916067146283, "percentage": 17.79, "elapsed_time": "3:30:53", "remaining_time": "16:14:39"}
+{"current_steps": 38, "total_steps": 208, "loss": 0.5153, "lr": 1.9594929736144978e-05, "epoch": 0.3645083932853717, "percentage": 18.27, "elapsed_time": "3:35:57", "remaining_time": "16:06:09"}
+{"current_steps": 39, "total_steps": 208, "loss": 0.4818, "lr": 1.9546247005377065e-05, "epoch": 0.37410071942446044, "percentage": 18.75, "elapsed_time": "3:41:38", "remaining_time": "16:00:28"}
+{"current_steps": 40, "total_steps": 208, "loss": 0.4673, "lr": 1.9494870017824877e-05, "epoch": 0.38369304556354916, "percentage": 19.23, "elapsed_time": "3:47:01", "remaining_time": "15:53:31"}
+{"current_steps": 41, "total_steps": 208, "loss": 0.4622, "lr": 1.9440813273720504e-05, "epoch": 0.3932853717026379, "percentage": 19.71, "elapsed_time": "3:52:09", "remaining_time": "15:45:37"}
+{"current_steps": 42, "total_steps": 208, "loss": 0.459, "lr": 1.938409202960922e-05, "epoch": 0.4028776978417266, "percentage": 20.19, "elapsed_time": "3:57:39", "remaining_time": "15:39:20"}
+{"current_steps": 43, "total_steps": 208, "loss": 0.4919, "lr": 1.932472229404356e-05, "epoch": 0.41247002398081534, "percentage": 20.67, "elapsed_time": "4:03:11", "remaining_time": "15:33:11"}
+{"current_steps": 44, "total_steps": 208, "loss": 0.4957, "lr": 1.9262720823065217e-05, "epoch": 0.42206235011990406, "percentage": 21.15, "elapsed_time": "4:09:23", "remaining_time": "15:29:32"}
+{"current_steps": 45, "total_steps": 208, "loss": 0.4775, "lr": 1.9198105115475946e-05, "epoch": 0.4316546762589928, "percentage": 21.63, "elapsed_time": "4:14:44", "remaining_time": "15:22:42"}
+{"current_steps": 46, "total_steps": 208, "loss": 0.4828, "lr": 1.9130893407898834e-05, "epoch": 0.4412470023980815, "percentage": 22.12, "elapsed_time": "4:20:21", "remaining_time": "15:16:53"}
+{"current_steps": 47, "total_steps": 208, "loss": 0.4686, "lr": 1.9061104669631343e-05, "epoch": 0.45083932853717024, "percentage": 22.6, "elapsed_time": "4:26:19", "remaining_time": "15:12:18"}
+{"current_steps": 48, "total_steps": 208, "loss": 0.4886, "lr": 1.8988758597291577e-05, "epoch": 0.460431654676259, "percentage": 23.08, "elapsed_time": "4:32:00", "remaining_time": "15:06:42"}
+{"current_steps": 49, "total_steps": 208, "loss": 0.4587, "lr": 1.8913875609259246e-05, "epoch": 0.47002398081534774, "percentage": 23.56, "elapsed_time": "4:37:54", "remaining_time": "15:01:48"}
+{"current_steps": 50, "total_steps": 208, "loss": 0.4727, "lr": 1.8836476839912967e-05, "epoch": 0.47961630695443647, "percentage": 24.04, "elapsed_time": "4:43:11", "remaining_time": "14:54:54"}
+{"current_steps": 51, "total_steps": 208, "loss": 0.4888, "lr": 1.8756584133665447e-05, "epoch": 0.4892086330935252, "percentage": 24.52, "elapsed_time": "4:48:37", "remaining_time": "14:48:31"}
+{"current_steps": 52, "total_steps": 208, "loss": 0.4842, "lr": 1.86742200387983e-05, "epoch": 0.4988009592326139, "percentage": 25.0, "elapsed_time": "4:54:31", "remaining_time": "14:43:35"}
+{"current_steps": 53, "total_steps": 208, "loss": 0.4366, "lr": 1.8589407801098192e-05, "epoch": 0.5083932853717026, "percentage": 25.48, "elapsed_time": "5:00:06", "remaining_time": "14:37:39"}
+{"current_steps": 54, "total_steps": 208, "loss": 0.47, "lr": 1.8502171357296144e-05, "epoch": 0.5179856115107914, "percentage": 25.96, "elapsed_time": "5:05:57", "remaining_time": "14:32:33"}
+{"current_steps": 55, "total_steps": 208, "loss": 0.4816, "lr": 1.8412535328311813e-05, "epoch": 0.5275779376498801, "percentage": 26.44, "elapsed_time": "5:11:31", "remaining_time": "14:26:37"}
+{"current_steps": 56, "total_steps": 208, "loss": 0.4529, "lr": 1.8320525012304685e-05, "epoch": 0.5371702637889688, "percentage": 26.92, "elapsed_time": "5:17:10", "remaining_time": "14:20:55"}
+{"current_steps": 57, "total_steps": 208, "loss": 0.4583, "lr": 1.8226166377534113e-05, "epoch": 0.5467625899280576, "percentage": 27.4, "elapsed_time": "5:23:01", "remaining_time": "14:15:42"}
+{"current_steps": 58, "total_steps": 208, "loss": 0.4861, "lr": 1.8129486055030255e-05, "epoch": 0.5563549160671463, "percentage": 27.88, "elapsed_time": "5:29:06", "remaining_time": "14:11:09"}
+{"current_steps": 59, "total_steps": 208, "loss": 0.4245, "lr": 1.8030511331077945e-05, "epoch": 0.565947242206235, "percentage": 28.37, "elapsed_time": "5:34:31", "remaining_time": "14:04:50"}
+{"current_steps": 60, "total_steps": 208, "loss": 0.458, "lr": 1.7929270139515606e-05, "epoch": 0.5755395683453237, "percentage": 28.85, "elapsed_time": "5:40:32", "remaining_time": "14:00:00"}
+{"current_steps": 61, "total_steps": 208, "loss": 0.4383, "lr": 1.782579105385145e-05, "epoch": 0.5851318944844125, "percentage": 29.33, "elapsed_time": "5:44:32", "remaining_time": "13:50:17"}
+{"current_steps": 62, "total_steps": 208, "loss": 0.4809, "lr": 1.772010327919912e-05, "epoch": 0.5947242206235012, "percentage": 29.81, "elapsed_time": "5:51:28", "remaining_time": "13:47:39"}
+{"current_steps": 63, "total_steps": 208, "loss": 0.4685, "lr": 1.761223664403505e-05, "epoch": 0.60431654676259, "percentage": 30.29, "elapsed_time": "5:57:55", "remaining_time": "13:43:47"}
+{"current_steps": 64, "total_steps": 208, "loss": 0.4591, "lr": 1.7502221591779932e-05, "epoch": 0.6139088729016786, "percentage": 30.77, "elapsed_time": "6:03:50", "remaining_time": "13:38:38"}
+{"current_steps": 65, "total_steps": 208, "loss": 0.4747, "lr": 1.7390089172206594e-05, "epoch": 0.6235011990407674, "percentage": 31.25, "elapsed_time": "6:10:09", "remaining_time": "13:34:20"}
+{"current_steps": 66, "total_steps": 208, "loss": 0.4706, "lr": 1.727587103267677e-05, "epoch": 0.6330935251798561, "percentage": 31.73, "elapsed_time": "6:15:42", "remaining_time": "13:28:21"}
+{"current_steps": 67, "total_steps": 208, "loss": 0.5017, "lr": 1.7159599409209194e-05, "epoch": 0.6426858513189448, "percentage": 32.21, "elapsed_time": "6:21:46", "remaining_time": "13:23:25"}
+{"current_steps": 68, "total_steps": 208, "loss": 0.4193, "lr": 1.704130711738157e-05, "epoch": 0.6522781774580336, "percentage": 32.69, "elapsed_time": "6:25:57", "remaining_time": "13:14:36"}
+{"current_steps": 69, "total_steps": 208, "loss": 0.4606, "lr": 1.692102754306895e-05, "epoch": 0.6618705035971223, "percentage": 33.17, "elapsed_time": "6:32:13", "remaining_time": "13:10:07"}
+{"current_steps": 70, "total_steps": 208, "loss": 0.4637, "lr": 1.6798794633021192e-05, "epoch": 0.6714628297362111, "percentage": 33.65, "elapsed_time": "6:38:49", "remaining_time": "13:06:14"}
+{"current_steps": 71, "total_steps": 208, "loss": 0.4672, "lr": 1.667464288528207e-05, "epoch": 0.6810551558752997, "percentage": 34.13, "elapsed_time": "6:44:30", "remaining_time": "13:00:31"}
+{"current_steps": 72, "total_steps": 208, "loss": 0.4525, "lr": 1.6548607339452853e-05, "epoch": 0.6906474820143885, "percentage": 34.62, "elapsed_time": "6:50:24", "remaining_time": "12:55:13"}
+{"current_steps": 73, "total_steps": 208, "loss": 0.4512, "lr": 1.6420723566802982e-05, "epoch": 0.7002398081534772, "percentage": 35.1, "elapsed_time": "6:55:52", "remaining_time": "12:49:04"}
+{"current_steps": 74, "total_steps": 208, "loss": 0.4645, "lr": 1.6291027660230735e-05, "epoch": 0.709832134292566, "percentage": 35.58, "elapsed_time": "7:00:54", "remaining_time": "12:42:11"}
+{"current_steps": 75, "total_steps": 208, "loss": 0.4418, "lr": 1.6159556224076637e-05, "epoch": 0.7194244604316546, "percentage": 36.06, "elapsed_time": "7:06:20", "remaining_time": "12:36:03"}
+{"current_steps": 76, "total_steps": 208, "loss": 0.4761, "lr": 1.6026346363792565e-05, "epoch": 0.7290167865707434, "percentage": 36.54, "elapsed_time": "7:12:52", "remaining_time": "12:31:49"}
+{"current_steps": 77, "total_steps": 208, "loss": 0.4759, "lr": 1.5891435675469376e-05, "epoch": 0.7386091127098321, "percentage": 37.02, "elapsed_time": "7:18:40", "remaining_time": "12:26:18"}
+{"current_steps": 78, "total_steps": 208, "loss": 0.4734, "lr": 1.57548622352261e-05, "epoch": 0.7482014388489209, "percentage": 37.5, "elapsed_time": "7:24:06", "remaining_time": "12:20:11"}
+{"current_steps": 79, "total_steps": 208, "loss": 0.4592, "lr": 1.561666458846365e-05, "epoch": 0.7577937649880095, "percentage": 37.98, "elapsed_time": "7:31:03", "remaining_time": "12:16:32"}
+{"current_steps": 80, "total_steps": 208, "loss": 0.4715, "lr": 1.5476881738986037e-05, "epoch": 0.7673860911270983, "percentage": 38.46, "elapsed_time": "7:36:51", "remaining_time": "12:10:57"}
+{"current_steps": 81, "total_steps": 208, "loss": 0.425, "lr": 1.5335553137992286e-05, "epoch": 0.7769784172661871, "percentage": 38.94, "elapsed_time": "7:41:55", "remaining_time": "12:04:15"}
+{"current_steps": 82, "total_steps": 208, "loss": 0.4441, "lr": 1.519271867294203e-05, "epoch": 0.7865707434052758, "percentage": 39.42, "elapsed_time": "7:48:14", "remaining_time": "11:59:29"}
+{"current_steps": 83, "total_steps": 208, "loss": 0.4902, "lr": 1.504841865629799e-05, "epoch": 0.7961630695443646, "percentage": 39.9, "elapsed_time": "7:54:19", "remaining_time": "11:54:20"}
+{"current_steps": 84, "total_steps": 208, "loss": 0.4918, "lr": 1.490269381414849e-05, "epoch": 0.8057553956834532, "percentage": 40.38, "elapsed_time": "8:00:03", "remaining_time": "11:48:38"}
+{"current_steps": 85, "total_steps": 208, "loss": 0.4449, "lr": 1.4755585274713289e-05, "epoch": 0.815347721822542, "percentage": 40.87, "elapsed_time": "8:06:03", "remaining_time": "11:43:21"}
+{"current_steps": 86, "total_steps": 208, "loss": 0.4239, "lr": 1.4607134556735836e-05, "epoch": 0.8249400479616307, "percentage": 41.35, "elapsed_time": "8:10:57", "remaining_time": "11:36:27"}
+{"current_steps": 87, "total_steps": 208, "loss": 0.4795, "lr": 1.4457383557765385e-05, "epoch": 0.8345323741007195, "percentage": 41.83, "elapsed_time": "8:16:42", "remaining_time": "11:30:49"}
+{"current_steps": 88, "total_steps": 208, "loss": 0.459, "lr": 1.4306374542332141e-05, "epoch": 0.8441247002398081, "percentage": 42.31, "elapsed_time": "8:21:55", "remaining_time": "11:24:26"}
+{"current_steps": 89, "total_steps": 208, "loss": 0.4471, "lr": 1.4154150130018867e-05, "epoch": 0.8537170263788969, "percentage": 42.79, "elapsed_time": "8:27:16", "remaining_time": "11:18:16"}
+{"current_steps": 90, "total_steps": 208, "loss": 0.4765, "lr": 1.4000753283432267e-05, "epoch": 0.8633093525179856, "percentage": 43.27, "elapsed_time": "8:33:15", "remaining_time": "11:12:56"}
+{"current_steps": 91, "total_steps": 208, "loss": 0.464, "lr": 1.3846227296077568e-05, "epoch": 0.8729016786570744, "percentage": 43.75, "elapsed_time": "8:38:55", "remaining_time": "11:07:11"}
+{"current_steps": 92, "total_steps": 208, "loss": 0.4371, "lr": 1.3690615780139703e-05, "epoch": 0.882494004796163, "percentage": 44.23, "elapsed_time": "8:44:11", "remaining_time": "11:00:56"}
+{"current_steps": 93, "total_steps": 208, "loss": 0.4609, "lr": 1.3533962654174542e-05, "epoch": 0.8920863309352518, "percentage": 44.71, "elapsed_time": "8:50:10", "remaining_time": "10:55:35"}
+{"current_steps": 94, "total_steps": 208, "loss": 0.4466, "lr": 1.337631213071369e-05, "epoch": 0.9016786570743405, "percentage": 45.19, "elapsed_time": "8:55:51", "remaining_time": "10:49:52"}
+{"current_steps": 95, "total_steps": 208, "loss": 0.4531, "lr": 1.321770870378628e-05, "epoch": 0.9112709832134293, "percentage": 45.67, "elapsed_time": "9:01:34", "remaining_time": "10:44:10"}
+{"current_steps": 96, "total_steps": 208, "loss": 0.4522, "lr": 1.3058197136361344e-05, "epoch": 0.920863309352518, "percentage": 46.15, "elapsed_time": "9:07:35", "remaining_time": "10:38:51"}
+{"current_steps": 97, "total_steps": 208, "loss": 0.4605, "lr": 1.2897822447714247e-05, "epoch": 0.9304556354916067, "percentage": 46.63, "elapsed_time": "9:12:46", "remaining_time": "10:32:33"}
+{"current_steps": 98, "total_steps": 208, "loss": 0.4389, "lr": 1.2736629900720832e-05, "epoch": 0.9400479616306955, "percentage": 47.12, "elapsed_time": "9:18:37", "remaining_time": "10:27:01"}
+{"current_steps": 99, "total_steps": 208, "loss": 0.4509, "lr": 1.257466498908276e-05, "epoch": 0.9496402877697842, "percentage": 47.6, "elapsed_time": "9:24:13", "remaining_time": "10:21:12"}
+{"current_steps": 100, "total_steps": 208, "loss": 0.4728, "lr": 1.2411973424487751e-05, "epoch": 0.9592326139088729, "percentage": 48.08, "elapsed_time": "9:29:15", "remaining_time": "10:14:48"}
+{"current_steps": 101, "total_steps": 208, "loss": 0.4602, "lr": 1.2248601123708279e-05, "epoch": 0.9688249400479616, "percentage": 48.56, "elapsed_time": "9:39:18", "remaining_time": "10:13:42"}
+{"current_steps": 102, "total_steps": 208, "loss": 0.4558, "lr": 1.2084594195642367e-05, "epoch": 0.9784172661870504, "percentage": 49.04, "elapsed_time": "9:45:33", "remaining_time": "10:08:30"}
+{"current_steps": 103, "total_steps": 208, "loss": 0.4542, "lr": 1.1919998928300203e-05, "epoch": 0.988009592326139, "percentage": 49.52, "elapsed_time": "9:51:42", "remaining_time": "10:03:11"}
+{"current_steps": 104, "total_steps": 208, "loss": 0.4797, "lr": 1.1754861775740163e-05, "epoch": 0.9976019184652278, "percentage": 50.0, "elapsed_time": "9:57:37", "remaining_time": "9:57:37"}
+{"current_steps": 105, "total_steps": 208, "loss": 0.7123, "lr": 1.1589229344958e-05, "epoch": 1.0071942446043165, "percentage": 50.48, "elapsed_time": "10:03:08", "remaining_time": "9:51:38"}
+{"current_steps": 106, "total_steps": 208, "loss": 0.3439, "lr": 1.1423148382732854e-05, "epoch": 1.0167865707434052, "percentage": 50.96, "elapsed_time": "10:08:04", "remaining_time": "9:45:08"}
+{"current_steps": 107, "total_steps": 208, "loss": 0.3908, "lr": 1.1256665762433798e-05, "epoch": 1.026378896882494, "percentage": 51.44, "elapsed_time": "10:13:15", "remaining_time": "9:38:52"}
+{"current_steps": 108, "total_steps": 208, "loss": 0.3997, "lr": 1.1089828470790694e-05, "epoch": 1.0359712230215827, "percentage": 51.92, "elapsed_time": "10:18:24", "remaining_time": "9:32:35"}
+{"current_steps": 109, "total_steps": 208, "loss": 0.4586, "lr": 1.092268359463302e-05, "epoch": 1.0455635491606714, "percentage": 52.4, "elapsed_time": "10:23:59", "remaining_time": "9:26:44"}
+{"current_steps": 110, "total_steps": 208, "loss": 0.4046, "lr": 1.0755278307600459e-05, "epoch": 1.0551558752997603, "percentage": 52.88, "elapsed_time": "10:29:35", "remaining_time": "9:20:54"}
+{"current_steps": 111, "total_steps": 208, "loss": 0.374, "lr": 1.058765985682898e-05, "epoch": 1.064748201438849, "percentage": 53.37, "elapsed_time": "10:35:05", "remaining_time": "9:14:59"}
+{"current_steps": 112, "total_steps": 208, "loss": 0.3692, "lr": 1.0419875549616196e-05, "epoch": 1.0743405275779376, "percentage": 53.85, "elapsed_time": "10:40:48", "remaining_time": "9:09:16"}
+{"current_steps": 113, "total_steps": 208, "loss": 0.4327, "lr": 1.0251972740069724e-05, "epoch": 1.0839328537170263, "percentage": 54.33, "elapsed_time": "10:47:13", "remaining_time": "9:04:07"}
+{"current_steps": 114, "total_steps": 208, "loss": 0.3766, "lr": 1.0083998815742335e-05, "epoch": 1.0935251798561152, "percentage": 54.81, "elapsed_time": "10:52:54", "remaining_time": "8:58:22"}
+{"current_steps": 115, "total_steps": 208, "loss": 0.3503, "lr": 9.916001184257668e-06, "epoch": 1.1031175059952039, "percentage": 55.29, "elapsed_time": "10:57:17", "remaining_time": "8:51:32"}
+{"current_steps": 116, "total_steps": 208, "loss": 0.4089, "lr": 9.748027259930276e-06, "epoch": 1.1127098321342925, "percentage": 55.77, "elapsed_time": "11:03:18", "remaining_time": "8:46:04"}
+{"current_steps": 117, "total_steps": 208, "loss": 0.4489, "lr": 9.580124450383804e-06, "epoch": 1.1223021582733812, "percentage": 56.25, "elapsed_time": "11:09:45", "remaining_time": "8:40:55"}
+{"current_steps": 118, "total_steps": 208, "loss": 0.3736, "lr": 9.412340143171025e-06, "epoch": 1.13189448441247, "percentage": 56.73, "elapsed_time": "11:14:51", "remaining_time": "8:34:43"}
+{"current_steps": 119, "total_steps": 208, "loss": 0.3961, "lr": 9.244721692399545e-06, "epoch": 1.1414868105515588, "percentage": 57.21, "elapsed_time": "11:20:46", "remaining_time": "8:29:09"}
+{"current_steps": 120, "total_steps": 208, "loss": 0.3863, "lr": 9.07731640536698e-06, "epoch": 1.1510791366906474, "percentage": 57.69, "elapsed_time": "11:26:02", "remaining_time": "8:23:06"}
+{"current_steps": 121, "total_steps": 208, "loss": 0.3797, "lr": 8.910171529209306e-06, "epoch": 1.160671462829736, "percentage": 58.17, "elapsed_time": "11:31:42", "remaining_time": "8:17:20"}
+{"current_steps": 122, "total_steps": 208, "loss": 0.4264, "lr": 8.743334237566202e-06, "epoch": 1.170263788968825, "percentage": 58.65, "elapsed_time": "11:36:51", "remaining_time": "8:11:13"}
+{"current_steps": 123, "total_steps": 208, "loss": 0.388, "lr": 8.576851617267151e-06, "epoch": 1.1798561151079137, "percentage": 59.13, "elapsed_time": "11:42:38", "remaining_time": "8:05:34"}
+{"current_steps": 124, "total_steps": 208, "loss": 0.3899, "lr": 8.410770655042003e-06, "epoch": 1.1894484412470023, "percentage": 59.62, "elapsed_time": "11:47:52", "remaining_time": "7:59:31"}
+{"current_steps": 125, "total_steps": 208, "loss": 0.431, "lr": 8.24513822425984e-06, "epoch": 1.1990407673860912, "percentage": 60.1, "elapsed_time": "11:53:53", "remaining_time": "7:54:01"}
+{"current_steps": 126, "total_steps": 208, "loss": 0.383, "lr": 8.0800010716998e-06, "epoch": 1.20863309352518, "percentage": 60.58, "elapsed_time": "11:59:58", "remaining_time": "7:48:33"}
+{"current_steps": 127, "total_steps": 208, "loss": 0.3746, "lr": 7.915405804357632e-06, "epoch": 1.2182254196642686, "percentage": 61.06, "elapsed_time": "12:05:25", "remaining_time": "7:42:40"}
+{"current_steps": 128, "total_steps": 208, "loss": 0.3792, "lr": 7.751398876291725e-06, "epoch": 1.2278177458033572, "percentage": 61.54, "elapsed_time": "12:10:29", "remaining_time": "7:36:33"}
+{"current_steps": 129, "total_steps": 208, "loss": 0.4404, "lr": 7.58802657551225e-06, "epoch": 1.2374100719424461, "percentage": 62.02, "elapsed_time": "12:16:33", "remaining_time": "7:31:04"}
+{"current_steps": 130, "total_steps": 208, "loss": 0.3757, "lr": 7.425335010917244e-06, "epoch": 1.2470023980815348, "percentage": 62.5, "elapsed_time": "12:22:36", "remaining_time": "7:25:33"}
+{"current_steps": 131, "total_steps": 208, "loss": 0.474, "lr": 7.263370099279173e-06, "epoch": 1.2565947242206235, "percentage": 62.98, "elapsed_time": "12:29:20", "remaining_time": "7:20:27"}
+{"current_steps": 132, "total_steps": 208, "loss": 0.3462, "lr": 7.102177552285753e-06, "epoch": 1.2661870503597124, "percentage": 63.46, "elapsed_time": "12:34:02", "remaining_time": "7:14:08"}
+{"current_steps": 133, "total_steps": 208, "loss": 0.3856, "lr": 6.9418028636386595e-06, "epoch": 1.275779376498801, "percentage": 63.94, "elapsed_time": "12:39:01", "remaining_time": "7:08:01"}
+{"current_steps": 134, "total_steps": 208, "loss": 0.3923, "lr": 6.7822912962137225e-06, "epoch": 1.2853717026378897, "percentage": 64.42, "elapsed_time": "12:44:50", "remaining_time": "7:02:22"}
+{"current_steps": 135, "total_steps": 208, "loss": 0.4054, "lr": 6.623687869286314e-06, "epoch": 1.2949640287769784, "percentage": 64.9, "elapsed_time": "12:50:42", "remaining_time": "6:56:44"}
+{"current_steps": 136, "total_steps": 208, "loss": 0.3854, "lr": 6.466037345825462e-06, "epoch": 1.304556354916067, "percentage": 65.38, "elapsed_time": "12:56:36", "remaining_time": "6:51:08"}
+{"current_steps": 137, "total_steps": 208, "loss": 0.3847, "lr": 6.3093842198603014e-06, "epoch": 1.314148681055156, "percentage": 65.87, "elapsed_time": "13:02:23", "remaining_time": "6:45:28"}
+{"current_steps": 138, "total_steps": 208, "loss": 0.3721, "lr": 6.153772703922434e-06, "epoch": 1.3237410071942446, "percentage": 66.35, "elapsed_time": "13:07:13", "remaining_time": "6:39:19"}
+{"current_steps": 139, "total_steps": 208, "loss": 0.3854, "lr": 5.999246716567737e-06, "epoch": 1.3333333333333333, "percentage": 66.83, "elapsed_time": "13:13:08", "remaining_time": "6:33:43"}
+{"current_steps": 140, "total_steps": 208, "loss": 0.3819, "lr": 5.845849869981137e-06, "epoch": 1.3429256594724222, "percentage": 67.31, "elapsed_time": "13:18:30", "remaining_time": "6:27:50"}
+{"current_steps": 141, "total_steps": 208, "loss": 0.3562, "lr": 5.693625457667862e-06, "epoch": 1.3525179856115108, "percentage": 67.79, "elapsed_time": "13:23:41", "remaining_time": "6:21:53"}
+{"current_steps": 142, "total_steps": 208, "loss": 0.4148, "lr": 5.542616442234618e-06, "epoch": 1.3621103117505995, "percentage": 68.27, "elapsed_time": "13:29:51", "remaining_time": "6:16:24"}
+{"current_steps": 143, "total_steps": 208, "loss": 0.4044, "lr": 5.392865443264164e-06, "epoch": 1.3717026378896882, "percentage": 68.75, "elapsed_time": "13:35:36", "remaining_time": "6:10:44"}
+{"current_steps": 144, "total_steps": 208, "loss": 0.404, "lr": 5.244414725286717e-06, "epoch": 1.381294964028777, "percentage": 69.23, "elapsed_time": "13:41:42", "remaining_time": "6:05:12"}
+{"current_steps": 145, "total_steps": 208, "loss": 0.405, "lr": 5.097306185851515e-06, "epoch": 1.3908872901678657, "percentage": 69.71, "elapsed_time": "13:47:36", "remaining_time": "5:59:34"}
+{"current_steps": 146, "total_steps": 208, "loss": 0.3787, "lr": 4.951581343702014e-06, "epoch": 1.4004796163069544, "percentage": 70.19, "elapsed_time": "13:53:37", "remaining_time": "5:54:00"}
+{"current_steps": 147, "total_steps": 208, "loss": 0.3969, "lr": 4.807281327057972e-06, "epoch": 1.4100719424460433, "percentage": 70.67, "elapsed_time": "13:59:26", "remaining_time": "5:48:20"}
+{"current_steps": 148, "total_steps": 208, "loss": 0.3686, "lr": 4.664446862007718e-06, "epoch": 1.419664268585132, "percentage": 71.15, "elapsed_time": "14:05:17", "remaining_time": "5:42:40"}
+{"current_steps": 149, "total_steps": 208, "loss": 0.4435, "lr": 4.523118261013969e-06, "epoch": 1.4292565947242206, "percentage": 71.63, "elapsed_time": "14:10:43", "remaining_time": "5:36:51"}
+{"current_steps": 150, "total_steps": 208, "loss": 0.3731, "lr": 4.383335411536357e-06, "epoch": 1.4388489208633093, "percentage": 72.12, "elapsed_time": "14:15:48", "remaining_time": "5:30:54"}
+{"current_steps": 151, "total_steps": 208, "loss": 0.3882, "lr": 4.245137764773899e-06, "epoch": 1.448441247002398, "percentage": 72.6, "elapsed_time": "14:21:26", "remaining_time": "5:25:10"}
+{"current_steps": 152, "total_steps": 208, "loss": 0.3697, "lr": 4.108564324530626e-06, "epoch": 1.4580335731414868, "percentage": 73.08, "elapsed_time": "14:26:51", "remaining_time": "5:19:22"}
+{"current_steps": 153, "total_steps": 208, "loss": 0.4264, "lr": 3.973653636207437e-06, "epoch": 1.4676258992805755, "percentage": 73.56, "elapsed_time": "14:32:48", "remaining_time": "5:13:45"}
+{"current_steps": 154, "total_steps": 208, "loss": 0.3594, "lr": 3.840443775923365e-06, "epoch": 1.4772182254196642, "percentage": 74.04, "elapsed_time": "14:38:24", "remaining_time": "5:08:00"}
+{"current_steps": 155, "total_steps": 208, "loss": 0.3914, "lr": 3.70897233976927e-06, "epoch": 1.486810551558753, "percentage": 74.52, "elapsed_time": "14:43:41", "remaining_time": "5:02:10"}
+{"current_steps": 156, "total_steps": 208, "loss": 0.3922, "lr": 3.5792764331970187e-06, "epoch": 1.4964028776978417, "percentage": 75.0, "elapsed_time": "14:49:57", "remaining_time": "4:56:39"}
+{"current_steps": 157, "total_steps": 208, "loss": 0.3665, "lr": 3.4513926605471504e-06, "epoch": 1.5059952038369304, "percentage": 75.48, "elapsed_time": "14:54:41", "remaining_time": "4:50:37"}
+{"current_steps": 158, "total_steps": 208, "loss": 0.3381, "lr": 3.3253571147179333e-06, "epoch": 1.515587529976019, "percentage": 75.96, "elapsed_time": "15:00:56", "remaining_time": "4:45:06"}
+{"current_steps": 159, "total_steps": 208, "loss": 0.4613, "lr": 3.2012053669788136e-06, "epoch": 1.5251798561151078, "percentage": 76.44, "elapsed_time": "15:07:17", "remaining_time": "4:39:36"}
+{"current_steps": 160, "total_steps": 208, "loss": 0.4428, "lr": 3.0789724569310532e-06, "epoch": 1.5347721822541966, "percentage": 76.92, "elapsed_time": "15:14:08", "remaining_time": "4:34:14"}
+{"current_steps": 161, "total_steps": 208, "loss": 0.3357, "lr": 2.9586928826184323e-06, "epoch": 1.5443645083932853, "percentage": 77.4, "elapsed_time": "15:19:59", "remaining_time": "4:28:34"}
+{"current_steps": 162, "total_steps": 208, "loss": 0.4203, "lr": 2.8404005907908083e-06, "epoch": 1.5539568345323742, "percentage": 77.88, "elapsed_time": "15:26:32", "remaining_time": "4:23:05"}
+{"current_steps": 163, "total_steps": 208, "loss": 0.3881, "lr": 2.724128967323234e-06, "epoch": 1.5635491606714629, "percentage": 78.37, "elapsed_time": "15:32:09", "remaining_time": "4:17:20"}
+{"current_steps": 164, "total_steps": 208, "loss": 0.4334, "lr": 2.6099108277934105e-06, "epoch": 1.5731414868105515, "percentage": 78.85, "elapsed_time": "15:39:02", "remaining_time": "4:11:56"}
+{"current_steps": 165, "total_steps": 208, "loss": 0.3885, "lr": 2.4977784082200728e-06, "epoch": 1.5827338129496402, "percentage": 79.33, "elapsed_time": "15:44:41", "remaining_time": "4:06:11"}
+{"current_steps": 166, "total_steps": 208, "loss": 0.3901, "lr": 2.3877633559649505e-06, "epoch": 1.5923261390887289, "percentage": 79.81, "elapsed_time": "15:50:11", "remaining_time": "4:00:24"}
+{"current_steps": 167, "total_steps": 208, "loss": 0.3769, "lr": 2.2798967208008806e-06, "epoch": 1.6019184652278178, "percentage": 80.29, "elapsed_time": "15:55:06", "remaining_time": "3:54:29"}
+{"current_steps": 168, "total_steps": 208, "loss": 0.404, "lr": 2.1742089461485504e-06, "epoch": 1.6115107913669064, "percentage": 80.77, "elapsed_time": "16:00:19", "remaining_time": "3:48:38"}
+{"current_steps": 169, "total_steps": 208, "loss": 0.3879, "lr": 2.0707298604843964e-06, "epoch": 1.6211031175059953, "percentage": 81.25, "elapsed_time": "16:06:31", "remaining_time": "3:43:02"}
+{"current_steps": 170, "total_steps": 208, "loss": 0.3728, "lr": 1.9694886689220592e-06, "epoch": 1.630695443645084, "percentage": 81.73, "elapsed_time": "16:11:45", "remaining_time": "3:37:12"}
+{"current_steps": 171, "total_steps": 208, "loss": 0.4245, "lr": 1.870513944969743e-06, "epoch": 1.6402877697841727, "percentage": 82.21, "elapsed_time": "16:18:06", "remaining_time": "3:31:38"}
+{"current_steps": 172, "total_steps": 208, "loss": 0.3685, "lr": 1.773833622465888e-06, "epoch": 1.6498800959232613, "percentage": 82.69, "elapsed_time": "16:23:06", "remaining_time": "3:25:45"}
+{"current_steps": 173, "total_steps": 208, "loss": 0.385, "lr": 1.6794749876953187e-06, "epoch": 1.65947242206235, "percentage": 83.17, "elapsed_time": "16:28:45", "remaining_time": "3:20:02"}
+{"current_steps": 174, "total_steps": 208, "loss": 0.4342, "lr": 1.587464671688187e-06, "epoch": 1.6690647482014387, "percentage": 83.65, "elapsed_time": "16:34:38", "remaining_time": "3:14:21"}
+{"current_steps": 175, "total_steps": 208, "loss": 0.3845, "lr": 1.4978286427038602e-06, "epoch": 1.6786570743405276, "percentage": 84.13, "elapsed_time": "16:39:39", "remaining_time": "3:08:30"}
+{"current_steps": 176, "total_steps": 208, "loss": 0.3671, "lr": 1.4105921989018112e-06, "epoch": 1.6882494004796165, "percentage": 84.62, "elapsed_time": "16:45:19", "remaining_time": "3:02:47"}
+{"current_steps": 177, "total_steps": 208, "loss": 0.4138, "lr": 1.325779961201703e-06, "epoch": 1.6978417266187051, "percentage": 85.1, "elapsed_time": "16:51:04", "remaining_time": "2:57:04"}
+{"current_steps": 178, "total_steps": 208, "loss": 0.3297, "lr": 1.2434158663345553e-06, "epoch": 1.7074340527577938, "percentage": 85.58, "elapsed_time": "16:57:05", "remaining_time": "2:51:25"}
+{"current_steps": 179, "total_steps": 208, "loss": 0.4104, "lr": 1.1635231600870334e-06, "epoch": 1.7170263788968825, "percentage": 86.06, "elapsed_time": "17:02:08", "remaining_time": "2:45:35"}
+{"current_steps": 180, "total_steps": 208, "loss": 0.3553, "lr": 1.086124390740757e-06, "epoch": 1.7266187050359711, "percentage": 86.54, "elapsed_time": "17:07:45", "remaining_time": "2:39:52"}
+{"current_steps": 181, "total_steps": 208, "loss": 0.3862, "lr": 1.0112414027084262e-06, "epoch": 1.7362110311750598, "percentage": 87.02, "elapsed_time": "17:12:38", "remaining_time": "2:34:02"}
+{"current_steps": 182, "total_steps": 208, "loss": 0.4316, "lr": 9.388953303686587e-07, "epoch": 1.7458033573141487, "percentage": 87.5, "elapsed_time": "17:18:42", "remaining_time": "2:28:23"}
+{"current_steps": 183, "total_steps": 208, "loss": 0.3422, "lr": 8.691065921011687e-07, "epoch": 1.7553956834532374, "percentage": 87.98, "elapsed_time": "17:24:16", "remaining_time": "2:22:39"}
+{"current_steps": 184, "total_steps": 208, "loss": 0.3584, "lr": 8.018948845240538e-07, "epoch": 1.7649880095923263, "percentage": 88.46, "elapsed_time": "17:29:58", "remaining_time": "2:16:57"}
+{"current_steps": 185, "total_steps": 208, "loss": 0.4099, "lr": 7.372791769347843e-07, "epoch": 1.774580335731415, "percentage": 88.94, "elapsed_time": "17:35:23", "remaining_time": "2:11:12"}
+{"current_steps": 186, "total_steps": 208, "loss": 0.3968, "lr": 6.752777059564431e-07, "epoch": 1.7841726618705036, "percentage": 89.42, "elapsed_time": "17:41:20", "remaining_time": "2:05:32"}
+{"current_steps": 187, "total_steps": 208, "loss": 0.34, "lr": 6.159079703907823e-07, "epoch": 1.7937649880095923, "percentage": 89.9, "elapsed_time": "17:47:33", "remaining_time": "1:59:53"}
+{"current_steps": 188, "total_steps": 208, "loss": 0.3729, "lr": 5.591867262794969e-07, "epoch": 1.803357314148681, "percentage": 90.38, "elapsed_time": "17:52:29", "remaining_time": "1:54:05"}
+{"current_steps": 189, "total_steps": 208, "loss": 0.3928, "lr": 5.051299821751254e-07, "epoch": 1.8129496402877698, "percentage": 90.87, "elapsed_time": "17:58:32", "remaining_time": "1:48:25"}
+{"current_steps": 190, "total_steps": 208, "loss": 0.3818, "lr": 4.537529946229369e-07, "epoch": 1.8225419664268585, "percentage": 91.35, "elapsed_time": "18:04:03", "remaining_time": "1:42:42"}
+{"current_steps": 191, "total_steps": 208, "loss": 0.3448, "lr": 4.0507026385502747e-07, "epoch": 1.8321342925659474, "percentage": 91.83, "elapsed_time": "18:09:16", "remaining_time": "1:36:57"}
+{"current_steps": 192, "total_steps": 208, "loss": 0.4311, "lr": 3.5909552969790376e-07, "epoch": 1.841726618705036, "percentage": 92.31, "elapsed_time": "18:15:06", "remaining_time": "1:31:15"}
+{"current_steps": 193, "total_steps": 208, "loss": 0.3701, "lr": 3.158417676946635e-07, "epoch": 1.8513189448441247, "percentage": 92.79, "elapsed_time": "18:20:56", "remaining_time": "1:25:33"}
+{"current_steps": 194, "total_steps": 208, "loss": 0.3833, "lr": 2.753211854428728e-07, "epoch": 1.8609112709832134, "percentage": 93.27, "elapsed_time": "18:26:26", "remaining_time": "1:19:50"}
+{"current_steps": 195, "total_steps": 208, "loss": 0.4594, "lr": 2.375452191491967e-07, "epoch": 1.870503597122302, "percentage": 93.75, "elapsed_time": "18:33:20", "remaining_time": "1:14:13"}
+{"current_steps": 196, "total_steps": 208, "loss": 0.3805, "lr": 2.0252453040173646e-07, "epoch": 1.8800959232613907, "percentage": 94.23, "elapsed_time": "18:39:38", "remaining_time": "1:08:32"}
+{"current_steps": 197, "total_steps": 208, "loss": 0.3504, "lr": 1.7026900316098217e-07, "epoch": 1.8896882494004796, "percentage": 94.71, "elapsed_time": "18:44:31", "remaining_time": "1:02:47"}
+{"current_steps": 198, "total_steps": 208, "loss": 0.3396, "lr": 1.407877409702496e-07, "epoch": 1.8992805755395683, "percentage": 95.19, "elapsed_time": "18:49:12", "remaining_time": "0:57:01"}
+{"current_steps": 199, "total_steps": 208, "loss": 0.4681, "lr": 1.1408906438636236e-07, "epoch": 1.9088729016786572, "percentage": 95.67, "elapsed_time": "18:55:15", "remaining_time": "0:51:20"}
+{"current_steps": 200, "total_steps": 208, "loss": 0.3943, "lr": 9.018050863132566e-08, "epoch": 1.9184652278177459, "percentage": 96.15, "elapsed_time": "19:00:52", "remaining_time": "0:45:38"}
+{"current_steps": 201, "total_steps": 208, "loss": 0.3736, "lr": 6.906882146565097e-08, "epoch": 1.9280575539568345, "percentage": 96.63, "elapsed_time": "19:11:41", "remaining_time": "0:40:06"}
+{"current_steps": 202, "total_steps": 208, "loss": 0.4146, "lr": 5.0759961283911584e-08, "epoch": 1.9376498800959232, "percentage": 97.12, "elapsed_time": "19:17:38", "remaining_time": "0:34:23"}
+{"current_steps": 203, "total_steps": 208, "loss": 0.3537, "lr": 3.525909543310002e-08, "epoch": 1.9472422062350119, "percentage": 97.6, "elapsed_time": "19:22:32", "remaining_time": "0:28:38"}
+{"current_steps": 204, "total_steps": 208, "loss": 0.3812, "lr": 2.257059875423795e-08, "epoch": 1.9568345323741008, "percentage": 98.08, "elapsed_time": "19:29:11", "remaining_time": "0:22:55"}
+{"current_steps": 205, "total_steps": 208, "loss": 0.3976, "lr": 1.2698052347649426e-08, "epoch": 1.9664268585131894, "percentage": 98.56, "elapsed_time": "19:35:16", "remaining_time": "0:17:11"}
+{"current_steps": 206, "total_steps": 208, "loss": 0.3976, "lr": 5.644242562264923e-09, "epoch": 1.9760191846522783, "percentage": 99.04, "elapsed_time": "19:41:21", "remaining_time": "0:11:28"}
+{"current_steps": 207, "total_steps": 208, "loss": 0.3929, "lr": 1.4111602092226062e-09, "epoch": 1.985611510791367, "percentage": 99.52, "elapsed_time": "19:48:25", "remaining_time": "0:05:44"}
+{"current_steps": 208, "total_steps": 208, "loss": 0.4285, "lr": 0.0, "epoch": 1.9952038369304557, "percentage": 100.0, "elapsed_time": "19:54:37", "remaining_time": "0:00:00"}
+{"current_steps": 208, "total_steps": 208, "epoch": 1.9952038369304557, "percentage": 100.0, "elapsed_time": "19:59:52", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1498 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9952038369304557,
+  "eval_steps": 500,
+  "global_step": 208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009592326139088728,
+      "grad_norm": 2.6591761112213135,
+      "learning_rate": 9.523809523809525e-07,
+      "loss": 0.7408,
+      "step": 1
+    },
+    {
+      "epoch": 0.019184652278177457,
+      "grad_norm": 2.5914506912231445,
+      "learning_rate": 1.904761904761905e-06,
+      "loss": 0.7838,
+      "step": 2
+    },
+    {
+      "epoch": 0.02877697841726619,
+      "grad_norm": 2.4312615394592285,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.7863,
+      "step": 3
+    },
+    {
+      "epoch": 0.03836930455635491,
+      "grad_norm": 2.2820498943328857,
+      "learning_rate": 3.80952380952381e-06,
+      "loss": 0.775,
+      "step": 4
+    },
+    {
+      "epoch": 0.047961630695443645,
+      "grad_norm": 1.923662543296814,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.7394,
+      "step": 5
+    },
+    {
+      "epoch": 0.05755395683453238,
+      "grad_norm": 1.4304736852645874,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.7485,
+      "step": 6
+    },
+    {
+      "epoch": 0.0671462829736211,
+      "grad_norm": 1.3127758502960205,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.7022,
+      "step": 7
+    },
+    {
+      "epoch": 0.07673860911270983,
+      "grad_norm": 1.3539044857025146,
+      "learning_rate": 7.61904761904762e-06,
+      "loss": 0.6913,
+      "step": 8
+    },
+    {
+      "epoch": 0.08633093525179857,
+      "grad_norm": 1.3196394443511963,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.7041,
+      "step": 9
+    },
+    {
+      "epoch": 0.09592326139088729,
+      "grad_norm": 1.1037274599075317,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.6186,
+      "step": 10
+    },
+    {
+      "epoch": 0.10551558752997602,
+      "grad_norm": 1.3987900018692017,
+      "learning_rate": 1.0476190476190477e-05,
+      "loss": 0.6306,
+      "step": 11
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 0.9192888736724854,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.6073,
+      "step": 12
+    },
+    {
+      "epoch": 0.12470023980815348,
+      "grad_norm": 0.7664029002189636,
+      "learning_rate": 1.2380952380952383e-05,
+      "loss": 0.6209,
+      "step": 13
+    },
+    {
+      "epoch": 0.1342925659472422,
+      "grad_norm": 1.2668217420578003,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.6077,
+      "step": 14
+    },
+    {
+      "epoch": 0.14388489208633093,
+      "grad_norm": 1.1923428773880005,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.5864,
+      "step": 15
+    },
+    {
+      "epoch": 0.15347721822541965,
+      "grad_norm": 0.8919103145599365,
+      "learning_rate": 1.523809523809524e-05,
+      "loss": 0.5837,
+      "step": 16
+    },
+    {
+      "epoch": 0.1630695443645084,
+      "grad_norm": 0.8827866911888123,
+      "learning_rate": 1.6190476190476193e-05,
+      "loss": 0.5701,
+      "step": 17
+    },
+    {
+      "epoch": 0.17266187050359713,
+      "grad_norm": 0.9107728600502014,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.5569,
+      "step": 18
+    },
+    {
+      "epoch": 0.18225419664268586,
+      "grad_norm": 0.8279157876968384,
+      "learning_rate": 1.8095238095238097e-05,
+      "loss": 0.5824,
+      "step": 19
+    },
+    {
+      "epoch": 0.19184652278177458,
+      "grad_norm": 0.5704746842384338,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 0.5305,
+      "step": 20
+    },
+    {
+      "epoch": 0.2014388489208633,
+      "grad_norm": 0.788601815700531,
+      "learning_rate": 2e-05,
+      "loss": 0.5451,
+      "step": 21
+    },
+    {
+      "epoch": 0.21103117505995203,
+      "grad_norm": 0.9100444912910461,
+      "learning_rate": 1.9998588839790777e-05,
+      "loss": 0.5611,
+      "step": 22
+    },
+    {
+      "epoch": 0.22062350119904076,
+      "grad_norm": 0.529228925704956,
+      "learning_rate": 1.999435575743774e-05,
+      "loss": 0.5204,
+      "step": 23
+    },
+    {
+      "epoch": 0.2302158273381295,
+      "grad_norm": 0.5239225625991821,
+      "learning_rate": 1.9987301947652354e-05,
+      "loss": 0.5459,
+      "step": 24
+    },
+    {
+      "epoch": 0.23980815347721823,
+      "grad_norm": 0.6502991914749146,
+      "learning_rate": 1.9977429401245764e-05,
+      "loss": 0.5501,
+      "step": 25
+    },
+    {
+      "epoch": 0.24940047961630696,
+      "grad_norm": 0.5559574365615845,
+      "learning_rate": 1.9964740904566903e-05,
+      "loss": 0.5219,
+      "step": 26
+    },
+    {
+      "epoch": 0.2589928057553957,
+      "grad_norm": 0.5296733379364014,
+      "learning_rate": 1.9949240038716092e-05,
+      "loss": 0.5043,
+      "step": 27
+    },
+    {
+      "epoch": 0.2685851318944844,
+      "grad_norm": 0.4866749942302704,
+      "learning_rate": 1.9930931178534353e-05,
+      "loss": 0.5106,
+      "step": 28
+    },
+    {
+      "epoch": 0.27817745803357313,
+      "grad_norm": 1.6436631679534912,
+      "learning_rate": 1.9909819491368677e-05,
+      "loss": 0.5059,
+      "step": 29
+    },
+    {
+      "epoch": 0.28776978417266186,
+      "grad_norm": 0.5561839938163757,
+      "learning_rate": 1.988591093561364e-05,
+      "loss": 0.5209,
+      "step": 30
+    },
+    {
+      "epoch": 0.2973621103117506,
+      "grad_norm": 0.4857185482978821,
+      "learning_rate": 1.985921225902975e-05,
+      "loss": 0.5173,
+      "step": 31
+    },
+    {
+      "epoch": 0.3069544364508393,
+      "grad_norm": 0.41804176568984985,
+      "learning_rate": 1.982973099683902e-05,
+      "loss": 0.4928,
+      "step": 32
+    },
+    {
+      "epoch": 0.31654676258992803,
+      "grad_norm": 0.49216267466545105,
+      "learning_rate": 1.9797475469598267e-05,
+      "loss": 0.4993,
+      "step": 33
+    },
+    {
+      "epoch": 0.3261390887290168,
+      "grad_norm": 0.4702392518520355,
+      "learning_rate": 1.9762454780850807e-05,
+      "loss": 0.4934,
+      "step": 34
+    },
+    {
+      "epoch": 0.33573141486810554,
+      "grad_norm": 0.4079640507698059,
+      "learning_rate": 1.972467881455713e-05,
+      "loss": 0.5058,
+      "step": 35
+    },
+    {
+      "epoch": 0.34532374100719426,
+      "grad_norm": 0.46476152539253235,
+      "learning_rate": 1.968415823230534e-05,
+      "loss": 0.4971,
+      "step": 36
+    },
+    {
+      "epoch": 0.354916067146283,
+      "grad_norm": 0.43748095631599426,
+      "learning_rate": 1.96409044703021e-05,
+      "loss": 0.4743,
+      "step": 37
+    },
+    {
+      "epoch": 0.3645083932853717,
+      "grad_norm": 0.46373656392097473,
+      "learning_rate": 1.9594929736144978e-05,
+      "loss": 0.5153,
+      "step": 38
+    },
+    {
+      "epoch": 0.37410071942446044,
+      "grad_norm": 0.42808473110198975,
+      "learning_rate": 1.9546247005377065e-05,
+      "loss": 0.4818,
+      "step": 39
+    },
+    {
+      "epoch": 0.38369304556354916,
+      "grad_norm": 0.4117816388607025,
+      "learning_rate": 1.9494870017824877e-05,
+      "loss": 0.4673,
+      "step": 40
+    },
+    {
+      "epoch": 0.3932853717026379,
+      "grad_norm": 0.43123477697372437,
+      "learning_rate": 1.9440813273720504e-05,
+      "loss": 0.4622,
+      "step": 41
+    },
+    {
+      "epoch": 0.4028776978417266,
+      "grad_norm": 0.36057785153388977,
+      "learning_rate": 1.938409202960922e-05,
+      "loss": 0.459,
+      "step": 42
+    },
+    {
+      "epoch": 0.41247002398081534,
+      "grad_norm": 0.3770412802696228,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 0.4919,
+      "step": 43
+    },
+    {
+      "epoch": 0.42206235011990406,
+      "grad_norm": 0.4013001620769501,
+      "learning_rate": 1.9262720823065217e-05,
+      "loss": 0.4957,
+      "step": 44
+    },
+    {
+      "epoch": 0.4316546762589928,
+      "grad_norm": 0.3589963912963867,
+      "learning_rate": 1.9198105115475946e-05,
+      "loss": 0.4775,
+      "step": 45
+    },
+    {
+      "epoch": 0.4412470023980815,
+      "grad_norm": 0.3630225658416748,
+      "learning_rate": 1.9130893407898834e-05,
+      "loss": 0.4828,
+      "step": 46
+    },
+    {
+      "epoch": 0.45083932853717024,
+      "grad_norm": 0.32825136184692383,
+      "learning_rate": 1.9061104669631343e-05,
+      "loss": 0.4686,
+      "step": 47
+    },
+    {
+      "epoch": 0.460431654676259,
+      "grad_norm": 0.34000617265701294,
+      "learning_rate": 1.8988758597291577e-05,
+      "loss": 0.4886,
+      "step": 48
+    },
+    {
+      "epoch": 0.47002398081534774,
+      "grad_norm": 0.3201892673969269,
+      "learning_rate": 1.8913875609259246e-05,
+      "loss": 0.4587,
+      "step": 49
+    },
+    {
+      "epoch": 0.47961630695443647,
+      "grad_norm": 0.3151942789554596,
+      "learning_rate": 1.8836476839912967e-05,
+      "loss": 0.4727,
+      "step": 50
+    },
+    {
+      "epoch": 0.4892086330935252,
+      "grad_norm": 0.3298013210296631,
+      "learning_rate": 1.8756584133665447e-05,
+      "loss": 0.4888,
+      "step": 51
+    },
+    {
+      "epoch": 0.4988009592326139,
+      "grad_norm": 0.3365343511104584,
+      "learning_rate": 1.86742200387983e-05,
+      "loss": 0.4842,
+      "step": 52
+    },
+    {
+      "epoch": 0.5083932853717026,
+      "grad_norm": 0.3066977560520172,
+      "learning_rate": 1.8589407801098192e-05,
+      "loss": 0.4366,
+      "step": 53
+    },
+    {
+      "epoch": 0.5179856115107914,
+      "grad_norm": 0.3741927444934845,
+      "learning_rate": 1.8502171357296144e-05,
+      "loss": 0.47,
+      "step": 54
+    },
+    {
+      "epoch": 0.5275779376498801,
+      "grad_norm": 0.32977259159088135,
+      "learning_rate": 1.8412535328311813e-05,
+      "loss": 0.4816,
+      "step": 55
+    },
+    {
+      "epoch": 0.5371702637889688,
+      "grad_norm": 0.313314288854599,
+      "learning_rate": 1.8320525012304685e-05,
+      "loss": 0.4529,
+      "step": 56
+    },
+    {
+      "epoch": 0.5467625899280576,
+      "grad_norm": 0.3619432747364044,
+      "learning_rate": 1.8226166377534113e-05,
+      "loss": 0.4583,
+      "step": 57
+    },
+    {
+      "epoch": 0.5563549160671463,
+      "grad_norm": 0.2958439886569977,
+      "learning_rate": 1.8129486055030255e-05,
+      "loss": 0.4861,
+      "step": 58
+    },
+    {
+      "epoch": 0.565947242206235,
+      "grad_norm": 0.3760446012020111,
+      "learning_rate": 1.8030511331077945e-05,
+      "loss": 0.4245,
+      "step": 59
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 0.3982815146446228,
+      "learning_rate": 1.7929270139515606e-05,
+      "loss": 0.458,
+      "step": 60
+    },
+    {
+      "epoch": 0.5851318944844125,
+      "grad_norm": 0.31815674901008606,
+      "learning_rate": 1.782579105385145e-05,
+      "loss": 0.4383,
+      "step": 61
+    },
+    {
+      "epoch": 0.5947242206235012,
+      "grad_norm": 0.3115115463733673,
+      "learning_rate": 1.772010327919912e-05,
+      "loss": 0.4809,
+      "step": 62
+    },
+    {
+      "epoch": 0.60431654676259,
+      "grad_norm": 0.3637670576572418,
+      "learning_rate": 1.761223664403505e-05,
+      "loss": 0.4685,
+      "step": 63
+    },
+    {
+      "epoch": 0.6139088729016786,
+      "grad_norm": 0.3954397141933441,
+      "learning_rate": 1.7502221591779932e-05,
+      "loss": 0.4591,
+      "step": 64
+    },
+    {
+      "epoch": 0.6235011990407674,
+      "grad_norm": 0.30222615599632263,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 0.4747,
+      "step": 65
+    },
+    {
+      "epoch": 0.6330935251798561,
+      "grad_norm": 0.3727622926235199,
+      "learning_rate": 1.727587103267677e-05,
+      "loss": 0.4706,
+      "step": 66
+    },
+    {
+      "epoch": 0.6426858513189448,
+      "grad_norm": 0.35147586464881897,
+      "learning_rate": 1.7159599409209194e-05,
+      "loss": 0.5017,
+      "step": 67
+    },
+    {
+      "epoch": 0.6522781774580336,
+      "grad_norm": 0.3155067265033722,
+      "learning_rate": 1.704130711738157e-05,
+      "loss": 0.4193,
+      "step": 68
+    },
+    {
+      "epoch": 0.6618705035971223,
+      "grad_norm": 0.328908234834671,
+      "learning_rate": 1.692102754306895e-05,
+      "loss": 0.4606,
+      "step": 69
+    },
+    {
+      "epoch": 0.6714628297362111,
+      "grad_norm": 0.3115673363208771,
+      "learning_rate": 1.6798794633021192e-05,
+      "loss": 0.4637,
+      "step": 70
+    },
+    {
+      "epoch": 0.6810551558752997,
+      "grad_norm": 0.34590572118759155,
+      "learning_rate": 1.667464288528207e-05,
+      "loss": 0.4672,
+      "step": 71
+    },
+    {
+      "epoch": 0.6906474820143885,
+      "grad_norm": 0.32452234625816345,
+      "learning_rate": 1.6548607339452853e-05,
+      "loss": 0.4525,
+      "step": 72
+    },
+    {
+      "epoch": 0.7002398081534772,
+      "grad_norm": 0.35198819637298584,
+      "learning_rate": 1.6420723566802982e-05,
+      "loss": 0.4512,
+      "step": 73
+    },
+    {
+      "epoch": 0.709832134292566,
+      "grad_norm": 0.3182852268218994,
+      "learning_rate": 1.6291027660230735e-05,
+      "loss": 0.4645,
+      "step": 74
+    },
+    {
+      "epoch": 0.7194244604316546,
+      "grad_norm": 0.34308016300201416,
+      "learning_rate": 1.6159556224076637e-05,
+      "loss": 0.4418,
+      "step": 75
+    },
+    {
+      "epoch": 0.7290167865707434,
+      "grad_norm": 0.36044055223464966,
+      "learning_rate": 1.6026346363792565e-05,
+      "loss": 0.4761,
+      "step": 76
+    },
+    {
+      "epoch": 0.7386091127098321,
+      "grad_norm": 0.3420026898384094,
+      "learning_rate": 1.5891435675469376e-05,
+      "loss": 0.4759,
+      "step": 77
+    },
+    {
+      "epoch": 0.7482014388489209,
+      "grad_norm": 0.3534936010837555,
+      "learning_rate": 1.57548622352261e-05,
+      "loss": 0.4734,
+      "step": 78
+    },
+    {
+      "epoch": 0.7577937649880095,
+      "grad_norm": 0.3484748601913452,
+      "learning_rate": 1.561666458846365e-05,
+      "loss": 0.4592,
+      "step": 79
+    },
+    {
+      "epoch": 0.7673860911270983,
+      "grad_norm": 0.32589343190193176,
+      "learning_rate": 1.5476881738986037e-05,
+      "loss": 0.4715,
+      "step": 80
+    },
+    {
+      "epoch": 0.7769784172661871,
+      "grad_norm": 0.30610567331314087,
+      "learning_rate": 1.5335553137992286e-05,
+      "loss": 0.425,
+      "step": 81
+    },
+    {
+      "epoch": 0.7865707434052758,
+      "grad_norm": 0.3320309817790985,
+      "learning_rate": 1.519271867294203e-05,
+      "loss": 0.4441,
+      "step": 82
+    },
+    {
+      "epoch": 0.7961630695443646,
+      "grad_norm": 0.31670084595680237,
+      "learning_rate": 1.504841865629799e-05,
+      "loss": 0.4902,
+      "step": 83
+    },
+    {
+      "epoch": 0.8057553956834532,
+      "grad_norm": 0.3276488184928894,
+      "learning_rate": 1.490269381414849e-05,
+      "loss": 0.4918,
+      "step": 84
+    },
+    {
+      "epoch": 0.815347721822542,
+      "grad_norm": 0.35845503211021423,
+      "learning_rate": 1.4755585274713289e-05,
+      "loss": 0.4449,
+      "step": 85
+    },
+    {
+      "epoch": 0.8249400479616307,
+      "grad_norm": 0.30946382880210876,
+      "learning_rate": 1.4607134556735836e-05,
+      "loss": 0.4239,
+      "step": 86
+    },
+    {
+      "epoch": 0.8345323741007195,
+      "grad_norm": 0.35152146220207214,
+      "learning_rate": 1.4457383557765385e-05,
+      "loss": 0.4795,
+      "step": 87
+    },
+    {
+      "epoch": 0.8441247002398081,
+      "grad_norm": 0.3176645338535309,
+      "learning_rate": 1.4306374542332141e-05,
+      "loss": 0.459,
+      "step": 88
+    },
+    {
+      "epoch": 0.8537170263788969,
+      "grad_norm": 0.31331124901771545,
+      "learning_rate": 1.4154150130018867e-05,
+      "loss": 0.4471,
+      "step": 89
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 0.32980385422706604,
+      "learning_rate": 1.4000753283432267e-05,
+      "loss": 0.4765,
+      "step": 90
+    },
+    {
+      "epoch": 0.8729016786570744,
+      "grad_norm": 0.3267308175563812,
+      "learning_rate": 1.3846227296077568e-05,
+      "loss": 0.464,
+      "step": 91
+    },
+    {
+      "epoch": 0.882494004796163,
+      "grad_norm": 0.30493155121803284,
+      "learning_rate": 1.3690615780139703e-05,
+      "loss": 0.4371,
+      "step": 92
+    },
+    {
+      "epoch": 0.8920863309352518,
+      "grad_norm": 0.28876054286956787,
+      "learning_rate": 1.3533962654174542e-05,
+      "loss": 0.4609,
+      "step": 93
+    },
+    {
+      "epoch": 0.9016786570743405,
+      "grad_norm": 0.2889139652252197,
+      "learning_rate": 1.337631213071369e-05,
+      "loss": 0.4466,
+      "step": 94
+    },
+    {
+      "epoch": 0.9112709832134293,
+      "grad_norm": 0.3536216914653778,
+      "learning_rate": 1.321770870378628e-05,
+      "loss": 0.4531,
+      "step": 95
+    },
+    {
+      "epoch": 0.920863309352518,
+      "grad_norm": 0.3439409136772156,
+      "learning_rate": 1.3058197136361344e-05,
+      "loss": 0.4522,
+      "step": 96
+    },
+    {
+      "epoch": 0.9304556354916067,
+      "grad_norm": 0.3083202540874481,
+      "learning_rate": 1.2897822447714247e-05,
+      "loss": 0.4605,
+      "step": 97
+    },
+    {
+      "epoch": 0.9400479616306955,
+      "grad_norm": 0.3410809636116028,
+      "learning_rate": 1.2736629900720832e-05,
+      "loss": 0.4389,
+      "step": 98
+    },
+    {
+      "epoch": 0.9496402877697842,
+      "grad_norm": 0.28464362025260925,
+      "learning_rate": 1.257466498908276e-05,
+      "loss": 0.4509,
+      "step": 99
+    },
+    {
+      "epoch": 0.9592326139088729,
+      "grad_norm": 0.279031366109848,
+      "learning_rate": 1.2411973424487751e-05,
+      "loss": 0.4728,
+      "step": 100
+    },
+    {
+      "epoch": 0.9688249400479616,
+      "grad_norm": 0.29481759667396545,
+      "learning_rate": 1.2248601123708279e-05,
+      "loss": 0.4602,
+      "step": 101
+    },
+    {
+      "epoch": 0.9784172661870504,
+      "grad_norm": 0.30976414680480957,
+      "learning_rate": 1.2084594195642367e-05,
+      "loss": 0.4558,
+      "step": 102
+    },
+    {
+      "epoch": 0.988009592326139,
+      "grad_norm": 0.31227511167526245,
+      "learning_rate": 1.1919998928300203e-05,
+      "loss": 0.4542,
+      "step": 103
+    },
+    {
+      "epoch": 0.9976019184652278,
+      "grad_norm": 0.30893808603286743,
+      "learning_rate": 1.1754861775740163e-05,
+      "loss": 0.4797,
+      "step": 104
+    },
+    {
+      "epoch": 1.0071942446043165,
+      "grad_norm": 0.6754066348075867,
+      "learning_rate": 1.1589229344958e-05,
+      "loss": 0.7123,
+      "step": 105
+    },
+    {
+      "epoch": 1.0167865707434052,
+      "grad_norm": 0.2993621528148651,
+      "learning_rate": 1.1423148382732854e-05,
+      "loss": 0.3439,
+      "step": 106
+    },
+    {
+      "epoch": 1.026378896882494,
+      "grad_norm": 0.37703534960746765,
+      "learning_rate": 1.1256665762433798e-05,
+      "loss": 0.3908,
+      "step": 107
+    },
+    {
+      "epoch": 1.0359712230215827,
+      "grad_norm": 0.3754074275493622,
+      "learning_rate": 1.1089828470790694e-05,
+      "loss": 0.3997,
+      "step": 108
+    },
+    {
+      "epoch": 1.0455635491606714,
+      "grad_norm": 0.3877393901348114,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 0.4586,
+      "step": 109
+    },
+    {
+      "epoch": 1.0551558752997603,
+      "grad_norm": 0.40832141041755676,
+      "learning_rate": 1.0755278307600459e-05,
+      "loss": 0.4046,
+      "step": 110
+    },
+    {
+      "epoch": 1.064748201438849,
+      "grad_norm": 0.3649183213710785,
+      "learning_rate": 1.058765985682898e-05,
+      "loss": 0.374,
+      "step": 111
+    },
+    {
+      "epoch": 1.0743405275779376,
+      "grad_norm": 0.3570377826690674,
+      "learning_rate": 1.0419875549616196e-05,
+      "loss": 0.3692,
+      "step": 112
+    },
+    {
+      "epoch": 1.0839328537170263,
+      "grad_norm": 0.4568242132663727,
+      "learning_rate": 1.0251972740069724e-05,
+      "loss": 0.4327,
+      "step": 113
+    },
+    {
+      "epoch": 1.0935251798561152,
+      "grad_norm": 0.3146553039550781,
+      "learning_rate": 1.0083998815742335e-05,
+      "loss": 0.3766,
+      "step": 114
+    },
+    {
+      "epoch": 1.1031175059952039,
+      "grad_norm": 0.29733189940452576,
+      "learning_rate": 9.916001184257668e-06,
+      "loss": 0.3503,
+      "step": 115
+    },
+    {
+      "epoch": 1.1127098321342925,
+      "grad_norm": 0.3751276433467865,
+      "learning_rate": 9.748027259930276e-06,
+      "loss": 0.4089,
+      "step": 116
+    },
+    {
+      "epoch": 1.1223021582733812,
+      "grad_norm": 0.38529419898986816,
+      "learning_rate": 9.580124450383804e-06,
+      "loss": 0.4489,
+      "step": 117
+    },
+    {
+      "epoch": 1.13189448441247,
+      "grad_norm": 0.32772964239120483,
+      "learning_rate": 9.412340143171025e-06,
+      "loss": 0.3736,
+      "step": 118
+    },
+    {
+      "epoch": 1.1414868105515588,
+      "grad_norm": 0.32223913073539734,
+      "learning_rate": 9.244721692399545e-06,
+      "loss": 0.3961,
+      "step": 119
+    },
+    {
+      "epoch": 1.1510791366906474,
+      "grad_norm": 0.3014141917228699,
+      "learning_rate": 9.07731640536698e-06,
+      "loss": 0.3863,
+      "step": 120
+    },
+    {
+      "epoch": 1.160671462829736,
+      "grad_norm": 0.3261420726776123,
+      "learning_rate": 8.910171529209306e-06,
+      "loss": 0.3797,
+      "step": 121
+    },
+    {
+      "epoch": 1.170263788968825,
+      "grad_norm": 0.30444827675819397,
+      "learning_rate": 8.743334237566202e-06,
+      "loss": 0.4264,
+      "step": 122
+    },
+    {
+      "epoch": 1.1798561151079137,
+      "grad_norm": 0.26329320669174194,
+      "learning_rate": 8.576851617267151e-06,
+      "loss": 0.388,
+      "step": 123
+    },
+    {
+      "epoch": 1.1894484412470023,
+      "grad_norm": 0.28534045815467834,
+      "learning_rate": 8.410770655042003e-06,
+      "loss": 0.3899,
+      "step": 124
+    },
+    {
+      "epoch": 1.1990407673860912,
+      "grad_norm": 0.30171987414360046,
+      "learning_rate": 8.24513822425984e-06,
+      "loss": 0.431,
+      "step": 125
+    },
+    {
+      "epoch": 1.20863309352518,
+      "grad_norm": 0.27923017740249634,
+      "learning_rate": 8.0800010716998e-06,
+      "loss": 0.383,
+      "step": 126
+    },
+    {
+      "epoch": 1.2182254196642686,
+      "grad_norm": 0.24267299473285675,
+      "learning_rate": 7.915405804357632e-06,
+      "loss": 0.3746,
+      "step": 127
+    },
+    {
+      "epoch": 1.2278177458033572,
+      "grad_norm": 0.2610694169998169,
+      "learning_rate": 7.751398876291725e-06,
+      "loss": 0.3792,
+      "step": 128
+    },
+    {
+      "epoch": 1.2374100719424461,
+      "grad_norm": 0.29287707805633545,
+      "learning_rate": 7.58802657551225e-06,
+      "loss": 0.4404,
+      "step": 129
+    },
+    {
+      "epoch": 1.2470023980815348,
+      "grad_norm": 0.33182862401008606,
+      "learning_rate": 7.425335010917244e-06,
+      "loss": 0.3757,
+      "step": 130
+    },
+    {
+      "epoch": 1.2565947242206235,
+      "grad_norm": 0.3336862325668335,
+      "learning_rate": 7.263370099279173e-06,
+      "loss": 0.474,
+      "step": 131
+    },
+    {
+      "epoch": 1.2661870503597124,
+      "grad_norm": 0.26169589161872864,
+      "learning_rate": 7.102177552285753e-06,
+      "loss": 0.3462,
+      "step": 132
+    },
+    {
+      "epoch": 1.275779376498801,
+      "grad_norm": 0.29609155654907227,
+      "learning_rate": 6.9418028636386595e-06,
+      "loss": 0.3856,
+      "step": 133
+    },
+    {
+      "epoch": 1.2853717026378897,
+      "grad_norm": 0.293792188167572,
+      "learning_rate": 6.7822912962137225e-06,
+      "loss": 0.3923,
+      "step": 134
+    },
+    {
+      "epoch": 1.2949640287769784,
+      "grad_norm": 0.2877916395664215,
+      "learning_rate": 6.623687869286314e-06,
+      "loss": 0.4054,
+      "step": 135
+    },
+    {
+      "epoch": 1.304556354916067,
+      "grad_norm": 0.26534056663513184,
+      "learning_rate": 6.466037345825462e-06,
+      "loss": 0.3854,
+      "step": 136
+    },
+    {
+      "epoch": 1.314148681055156,
+      "grad_norm": 0.2668323218822479,
+      "learning_rate": 6.3093842198603014e-06,
+      "loss": 0.3847,
+      "step": 137
+    },
+    {
+      "epoch": 1.3237410071942446,
+      "grad_norm": 0.2445860207080841,
+      "learning_rate": 6.153772703922434e-06,
+      "loss": 0.3721,
+      "step": 138
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.27340319752693176,
+      "learning_rate": 5.999246716567737e-06,
+      "loss": 0.3854,
+      "step": 139
+    },
+    {
+      "epoch": 1.3429256594724222,
+      "grad_norm": 0.2549520432949066,
+      "learning_rate": 5.845849869981137e-06,
+      "loss": 0.3819,
+      "step": 140
+    },
+    {
+      "epoch": 1.3525179856115108,
+      "grad_norm": 0.21786105632781982,
+      "learning_rate": 5.693625457667862e-06,
+      "loss": 0.3562,
+      "step": 141
+    },
+    {
+      "epoch": 1.3621103117505995,
+      "grad_norm": 0.2585865259170532,
+      "learning_rate": 5.542616442234618e-06,
+      "loss": 0.4148,
+      "step": 142
+    },
+    {
+      "epoch": 1.3717026378896882,
+      "grad_norm": 0.25335797667503357,
+      "learning_rate": 5.392865443264164e-06,
+      "loss": 0.4044,
+      "step": 143
+    },
+    {
+      "epoch": 1.381294964028777,
+      "grad_norm": 0.23658272624015808,
+      "learning_rate": 5.244414725286717e-06,
+      "loss": 0.404,
+      "step": 144
+    },
+    {
+      "epoch": 1.3908872901678657,
+      "grad_norm": 0.2405097484588623,
+      "learning_rate": 5.097306185851515e-06,
+      "loss": 0.405,
+      "step": 145
+    },
+    {
+      "epoch": 1.4004796163069544,
+      "grad_norm": 0.22226805984973907,
+      "learning_rate": 4.951581343702014e-06,
+      "loss": 0.3787,
+      "step": 146
+    },
+    {
+      "epoch": 1.4100719424460433,
+      "grad_norm": 0.2628573179244995,
+      "learning_rate": 4.807281327057972e-06,
+      "loss": 0.3969,
+      "step": 147
+    },
+    {
+      "epoch": 1.419664268585132,
+      "grad_norm": 0.2247915416955948,
+      "learning_rate": 4.664446862007718e-06,
+      "loss": 0.3686,
+      "step": 148
+    },
+    {
+      "epoch": 1.4292565947242206,
+      "grad_norm": 0.2676323652267456,
+      "learning_rate": 4.523118261013969e-06,
+      "loss": 0.4435,
+      "step": 149
+    },
+    {
+      "epoch": 1.4388489208633093,
+      "grad_norm": 0.25832346081733704,
+      "learning_rate": 4.383335411536357e-06,
+      "loss": 0.3731,
+      "step": 150
+    },
+    {
+      "epoch": 1.448441247002398,
+      "grad_norm": 0.24996225535869598,
+      "learning_rate": 4.245137764773899e-06,
+      "loss": 0.3882,
+      "step": 151
+    },
+    {
+      "epoch": 1.4580335731414868,
+      "grad_norm": 0.21546132862567902,
+      "learning_rate": 4.108564324530626e-06,
+      "loss": 0.3697,
+      "step": 152
+    },
+    {
+      "epoch": 1.4676258992805755,
+      "grad_norm": 0.25346457958221436,
+      "learning_rate": 3.973653636207437e-06,
+      "loss": 0.4264,
+      "step": 153
+    },
+    {
+      "epoch": 1.4772182254196642,
+      "grad_norm": 0.22166943550109863,
+      "learning_rate": 3.840443775923365e-06,
+      "loss": 0.3594,
+      "step": 154
+    },
+    {
+      "epoch": 1.486810551558753,
+      "grad_norm": 0.22984443604946136,
+      "learning_rate": 3.70897233976927e-06,
+      "loss": 0.3914,
+      "step": 155
+    },
+    {
+      "epoch": 1.4964028776978417,
+      "grad_norm": 0.24873270094394684,
+      "learning_rate": 3.5792764331970187e-06,
+      "loss": 0.3922,
+      "step": 156
+    },
+    {
+      "epoch": 1.5059952038369304,
+      "grad_norm": 0.23538856208324432,
+      "learning_rate": 3.4513926605471504e-06,
+      "loss": 0.3665,
+      "step": 157
+    },
+    {
+      "epoch": 1.515587529976019,
+      "grad_norm": 0.2180040031671524,
+      "learning_rate": 3.3253571147179333e-06,
+      "loss": 0.3381,
+      "step": 158
+    },
+    {
+      "epoch": 1.5251798561151078,
+      "grad_norm": 0.24928021430969238,
+      "learning_rate": 3.2012053669788136e-06,
+      "loss": 0.4613,
+      "step": 159
+    },
+    {
+      "epoch": 1.5347721822541966,
+      "grad_norm": 0.2552678883075714,
+      "learning_rate": 3.0789724569310532e-06,
+      "loss": 0.4428,
+      "step": 160
+    },
+    {
+      "epoch": 1.5443645083932853,
+      "grad_norm": 0.19574448466300964,
+      "learning_rate": 2.9586928826184323e-06,
+      "loss": 0.3357,
+      "step": 161
+    },
+    {
+      "epoch": 1.5539568345323742,
+      "grad_norm": 0.22724831104278564,
+      "learning_rate": 2.8404005907908083e-06,
+      "loss": 0.4203,
+      "step": 162
+    },
+    {
+      "epoch": 1.5635491606714629,
+      "grad_norm": 0.21780751645565033,
+      "learning_rate": 2.724128967323234e-06,
+      "loss": 0.3881,
+      "step": 163
+    },
+    {
+      "epoch": 1.5731414868105515,
+      "grad_norm": 0.24764929711818695,
+      "learning_rate": 2.6099108277934105e-06,
+      "loss": 0.4334,
+      "step": 164
+    },
+    {
+      "epoch": 1.5827338129496402,
+      "grad_norm": 0.23750008642673492,
+      "learning_rate": 2.4977784082200728e-06,
+      "loss": 0.3885,
+      "step": 165
+    },
+    {
+      "epoch": 1.5923261390887289,
+      "grad_norm": 0.24234673380851746,
+      "learning_rate": 2.3877633559649505e-06,
+      "loss": 0.3901,
+      "step": 166
+    },
+    {
+      "epoch": 1.6019184652278178,
+      "grad_norm": 0.22565028071403503,
+      "learning_rate": 2.2798967208008806e-06,
+      "loss": 0.3769,
+      "step": 167
+    },
+    {
+      "epoch": 1.6115107913669064,
+      "grad_norm": 0.2320602983236313,
+      "learning_rate": 2.1742089461485504e-06,
+      "loss": 0.404,
+      "step": 168
+    },
+    {
+      "epoch": 1.6211031175059953,
+      "grad_norm": 0.21093355119228363,
+      "learning_rate": 2.0707298604843964e-06,
+      "loss": 0.3879,
+      "step": 169
+    },
+    {
+      "epoch": 1.630695443645084,
+      "grad_norm": 0.23324111104011536,
+      "learning_rate": 1.9694886689220592e-06,
+      "loss": 0.3728,
+      "step": 170
+    },
+    {
+      "epoch": 1.6402877697841727,
+      "grad_norm": 0.23098240792751312,
+      "learning_rate": 1.870513944969743e-06,
+      "loss": 0.4245,
+      "step": 171
+    },
+    {
+      "epoch": 1.6498800959232613,
+      "grad_norm": 0.21313826739788055,
+      "learning_rate": 1.773833622465888e-06,
+      "loss": 0.3685,
+      "step": 172
+    },
+    {
+      "epoch": 1.65947242206235,
+      "grad_norm": 0.2202357053756714,
+      "learning_rate": 1.6794749876953187e-06,
+      "loss": 0.385,
+      "step": 173
+    },
+    {
+      "epoch": 1.6690647482014387,
+      "grad_norm": 0.24201858043670654,
+      "learning_rate": 1.587464671688187e-06,
+      "loss": 0.4342,
+      "step": 174
+    },
+    {
+      "epoch": 1.6786570743405276,
+      "grad_norm": 0.22546477615833282,
+      "learning_rate": 1.4978286427038602e-06,
+      "loss": 0.3845,
+      "step": 175
+    },
+    {
+      "epoch": 1.6882494004796165,
+      "grad_norm": 0.2069396823644638,
+      "learning_rate": 1.4105921989018112e-06,
+      "loss": 0.3671,
+      "step": 176
+    },
+    {
+      "epoch": 1.6978417266187051,
+      "grad_norm": 0.22818851470947266,
+      "learning_rate": 1.325779961201703e-06,
+      "loss": 0.4138,
+      "step": 177
+    },
+    {
+      "epoch": 1.7074340527577938,
+      "grad_norm": 0.1912079006433487,
+      "learning_rate": 1.2434158663345553e-06,
+      "loss": 0.3297,
+      "step": 178
+    },
+    {
+      "epoch": 1.7170263788968825,
+      "grad_norm": 0.2530308961868286,
+      "learning_rate": 1.1635231600870334e-06,
+      "loss": 0.4104,
+      "step": 179
+    },
+    {
+      "epoch": 1.7266187050359711,
+      "grad_norm": 0.21219122409820557,
+      "learning_rate": 1.086124390740757e-06,
+      "loss": 0.3553,
+      "step": 180
+    },
+    {
+      "epoch": 1.7362110311750598,
+      "grad_norm": 0.23752814531326294,
+      "learning_rate": 1.0112414027084262e-06,
+      "loss": 0.3862,
+      "step": 181
+    },
+    {
+      "epoch": 1.7458033573141487,
+      "grad_norm": 0.2403864711523056,
+      "learning_rate": 9.388953303686587e-07,
+      "loss": 0.4316,
+      "step": 182
+    },
+    {
+      "epoch": 1.7553956834532374,
+      "grad_norm": 0.20274099707603455,
+      "learning_rate": 8.691065921011687e-07,
+      "loss": 0.3422,
+      "step": 183
+    },
+    {
+      "epoch": 1.7649880095923263,
+      "grad_norm": 0.21107341349124908,
+      "learning_rate": 8.018948845240538e-07,
+      "loss": 0.3584,
+      "step": 184
+    },
+    {
+      "epoch": 1.774580335731415,
+      "grad_norm": 0.21734651923179626,
+      "learning_rate": 7.372791769347843e-07,
+      "loss": 0.4099,
+      "step": 185
+    },
+    {
+      "epoch": 1.7841726618705036,
+      "grad_norm": 0.2155366688966751,
+      "learning_rate": 6.752777059564431e-07,
+      "loss": 0.3968,
+      "step": 186
+    },
+    {
+      "epoch": 1.7937649880095923,
+      "grad_norm": 0.20627352595329285,
+      "learning_rate": 6.159079703907823e-07,
+      "loss": 0.34,
+      "step": 187
+    },
+    {
+      "epoch": 1.803357314148681,
+      "grad_norm": 0.2195385843515396,
+      "learning_rate": 5.591867262794969e-07,
+      "loss": 0.3729,
+      "step": 188
+    },
+    {
+      "epoch": 1.8129496402877698,
+      "grad_norm": 0.23355402052402496,
+      "learning_rate": 5.051299821751254e-07,
+      "loss": 0.3928,
+      "step": 189
+    },
+    {
+      "epoch": 1.8225419664268585,
+      "grad_norm": 0.22403055429458618,
+      "learning_rate": 4.537529946229369e-07,
+      "loss": 0.3818,
+      "step": 190
+    },
+    {
+      "epoch": 1.8321342925659474,
+      "grad_norm": 0.21041440963745117,
+      "learning_rate": 4.0507026385502747e-07,
+      "loss": 0.3448,
+      "step": 191
+    },
+    {
+      "epoch": 1.841726618705036,
+      "grad_norm": 0.22846421599388123,
+      "learning_rate": 3.5909552969790376e-07,
+      "loss": 0.4311,
+      "step": 192
+    },
+    {
+      "epoch": 1.8513189448441247,
+      "grad_norm": 0.22553186118602753,
+      "learning_rate": 3.158417676946635e-07,
+      "loss": 0.3701,
+      "step": 193
+    },
+    {
+      "epoch": 1.8609112709832134,
+      "grad_norm": 0.20845209062099457,
+      "learning_rate": 2.753211854428728e-07,
+      "loss": 0.3833,
+      "step": 194
+    },
+    {
+      "epoch": 1.870503597122302,
+      "grad_norm": 0.23942551016807556,
+      "learning_rate": 2.375452191491967e-07,
+      "loss": 0.4594,
+      "step": 195
+    },
+    {
+      "epoch": 1.8800959232613907,
+      "grad_norm": 0.21887589991092682,
+      "learning_rate": 2.0252453040173646e-07,
+      "loss": 0.3805,
+      "step": 196
+    },
+    {
+      "epoch": 1.8896882494004796,
+      "grad_norm": 0.21494026482105255,
+      "learning_rate": 1.7026900316098217e-07,
+      "loss": 0.3504,
+      "step": 197
+    },
+    {
+      "epoch": 1.8992805755395683,
+      "grad_norm": 0.21897700428962708,
+      "learning_rate": 1.407877409702496e-07,
+      "loss": 0.3396,
+      "step": 198
+    },
+    {
+      "epoch": 1.9088729016786572,
+      "grad_norm": 0.2428821474313736,
+      "learning_rate": 1.1408906438636236e-07,
+      "loss": 0.4681,
+      "step": 199
+    },
+    {
+      "epoch": 1.9184652278177459,
+      "grad_norm": 0.20344102382659912,
+      "learning_rate": 9.018050863132566e-08,
+      "loss": 0.3943,
+      "step": 200
+    },
+    {
+      "epoch": 1.9280575539568345,
+      "grad_norm": 0.19937625527381897,
+      "learning_rate": 6.906882146565097e-08,
+      "loss": 0.3736,
+      "step": 201
+    },
+    {
+      "epoch": 1.9376498800959232,
+      "grad_norm": 0.3866899311542511,
+      "learning_rate": 5.0759961283911584e-08,
+      "loss": 0.4146,
+      "step": 202
+    },
+    {
+      "epoch": 1.9472422062350119,
+      "grad_norm": 0.1998918056488037,
+      "learning_rate": 3.525909543310002e-08,
+      "loss": 0.3537,
+      "step": 203
+    },
+    {
+      "epoch": 1.9568345323741008,
+      "grad_norm": 0.19235286116600037,
+      "learning_rate": 2.257059875423795e-08,
+      "loss": 0.3812,
+      "step": 204
+    },
+    {
+      "epoch": 1.9664268585131894,
+      "grad_norm": 0.21340519189834595,
+      "learning_rate": 1.2698052347649426e-08,
+      "loss": 0.3976,
+      "step": 205
+    },
+    {
+      "epoch": 1.9760191846522783,
+      "grad_norm": 0.21041817963123322,
+      "learning_rate": 5.644242562264923e-09,
+      "loss": 0.3976,
+      "step": 206
+    },
+    {
+      "epoch": 1.985611510791367,
+      "grad_norm": 0.22794745862483978,
+      "learning_rate": 1.4111602092226062e-09,
+      "loss": 0.3929,
+      "step": 207
+    },
+    {
+      "epoch": 1.9952038369304557,
+      "grad_norm": 0.22788451611995697,
+      "learning_rate": 0.0,
+      "loss": 0.4285,
+      "step": 208
+    },
+    {
+      "epoch": 1.9952038369304557,
+      "step": 208,
+      "total_flos": 716120051679232.0,
+      "train_loss": 0.4522540926073606,
+      "train_runtime": 71993.7308,
+      "train_samples_per_second": 0.278,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 208,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 716120051679232.0,
+  "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 sha256:5f88a1b7a9faf483274a4d60c9dcd632df9f30e08d1ec3a62cf103795863faf3
+size 7416