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/Qwen2.5-14B-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/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-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": 1.9961919268849961,
+    "total_flos": 418179526819840.0,
+    "train_loss": 0.09776416790047916,
+    "train_runtime": 5460.3908,
+    "train_samples_per_second": 3.846,
+    "train_steps_per_second": 0.04
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-14B-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": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "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-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f447b69dcdb8359f0c756ec67cbc39e15f7bd0fe7be18eae9f074094aa812684
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c1ae0b327339f9e9ec383d4615a358c59a836aecb09659ec7cd7b6ba8777f5
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10049e86938e72aabdff0a311d04496e565168f298cec101200e0c9fc039c36
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f42285cedd2eb73479e03c498d1b633b7d823ede0832b8a6974fb0a7006250a
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa4b4303709a35e16263371a05a5771d89ce039dcb068a26d9243418c9bb989
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d180f81e6f41b324393c0948dc675e53ae935a4e7b41cd01f1cbc0e6da023be2
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.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": 1.9961919268849961,
+    "total_flos": 418179526819840.0,
+    "train_loss": 0.09776416790047916,
+    "train_runtime": 5460.3908,
+    "train_samples_per_second": 3.846,
+    "train_steps_per_second": 0.04
+}

trainer_log.jsonl

@@ -0,0 +1,244 @@
+{"current_steps": 1, "total_steps": 218, "loss": 0.6708, "lr": 9.090909090909091e-07, "epoch": 0.00913937547600914, "percentage": 0.46, "elapsed_time": "0:01:19", "remaining_time": "4:49:00"}
+{"current_steps": 2, "total_steps": 218, "loss": 0.6794, "lr": 1.8181818181818183e-06, "epoch": 0.01827875095201828, "percentage": 0.92, "elapsed_time": "0:02:42", "remaining_time": "4:52:43"}
+{"current_steps": 3, "total_steps": 218, "loss": 0.6599, "lr": 2.7272727272727272e-06, "epoch": 0.027418126428027417, "percentage": 1.38, "elapsed_time": "0:03:56", "remaining_time": "4:42:14"}
+{"current_steps": 4, "total_steps": 218, "loss": 0.6689, "lr": 3.6363636363636366e-06, "epoch": 0.03655750190403656, "percentage": 1.83, "elapsed_time": "0:05:04", "remaining_time": "4:31:32"}
+{"current_steps": 5, "total_steps": 218, "loss": 0.6512, "lr": 4.5454545454545455e-06, "epoch": 0.0456968773800457, "percentage": 2.29, "elapsed_time": "0:06:18", "remaining_time": "4:28:53"}
+{"current_steps": 6, "total_steps": 218, "loss": 0.6187, "lr": 5.4545454545454545e-06, "epoch": 0.05483625285605483, "percentage": 2.75, "elapsed_time": "0:07:42", "remaining_time": "4:32:36"}
+{"current_steps": 7, "total_steps": 218, "loss": 0.6179, "lr": 6.363636363636364e-06, "epoch": 0.06397562833206398, "percentage": 3.21, "elapsed_time": "0:09:00", "remaining_time": "4:31:20"}
+{"current_steps": 8, "total_steps": 218, "loss": 0.6075, "lr": 7.272727272727273e-06, "epoch": 0.07311500380807312, "percentage": 3.67, "elapsed_time": "0:10:09", "remaining_time": "4:26:27"}
+{"current_steps": 9, "total_steps": 218, "loss": 0.5964, "lr": 8.181818181818183e-06, "epoch": 0.08225437928408226, "percentage": 4.13, "elapsed_time": "0:11:25", "remaining_time": "4:25:20"}
+{"current_steps": 10, "total_steps": 218, "loss": 0.5533, "lr": 9.090909090909091e-06, "epoch": 0.0913937547600914, "percentage": 4.59, "elapsed_time": "0:12:51", "remaining_time": "4:27:34"}
+{"current_steps": 11, "total_steps": 218, "loss": 0.5382, "lr": 1e-05, "epoch": 0.10053313023610053, "percentage": 5.05, "elapsed_time": "0:14:06", "remaining_time": "4:25:36"}
+{"current_steps": 12, "total_steps": 218, "loss": 0.5104, "lr": 1.0909090909090909e-05, "epoch": 0.10967250571210967, "percentage": 5.5, "elapsed_time": "0:15:33", "remaining_time": "4:27:05"}
+{"current_steps": 13, "total_steps": 218, "loss": 0.5173, "lr": 1.181818181818182e-05, "epoch": 0.1188118811881188, "percentage": 5.96, "elapsed_time": "0:17:00", "remaining_time": "4:28:10"}
+{"current_steps": 14, "total_steps": 218, "loss": 0.5133, "lr": 1.2727272727272728e-05, "epoch": 0.12795125666412796, "percentage": 6.42, "elapsed_time": "0:18:24", "remaining_time": "4:28:16"}
+{"current_steps": 15, "total_steps": 218, "loss": 0.5109, "lr": 1.3636363636363637e-05, "epoch": 0.1370906321401371, "percentage": 6.88, "elapsed_time": "0:19:30", "remaining_time": "4:24:03"}
+{"current_steps": 16, "total_steps": 218, "loss": 0.4618, "lr": 1.4545454545454546e-05, "epoch": 0.14623000761614624, "percentage": 7.34, "elapsed_time": "0:20:41", "remaining_time": "4:21:13"}
+{"current_steps": 17, "total_steps": 218, "loss": 0.4867, "lr": 1.5454545454545454e-05, "epoch": 0.15536938309215537, "percentage": 7.8, "elapsed_time": "0:22:12", "remaining_time": "4:22:29"}
+{"current_steps": 18, "total_steps": 218, "loss": 0.4731, "lr": 1.6363636363636366e-05, "epoch": 0.16450875856816452, "percentage": 8.26, "elapsed_time": "0:23:34", "remaining_time": "4:21:52"}
+{"current_steps": 19, "total_steps": 218, "loss": 0.4439, "lr": 1.7272727272727274e-05, "epoch": 0.17364813404417365, "percentage": 8.72, "elapsed_time": "0:24:34", "remaining_time": "4:17:19"}
+{"current_steps": 20, "total_steps": 218, "loss": 0.4716, "lr": 1.8181818181818182e-05, "epoch": 0.1827875095201828, "percentage": 9.17, "elapsed_time": "0:25:41", "remaining_time": "4:14:25"}
+{"current_steps": 21, "total_steps": 218, "loss": 0.4412, "lr": 1.9090909090909094e-05, "epoch": 0.19192688499619193, "percentage": 9.63, "elapsed_time": "0:26:47", "remaining_time": "4:11:19"}
+{"current_steps": 22, "total_steps": 218, "loss": 0.4459, "lr": 2e-05, "epoch": 0.20106626047220105, "percentage": 10.09, "elapsed_time": "0:27:54", "remaining_time": "4:08:34"}
+{"current_steps": 23, "total_steps": 218, "loss": 0.45, "lr": 1.9998715457999313e-05, "epoch": 0.2102056359482102, "percentage": 10.55, "elapsed_time": "0:28:55", "remaining_time": "4:05:11"}
+{"current_steps": 24, "total_steps": 218, "loss": 0.4362, "lr": 1.999486216200688e-05, "epoch": 0.21934501142421933, "percentage": 11.01, "elapsed_time": "0:30:17", "remaining_time": "4:04:48"}
+{"current_steps": 25, "total_steps": 218, "loss": 0.4562, "lr": 1.9988441101966807e-05, "epoch": 0.2284843869002285, "percentage": 11.47, "elapsed_time": "0:31:43", "remaining_time": "4:04:51"}
+{"current_steps": 26, "total_steps": 218, "loss": 0.4684, "lr": 1.9979453927503366e-05, "epoch": 0.2376237623762376, "percentage": 11.93, "elapsed_time": "0:33:06", "remaining_time": "4:04:29"}
+{"current_steps": 27, "total_steps": 218, "loss": 0.4526, "lr": 1.9967902947497158e-05, "epoch": 0.24676313785224677, "percentage": 12.39, "elapsed_time": "0:34:21", "remaining_time": "4:03:01"}
+{"current_steps": 28, "total_steps": 218, "loss": 0.4468, "lr": 1.9953791129491985e-05, "epoch": 0.2559025133282559, "percentage": 12.84, "elapsed_time": "0:35:49", "remaining_time": "4:03:03"}
+{"current_steps": 29, "total_steps": 218, "loss": 0.4272, "lr": 1.9937122098932428e-05, "epoch": 0.26504188880426505, "percentage": 13.3, "elapsed_time": "0:36:53", "remaining_time": "4:00:27"}
+{"current_steps": 30, "total_steps": 218, "loss": 0.4456, "lr": 1.991790013823246e-05, "epoch": 0.2741812642802742, "percentage": 13.76, "elapsed_time": "0:38:29", "remaining_time": "4:01:13"}
+{"current_steps": 31, "total_steps": 218, "loss": 0.4436, "lr": 1.9896130185675263e-05, "epoch": 0.2833206397562833, "percentage": 14.22, "elapsed_time": "0:39:51", "remaining_time": "4:00:25"}
+{"current_steps": 32, "total_steps": 218, "loss": 0.4285, "lr": 1.9871817834144506e-05, "epoch": 0.2924600152322925, "percentage": 14.68, "elapsed_time": "0:41:08", "remaining_time": "3:59:08"}
+{"current_steps": 33, "total_steps": 218, "loss": 0.4385, "lr": 1.9844969329687526e-05, "epoch": 0.3015993907083016, "percentage": 15.14, "elapsed_time": "0:42:21", "remaining_time": "3:57:30"}
+{"current_steps": 34, "total_steps": 218, "loss": 0.4159, "lr": 1.9815591569910654e-05, "epoch": 0.31073876618431073, "percentage": 15.6, "elapsed_time": "0:43:23", "remaining_time": "3:54:49"}
+{"current_steps": 35, "total_steps": 218, "loss": 0.4407, "lr": 1.9783692102207156e-05, "epoch": 0.31987814166031986, "percentage": 16.06, "elapsed_time": "0:44:48", "remaining_time": "3:54:15"}
+{"current_steps": 36, "total_steps": 218, "loss": 0.3885, "lr": 1.9749279121818235e-05, "epoch": 0.32901751713632904, "percentage": 16.51, "elapsed_time": "0:45:57", "remaining_time": "3:52:21"}
+{"current_steps": 37, "total_steps": 218, "loss": 0.3883, "lr": 1.971236146972764e-05, "epoch": 0.33815689261233817, "percentage": 16.97, "elapsed_time": "0:47:23", "remaining_time": "3:51:51"}
+{"current_steps": 38, "total_steps": 218, "loss": 0.3881, "lr": 1.9672948630390296e-05, "epoch": 0.3472962680883473, "percentage": 17.43, "elapsed_time": "0:48:28", "remaining_time": "3:49:37"}
+{"current_steps": 39, "total_steps": 218, "loss": 0.4378, "lr": 1.9631050729295705e-05, "epoch": 0.3564356435643564, "percentage": 17.89, "elapsed_time": "0:49:52", "remaining_time": "3:48:56"}
+{"current_steps": 40, "total_steps": 218, "loss": 0.4125, "lr": 1.9586678530366607e-05, "epoch": 0.3655750190403656, "percentage": 18.35, "elapsed_time": "0:51:11", "remaining_time": "3:47:46"}
+{"current_steps": 41, "total_steps": 218, "loss": 0.3944, "lr": 1.953984343319364e-05, "epoch": 0.3747143945163747, "percentage": 18.81, "elapsed_time": "0:52:21", "remaining_time": "3:46:01"}
+{"current_steps": 42, "total_steps": 218, "loss": 0.4164, "lr": 1.949055747010669e-05, "epoch": 0.38385376999238385, "percentage": 19.27, "elapsed_time": "0:53:49", "remaining_time": "3:45:33"}
+{"current_steps": 43, "total_steps": 218, "loss": 0.4196, "lr": 1.9438833303083677e-05, "epoch": 0.392993145468393, "percentage": 19.72, "elapsed_time": "0:55:05", "remaining_time": "3:44:13"}
+{"current_steps": 44, "total_steps": 218, "loss": 0.3882, "lr": 1.9384684220497605e-05, "epoch": 0.4021325209444021, "percentage": 20.18, "elapsed_time": "0:55:52", "remaining_time": "3:40:58"}
+{"current_steps": 45, "total_steps": 218, "loss": 0.4301, "lr": 1.932812413370265e-05, "epoch": 0.4112718964204113, "percentage": 20.64, "elapsed_time": "0:57:14", "remaining_time": "3:40:02"}
+{"current_steps": 46, "total_steps": 218, "loss": 0.3943, "lr": 1.926916757346022e-05, "epoch": 0.4204112718964204, "percentage": 21.1, "elapsed_time": "0:58:22", "remaining_time": "3:38:15"}
+{"current_steps": 47, "total_steps": 218, "loss": 0.3888, "lr": 1.9207829686205882e-05, "epoch": 0.42955064737242954, "percentage": 21.56, "elapsed_time": "0:59:32", "remaining_time": "3:36:36"}
+{"current_steps": 48, "total_steps": 218, "loss": 0.4084, "lr": 1.9144126230158127e-05, "epoch": 0.43869002284843867, "percentage": 22.02, "elapsed_time": "1:00:33", "remaining_time": "3:34:29"}
+{"current_steps": 49, "total_steps": 218, "loss": 0.3892, "lr": 1.9078073571269922e-05, "epoch": 0.44782939832444785, "percentage": 22.48, "elapsed_time": "1:01:43", "remaining_time": "3:32:54"}
+{"current_steps": 50, "total_steps": 218, "loss": 0.3911, "lr": 1.900968867902419e-05, "epoch": 0.456968773800457, "percentage": 22.94, "elapsed_time": "1:03:18", "remaining_time": "3:32:44"}
+{"current_steps": 51, "total_steps": 218, "loss": 0.3985, "lr": 1.8938989122074195e-05, "epoch": 0.4661081492764661, "percentage": 23.39, "elapsed_time": "1:06:18", "remaining_time": "3:37:06"}
+{"current_steps": 52, "total_steps": 218, "loss": 0.4156, "lr": 1.8865993063730003e-05, "epoch": 0.4752475247524752, "percentage": 23.85, "elapsed_time": "1:07:39", "remaining_time": "3:35:58"}
+{"current_steps": 53, "total_steps": 218, "loss": 0.4189, "lr": 1.8790719257292175e-05, "epoch": 0.4843869002284844, "percentage": 24.31, "elapsed_time": "1:09:17", "remaining_time": "3:35:44"}
+{"current_steps": 54, "total_steps": 218, "loss": 0.4105, "lr": 1.8713187041233896e-05, "epoch": 0.49352627570449353, "percentage": 24.77, "elapsed_time": "1:10:45", "remaining_time": "3:34:52"}
+{"current_steps": 55, "total_steps": 218, "loss": 0.389, "lr": 1.8633416334232754e-05, "epoch": 0.5026656511805027, "percentage": 25.23, "elapsed_time": "1:11:57", "remaining_time": "3:33:14"}
+{"current_steps": 56, "total_steps": 218, "loss": 0.4168, "lr": 1.8551427630053464e-05, "epoch": 0.5118050266565118, "percentage": 25.69, "elapsed_time": "1:13:12", "remaining_time": "3:31:46"}
+{"current_steps": 57, "total_steps": 218, "loss": 0.3745, "lr": 1.8467241992282842e-05, "epoch": 0.5209444021325209, "percentage": 26.15, "elapsed_time": "1:14:30", "remaining_time": "3:30:27"}
+{"current_steps": 58, "total_steps": 218, "loss": 0.4024, "lr": 1.8380881048918406e-05, "epoch": 0.5300837776085301, "percentage": 26.61, "elapsed_time": "1:16:16", "remaining_time": "3:30:26"}
+{"current_steps": 59, "total_steps": 218, "loss": 0.379, "lr": 1.8292366986811952e-05, "epoch": 0.5392231530845393, "percentage": 27.06, "elapsed_time": "1:17:37", "remaining_time": "3:29:11"}
+{"current_steps": 60, "total_steps": 218, "loss": 0.3959, "lr": 1.820172254596956e-05, "epoch": 0.5483625285605483, "percentage": 27.52, "elapsed_time": "1:18:54", "remaining_time": "3:27:46"}
+{"current_steps": 61, "total_steps": 218, "loss": 0.3833, "lr": 1.8108971013709512e-05, "epoch": 0.5575019040365575, "percentage": 27.98, "elapsed_time": "1:19:45", "remaining_time": "3:25:16"}
+{"current_steps": 62, "total_steps": 218, "loss": 0.3847, "lr": 1.8014136218679566e-05, "epoch": 0.5666412795125666, "percentage": 28.44, "elapsed_time": "1:20:57", "remaining_time": "3:23:41"}
+{"current_steps": 63, "total_steps": 218, "loss": 0.384, "lr": 1.79172425247352e-05, "epoch": 0.5757806549885758, "percentage": 28.9, "elapsed_time": "1:22:16", "remaining_time": "3:22:25"}
+{"current_steps": 64, "total_steps": 218, "loss": 0.3827, "lr": 1.78183148246803e-05, "epoch": 0.584920030464585, "percentage": 29.36, "elapsed_time": "1:23:36", "remaining_time": "3:21:12"}
+{"current_steps": 65, "total_steps": 218, "loss": 0.3971, "lr": 1.771737853387202e-05, "epoch": 0.594059405940594, "percentage": 29.82, "elapsed_time": "1:25:14", "remaining_time": "3:20:39"}
+{"current_steps": 66, "total_steps": 218, "loss": 0.3965, "lr": 1.7614459583691346e-05, "epoch": 0.6031987814166032, "percentage": 30.28, "elapsed_time": "1:26:29", "remaining_time": "3:19:11"}
+{"current_steps": 67, "total_steps": 218, "loss": 0.3933, "lr": 1.7509584414881114e-05, "epoch": 0.6123381568926123, "percentage": 30.73, "elapsed_time": "1:28:10", "remaining_time": "3:18:42"}
+{"current_steps": 68, "total_steps": 218, "loss": 0.4008, "lr": 1.7402779970753156e-05, "epoch": 0.6214775323686215, "percentage": 31.19, "elapsed_time": "1:29:47", "remaining_time": "3:18:04"}
+{"current_steps": 69, "total_steps": 218, "loss": 0.4058, "lr": 1.7294073690266343e-05, "epoch": 0.6306169078446306, "percentage": 31.65, "elapsed_time": "1:30:54", "remaining_time": "3:16:18"}
+{"current_steps": 70, "total_steps": 218, "loss": 0.3911, "lr": 1.7183493500977277e-05, "epoch": 0.6397562833206397, "percentage": 32.11, "elapsed_time": "1:32:17", "remaining_time": "3:15:08"}
+{"current_steps": 71, "total_steps": 218, "loss": 0.389, "lr": 1.7071067811865477e-05, "epoch": 0.6488956587966489, "percentage": 32.57, "elapsed_time": "1:34:02", "remaining_time": "3:14:42"}
+{"current_steps": 72, "total_steps": 218, "loss": 0.3824, "lr": 1.6956825506034866e-05, "epoch": 0.6580350342726581, "percentage": 33.03, "elapsed_time": "1:35:07", "remaining_time": "3:12:53"}
+{"current_steps": 73, "total_steps": 218, "loss": 0.3797, "lr": 1.6840795933293464e-05, "epoch": 0.6671744097486672, "percentage": 33.49, "elapsed_time": "1:36:27", "remaining_time": "3:11:35"}
+{"current_steps": 74, "total_steps": 218, "loss": 0.3769, "lr": 1.672300890261317e-05, "epoch": 0.6763137852246763, "percentage": 33.94, "elapsed_time": "1:37:35", "remaining_time": "3:09:54"}
+{"current_steps": 75, "total_steps": 218, "loss": 0.3765, "lr": 1.6603494674471595e-05, "epoch": 0.6854531607006854, "percentage": 34.4, "elapsed_time": "1:39:08", "remaining_time": "3:09:02"}
+{"current_steps": 76, "total_steps": 218, "loss": 0.402, "lr": 1.6482283953077887e-05, "epoch": 0.6945925361766946, "percentage": 34.86, "elapsed_time": "1:40:13", "remaining_time": "3:07:15"}
+{"current_steps": 77, "total_steps": 218, "loss": 0.3776, "lr": 1.635940787848455e-05, "epoch": 0.7037319116527038, "percentage": 35.32, "elapsed_time": "1:41:12", "remaining_time": "3:05:19"}
+{"current_steps": 78, "total_steps": 218, "loss": 0.381, "lr": 1.6234898018587336e-05, "epoch": 0.7128712871287128, "percentage": 35.78, "elapsed_time": "1:42:33", "remaining_time": "3:04:05"}
+{"current_steps": 79, "total_steps": 218, "loss": 0.3723, "lr": 1.6108786361015145e-05, "epoch": 0.722010662604722, "percentage": 36.24, "elapsed_time": "1:43:34", "remaining_time": "3:02:13"}
+{"current_steps": 80, "total_steps": 218, "loss": 0.4152, "lr": 1.598110530491216e-05, "epoch": 0.7311500380807312, "percentage": 36.7, "elapsed_time": "1:45:11", "remaining_time": "3:01:27"}
+{"current_steps": 81, "total_steps": 218, "loss": 0.3937, "lr": 1.5851887652614238e-05, "epoch": 0.7402894135567403, "percentage": 37.16, "elapsed_time": "1:46:21", "remaining_time": "2:59:53"}
+{"current_steps": 82, "total_steps": 218, "loss": 0.4073, "lr": 1.5721166601221697e-05, "epoch": 0.7494287890327495, "percentage": 37.61, "elapsed_time": "1:47:41", "remaining_time": "2:58:36"}
+{"current_steps": 83, "total_steps": 218, "loss": 0.3756, "lr": 1.5588975734070717e-05, "epoch": 0.7585681645087585, "percentage": 38.07, "elapsed_time": "1:48:43", "remaining_time": "2:56:50"}
+{"current_steps": 84, "total_steps": 218, "loss": 0.3902, "lr": 1.5455349012105488e-05, "epoch": 0.7677075399847677, "percentage": 38.53, "elapsed_time": "1:50:04", "remaining_time": "2:55:36"}
+{"current_steps": 85, "total_steps": 218, "loss": 0.3879, "lr": 1.5320320765153367e-05, "epoch": 0.7768469154607769, "percentage": 38.99, "elapsed_time": "1:51:34", "remaining_time": "2:54:35"}
+{"current_steps": 86, "total_steps": 218, "loss": 0.3887, "lr": 1.5183925683105254e-05, "epoch": 0.785986290936786, "percentage": 39.45, "elapsed_time": "1:52:54", "remaining_time": "2:53:17"}
+{"current_steps": 87, "total_steps": 218, "loss": 0.3859, "lr": 1.504619880700346e-05, "epoch": 0.7951256664127951, "percentage": 39.91, "elapsed_time": "1:53:49", "remaining_time": "2:51:24"}
+{"current_steps": 88, "total_steps": 218, "loss": 0.381, "lr": 1.4907175520039381e-05, "epoch": 0.8042650418888042, "percentage": 40.37, "elapsed_time": "1:55:23", "remaining_time": "2:50:27"}
+{"current_steps": 89, "total_steps": 218, "loss": 0.3798, "lr": 1.4766891538463255e-05, "epoch": 0.8134044173648134, "percentage": 40.83, "elapsed_time": "1:56:27", "remaining_time": "2:48:47"}
+{"current_steps": 90, "total_steps": 218, "loss": 0.376, "lr": 1.4625382902408356e-05, "epoch": 0.8225437928408226, "percentage": 41.28, "elapsed_time": "1:57:42", "remaining_time": "2:47:24"}
+{"current_steps": 91, "total_steps": 218, "loss": 0.3692, "lr": 1.448268596663197e-05, "epoch": 0.8316831683168316, "percentage": 41.74, "elapsed_time": "1:58:57", "remaining_time": "2:46:01"}
+{"current_steps": 92, "total_steps": 218, "loss": 0.385, "lr": 1.4338837391175582e-05, "epoch": 0.8408225437928408, "percentage": 42.2, "elapsed_time": "2:00:30", "remaining_time": "2:45:02"}
+{"current_steps": 93, "total_steps": 218, "loss": 0.3711, "lr": 1.419387413194657e-05, "epoch": 0.84996191926885, "percentage": 42.66, "elapsed_time": "2:01:27", "remaining_time": "2:43:15"}
+{"current_steps": 94, "total_steps": 218, "loss": 0.3772, "lr": 1.4047833431223938e-05, "epoch": 0.8591012947448591, "percentage": 43.12, "elapsed_time": "2:02:52", "remaining_time": "2:42:05"}
+{"current_steps": 95, "total_steps": 218, "loss": 0.3791, "lr": 1.390075280809047e-05, "epoch": 0.8682406702208683, "percentage": 43.58, "elapsed_time": "2:04:05", "remaining_time": "2:40:40"}
+{"current_steps": 96, "total_steps": 218, "loss": 0.3767, "lr": 1.3752670048793744e-05, "epoch": 0.8773800456968773, "percentage": 44.04, "elapsed_time": "2:05:21", "remaining_time": "2:39:18"}
+{"current_steps": 97, "total_steps": 218, "loss": 0.3831, "lr": 1.3603623197038536e-05, "epoch": 0.8865194211728865, "percentage": 44.5, "elapsed_time": "2:06:31", "remaining_time": "2:37:50"}
+{"current_steps": 98, "total_steps": 218, "loss": 0.3933, "lr": 1.3453650544213078e-05, "epoch": 0.8956587966488957, "percentage": 44.95, "elapsed_time": "2:08:07", "remaining_time": "2:36:53"}
+{"current_steps": 99, "total_steps": 218, "loss": 0.366, "lr": 1.3302790619551673e-05, "epoch": 0.9047981721249048, "percentage": 45.41, "elapsed_time": "2:09:15", "remaining_time": "2:35:21"}
+{"current_steps": 100, "total_steps": 218, "loss": 0.3824, "lr": 1.315108218023621e-05, "epoch": 0.913937547600914, "percentage": 45.87, "elapsed_time": "2:10:25", "remaining_time": "2:33:54"}
+{"current_steps": 101, "total_steps": 218, "loss": 0.3845, "lr": 1.2998564201439117e-05, "epoch": 0.9230769230769231, "percentage": 46.33, "elapsed_time": "2:12:50", "remaining_time": "2:33:52"}
+{"current_steps": 102, "total_steps": 218, "loss": 0.3819, "lr": 1.2845275866310325e-05, "epoch": 0.9322162985529322, "percentage": 46.79, "elapsed_time": "2:14:16", "remaining_time": "2:32:42"}
+{"current_steps": 103, "total_steps": 218, "loss": 0.3759, "lr": 1.2691256555910769e-05, "epoch": 0.9413556740289414, "percentage": 47.25, "elapsed_time": "2:15:21", "remaining_time": "2:31:08"}
+{"current_steps": 104, "total_steps": 218, "loss": 0.3963, "lr": 1.2536545839095074e-05, "epoch": 0.9504950495049505, "percentage": 47.71, "elapsed_time": "2:16:58", "remaining_time": "2:30:08"}
+{"current_steps": 105, "total_steps": 218, "loss": 0.3805, "lr": 1.2381183462345983e-05, "epoch": 0.9596344249809596, "percentage": 48.17, "elapsed_time": "2:18:14", "remaining_time": "2:28:46"}
+{"current_steps": 106, "total_steps": 218, "loss": 0.3781, "lr": 1.2225209339563144e-05, "epoch": 0.9687738004569688, "percentage": 48.62, "elapsed_time": "2:19:39", "remaining_time": "2:27:34"}
+{"current_steps": 107, "total_steps": 218, "loss": 0.3777, "lr": 1.206866354180891e-05, "epoch": 0.9779131759329779, "percentage": 49.08, "elapsed_time": "2:21:12", "remaining_time": "2:26:29"}
+{"current_steps": 108, "total_steps": 218, "loss": 0.3822, "lr": 1.1911586287013726e-05, "epoch": 0.9870525514089871, "percentage": 49.54, "elapsed_time": "2:22:34", "remaining_time": "2:25:12"}
+{"current_steps": 109, "total_steps": 218, "loss": 0.3761, "lr": 1.1754017929643818e-05, "epoch": 0.9961919268849961, "percentage": 50.0, "elapsed_time": "2:23:35", "remaining_time": "2:23:35"}
+{"current_steps": 110, "total_steps": 218, "loss": 0.5449, "lr": 1.1595998950333794e-05, "epoch": 1.0053313023610053, "percentage": 50.46, "elapsed_time": "2:24:52", "remaining_time": "2:22:14"}
+{"current_steps": 111, "total_steps": 218, "loss": 0.3479, "lr": 1.143756994548682e-05, "epoch": 1.0144706778370145, "percentage": 50.92, "elapsed_time": "2:26:21", "remaining_time": "2:21:05"}
+{"current_steps": 112, "total_steps": 218, "loss": 0.338, "lr": 1.1278771616845061e-05, "epoch": 1.0236100533130237, "percentage": 51.38, "elapsed_time": "2:27:51", "remaining_time": "2:19:56"}
+{"current_steps": 113, "total_steps": 218, "loss": 0.3353, "lr": 1.1119644761033079e-05, "epoch": 1.0327494287890326, "percentage": 51.83, "elapsed_time": "2:29:36", "remaining_time": "2:19:01"}
+{"current_steps": 114, "total_steps": 218, "loss": 0.3257, "lr": 1.0960230259076819e-05, "epoch": 1.0418888042650418, "percentage": 52.29, "elapsed_time": "2:30:56", "remaining_time": "2:17:41"}
+{"current_steps": 115, "total_steps": 218, "loss": 0.3521, "lr": 1.0800569065900935e-05, "epoch": 1.051028179741051, "percentage": 52.75, "elapsed_time": "2:32:31", "remaining_time": "2:16:36"}
+{"current_steps": 116, "total_steps": 218, "loss": 0.3117, "lr": 1.064070219980713e-05, "epoch": 1.0601675552170602, "percentage": 53.21, "elapsed_time": "2:33:37", "remaining_time": "2:15:05"}
+{"current_steps": 117, "total_steps": 218, "loss": 0.3093, "lr": 1.0480670731936209e-05, "epoch": 1.0693069306930694, "percentage": 53.67, "elapsed_time": "2:35:07", "remaining_time": "2:13:54"}
+{"current_steps": 118, "total_steps": 218, "loss": 0.2998, "lr": 1.0320515775716556e-05, "epoch": 1.0784463061690786, "percentage": 54.13, "elapsed_time": "2:36:24", "remaining_time": "2:12:33"}
+{"current_steps": 119, "total_steps": 218, "loss": 0.3737, "lr": 1.0160278476301739e-05, "epoch": 1.0875856816450875, "percentage": 54.59, "elapsed_time": "2:37:47", "remaining_time": "2:11:16"}
+{"current_steps": 120, "total_steps": 218, "loss": 0.3267, "lr": 1e-05, "epoch": 1.0967250571210967, "percentage": 55.05, "elapsed_time": "2:39:17", "remaining_time": "2:10:05"}
+{"current_steps": 121, "total_steps": 218, "loss": 0.2584, "lr": 9.839721523698265e-06, "epoch": 1.1058644325971059, "percentage": 55.5, "elapsed_time": "2:40:10", "remaining_time": "2:08:24"}
+{"current_steps": 122, "total_steps": 218, "loss": 0.3526, "lr": 9.67948422428345e-06, "epoch": 1.115003808073115, "percentage": 55.96, "elapsed_time": "2:41:35", "remaining_time": "2:07:09"}
+{"current_steps": 123, "total_steps": 218, "loss": 0.3425, "lr": 9.519329268063795e-06, "epoch": 1.1241431835491242, "percentage": 56.42, "elapsed_time": "2:43:04", "remaining_time": "2:05:57"}
+{"current_steps": 124, "total_steps": 218, "loss": 0.3097, "lr": 9.359297800192873e-06, "epoch": 1.1332825590251332, "percentage": 56.88, "elapsed_time": "2:44:16", "remaining_time": "2:04:31"}
+{"current_steps": 125, "total_steps": 218, "loss": 0.3052, "lr": 9.199430934099068e-06, "epoch": 1.1424219345011424, "percentage": 57.34, "elapsed_time": "2:45:23", "remaining_time": "2:03:03"}
+{"current_steps": 126, "total_steps": 218, "loss": 0.2977, "lr": 9.039769740923183e-06, "epoch": 1.1515613099771516, "percentage": 57.8, "elapsed_time": "2:46:51", "remaining_time": "2:01:49"}
+{"current_steps": 127, "total_steps": 218, "loss": 0.3113, "lr": 8.880355238966923e-06, "epoch": 1.1607006854531607, "percentage": 58.26, "elapsed_time": "2:48:01", "remaining_time": "2:00:24"}
+{"current_steps": 128, "total_steps": 218, "loss": 0.3205, "lr": 8.721228383154939e-06, "epoch": 1.16984006092917, "percentage": 58.72, "elapsed_time": "2:49:51", "remaining_time": "1:59:25"}
+{"current_steps": 129, "total_steps": 218, "loss": 0.3176, "lr": 8.562430054513184e-06, "epoch": 1.178979436405179, "percentage": 59.17, "elapsed_time": "2:51:15", "remaining_time": "1:58:09"}
+{"current_steps": 130, "total_steps": 218, "loss": 0.3201, "lr": 8.404001049666211e-06, "epoch": 1.188118811881188, "percentage": 59.63, "elapsed_time": "2:52:26", "remaining_time": "1:56:43"}
+{"current_steps": 131, "total_steps": 218, "loss": 0.297, "lr": 8.245982070356186e-06, "epoch": 1.1972581873571972, "percentage": 60.09, "elapsed_time": "2:53:51", "remaining_time": "1:55:27"}
+{"current_steps": 132, "total_steps": 218, "loss": 0.3163, "lr": 8.08841371298628e-06, "epoch": 1.2063975628332064, "percentage": 60.55, "elapsed_time": "2:55:11", "remaining_time": "1:54:08"}
+{"current_steps": 133, "total_steps": 218, "loss": 0.3421, "lr": 7.931336458191092e-06, "epoch": 1.2155369383092156, "percentage": 61.01, "elapsed_time": "2:56:25", "remaining_time": "1:52:45"}
+{"current_steps": 134, "total_steps": 218, "loss": 0.3097, "lr": 7.774790660436857e-06, "epoch": 1.2246763137852246, "percentage": 61.47, "elapsed_time": "2:57:35", "remaining_time": "1:51:19"}
+{"current_steps": 135, "total_steps": 218, "loss": 0.3201, "lr": 7.618816537654018e-06, "epoch": 1.2338156892612338, "percentage": 61.93, "elapsed_time": "2:59:00", "remaining_time": "1:50:03"}
+{"current_steps": 136, "total_steps": 218, "loss": 0.2807, "lr": 7.463454160904928e-06, "epoch": 1.242955064737243, "percentage": 62.39, "elapsed_time": "3:00:22", "remaining_time": "1:48:45"}
+{"current_steps": 137, "total_steps": 218, "loss": 0.3258, "lr": 7.308743444089232e-06, "epoch": 1.2520944402132521, "percentage": 62.84, "elapsed_time": "3:01:41", "remaining_time": "1:47:25"}
+{"current_steps": 138, "total_steps": 218, "loss": 0.2958, "lr": 7.154724133689677e-06, "epoch": 1.2612338156892613, "percentage": 63.3, "elapsed_time": "3:03:06", "remaining_time": "1:46:08"}
+{"current_steps": 139, "total_steps": 218, "loss": 0.321, "lr": 7.001435798560884e-06, "epoch": 1.2703731911652705, "percentage": 63.76, "elapsed_time": "3:04:32", "remaining_time": "1:44:53"}
+{"current_steps": 140, "total_steps": 218, "loss": 0.3006, "lr": 6.848917819763794e-06, "epoch": 1.2795125666412794, "percentage": 64.22, "elapsed_time": "3:05:50", "remaining_time": "1:43:32"}
+{"current_steps": 141, "total_steps": 218, "loss": 0.3311, "lr": 6.697209380448333e-06, "epoch": 1.2886519421172886, "percentage": 64.68, "elapsed_time": "3:07:00", "remaining_time": "1:42:07"}
+{"current_steps": 142, "total_steps": 218, "loss": 0.3646, "lr": 6.546349455786926e-06, "epoch": 1.2977913175932978, "percentage": 65.14, "elapsed_time": "3:08:04", "remaining_time": "1:40:39"}
+{"current_steps": 143, "total_steps": 218, "loss": 0.3165, "lr": 6.396376802961468e-06, "epoch": 1.306930693069307, "percentage": 65.6, "elapsed_time": "3:09:23", "remaining_time": "1:39:19"}
+{"current_steps": 144, "total_steps": 218, "loss": 0.3019, "lr": 6.24732995120626e-06, "epoch": 1.316070068545316, "percentage": 66.06, "elapsed_time": "3:10:32", "remaining_time": "1:37:54"}
+{"current_steps": 145, "total_steps": 218, "loss": 0.2998, "lr": 6.099247191909532e-06, "epoch": 1.3252094440213251, "percentage": 66.51, "elapsed_time": "3:11:32", "remaining_time": "1:36:26"}
+{"current_steps": 146, "total_steps": 218, "loss": 0.3368, "lr": 5.952166568776062e-06, "epoch": 1.3343488194973343, "percentage": 66.97, "elapsed_time": "3:13:04", "remaining_time": "1:35:12"}
+{"current_steps": 147, "total_steps": 218, "loss": 0.2851, "lr": 5.806125868053433e-06, "epoch": 1.3434881949733435, "percentage": 67.43, "elapsed_time": "3:14:10", "remaining_time": "1:33:47"}
+{"current_steps": 148, "total_steps": 218, "loss": 0.2959, "lr": 5.66116260882442e-06, "epoch": 1.3526275704493527, "percentage": 67.89, "elapsed_time": "3:15:15", "remaining_time": "1:32:21"}
+{"current_steps": 149, "total_steps": 218, "loss": 0.3239, "lr": 5.517314033368031e-06, "epoch": 1.3617669459253618, "percentage": 68.35, "elapsed_time": "3:16:35", "remaining_time": "1:31:02"}
+{"current_steps": 150, "total_steps": 218, "loss": 0.3288, "lr": 5.37461709759165e-06, "epoch": 1.370906321401371, "percentage": 68.81, "elapsed_time": "3:17:50", "remaining_time": "1:29:41"}
+{"current_steps": 151, "total_steps": 218, "loss": 0.3233, "lr": 5.233108461536749e-06, "epoch": 1.38004569687738, "percentage": 69.27, "elapsed_time": "3:20:42", "remaining_time": "1:29:03"}
+{"current_steps": 152, "total_steps": 218, "loss": 0.331, "lr": 5.092824479960625e-06, "epoch": 1.3891850723533892, "percentage": 69.72, "elapsed_time": "3:22:18", "remaining_time": "1:27:50"}
+{"current_steps": 153, "total_steps": 218, "loss": 0.3415, "lr": 4.9538011929965436e-06, "epoch": 1.3983244478293984, "percentage": 70.18, "elapsed_time": "3:23:44", "remaining_time": "1:26:33"}
+{"current_steps": 154, "total_steps": 218, "loss": 0.309, "lr": 4.81607431689475e-06, "epoch": 1.4074638233054075, "percentage": 70.64, "elapsed_time": "3:24:53", "remaining_time": "1:25:09"}
+{"current_steps": 155, "total_steps": 218, "loss": 0.3297, "lr": 4.679679234846636e-06, "epoch": 1.4166031987814165, "percentage": 71.1, "elapsed_time": "3:26:11", "remaining_time": "1:23:48"}
+{"current_steps": 156, "total_steps": 218, "loss": 0.2847, "lr": 4.544650987894514e-06, "epoch": 1.4257425742574257, "percentage": 71.56, "elapsed_time": "3:27:15", "remaining_time": "1:22:22"}
+{"current_steps": 157, "total_steps": 218, "loss": 0.3081, "lr": 4.411024265929283e-06, "epoch": 1.4348819497334349, "percentage": 72.02, "elapsed_time": "3:28:20", "remaining_time": "1:20:57"}
+{"current_steps": 158, "total_steps": 218, "loss": 0.271, "lr": 4.278833398778306e-06, "epoch": 1.444021325209444, "percentage": 72.48, "elapsed_time": "3:29:39", "remaining_time": "1:19:37"}
+{"current_steps": 159, "total_steps": 218, "loss": 0.3519, "lr": 4.148112347385762e-06, "epoch": 1.4531607006854532, "percentage": 72.94, "elapsed_time": "3:31:05", "remaining_time": "1:18:19"}
+{"current_steps": 160, "total_steps": 218, "loss": 0.31, "lr": 4.01889469508784e-06, "epoch": 1.4623000761614624, "percentage": 73.39, "elapsed_time": "3:32:13", "remaining_time": "1:16:55"}
+{"current_steps": 161, "total_steps": 218, "loss": 0.3293, "lr": 3.891213638984858e-06, "epoch": 1.4714394516374714, "percentage": 73.85, "elapsed_time": "3:33:31", "remaining_time": "1:15:35"}
+{"current_steps": 162, "total_steps": 218, "loss": 0.2816, "lr": 3.7651019814126656e-06, "epoch": 1.4805788271134805, "percentage": 74.31, "elapsed_time": "3:34:44", "remaining_time": "1:14:13"}
+{"current_steps": 163, "total_steps": 218, "loss": 0.3371, "lr": 3.6405921215154492e-06, "epoch": 1.4897182025894897, "percentage": 74.77, "elapsed_time": "3:36:04", "remaining_time": "1:12:54"}
+{"current_steps": 164, "total_steps": 218, "loss": 0.3139, "lr": 3.5177160469221184e-06, "epoch": 1.498857578065499, "percentage": 75.23, "elapsed_time": "3:37:32", "remaining_time": "1:11:37"}
+{"current_steps": 165, "total_steps": 218, "loss": 0.2753, "lr": 3.3965053255284085e-06, "epoch": 1.5079969535415079, "percentage": 75.69, "elapsed_time": "3:38:49", "remaining_time": "1:10:17"}
+{"current_steps": 166, "total_steps": 218, "loss": 0.3384, "lr": 3.2769910973868314e-06, "epoch": 1.517136329017517, "percentage": 76.15, "elapsed_time": "3:40:00", "remaining_time": "1:08:55"}
+{"current_steps": 167, "total_steps": 218, "loss": 0.289, "lr": 3.1592040667065393e-06, "epoch": 1.5262757044935262, "percentage": 76.61, "elapsed_time": "3:41:10", "remaining_time": "1:07:32"}
+{"current_steps": 168, "total_steps": 218, "loss": 0.3314, "lr": 3.0431744939651365e-06, "epoch": 1.5354150799695354, "percentage": 77.06, "elapsed_time": "3:42:37", "remaining_time": "1:06:15"}
+{"current_steps": 169, "total_steps": 218, "loss": 0.287, "lr": 2.9289321881345257e-06, "epoch": 1.5445544554455446, "percentage": 77.52, "elapsed_time": "3:43:43", "remaining_time": "1:04:51"}
+{"current_steps": 170, "total_steps": 218, "loss": 0.3123, "lr": 2.8165064990227255e-06, "epoch": 1.5536938309215538, "percentage": 77.98, "elapsed_time": "3:44:53", "remaining_time": "1:03:29"}
+{"current_steps": 171, "total_steps": 218, "loss": 0.3503, "lr": 2.7059263097336595e-06, "epoch": 1.562833206397563, "percentage": 78.44, "elapsed_time": "3:46:40", "remaining_time": "1:02:18"}
+{"current_steps": 172, "total_steps": 218, "loss": 0.3396, "lr": 2.597220029246846e-06, "epoch": 1.5719725818735721, "percentage": 78.9, "elapsed_time": "3:48:02", "remaining_time": "1:00:59"}
+{"current_steps": 173, "total_steps": 218, "loss": 0.2687, "lr": 2.490415585118887e-06, "epoch": 1.581111957349581, "percentage": 79.36, "elapsed_time": "3:49:01", "remaining_time": "0:59:34"}
+{"current_steps": 174, "total_steps": 218, "loss": 0.3275, "lr": 2.3855404163086558e-06, "epoch": 1.5902513328255903, "percentage": 79.82, "elapsed_time": "3:49:57", "remaining_time": "0:58:09"}
+{"current_steps": 175, "total_steps": 218, "loss": 0.2738, "lr": 2.282621466127982e-06, "epoch": 1.5993907083015992, "percentage": 80.28, "elapsed_time": "3:50:57", "remaining_time": "0:56:45"}
+{"current_steps": 151, "total_steps": 218, "loss": 0.3226, "lr": 5.233108461536749e-06, "epoch": 1.3838537699923839, "percentage": 69.27, "elapsed_time": "0:01:45", "remaining_time": "0:00:46"}
+{"current_steps": 152, "total_steps": 218, "loss": 0.3039, "lr": 5.092824479960625e-06, "epoch": 1.392993145468393, "percentage": 69.72, "elapsed_time": "0:03:15", "remaining_time": "0:01:25"}
+{"current_steps": 153, "total_steps": 218, "loss": 0.3441, "lr": 4.9538011929965436e-06, "epoch": 1.4021325209444022, "percentage": 70.18, "elapsed_time": "0:04:28", "remaining_time": "0:01:54"}
+{"current_steps": 154, "total_steps": 218, "loss": 0.3127, "lr": 4.81607431689475e-06, "epoch": 1.4112718964204114, "percentage": 70.64, "elapsed_time": "0:05:31", "remaining_time": "0:02:17"}
+{"current_steps": 155, "total_steps": 218, "loss": 0.3119, "lr": 4.679679234846636e-06, "epoch": 1.4204112718964204, "percentage": 71.1, "elapsed_time": "0:06:58", "remaining_time": "0:02:50"}
+{"current_steps": 156, "total_steps": 218, "loss": 0.2909, "lr": 4.544650987894514e-06, "epoch": 1.4295506473724295, "percentage": 71.56, "elapsed_time": "0:07:49", "remaining_time": "0:03:06"}
+{"current_steps": 157, "total_steps": 218, "loss": 0.3118, "lr": 4.411024265929283e-06, "epoch": 1.4386900228484387, "percentage": 72.02, "elapsed_time": "0:09:16", "remaining_time": "0:03:36"}
+{"current_steps": 158, "total_steps": 218, "loss": 0.3122, "lr": 4.278833398778306e-06, "epoch": 1.447829398324448, "percentage": 72.48, "elapsed_time": "0:10:34", "remaining_time": "0:04:00"}
+{"current_steps": 159, "total_steps": 218, "loss": 0.3073, "lr": 4.148112347385762e-06, "epoch": 1.4569687738004569, "percentage": 72.94, "elapsed_time": "0:11:48", "remaining_time": "0:04:22"}
+{"current_steps": 160, "total_steps": 218, "loss": 0.3206, "lr": 4.01889469508784e-06, "epoch": 1.466108149276466, "percentage": 73.39, "elapsed_time": "0:12:54", "remaining_time": "0:04:40"}
+{"current_steps": 161, "total_steps": 218, "loss": 0.3147, "lr": 3.891213638984858e-06, "epoch": 1.4752475247524752, "percentage": 73.85, "elapsed_time": "0:14:05", "remaining_time": "0:04:59"}
+{"current_steps": 162, "total_steps": 218, "loss": 0.3249, "lr": 3.7651019814126656e-06, "epoch": 1.4843869002284844, "percentage": 74.31, "elapsed_time": "0:15:27", "remaining_time": "0:05:20"}
+{"current_steps": 163, "total_steps": 218, "loss": 0.3121, "lr": 3.6405921215154492e-06, "epoch": 1.4935262757044936, "percentage": 74.77, "elapsed_time": "0:16:49", "remaining_time": "0:05:40"}
+{"current_steps": 164, "total_steps": 218, "loss": 0.3003, "lr": 3.5177160469221184e-06, "epoch": 1.5026656511805028, "percentage": 75.23, "elapsed_time": "0:18:22", "remaining_time": "0:06:02"}
+{"current_steps": 165, "total_steps": 218, "loss": 0.3115, "lr": 3.3965053255284085e-06, "epoch": 1.511805026656512, "percentage": 75.69, "elapsed_time": "0:19:32", "remaining_time": "0:06:16"}
+{"current_steps": 166, "total_steps": 218, "loss": 0.3131, "lr": 3.2769910973868314e-06, "epoch": 1.520944402132521, "percentage": 76.15, "elapsed_time": "0:20:36", "remaining_time": "0:06:27"}
+{"current_steps": 167, "total_steps": 218, "loss": 0.2978, "lr": 3.1592040667065393e-06, "epoch": 1.53008377760853, "percentage": 76.61, "elapsed_time": "0:22:00", "remaining_time": "0:06:43"}
+{"current_steps": 168, "total_steps": 218, "loss": 0.3075, "lr": 3.0431744939651365e-06, "epoch": 1.5392231530845393, "percentage": 77.06, "elapsed_time": "0:23:03", "remaining_time": "0:06:51"}
+{"current_steps": 169, "total_steps": 218, "loss": 0.3107, "lr": 2.9289321881345257e-06, "epoch": 1.5483625285605482, "percentage": 77.52, "elapsed_time": "0:24:18", "remaining_time": "0:07:02"}
+{"current_steps": 170, "total_steps": 218, "loss": 0.3338, "lr": 2.8165064990227255e-06, "epoch": 1.5575019040365574, "percentage": 77.98, "elapsed_time": "0:25:55", "remaining_time": "0:07:19"}
+{"current_steps": 171, "total_steps": 218, "loss": 0.3184, "lr": 2.7059263097336595e-06, "epoch": 1.5666412795125666, "percentage": 78.44, "elapsed_time": "0:27:06", "remaining_time": "0:07:27"}
+{"current_steps": 172, "total_steps": 218, "loss": 0.3241, "lr": 2.597220029246846e-06, "epoch": 1.5757806549885758, "percentage": 78.9, "elapsed_time": "0:28:28", "remaining_time": "0:07:36"}
+{"current_steps": 173, "total_steps": 218, "loss": 0.3033, "lr": 2.490415585118887e-06, "epoch": 1.584920030464585, "percentage": 79.36, "elapsed_time": "0:29:28", "remaining_time": "0:07:40"}
+{"current_steps": 174, "total_steps": 218, "loss": 0.2965, "lr": 2.3855404163086558e-06, "epoch": 1.5940594059405941, "percentage": 79.82, "elapsed_time": "0:30:16", "remaining_time": "0:07:39"}
+{"current_steps": 175, "total_steps": 218, "loss": 0.3046, "lr": 2.282621466127982e-06, "epoch": 1.6031987814166033, "percentage": 80.28, "elapsed_time": "0:31:23", "remaining_time": "0:07:42"}
+{"current_steps": 176, "total_steps": 218, "loss": 0.2998, "lr": 2.1816851753197023e-06, "epoch": 1.6123381568926123, "percentage": 80.73, "elapsed_time": "0:32:39", "remaining_time": "0:07:47"}
+{"current_steps": 177, "total_steps": 218, "loss": 0.3047, "lr": 2.082757475264804e-06, "epoch": 1.6214775323686215, "percentage": 81.19, "elapsed_time": "0:33:56", "remaining_time": "0:07:51"}
+{"current_steps": 178, "total_steps": 218, "loss": 0.2906, "lr": 1.9858637813204352e-06, "epoch": 1.6306169078446306, "percentage": 81.65, "elapsed_time": "0:35:15", "remaining_time": "0:07:55"}
+{"current_steps": 179, "total_steps": 218, "loss": 0.3223, "lr": 1.8910289862904917e-06, "epoch": 1.6397562833206396, "percentage": 82.11, "elapsed_time": "0:36:38", "remaining_time": "0:07:59"}
+{"current_steps": 180, "total_steps": 218, "loss": 0.3286, "lr": 1.7982774540304404e-06, "epoch": 1.6488956587966488, "percentage": 82.57, "elapsed_time": "0:37:59", "remaining_time": "0:08:01"}
+{"current_steps": 181, "total_steps": 218, "loss": 0.3162, "lr": 1.7076330131880525e-06, "epoch": 1.658035034272658, "percentage": 83.03, "elapsed_time": "0:39:24", "remaining_time": "0:08:03"}
+{"current_steps": 182, "total_steps": 218, "loss": 0.3147, "lr": 1.6191189510815942e-06, "epoch": 1.6671744097486672, "percentage": 83.49, "elapsed_time": "0:40:58", "remaining_time": "0:08:06"}
+{"current_steps": 183, "total_steps": 218, "loss": 0.3086, "lr": 1.5327580077171589e-06, "epoch": 1.6763137852246763, "percentage": 83.94, "elapsed_time": "0:42:19", "remaining_time": "0:08:05"}
+{"current_steps": 184, "total_steps": 218, "loss": 0.3259, "lr": 1.4485723699465392e-06, "epoch": 1.6854531607006855, "percentage": 84.4, "elapsed_time": "0:43:18", "remaining_time": "0:08:00"}
+{"current_steps": 185, "total_steps": 218, "loss": 0.3126, "lr": 1.3665836657672493e-06, "epoch": 1.6945925361766947, "percentage": 84.86, "elapsed_time": "0:44:33", "remaining_time": "0:07:56"}
+{"current_steps": 186, "total_steps": 218, "loss": 0.3194, "lr": 1.286812958766106e-06, "epoch": 1.7037319116527039, "percentage": 85.32, "elapsed_time": "0:46:02", "remaining_time": "0:07:55"}
+{"current_steps": 187, "total_steps": 218, "loss": 0.3051, "lr": 1.209280742707828e-06, "epoch": 1.7128712871287128, "percentage": 85.78, "elapsed_time": "0:47:02", "remaining_time": "0:07:47"}
+{"current_steps": 188, "total_steps": 218, "loss": 0.3267, "lr": 1.134006936269999e-06, "epoch": 1.722010662604722, "percentage": 86.24, "elapsed_time": "0:48:10", "remaining_time": "0:07:41"}
+{"current_steps": 189, "total_steps": 218, "loss": 0.3171, "lr": 1.0610108779258043e-06, "epoch": 1.7311500380807312, "percentage": 86.7, "elapsed_time": "0:49:28", "remaining_time": "0:07:35"}
+{"current_steps": 190, "total_steps": 218, "loss": 0.2924, "lr": 9.903113209758098e-07, "epoch": 1.7402894135567402, "percentage": 87.16, "elapsed_time": "0:50:27", "remaining_time": "0:07:26"}
+{"current_steps": 191, "total_steps": 218, "loss": 0.3193, "lr": 9.2192642873008e-07, "epoch": 1.7494287890327493, "percentage": 87.61, "elapsed_time": "0:51:54", "remaining_time": "0:07:20"}
+{"current_steps": 192, "total_steps": 218, "loss": 0.2915, "lr": 8.558737698418762e-07, "epoch": 1.7585681645087585, "percentage": 88.07, "elapsed_time": "0:53:04", "remaining_time": "0:07:11"}
+{"current_steps": 193, "total_steps": 218, "loss": 0.3139, "lr": 7.921703137941172e-07, "epoch": 1.7677075399847677, "percentage": 88.53, "elapsed_time": "0:54:22", "remaining_time": "0:07:02"}
+{"current_steps": 194, "total_steps": 218, "loss": 0.31, "lr": 7.308324265397837e-07, "epoch": 1.7768469154607769, "percentage": 88.99, "elapsed_time": "0:55:26", "remaining_time": "0:06:51"}
+{"current_steps": 195, "total_steps": 218, "loss": 0.3264, "lr": 6.718758662973524e-07, "epoch": 1.785986290936786, "percentage": 89.45, "elapsed_time": "0:57:18", "remaining_time": "0:06:45"}
+{"current_steps": 196, "total_steps": 218, "loss": 0.3187, "lr": 6.153157795023956e-07, "epoch": 1.7951256664127953, "percentage": 89.91, "elapsed_time": "0:58:34", "remaining_time": "0:06:34"}
+{"current_steps": 197, "total_steps": 218, "loss": 0.3249, "lr": 5.611666969163243e-07, "epoch": 1.8042650418888042, "percentage": 90.37, "elapsed_time": "0:59:59", "remaining_time": "0:06:23"}
+{"current_steps": 198, "total_steps": 218, "loss": 0.3174, "lr": 5.094425298933136e-07, "epoch": 1.8134044173648134, "percentage": 90.83, "elapsed_time": "1:01:28", "remaining_time": "0:06:12"}
+{"current_steps": 199, "total_steps": 218, "loss": 0.3278, "lr": 4.6015656680636234e-07, "epoch": 1.8225437928408226, "percentage": 91.28, "elapsed_time": "1:02:46", "remaining_time": "0:05:59"}
+{"current_steps": 200, "total_steps": 218, "loss": 0.3167, "lr": 4.133214696333943e-07, "epoch": 1.8316831683168315, "percentage": 91.74, "elapsed_time": "1:04:11", "remaining_time": "0:05:46"}
+{"current_steps": 201, "total_steps": 218, "loss": 0.3189, "lr": 3.6894927070429744e-07, "epoch": 1.8408225437928407, "percentage": 92.2, "elapsed_time": "1:06:43", "remaining_time": "0:05:38"}
+{"current_steps": 202, "total_steps": 218, "loss": 0.3153, "lr": 3.2705136960970554e-07, "epoch": 1.84996191926885, "percentage": 92.66, "elapsed_time": "1:08:11", "remaining_time": "0:05:24"}
+{"current_steps": 203, "total_steps": 218, "loss": 0.3178, "lr": 2.8763853027236277e-07, "epoch": 1.859101294744859, "percentage": 93.12, "elapsed_time": "1:09:14", "remaining_time": "0:05:07"}
+{"current_steps": 204, "total_steps": 218, "loss": 0.3042, "lr": 2.507208781817638e-07, "epoch": 1.8682406702208683, "percentage": 93.58, "elapsed_time": "1:10:23", "remaining_time": "0:04:49"}
+{"current_steps": 205, "total_steps": 218, "loss": 0.3121, "lr": 2.1630789779284677e-07, "epoch": 1.8773800456968774, "percentage": 94.04, "elapsed_time": "1:11:36", "remaining_time": "0:04:32"}
+{"current_steps": 206, "total_steps": 218, "loss": 0.3083, "lr": 1.844084300893456e-07, "epoch": 1.8865194211728866, "percentage": 94.5, "elapsed_time": "1:13:03", "remaining_time": "0:04:15"}
+{"current_steps": 207, "total_steps": 218, "loss": 0.3198, "lr": 1.55030670312476e-07, "epoch": 1.8956587966488958, "percentage": 94.95, "elapsed_time": "1:14:29", "remaining_time": "0:03:57"}
+{"current_steps": 208, "total_steps": 218, "loss": 0.3137, "lr": 1.2818216585549824e-07, "epoch": 1.9047981721249048, "percentage": 95.41, "elapsed_time": "1:16:04", "remaining_time": "0:03:39"}
+{"current_steps": 209, "total_steps": 218, "loss": 0.3199, "lr": 1.0386981432474075e-07, "epoch": 1.913937547600914, "percentage": 95.87, "elapsed_time": "1:17:27", "remaining_time": "0:03:20"}
+{"current_steps": 210, "total_steps": 218, "loss": 0.3091, "lr": 8.209986176753947e-08, "epoch": 1.9230769230769231, "percentage": 96.33, "elapsed_time": "1:18:41", "remaining_time": "0:02:59"}
+{"current_steps": 211, "total_steps": 218, "loss": 0.3267, "lr": 6.287790106757396e-08, "epoch": 1.932216298552932, "percentage": 96.79, "elapsed_time": "1:20:12", "remaining_time": "0:02:39"}
+{"current_steps": 212, "total_steps": 218, "loss": 0.3084, "lr": 4.6208870508017703e-08, "epoch": 1.9413556740289413, "percentage": 97.25, "elapsed_time": "1:21:25", "remaining_time": "0:02:18"}
+{"current_steps": 213, "total_steps": 218, "loss": 0.308, "lr": 3.2097052502843005e-08, "epoch": 1.9504950495049505, "percentage": 97.71, "elapsed_time": "1:23:01", "remaining_time": "0:01:56"}
+{"current_steps": 214, "total_steps": 218, "loss": 0.2959, "lr": 2.054607249663665e-08, "epoch": 1.9596344249809596, "percentage": 98.17, "elapsed_time": "1:24:11", "remaining_time": "0:01:34"}
+{"current_steps": 215, "total_steps": 218, "loss": 0.325, "lr": 1.1558898033191545e-08, "epoch": 1.9687738004569688, "percentage": 98.62, "elapsed_time": "1:25:36", "remaining_time": "0:01:11"}
+{"current_steps": 216, "total_steps": 218, "loss": 0.3208, "lr": 5.137837993121064e-09, "epoch": 1.977913175932978, "percentage": 99.08, "elapsed_time": "1:26:51", "remaining_time": "0:00:48"}
+{"current_steps": 217, "total_steps": 218, "loss": 0.3123, "lr": 1.2845420006879494e-09, "epoch": 1.9870525514089872, "percentage": 99.54, "elapsed_time": "1:28:12", "remaining_time": "0:00:24"}
+{"current_steps": 218, "total_steps": 218, "loss": 0.3137, "lr": 0.0, "epoch": 1.9961919268849961, "percentage": 100.0, "elapsed_time": "1:29:36", "remaining_time": "0:00:00"}
+{"current_steps": 218, "total_steps": 218, "epoch": 1.9961919268849961, "percentage": 100.0, "elapsed_time": "1:30:58", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1568 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9961919268849961,
+  "eval_steps": 500,
+  "global_step": 218,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00913937547600914,
+      "grad_norm": 3.3369264602661133,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.6708,
+      "step": 1
+    },
+    {
+      "epoch": 0.01827875095201828,
+      "grad_norm": 3.4893620014190674,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.6794,
+      "step": 2
+    },
+    {
+      "epoch": 0.027418126428027417,
+      "grad_norm": 3.4242701530456543,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.6599,
+      "step": 3
+    },
+    {
+      "epoch": 0.03655750190403656,
+      "grad_norm": 3.155944347381592,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.6689,
+      "step": 4
+    },
+    {
+      "epoch": 0.0456968773800457,
+      "grad_norm": 2.458157539367676,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.6512,
+      "step": 5
+    },
+    {
+      "epoch": 0.05483625285605483,
+      "grad_norm": 1.8310825824737549,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.6187,
+      "step": 6
+    },
+    {
+      "epoch": 0.06397562833206398,
+      "grad_norm": 1.7105038166046143,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.6179,
+      "step": 7
+    },
+    {
+      "epoch": 0.07311500380807312,
+      "grad_norm": 1.7482938766479492,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.6075,
+      "step": 8
+    },
+    {
+      "epoch": 0.08225437928408226,
+      "grad_norm": 1.6708910465240479,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.5964,
+      "step": 9
+    },
+    {
+      "epoch": 0.0913937547600914,
+      "grad_norm": 1.1437326669692993,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.5533,
+      "step": 10
+    },
+    {
+      "epoch": 0.10053313023610053,
+      "grad_norm": 1.5597337484359741,
+      "learning_rate": 1e-05,
+      "loss": 0.5382,
+      "step": 11
+    },
+    {
+      "epoch": 0.10967250571210967,
+      "grad_norm": 1.0245758295059204,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 0.5104,
+      "step": 12
+    },
+    {
+      "epoch": 0.1188118811881188,
+      "grad_norm": 0.8286274671554565,
+      "learning_rate": 1.181818181818182e-05,
+      "loss": 0.5173,
+      "step": 13
+    },
+    {
+      "epoch": 0.12795125666412796,
+      "grad_norm": 1.0838040113449097,
+      "learning_rate": 1.2727272727272728e-05,
+      "loss": 0.5133,
+      "step": 14
+    },
+    {
+      "epoch": 0.1370906321401371,
+      "grad_norm": 1.0685889720916748,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 0.5109,
+      "step": 15
+    },
+    {
+      "epoch": 0.14623000761614624,
+      "grad_norm": 0.794349193572998,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 0.4618,
+      "step": 16
+    },
+    {
+      "epoch": 0.15536938309215537,
+      "grad_norm": 0.8422227501869202,
+      "learning_rate": 1.5454545454545454e-05,
+      "loss": 0.4867,
+      "step": 17
+    },
+    {
+      "epoch": 0.16450875856816452,
+      "grad_norm": 0.7492879629135132,
+      "learning_rate": 1.6363636363636366e-05,
+      "loss": 0.4731,
+      "step": 18
+    },
+    {
+      "epoch": 0.17364813404417365,
+      "grad_norm": 0.6844476461410522,
+      "learning_rate": 1.7272727272727274e-05,
+      "loss": 0.4439,
+      "step": 19
+    },
+    {
+      "epoch": 0.1827875095201828,
+      "grad_norm": 0.7250885367393494,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.4716,
+      "step": 20
+    },
+    {
+      "epoch": 0.19192688499619193,
+      "grad_norm": 0.67299485206604,
+      "learning_rate": 1.9090909090909094e-05,
+      "loss": 0.4412,
+      "step": 21
+    },
+    {
+      "epoch": 0.20106626047220105,
+      "grad_norm": 0.6760995388031006,
+      "learning_rate": 2e-05,
+      "loss": 0.4459,
+      "step": 22
+    },
+    {
+      "epoch": 0.2102056359482102,
+      "grad_norm": 0.5327174067497253,
+      "learning_rate": 1.9998715457999313e-05,
+      "loss": 0.45,
+      "step": 23
+    },
+    {
+      "epoch": 0.21934501142421933,
+      "grad_norm": 0.5728371143341064,
+      "learning_rate": 1.999486216200688e-05,
+      "loss": 0.4362,
+      "step": 24
+    },
+    {
+      "epoch": 0.2284843869002285,
+      "grad_norm": 0.4978387951850891,
+      "learning_rate": 1.9988441101966807e-05,
+      "loss": 0.4562,
+      "step": 25
+    },
+    {
+      "epoch": 0.2376237623762376,
+      "grad_norm": 0.5106445550918579,
+      "learning_rate": 1.9979453927503366e-05,
+      "loss": 0.4684,
+      "step": 26
+    },
+    {
+      "epoch": 0.24676313785224677,
+      "grad_norm": 0.4982711374759674,
+      "learning_rate": 1.9967902947497158e-05,
+      "loss": 0.4526,
+      "step": 27
+    },
+    {
+      "epoch": 0.2559025133282559,
+      "grad_norm": 0.5087048411369324,
+      "learning_rate": 1.9953791129491985e-05,
+      "loss": 0.4468,
+      "step": 28
+    },
+    {
+      "epoch": 0.26504188880426505,
+      "grad_norm": 0.47533684968948364,
+      "learning_rate": 1.9937122098932428e-05,
+      "loss": 0.4272,
+      "step": 29
+    },
+    {
+      "epoch": 0.2741812642802742,
+      "grad_norm": 0.4664396643638611,
+      "learning_rate": 1.991790013823246e-05,
+      "loss": 0.4456,
+      "step": 30
+    },
+    {
+      "epoch": 0.2833206397562833,
+      "grad_norm": 0.44873371720314026,
+      "learning_rate": 1.9896130185675263e-05,
+      "loss": 0.4436,
+      "step": 31
+    },
+    {
+      "epoch": 0.2924600152322925,
+      "grad_norm": 0.46020084619522095,
+      "learning_rate": 1.9871817834144506e-05,
+      "loss": 0.4285,
+      "step": 32
+    },
+    {
+      "epoch": 0.3015993907083016,
+      "grad_norm": 0.6484828591346741,
+      "learning_rate": 1.9844969329687526e-05,
+      "loss": 0.4385,
+      "step": 33
+    },
+    {
+      "epoch": 0.31073876618431073,
+      "grad_norm": 0.40165239572525024,
+      "learning_rate": 1.9815591569910654e-05,
+      "loss": 0.4159,
+      "step": 34
+    },
+    {
+      "epoch": 0.31987814166031986,
+      "grad_norm": 0.42455559968948364,
+      "learning_rate": 1.9783692102207156e-05,
+      "loss": 0.4407,
+      "step": 35
+    },
+    {
+      "epoch": 0.32901751713632904,
+      "grad_norm": 0.4265769124031067,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 0.3885,
+      "step": 36
+    },
+    {
+      "epoch": 0.33815689261233817,
+      "grad_norm": 0.38099807500839233,
+      "learning_rate": 1.971236146972764e-05,
+      "loss": 0.3883,
+      "step": 37
+    },
+    {
+      "epoch": 0.3472962680883473,
+      "grad_norm": 0.43669813871383667,
+      "learning_rate": 1.9672948630390296e-05,
+      "loss": 0.3881,
+      "step": 38
+    },
+    {
+      "epoch": 0.3564356435643564,
+      "grad_norm": 0.39924174547195435,
+      "learning_rate": 1.9631050729295705e-05,
+      "loss": 0.4378,
+      "step": 39
+    },
+    {
+      "epoch": 0.3655750190403656,
+      "grad_norm": 0.44854018092155457,
+      "learning_rate": 1.9586678530366607e-05,
+      "loss": 0.4125,
+      "step": 40
+    },
+    {
+      "epoch": 0.3747143945163747,
+      "grad_norm": 0.3688861131668091,
+      "learning_rate": 1.953984343319364e-05,
+      "loss": 0.3944,
+      "step": 41
+    },
+    {
+      "epoch": 0.38385376999238385,
+      "grad_norm": 0.3711301386356354,
+      "learning_rate": 1.949055747010669e-05,
+      "loss": 0.4164,
+      "step": 42
+    },
+    {
+      "epoch": 0.392993145468393,
+      "grad_norm": 0.4008907675743103,
+      "learning_rate": 1.9438833303083677e-05,
+      "loss": 0.4196,
+      "step": 43
+    },
+    {
+      "epoch": 0.4021325209444021,
+      "grad_norm": 0.42354318499565125,
+      "learning_rate": 1.9384684220497605e-05,
+      "loss": 0.3882,
+      "step": 44
+    },
+    {
+      "epoch": 0.4112718964204113,
+      "grad_norm": 0.42434418201446533,
+      "learning_rate": 1.932812413370265e-05,
+      "loss": 0.4301,
+      "step": 45
+    },
+    {
+      "epoch": 0.4204112718964204,
+      "grad_norm": 0.4077893793582916,
+      "learning_rate": 1.926916757346022e-05,
+      "loss": 0.3943,
+      "step": 46
+    },
+    {
+      "epoch": 0.42955064737242954,
+      "grad_norm": 0.3807850182056427,
+      "learning_rate": 1.9207829686205882e-05,
+      "loss": 0.3888,
+      "step": 47
+    },
+    {
+      "epoch": 0.43869002284843867,
+      "grad_norm": 0.3933984637260437,
+      "learning_rate": 1.9144126230158127e-05,
+      "loss": 0.4084,
+      "step": 48
+    },
+    {
+      "epoch": 0.44782939832444785,
+      "grad_norm": 0.45636460185050964,
+      "learning_rate": 1.9078073571269922e-05,
+      "loss": 0.3892,
+      "step": 49
+    },
+    {
+      "epoch": 0.456968773800457,
+      "grad_norm": 0.3460674583911896,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 0.3911,
+      "step": 50
+    },
+    {
+      "epoch": 0.4661081492764661,
+      "grad_norm": 0.40278884768486023,
+      "learning_rate": 1.8938989122074195e-05,
+      "loss": 0.3985,
+      "step": 51
+    },
+    {
+      "epoch": 0.4752475247524752,
+      "grad_norm": 0.4178655743598938,
+      "learning_rate": 1.8865993063730003e-05,
+      "loss": 0.4156,
+      "step": 52
+    },
+    {
+      "epoch": 0.4843869002284844,
+      "grad_norm": 0.3947036862373352,
+      "learning_rate": 1.8790719257292175e-05,
+      "loss": 0.4189,
+      "step": 53
+    },
+    {
+      "epoch": 0.49352627570449353,
+      "grad_norm": 0.3686043322086334,
+      "learning_rate": 1.8713187041233896e-05,
+      "loss": 0.4105,
+      "step": 54
+    },
+    {
+      "epoch": 0.5026656511805027,
+      "grad_norm": 0.4284152090549469,
+      "learning_rate": 1.8633416334232754e-05,
+      "loss": 0.389,
+      "step": 55
+    },
+    {
+      "epoch": 0.5118050266565118,
+      "grad_norm": 0.40143266320228577,
+      "learning_rate": 1.8551427630053464e-05,
+      "loss": 0.4168,
+      "step": 56
+    },
+    {
+      "epoch": 0.5209444021325209,
+      "grad_norm": 0.37129855155944824,
+      "learning_rate": 1.8467241992282842e-05,
+      "loss": 0.3745,
+      "step": 57
+    },
+    {
+      "epoch": 0.5300837776085301,
+      "grad_norm": 0.4992600679397583,
+      "learning_rate": 1.8380881048918406e-05,
+      "loss": 0.4024,
+      "step": 58
+    },
+    {
+      "epoch": 0.5392231530845393,
+      "grad_norm": 0.403962641954422,
+      "learning_rate": 1.8292366986811952e-05,
+      "loss": 0.379,
+      "step": 59
+    },
+    {
+      "epoch": 0.5483625285605483,
+      "grad_norm": 0.3711932301521301,
+      "learning_rate": 1.820172254596956e-05,
+      "loss": 0.3959,
+      "step": 60
+    },
+    {
+      "epoch": 0.5575019040365575,
+      "grad_norm": 0.45666763186454773,
+      "learning_rate": 1.8108971013709512e-05,
+      "loss": 0.3833,
+      "step": 61
+    },
+    {
+      "epoch": 0.5666412795125666,
+      "grad_norm": 0.34401726722717285,
+      "learning_rate": 1.8014136218679566e-05,
+      "loss": 0.3847,
+      "step": 62
+    },
+    {
+      "epoch": 0.5757806549885758,
+      "grad_norm": 0.36564773321151733,
+      "learning_rate": 1.79172425247352e-05,
+      "loss": 0.384,
+      "step": 63
+    },
+    {
+      "epoch": 0.584920030464585,
+      "grad_norm": 0.3763687014579773,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.3827,
+      "step": 64
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 0.3825934827327728,
+      "learning_rate": 1.771737853387202e-05,
+      "loss": 0.3971,
+      "step": 65
+    },
+    {
+      "epoch": 0.6031987814166032,
+      "grad_norm": 0.3348219394683838,
+      "learning_rate": 1.7614459583691346e-05,
+      "loss": 0.3965,
+      "step": 66
+    },
+    {
+      "epoch": 0.6123381568926123,
+      "grad_norm": 0.3712629973888397,
+      "learning_rate": 1.7509584414881114e-05,
+      "loss": 0.3933,
+      "step": 67
+    },
+    {
+      "epoch": 0.6214775323686215,
+      "grad_norm": 0.3879682123661041,
+      "learning_rate": 1.7402779970753156e-05,
+      "loss": 0.4008,
+      "step": 68
+    },
+    {
+      "epoch": 0.6306169078446306,
+      "grad_norm": 0.3735283315181732,
+      "learning_rate": 1.7294073690266343e-05,
+      "loss": 0.4058,
+      "step": 69
+    },
+    {
+      "epoch": 0.6397562833206397,
+      "grad_norm": 0.36928698420524597,
+      "learning_rate": 1.7183493500977277e-05,
+      "loss": 0.3911,
+      "step": 70
+    },
+    {
+      "epoch": 0.6488956587966489,
+      "grad_norm": 0.32693177461624146,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.389,
+      "step": 71
+    },
+    {
+      "epoch": 0.6580350342726581,
+      "grad_norm": 0.35049450397491455,
+      "learning_rate": 1.6956825506034866e-05,
+      "loss": 0.3824,
+      "step": 72
+    },
+    {
+      "epoch": 0.6671744097486672,
+      "grad_norm": 0.3910599946975708,
+      "learning_rate": 1.6840795933293464e-05,
+      "loss": 0.3797,
+      "step": 73
+    },
+    {
+      "epoch": 0.6763137852246763,
+      "grad_norm": 0.34450212121009827,
+      "learning_rate": 1.672300890261317e-05,
+      "loss": 0.3769,
+      "step": 74
+    },
+    {
+      "epoch": 0.6854531607006854,
+      "grad_norm": 0.3638371229171753,
+      "learning_rate": 1.6603494674471595e-05,
+      "loss": 0.3765,
+      "step": 75
+    },
+    {
+      "epoch": 0.6945925361766946,
+      "grad_norm": 0.3630662262439728,
+      "learning_rate": 1.6482283953077887e-05,
+      "loss": 0.402,
+      "step": 76
+    },
+    {
+      "epoch": 0.7037319116527038,
+      "grad_norm": 0.3464076519012451,
+      "learning_rate": 1.635940787848455e-05,
+      "loss": 0.3776,
+      "step": 77
+    },
+    {
+      "epoch": 0.7128712871287128,
+      "grad_norm": 0.35827362537384033,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 0.381,
+      "step": 78
+    },
+    {
+      "epoch": 0.722010662604722,
+      "grad_norm": 0.3732692301273346,
+      "learning_rate": 1.6108786361015145e-05,
+      "loss": 0.3723,
+      "step": 79
+    },
+    {
+      "epoch": 0.7311500380807312,
+      "grad_norm": 0.3525165617465973,
+      "learning_rate": 1.598110530491216e-05,
+      "loss": 0.4152,
+      "step": 80
+    },
+    {
+      "epoch": 0.7402894135567403,
+      "grad_norm": 0.39010149240493774,
+      "learning_rate": 1.5851887652614238e-05,
+      "loss": 0.3937,
+      "step": 81
+    },
+    {
+      "epoch": 0.7494287890327495,
+      "grad_norm": 0.349071741104126,
+      "learning_rate": 1.5721166601221697e-05,
+      "loss": 0.4073,
+      "step": 82
+    },
+    {
+      "epoch": 0.7585681645087585,
+      "grad_norm": 0.33521854877471924,
+      "learning_rate": 1.5588975734070717e-05,
+      "loss": 0.3756,
+      "step": 83
+    },
+    {
+      "epoch": 0.7677075399847677,
+      "grad_norm": 0.36783722043037415,
+      "learning_rate": 1.5455349012105488e-05,
+      "loss": 0.3902,
+      "step": 84
+    },
+    {
+      "epoch": 0.7768469154607769,
+      "grad_norm": 0.3330143690109253,
+      "learning_rate": 1.5320320765153367e-05,
+      "loss": 0.3879,
+      "step": 85
+    },
+    {
+      "epoch": 0.785986290936786,
+      "grad_norm": 0.35695841908454895,
+      "learning_rate": 1.5183925683105254e-05,
+      "loss": 0.3887,
+      "step": 86
+    },
+    {
+      "epoch": 0.7951256664127951,
+      "grad_norm": 0.35579657554626465,
+      "learning_rate": 1.504619880700346e-05,
+      "loss": 0.3859,
+      "step": 87
+    },
+    {
+      "epoch": 0.8042650418888042,
+      "grad_norm": 0.3615005314350128,
+      "learning_rate": 1.4907175520039381e-05,
+      "loss": 0.381,
+      "step": 88
+    },
+    {
+      "epoch": 0.8134044173648134,
+      "grad_norm": 0.37881505489349365,
+      "learning_rate": 1.4766891538463255e-05,
+      "loss": 0.3798,
+      "step": 89
+    },
+    {
+      "epoch": 0.8225437928408226,
+      "grad_norm": 0.3448372483253479,
+      "learning_rate": 1.4625382902408356e-05,
+      "loss": 0.376,
+      "step": 90
+    },
+    {
+      "epoch": 0.8316831683168316,
+      "grad_norm": 0.34421786665916443,
+      "learning_rate": 1.448268596663197e-05,
+      "loss": 0.3692,
+      "step": 91
+    },
+    {
+      "epoch": 0.8408225437928408,
+      "grad_norm": 0.32549339532852173,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 0.385,
+      "step": 92
+    },
+    {
+      "epoch": 0.84996191926885,
+      "grad_norm": 0.34452754259109497,
+      "learning_rate": 1.419387413194657e-05,
+      "loss": 0.3711,
+      "step": 93
+    },
+    {
+      "epoch": 0.8591012947448591,
+      "grad_norm": 0.3506733477115631,
+      "learning_rate": 1.4047833431223938e-05,
+      "loss": 0.3772,
+      "step": 94
+    },
+    {
+      "epoch": 0.8682406702208683,
+      "grad_norm": 0.3662183880805969,
+      "learning_rate": 1.390075280809047e-05,
+      "loss": 0.3791,
+      "step": 95
+    },
+    {
+      "epoch": 0.8773800456968773,
+      "grad_norm": 0.3463532030582428,
+      "learning_rate": 1.3752670048793744e-05,
+      "loss": 0.3767,
+      "step": 96
+    },
+    {
+      "epoch": 0.8865194211728865,
+      "grad_norm": 0.3397160768508911,
+      "learning_rate": 1.3603623197038536e-05,
+      "loss": 0.3831,
+      "step": 97
+    },
+    {
+      "epoch": 0.8956587966488957,
+      "grad_norm": 0.3651241660118103,
+      "learning_rate": 1.3453650544213078e-05,
+      "loss": 0.3933,
+      "step": 98
+    },
+    {
+      "epoch": 0.9047981721249048,
+      "grad_norm": 0.3426673710346222,
+      "learning_rate": 1.3302790619551673e-05,
+      "loss": 0.366,
+      "step": 99
+    },
+    {
+      "epoch": 0.913937547600914,
+      "grad_norm": 0.32238805294036865,
+      "learning_rate": 1.315108218023621e-05,
+      "loss": 0.3824,
+      "step": 100
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.3311628997325897,
+      "learning_rate": 1.2998564201439117e-05,
+      "loss": 0.3845,
+      "step": 101
+    },
+    {
+      "epoch": 0.9322162985529322,
+      "grad_norm": 0.34884315729141235,
+      "learning_rate": 1.2845275866310325e-05,
+      "loss": 0.3819,
+      "step": 102
+    },
+    {
+      "epoch": 0.9413556740289414,
+      "grad_norm": 0.32266736030578613,
+      "learning_rate": 1.2691256555910769e-05,
+      "loss": 0.3759,
+      "step": 103
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 0.3028276264667511,
+      "learning_rate": 1.2536545839095074e-05,
+      "loss": 0.3963,
+      "step": 104
+    },
+    {
+      "epoch": 0.9596344249809596,
+      "grad_norm": 0.3258204460144043,
+      "learning_rate": 1.2381183462345983e-05,
+      "loss": 0.3805,
+      "step": 105
+    },
+    {
+      "epoch": 0.9687738004569688,
+      "grad_norm": 0.30626070499420166,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 0.3781,
+      "step": 106
+    },
+    {
+      "epoch": 0.9779131759329779,
+      "grad_norm": 0.29698455333709717,
+      "learning_rate": 1.206866354180891e-05,
+      "loss": 0.3777,
+      "step": 107
+    },
+    {
+      "epoch": 0.9870525514089871,
+      "grad_norm": 0.30517199635505676,
+      "learning_rate": 1.1911586287013726e-05,
+      "loss": 0.3822,
+      "step": 108
+    },
+    {
+      "epoch": 0.9961919268849961,
+      "grad_norm": 0.30879127979278564,
+      "learning_rate": 1.1754017929643818e-05,
+      "loss": 0.3761,
+      "step": 109
+    },
+    {
+      "epoch": 1.0053313023610053,
+      "grad_norm": 0.547318160533905,
+      "learning_rate": 1.1595998950333794e-05,
+      "loss": 0.5449,
+      "step": 110
+    },
+    {
+      "epoch": 1.0144706778370145,
+      "grad_norm": 0.37278491258621216,
+      "learning_rate": 1.143756994548682e-05,
+      "loss": 0.3479,
+      "step": 111
+    },
+    {
+      "epoch": 1.0236100533130237,
+      "grad_norm": 0.35126781463623047,
+      "learning_rate": 1.1278771616845061e-05,
+      "loss": 0.338,
+      "step": 112
+    },
+    {
+      "epoch": 1.0327494287890326,
+      "grad_norm": 0.37905386090278625,
+      "learning_rate": 1.1119644761033079e-05,
+      "loss": 0.3353,
+      "step": 113
+    },
+    {
+      "epoch": 1.0418888042650418,
+      "grad_norm": 0.41645359992980957,
+      "learning_rate": 1.0960230259076819e-05,
+      "loss": 0.3257,
+      "step": 114
+    },
+    {
+      "epoch": 1.051028179741051,
+      "grad_norm": 0.418813019990921,
+      "learning_rate": 1.0800569065900935e-05,
+      "loss": 0.3521,
+      "step": 115
+    },
+    {
+      "epoch": 1.0601675552170602,
+      "grad_norm": 0.41467365622520447,
+      "learning_rate": 1.064070219980713e-05,
+      "loss": 0.3117,
+      "step": 116
+    },
+    {
+      "epoch": 1.0693069306930694,
+      "grad_norm": 0.4041651487350464,
+      "learning_rate": 1.0480670731936209e-05,
+      "loss": 0.3093,
+      "step": 117
+    },
+    {
+      "epoch": 1.0784463061690786,
+      "grad_norm": 0.3533031642436981,
+      "learning_rate": 1.0320515775716556e-05,
+      "loss": 0.2998,
+      "step": 118
+    },
+    {
+      "epoch": 1.0875856816450875,
+      "grad_norm": 0.41691580414772034,
+      "learning_rate": 1.0160278476301739e-05,
+      "loss": 0.3737,
+      "step": 119
+    },
+    {
+      "epoch": 1.0967250571210967,
+      "grad_norm": 0.36301714181900024,
+      "learning_rate": 1e-05,
+      "loss": 0.3267,
+      "step": 120
+    },
+    {
+      "epoch": 1.1058644325971059,
+      "grad_norm": 0.3264053761959076,
+      "learning_rate": 9.839721523698265e-06,
+      "loss": 0.2584,
+      "step": 121
+    },
+    {
+      "epoch": 1.115003808073115,
+      "grad_norm": 0.4043513238430023,
+      "learning_rate": 9.67948422428345e-06,
+      "loss": 0.3526,
+      "step": 122
+    },
+    {
+      "epoch": 1.1241431835491242,
+      "grad_norm": 0.3653642237186432,
+      "learning_rate": 9.519329268063795e-06,
+      "loss": 0.3425,
+      "step": 123
+    },
+    {
+      "epoch": 1.1332825590251332,
+      "grad_norm": 0.33410775661468506,
+      "learning_rate": 9.359297800192873e-06,
+      "loss": 0.3097,
+      "step": 124
+    },
+    {
+      "epoch": 1.1424219345011424,
+      "grad_norm": 0.340742826461792,
+      "learning_rate": 9.199430934099068e-06,
+      "loss": 0.3052,
+      "step": 125
+    },
+    {
+      "epoch": 1.1515613099771516,
+      "grad_norm": 0.3352021872997284,
+      "learning_rate": 9.039769740923183e-06,
+      "loss": 0.2977,
+      "step": 126
+    },
+    {
+      "epoch": 1.1607006854531607,
+      "grad_norm": 0.3389112949371338,
+      "learning_rate": 8.880355238966923e-06,
+      "loss": 0.3113,
+      "step": 127
+    },
+    {
+      "epoch": 1.16984006092917,
+      "grad_norm": 0.3363248407840729,
+      "learning_rate": 8.721228383154939e-06,
+      "loss": 0.3205,
+      "step": 128
+    },
+    {
+      "epoch": 1.178979436405179,
+      "grad_norm": 0.34208640456199646,
+      "learning_rate": 8.562430054513184e-06,
+      "loss": 0.3176,
+      "step": 129
+    },
+    {
+      "epoch": 1.188118811881188,
+      "grad_norm": 0.3295469284057617,
+      "learning_rate": 8.404001049666211e-06,
+      "loss": 0.3201,
+      "step": 130
+    },
+    {
+      "epoch": 1.1972581873571972,
+      "grad_norm": 0.3238345682621002,
+      "learning_rate": 8.245982070356186e-06,
+      "loss": 0.297,
+      "step": 131
+    },
+    {
+      "epoch": 1.2063975628332064,
+      "grad_norm": 0.3155887722969055,
+      "learning_rate": 8.08841371298628e-06,
+      "loss": 0.3163,
+      "step": 132
+    },
+    {
+      "epoch": 1.2155369383092156,
+      "grad_norm": 0.30575722455978394,
+      "learning_rate": 7.931336458191092e-06,
+      "loss": 0.3421,
+      "step": 133
+    },
+    {
+      "epoch": 1.2246763137852246,
+      "grad_norm": 0.31150344014167786,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.3097,
+      "step": 134
+    },
+    {
+      "epoch": 1.2338156892612338,
+      "grad_norm": 0.32414835691452026,
+      "learning_rate": 7.618816537654018e-06,
+      "loss": 0.3201,
+      "step": 135
+    },
+    {
+      "epoch": 1.242955064737243,
+      "grad_norm": 0.2960313558578491,
+      "learning_rate": 7.463454160904928e-06,
+      "loss": 0.2807,
+      "step": 136
+    },
+    {
+      "epoch": 1.2520944402132521,
+      "grad_norm": 0.308651864528656,
+      "learning_rate": 7.308743444089232e-06,
+      "loss": 0.3258,
+      "step": 137
+    },
+    {
+      "epoch": 1.2612338156892613,
+      "grad_norm": 0.3236067593097687,
+      "learning_rate": 7.154724133689677e-06,
+      "loss": 0.2958,
+      "step": 138
+    },
+    {
+      "epoch": 1.2703731911652705,
+      "grad_norm": 0.3053479492664337,
+      "learning_rate": 7.001435798560884e-06,
+      "loss": 0.321,
+      "step": 139
+    },
+    {
+      "epoch": 1.2795125666412794,
+      "grad_norm": 0.3023087978363037,
+      "learning_rate": 6.848917819763794e-06,
+      "loss": 0.3006,
+      "step": 140
+    },
+    {
+      "epoch": 1.2886519421172886,
+      "grad_norm": 0.3476320505142212,
+      "learning_rate": 6.697209380448333e-06,
+      "loss": 0.3311,
+      "step": 141
+    },
+    {
+      "epoch": 1.2977913175932978,
+      "grad_norm": 0.3587212562561035,
+      "learning_rate": 6.546349455786926e-06,
+      "loss": 0.3646,
+      "step": 142
+    },
+    {
+      "epoch": 1.306930693069307,
+      "grad_norm": 0.28520774841308594,
+      "learning_rate": 6.396376802961468e-06,
+      "loss": 0.3165,
+      "step": 143
+    },
+    {
+      "epoch": 1.316070068545316,
+      "grad_norm": 0.28903257846832275,
+      "learning_rate": 6.24732995120626e-06,
+      "loss": 0.3019,
+      "step": 144
+    },
+    {
+      "epoch": 1.3252094440213251,
+      "grad_norm": 0.3147772252559662,
+      "learning_rate": 6.099247191909532e-06,
+      "loss": 0.2998,
+      "step": 145
+    },
+    {
+      "epoch": 1.3343488194973343,
+      "grad_norm": 0.32797104120254517,
+      "learning_rate": 5.952166568776062e-06,
+      "loss": 0.3368,
+      "step": 146
+    },
+    {
+      "epoch": 1.3434881949733435,
+      "grad_norm": 0.2969732880592346,
+      "learning_rate": 5.806125868053433e-06,
+      "loss": 0.2851,
+      "step": 147
+    },
+    {
+      "epoch": 1.3526275704493527,
+      "grad_norm": 0.3113080561161041,
+      "learning_rate": 5.66116260882442e-06,
+      "loss": 0.2959,
+      "step": 148
+    },
+    {
+      "epoch": 1.3617669459253618,
+      "grad_norm": 0.32516226172447205,
+      "learning_rate": 5.517314033368031e-06,
+      "loss": 0.3239,
+      "step": 149
+    },
+    {
+      "epoch": 1.370906321401371,
+      "grad_norm": 0.32933881878852844,
+      "learning_rate": 5.37461709759165e-06,
+      "loss": 0.3288,
+      "step": 150
+    },
+    {
+      "epoch": 1.3838537699923839,
+      "grad_norm": 0.29292726516723633,
+      "learning_rate": 5.233108461536749e-06,
+      "loss": 0.3226,
+      "step": 151
+    },
+    {
+      "epoch": 1.392993145468393,
+      "grad_norm": 0.3006382882595062,
+      "learning_rate": 5.092824479960625e-06,
+      "loss": 0.3039,
+      "step": 152
+    },
+    {
+      "epoch": 1.4021325209444022,
+      "grad_norm": 0.29254230856895447,
+      "learning_rate": 4.9538011929965436e-06,
+      "loss": 0.3441,
+      "step": 153
+    },
+    {
+      "epoch": 1.4112718964204114,
+      "grad_norm": 0.30929845571517944,
+      "learning_rate": 4.81607431689475e-06,
+      "loss": 0.3127,
+      "step": 154
+    },
+    {
+      "epoch": 1.4204112718964204,
+      "grad_norm": 0.28565043210983276,
+      "learning_rate": 4.679679234846636e-06,
+      "loss": 0.3119,
+      "step": 155
+    },
+    {
+      "epoch": 1.4295506473724295,
+      "grad_norm": 0.3046690821647644,
+      "learning_rate": 4.544650987894514e-06,
+      "loss": 0.2909,
+      "step": 156
+    },
+    {
+      "epoch": 1.4386900228484387,
+      "grad_norm": 0.279197096824646,
+      "learning_rate": 4.411024265929283e-06,
+      "loss": 0.3118,
+      "step": 157
+    },
+    {
+      "epoch": 1.447829398324448,
+      "grad_norm": 0.29681769013404846,
+      "learning_rate": 4.278833398778306e-06,
+      "loss": 0.3122,
+      "step": 158
+    },
+    {
+      "epoch": 1.4569687738004569,
+      "grad_norm": 0.28999167680740356,
+      "learning_rate": 4.148112347385762e-06,
+      "loss": 0.3073,
+      "step": 159
+    },
+    {
+      "epoch": 1.466108149276466,
+      "grad_norm": 0.3117202818393707,
+      "learning_rate": 4.01889469508784e-06,
+      "loss": 0.3206,
+      "step": 160
+    },
+    {
+      "epoch": 1.4752475247524752,
+      "grad_norm": 0.28692707419395447,
+      "learning_rate": 3.891213638984858e-06,
+      "loss": 0.3147,
+      "step": 161
+    },
+    {
+      "epoch": 1.4843869002284844,
+      "grad_norm": 0.2778036296367645,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.3249,
+      "step": 162
+    },
+    {
+      "epoch": 1.4935262757044936,
+      "grad_norm": 0.30285775661468506,
+      "learning_rate": 3.6405921215154492e-06,
+      "loss": 0.3121,
+      "step": 163
+    },
+    {
+      "epoch": 1.5026656511805028,
+      "grad_norm": 0.3020969033241272,
+      "learning_rate": 3.5177160469221184e-06,
+      "loss": 0.3003,
+      "step": 164
+    },
+    {
+      "epoch": 1.511805026656512,
+      "grad_norm": 0.2875075340270996,
+      "learning_rate": 3.3965053255284085e-06,
+      "loss": 0.3115,
+      "step": 165
+    },
+    {
+      "epoch": 1.520944402132521,
+      "grad_norm": 0.3074340522289276,
+      "learning_rate": 3.2769910973868314e-06,
+      "loss": 0.3131,
+      "step": 166
+    },
+    {
+      "epoch": 1.53008377760853,
+      "grad_norm": 0.2820333242416382,
+      "learning_rate": 3.1592040667065393e-06,
+      "loss": 0.2978,
+      "step": 167
+    },
+    {
+      "epoch": 1.5392231530845393,
+      "grad_norm": 0.3219679296016693,
+      "learning_rate": 3.0431744939651365e-06,
+      "loss": 0.3075,
+      "step": 168
+    },
+    {
+      "epoch": 1.5483625285605482,
+      "grad_norm": 0.2894546389579773,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.3107,
+      "step": 169
+    },
+    {
+      "epoch": 1.5575019040365574,
+      "grad_norm": 0.33814314007759094,
+      "learning_rate": 2.8165064990227255e-06,
+      "loss": 0.3338,
+      "step": 170
+    },
+    {
+      "epoch": 1.5666412795125666,
+      "grad_norm": 0.330655962228775,
+      "learning_rate": 2.7059263097336595e-06,
+      "loss": 0.3184,
+      "step": 171
+    },
+    {
+      "epoch": 1.5757806549885758,
+      "grad_norm": 0.29267704486846924,
+      "learning_rate": 2.597220029246846e-06,
+      "loss": 0.3241,
+      "step": 172
+    },
+    {
+      "epoch": 1.584920030464585,
+      "grad_norm": 0.30491986870765686,
+      "learning_rate": 2.490415585118887e-06,
+      "loss": 0.3033,
+      "step": 173
+    },
+    {
+      "epoch": 1.5940594059405941,
+      "grad_norm": 0.30731192231178284,
+      "learning_rate": 2.3855404163086558e-06,
+      "loss": 0.2965,
+      "step": 174
+    },
+    {
+      "epoch": 1.6031987814166033,
+      "grad_norm": 0.2904992699623108,
+      "learning_rate": 2.282621466127982e-06,
+      "loss": 0.3046,
+      "step": 175
+    },
+    {
+      "epoch": 1.6123381568926123,
+      "grad_norm": 0.31819531321525574,
+      "learning_rate": 2.1816851753197023e-06,
+      "loss": 0.2998,
+      "step": 176
+    },
+    {
+      "epoch": 1.6214775323686215,
+      "grad_norm": 0.30998897552490234,
+      "learning_rate": 2.082757475264804e-06,
+      "loss": 0.3047,
+      "step": 177
+    },
+    {
+      "epoch": 1.6306169078446306,
+      "grad_norm": 0.2906753718852997,
+      "learning_rate": 1.9858637813204352e-06,
+      "loss": 0.2906,
+      "step": 178
+    },
+    {
+      "epoch": 1.6397562833206396,
+      "grad_norm": 0.29853326082229614,
+      "learning_rate": 1.8910289862904917e-06,
+      "loss": 0.3223,
+      "step": 179
+    },
+    {
+      "epoch": 1.6488956587966488,
+      "grad_norm": 0.31702253222465515,
+      "learning_rate": 1.7982774540304404e-06,
+      "loss": 0.3286,
+      "step": 180
+    },
+    {
+      "epoch": 1.658035034272658,
+      "grad_norm": 0.2962207794189453,
+      "learning_rate": 1.7076330131880525e-06,
+      "loss": 0.3162,
+      "step": 181
+    },
+    {
+      "epoch": 1.6671744097486672,
+      "grad_norm": 0.2774161100387573,
+      "learning_rate": 1.6191189510815942e-06,
+      "loss": 0.3147,
+      "step": 182
+    },
+    {
+      "epoch": 1.6763137852246763,
+      "grad_norm": 0.2778419852256775,
+      "learning_rate": 1.5327580077171589e-06,
+      "loss": 0.3086,
+      "step": 183
+    },
+    {
+      "epoch": 1.6854531607006855,
+      "grad_norm": 0.31520137190818787,
+      "learning_rate": 1.4485723699465392e-06,
+      "loss": 0.3259,
+      "step": 184
+    },
+    {
+      "epoch": 1.6945925361766947,
+      "grad_norm": 0.29337337613105774,
+      "learning_rate": 1.3665836657672493e-06,
+      "loss": 0.3126,
+      "step": 185
+    },
+    {
+      "epoch": 1.7037319116527039,
+      "grad_norm": 0.3039644956588745,
+      "learning_rate": 1.286812958766106e-06,
+      "loss": 0.3194,
+      "step": 186
+    },
+    {
+      "epoch": 1.7128712871287128,
+      "grad_norm": 0.31187689304351807,
+      "learning_rate": 1.209280742707828e-06,
+      "loss": 0.3051,
+      "step": 187
+    },
+    {
+      "epoch": 1.722010662604722,
+      "grad_norm": 0.30652114748954773,
+      "learning_rate": 1.134006936269999e-06,
+      "loss": 0.3267,
+      "step": 188
+    },
+    {
+      "epoch": 1.7311500380807312,
+      "grad_norm": 0.33868396282196045,
+      "learning_rate": 1.0610108779258043e-06,
+      "loss": 0.3171,
+      "step": 189
+    },
+    {
+      "epoch": 1.7402894135567402,
+      "grad_norm": 0.3216879963874817,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.2924,
+      "step": 190
+    },
+    {
+      "epoch": 1.7494287890327493,
+      "grad_norm": 0.2990855872631073,
+      "learning_rate": 9.2192642873008e-07,
+      "loss": 0.3193,
+      "step": 191
+    },
+    {
+      "epoch": 1.7585681645087585,
+      "grad_norm": 0.2846771478652954,
+      "learning_rate": 8.558737698418762e-07,
+      "loss": 0.2915,
+      "step": 192
+    },
+    {
+      "epoch": 1.7677075399847677,
+      "grad_norm": 0.30743762850761414,
+      "learning_rate": 7.921703137941172e-07,
+      "loss": 0.3139,
+      "step": 193
+    },
+    {
+      "epoch": 1.7768469154607769,
+      "grad_norm": 0.30846983194351196,
+      "learning_rate": 7.308324265397837e-07,
+      "loss": 0.31,
+      "step": 194
+    },
+    {
+      "epoch": 1.785986290936786,
+      "grad_norm": 0.26738885045051575,
+      "learning_rate": 6.718758662973524e-07,
+      "loss": 0.3264,
+      "step": 195
+    },
+    {
+      "epoch": 1.7951256664127953,
+      "grad_norm": 0.3010248839855194,
+      "learning_rate": 6.153157795023956e-07,
+      "loss": 0.3187,
+      "step": 196
+    },
+    {
+      "epoch": 1.8042650418888042,
+      "grad_norm": 0.29657527804374695,
+      "learning_rate": 5.611666969163243e-07,
+      "loss": 0.3249,
+      "step": 197
+    },
+    {
+      "epoch": 1.8134044173648134,
+      "grad_norm": 0.29564720392227173,
+      "learning_rate": 5.094425298933136e-07,
+      "loss": 0.3174,
+      "step": 198
+    },
+    {
+      "epoch": 1.8225437928408226,
+      "grad_norm": 0.2934928834438324,
+      "learning_rate": 4.6015656680636234e-07,
+      "loss": 0.3278,
+      "step": 199
+    },
+    {
+      "epoch": 1.8316831683168315,
+      "grad_norm": 0.2969776690006256,
+      "learning_rate": 4.133214696333943e-07,
+      "loss": 0.3167,
+      "step": 200
+    },
+    {
+      "epoch": 1.8408225437928407,
+      "grad_norm": 0.3145069181919098,
+      "learning_rate": 3.6894927070429744e-07,
+      "loss": 0.3189,
+      "step": 201
+    },
+    {
+      "epoch": 1.84996191926885,
+      "grad_norm": 0.2936561703681946,
+      "learning_rate": 3.2705136960970554e-07,
+      "loss": 0.3153,
+      "step": 202
+    },
+    {
+      "epoch": 1.859101294744859,
+      "grad_norm": 0.3092540502548218,
+      "learning_rate": 2.8763853027236277e-07,
+      "loss": 0.3178,
+      "step": 203
+    },
+    {
+      "epoch": 1.8682406702208683,
+      "grad_norm": 0.3078237473964691,
+      "learning_rate": 2.507208781817638e-07,
+      "loss": 0.3042,
+      "step": 204
+    },
+    {
+      "epoch": 1.8773800456968774,
+      "grad_norm": 0.31245988607406616,
+      "learning_rate": 2.1630789779284677e-07,
+      "loss": 0.3121,
+      "step": 205
+    },
+    {
+      "epoch": 1.8865194211728866,
+      "grad_norm": 0.29274481534957886,
+      "learning_rate": 1.844084300893456e-07,
+      "loss": 0.3083,
+      "step": 206
+    },
+    {
+      "epoch": 1.8956587966488958,
+      "grad_norm": 0.27361243963241577,
+      "learning_rate": 1.55030670312476e-07,
+      "loss": 0.3198,
+      "step": 207
+    },
+    {
+      "epoch": 1.9047981721249048,
+      "grad_norm": 0.28884297609329224,
+      "learning_rate": 1.2818216585549824e-07,
+      "loss": 0.3137,
+      "step": 208
+    },
+    {
+      "epoch": 1.913937547600914,
+      "grad_norm": 0.3390906751155853,
+      "learning_rate": 1.0386981432474075e-07,
+      "loss": 0.3199,
+      "step": 209
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.3025045096874237,
+      "learning_rate": 8.209986176753947e-08,
+      "loss": 0.3091,
+      "step": 210
+    },
+    {
+      "epoch": 1.932216298552932,
+      "grad_norm": 0.30933359265327454,
+      "learning_rate": 6.287790106757396e-08,
+      "loss": 0.3267,
+      "step": 211
+    },
+    {
+      "epoch": 1.9413556740289413,
+      "grad_norm": 0.3036198914051056,
+      "learning_rate": 4.6208870508017703e-08,
+      "loss": 0.3084,
+      "step": 212
+    },
+    {
+      "epoch": 1.9504950495049505,
+      "grad_norm": 0.2938263416290283,
+      "learning_rate": 3.2097052502843005e-08,
+      "loss": 0.308,
+      "step": 213
+    },
+    {
+      "epoch": 1.9596344249809596,
+      "grad_norm": 0.2950015664100647,
+      "learning_rate": 2.054607249663665e-08,
+      "loss": 0.2959,
+      "step": 214
+    },
+    {
+      "epoch": 1.9687738004569688,
+      "grad_norm": 0.28699854016304016,
+      "learning_rate": 1.1558898033191545e-08,
+      "loss": 0.325,
+      "step": 215
+    },
+    {
+      "epoch": 1.977913175932978,
+      "grad_norm": 0.3103504478931427,
+      "learning_rate": 5.137837993121064e-09,
+      "loss": 0.3208,
+      "step": 216
+    },
+    {
+      "epoch": 1.9870525514089872,
+      "grad_norm": 0.30485469102859497,
+      "learning_rate": 1.2845420006879494e-09,
+      "loss": 0.3123,
+      "step": 217
+    },
+    {
+      "epoch": 1.9961919268849961,
+      "grad_norm": 0.3055669367313385,
+      "learning_rate": 0.0,
+      "loss": 0.3137,
+      "step": 218
+    },
+    {
+      "epoch": 1.9961919268849961,
+      "step": 218,
+      "total_flos": 418179526819840.0,
+      "train_loss": 0.09776416790047916,
+      "train_runtime": 5460.3908,
+      "train_samples_per_second": 3.846,
+      "train_steps_per_second": 0.04
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 218,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 418179526819840.0,
+  "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 sha256:0870e64934c0ba6682cbd0dab59841a55963ca5203051f974e7ab6f76f38b33d
+size 7544