Add files using upload-large-folder tool

.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 +1,64 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: t1_5k_v1_tag5mini
+  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. -->
+
+# t1_5k_v1_tag5mini
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the t1_5k_v1_tag5mini dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3651
+
+## 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: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- 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
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5022        | 0.5435 | 100  | 0.3715          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.36512017250061035,
+    "eval_runtime": 0.9104,
+    "eval_samples_per_second": 2.197,
+    "eval_steps_per_second": 1.098,
+    "total_flos": 35325739008000.0,
+    "train_loss": 0.4644851030214973,
+    "train_runtime": 696.0462,
+    "train_samples_per_second": 2.11,
+    "train_steps_per_second": 0.264
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "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
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.36512017250061035,
+    "eval_runtime": 0.9104,
+    "eval_samples_per_second": 2.197,
+    "eval_steps_per_second": 1.098
+}

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": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c7a94e81aa80af4a1c704c093288496942495c1959acff9cc010f1845653c5
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6551f9b73d4c34b15f947b13ba2778717f5f7cf821ec92944e205ab669085c7
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a4f8705973d5d61865772f5f8910a2024bcf75b39911459d4b10ec5cbea1970
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89278a586239a896f42f3c2129eb6ba344a7d22133b8014bceda564113893783
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.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": "<|im_end|>",
+    "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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 35325739008000.0,
+    "train_loss": 0.4644851030214973,
+    "train_runtime": 696.0462,
+    "train_samples_per_second": 2.11,
+    "train_steps_per_second": 0.264
+}

trainer_log.jsonl

@@ -0,0 +1,186 @@
+{"current_steps": 1, "total_steps": 184, "loss": 0.9436, "lr": 4.999635612423198e-06, "epoch": 0.005434782608695652, "percentage": 0.54, "elapsed_time": "0:00:04", "remaining_time": "0:15:05"}
+{"current_steps": 2, "total_steps": 184, "loss": 0.8096, "lr": 4.998542555915435e-06, "epoch": 0.010869565217391304, "percentage": 1.09, "elapsed_time": "0:00:08", "remaining_time": "0:13:21"}
+{"current_steps": 3, "total_steps": 184, "loss": 0.815, "lr": 4.996721149113682e-06, "epoch": 0.016304347826086956, "percentage": 1.63, "elapsed_time": "0:00:12", "remaining_time": "0:12:37"}
+{"current_steps": 4, "total_steps": 184, "loss": 0.7972, "lr": 4.994171922976349e-06, "epoch": 0.021739130434782608, "percentage": 2.17, "elapsed_time": "0:00:16", "remaining_time": "0:12:09"}
+{"current_steps": 5, "total_steps": 184, "loss": 0.7517, "lr": 4.990895620628501e-06, "epoch": 0.02717391304347826, "percentage": 2.72, "elapsed_time": "0:00:19", "remaining_time": "0:11:50"}
+{"current_steps": 6, "total_steps": 184, "loss": 0.8488, "lr": 4.986893197145238e-06, "epoch": 0.03260869565217391, "percentage": 3.26, "elapsed_time": "0:00:23", "remaining_time": "0:11:36"}
+{"current_steps": 7, "total_steps": 184, "loss": 0.6819, "lr": 4.982165819273275e-06, "epoch": 0.03804347826086957, "percentage": 3.8, "elapsed_time": "0:00:26", "remaining_time": "0:11:21"}
+{"current_steps": 8, "total_steps": 184, "loss": 0.7176, "lr": 4.976714865090827e-06, "epoch": 0.043478260869565216, "percentage": 4.35, "elapsed_time": "0:00:30", "remaining_time": "0:11:13"}
+{"current_steps": 9, "total_steps": 184, "loss": 0.6674, "lr": 4.9705419236058825e-06, "epoch": 0.04891304347826087, "percentage": 4.89, "elapsed_time": "0:00:34", "remaining_time": "0:11:04"}
+{"current_steps": 10, "total_steps": 184, "loss": 0.66, "lr": 4.963648794292992e-06, "epoch": 0.05434782608695652, "percentage": 5.43, "elapsed_time": "0:00:37", "remaining_time": "0:11:00"}
+{"current_steps": 11, "total_steps": 184, "loss": 0.6165, "lr": 4.956037486568707e-06, "epoch": 0.059782608695652176, "percentage": 5.98, "elapsed_time": "0:00:41", "remaining_time": "0:10:54"}
+{"current_steps": 12, "total_steps": 184, "loss": 0.621, "lr": 4.947710219205808e-06, "epoch": 0.06521739130434782, "percentage": 6.52, "elapsed_time": "0:00:45", "remaining_time": "0:10:48"}
+{"current_steps": 13, "total_steps": 184, "loss": 0.5038, "lr": 4.938669419686516e-06, "epoch": 0.07065217391304347, "percentage": 7.07, "elapsed_time": "0:00:48", "remaining_time": "0:10:42"}
+{"current_steps": 14, "total_steps": 184, "loss": 0.6525, "lr": 4.928917723494854e-06, "epoch": 0.07608695652173914, "percentage": 7.61, "elapsed_time": "0:00:52", "remaining_time": "0:10:36"}
+{"current_steps": 15, "total_steps": 184, "loss": 0.509, "lr": 4.91845797334838e-06, "epoch": 0.08152173913043478, "percentage": 8.15, "elapsed_time": "0:00:56", "remaining_time": "0:10:31"}
+{"current_steps": 16, "total_steps": 184, "loss": 0.5995, "lr": 4.907293218369499e-06, "epoch": 0.08695652173913043, "percentage": 8.7, "elapsed_time": "0:00:59", "remaining_time": "0:10:26"}
+{"current_steps": 17, "total_steps": 184, "loss": 0.5035, "lr": 4.895426713196623e-06, "epoch": 0.09239130434782608, "percentage": 9.24, "elapsed_time": "0:01:03", "remaining_time": "0:10:21"}
+{"current_steps": 18, "total_steps": 184, "loss": 0.5725, "lr": 4.882861917035403e-06, "epoch": 0.09782608695652174, "percentage": 9.78, "elapsed_time": "0:01:07", "remaining_time": "0:10:17"}
+{"current_steps": 19, "total_steps": 184, "loss": 0.6055, "lr": 4.86960249265034e-06, "epoch": 0.10326086956521739, "percentage": 10.33, "elapsed_time": "0:01:10", "remaining_time": "0:10:12"}
+{"current_steps": 20, "total_steps": 184, "loss": 0.604, "lr": 4.855652305297052e-06, "epoch": 0.10869565217391304, "percentage": 10.87, "elapsed_time": "0:01:14", "remaining_time": "0:10:07"}
+{"current_steps": 21, "total_steps": 184, "loss": 0.6176, "lr": 4.841015421595511e-06, "epoch": 0.11413043478260869, "percentage": 11.41, "elapsed_time": "0:01:17", "remaining_time": "0:10:02"}
+{"current_steps": 22, "total_steps": 184, "loss": 0.5518, "lr": 4.825696108344583e-06, "epoch": 0.11956521739130435, "percentage": 11.96, "elapsed_time": "0:01:21", "remaining_time": "0:09:57"}
+{"current_steps": 23, "total_steps": 184, "loss": 0.5245, "lr": 4.809698831278217e-06, "epoch": 0.125, "percentage": 12.5, "elapsed_time": "0:01:24", "remaining_time": "0:09:53"}
+{"current_steps": 24, "total_steps": 184, "loss": 0.5473, "lr": 4.793028253763633e-06, "epoch": 0.13043478260869565, "percentage": 13.04, "elapsed_time": "0:01:28", "remaining_time": "0:09:49"}
+{"current_steps": 25, "total_steps": 184, "loss": 0.5001, "lr": 4.775689235441906e-06, "epoch": 0.1358695652173913, "percentage": 13.59, "elapsed_time": "0:01:31", "remaining_time": "0:09:45"}
+{"current_steps": 26, "total_steps": 184, "loss": 0.6344, "lr": 4.757686830811332e-06, "epoch": 0.14130434782608695, "percentage": 14.13, "elapsed_time": "0:01:35", "remaining_time": "0:09:41"}
+{"current_steps": 27, "total_steps": 184, "loss": 0.5064, "lr": 4.7390262877539915e-06, "epoch": 0.14673913043478262, "percentage": 14.67, "elapsed_time": "0:01:39", "remaining_time": "0:09:37"}
+{"current_steps": 28, "total_steps": 184, "loss": 0.4852, "lr": 4.7197130460059385e-06, "epoch": 0.15217391304347827, "percentage": 15.22, "elapsed_time": "0:01:42", "remaining_time": "0:09:32"}
+{"current_steps": 29, "total_steps": 184, "loss": 0.4956, "lr": 4.69975273557146e-06, "epoch": 0.15760869565217392, "percentage": 15.76, "elapsed_time": "0:01:46", "remaining_time": "0:09:28"}
+{"current_steps": 30, "total_steps": 184, "loss": 0.4726, "lr": 4.679151175081879e-06, "epoch": 0.16304347826086957, "percentage": 16.3, "elapsed_time": "0:01:49", "remaining_time": "0:09:24"}
+{"current_steps": 31, "total_steps": 184, "loss": 0.5194, "lr": 4.657914370099357e-06, "epoch": 0.16847826086956522, "percentage": 16.85, "elapsed_time": "0:01:53", "remaining_time": "0:09:21"}
+{"current_steps": 32, "total_steps": 184, "loss": 0.5376, "lr": 4.636048511366222e-06, "epoch": 0.17391304347826086, "percentage": 17.39, "elapsed_time": "0:01:57", "remaining_time": "0:09:17"}
+{"current_steps": 33, "total_steps": 184, "loss": 0.4863, "lr": 4.613559973000295e-06, "epoch": 0.1793478260869565, "percentage": 17.93, "elapsed_time": "0:02:01", "remaining_time": "0:09:13"}
+{"current_steps": 34, "total_steps": 184, "loss": 0.425, "lr": 4.590455310636778e-06, "epoch": 0.18478260869565216, "percentage": 18.48, "elapsed_time": "0:02:04", "remaining_time": "0:09:09"}
+{"current_steps": 35, "total_steps": 184, "loss": 0.4431, "lr": 4.566741259517214e-06, "epoch": 0.19021739130434784, "percentage": 19.02, "elapsed_time": "0:02:08", "remaining_time": "0:09:05"}
+{"current_steps": 36, "total_steps": 184, "loss": 0.454, "lr": 4.542424732526105e-06, "epoch": 0.1956521739130435, "percentage": 19.57, "elapsed_time": "0:02:11", "remaining_time": "0:09:01"}
+{"current_steps": 37, "total_steps": 184, "loss": 0.5536, "lr": 4.517512818175726e-06, "epoch": 0.20108695652173914, "percentage": 20.11, "elapsed_time": "0:02:15", "remaining_time": "0:08:57"}
+{"current_steps": 38, "total_steps": 184, "loss": 0.4864, "lr": 4.4920127785397615e-06, "epoch": 0.20652173913043478, "percentage": 20.65, "elapsed_time": "0:02:19", "remaining_time": "0:08:54"}
+{"current_steps": 39, "total_steps": 184, "loss": 0.4217, "lr": 4.465932047136331e-06, "epoch": 0.21195652173913043, "percentage": 21.2, "elapsed_time": "0:02:22", "remaining_time": "0:08:50"}
+{"current_steps": 40, "total_steps": 184, "loss": 0.4627, "lr": 4.43927822676105e-06, "epoch": 0.21739130434782608, "percentage": 21.74, "elapsed_time": "0:02:26", "remaining_time": "0:08:46"}
+{"current_steps": 41, "total_steps": 184, "loss": 0.4748, "lr": 4.412059087270732e-06, "epoch": 0.22282608695652173, "percentage": 22.28, "elapsed_time": "0:02:29", "remaining_time": "0:08:42"}
+{"current_steps": 42, "total_steps": 184, "loss": 0.4709, "lr": 4.384282563318403e-06, "epoch": 0.22826086956521738, "percentage": 22.83, "elapsed_time": "0:02:33", "remaining_time": "0:08:38"}
+{"current_steps": 43, "total_steps": 184, "loss": 0.4805, "lr": 4.355956752040267e-06, "epoch": 0.23369565217391305, "percentage": 23.37, "elapsed_time": "0:02:37", "remaining_time": "0:08:34"}
+{"current_steps": 44, "total_steps": 184, "loss": 0.5394, "lr": 4.32708991069531e-06, "epoch": 0.2391304347826087, "percentage": 23.91, "elapsed_time": "0:02:40", "remaining_time": "0:08:31"}
+{"current_steps": 45, "total_steps": 184, "loss": 0.5601, "lr": 4.297690454258227e-06, "epoch": 0.24456521739130435, "percentage": 24.46, "elapsed_time": "0:02:44", "remaining_time": "0:08:26"}
+{"current_steps": 46, "total_steps": 184, "loss": 0.4798, "lr": 4.267766952966369e-06, "epoch": 0.25, "percentage": 25.0, "elapsed_time": "0:02:47", "remaining_time": "0:08:23"}
+{"current_steps": 47, "total_steps": 184, "loss": 0.4271, "lr": 4.237328129821437e-06, "epoch": 0.2554347826086957, "percentage": 25.54, "elapsed_time": "0:02:51", "remaining_time": "0:08:19"}
+{"current_steps": 48, "total_steps": 184, "loss": 0.4118, "lr": 4.206382858046636e-06, "epoch": 0.2608695652173913, "percentage": 26.09, "elapsed_time": "0:02:54", "remaining_time": "0:08:15"}
+{"current_steps": 49, "total_steps": 184, "loss": 0.4322, "lr": 4.1749401585000415e-06, "epoch": 0.266304347826087, "percentage": 26.63, "elapsed_time": "0:02:58", "remaining_time": "0:08:12"}
+{"current_steps": 50, "total_steps": 184, "loss": 0.4666, "lr": 4.143009197044932e-06, "epoch": 0.2717391304347826, "percentage": 27.17, "elapsed_time": "0:03:02", "remaining_time": "0:08:08"}
+{"current_steps": 51, "total_steps": 184, "loss": 0.4065, "lr": 4.1105992818778416e-06, "epoch": 0.27717391304347827, "percentage": 27.72, "elapsed_time": "0:03:05", "remaining_time": "0:08:04"}
+{"current_steps": 52, "total_steps": 184, "loss": 0.4755, "lr": 4.077719860815132e-06, "epoch": 0.2826086956521739, "percentage": 28.26, "elapsed_time": "0:03:09", "remaining_time": "0:08:00"}
+{"current_steps": 53, "total_steps": 184, "loss": 0.4954, "lr": 4.044380518538859e-06, "epoch": 0.28804347826086957, "percentage": 28.8, "elapsed_time": "0:03:13", "remaining_time": "0:07:57"}
+{"current_steps": 54, "total_steps": 184, "loss": 0.4178, "lr": 4.010590973802737e-06, "epoch": 0.29347826086956524, "percentage": 29.35, "elapsed_time": "0:03:16", "remaining_time": "0:07:53"}
+{"current_steps": 55, "total_steps": 184, "loss": 0.4033, "lr": 3.976361076599027e-06, "epoch": 0.29891304347826086, "percentage": 29.89, "elapsed_time": "0:03:20", "remaining_time": "0:07:49"}
+{"current_steps": 56, "total_steps": 184, "loss": 0.4588, "lr": 3.941700805287169e-06, "epoch": 0.30434782608695654, "percentage": 30.43, "elapsed_time": "0:03:23", "remaining_time": "0:07:46"}
+{"current_steps": 57, "total_steps": 184, "loss": 0.4786, "lr": 3.906620263684979e-06, "epoch": 0.30978260869565216, "percentage": 30.98, "elapsed_time": "0:03:27", "remaining_time": "0:07:42"}
+{"current_steps": 58, "total_steps": 184, "loss": 0.522, "lr": 3.871129678123297e-06, "epoch": 0.31521739130434784, "percentage": 31.52, "elapsed_time": "0:03:31", "remaining_time": "0:07:38"}
+{"current_steps": 59, "total_steps": 184, "loss": 0.4062, "lr": 3.835239394464901e-06, "epoch": 0.32065217391304346, "percentage": 32.07, "elapsed_time": "0:03:34", "remaining_time": "0:07:34"}
+{"current_steps": 60, "total_steps": 184, "loss": 0.408, "lr": 3.798959875088584e-06, "epoch": 0.32608695652173914, "percentage": 32.61, "elapsed_time": "0:03:38", "remaining_time": "0:07:31"}
+{"current_steps": 61, "total_steps": 184, "loss": 0.4419, "lr": 3.7623016958392706e-06, "epoch": 0.33152173913043476, "percentage": 33.15, "elapsed_time": "0:03:42", "remaining_time": "0:07:27"}
+{"current_steps": 62, "total_steps": 184, "loss": 0.4245, "lr": 3.7252755429450437e-06, "epoch": 0.33695652173913043, "percentage": 33.7, "elapsed_time": "0:03:45", "remaining_time": "0:07:24"}
+{"current_steps": 63, "total_steps": 184, "loss": 0.393, "lr": 3.687892209902009e-06, "epoch": 0.3423913043478261, "percentage": 34.24, "elapsed_time": "0:03:49", "remaining_time": "0:07:20"}
+{"current_steps": 64, "total_steps": 184, "loss": 0.4183, "lr": 3.650162594327881e-06, "epoch": 0.34782608695652173, "percentage": 34.78, "elapsed_time": "0:03:53", "remaining_time": "0:07:17"}
+{"current_steps": 65, "total_steps": 184, "loss": 0.4696, "lr": 3.612097694785211e-06, "epoch": 0.3532608695652174, "percentage": 35.33, "elapsed_time": "0:03:56", "remaining_time": "0:07:13"}
+{"current_steps": 66, "total_steps": 184, "loss": 0.4338, "lr": 3.5737086075752054e-06, "epoch": 0.358695652173913, "percentage": 35.87, "elapsed_time": "0:04:00", "remaining_time": "0:07:09"}
+{"current_steps": 67, "total_steps": 184, "loss": 0.4399, "lr": 3.535006523503034e-06, "epoch": 0.3641304347826087, "percentage": 36.41, "elapsed_time": "0:04:04", "remaining_time": "0:07:06"}
+{"current_steps": 68, "total_steps": 184, "loss": 0.4385, "lr": 3.4960027246156043e-06, "epoch": 0.3695652173913043, "percentage": 36.96, "elapsed_time": "0:04:07", "remaining_time": "0:07:02"}
+{"current_steps": 69, "total_steps": 184, "loss": 0.4302, "lr": 3.4567085809127247e-06, "epoch": 0.375, "percentage": 37.5, "elapsed_time": "0:04:11", "remaining_time": "0:06:58"}
+{"current_steps": 70, "total_steps": 184, "loss": 0.5276, "lr": 3.417135547032642e-06, "epoch": 0.3804347826086957, "percentage": 38.04, "elapsed_time": "0:04:14", "remaining_time": "0:06:55"}
+{"current_steps": 71, "total_steps": 184, "loss": 0.4742, "lr": 3.3772951589128926e-06, "epoch": 0.3858695652173913, "percentage": 38.59, "elapsed_time": "0:04:18", "remaining_time": "0:06:51"}
+{"current_steps": 72, "total_steps": 184, "loss": 0.3976, "lr": 3.3371990304274654e-06, "epoch": 0.391304347826087, "percentage": 39.13, "elapsed_time": "0:04:22", "remaining_time": "0:06:48"}
+{"current_steps": 73, "total_steps": 184, "loss": 0.4093, "lr": 3.29685885000124e-06, "epoch": 0.3967391304347826, "percentage": 39.67, "elapsed_time": "0:04:25", "remaining_time": "0:06:44"}
+{"current_steps": 74, "total_steps": 184, "loss": 0.4092, "lr": 3.25628637720269e-06, "epoch": 0.40217391304347827, "percentage": 40.22, "elapsed_time": "0:04:29", "remaining_time": "0:06:40"}
+{"current_steps": 75, "total_steps": 184, "loss": 0.4763, "lr": 3.215493439315854e-06, "epoch": 0.4076086956521739, "percentage": 40.76, "elapsed_time": "0:04:33", "remaining_time": "0:06:36"}
+{"current_steps": 76, "total_steps": 184, "loss": 0.483, "lr": 3.174491927892561e-06, "epoch": 0.41304347826086957, "percentage": 41.3, "elapsed_time": "0:04:36", "remaining_time": "0:06:33"}
+{"current_steps": 77, "total_steps": 184, "loss": 0.391, "lr": 3.133293795285926e-06, "epoch": 0.41847826086956524, "percentage": 41.85, "elapsed_time": "0:04:40", "remaining_time": "0:06:29"}
+{"current_steps": 78, "total_steps": 184, "loss": 0.5047, "lr": 3.091911051166117e-06, "epoch": 0.42391304347826086, "percentage": 42.39, "elapsed_time": "0:04:44", "remaining_time": "0:06:25"}
+{"current_steps": 79, "total_steps": 184, "loss": 0.434, "lr": 3.050355759019414e-06, "epoch": 0.42934782608695654, "percentage": 42.93, "elapsed_time": "0:04:47", "remaining_time": "0:06:22"}
+{"current_steps": 80, "total_steps": 184, "loss": 0.4153, "lr": 3.0086400326315853e-06, "epoch": 0.43478260869565216, "percentage": 43.48, "elapsed_time": "0:04:51", "remaining_time": "0:06:18"}
+{"current_steps": 81, "total_steps": 184, "loss": 0.3982, "lr": 2.966776032556591e-06, "epoch": 0.44021739130434784, "percentage": 44.02, "elapsed_time": "0:04:54", "remaining_time": "0:06:15"}
+{"current_steps": 82, "total_steps": 184, "loss": 0.4108, "lr": 2.924775962571667e-06, "epoch": 0.44565217391304346, "percentage": 44.57, "elapsed_time": "0:04:58", "remaining_time": "0:06:11"}
+{"current_steps": 83, "total_steps": 184, "loss": 0.4788, "lr": 2.882652066119795e-06, "epoch": 0.45108695652173914, "percentage": 45.11, "elapsed_time": "0:05:02", "remaining_time": "0:06:07"}
+{"current_steps": 84, "total_steps": 184, "loss": 0.4646, "lr": 2.840416622740617e-06, "epoch": 0.45652173913043476, "percentage": 45.65, "elapsed_time": "0:05:05", "remaining_time": "0:06:04"}
+{"current_steps": 85, "total_steps": 184, "loss": 0.4538, "lr": 2.798081944490828e-06, "epoch": 0.46195652173913043, "percentage": 46.2, "elapsed_time": "0:05:09", "remaining_time": "0:06:00"}
+{"current_steps": 86, "total_steps": 184, "loss": 0.4356, "lr": 2.7556603723550855e-06, "epoch": 0.4673913043478261, "percentage": 46.74, "elapsed_time": "0:05:13", "remaining_time": "0:05:56"}
+{"current_steps": 87, "total_steps": 184, "loss": 0.4032, "lr": 2.7131642726484902e-06, "epoch": 0.47282608695652173, "percentage": 47.28, "elapsed_time": "0:05:16", "remaining_time": "0:05:53"}
+{"current_steps": 88, "total_steps": 184, "loss": 0.429, "lr": 2.670606033411678e-06, "epoch": 0.4782608695652174, "percentage": 47.83, "elapsed_time": "0:05:20", "remaining_time": "0:05:49"}
+{"current_steps": 89, "total_steps": 184, "loss": 0.4594, "lr": 2.6279980607995837e-06, "epoch": 0.483695652173913, "percentage": 48.37, "elapsed_time": "0:05:24", "remaining_time": "0:05:45"}
+{"current_steps": 90, "total_steps": 184, "loss": 0.4404, "lr": 2.58535277546492e-06, "epoch": 0.4891304347826087, "percentage": 48.91, "elapsed_time": "0:05:27", "remaining_time": "0:05:42"}
+{"current_steps": 91, "total_steps": 184, "loss": 0.4334, "lr": 2.5426826089374374e-06, "epoch": 0.4945652173913043, "percentage": 49.46, "elapsed_time": "0:05:31", "remaining_time": "0:05:38"}
+{"current_steps": 92, "total_steps": 184, "loss": 0.4405, "lr": 2.5e-06, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:05:34", "remaining_time": "0:05:34"}
+{"current_steps": 93, "total_steps": 184, "loss": 0.4071, "lr": 2.4573173910625634e-06, "epoch": 0.5054347826086957, "percentage": 50.54, "elapsed_time": "0:05:38", "remaining_time": "0:05:31"}
+{"current_steps": 94, "total_steps": 184, "loss": 0.4756, "lr": 2.4146472245350804e-06, "epoch": 0.5108695652173914, "percentage": 51.09, "elapsed_time": "0:05:42", "remaining_time": "0:05:27"}
+{"current_steps": 95, "total_steps": 184, "loss": 0.3921, "lr": 2.372001939200418e-06, "epoch": 0.5163043478260869, "percentage": 51.63, "elapsed_time": "0:05:45", "remaining_time": "0:05:23"}
+{"current_steps": 96, "total_steps": 184, "loss": 0.409, "lr": 2.3293939665883233e-06, "epoch": 0.5217391304347826, "percentage": 52.17, "elapsed_time": "0:05:49", "remaining_time": "0:05:20"}
+{"current_steps": 97, "total_steps": 184, "loss": 0.4451, "lr": 2.28683572735151e-06, "epoch": 0.5271739130434783, "percentage": 52.72, "elapsed_time": "0:05:53", "remaining_time": "0:05:16"}
+{"current_steps": 98, "total_steps": 184, "loss": 0.4839, "lr": 2.2443396276449145e-06, "epoch": 0.532608695652174, "percentage": 53.26, "elapsed_time": "0:05:56", "remaining_time": "0:05:12"}
+{"current_steps": 99, "total_steps": 184, "loss": 0.4896, "lr": 2.201918055509173e-06, "epoch": 0.5380434782608695, "percentage": 53.8, "elapsed_time": "0:06:00", "remaining_time": "0:05:09"}
+{"current_steps": 100, "total_steps": 184, "loss": 0.5022, "lr": 2.159583377259384e-06, "epoch": 0.5434782608695652, "percentage": 54.35, "elapsed_time": "0:06:03", "remaining_time": "0:05:05"}
+{"current_steps": 100, "total_steps": 184, "eval_loss": 0.3715117275714874, "epoch": 0.5434782608695652, "percentage": 54.35, "elapsed_time": "0:06:04", "remaining_time": "0:05:06"}
+{"current_steps": 101, "total_steps": 184, "loss": 0.3849, "lr": 2.117347933880206e-06, "epoch": 0.5489130434782609, "percentage": 54.89, "elapsed_time": "0:06:08", "remaining_time": "0:05:02"}
+{"current_steps": 102, "total_steps": 184, "loss": 0.3907, "lr": 2.0752240374283334e-06, "epoch": 0.5543478260869565, "percentage": 55.43, "elapsed_time": "0:06:11", "remaining_time": "0:04:58"}
+{"current_steps": 103, "total_steps": 184, "loss": 0.4176, "lr": 2.0332239674434096e-06, "epoch": 0.5597826086956522, "percentage": 55.98, "elapsed_time": "0:06:15", "remaining_time": "0:04:55"}
+{"current_steps": 104, "total_steps": 184, "loss": 0.4004, "lr": 1.991359967368416e-06, "epoch": 0.5652173913043478, "percentage": 56.52, "elapsed_time": "0:06:19", "remaining_time": "0:04:51"}
+{"current_steps": 105, "total_steps": 184, "loss": 0.475, "lr": 1.9496442409805867e-06, "epoch": 0.5706521739130435, "percentage": 57.07, "elapsed_time": "0:06:22", "remaining_time": "0:04:47"}
+{"current_steps": 106, "total_steps": 184, "loss": 0.4699, "lr": 1.9080889488338833e-06, "epoch": 0.5760869565217391, "percentage": 57.61, "elapsed_time": "0:06:26", "remaining_time": "0:04:44"}
+{"current_steps": 107, "total_steps": 184, "loss": 0.4527, "lr": 1.866706204714074e-06, "epoch": 0.5815217391304348, "percentage": 58.15, "elapsed_time": "0:06:30", "remaining_time": "0:04:40"}
+{"current_steps": 108, "total_steps": 184, "loss": 0.4163, "lr": 1.8255080721074391e-06, "epoch": 0.5869565217391305, "percentage": 58.7, "elapsed_time": "0:06:33", "remaining_time": "0:04:36"}
+{"current_steps": 109, "total_steps": 184, "loss": 0.4462, "lr": 1.7845065606841471e-06, "epoch": 0.592391304347826, "percentage": 59.24, "elapsed_time": "0:06:37", "remaining_time": "0:04:33"}
+{"current_steps": 110, "total_steps": 184, "loss": 0.4248, "lr": 1.7437136227973108e-06, "epoch": 0.5978260869565217, "percentage": 59.78, "elapsed_time": "0:06:40", "remaining_time": "0:04:29"}
+{"current_steps": 111, "total_steps": 184, "loss": 0.3889, "lr": 1.7031411499987604e-06, "epoch": 0.6032608695652174, "percentage": 60.33, "elapsed_time": "0:06:44", "remaining_time": "0:04:26"}
+{"current_steps": 112, "total_steps": 184, "loss": 0.38, "lr": 1.6628009695725348e-06, "epoch": 0.6086956521739131, "percentage": 60.87, "elapsed_time": "0:06:48", "remaining_time": "0:04:22"}
+{"current_steps": 113, "total_steps": 184, "loss": 0.4233, "lr": 1.6227048410871085e-06, "epoch": 0.6141304347826086, "percentage": 61.41, "elapsed_time": "0:06:51", "remaining_time": "0:04:18"}
+{"current_steps": 114, "total_steps": 184, "loss": 0.5463, "lr": 1.5828644529673592e-06, "epoch": 0.6195652173913043, "percentage": 61.96, "elapsed_time": "0:06:55", "remaining_time": "0:04:15"}
+{"current_steps": 115, "total_steps": 184, "loss": 0.3818, "lr": 1.5432914190872757e-06, "epoch": 0.625, "percentage": 62.5, "elapsed_time": "0:06:58", "remaining_time": "0:04:11"}
+{"current_steps": 116, "total_steps": 184, "loss": 0.4116, "lr": 1.5039972753843966e-06, "epoch": 0.6304347826086957, "percentage": 63.04, "elapsed_time": "0:07:02", "remaining_time": "0:04:07"}
+{"current_steps": 117, "total_steps": 184, "loss": 0.4151, "lr": 1.4649934764969665e-06, "epoch": 0.6358695652173914, "percentage": 63.59, "elapsed_time": "0:07:06", "remaining_time": "0:04:04"}
+{"current_steps": 118, "total_steps": 184, "loss": 0.4156, "lr": 1.4262913924247956e-06, "epoch": 0.6413043478260869, "percentage": 64.13, "elapsed_time": "0:07:10", "remaining_time": "0:04:00"}
+{"current_steps": 119, "total_steps": 184, "loss": 0.3774, "lr": 1.38790230521479e-06, "epoch": 0.6467391304347826, "percentage": 64.67, "elapsed_time": "0:07:13", "remaining_time": "0:03:56"}
+{"current_steps": 120, "total_steps": 184, "loss": 0.4139, "lr": 1.3498374056721198e-06, "epoch": 0.6521739130434783, "percentage": 65.22, "elapsed_time": "0:07:17", "remaining_time": "0:03:53"}
+{"current_steps": 121, "total_steps": 184, "loss": 0.3947, "lr": 1.3121077900979907e-06, "epoch": 0.657608695652174, "percentage": 65.76, "elapsed_time": "0:07:21", "remaining_time": "0:03:49"}
+{"current_steps": 122, "total_steps": 184, "loss": 0.4331, "lr": 1.2747244570549578e-06, "epoch": 0.6630434782608695, "percentage": 66.3, "elapsed_time": "0:07:24", "remaining_time": "0:03:46"}
+{"current_steps": 123, "total_steps": 184, "loss": 0.3783, "lr": 1.2376983041607307e-06, "epoch": 0.6684782608695652, "percentage": 66.85, "elapsed_time": "0:07:28", "remaining_time": "0:03:42"}
+{"current_steps": 124, "total_steps": 184, "loss": 0.4424, "lr": 1.2010401249114166e-06, "epoch": 0.6739130434782609, "percentage": 67.39, "elapsed_time": "0:07:31", "remaining_time": "0:03:38"}
+{"current_steps": 125, "total_steps": 184, "loss": 0.4392, "lr": 1.1647606055350997e-06, "epoch": 0.6793478260869565, "percentage": 67.93, "elapsed_time": "0:07:35", "remaining_time": "0:03:35"}
+{"current_steps": 126, "total_steps": 184, "loss": 0.464, "lr": 1.1288703218767027e-06, "epoch": 0.6847826086956522, "percentage": 68.48, "elapsed_time": "0:07:39", "remaining_time": "0:03:31"}
+{"current_steps": 127, "total_steps": 184, "loss": 0.4339, "lr": 1.0933797363150225e-06, "epoch": 0.6902173913043478, "percentage": 69.02, "elapsed_time": "0:07:42", "remaining_time": "0:03:27"}
+{"current_steps": 128, "total_steps": 184, "loss": 0.365, "lr": 1.0582991947128324e-06, "epoch": 0.6956521739130435, "percentage": 69.57, "elapsed_time": "0:07:46", "remaining_time": "0:03:24"}
+{"current_steps": 129, "total_steps": 184, "loss": 0.3748, "lr": 1.0236389234009728e-06, "epoch": 0.7010869565217391, "percentage": 70.11, "elapsed_time": "0:07:50", "remaining_time": "0:03:20"}
+{"current_steps": 130, "total_steps": 184, "loss": 0.4782, "lr": 9.89409026197264e-07, "epoch": 0.7065217391304348, "percentage": 70.65, "elapsed_time": "0:07:53", "remaining_time": "0:03:16"}
+{"current_steps": 131, "total_steps": 184, "loss": 0.4098, "lr": 9.55619481461141e-07, "epoch": 0.7119565217391305, "percentage": 71.2, "elapsed_time": "0:07:57", "remaining_time": "0:03:13"}
+{"current_steps": 132, "total_steps": 184, "loss": 0.4458, "lr": 9.222801391848688e-07, "epoch": 0.717391304347826, "percentage": 71.74, "elapsed_time": "0:08:01", "remaining_time": "0:03:09"}
+{"current_steps": 133, "total_steps": 184, "loss": 0.4402, "lr": 8.894007181221595e-07, "epoch": 0.7228260869565217, "percentage": 72.28, "elapsed_time": "0:08:04", "remaining_time": "0:03:05"}
+{"current_steps": 134, "total_steps": 184, "loss": 0.4857, "lr": 8.569908029550686e-07, "epoch": 0.7282608695652174, "percentage": 72.83, "elapsed_time": "0:08:08", "remaining_time": "0:03:02"}
+{"current_steps": 135, "total_steps": 184, "loss": 0.4406, "lr": 8.250598414999589e-07, "epoch": 0.7336956521739131, "percentage": 73.37, "elapsed_time": "0:08:11", "remaining_time": "0:02:58"}
+{"current_steps": 136, "total_steps": 184, "loss": 0.4333, "lr": 7.936171419533653e-07, "epoch": 0.7391304347826086, "percentage": 73.91, "elapsed_time": "0:08:15", "remaining_time": "0:02:54"}
+{"current_steps": 137, "total_steps": 184, "loss": 0.4512, "lr": 7.62671870178564e-07, "epoch": 0.7445652173913043, "percentage": 74.46, "elapsed_time": "0:08:19", "remaining_time": "0:02:51"}
+{"current_steps": 138, "total_steps": 184, "loss": 0.4849, "lr": 7.322330470336314e-07, "epoch": 0.75, "percentage": 75.0, "elapsed_time": "0:08:22", "remaining_time": "0:02:47"}
+{"current_steps": 139, "total_steps": 184, "loss": 0.4253, "lr": 7.02309545741773e-07, "epoch": 0.7554347826086957, "percentage": 75.54, "elapsed_time": "0:08:26", "remaining_time": "0:02:43"}
+{"current_steps": 140, "total_steps": 184, "loss": 0.4188, "lr": 6.729100893046897e-07, "epoch": 0.7608695652173914, "percentage": 76.09, "elapsed_time": "0:08:29", "remaining_time": "0:02:40"}
+{"current_steps": 141, "total_steps": 184, "loss": 0.4505, "lr": 6.440432479597333e-07, "epoch": 0.7663043478260869, "percentage": 76.63, "elapsed_time": "0:08:33", "remaining_time": "0:02:36"}
+{"current_steps": 142, "total_steps": 184, "loss": 0.3826, "lr": 6.157174366815979e-07, "epoch": 0.7717391304347826, "percentage": 77.17, "elapsed_time": "0:08:36", "remaining_time": "0:02:32"}
+{"current_steps": 143, "total_steps": 184, "loss": 0.3957, "lr": 5.879409127292685e-07, "epoch": 0.7771739130434783, "percentage": 77.72, "elapsed_time": "0:08:40", "remaining_time": "0:02:29"}
+{"current_steps": 144, "total_steps": 184, "loss": 0.4133, "lr": 5.607217732389503e-07, "epoch": 0.782608695652174, "percentage": 78.26, "elapsed_time": "0:08:44", "remaining_time": "0:02:25"}
+{"current_steps": 145, "total_steps": 184, "loss": 0.3539, "lr": 5.340679528636694e-07, "epoch": 0.7880434782608695, "percentage": 78.8, "elapsed_time": "0:08:47", "remaining_time": "0:02:21"}
+{"current_steps": 146, "total_steps": 184, "loss": 0.4274, "lr": 5.079872214602388e-07, "epoch": 0.7934782608695652, "percentage": 79.35, "elapsed_time": "0:08:51", "remaining_time": "0:02:18"}
+{"current_steps": 147, "total_steps": 184, "loss": 0.3931, "lr": 4.82487181824274e-07, "epoch": 0.7989130434782609, "percentage": 79.89, "elapsed_time": "0:08:55", "remaining_time": "0:02:14"}
+{"current_steps": 148, "total_steps": 184, "loss": 0.4495, "lr": 4.5757526747389506e-07, "epoch": 0.8043478260869565, "percentage": 80.43, "elapsed_time": "0:08:58", "remaining_time": "0:02:11"}
+{"current_steps": 149, "total_steps": 184, "loss": 0.4076, "lr": 4.3325874048278537e-07, "epoch": 0.8097826086956522, "percentage": 80.98, "elapsed_time": "0:09:02", "remaining_time": "0:02:07"}
+{"current_steps": 150, "total_steps": 184, "loss": 0.4166, "lr": 4.095446893632235e-07, "epoch": 0.8152173913043478, "percentage": 81.52, "elapsed_time": "0:09:05", "remaining_time": "0:02:03"}
+{"current_steps": 151, "total_steps": 184, "loss": 0.499, "lr": 3.8644002699970566e-07, "epoch": 0.8206521739130435, "percentage": 82.07, "elapsed_time": "0:09:09", "remaining_time": "0:02:00"}
+{"current_steps": 152, "total_steps": 184, "loss": 0.3897, "lr": 3.639514886337786e-07, "epoch": 0.8260869565217391, "percentage": 82.61, "elapsed_time": "0:09:13", "remaining_time": "0:01:56"}
+{"current_steps": 153, "total_steps": 184, "loss": 0.3548, "lr": 3.4208562990064334e-07, "epoch": 0.8315217391304348, "percentage": 83.15, "elapsed_time": "0:09:16", "remaining_time": "0:01:52"}
+{"current_steps": 154, "total_steps": 184, "loss": 0.3645, "lr": 3.208488249181216e-07, "epoch": 0.8369565217391305, "percentage": 83.7, "elapsed_time": "0:09:20", "remaining_time": "0:01:49"}
+{"current_steps": 155, "total_steps": 184, "loss": 0.3862, "lr": 3.0024726442854063e-07, "epoch": 0.842391304347826, "percentage": 84.24, "elapsed_time": "0:09:23", "remaining_time": "0:01:45"}
+{"current_steps": 156, "total_steps": 184, "loss": 0.3874, "lr": 2.80286953994062e-07, "epoch": 0.8478260869565217, "percentage": 84.78, "elapsed_time": "0:09:27", "remaining_time": "0:01:41"}
+{"current_steps": 157, "total_steps": 184, "loss": 0.398, "lr": 2.609737122460082e-07, "epoch": 0.8532608695652174, "percentage": 85.33, "elapsed_time": "0:09:31", "remaining_time": "0:01:38"}
+{"current_steps": 158, "total_steps": 184, "loss": 0.4108, "lr": 2.423131691886682e-07, "epoch": 0.8586956521739131, "percentage": 85.87, "elapsed_time": "0:09:34", "remaining_time": "0:01:34"}
+{"current_steps": 159, "total_steps": 184, "loss": 0.4099, "lr": 2.243107645580947e-07, "epoch": 0.8641304347826086, "percentage": 86.41, "elapsed_time": "0:09:38", "remaining_time": "0:01:30"}
+{"current_steps": 160, "total_steps": 184, "loss": 0.4135, "lr": 2.0697174623636795e-07, "epoch": 0.8695652173913043, "percentage": 86.96, "elapsed_time": "0:09:41", "remaining_time": "0:01:27"}
+{"current_steps": 161, "total_steps": 184, "loss": 0.3928, "lr": 1.9030116872178317e-07, "epoch": 0.875, "percentage": 87.5, "elapsed_time": "0:09:45", "remaining_time": "0:01:23"}
+{"current_steps": 162, "total_steps": 184, "loss": 0.348, "lr": 1.743038916554171e-07, "epoch": 0.8804347826086957, "percentage": 88.04, "elapsed_time": "0:09:49", "remaining_time": "0:01:20"}
+{"current_steps": 163, "total_steps": 184, "loss": 0.4296, "lr": 1.5898457840448994e-07, "epoch": 0.8858695652173914, "percentage": 88.59, "elapsed_time": "0:09:53", "remaining_time": "0:01:16"}
+{"current_steps": 164, "total_steps": 184, "loss": 0.3888, "lr": 1.44347694702949e-07, "epoch": 0.8913043478260869, "percentage": 89.13, "elapsed_time": "0:09:56", "remaining_time": "0:01:12"}
+{"current_steps": 165, "total_steps": 184, "loss": 0.4254, "lr": 1.3039750734966077e-07, "epoch": 0.8967391304347826, "percentage": 89.67, "elapsed_time": "0:10:00", "remaining_time": "0:01:09"}
+{"current_steps": 166, "total_steps": 184, "loss": 0.407, "lr": 1.1713808296459794e-07, "epoch": 0.9021739130434783, "percentage": 90.22, "elapsed_time": "0:10:04", "remaining_time": "0:01:05"}
+{"current_steps": 167, "total_steps": 184, "loss": 0.4081, "lr": 1.0457328680337803e-07, "epoch": 0.907608695652174, "percentage": 90.76, "elapsed_time": "0:10:07", "remaining_time": "0:01:01"}
+{"current_steps": 168, "total_steps": 184, "loss": 0.361, "lr": 9.270678163050218e-08, "epoch": 0.9130434782608695, "percentage": 91.3, "elapsed_time": "0:10:11", "remaining_time": "0:00:58"}
+{"current_steps": 169, "total_steps": 184, "loss": 0.4196, "lr": 8.154202665162147e-08, "epoch": 0.9184782608695652, "percentage": 91.85, "elapsed_time": "0:10:14", "remaining_time": "0:00:54"}
+{"current_steps": 170, "total_steps": 184, "loss": 0.4053, "lr": 7.108227650514637e-08, "epoch": 0.9239130434782609, "percentage": 92.39, "elapsed_time": "0:10:18", "remaining_time": "0:00:50"}
+{"current_steps": 171, "total_steps": 184, "loss": 0.4513, "lr": 6.133058031348477e-08, "epoch": 0.9293478260869565, "percentage": 92.93, "elapsed_time": "0:10:22", "remaining_time": "0:00:47"}
+{"current_steps": 172, "total_steps": 184, "loss": 0.5048, "lr": 5.2289780794192726e-08, "epoch": 0.9347826086956522, "percentage": 93.48, "elapsed_time": "0:10:25", "remaining_time": "0:00:43"}
+{"current_steps": 173, "total_steps": 184, "loss": 0.4139, "lr": 4.396251343129376e-08, "epoch": 0.9402173913043478, "percentage": 94.02, "elapsed_time": "0:10:29", "remaining_time": "0:00:40"}
+{"current_steps": 174, "total_steps": 184, "loss": 0.3555, "lr": 3.635120570700784e-08, "epoch": 0.9456521739130435, "percentage": 94.57, "elapsed_time": "0:10:33", "remaining_time": "0:00:36"}
+{"current_steps": 175, "total_steps": 184, "loss": 0.4414, "lr": 2.9458076394117686e-08, "epoch": 0.9510869565217391, "percentage": 95.11, "elapsed_time": "0:10:36", "remaining_time": "0:00:32"}
+{"current_steps": 176, "total_steps": 184, "loss": 0.4146, "lr": 2.3285134909173113e-08, "epoch": 0.9565217391304348, "percentage": 95.65, "elapsed_time": "0:10:40", "remaining_time": "0:00:29"}
+{"current_steps": 177, "total_steps": 184, "loss": 0.4367, "lr": 1.783418072672516e-08, "epoch": 0.9619565217391305, "percentage": 96.2, "elapsed_time": "0:10:43", "remaining_time": "0:00:25"}
+{"current_steps": 178, "total_steps": 184, "loss": 0.456, "lr": 1.3106802854762901e-08, "epoch": 0.967391304347826, "percentage": 96.74, "elapsed_time": "0:10:47", "remaining_time": "0:00:21"}
+{"current_steps": 179, "total_steps": 184, "loss": 0.3899, "lr": 9.104379371500104e-09, "epoch": 0.9728260869565217, "percentage": 97.28, "elapsed_time": "0:10:51", "remaining_time": "0:00:18"}
+{"current_steps": 180, "total_steps": 184, "loss": 0.4089, "lr": 5.828077023651846e-09, "epoch": 0.9782608695652174, "percentage": 97.83, "elapsed_time": "0:10:55", "remaining_time": "0:00:14"}
+{"current_steps": 181, "total_steps": 184, "loss": 0.3432, "lr": 3.278850886317686e-09, "epoch": 0.9836956521739131, "percentage": 98.37, "elapsed_time": "0:10:58", "remaining_time": "0:00:10"}
+{"current_steps": 182, "total_steps": 184, "loss": 0.4631, "lr": 1.4574440845649406e-09, "epoch": 0.9891304347826086, "percentage": 98.91, "elapsed_time": "0:11:02", "remaining_time": "0:00:07"}
+{"current_steps": 183, "total_steps": 184, "loss": 0.3882, "lr": 3.643875768025162e-10, "epoch": 0.9945652173913043, "percentage": 99.46, "elapsed_time": "0:11:05", "remaining_time": "0:00:03"}
+{"current_steps": 184, "total_steps": 184, "loss": 0.3512, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:11:09", "remaining_time": "0:00:00"}
+{"current_steps": 184, "total_steps": 184, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:11:36", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1338 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 184,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005434782608695652,
+      "grad_norm": 3.848675456224903,
+      "learning_rate": 4.999635612423198e-06,
+      "loss": 0.9436,
+      "step": 1
+    },
+    {
+      "epoch": 0.010869565217391304,
+      "grad_norm": 3.0895803137732987,
+      "learning_rate": 4.998542555915435e-06,
+      "loss": 0.8096,
+      "step": 2
+    },
+    {
+      "epoch": 0.016304347826086956,
+      "grad_norm": 2.4908898349252024,
+      "learning_rate": 4.996721149113682e-06,
+      "loss": 0.815,
+      "step": 3
+    },
+    {
+      "epoch": 0.021739130434782608,
+      "grad_norm": 2.033848203102757,
+      "learning_rate": 4.994171922976349e-06,
+      "loss": 0.7972,
+      "step": 4
+    },
+    {
+      "epoch": 0.02717391304347826,
+      "grad_norm": 1.7031162839496814,
+      "learning_rate": 4.990895620628501e-06,
+      "loss": 0.7517,
+      "step": 5
+    },
+    {
+      "epoch": 0.03260869565217391,
+      "grad_norm": 1.938110068963118,
+      "learning_rate": 4.986893197145238e-06,
+      "loss": 0.8488,
+      "step": 6
+    },
+    {
+      "epoch": 0.03804347826086957,
+      "grad_norm": 1.6977280649572781,
+      "learning_rate": 4.982165819273275e-06,
+      "loss": 0.6819,
+      "step": 7
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 1.8755876523465078,
+      "learning_rate": 4.976714865090827e-06,
+      "loss": 0.7176,
+      "step": 8
+    },
+    {
+      "epoch": 0.04891304347826087,
+      "grad_norm": 1.8742292407918357,
+      "learning_rate": 4.9705419236058825e-06,
+      "loss": 0.6674,
+      "step": 9
+    },
+    {
+      "epoch": 0.05434782608695652,
+      "grad_norm": 1.6922977361939497,
+      "learning_rate": 4.963648794292992e-06,
+      "loss": 0.66,
+      "step": 10
+    },
+    {
+      "epoch": 0.059782608695652176,
+      "grad_norm": 1.486499626033436,
+      "learning_rate": 4.956037486568707e-06,
+      "loss": 0.6165,
+      "step": 11
+    },
+    {
+      "epoch": 0.06521739130434782,
+      "grad_norm": 1.9241767657004376,
+      "learning_rate": 4.947710219205808e-06,
+      "loss": 0.621,
+      "step": 12
+    },
+    {
+      "epoch": 0.07065217391304347,
+      "grad_norm": 1.1217340861704879,
+      "learning_rate": 4.938669419686516e-06,
+      "loss": 0.5038,
+      "step": 13
+    },
+    {
+      "epoch": 0.07608695652173914,
+      "grad_norm": 1.370773875914219,
+      "learning_rate": 4.928917723494854e-06,
+      "loss": 0.6525,
+      "step": 14
+    },
+    {
+      "epoch": 0.08152173913043478,
+      "grad_norm": 1.0631151831275898,
+      "learning_rate": 4.91845797334838e-06,
+      "loss": 0.509,
+      "step": 15
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 1.2276056215005575,
+      "learning_rate": 4.907293218369499e-06,
+      "loss": 0.5995,
+      "step": 16
+    },
+    {
+      "epoch": 0.09239130434782608,
+      "grad_norm": 1.2125273337385667,
+      "learning_rate": 4.895426713196623e-06,
+      "loss": 0.5035,
+      "step": 17
+    },
+    {
+      "epoch": 0.09782608695652174,
+      "grad_norm": 1.2086803983333478,
+      "learning_rate": 4.882861917035403e-06,
+      "loss": 0.5725,
+      "step": 18
+    },
+    {
+      "epoch": 0.10326086956521739,
+      "grad_norm": 1.3136408886489137,
+      "learning_rate": 4.86960249265034e-06,
+      "loss": 0.6055,
+      "step": 19
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 1.202947724847509,
+      "learning_rate": 4.855652305297052e-06,
+      "loss": 0.604,
+      "step": 20
+    },
+    {
+      "epoch": 0.11413043478260869,
+      "grad_norm": 1.2932177436433814,
+      "learning_rate": 4.841015421595511e-06,
+      "loss": 0.6176,
+      "step": 21
+    },
+    {
+      "epoch": 0.11956521739130435,
+      "grad_norm": 1.2233453885681989,
+      "learning_rate": 4.825696108344583e-06,
+      "loss": 0.5518,
+      "step": 22
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 1.1379076803478194,
+      "learning_rate": 4.809698831278217e-06,
+      "loss": 0.5245,
+      "step": 23
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 1.31309679515545,
+      "learning_rate": 4.793028253763633e-06,
+      "loss": 0.5473,
+      "step": 24
+    },
+    {
+      "epoch": 0.1358695652173913,
+      "grad_norm": 0.99390426063158,
+      "learning_rate": 4.775689235441906e-06,
+      "loss": 0.5001,
+      "step": 25
+    },
+    {
+      "epoch": 0.14130434782608695,
+      "grad_norm": 1.181674293785137,
+      "learning_rate": 4.757686830811332e-06,
+      "loss": 0.6344,
+      "step": 26
+    },
+    {
+      "epoch": 0.14673913043478262,
+      "grad_norm": 1.0970262798136268,
+      "learning_rate": 4.7390262877539915e-06,
+      "loss": 0.5064,
+      "step": 27
+    },
+    {
+      "epoch": 0.15217391304347827,
+      "grad_norm": 1.10526150432178,
+      "learning_rate": 4.7197130460059385e-06,
+      "loss": 0.4852,
+      "step": 28
+    },
+    {
+      "epoch": 0.15760869565217392,
+      "grad_norm": 1.1269305012977633,
+      "learning_rate": 4.69975273557146e-06,
+      "loss": 0.4956,
+      "step": 29
+    },
+    {
+      "epoch": 0.16304347826086957,
+      "grad_norm": 1.0238616783741092,
+      "learning_rate": 4.679151175081879e-06,
+      "loss": 0.4726,
+      "step": 30
+    },
+    {
+      "epoch": 0.16847826086956522,
+      "grad_norm": 1.0169722474314777,
+      "learning_rate": 4.657914370099357e-06,
+      "loss": 0.5194,
+      "step": 31
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 1.0133571834838249,
+      "learning_rate": 4.636048511366222e-06,
+      "loss": 0.5376,
+      "step": 32
+    },
+    {
+      "epoch": 0.1793478260869565,
+      "grad_norm": 1.105543373282609,
+      "learning_rate": 4.613559973000295e-06,
+      "loss": 0.4863,
+      "step": 33
+    },
+    {
+      "epoch": 0.18478260869565216,
+      "grad_norm": 1.052148451435705,
+      "learning_rate": 4.590455310636778e-06,
+      "loss": 0.425,
+      "step": 34
+    },
+    {
+      "epoch": 0.19021739130434784,
+      "grad_norm": 0.9973722594959911,
+      "learning_rate": 4.566741259517214e-06,
+      "loss": 0.4431,
+      "step": 35
+    },
+    {
+      "epoch": 0.1956521739130435,
+      "grad_norm": 1.0379302621563518,
+      "learning_rate": 4.542424732526105e-06,
+      "loss": 0.454,
+      "step": 36
+    },
+    {
+      "epoch": 0.20108695652173914,
+      "grad_norm": 1.1865959342834085,
+      "learning_rate": 4.517512818175726e-06,
+      "loss": 0.5536,
+      "step": 37
+    },
+    {
+      "epoch": 0.20652173913043478,
+      "grad_norm": 1.0605343348212255,
+      "learning_rate": 4.4920127785397615e-06,
+      "loss": 0.4864,
+      "step": 38
+    },
+    {
+      "epoch": 0.21195652173913043,
+      "grad_norm": 0.8673739993097423,
+      "learning_rate": 4.465932047136331e-06,
+      "loss": 0.4217,
+      "step": 39
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 1.0815220904408205,
+      "learning_rate": 4.43927822676105e-06,
+      "loss": 0.4627,
+      "step": 40
+    },
+    {
+      "epoch": 0.22282608695652173,
+      "grad_norm": 1.0956358658760348,
+      "learning_rate": 4.412059087270732e-06,
+      "loss": 0.4748,
+      "step": 41
+    },
+    {
+      "epoch": 0.22826086956521738,
+      "grad_norm": 1.021602675539127,
+      "learning_rate": 4.384282563318403e-06,
+      "loss": 0.4709,
+      "step": 42
+    },
+    {
+      "epoch": 0.23369565217391305,
+      "grad_norm": 1.0553309512985825,
+      "learning_rate": 4.355956752040267e-06,
+      "loss": 0.4805,
+      "step": 43
+    },
+    {
+      "epoch": 0.2391304347826087,
+      "grad_norm": 1.0035822724408363,
+      "learning_rate": 4.32708991069531e-06,
+      "loss": 0.5394,
+      "step": 44
+    },
+    {
+      "epoch": 0.24456521739130435,
+      "grad_norm": 1.07078036597118,
+      "learning_rate": 4.297690454258227e-06,
+      "loss": 0.5601,
+      "step": 45
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.9611507450827443,
+      "learning_rate": 4.267766952966369e-06,
+      "loss": 0.4798,
+      "step": 46
+    },
+    {
+      "epoch": 0.2554347826086957,
+      "grad_norm": 1.0000175347652656,
+      "learning_rate": 4.237328129821437e-06,
+      "loss": 0.4271,
+      "step": 47
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 0.9242111223677066,
+      "learning_rate": 4.206382858046636e-06,
+      "loss": 0.4118,
+      "step": 48
+    },
+    {
+      "epoch": 0.266304347826087,
+      "grad_norm": 1.028264771084294,
+      "learning_rate": 4.1749401585000415e-06,
+      "loss": 0.4322,
+      "step": 49
+    },
+    {
+      "epoch": 0.2717391304347826,
+      "grad_norm": 1.0771315965381705,
+      "learning_rate": 4.143009197044932e-06,
+      "loss": 0.4666,
+      "step": 50
+    },
+    {
+      "epoch": 0.27717391304347827,
+      "grad_norm": 1.0040817257242265,
+      "learning_rate": 4.1105992818778416e-06,
+      "loss": 0.4065,
+      "step": 51
+    },
+    {
+      "epoch": 0.2826086956521739,
+      "grad_norm": 1.038045673123147,
+      "learning_rate": 4.077719860815132e-06,
+      "loss": 0.4755,
+      "step": 52
+    },
+    {
+      "epoch": 0.28804347826086957,
+      "grad_norm": 1.0544574162960125,
+      "learning_rate": 4.044380518538859e-06,
+      "loss": 0.4954,
+      "step": 53
+    },
+    {
+      "epoch": 0.29347826086956524,
+      "grad_norm": 0.9958513271570262,
+      "learning_rate": 4.010590973802737e-06,
+      "loss": 0.4178,
+      "step": 54
+    },
+    {
+      "epoch": 0.29891304347826086,
+      "grad_norm": 1.0097460648720127,
+      "learning_rate": 3.976361076599027e-06,
+      "loss": 0.4033,
+      "step": 55
+    },
+    {
+      "epoch": 0.30434782608695654,
+      "grad_norm": 1.0091228454006114,
+      "learning_rate": 3.941700805287169e-06,
+      "loss": 0.4588,
+      "step": 56
+    },
+    {
+      "epoch": 0.30978260869565216,
+      "grad_norm": 1.0857951055357693,
+      "learning_rate": 3.906620263684979e-06,
+      "loss": 0.4786,
+      "step": 57
+    },
+    {
+      "epoch": 0.31521739130434784,
+      "grad_norm": 1.0969503919862431,
+      "learning_rate": 3.871129678123297e-06,
+      "loss": 0.522,
+      "step": 58
+    },
+    {
+      "epoch": 0.32065217391304346,
+      "grad_norm": 0.9839494108109739,
+      "learning_rate": 3.835239394464901e-06,
+      "loss": 0.4062,
+      "step": 59
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 0.9090774358899829,
+      "learning_rate": 3.798959875088584e-06,
+      "loss": 0.408,
+      "step": 60
+    },
+    {
+      "epoch": 0.33152173913043476,
+      "grad_norm": 1.2732936370569947,
+      "learning_rate": 3.7623016958392706e-06,
+      "loss": 0.4419,
+      "step": 61
+    },
+    {
+      "epoch": 0.33695652173913043,
+      "grad_norm": 0.926309712014225,
+      "learning_rate": 3.7252755429450437e-06,
+      "loss": 0.4245,
+      "step": 62
+    },
+    {
+      "epoch": 0.3423913043478261,
+      "grad_norm": 0.9497852432230279,
+      "learning_rate": 3.687892209902009e-06,
+      "loss": 0.393,
+      "step": 63
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.9545400829257247,
+      "learning_rate": 3.650162594327881e-06,
+      "loss": 0.4183,
+      "step": 64
+    },
+    {
+      "epoch": 0.3532608695652174,
+      "grad_norm": 1.1756359747464735,
+      "learning_rate": 3.612097694785211e-06,
+      "loss": 0.4696,
+      "step": 65
+    },
+    {
+      "epoch": 0.358695652173913,
+      "grad_norm": 1.0284202857037255,
+      "learning_rate": 3.5737086075752054e-06,
+      "loss": 0.4338,
+      "step": 66
+    },
+    {
+      "epoch": 0.3641304347826087,
+      "grad_norm": 1.0958411237100065,
+      "learning_rate": 3.535006523503034e-06,
+      "loss": 0.4399,
+      "step": 67
+    },
+    {
+      "epoch": 0.3695652173913043,
+      "grad_norm": 0.9844412675310313,
+      "learning_rate": 3.4960027246156043e-06,
+      "loss": 0.4385,
+      "step": 68
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.9898365415991396,
+      "learning_rate": 3.4567085809127247e-06,
+      "loss": 0.4302,
+      "step": 69
+    },
+    {
+      "epoch": 0.3804347826086957,
+      "grad_norm": 1.0582212588014415,
+      "learning_rate": 3.417135547032642e-06,
+      "loss": 0.5276,
+      "step": 70
+    },
+    {
+      "epoch": 0.3858695652173913,
+      "grad_norm": 1.019417494198468,
+      "learning_rate": 3.3772951589128926e-06,
+      "loss": 0.4742,
+      "step": 71
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 0.9463317429663586,
+      "learning_rate": 3.3371990304274654e-06,
+      "loss": 0.3976,
+      "step": 72
+    },
+    {
+      "epoch": 0.3967391304347826,
+      "grad_norm": 0.9709474517871337,
+      "learning_rate": 3.29685885000124e-06,
+      "loss": 0.4093,
+      "step": 73
+    },
+    {
+      "epoch": 0.40217391304347827,
+      "grad_norm": 0.863344821043942,
+      "learning_rate": 3.25628637720269e-06,
+      "loss": 0.4092,
+      "step": 74
+    },
+    {
+      "epoch": 0.4076086956521739,
+      "grad_norm": 0.9993622603586281,
+      "learning_rate": 3.215493439315854e-06,
+      "loss": 0.4763,
+      "step": 75
+    },
+    {
+      "epoch": 0.41304347826086957,
+      "grad_norm": 1.1526670488874815,
+      "learning_rate": 3.174491927892561e-06,
+      "loss": 0.483,
+      "step": 76
+    },
+    {
+      "epoch": 0.41847826086956524,
+      "grad_norm": 0.8998288666010263,
+      "learning_rate": 3.133293795285926e-06,
+      "loss": 0.391,
+      "step": 77
+    },
+    {
+      "epoch": 0.42391304347826086,
+      "grad_norm": 0.9336968611863948,
+      "learning_rate": 3.091911051166117e-06,
+      "loss": 0.5047,
+      "step": 78
+    },
+    {
+      "epoch": 0.42934782608695654,
+      "grad_norm": 0.9682376666728174,
+      "learning_rate": 3.050355759019414e-06,
+      "loss": 0.434,
+      "step": 79
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.9688021493484491,
+      "learning_rate": 3.0086400326315853e-06,
+      "loss": 0.4153,
+      "step": 80
+    },
+    {
+      "epoch": 0.44021739130434784,
+      "grad_norm": 0.8920569113789679,
+      "learning_rate": 2.966776032556591e-06,
+      "loss": 0.3982,
+      "step": 81
+    },
+    {
+      "epoch": 0.44565217391304346,
+      "grad_norm": 0.9133404413578968,
+      "learning_rate": 2.924775962571667e-06,
+      "loss": 0.4108,
+      "step": 82
+    },
+    {
+      "epoch": 0.45108695652173914,
+      "grad_norm": 1.1118165873307637,
+      "learning_rate": 2.882652066119795e-06,
+      "loss": 0.4788,
+      "step": 83
+    },
+    {
+      "epoch": 0.45652173913043476,
+      "grad_norm": 1.0151765034739209,
+      "learning_rate": 2.840416622740617e-06,
+      "loss": 0.4646,
+      "step": 84
+    },
+    {
+      "epoch": 0.46195652173913043,
+      "grad_norm": 0.9375173402952548,
+      "learning_rate": 2.798081944490828e-06,
+      "loss": 0.4538,
+      "step": 85
+    },
+    {
+      "epoch": 0.4673913043478261,
+      "grad_norm": 0.9680202667364934,
+      "learning_rate": 2.7556603723550855e-06,
+      "loss": 0.4356,
+      "step": 86
+    },
+    {
+      "epoch": 0.47282608695652173,
+      "grad_norm": 0.9422331373651006,
+      "learning_rate": 2.7131642726484902e-06,
+      "loss": 0.4032,
+      "step": 87
+    },
+    {
+      "epoch": 0.4782608695652174,
+      "grad_norm": 1.0481805110365574,
+      "learning_rate": 2.670606033411678e-06,
+      "loss": 0.429,
+      "step": 88
+    },
+    {
+      "epoch": 0.483695652173913,
+      "grad_norm": 0.9569814295107208,
+      "learning_rate": 2.6279980607995837e-06,
+      "loss": 0.4594,
+      "step": 89
+    },
+    {
+      "epoch": 0.4891304347826087,
+      "grad_norm": 1.0279998343634464,
+      "learning_rate": 2.58535277546492e-06,
+      "loss": 0.4404,
+      "step": 90
+    },
+    {
+      "epoch": 0.4945652173913043,
+      "grad_norm": 1.164962602586998,
+      "learning_rate": 2.5426826089374374e-06,
+      "loss": 0.4334,
+      "step": 91
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.9856154071356357,
+      "learning_rate": 2.5e-06,
+      "loss": 0.4405,
+      "step": 92
+    },
+    {
+      "epoch": 0.5054347826086957,
+      "grad_norm": 0.9542531977857515,
+      "learning_rate": 2.4573173910625634e-06,
+      "loss": 0.4071,
+      "step": 93
+    },
+    {
+      "epoch": 0.5108695652173914,
+      "grad_norm": 0.9642092100918749,
+      "learning_rate": 2.4146472245350804e-06,
+      "loss": 0.4756,
+      "step": 94
+    },
+    {
+      "epoch": 0.5163043478260869,
+      "grad_norm": 0.8900959458382038,
+      "learning_rate": 2.372001939200418e-06,
+      "loss": 0.3921,
+      "step": 95
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.9604266344799055,
+      "learning_rate": 2.3293939665883233e-06,
+      "loss": 0.409,
+      "step": 96
+    },
+    {
+      "epoch": 0.5271739130434783,
+      "grad_norm": 0.9990377921407856,
+      "learning_rate": 2.28683572735151e-06,
+      "loss": 0.4451,
+      "step": 97
+    },
+    {
+      "epoch": 0.532608695652174,
+      "grad_norm": 1.0462984343675805,
+      "learning_rate": 2.2443396276449145e-06,
+      "loss": 0.4839,
+      "step": 98
+    },
+    {
+      "epoch": 0.5380434782608695,
+      "grad_norm": 1.073400506995491,
+      "learning_rate": 2.201918055509173e-06,
+      "loss": 0.4896,
+      "step": 99
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 1.1909550497513488,
+      "learning_rate": 2.159583377259384e-06,
+      "loss": 0.5022,
+      "step": 100
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "eval_loss": 0.3715117275714874,
+      "eval_runtime": 0.935,
+      "eval_samples_per_second": 2.139,
+      "eval_steps_per_second": 1.069,
+      "step": 100
+    },
+    {
+      "epoch": 0.5489130434782609,
+      "grad_norm": 0.9400718427186292,
+      "learning_rate": 2.117347933880206e-06,
+      "loss": 0.3849,
+      "step": 101
+    },
+    {
+      "epoch": 0.5543478260869565,
+      "grad_norm": 0.9727361374013445,
+      "learning_rate": 2.0752240374283334e-06,
+      "loss": 0.3907,
+      "step": 102
+    },
+    {
+      "epoch": 0.5597826086956522,
+      "grad_norm": 1.3022499793776776,
+      "learning_rate": 2.0332239674434096e-06,
+      "loss": 0.4176,
+      "step": 103
+    },
+    {
+      "epoch": 0.5652173913043478,
+      "grad_norm": 1.1069006297376052,
+      "learning_rate": 1.991359967368416e-06,
+      "loss": 0.4004,
+      "step": 104
+    },
+    {
+      "epoch": 0.5706521739130435,
+      "grad_norm": 1.0486553461137778,
+      "learning_rate": 1.9496442409805867e-06,
+      "loss": 0.475,
+      "step": 105
+    },
+    {
+      "epoch": 0.5760869565217391,
+      "grad_norm": 1.0365724390047242,
+      "learning_rate": 1.9080889488338833e-06,
+      "loss": 0.4699,
+      "step": 106
+    },
+    {
+      "epoch": 0.5815217391304348,
+      "grad_norm": 0.9317372098910932,
+      "learning_rate": 1.866706204714074e-06,
+      "loss": 0.4527,
+      "step": 107
+    },
+    {
+      "epoch": 0.5869565217391305,
+      "grad_norm": 0.9524845392902372,
+      "learning_rate": 1.8255080721074391e-06,
+      "loss": 0.4163,
+      "step": 108
+    },
+    {
+      "epoch": 0.592391304347826,
+      "grad_norm": 1.0280946679262946,
+      "learning_rate": 1.7845065606841471e-06,
+      "loss": 0.4462,
+      "step": 109
+    },
+    {
+      "epoch": 0.5978260869565217,
+      "grad_norm": 1.0188541850859467,
+      "learning_rate": 1.7437136227973108e-06,
+      "loss": 0.4248,
+      "step": 110
+    },
+    {
+      "epoch": 0.6032608695652174,
+      "grad_norm": 1.0482920195174448,
+      "learning_rate": 1.7031411499987604e-06,
+      "loss": 0.3889,
+      "step": 111
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 0.8707132047823042,
+      "learning_rate": 1.6628009695725348e-06,
+      "loss": 0.38,
+      "step": 112
+    },
+    {
+      "epoch": 0.6141304347826086,
+      "grad_norm": 1.0343528495542806,
+      "learning_rate": 1.6227048410871085e-06,
+      "loss": 0.4233,
+      "step": 113
+    },
+    {
+      "epoch": 0.6195652173913043,
+      "grad_norm": 1.0443256128213538,
+      "learning_rate": 1.5828644529673592e-06,
+      "loss": 0.5463,
+      "step": 114
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.9228384601072962,
+      "learning_rate": 1.5432914190872757e-06,
+      "loss": 0.3818,
+      "step": 115
+    },
+    {
+      "epoch": 0.6304347826086957,
+      "grad_norm": 0.9263261363868085,
+      "learning_rate": 1.5039972753843966e-06,
+      "loss": 0.4116,
+      "step": 116
+    },
+    {
+      "epoch": 0.6358695652173914,
+      "grad_norm": 1.0285393144193637,
+      "learning_rate": 1.4649934764969665e-06,
+      "loss": 0.4151,
+      "step": 117
+    },
+    {
+      "epoch": 0.6413043478260869,
+      "grad_norm": 0.9076001194115818,
+      "learning_rate": 1.4262913924247956e-06,
+      "loss": 0.4156,
+      "step": 118
+    },
+    {
+      "epoch": 0.6467391304347826,
+      "grad_norm": 0.9087430569687185,
+      "learning_rate": 1.38790230521479e-06,
+      "loss": 0.3774,
+      "step": 119
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.901072751540499,
+      "learning_rate": 1.3498374056721198e-06,
+      "loss": 0.4139,
+      "step": 120
+    },
+    {
+      "epoch": 0.657608695652174,
+      "grad_norm": 0.9400408481939949,
+      "learning_rate": 1.3121077900979907e-06,
+      "loss": 0.3947,
+      "step": 121
+    },
+    {
+      "epoch": 0.6630434782608695,
+      "grad_norm": 0.9994277599062233,
+      "learning_rate": 1.2747244570549578e-06,
+      "loss": 0.4331,
+      "step": 122
+    },
+    {
+      "epoch": 0.6684782608695652,
+      "grad_norm": 0.931767446245499,
+      "learning_rate": 1.2376983041607307e-06,
+      "loss": 0.3783,
+      "step": 123
+    },
+    {
+      "epoch": 0.6739130434782609,
+      "grad_norm": 0.9268028742602399,
+      "learning_rate": 1.2010401249114166e-06,
+      "loss": 0.4424,
+      "step": 124
+    },
+    {
+      "epoch": 0.6793478260869565,
+      "grad_norm": 0.9292292630523812,
+      "learning_rate": 1.1647606055350997e-06,
+      "loss": 0.4392,
+      "step": 125
+    },
+    {
+      "epoch": 0.6847826086956522,
+      "grad_norm": 0.9451837833621994,
+      "learning_rate": 1.1288703218767027e-06,
+      "loss": 0.464,
+      "step": 126
+    },
+    {
+      "epoch": 0.6902173913043478,
+      "grad_norm": 0.9660334718086987,
+      "learning_rate": 1.0933797363150225e-06,
+      "loss": 0.4339,
+      "step": 127
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.8514103511766907,
+      "learning_rate": 1.0582991947128324e-06,
+      "loss": 0.365,
+      "step": 128
+    },
+    {
+      "epoch": 0.7010869565217391,
+      "grad_norm": 0.92426723208175,
+      "learning_rate": 1.0236389234009728e-06,
+      "loss": 0.3748,
+      "step": 129
+    },
+    {
+      "epoch": 0.7065217391304348,
+      "grad_norm": 1.1022691845671295,
+      "learning_rate": 9.89409026197264e-07,
+      "loss": 0.4782,
+      "step": 130
+    },
+    {
+      "epoch": 0.7119565217391305,
+      "grad_norm": 0.9501774740588051,
+      "learning_rate": 9.55619481461141e-07,
+      "loss": 0.4098,
+      "step": 131
+    },
+    {
+      "epoch": 0.717391304347826,
+      "grad_norm": 0.9917666719091651,
+      "learning_rate": 9.222801391848688e-07,
+      "loss": 0.4458,
+      "step": 132
+    },
+    {
+      "epoch": 0.7228260869565217,
+      "grad_norm": 1.021677038779048,
+      "learning_rate": 8.894007181221595e-07,
+      "loss": 0.4402,
+      "step": 133
+    },
+    {
+      "epoch": 0.7282608695652174,
+      "grad_norm": 1.0294072844823146,
+      "learning_rate": 8.569908029550686e-07,
+      "loss": 0.4857,
+      "step": 134
+    },
+    {
+      "epoch": 0.7336956521739131,
+      "grad_norm": 0.9956668167185507,
+      "learning_rate": 8.250598414999589e-07,
+      "loss": 0.4406,
+      "step": 135
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 0.9822165903831569,
+      "learning_rate": 7.936171419533653e-07,
+      "loss": 0.4333,
+      "step": 136
+    },
+    {
+      "epoch": 0.7445652173913043,
+      "grad_norm": 0.8569047748464629,
+      "learning_rate": 7.62671870178564e-07,
+      "loss": 0.4512,
+      "step": 137
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.0455210578743888,
+      "learning_rate": 7.322330470336314e-07,
+      "loss": 0.4849,
+      "step": 138
+    },
+    {
+      "epoch": 0.7554347826086957,
+      "grad_norm": 1.0722105793338157,
+      "learning_rate": 7.02309545741773e-07,
+      "loss": 0.4253,
+      "step": 139
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 0.9560191958831448,
+      "learning_rate": 6.729100893046897e-07,
+      "loss": 0.4188,
+      "step": 140
+    },
+    {
+      "epoch": 0.7663043478260869,
+      "grad_norm": 1.020699221188623,
+      "learning_rate": 6.440432479597333e-07,
+      "loss": 0.4505,
+      "step": 141
+    },
+    {
+      "epoch": 0.7717391304347826,
+      "grad_norm": 0.9630611230852171,
+      "learning_rate": 6.157174366815979e-07,
+      "loss": 0.3826,
+      "step": 142
+    },
+    {
+      "epoch": 0.7771739130434783,
+      "grad_norm": 0.8314388256793225,
+      "learning_rate": 5.879409127292685e-07,
+      "loss": 0.3957,
+      "step": 143
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 1.0064561329438817,
+      "learning_rate": 5.607217732389503e-07,
+      "loss": 0.4133,
+      "step": 144
+    },
+    {
+      "epoch": 0.7880434782608695,
+      "grad_norm": 0.8790902643562911,
+      "learning_rate": 5.340679528636694e-07,
+      "loss": 0.3539,
+      "step": 145
+    },
+    {
+      "epoch": 0.7934782608695652,
+      "grad_norm": 0.9949022795393011,
+      "learning_rate": 5.079872214602388e-07,
+      "loss": 0.4274,
+      "step": 146
+    },
+    {
+      "epoch": 0.7989130434782609,
+      "grad_norm": 0.9716596662546093,
+      "learning_rate": 4.82487181824274e-07,
+      "loss": 0.3931,
+      "step": 147
+    },
+    {
+      "epoch": 0.8043478260869565,
+      "grad_norm": 1.1016284432641374,
+      "learning_rate": 4.5757526747389506e-07,
+      "loss": 0.4495,
+      "step": 148
+    },
+    {
+      "epoch": 0.8097826086956522,
+      "grad_norm": 0.9750884127860542,
+      "learning_rate": 4.3325874048278537e-07,
+      "loss": 0.4076,
+      "step": 149
+    },
+    {
+      "epoch": 0.8152173913043478,
+      "grad_norm": 0.9851338434418264,
+      "learning_rate": 4.095446893632235e-07,
+      "loss": 0.4166,
+      "step": 150
+    },
+    {
+      "epoch": 0.8206521739130435,
+      "grad_norm": 0.9806382759341247,
+      "learning_rate": 3.8644002699970566e-07,
+      "loss": 0.499,
+      "step": 151
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 0.9618867355841195,
+      "learning_rate": 3.639514886337786e-07,
+      "loss": 0.3897,
+      "step": 152
+    },
+    {
+      "epoch": 0.8315217391304348,
+      "grad_norm": 0.8918258169737707,
+      "learning_rate": 3.4208562990064334e-07,
+      "loss": 0.3548,
+      "step": 153
+    },
+    {
+      "epoch": 0.8369565217391305,
+      "grad_norm": 0.9473535055854944,
+      "learning_rate": 3.208488249181216e-07,
+      "loss": 0.3645,
+      "step": 154
+    },
+    {
+      "epoch": 0.842391304347826,
+      "grad_norm": 0.926541933774413,
+      "learning_rate": 3.0024726442854063e-07,
+      "loss": 0.3862,
+      "step": 155
+    },
+    {
+      "epoch": 0.8478260869565217,
+      "grad_norm": 0.9377718233291452,
+      "learning_rate": 2.80286953994062e-07,
+      "loss": 0.3874,
+      "step": 156
+    },
+    {
+      "epoch": 0.8532608695652174,
+      "grad_norm": 0.9087021840918877,
+      "learning_rate": 2.609737122460082e-07,
+      "loss": 0.398,
+      "step": 157
+    },
+    {
+      "epoch": 0.8586956521739131,
+      "grad_norm": 0.9298831574256063,
+      "learning_rate": 2.423131691886682e-07,
+      "loss": 0.4108,
+      "step": 158
+    },
+    {
+      "epoch": 0.8641304347826086,
+      "grad_norm": 0.9942723543820461,
+      "learning_rate": 2.243107645580947e-07,
+      "loss": 0.4099,
+      "step": 159
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.933474792444763,
+      "learning_rate": 2.0697174623636795e-07,
+      "loss": 0.4135,
+      "step": 160
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.959186301766111,
+      "learning_rate": 1.9030116872178317e-07,
+      "loss": 0.3928,
+      "step": 161
+    },
+    {
+      "epoch": 0.8804347826086957,
+      "grad_norm": 0.859472699780449,
+      "learning_rate": 1.743038916554171e-07,
+      "loss": 0.348,
+      "step": 162
+    },
+    {
+      "epoch": 0.8858695652173914,
+      "grad_norm": 0.9725373730150572,
+      "learning_rate": 1.5898457840448994e-07,
+      "loss": 0.4296,
+      "step": 163
+    },
+    {
+      "epoch": 0.8913043478260869,
+      "grad_norm": 0.8608562583903794,
+      "learning_rate": 1.44347694702949e-07,
+      "loss": 0.3888,
+      "step": 164
+    },
+    {
+      "epoch": 0.8967391304347826,
+      "grad_norm": 0.9246961971953663,
+      "learning_rate": 1.3039750734966077e-07,
+      "loss": 0.4254,
+      "step": 165
+    },
+    {
+      "epoch": 0.9021739130434783,
+      "grad_norm": 0.8828678920115092,
+      "learning_rate": 1.1713808296459794e-07,
+      "loss": 0.407,
+      "step": 166
+    },
+    {
+      "epoch": 0.907608695652174,
+      "grad_norm": 0.9188852969350877,
+      "learning_rate": 1.0457328680337803e-07,
+      "loss": 0.4081,
+      "step": 167
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 0.9452831770803417,
+      "learning_rate": 9.270678163050218e-08,
+      "loss": 0.361,
+      "step": 168
+    },
+    {
+      "epoch": 0.9184782608695652,
+      "grad_norm": 0.9364787114852356,
+      "learning_rate": 8.154202665162147e-08,
+      "loss": 0.4196,
+      "step": 169
+    },
+    {
+      "epoch": 0.9239130434782609,
+      "grad_norm": 0.9377813379752988,
+      "learning_rate": 7.108227650514637e-08,
+      "loss": 0.4053,
+      "step": 170
+    },
+    {
+      "epoch": 0.9293478260869565,
+      "grad_norm": 0.973174255885484,
+      "learning_rate": 6.133058031348477e-08,
+      "loss": 0.4513,
+      "step": 171
+    },
+    {
+      "epoch": 0.9347826086956522,
+      "grad_norm": 0.9870763149755367,
+      "learning_rate": 5.2289780794192726e-08,
+      "loss": 0.5048,
+      "step": 172
+    },
+    {
+      "epoch": 0.9402173913043478,
+      "grad_norm": 0.848119894217448,
+      "learning_rate": 4.396251343129376e-08,
+      "loss": 0.4139,
+      "step": 173
+    },
+    {
+      "epoch": 0.9456521739130435,
+      "grad_norm": 0.8619004832051838,
+      "learning_rate": 3.635120570700784e-08,
+      "loss": 0.3555,
+      "step": 174
+    },
+    {
+      "epoch": 0.9510869565217391,
+      "grad_norm": 0.9499001892635056,
+      "learning_rate": 2.9458076394117686e-08,
+      "loss": 0.4414,
+      "step": 175
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 0.9253704314851796,
+      "learning_rate": 2.3285134909173113e-08,
+      "loss": 0.4146,
+      "step": 176
+    },
+    {
+      "epoch": 0.9619565217391305,
+      "grad_norm": 0.9863678874772576,
+      "learning_rate": 1.783418072672516e-08,
+      "loss": 0.4367,
+      "step": 177
+    },
+    {
+      "epoch": 0.967391304347826,
+      "grad_norm": 0.9663678855967001,
+      "learning_rate": 1.3106802854762901e-08,
+      "loss": 0.456,
+      "step": 178
+    },
+    {
+      "epoch": 0.9728260869565217,
+      "grad_norm": 0.8818345490886487,
+      "learning_rate": 9.104379371500104e-09,
+      "loss": 0.3899,
+      "step": 179
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 0.9092256558045821,
+      "learning_rate": 5.828077023651846e-09,
+      "loss": 0.4089,
+      "step": 180
+    },
+    {
+      "epoch": 0.9836956521739131,
+      "grad_norm": 0.9204571143511551,
+      "learning_rate": 3.278850886317686e-09,
+      "loss": 0.3432,
+      "step": 181
+    },
+    {
+      "epoch": 0.9891304347826086,
+      "grad_norm": 1.0757508596317866,
+      "learning_rate": 1.4574440845649406e-09,
+      "loss": 0.4631,
+      "step": 182
+    },
+    {
+      "epoch": 0.9945652173913043,
+      "grad_norm": 0.9341746011561843,
+      "learning_rate": 3.643875768025162e-10,
+      "loss": 0.3882,
+      "step": 183
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.925796005610107,
+      "learning_rate": 0.0,
+      "loss": 0.3512,
+      "step": 184
+    },
+    {
+      "epoch": 1.0,
+      "step": 184,
+      "total_flos": 35325739008000.0,
+      "train_loss": 0.4644851030214973,
+      "train_runtime": 696.0462,
+      "train_samples_per_second": 2.11,
+      "train_steps_per_second": 0.264
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 184,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 35325739008000.0,
+  "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:a081a499667317fc5d8c7fb3075191ebd642b52c90d610ed21c2961f4a73d756
+size 7160