Upload model

.gitattributes

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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: c1_math_nod_16s_10k
+  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. -->
+
+# c1_math_nod_16s_10k
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/c1_math_nod_16s_10k dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.5.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.992,
+    "total_flos": 2.045882781443031e+18,
+    "train_loss": 0.3715052679945261,
+    "train_runtime": 59669.4193,
+    "train_samples_per_second": 0.838,
+    "train_steps_per_second": 0.007
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
+  "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
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4458ac509cb411db9764a706f60190c3cbe435e084ebe0fd958548cad25494bb
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7bc4524a84a754c53515f47e67604f172e56e7218c37fae6cab46c513afe692
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c79e3f022b71e165d80643c3efa55fd8ac8961d29e8db8363db17d122f80dd
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6ed27770a666b797a6328cbd575d8f03d2320ad63d9f9f9e2d1cdca2a57172
+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"
+  }
+}

runs/Apr27_09-09-10_jrc0915/events.out.tfevents.1745737809.jrc0915.2792682.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a10118409880bc4a49154c0522b0932f4f03a33c78126d462264b2a0ccffa741
-size 76737
+oid sha256:3d76475906465c6b254353a135ae54f65c2bc463b69ed3b66456e27d3f6f4d98
+size 87641

special_tokens_map.json

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

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-27 09:09:10", "end_time": "2025-04-28 01:44:53"}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.992,
+    "total_flos": 2.045882781443031e+18,
+    "train_loss": 0.3715052679945261,
+    "train_runtime": 59669.4193,
+    "train_samples_per_second": 0.838,
+    "train_steps_per_second": 0.007
+}

trainer_log.jsonl

@@ -338,3 +338,54 @@
 {"current_steps": 338, "total_steps": 390, "loss": 0.2555, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "14:22:07", "remaining_time": "2:12:38"}
 {"current_steps": 339, "total_steps": 390, "loss": 0.2556, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "14:24:41", "remaining_time": "2:10:05"}
 {"current_steps": 340, "total_steps": 390, "loss": 0.2553, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "14:27:10", "remaining_time": "2:07:31"}
+{"current_steps": 341, "total_steps": 390, "loss": 0.2547, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "14:29:49", "remaining_time": "2:04:59"}
+{"current_steps": 342, "total_steps": 390, "loss": 0.2531, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "14:32:14", "remaining_time": "2:02:25"}
+{"current_steps": 343, "total_steps": 390, "loss": 0.2561, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "14:34:59", "remaining_time": "1:59:53"}
+{"current_steps": 344, "total_steps": 390, "loss": 0.2576, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "14:37:28", "remaining_time": "1:57:20"}
+{"current_steps": 345, "total_steps": 390, "loss": 0.2536, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "14:40:12", "remaining_time": "1:54:48"}
+{"current_steps": 346, "total_steps": 390, "loss": 0.2537, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "14:42:47", "remaining_time": "1:52:15"}
+{"current_steps": 347, "total_steps": 390, "loss": 0.2594, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "14:45:25", "remaining_time": "1:49:43"}
+{"current_steps": 348, "total_steps": 390, "loss": 0.2633, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "14:48:02", "remaining_time": "1:47:10"}
+{"current_steps": 349, "total_steps": 390, "loss": 0.2477, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "14:50:36", "remaining_time": "1:44:37"}
+{"current_steps": 350, "total_steps": 390, "loss": 0.2573, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "14:53:08", "remaining_time": "1:42:04"}
+{"current_steps": 351, "total_steps": 390, "loss": 0.2587, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "14:55:33", "remaining_time": "1:39:30"}
+{"current_steps": 352, "total_steps": 390, "loss": 0.2565, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "14:58:18", "remaining_time": "1:36:58"}
+{"current_steps": 353, "total_steps": 390, "loss": 0.2529, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "15:00:44", "remaining_time": "1:34:24"}
+{"current_steps": 354, "total_steps": 390, "loss": 0.2508, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "15:03:04", "remaining_time": "1:31:50"}
+{"current_steps": 355, "total_steps": 390, "loss": 0.2667, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "15:05:29", "remaining_time": "1:29:16"}
+{"current_steps": 356, "total_steps": 390, "loss": 0.2542, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "15:08:05", "remaining_time": "1:26:43"}
+{"current_steps": 357, "total_steps": 390, "loss": 0.2434, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "15:10:30", "remaining_time": "1:24:09"}
+{"current_steps": 358, "total_steps": 390, "loss": 0.2521, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "15:12:53", "remaining_time": "1:21:35"}
+{"current_steps": 359, "total_steps": 390, "loss": 0.2575, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "15:15:25", "remaining_time": "1:19:02"}
+{"current_steps": 360, "total_steps": 390, "loss": 0.2559, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "15:18:07", "remaining_time": "1:16:30"}
+{"current_steps": 361, "total_steps": 390, "loss": 0.2502, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "15:20:35", "remaining_time": "1:13:57"}
+{"current_steps": 362, "total_steps": 390, "loss": 0.2539, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "15:23:10", "remaining_time": "1:11:24"}
+{"current_steps": 363, "total_steps": 390, "loss": 0.2566, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "15:25:47", "remaining_time": "1:08:51"}
+{"current_steps": 364, "total_steps": 390, "loss": 0.2614, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "15:28:15", "remaining_time": "1:06:18"}
+{"current_steps": 365, "total_steps": 390, "loss": 0.2679, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "15:30:47", "remaining_time": "1:03:45"}
+{"current_steps": 366, "total_steps": 390, "loss": 0.2461, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "15:33:14", "remaining_time": "1:01:11"}
+{"current_steps": 367, "total_steps": 390, "loss": 0.2429, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "15:35:33", "remaining_time": "0:58:37"}
+{"current_steps": 368, "total_steps": 390, "loss": 0.2544, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "15:38:11", "remaining_time": "0:56:05"}
+{"current_steps": 369, "total_steps": 390, "loss": 0.2457, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "15:40:46", "remaining_time": "0:53:32"}
+{"current_steps": 370, "total_steps": 390, "loss": 0.2571, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "15:43:18", "remaining_time": "0:50:59"}
+{"current_steps": 371, "total_steps": 390, "loss": 0.2494, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "15:45:59", "remaining_time": "0:48:26"}
+{"current_steps": 372, "total_steps": 390, "loss": 0.2634, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "15:48:39", "remaining_time": "0:45:54"}
+{"current_steps": 373, "total_steps": 390, "loss": 0.2594, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "15:51:14", "remaining_time": "0:43:21"}
+{"current_steps": 374, "total_steps": 390, "loss": 0.2586, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "15:53:43", "remaining_time": "0:40:48"}
+{"current_steps": 375, "total_steps": 390, "loss": 0.2513, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "15:56:14", "remaining_time": "0:38:14"}
+{"current_steps": 376, "total_steps": 390, "loss": 0.2575, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "15:58:33", "remaining_time": "0:35:41"}
+{"current_steps": 377, "total_steps": 390, "loss": 0.265, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "16:01:14", "remaining_time": "0:33:08"}
+{"current_steps": 378, "total_steps": 390, "loss": 0.2446, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "16:03:44", "remaining_time": "0:30:35"}
+{"current_steps": 379, "total_steps": 390, "loss": 0.2642, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "16:06:22", "remaining_time": "0:28:02"}
+{"current_steps": 380, "total_steps": 390, "loss": 0.2646, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "16:09:08", "remaining_time": "0:25:30"}
+{"current_steps": 381, "total_steps": 390, "loss": 0.2484, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "16:11:50", "remaining_time": "0:22:57"}
+{"current_steps": 382, "total_steps": 390, "loss": 0.2519, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "16:14:26", "remaining_time": "0:20:24"}
+{"current_steps": 383, "total_steps": 390, "loss": 0.2581, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "16:17:02", "remaining_time": "0:17:51"}
+{"current_steps": 384, "total_steps": 390, "loss": 0.2542, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "16:19:27", "remaining_time": "0:15:18"}
+{"current_steps": 385, "total_steps": 390, "loss": 0.2498, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "16:21:44", "remaining_time": "0:12:44"}
+{"current_steps": 386, "total_steps": 390, "loss": 0.2466, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "16:24:13", "remaining_time": "0:10:11"}
+{"current_steps": 387, "total_steps": 390, "loss": 0.252, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "16:26:34", "remaining_time": "0:07:38"}
+{"current_steps": 388, "total_steps": 390, "loss": 0.2619, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "16:29:00", "remaining_time": "0:05:05"}
+{"current_steps": 389, "total_steps": 390, "loss": 0.251, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "16:31:13", "remaining_time": "0:02:32"}
+{"current_steps": 390, "total_steps": 390, "loss": 0.2486, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "16:33:33", "remaining_time": "0:00:00"}
+{"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "16:34:26", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2772 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.992,
+  "eval_steps": 500,
+  "global_step": 390,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0128,
+      "grad_norm": 6.348719385400729,
+      "learning_rate": 1.0256410256410257e-06,
+      "loss": 0.8218,
+      "step": 1
+    },
+    {
+      "epoch": 0.0256,
+      "grad_norm": 6.379954751506956,
+      "learning_rate": 2.0512820512820513e-06,
+      "loss": 0.8227,
+      "step": 2
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 6.210132772767404,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 0.8096,
+      "step": 3
+    },
+    {
+      "epoch": 0.0512,
+      "grad_norm": 5.555223269299381,
+      "learning_rate": 4.102564102564103e-06,
+      "loss": 0.7763,
+      "step": 4
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 4.013837876407829,
+      "learning_rate": 5.128205128205128e-06,
+      "loss": 0.7497,
+      "step": 5
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 2.2206462685611914,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.7183,
+      "step": 6
+    },
+    {
+      "epoch": 0.0896,
+      "grad_norm": 1.882759699089568,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 0.6852,
+      "step": 7
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 4.0630440682988125,
+      "learning_rate": 8.205128205128205e-06,
+      "loss": 0.726,
+      "step": 8
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 4.228183041761707,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.717,
+      "step": 9
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 4.359511380577437,
+      "learning_rate": 1.0256410256410256e-05,
+      "loss": 0.6937,
+      "step": 10
+    },
+    {
+      "epoch": 0.1408,
+      "grad_norm": 3.843158263355942,
+      "learning_rate": 1.1282051282051283e-05,
+      "loss": 0.6795,
+      "step": 11
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 2.128474260030976,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 0.6543,
+      "step": 12
+    },
+    {
+      "epoch": 0.1664,
+      "grad_norm": 1.7717501624194085,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.6425,
+      "step": 13
+    },
+    {
+      "epoch": 0.1792,
+      "grad_norm": 2.1455329319772543,
+      "learning_rate": 1.435897435897436e-05,
+      "loss": 0.6301,
+      "step": 14
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 1.7156298959789036,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.601,
+      "step": 15
+    },
+    {
+      "epoch": 0.2048,
+      "grad_norm": 1.0545385296489183,
+      "learning_rate": 1.641025641025641e-05,
+      "loss": 0.583,
+      "step": 16
+    },
+    {
+      "epoch": 0.2176,
+      "grad_norm": 1.1443968955651758,
+      "learning_rate": 1.7435897435897438e-05,
+      "loss": 0.5968,
+      "step": 17
+    },
+    {
+      "epoch": 0.2304,
+      "grad_norm": 0.8833328251136545,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 0.5671,
+      "step": 18
+    },
+    {
+      "epoch": 0.2432,
+      "grad_norm": 0.991604766166693,
+      "learning_rate": 1.9487179487179488e-05,
+      "loss": 0.5727,
+      "step": 19
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.8995658386946415,
+      "learning_rate": 2.0512820512820512e-05,
+      "loss": 0.5725,
+      "step": 20
+    },
+    {
+      "epoch": 0.2688,
+      "grad_norm": 0.8199813687662335,
+      "learning_rate": 2.153846153846154e-05,
+      "loss": 0.5398,
+      "step": 21
+    },
+    {
+      "epoch": 0.2816,
+      "grad_norm": 1.0260835390861582,
+      "learning_rate": 2.2564102564102566e-05,
+      "loss": 0.5317,
+      "step": 22
+    },
+    {
+      "epoch": 0.2944,
+      "grad_norm": 0.6832086635108956,
+      "learning_rate": 2.3589743589743593e-05,
+      "loss": 0.5407,
+      "step": 23
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 0.8625680681856057,
+      "learning_rate": 2.461538461538462e-05,
+      "loss": 0.55,
+      "step": 24
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.7939913972073019,
+      "learning_rate": 2.5641025641025646e-05,
+      "loss": 0.5309,
+      "step": 25
+    },
+    {
+      "epoch": 0.3328,
+      "grad_norm": 0.7937550421722755,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.5292,
+      "step": 26
+    },
+    {
+      "epoch": 0.3456,
+      "grad_norm": 0.8528014349564067,
+      "learning_rate": 2.7692307692307694e-05,
+      "loss": 0.5202,
+      "step": 27
+    },
+    {
+      "epoch": 0.3584,
+      "grad_norm": 0.8680007998806677,
+      "learning_rate": 2.871794871794872e-05,
+      "loss": 0.511,
+      "step": 28
+    },
+    {
+      "epoch": 0.3712,
+      "grad_norm": 0.6880356086342507,
+      "learning_rate": 2.9743589743589747e-05,
+      "loss": 0.5109,
+      "step": 29
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.8111547783270939,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 0.5059,
+      "step": 30
+    },
+    {
+      "epoch": 0.3968,
+      "grad_norm": 0.7842669557145766,
+      "learning_rate": 3.1794871794871795e-05,
+      "loss": 0.5164,
+      "step": 31
+    },
+    {
+      "epoch": 0.4096,
+      "grad_norm": 1.1184692126926417,
+      "learning_rate": 3.282051282051282e-05,
+      "loss": 0.5091,
+      "step": 32
+    },
+    {
+      "epoch": 0.4224,
+      "grad_norm": 0.9325784798643783,
+      "learning_rate": 3.384615384615385e-05,
+      "loss": 0.5,
+      "step": 33
+    },
+    {
+      "epoch": 0.4352,
+      "grad_norm": 0.8798203145744703,
+      "learning_rate": 3.4871794871794875e-05,
+      "loss": 0.4964,
+      "step": 34
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.6593479804265344,
+      "learning_rate": 3.58974358974359e-05,
+      "loss": 0.5219,
+      "step": 35
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 0.8678038838330197,
+      "learning_rate": 3.692307692307693e-05,
+      "loss": 0.5088,
+      "step": 36
+    },
+    {
+      "epoch": 0.4736,
+      "grad_norm": 0.6932296734866301,
+      "learning_rate": 3.794871794871795e-05,
+      "loss": 0.4759,
+      "step": 37
+    },
+    {
+      "epoch": 0.4864,
+      "grad_norm": 0.6328092927082333,
+      "learning_rate": 3.8974358974358976e-05,
+      "loss": 0.5014,
+      "step": 38
+    },
+    {
+      "epoch": 0.4992,
+      "grad_norm": 0.8012418340674077,
+      "learning_rate": 4e-05,
+      "loss": 0.4933,
+      "step": 39
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 2.294292075517914,
+      "learning_rate": 3.9999198907597046e-05,
+      "loss": 0.5043,
+      "step": 40
+    },
+    {
+      "epoch": 0.5248,
+      "grad_norm": 1.0279572081538422,
+      "learning_rate": 3.9996795694563096e-05,
+      "loss": 0.4928,
+      "step": 41
+    },
+    {
+      "epoch": 0.5376,
+      "grad_norm": 1.5275881600236365,
+      "learning_rate": 3.999279055341771e-05,
+      "loss": 0.4992,
+      "step": 42
+    },
+    {
+      "epoch": 0.5504,
+      "grad_norm": 0.959850333759674,
+      "learning_rate": 3.998718380500971e-05,
+      "loss": 0.4911,
+      "step": 43
+    },
+    {
+      "epoch": 0.5632,
+      "grad_norm": 1.4500214279522923,
+      "learning_rate": 3.997997589849145e-05,
+      "loss": 0.4988,
+      "step": 44
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 1.1957858838427657,
+      "learning_rate": 3.9971167411282835e-05,
+      "loss": 0.4941,
+      "step": 45
+    },
+    {
+      "epoch": 0.5888,
+      "grad_norm": 1.0610514145679766,
+      "learning_rate": 3.99607590490251e-05,
+      "loss": 0.4821,
+      "step": 46
+    },
+    {
+      "epoch": 0.6016,
+      "grad_norm": 1.3103377509652188,
+      "learning_rate": 3.9948751645524235e-05,
+      "loss": 0.494,
+      "step": 47
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 0.7690187477717879,
+      "learning_rate": 3.9935146162684206e-05,
+      "loss": 0.4966,
+      "step": 48
+    },
+    {
+      "epoch": 0.6272,
+      "grad_norm": 1.230084513161983,
+      "learning_rate": 3.9919943690429906e-05,
+      "loss": 0.4967,
+      "step": 49
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.7648758052449948,
+      "learning_rate": 3.9903145446619837e-05,
+      "loss": 0.4763,
+      "step": 50
+    },
+    {
+      "epoch": 0.6528,
+      "grad_norm": 1.1100485573326222,
+      "learning_rate": 3.9884752776948564e-05,
+      "loss": 0.4949,
+      "step": 51
+    },
+    {
+      "epoch": 0.6656,
+      "grad_norm": 0.9473987265953581,
+      "learning_rate": 3.9864767154838864e-05,
+      "loss": 0.4851,
+      "step": 52
+    },
+    {
+      "epoch": 0.6784,
+      "grad_norm": 0.6303619267038715,
+      "learning_rate": 3.9843190181323744e-05,
+      "loss": 0.4594,
+      "step": 53
+    },
+    {
+      "epoch": 0.6912,
+      "grad_norm": 0.9006285259920646,
+      "learning_rate": 3.982002358491817e-05,
+      "loss": 0.4766,
+      "step": 54
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.5661965904399766,
+      "learning_rate": 3.979526922148058e-05,
+      "loss": 0.4819,
+      "step": 55
+    },
+    {
+      "epoch": 0.7168,
+      "grad_norm": 0.7633176436718434,
+      "learning_rate": 3.9768929074064206e-05,
+      "loss": 0.4865,
+      "step": 56
+    },
+    {
+      "epoch": 0.7296,
+      "grad_norm": 0.58688207468279,
+      "learning_rate": 3.9741005252758255e-05,
+      "loss": 0.4725,
+      "step": 57
+    },
+    {
+      "epoch": 0.7424,
+      "grad_norm": 0.6250584704185816,
+      "learning_rate": 3.971149999451886e-05,
+      "loss": 0.4553,
+      "step": 58
+    },
+    {
+      "epoch": 0.7552,
+      "grad_norm": 0.6197662908437699,
+      "learning_rate": 3.9680415662989806e-05,
+      "loss": 0.4614,
+      "step": 59
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.7543087391929115,
+      "learning_rate": 3.9647754748313294e-05,
+      "loss": 0.4743,
+      "step": 60
+    },
+    {
+      "epoch": 0.7808,
+      "grad_norm": 0.5961068368949659,
+      "learning_rate": 3.96135198669304e-05,
+      "loss": 0.4564,
+      "step": 61
+    },
+    {
+      "epoch": 0.7936,
+      "grad_norm": 0.6303369279299224,
+      "learning_rate": 3.957771376137144e-05,
+      "loss": 0.472,
+      "step": 62
+    },
+    {
+      "epoch": 0.8064,
+      "grad_norm": 0.498029115786155,
+      "learning_rate": 3.954033930003634e-05,
+      "loss": 0.4512,
+      "step": 63
+    },
+    {
+      "epoch": 0.8192,
+      "grad_norm": 0.5739651320118427,
+      "learning_rate": 3.9501399476964806e-05,
+      "loss": 0.4638,
+      "step": 64
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.4595956447481022,
+      "learning_rate": 3.946089741159648e-05,
+      "loss": 0.4508,
+      "step": 65
+    },
+    {
+      "epoch": 0.8448,
+      "grad_norm": 0.5046418509990033,
+      "learning_rate": 3.9418836348521045e-05,
+      "loss": 0.4679,
+      "step": 66
+    },
+    {
+      "epoch": 0.8576,
+      "grad_norm": 0.41967465614562705,
+      "learning_rate": 3.937521965721831e-05,
+      "loss": 0.4624,
+      "step": 67
+    },
+    {
+      "epoch": 0.8704,
+      "grad_norm": 0.5472710578638964,
+      "learning_rate": 3.933005083178828e-05,
+      "loss": 0.4532,
+      "step": 68
+    },
+    {
+      "epoch": 0.8832,
+      "grad_norm": 0.4876940094426317,
+      "learning_rate": 3.928333349067125e-05,
+      "loss": 0.4682,
+      "step": 69
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.5315771109939708,
+      "learning_rate": 3.923507137635792e-05,
+      "loss": 0.4796,
+      "step": 70
+    },
+    {
+      "epoch": 0.9088,
+      "grad_norm": 0.6536628077401216,
+      "learning_rate": 3.9185268355089606e-05,
+      "loss": 0.453,
+      "step": 71
+    },
+    {
+      "epoch": 0.9216,
+      "grad_norm": 0.4283216636301797,
+      "learning_rate": 3.913392841654851e-05,
+      "loss": 0.4372,
+      "step": 72
+    },
+    {
+      "epoch": 0.9344,
+      "grad_norm": 0.5123343639419006,
+      "learning_rate": 3.9081055673538093e-05,
+      "loss": 0.4636,
+      "step": 73
+    },
+    {
+      "epoch": 0.9472,
+      "grad_norm": 0.38168726743614473,
+      "learning_rate": 3.902665436165364e-05,
+      "loss": 0.4549,
+      "step": 74
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.5703789091002631,
+      "learning_rate": 3.897072883894291e-05,
+      "loss": 0.4688,
+      "step": 75
+    },
+    {
+      "epoch": 0.9728,
+      "grad_norm": 0.48986576695749307,
+      "learning_rate": 3.8913283585557054e-05,
+      "loss": 0.4497,
+      "step": 76
+    },
+    {
+      "epoch": 0.9856,
+      "grad_norm": 0.42908631293380195,
+      "learning_rate": 3.885432320339167e-05,
+      "loss": 0.4574,
+      "step": 77
+    },
+    {
+      "epoch": 0.9984,
+      "grad_norm": 0.551886846221264,
+      "learning_rate": 3.879385241571817e-05,
+      "loss": 0.4554,
+      "step": 78
+    },
+    {
+      "epoch": 1.0112,
+      "grad_norm": 1.160566989928732,
+      "learning_rate": 3.873187606680543e-05,
+      "loss": 0.8193,
+      "step": 79
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 1.4911505536574488,
+      "learning_rate": 3.866839912153168e-05,
+      "loss": 0.4354,
+      "step": 80
+    },
+    {
+      "epoch": 1.0368,
+      "grad_norm": 0.6471052825546909,
+      "learning_rate": 3.860342666498677e-05,
+      "loss": 0.4271,
+      "step": 81
+    },
+    {
+      "epoch": 1.0496,
+      "grad_norm": 0.8508360664837862,
+      "learning_rate": 3.853696390206484e-05,
+      "loss": 0.4131,
+      "step": 82
+    },
+    {
+      "epoch": 1.0624,
+      "grad_norm": 0.8812303236317185,
+      "learning_rate": 3.846901615704734e-05,
+      "loss": 0.4277,
+      "step": 83
+    },
+    {
+      "epoch": 1.0752,
+      "grad_norm": 0.8040978948555603,
+      "learning_rate": 3.839958887317649e-05,
+      "loss": 0.4329,
+      "step": 84
+    },
+    {
+      "epoch": 1.088,
+      "grad_norm": 0.6640777420807941,
+      "learning_rate": 3.832868761221926e-05,
+      "loss": 0.4111,
+      "step": 85
+    },
+    {
+      "epoch": 1.1008,
+      "grad_norm": 0.7372753644267089,
+      "learning_rate": 3.825631805402182e-05,
+      "loss": 0.4119,
+      "step": 86
+    },
+    {
+      "epoch": 1.1136,
+      "grad_norm": 0.6108533277182515,
+      "learning_rate": 3.818248599605448e-05,
+      "loss": 0.4374,
+      "step": 87
+    },
+    {
+      "epoch": 1.1264,
+      "grad_norm": 0.6755422553776933,
+      "learning_rate": 3.810719735294731e-05,
+      "loss": 0.4246,
+      "step": 88
+    },
+    {
+      "epoch": 1.1392,
+      "grad_norm": 0.6735701854764322,
+      "learning_rate": 3.8030458156016326e-05,
+      "loss": 0.4256,
+      "step": 89
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 0.634913204395266,
+      "learning_rate": 3.795227455278029e-05,
+      "loss": 0.418,
+      "step": 90
+    },
+    {
+      "epoch": 1.1648,
+      "grad_norm": 0.6101913254273709,
+      "learning_rate": 3.787265280646825e-05,
+      "loss": 0.4156,
+      "step": 91
+    },
+    {
+      "epoch": 1.1776,
+      "grad_norm": 0.6630463952719416,
+      "learning_rate": 3.7791599295517825e-05,
+      "loss": 0.4161,
+      "step": 92
+    },
+    {
+      "epoch": 1.1904,
+      "grad_norm": 0.540715859249182,
+      "learning_rate": 3.7709120513064196e-05,
+      "loss": 0.4214,
+      "step": 93
+    },
+    {
+      "epoch": 1.2032,
+      "grad_norm": 0.6872658183726058,
+      "learning_rate": 3.762522306641998e-05,
+      "loss": 0.4248,
+      "step": 94
+    },
+    {
+      "epoch": 1.216,
+      "grad_norm": 0.5814808743468538,
+      "learning_rate": 3.7539913676545874e-05,
+      "loss": 0.4022,
+      "step": 95
+    },
+    {
+      "epoch": 1.2288000000000001,
+      "grad_norm": 0.5369083951917868,
+      "learning_rate": 3.745319917751229e-05,
+      "loss": 0.4168,
+      "step": 96
+    },
+    {
+      "epoch": 1.2416,
+      "grad_norm": 0.565027828995751,
+      "learning_rate": 3.736508651595188e-05,
+      "loss": 0.4044,
+      "step": 97
+    },
+    {
+      "epoch": 1.2544,
+      "grad_norm": 0.46918728589873765,
+      "learning_rate": 3.727558275050301e-05,
+      "loss": 0.4141,
+      "step": 98
+    },
+    {
+      "epoch": 1.2671999999999999,
+      "grad_norm": 0.5600534312608921,
+      "learning_rate": 3.718469505124434e-05,
+      "loss": 0.4215,
+      "step": 99
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.4452629483666243,
+      "learning_rate": 3.709243069912041e-05,
+      "loss": 0.4234,
+      "step": 100
+    },
+    {
+      "epoch": 1.2928,
+      "grad_norm": 0.5386764173519087,
+      "learning_rate": 3.699879708535838e-05,
+      "loss": 0.4176,
+      "step": 101
+    },
+    {
+      "epoch": 1.3056,
+      "grad_norm": 0.47495462747978756,
+      "learning_rate": 3.69038017108759e-05,
+      "loss": 0.4152,
+      "step": 102
+    },
+    {
+      "epoch": 1.3184,
+      "grad_norm": 0.4556852239466066,
+      "learning_rate": 3.680745218568026e-05,
+      "loss": 0.4077,
+      "step": 103
+    },
+    {
+      "epoch": 1.3312,
+      "grad_norm": 0.5154397546464594,
+      "learning_rate": 3.6709756228258735e-05,
+      "loss": 0.4327,
+      "step": 104
+    },
+    {
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.4221553072345879,
+      "learning_rate": 3.6610721664960236e-05,
+      "loss": 0.4025,
+      "step": 105
+    },
+    {
+      "epoch": 1.3568,
+      "grad_norm": 0.45999727686316505,
+      "learning_rate": 3.65103564293684e-05,
+      "loss": 0.402,
+      "step": 106
+    },
+    {
+      "epoch": 1.3696,
+      "grad_norm": 0.3786919376191657,
+      "learning_rate": 3.640866856166601e-05,
+      "loss": 0.4134,
+      "step": 107
+    },
+    {
+      "epoch": 1.3824,
+      "grad_norm": 0.41869587096058153,
+      "learning_rate": 3.6305666207990886e-05,
+      "loss": 0.407,
+      "step": 108
+    },
+    {
+      "epoch": 1.3952,
+      "grad_norm": 0.3042293142497492,
+      "learning_rate": 3.6201357619783336e-05,
+      "loss": 0.4013,
+      "step": 109
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 0.42396948323179723,
+      "learning_rate": 3.609575115312511e-05,
+      "loss": 0.4259,
+      "step": 110
+    },
+    {
+      "epoch": 1.4208,
+      "grad_norm": 0.3479027912678823,
+      "learning_rate": 3.598885526807003e-05,
+      "loss": 0.3981,
+      "step": 111
+    },
+    {
+      "epoch": 1.4336,
+      "grad_norm": 0.42494919707328943,
+      "learning_rate": 3.5880678527966224e-05,
+      "loss": 0.406,
+      "step": 112
+    },
+    {
+      "epoch": 1.4464000000000001,
+      "grad_norm": 0.3080481092119053,
+      "learning_rate": 3.577122959877017e-05,
+      "loss": 0.392,
+      "step": 113
+    },
+    {
+      "epoch": 1.4592,
+      "grad_norm": 0.3797077757315768,
+      "learning_rate": 3.566051724835245e-05,
+      "loss": 0.412,
+      "step": 114
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.36410660310467663,
+      "learning_rate": 3.554855034579532e-05,
+      "loss": 0.4118,
+      "step": 115
+    },
+    {
+      "epoch": 1.4848,
+      "grad_norm": 0.3586536272996398,
+      "learning_rate": 3.5435337860682304e-05,
+      "loss": 0.391,
+      "step": 116
+    },
+    {
+      "epoch": 1.4976,
+      "grad_norm": 0.3381546817037872,
+      "learning_rate": 3.532088886237956e-05,
+      "loss": 0.4216,
+      "step": 117
+    },
+    {
+      "epoch": 1.5104,
+      "grad_norm": 0.41591871367264127,
+      "learning_rate": 3.520521251930941e-05,
+      "loss": 0.4084,
+      "step": 118
+    },
+    {
+      "epoch": 1.5232,
+      "grad_norm": 0.3830188969686834,
+      "learning_rate": 3.5088318098215805e-05,
+      "loss": 0.3988,
+      "step": 119
+    },
+    {
+      "epoch": 1.536,
+      "grad_norm": 0.36578779264910555,
+      "learning_rate": 3.497021496342203e-05,
+      "loss": 0.4191,
+      "step": 120
+    },
+    {
+      "epoch": 1.5488,
+      "grad_norm": 0.40769244471248295,
+      "learning_rate": 3.485091257608047e-05,
+      "loss": 0.4045,
+      "step": 121
+    },
+    {
+      "epoch": 1.5615999999999999,
+      "grad_norm": 0.43800487909488256,
+      "learning_rate": 3.473042049341474e-05,
+      "loss": 0.4115,
+      "step": 122
+    },
+    {
+      "epoch": 1.5744,
+      "grad_norm": 0.3272253449664985,
+      "learning_rate": 3.4608748367954064e-05,
+      "loss": 0.4072,
+      "step": 123
+    },
+    {
+      "epoch": 1.5872000000000002,
+      "grad_norm": 0.4586096588271858,
+      "learning_rate": 3.4485905946759965e-05,
+      "loss": 0.3972,
+      "step": 124
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.39191689279960934,
+      "learning_rate": 3.4361903070645484e-05,
+      "loss": 0.4169,
+      "step": 125
+    },
+    {
+      "epoch": 1.6128,
+      "grad_norm": 0.31988900575159457,
+      "learning_rate": 3.423674967338681e-05,
+      "loss": 0.4085,
+      "step": 126
+    },
+    {
+      "epoch": 1.6256,
+      "grad_norm": 0.3582752218421195,
+      "learning_rate": 3.411045578092754e-05,
+      "loss": 0.4069,
+      "step": 127
+    },
+    {
+      "epoch": 1.6383999999999999,
+      "grad_norm": 0.3577653716972445,
+      "learning_rate": 3.398303151057543e-05,
+      "loss": 0.4104,
+      "step": 128
+    },
+    {
+      "epoch": 1.6512,
+      "grad_norm": 0.29375379841406046,
+      "learning_rate": 3.385448707019199e-05,
+      "loss": 0.3929,
+      "step": 129
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.3633389891783201,
+      "learning_rate": 3.372483275737468e-05,
+      "loss": 0.4114,
+      "step": 130
+    },
+    {
+      "epoch": 1.6768,
+      "grad_norm": 0.3210601977705595,
+      "learning_rate": 3.359407895863199e-05,
+      "loss": 0.3996,
+      "step": 131
+    },
+    {
+      "epoch": 1.6896,
+      "grad_norm": 0.3326740704204422,
+      "learning_rate": 3.34622361485514e-05,
+      "loss": 0.4013,
+      "step": 132
+    },
+    {
+      "epoch": 1.7024,
+      "grad_norm": 0.3014802942326302,
+      "learning_rate": 3.332931488896029e-05,
+      "loss": 0.4011,
+      "step": 133
+    },
+    {
+      "epoch": 1.7151999999999998,
+      "grad_norm": 0.34655444944495806,
+      "learning_rate": 3.319532582807977e-05,
+      "loss": 0.4063,
+      "step": 134
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.34212464785286284,
+      "learning_rate": 3.30602796996717e-05,
+      "loss": 0.3915,
+      "step": 135
+    },
+    {
+      "epoch": 1.7408000000000001,
+      "grad_norm": 0.31205603753947553,
+      "learning_rate": 3.2924187322178865e-05,
+      "loss": 0.4093,
+      "step": 136
+    },
+    {
+      "epoch": 1.7536,
+      "grad_norm": 0.3216120679187141,
+      "learning_rate": 3.278705959785821e-05,
+      "loss": 0.4143,
+      "step": 137
+    },
+    {
+      "epoch": 1.7664,
+      "grad_norm": 0.3937840865701883,
+      "learning_rate": 3.2648907511907544e-05,
+      "loss": 0.411,
+      "step": 138
+    },
+    {
+      "epoch": 1.7792,
+      "grad_norm": 0.35109640146106413,
+      "learning_rate": 3.250974213158555e-05,
+      "loss": 0.3958,
+      "step": 139
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.3284927116846856,
+      "learning_rate": 3.23695746053251e-05,
+      "loss": 0.4095,
+      "step": 140
+    },
+    {
+      "epoch": 1.8048,
+      "grad_norm": 0.28089985160161585,
+      "learning_rate": 3.222841616184025e-05,
+      "loss": 0.3981,
+      "step": 141
+    },
+    {
+      "epoch": 1.8176,
+      "grad_norm": 0.32384785241048564,
+      "learning_rate": 3.208627810922665e-05,
+      "loss": 0.4158,
+      "step": 142
+    },
+    {
+      "epoch": 1.8304,
+      "grad_norm": 0.31965227790963224,
+      "learning_rate": 3.194317183405573e-05,
+      "loss": 0.3917,
+      "step": 143
+    },
+    {
+      "epoch": 1.8432,
+      "grad_norm": 0.3595068269069532,
+      "learning_rate": 3.1799108800462466e-05,
+      "loss": 0.4177,
+      "step": 144
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.418443123997006,
+      "learning_rate": 3.1654100549227024e-05,
+      "loss": 0.3985,
+      "step": 145
+    },
+    {
+      "epoch": 1.8688,
+      "grad_norm": 0.32273710987386056,
+      "learning_rate": 3.1508158696850275e-05,
+      "loss": 0.3999,
+      "step": 146
+    },
+    {
+      "epoch": 1.8816000000000002,
+      "grad_norm": 0.31348145645897846,
+      "learning_rate": 3.136129493462312e-05,
+      "loss": 0.4042,
+      "step": 147
+    },
+    {
+      "epoch": 1.8944,
+      "grad_norm": 0.4005388342521965,
+      "learning_rate": 3.121352102768998e-05,
+      "loss": 0.4186,
+      "step": 148
+    },
+    {
+      "epoch": 1.9072,
+      "grad_norm": 0.35596025771656525,
+      "learning_rate": 3.106484881410628e-05,
+      "loss": 0.395,
+      "step": 149
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.39417443723548595,
+      "learning_rate": 3.091529020389009e-05,
+      "loss": 0.395,
+      "step": 150
+    },
+    {
+      "epoch": 1.9327999999999999,
+      "grad_norm": 0.30496713078562493,
+      "learning_rate": 3.076485717806808e-05,
+      "loss": 0.4011,
+      "step": 151
+    },
+    {
+      "epoch": 1.9456,
+      "grad_norm": 0.3354716453229167,
+      "learning_rate": 3.061356178771564e-05,
+      "loss": 0.3904,
+      "step": 152
+    },
+    {
+      "epoch": 1.9584000000000001,
+      "grad_norm": 0.29146301316840406,
+      "learning_rate": 3.0461416152991555e-05,
+      "loss": 0.4072,
+      "step": 153
+    },
+    {
+      "epoch": 1.9712,
+      "grad_norm": 0.36890582272023975,
+      "learning_rate": 3.0308432462167045e-05,
+      "loss": 0.3957,
+      "step": 154
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 0.3577410409564998,
+      "learning_rate": 3.015462297064936e-05,
+      "loss": 0.4038,
+      "step": 155
+    },
+    {
+      "epoch": 1.9968,
+      "grad_norm": 0.39550066406774714,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 0.3973,
+      "step": 156
+    },
+    {
+      "epoch": 2.0096,
+      "grad_norm": 0.7349169328758873,
+      "learning_rate": 2.98445759369477e-05,
+      "loss": 0.7441,
+      "step": 157
+    },
+    {
+      "epoch": 2.0224,
+      "grad_norm": 0.6046293803655142,
+      "learning_rate": 2.9688363232396056e-05,
+      "loss": 0.3418,
+      "step": 158
+    },
+    {
+      "epoch": 2.0352,
+      "grad_norm": 0.5300709002258949,
+      "learning_rate": 2.9531374400426158e-05,
+      "loss": 0.3572,
+      "step": 159
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 0.5709070692882054,
+      "learning_rate": 2.9373622017294075e-05,
+      "loss": 0.3594,
+      "step": 160
+    },
+    {
+      "epoch": 2.0608,
+      "grad_norm": 0.47703826616970035,
+      "learning_rate": 2.9215118720423375e-05,
+      "loss": 0.3517,
+      "step": 161
+    },
+    {
+      "epoch": 2.0736,
+      "grad_norm": 0.5700563972208256,
+      "learning_rate": 2.9055877207392752e-05,
+      "loss": 0.3587,
+      "step": 162
+    },
+    {
+      "epoch": 2.0864,
+      "grad_norm": 0.4301142046490084,
+      "learning_rate": 2.8895910234918828e-05,
+      "loss": 0.3438,
+      "step": 163
+    },
+    {
+      "epoch": 2.0992,
+      "grad_norm": 0.48344510958605985,
+      "learning_rate": 2.873523061783426e-05,
+      "loss": 0.3712,
+      "step": 164
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 0.4951944617518329,
+      "learning_rate": 2.8573851228061084e-05,
+      "loss": 0.3335,
+      "step": 165
+    },
+    {
+      "epoch": 2.1248,
+      "grad_norm": 0.42829530760033185,
+      "learning_rate": 2.8411784993579633e-05,
+      "loss": 0.3498,
+      "step": 166
+    },
+    {
+      "epoch": 2.1376,
+      "grad_norm": 0.42812407512097167,
+      "learning_rate": 2.8249044897392814e-05,
+      "loss": 0.3491,
+      "step": 167
+    },
+    {
+      "epoch": 2.1504,
+      "grad_norm": 0.4416432206812055,
+      "learning_rate": 2.80856439764861e-05,
+      "loss": 0.3487,
+      "step": 168
+    },
+    {
+      "epoch": 2.1632,
+      "grad_norm": 0.41085619522142347,
+      "learning_rate": 2.792159532078314e-05,
+      "loss": 0.3442,
+      "step": 169
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 0.37556644307089126,
+      "learning_rate": 2.77569120720971e-05,
+      "loss": 0.3428,
+      "step": 170
+    },
+    {
+      "epoch": 2.1888,
+      "grad_norm": 0.4336219125426427,
+      "learning_rate": 2.7591607423077932e-05,
+      "loss": 0.3528,
+      "step": 171
+    },
+    {
+      "epoch": 2.2016,
+      "grad_norm": 0.4763031931102983,
+      "learning_rate": 2.7425694616155474e-05,
+      "loss": 0.3519,
+      "step": 172
+    },
+    {
+      "epoch": 2.2144,
+      "grad_norm": 0.3594586794095501,
+      "learning_rate": 2.7259186942478656e-05,
+      "loss": 0.3425,
+      "step": 173
+    },
+    {
+      "epoch": 2.2272,
+      "grad_norm": 0.37805160822300177,
+      "learning_rate": 2.7092097740850712e-05,
+      "loss": 0.3404,
+      "step": 174
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.40273376972217534,
+      "learning_rate": 2.692444039666066e-05,
+      "loss": 0.3362,
+      "step": 175
+    },
+    {
+      "epoch": 2.2528,
+      "grad_norm": 0.3961502364519684,
+      "learning_rate": 2.6756228340810946e-05,
+      "loss": 0.3503,
+      "step": 176
+    },
+    {
+      "epoch": 2.2656,
+      "grad_norm": 0.3321312422360362,
+      "learning_rate": 2.6587475048641596e-05,
+      "loss": 0.337,
+      "step": 177
+    },
+    {
+      "epoch": 2.2784,
+      "grad_norm": 0.33910243297344955,
+      "learning_rate": 2.6418194038850634e-05,
+      "loss": 0.3406,
+      "step": 178
+    },
+    {
+      "epoch": 2.2912,
+      "grad_norm": 0.3543828311716588,
+      "learning_rate": 2.624839887241115e-05,
+      "loss": 0.3588,
+      "step": 179
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 0.3013610304401655,
+      "learning_rate": 2.607810315148494e-05,
+      "loss": 0.3357,
+      "step": 180
+    },
+    {
+      "epoch": 2.3168,
+      "grad_norm": 0.3132628369316018,
+      "learning_rate": 2.5907320518332827e-05,
+      "loss": 0.3571,
+      "step": 181
+    },
+    {
+      "epoch": 2.3296,
+      "grad_norm": 0.35025212243486903,
+      "learning_rate": 2.5736064654221808e-05,
+      "loss": 0.343,
+      "step": 182
+    },
+    {
+      "epoch": 2.3424,
+      "grad_norm": 0.3111821036731844,
+      "learning_rate": 2.5564349278329056e-05,
+      "loss": 0.3395,
+      "step": 183
+    },
+    {
+      "epoch": 2.3552,
+      "grad_norm": 0.3589431645726322,
+      "learning_rate": 2.539218814664288e-05,
+      "loss": 0.3529,
+      "step": 184
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 0.33750820735433296,
+      "learning_rate": 2.521959505086075e-05,
+      "loss": 0.3526,
+      "step": 185
+    },
+    {
+      "epoch": 2.3808,
+      "grad_norm": 0.2918816520824123,
+      "learning_rate": 2.5046583817284437e-05,
+      "loss": 0.3436,
+      "step": 186
+    },
+    {
+      "epoch": 2.3936,
+      "grad_norm": 0.33830775276255287,
+      "learning_rate": 2.487316830571244e-05,
+      "loss": 0.3501,
+      "step": 187
+    },
+    {
+      "epoch": 2.4064,
+      "grad_norm": 0.33876883590030404,
+      "learning_rate": 2.4699362408329646e-05,
+      "loss": 0.3516,
+      "step": 188
+    },
+    {
+      "epoch": 2.4192,
+      "grad_norm": 0.32437587614050645,
+      "learning_rate": 2.4525180048594452e-05,
+      "loss": 0.3371,
+      "step": 189
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 0.35401779894345015,
+      "learning_rate": 2.435063518012335e-05,
+      "loss": 0.343,
+      "step": 190
+    },
+    {
+      "epoch": 2.4448,
+      "grad_norm": 0.29954972263367513,
+      "learning_rate": 2.4175741785573177e-05,
+      "loss": 0.3518,
+      "step": 191
+    },
+    {
+      "epoch": 2.4576000000000002,
+      "grad_norm": 0.2798705269212463,
+      "learning_rate": 2.4000513875520892e-05,
+      "loss": 0.3554,
+      "step": 192
+    },
+    {
+      "epoch": 2.4704,
+      "grad_norm": 0.31107522550163086,
+      "learning_rate": 2.3824965487341247e-05,
+      "loss": 0.3487,
+      "step": 193
+    },
+    {
+      "epoch": 2.4832,
+      "grad_norm": 0.28916248242348347,
+      "learning_rate": 2.3649110684082258e-05,
+      "loss": 0.3453,
+      "step": 194
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 0.3214965828272813,
+      "learning_rate": 2.3472963553338614e-05,
+      "loss": 0.354,
+      "step": 195
+    },
+    {
+      "epoch": 2.5088,
+      "grad_norm": 0.29667047488503373,
+      "learning_rate": 2.3296538206123134e-05,
+      "loss": 0.3522,
+      "step": 196
+    },
+    {
+      "epoch": 2.5216,
+      "grad_norm": 0.3168468312303013,
+      "learning_rate": 2.311984877573636e-05,
+      "loss": 0.3484,
+      "step": 197
+    },
+    {
+      "epoch": 2.5343999999999998,
+      "grad_norm": 0.2628167160951945,
+      "learning_rate": 2.2942909416634326e-05,
+      "loss": 0.343,
+      "step": 198
+    },
+    {
+      "epoch": 2.5472,
+      "grad_norm": 0.3134801030981865,
+      "learning_rate": 2.2765734303294666e-05,
+      "loss": 0.344,
+      "step": 199
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.29356525193219674,
+      "learning_rate": 2.2588337629081107e-05,
+      "loss": 0.3485,
+      "step": 200
+    },
+    {
+      "epoch": 2.5728,
+      "grad_norm": 0.31620801059556713,
+      "learning_rate": 2.2410733605106462e-05,
+      "loss": 0.3419,
+      "step": 201
+    },
+    {
+      "epoch": 2.5856,
+      "grad_norm": 0.30754565103423764,
+      "learning_rate": 2.2232936459094158e-05,
+      "loss": 0.3646,
+      "step": 202
+    },
+    {
+      "epoch": 2.5984,
+      "grad_norm": 0.29483619255244087,
+      "learning_rate": 2.205496043423849e-05,
+      "loss": 0.3431,
+      "step": 203
+    },
+    {
+      "epoch": 2.6112,
+      "grad_norm": 0.279973189467925,
+      "learning_rate": 2.1876819788063586e-05,
+      "loss": 0.3384,
+      "step": 204
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 0.30539966847736144,
+      "learning_rate": 2.16985287912813e-05,
+      "loss": 0.3468,
+      "step": 205
+    },
+    {
+      "epoch": 2.6368,
+      "grad_norm": 0.2612319409933184,
+      "learning_rate": 2.1520101726647922e-05,
+      "loss": 0.3395,
+      "step": 206
+    },
+    {
+      "epoch": 2.6496,
+      "grad_norm": 0.3319435709328078,
+      "learning_rate": 2.1341552887820048e-05,
+      "loss": 0.3435,
+      "step": 207
+    },
+    {
+      "epoch": 2.6624,
+      "grad_norm": 0.246066694386649,
+      "learning_rate": 2.1162896578209517e-05,
+      "loss": 0.3399,
+      "step": 208
+    },
+    {
+      "epoch": 2.6752000000000002,
+      "grad_norm": 0.33418731079709435,
+      "learning_rate": 2.0984147109837564e-05,
+      "loss": 0.3378,
+      "step": 209
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.27413744396861145,
+      "learning_rate": 2.0805318802188307e-05,
+      "loss": 0.3474,
+      "step": 210
+    },
+    {
+      "epoch": 2.7008,
+      "grad_norm": 0.3005772923867193,
+      "learning_rate": 2.0626425981061608e-05,
+      "loss": 0.3492,
+      "step": 211
+    },
+    {
+      "epoch": 2.7136,
+      "grad_norm": 0.31425628645861947,
+      "learning_rate": 2.0447482977425465e-05,
+      "loss": 0.3433,
+      "step": 212
+    },
+    {
+      "epoch": 2.7264,
+      "grad_norm": 0.27853790436333337,
+      "learning_rate": 2.0268504126267952e-05,
+      "loss": 0.35,
+      "step": 213
+    },
+    {
+      "epoch": 2.7392,
+      "grad_norm": 0.2899027310013206,
+      "learning_rate": 2.008950376544887e-05,
+      "loss": 0.334,
+      "step": 214
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 0.25891063952509713,
+      "learning_rate": 1.9910496234551132e-05,
+      "loss": 0.3463,
+      "step": 215
+    },
+    {
+      "epoch": 2.7648,
+      "grad_norm": 0.2831126686014719,
+      "learning_rate": 1.9731495873732055e-05,
+      "loss": 0.3462,
+      "step": 216
+    },
+    {
+      "epoch": 2.7776,
+      "grad_norm": 0.2615915415780373,
+      "learning_rate": 1.9552517022574542e-05,
+      "loss": 0.3427,
+      "step": 217
+    },
+    {
+      "epoch": 2.7904,
+      "grad_norm": 0.29633791067566456,
+      "learning_rate": 1.93735740189384e-05,
+      "loss": 0.333,
+      "step": 218
+    },
+    {
+      "epoch": 2.8032,
+      "grad_norm": 0.2320916204376524,
+      "learning_rate": 1.9194681197811703e-05,
+      "loss": 0.3437,
+      "step": 219
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 0.2840136608356192,
+      "learning_rate": 1.901585289016244e-05,
+      "loss": 0.3477,
+      "step": 220
+    },
+    {
+      "epoch": 2.8288,
+      "grad_norm": 0.22496409809861406,
+      "learning_rate": 1.8837103421790486e-05,
+      "loss": 0.3529,
+      "step": 221
+    },
+    {
+      "epoch": 2.8416,
+      "grad_norm": 0.26690860897068885,
+      "learning_rate": 1.8658447112179952e-05,
+      "loss": 0.3454,
+      "step": 222
+    },
+    {
+      "epoch": 2.8544,
+      "grad_norm": 0.23291074951735677,
+      "learning_rate": 1.8479898273352084e-05,
+      "loss": 0.3555,
+      "step": 223
+    },
+    {
+      "epoch": 2.8672,
+      "grad_norm": 0.27838093031280436,
+      "learning_rate": 1.83014712087187e-05,
+      "loss": 0.3537,
+      "step": 224
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.22366982525693918,
+      "learning_rate": 1.8123180211936417e-05,
+      "loss": 0.3401,
+      "step": 225
+    },
+    {
+      "epoch": 2.8928000000000003,
+      "grad_norm": 0.26481465533494425,
+      "learning_rate": 1.794503956576152e-05,
+      "loss": 0.3454,
+      "step": 226
+    },
+    {
+      "epoch": 2.9055999999999997,
+      "grad_norm": 0.2205166562233389,
+      "learning_rate": 1.776706354090585e-05,
+      "loss": 0.3435,
+      "step": 227
+    },
+    {
+      "epoch": 2.9184,
+      "grad_norm": 0.24808662062379722,
+      "learning_rate": 1.758926639489354e-05,
+      "loss": 0.3509,
+      "step": 228
+    },
+    {
+      "epoch": 2.9312,
+      "grad_norm": 0.22564854058897144,
+      "learning_rate": 1.7411662370918893e-05,
+      "loss": 0.35,
+      "step": 229
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 0.22141880139305434,
+      "learning_rate": 1.7234265696705344e-05,
+      "loss": 0.3372,
+      "step": 230
+    },
+    {
+      "epoch": 2.9568,
+      "grad_norm": 0.22509395086678416,
+      "learning_rate": 1.7057090583365678e-05,
+      "loss": 0.3584,
+      "step": 231
+    },
+    {
+      "epoch": 2.9696,
+      "grad_norm": 0.22404764840393865,
+      "learning_rate": 1.6880151224263646e-05,
+      "loss": 0.3333,
+      "step": 232
+    },
+    {
+      "epoch": 2.9824,
+      "grad_norm": 0.21687844151176744,
+      "learning_rate": 1.6703461793876876e-05,
+      "loss": 0.3467,
+      "step": 233
+    },
+    {
+      "epoch": 2.9952,
+      "grad_norm": 0.21174299075960568,
+      "learning_rate": 1.6527036446661396e-05,
+      "loss": 0.3368,
+      "step": 234
+    },
+    {
+      "epoch": 3.008,
+      "grad_norm": 0.6150450603222863,
+      "learning_rate": 1.635088931591775e-05,
+      "loss": 0.6173,
+      "step": 235
+    },
+    {
+      "epoch": 3.0208,
+      "grad_norm": 0.3784125802583993,
+      "learning_rate": 1.6175034512658753e-05,
+      "loss": 0.2998,
+      "step": 236
+    },
+    {
+      "epoch": 3.0336,
+      "grad_norm": 0.37644755186990325,
+      "learning_rate": 1.5999486124479115e-05,
+      "loss": 0.285,
+      "step": 237
+    },
+    {
+      "epoch": 3.0464,
+      "grad_norm": 0.42810815012184483,
+      "learning_rate": 1.5824258214426833e-05,
+      "loss": 0.2869,
+      "step": 238
+    },
+    {
+      "epoch": 3.0592,
+      "grad_norm": 0.39695631055306285,
+      "learning_rate": 1.5649364819876655e-05,
+      "loss": 0.2814,
+      "step": 239
+    },
+    {
+      "epoch": 3.072,
+      "grad_norm": 0.407800624511283,
+      "learning_rate": 1.547481995140556e-05,
+      "loss": 0.2895,
+      "step": 240
+    },
+    {
+      "epoch": 3.0848,
+      "grad_norm": 0.3528539040753433,
+      "learning_rate": 1.5300637591670357e-05,
+      "loss": 0.288,
+      "step": 241
+    },
+    {
+      "epoch": 3.0976,
+      "grad_norm": 0.40332018366352024,
+      "learning_rate": 1.5126831694287564e-05,
+      "loss": 0.2902,
+      "step": 242
+    },
+    {
+      "epoch": 3.1104,
+      "grad_norm": 0.3135329182589025,
+      "learning_rate": 1.4953416182715566e-05,
+      "loss": 0.3019,
+      "step": 243
+    },
+    {
+      "epoch": 3.1232,
+      "grad_norm": 0.35842180457067746,
+      "learning_rate": 1.478040494913926e-05,
+      "loss": 0.2876,
+      "step": 244
+    },
+    {
+      "epoch": 3.136,
+      "grad_norm": 0.35384306003722515,
+      "learning_rate": 1.460781185335713e-05,
+      "loss": 0.2887,
+      "step": 245
+    },
+    {
+      "epoch": 3.1488,
+      "grad_norm": 0.29374453185741123,
+      "learning_rate": 1.443565072167095e-05,
+      "loss": 0.2982,
+      "step": 246
+    },
+    {
+      "epoch": 3.1616,
+      "grad_norm": 0.35626964049595355,
+      "learning_rate": 1.4263935345778202e-05,
+      "loss": 0.2844,
+      "step": 247
+    },
+    {
+      "epoch": 3.1744,
+      "grad_norm": 0.2954432844100599,
+      "learning_rate": 1.409267948166718e-05,
+      "loss": 0.2868,
+      "step": 248
+    },
+    {
+      "epoch": 3.1872,
+      "grad_norm": 0.24565886441998758,
+      "learning_rate": 1.3921896848515064e-05,
+      "loss": 0.2962,
+      "step": 249
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.30413912944332966,
+      "learning_rate": 1.3751601127588849e-05,
+      "loss": 0.2902,
+      "step": 250
+    },
+    {
+      "epoch": 3.2128,
+      "grad_norm": 0.2628578467079941,
+      "learning_rate": 1.3581805961149371e-05,
+      "loss": 0.2883,
+      "step": 251
+    },
+    {
+      "epoch": 3.2256,
+      "grad_norm": 0.24592227236325298,
+      "learning_rate": 1.341252495135841e-05,
+      "loss": 0.2784,
+      "step": 252
+    },
+    {
+      "epoch": 3.2384,
+      "grad_norm": 0.39231252740273126,
+      "learning_rate": 1.324377165918906e-05,
+      "loss": 0.3056,
+      "step": 253
+    },
+    {
+      "epoch": 3.2512,
+      "grad_norm": 0.26432320712953644,
+      "learning_rate": 1.3075559603339354e-05,
+      "loss": 0.2883,
+      "step": 254
+    },
+    {
+      "epoch": 3.2640000000000002,
+      "grad_norm": 0.27201318398207686,
+      "learning_rate": 1.2907902259149287e-05,
+      "loss": 0.2987,
+      "step": 255
+    },
+    {
+      "epoch": 3.2768,
+      "grad_norm": 0.2654527401113404,
+      "learning_rate": 1.274081305752135e-05,
+      "loss": 0.2863,
+      "step": 256
+    },
+    {
+      "epoch": 3.2896,
+      "grad_norm": 0.22555821058752512,
+      "learning_rate": 1.2574305383844528e-05,
+      "loss": 0.2884,
+      "step": 257
+    },
+    {
+      "epoch": 3.3024,
+      "grad_norm": 0.26371743401462283,
+      "learning_rate": 1.2408392576922075e-05,
+      "loss": 0.2923,
+      "step": 258
+    },
+    {
+      "epoch": 3.3152,
+      "grad_norm": 0.2406604012805146,
+      "learning_rate": 1.2243087927902905e-05,
+      "loss": 0.2831,
+      "step": 259
+    },
+    {
+      "epoch": 3.328,
+      "grad_norm": 0.23433570716517896,
+      "learning_rate": 1.2078404679216864e-05,
+      "loss": 0.2833,
+      "step": 260
+    },
+    {
+      "epoch": 3.3407999999999998,
+      "grad_norm": 0.24151607667532654,
+      "learning_rate": 1.1914356023513904e-05,
+      "loss": 0.2914,
+      "step": 261
+    },
+    {
+      "epoch": 3.3536,
+      "grad_norm": 0.23587921431969447,
+      "learning_rate": 1.1750955102607193e-05,
+      "loss": 0.279,
+      "step": 262
+    },
+    {
+      "epoch": 3.3664,
+      "grad_norm": 0.22189686154089822,
+      "learning_rate": 1.1588215006420374e-05,
+      "loss": 0.2856,
+      "step": 263
+    },
+    {
+      "epoch": 3.3792,
+      "grad_norm": 0.23114907098789855,
+      "learning_rate": 1.1426148771938915e-05,
+      "loss": 0.291,
+      "step": 264
+    },
+    {
+      "epoch": 3.392,
+      "grad_norm": 0.21861517705586683,
+      "learning_rate": 1.1264769382165748e-05,
+      "loss": 0.2879,
+      "step": 265
+    },
+    {
+      "epoch": 3.4048,
+      "grad_norm": 0.23662761334287458,
+      "learning_rate": 1.110408976508118e-05,
+      "loss": 0.2972,
+      "step": 266
+    },
+    {
+      "epoch": 3.4176,
+      "grad_norm": 0.22191457961794891,
+      "learning_rate": 1.094412279260726e-05,
+      "loss": 0.2978,
+      "step": 267
+    },
+    {
+      "epoch": 3.4304,
+      "grad_norm": 0.21110695974040253,
+      "learning_rate": 1.0784881279576635e-05,
+      "loss": 0.2891,
+      "step": 268
+    },
+    {
+      "epoch": 3.4432,
+      "grad_norm": 0.2197283565149141,
+      "learning_rate": 1.0626377982705929e-05,
+      "loss": 0.2831,
+      "step": 269
+    },
+    {
+      "epoch": 3.456,
+      "grad_norm": 0.22098652256256562,
+      "learning_rate": 1.0468625599573842e-05,
+      "loss": 0.2873,
+      "step": 270
+    },
+    {
+      "epoch": 3.4688,
+      "grad_norm": 0.23158208154885102,
+      "learning_rate": 1.0311636767603952e-05,
+      "loss": 0.3043,
+      "step": 271
+    },
+    {
+      "epoch": 3.4816,
+      "grad_norm": 0.2112075482755885,
+      "learning_rate": 1.0155424063052306e-05,
+      "loss": 0.2838,
+      "step": 272
+    },
+    {
+      "epoch": 3.4944,
+      "grad_norm": 0.22213455458504658,
+      "learning_rate": 1.0000000000000006e-05,
+      "loss": 0.3,
+      "step": 273
+    },
+    {
+      "epoch": 3.5072,
+      "grad_norm": 0.22018045919062074,
+      "learning_rate": 9.84537702935065e-06,
+      "loss": 0.2807,
+      "step": 274
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 0.2417462702940174,
+      "learning_rate": 9.691567537832964e-06,
+      "loss": 0.2931,
+      "step": 275
+    },
+    {
+      "epoch": 3.5328,
+      "grad_norm": 0.22048108077786358,
+      "learning_rate": 9.538583847008452e-06,
+      "loss": 0.291,
+      "step": 276
+    },
+    {
+      "epoch": 3.5456,
+      "grad_norm": 0.23035719282845266,
+      "learning_rate": 9.386438212284372e-06,
+      "loss": 0.2977,
+      "step": 277
+    },
+    {
+      "epoch": 3.5584,
+      "grad_norm": 0.21246686232470038,
+      "learning_rate": 9.235142821931928e-06,
+      "loss": 0.2864,
+      "step": 278
+    },
+    {
+      "epoch": 3.5712,
+      "grad_norm": 0.24063303263964456,
+      "learning_rate": 9.084709796109907e-06,
+      "loss": 0.2857,
+      "step": 279
+    },
+    {
+      "epoch": 3.584,
+      "grad_norm": 0.21471397475877052,
+      "learning_rate": 8.93515118589373e-06,
+      "loss": 0.2949,
+      "step": 280
+    },
+    {
+      "epoch": 3.5968,
+      "grad_norm": 0.23719605603843386,
+      "learning_rate": 8.786478972310023e-06,
+      "loss": 0.2876,
+      "step": 281
+    },
+    {
+      "epoch": 3.6096,
+      "grad_norm": 0.20227163289178307,
+      "learning_rate": 8.638705065376887e-06,
+      "loss": 0.2941,
+      "step": 282
+    },
+    {
+      "epoch": 3.6224,
+      "grad_norm": 0.2029522241904643,
+      "learning_rate": 8.491841303149728e-06,
+      "loss": 0.2893,
+      "step": 283
+    },
+    {
+      "epoch": 3.6352,
+      "grad_norm": 0.20659863617659016,
+      "learning_rate": 8.345899450772975e-06,
+      "loss": 0.2939,
+      "step": 284
+    },
+    {
+      "epoch": 3.648,
+      "grad_norm": 0.19314348871560064,
+      "learning_rate": 8.200891199537549e-06,
+      "loss": 0.2936,
+      "step": 285
+    },
+    {
+      "epoch": 3.6608,
+      "grad_norm": 0.19320849130992723,
+      "learning_rate": 8.056828165944282e-06,
+      "loss": 0.2857,
+      "step": 286
+    },
+    {
+      "epoch": 3.6736,
+      "grad_norm": 0.19451078802507166,
+      "learning_rate": 7.913721890773354e-06,
+      "loss": 0.2922,
+      "step": 287
+    },
+    {
+      "epoch": 3.6864,
+      "grad_norm": 0.20033248539991305,
+      "learning_rate": 7.771583838159756e-06,
+      "loss": 0.307,
+      "step": 288
+    },
+    {
+      "epoch": 3.6992000000000003,
+      "grad_norm": 0.19777389457136854,
+      "learning_rate": 7.630425394674903e-06,
+      "loss": 0.2915,
+      "step": 289
+    },
+    {
+      "epoch": 3.7119999999999997,
+      "grad_norm": 0.19732963940375622,
+      "learning_rate": 7.49025786841445e-06,
+      "loss": 0.2895,
+      "step": 290
+    },
+    {
+      "epoch": 3.7248,
+      "grad_norm": 0.22997188995718654,
+      "learning_rate": 7.3510924880924575e-06,
+      "loss": 0.2902,
+      "step": 291
+    },
+    {
+      "epoch": 3.7376,
+      "grad_norm": 0.20680822025584822,
+      "learning_rate": 7.212940402141808e-06,
+      "loss": 0.2858,
+      "step": 292
+    },
+    {
+      "epoch": 3.7504,
+      "grad_norm": 0.18972075169703784,
+      "learning_rate": 7.075812677821145e-06,
+      "loss": 0.293,
+      "step": 293
+    },
+    {
+      "epoch": 3.7632,
+      "grad_norm": 0.20300947245245715,
+      "learning_rate": 6.939720300328303e-06,
+      "loss": 0.295,
+      "step": 294
+    },
+    {
+      "epoch": 3.776,
+      "grad_norm": 0.21515613409400816,
+      "learning_rate": 6.8046741719202385e-06,
+      "loss": 0.2916,
+      "step": 295
+    },
+    {
+      "epoch": 3.7888,
+      "grad_norm": 0.19565729167422963,
+      "learning_rate": 6.67068511103971e-06,
+      "loss": 0.3008,
+      "step": 296
+    },
+    {
+      "epoch": 3.8016,
+      "grad_norm": 0.209801546401168,
+      "learning_rate": 6.537763851448593e-06,
+      "loss": 0.3005,
+      "step": 297
+    },
+    {
+      "epoch": 3.8144,
+      "grad_norm": 0.2026176152898242,
+      "learning_rate": 6.4059210413680175e-06,
+      "loss": 0.2851,
+      "step": 298
+    },
+    {
+      "epoch": 3.8272,
+      "grad_norm": 0.19719964410127247,
+      "learning_rate": 6.275167242625331e-06,
+      "loss": 0.2834,
+      "step": 299
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.19397830042984118,
+      "learning_rate": 6.145512929808013e-06,
+      "loss": 0.3027,
+      "step": 300
+    },
+    {
+      "epoch": 3.8528000000000002,
+      "grad_norm": 0.1875564799404977,
+      "learning_rate": 6.016968489424572e-06,
+      "loss": 0.2955,
+      "step": 301
+    },
+    {
+      "epoch": 3.8656,
+      "grad_norm": 0.19388689722800215,
+      "learning_rate": 5.889544219072465e-06,
+      "loss": 0.2939,
+      "step": 302
+    },
+    {
+      "epoch": 3.8784,
+      "grad_norm": 0.19368635353665362,
+      "learning_rate": 5.7632503266131925e-06,
+      "loss": 0.298,
+      "step": 303
+    },
+    {
+      "epoch": 3.8912,
+      "grad_norm": 0.17780779668749636,
+      "learning_rate": 5.638096929354522e-06,
+      "loss": 0.2807,
+      "step": 304
+    },
+    {
+      "epoch": 3.904,
+      "grad_norm": 0.1815219482071306,
+      "learning_rate": 5.514094053240035e-06,
+      "loss": 0.2962,
+      "step": 305
+    },
+    {
+      "epoch": 3.9168,
+      "grad_norm": 0.19525539459154728,
+      "learning_rate": 5.39125163204594e-06,
+      "loss": 0.282,
+      "step": 306
+    },
+    {
+      "epoch": 3.9295999999999998,
+      "grad_norm": 0.19530256131921614,
+      "learning_rate": 5.269579506585259e-06,
+      "loss": 0.2933,
+      "step": 307
+    },
+    {
+      "epoch": 3.9424,
+      "grad_norm": 0.1869644439134244,
+      "learning_rate": 5.149087423919541e-06,
+      "loss": 0.2986,
+      "step": 308
+    },
+    {
+      "epoch": 3.9552,
+      "grad_norm": 0.18476267314312086,
+      "learning_rate": 5.029785036577976e-06,
+      "loss": 0.282,
+      "step": 309
+    },
+    {
+      "epoch": 3.968,
+      "grad_norm": 0.186038858302677,
+      "learning_rate": 4.911681901784198e-06,
+      "loss": 0.3047,
+      "step": 310
+    },
+    {
+      "epoch": 3.9808,
+      "grad_norm": 0.1842829435665899,
+      "learning_rate": 4.794787480690597e-06,
+      "loss": 0.2915,
+      "step": 311
+    },
+    {
+      "epoch": 3.9936,
+      "grad_norm": 0.18612910036402916,
+      "learning_rate": 4.679111137620442e-06,
+      "loss": 0.2952,
+      "step": 312
+    },
+    {
+      "epoch": 4.0064,
+      "grad_norm": 0.5425186791080541,
+      "learning_rate": 4.5646621393177e-06,
+      "loss": 0.5592,
+      "step": 313
+    },
+    {
+      "epoch": 4.0192,
+      "grad_norm": 0.30049082924056936,
+      "learning_rate": 4.451449654204685e-06,
+      "loss": 0.2599,
+      "step": 314
+    },
+    {
+      "epoch": 4.032,
+      "grad_norm": 0.2554428843415845,
+      "learning_rate": 4.339482751647557e-06,
+      "loss": 0.2471,
+      "step": 315
+    },
+    {
+      "epoch": 4.0448,
+      "grad_norm": 0.1923843263970924,
+      "learning_rate": 4.228770401229824e-06,
+      "loss": 0.2485,
+      "step": 316
+    },
+    {
+      "epoch": 4.0576,
+      "grad_norm": 0.2303955821994753,
+      "learning_rate": 4.119321472033779e-06,
+      "loss": 0.2555,
+      "step": 317
+    },
+    {
+      "epoch": 4.0704,
+      "grad_norm": 0.29450051536649247,
+      "learning_rate": 4.011144731929981e-06,
+      "loss": 0.2566,
+      "step": 318
+    },
+    {
+      "epoch": 4.0832,
+      "grad_norm": 0.27634688592334744,
+      "learning_rate": 3.904248846874894e-06,
+      "loss": 0.2538,
+      "step": 319
+    },
+    {
+      "epoch": 4.096,
+      "grad_norm": 0.2618858928724669,
+      "learning_rate": 3.7986423802166705e-06,
+      "loss": 0.2675,
+      "step": 320
+    },
+    {
+      "epoch": 4.1088,
+      "grad_norm": 0.21006828185575305,
+      "learning_rate": 3.694333792009115e-06,
+      "loss": 0.2473,
+      "step": 321
+    },
+    {
+      "epoch": 4.1216,
+      "grad_norm": 0.23516108328640709,
+      "learning_rate": 3.5913314383339937e-06,
+      "loss": 0.2678,
+      "step": 322
+    },
+    {
+      "epoch": 4.1344,
+      "grad_norm": 0.2390848755564751,
+      "learning_rate": 3.4896435706316e-06,
+      "loss": 0.2601,
+      "step": 323
+    },
+    {
+      "epoch": 4.1472,
+      "grad_norm": 0.2420604905634408,
+      "learning_rate": 3.3892783350397675e-06,
+      "loss": 0.271,
+      "step": 324
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.2049093813322,
+      "learning_rate": 3.290243771741275e-06,
+      "loss": 0.2432,
+      "step": 325
+    },
+    {
+      "epoch": 4.1728,
+      "grad_norm": 0.198261804944073,
+      "learning_rate": 3.1925478143197418e-06,
+      "loss": 0.2403,
+      "step": 326
+    },
+    {
+      "epoch": 4.1856,
+      "grad_norm": 0.21009004259058608,
+      "learning_rate": 3.0961982891241083e-06,
+      "loss": 0.2656,
+      "step": 327
+    },
+    {
+      "epoch": 4.1984,
+      "grad_norm": 0.21623703106695663,
+      "learning_rate": 3.001202914641628e-06,
+      "loss": 0.2596,
+      "step": 328
+    },
+    {
+      "epoch": 4.2112,
+      "grad_norm": 0.21775149493124554,
+      "learning_rate": 2.907569300879596e-06,
+      "loss": 0.2452,
+      "step": 329
+    },
+    {
+      "epoch": 4.224,
+      "grad_norm": 0.2119765421737725,
+      "learning_rate": 2.815304948755664e-06,
+      "loss": 0.257,
+      "step": 330
+    },
+    {
+      "epoch": 4.2368,
+      "grad_norm": 0.21358534332250806,
+      "learning_rate": 2.7244172494969978e-06,
+      "loss": 0.2534,
+      "step": 331
+    },
+    {
+      "epoch": 4.2496,
+      "grad_norm": 0.19839201162605746,
+      "learning_rate": 2.6349134840481294e-06,
+      "loss": 0.2549,
+      "step": 332
+    },
+    {
+      "epoch": 4.2624,
+      "grad_norm": 0.1945973248614231,
+      "learning_rate": 2.546800822487714e-06,
+      "loss": 0.255,
+      "step": 333
+    },
+    {
+      "epoch": 4.2752,
+      "grad_norm": 0.1887154275395545,
+      "learning_rate": 2.4600863234541338e-06,
+      "loss": 0.2557,
+      "step": 334
+    },
+    {
+      "epoch": 4.288,
+      "grad_norm": 0.19410130477021506,
+      "learning_rate": 2.374776933580025e-06,
+      "loss": 0.263,
+      "step": 335
+    },
+    {
+      "epoch": 4.3008,
+      "grad_norm": 0.18880115274605572,
+      "learning_rate": 2.2908794869358044e-06,
+      "loss": 0.2527,
+      "step": 336
+    },
+    {
+      "epoch": 4.3136,
+      "grad_norm": 0.18466541122137084,
+      "learning_rate": 2.2084007044821764e-06,
+      "loss": 0.2514,
+      "step": 337
+    },
+    {
+      "epoch": 4.3264,
+      "grad_norm": 0.19515976219772285,
+      "learning_rate": 2.127347193531757e-06,
+      "loss": 0.2555,
+      "step": 338
+    },
+    {
+      "epoch": 4.3392,
+      "grad_norm": 0.18061046656004798,
+      "learning_rate": 2.0477254472197237e-06,
+      "loss": 0.2556,
+      "step": 339
+    },
+    {
+      "epoch": 4.352,
+      "grad_norm": 0.17892073515949666,
+      "learning_rate": 1.96954184398368e-06,
+      "loss": 0.2553,
+      "step": 340
+    },
+    {
+      "epoch": 4.3648,
+      "grad_norm": 0.1764514136188326,
+      "learning_rate": 1.8928026470526917e-06,
+      "loss": 0.2547,
+      "step": 341
+    },
+    {
+      "epoch": 4.3776,
+      "grad_norm": 0.1802666046912532,
+      "learning_rate": 1.817514003945524e-06,
+      "loss": 0.2531,
+      "step": 342
+    },
+    {
+      "epoch": 4.3904,
+      "grad_norm": 0.18250132986956513,
+      "learning_rate": 1.743681945978184e-06,
+      "loss": 0.2561,
+      "step": 343
+    },
+    {
+      "epoch": 4.4032,
+      "grad_norm": 0.1795018924116456,
+      "learning_rate": 1.6713123877807413e-06,
+      "loss": 0.2576,
+      "step": 344
+    },
+    {
+      "epoch": 4.416,
+      "grad_norm": 0.1738171940686021,
+      "learning_rate": 1.6004111268235156e-06,
+      "loss": 0.2536,
+      "step": 345
+    },
+    {
+      "epoch": 4.4288,
+      "grad_norm": 0.1792236057416642,
+      "learning_rate": 1.5309838429526714e-06,
+      "loss": 0.2537,
+      "step": 346
+    },
+    {
+      "epoch": 4.4416,
+      "grad_norm": 0.18091177528694136,
+      "learning_rate": 1.4630360979351644e-06,
+      "loss": 0.2594,
+      "step": 347
+    },
+    {
+      "epoch": 4.4544,
+      "grad_norm": 0.1764339933610419,
+      "learning_rate": 1.396573335013236e-06,
+      "loss": 0.2633,
+      "step": 348
+    },
+    {
+      "epoch": 4.4672,
+      "grad_norm": 0.17334987236682337,
+      "learning_rate": 1.3316008784683265e-06,
+      "loss": 0.2477,
+      "step": 349
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.16965402878049402,
+      "learning_rate": 1.2681239331945695e-06,
+      "loss": 0.2573,
+      "step": 350
+    },
+    {
+      "epoch": 4.4928,
+      "grad_norm": 0.1823167688036634,
+      "learning_rate": 1.2061475842818337e-06,
+      "loss": 0.2587,
+      "step": 351
+    },
+    {
+      "epoch": 4.5056,
+      "grad_norm": 0.17245193009132279,
+      "learning_rate": 1.1456767966083393e-06,
+      "loss": 0.2565,
+      "step": 352
+    },
+    {
+      "epoch": 4.5184,
+      "grad_norm": 0.174418834558664,
+      "learning_rate": 1.086716414442952e-06,
+      "loss": 0.2529,
+      "step": 353
+    },
+    {
+      "epoch": 4.5312,
+      "grad_norm": 0.17058796610147675,
+      "learning_rate": 1.0292711610570904e-06,
+      "loss": 0.2508,
+      "step": 354
+    },
+    {
+      "epoch": 4.5440000000000005,
+      "grad_norm": 0.18286868324686983,
+      "learning_rate": 9.733456383463658e-07,
+      "loss": 0.2667,
+      "step": 355
+    },
+    {
+      "epoch": 4.5568,
+      "grad_norm": 0.17525510431188923,
+      "learning_rate": 9.189443264619102e-07,
+      "loss": 0.2542,
+      "step": 356
+    },
+    {
+      "epoch": 4.5696,
+      "grad_norm": 0.1705345315904947,
+      "learning_rate": 8.660715834514977e-07,
+      "loss": 0.2434,
+      "step": 357
+    },
+    {
+      "epoch": 4.5824,
+      "grad_norm": 0.17467780152031645,
+      "learning_rate": 8.147316449103959e-07,
+      "loss": 0.2521,
+      "step": 358
+    },
+    {
+      "epoch": 4.5952,
+      "grad_norm": 0.17836783075235838,
+      "learning_rate": 7.649286236420806e-07,
+      "loss": 0.2575,
+      "step": 359
+    },
+    {
+      "epoch": 4.608,
+      "grad_norm": 0.17399952645070788,
+      "learning_rate": 7.166665093287539e-07,
+      "loss": 0.2559,
+      "step": 360
+    },
+    {
+      "epoch": 4.6208,
+      "grad_norm": 0.1744210723358522,
+      "learning_rate": 6.69949168211721e-07,
+      "loss": 0.2502,
+      "step": 361
+    },
+    {
+      "epoch": 4.6336,
+      "grad_norm": 0.17876183454473582,
+      "learning_rate": 6.247803427816945e-07,
+      "loss": 0.2539,
+      "step": 362
+    },
+    {
+      "epoch": 4.6464,
+      "grad_norm": 0.17144082771934835,
+      "learning_rate": 5.811636514789598e-07,
+      "loss": 0.2566,
+      "step": 363
+    },
+    {
+      "epoch": 4.6592,
+      "grad_norm": 0.17549887650819762,
+      "learning_rate": 5.391025884035239e-07,
+      "loss": 0.2614,
+      "step": 364
+    },
+    {
+      "epoch": 4.672,
+      "grad_norm": 0.175646760823254,
+      "learning_rate": 4.986005230351954e-07,
+      "loss": 0.2679,
+      "step": 365
+    },
+    {
+      "epoch": 4.6848,
+      "grad_norm": 0.16895723654477565,
+      "learning_rate": 4.5966069996365993e-07,
+      "loss": 0.2461,
+      "step": 366
+    },
+    {
+      "epoch": 4.6975999999999996,
+      "grad_norm": 0.16584727678036332,
+      "learning_rate": 4.22286238628562e-07,
+      "loss": 0.2429,
+      "step": 367
+    },
+    {
+      "epoch": 4.7104,
+      "grad_norm": 0.1671458193509566,
+      "learning_rate": 3.8648013306960664e-07,
+      "loss": 0.2544,
+      "step": 368
+    },
+    {
+      "epoch": 4.7232,
+      "grad_norm": 0.17185835388608134,
+      "learning_rate": 3.522452516867048e-07,
+      "loss": 0.2457,
+      "step": 369
+    },
+    {
+      "epoch": 4.736,
+      "grad_norm": 0.17178860611872154,
+      "learning_rate": 3.1958433701019697e-07,
+      "loss": 0.2571,
+      "step": 370
+    },
+    {
+      "epoch": 4.7488,
+      "grad_norm": 0.1656781502826062,
+      "learning_rate": 2.8850000548115155e-07,
+      "loss": 0.2494,
+      "step": 371
+    },
+    {
+      "epoch": 4.7616,
+      "grad_norm": 0.170930945233252,
+      "learning_rate": 2.5899474724174313e-07,
+      "loss": 0.2634,
+      "step": 372
+    },
+    {
+      "epoch": 4.7744,
+      "grad_norm": 0.16863449516523757,
+      "learning_rate": 2.3107092593579905e-07,
+      "loss": 0.2594,
+      "step": 373
+    },
+    {
+      "epoch": 4.7872,
+      "grad_norm": 0.1699635285971226,
+      "learning_rate": 2.0473077851942858e-07,
+      "loss": 0.2586,
+      "step": 374
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.17115901097443323,
+      "learning_rate": 1.799764150818306e-07,
+      "loss": 0.2513,
+      "step": 375
+    },
+    {
+      "epoch": 4.8128,
+      "grad_norm": 0.17265782620682332,
+      "learning_rate": 1.5680981867625566e-07,
+      "loss": 0.2575,
+      "step": 376
+    },
+    {
+      "epoch": 4.8256,
+      "grad_norm": 0.17734569800112507,
+      "learning_rate": 1.3523284516113955e-07,
+      "loss": 0.265,
+      "step": 377
+    },
+    {
+      "epoch": 4.8384,
+      "grad_norm": 0.16358522350699511,
+      "learning_rate": 1.1524722305144231e-07,
+      "loss": 0.2446,
+      "step": 378
+    },
+    {
+      "epoch": 4.8512,
+      "grad_norm": 0.17213123398860586,
+      "learning_rate": 9.685455338016347e-08,
+      "loss": 0.2642,
+      "step": 379
+    },
+    {
+      "epoch": 4.864,
+      "grad_norm": 0.17307604097783721,
+      "learning_rate": 8.005630957010014e-08,
+      "loss": 0.2646,
+      "step": 380
+    },
+    {
+      "epoch": 4.8768,
+      "grad_norm": 0.1650808423714322,
+      "learning_rate": 6.485383731580142e-08,
+      "loss": 0.2484,
+      "step": 381
+    },
+    {
+      "epoch": 4.8896,
+      "grad_norm": 0.16890869460039773,
+      "learning_rate": 5.1248354475768034e-08,
+      "loss": 0.2519,
+      "step": 382
+    },
+    {
+      "epoch": 4.9024,
+      "grad_norm": 0.16746724001296415,
+      "learning_rate": 3.924095097489922e-08,
+      "loss": 0.2581,
+      "step": 383
+    },
+    {
+      "epoch": 4.9152000000000005,
+      "grad_norm": 0.166676688938483,
+      "learning_rate": 2.8832588717164766e-08,
+      "loss": 0.2542,
+      "step": 384
+    },
+    {
+      "epoch": 4.928,
+      "grad_norm": 0.17151773107522686,
+      "learning_rate": 2.0024101508555604e-08,
+      "loss": 0.2498,
+      "step": 385
+    },
+    {
+      "epoch": 4.9408,
+      "grad_norm": 0.16347069665080277,
+      "learning_rate": 1.281619499029274e-08,
+      "loss": 0.2466,
+      "step": 386
+    },
+    {
+      "epoch": 4.9536,
+      "grad_norm": 0.1659590845712874,
+      "learning_rate": 7.209446582292501e-09,
+      "loss": 0.252,
+      "step": 387
+    },
+    {
+      "epoch": 4.9664,
+      "grad_norm": 0.17328298637256578,
+      "learning_rate": 3.2043054369057523e-09,
+      "loss": 0.2619,
+      "step": 388
+    },
+    {
+      "epoch": 4.9792,
+      "grad_norm": 0.1646526460547952,
+      "learning_rate": 8.010924029533406e-10,
+      "loss": 0.251,
+      "step": 389
+    },
+    {
+      "epoch": 4.992,
+      "grad_norm": 0.16843224591728478,
+      "learning_rate": 0.0,
+      "loss": 0.2486,
+      "step": 390
+    },
+    {
+      "epoch": 4.992,
+      "step": 390,
+      "total_flos": 2.045882781443031e+18,
+      "train_loss": 0.3715052679945261,
+      "train_runtime": 59669.4193,
+      "train_samples_per_second": 0.838,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 390,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.045882781443031e+18,
+  "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:aca2d9acdae80b69f76e5a69a3143c42233f5e15d43b380f58ddb2b4e566f9e7
+size 7288