End of training

.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 +1,58 @@
+---
+base_model: Qwen/Qwen3-8B-Base
+library_name: transformers
+model_name: inter-play-sim-assistant-sft-qwen3-8B
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for inter-play-sim-assistant-sft-qwen3-8B
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B-Base](https://huggingface.co/Qwen/Qwen3-8B-Base).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Sim4Rec/inter-play-sim-assistant-sft-qwen3-8B", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jerome-ramos-20/huggingface/runs/uiam4kxx) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.14.0
+- Transformers: 4.51.3
+- Pytorch: 2.6.0
+- Datasets: 3.0.1
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "</action>": 151672,
+  "</movie_title>": 151680,
+  "</response>": 151670,
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<accept>": 151678,
+  "<action>": 151671,
+  "<disclose-goal>": 151676,
+  "<feedback>": 151677,
+  "<greeting>": 151675,
+  "<inquire>": 151673,
+  "<movie_title>": 151679,
+  "<recommend>": 151674,
+  "<response>": 151669,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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 +1,9 @@
+{
+    "epoch": 1.9982692973347178,
+    "total_flos": 4.774796461726499e+18,
+    "train_loss": 0.7511481684000538,
+    "train_runtime": 11380.9982,
+    "train_samples": 46218,
+    "train_samples_per_second": 8.122,
+    "train_steps_per_second": 0.127
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151644,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151744
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d96a394cf06656eb935d8aca02a770eb51293879dac12830ca28cb3b3db52b73
+size 4900684832

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e36df7574ed89bb0a7d2333c9c3d1c174fc44e89e5d5c02a24295e815c6a64
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3265e7d720cb19447f8949b971b894cc15d84d77bafebc76b6d4c312650a6585
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566b74e36508f9f8b1f841d007f80c63469a6e2afb6d9afd9f230f5e3f96061b
+size 1578657400

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 16378324992
+  },
+  "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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-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_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "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_norm.weight": "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.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-00001-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_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

runs/May17_01-35-22_w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-56x5fg8/events.out.tfevents.1747445859.w-jerom-inter-play-sim-94c6890b9ccf44ea86f033a3db8a5dbd-56x5fg8.10629.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b81d6c00025b18fc4fa5d0b568e4a305a9904020144964bbfb41bba7dea80c1
+size 67464

special_tokens_map.json

@@ -0,0 +1,103 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<action>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</action>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<inquire>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<recommend>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<greeting>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<disclose-goal>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<feedback>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<accept>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<movie_title>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</movie_title>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "ÙģØŃ"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db976505810ec9dd83bba0026e309fb8472c6e5b43d986b588991da67502f70b
+size 11425005

tokenizer_config.json

@@ -0,0 +1,335 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "</response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<action>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "</action>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<inquire>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<recommend>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<greeting>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151676": {
+      "content": "<disclose-goal>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151677": {
+      "content": "<feedback>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151678": {
+      "content": "<accept>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151679": {
+      "content": "<movie_title>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151680": {
+      "content": "</movie_title>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<response>",
+    "</response>",
+    "<action>",
+    "</action>",
+    "<inquire>",
+    "<recommend>",
+    "<greeting>",
+    "<disclose-goal>",
+    "<feedback>",
+    "<accept>",
+    "<movie_title>",
+    "</movie_title>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "ÙģØŃ",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9982692973347178,
+    "total_flos": 4.774796461726499e+18,
+    "train_loss": 0.7511481684000538,
+    "train_runtime": 11380.9982,
+    "train_samples": 46218,
+    "train_samples_per_second": 8.122,
+    "train_steps_per_second": 0.127
+}

trainer_state.json

@@ -0,0 +1,2082 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9982692973347178,
+  "eval_steps": 500,
+  "global_step": 1444,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0013845621322256837,
+      "grad_norm": 36.99692916870117,
+      "learning_rate": 0.0,
+      "loss": 3.0679,
+      "step": 1
+    },
+    {
+      "epoch": 0.006922810661128418,
+      "grad_norm": 15.91442584991455,
+      "learning_rate": 5.517241379310345e-06,
+      "loss": 2.9546,
+      "step": 5
+    },
+    {
+      "epoch": 0.013845621322256836,
+      "grad_norm": 6.445705413818359,
+      "learning_rate": 1.2413793103448277e-05,
+      "loss": 2.3265,
+      "step": 10
+    },
+    {
+      "epoch": 0.020768431983385256,
+      "grad_norm": 7.000129699707031,
+      "learning_rate": 1.9310344827586207e-05,
+      "loss": 2.0234,
+      "step": 15
+    },
+    {
+      "epoch": 0.027691242644513673,
+      "grad_norm": 9.449470520019531,
+      "learning_rate": 2.620689655172414e-05,
+      "loss": 1.7883,
+      "step": 20
+    },
+    {
+      "epoch": 0.034614053305642094,
+      "grad_norm": 7.50212287902832,
+      "learning_rate": 3.310344827586207e-05,
+      "loss": 1.5598,
+      "step": 25
+    },
+    {
+      "epoch": 0.04153686396677051,
+      "grad_norm": 3.6690421104431152,
+      "learning_rate": 4e-05,
+      "loss": 1.2904,
+      "step": 30
+    },
+    {
+      "epoch": 0.04845967462789893,
+      "grad_norm": 3.425504446029663,
+      "learning_rate": 4.689655172413793e-05,
+      "loss": 1.2698,
+      "step": 35
+    },
+    {
+      "epoch": 0.055382485289027346,
+      "grad_norm": 3.642073392868042,
+      "learning_rate": 5.379310344827586e-05,
+      "loss": 1.2002,
+      "step": 40
+    },
+    {
+      "epoch": 0.06230529595015576,
+      "grad_norm": 3.359834909439087,
+      "learning_rate": 6.068965517241379e-05,
+      "loss": 1.1228,
+      "step": 45
+    },
+    {
+      "epoch": 0.06922810661128419,
+      "grad_norm": 2.215944528579712,
+      "learning_rate": 6.758620689655173e-05,
+      "loss": 1.0101,
+      "step": 50
+    },
+    {
+      "epoch": 0.0761509172724126,
+      "grad_norm": 1.9135385751724243,
+      "learning_rate": 7.448275862068966e-05,
+      "loss": 0.9731,
+      "step": 55
+    },
+    {
+      "epoch": 0.08307372793354102,
+      "grad_norm": 1.415416955947876,
+      "learning_rate": 8.137931034482759e-05,
+      "loss": 0.9475,
+      "step": 60
+    },
+    {
+      "epoch": 0.08999653859466944,
+      "grad_norm": 1.5166492462158203,
+      "learning_rate": 8.827586206896552e-05,
+      "loss": 0.998,
+      "step": 65
+    },
+    {
+      "epoch": 0.09691934925579786,
+      "grad_norm": 1.4899680614471436,
+      "learning_rate": 9.517241379310345e-05,
+      "loss": 0.9947,
+      "step": 70
+    },
+    {
+      "epoch": 0.10384215991692627,
+      "grad_norm": 1.1434413194656372,
+      "learning_rate": 0.0001020689655172414,
+      "loss": 0.9879,
+      "step": 75
+    },
+    {
+      "epoch": 0.11076497057805469,
+      "grad_norm": 1.0257912874221802,
+      "learning_rate": 0.00010896551724137931,
+      "loss": 1.0003,
+      "step": 80
+    },
+    {
+      "epoch": 0.11768778123918311,
+      "grad_norm": 1.187396764755249,
+      "learning_rate": 0.00011586206896551725,
+      "loss": 1.0114,
+      "step": 85
+    },
+    {
+      "epoch": 0.12461059190031153,
+      "grad_norm": 0.9548481106758118,
+      "learning_rate": 0.00012275862068965518,
+      "loss": 1.0146,
+      "step": 90
+    },
+    {
+      "epoch": 0.13153340256143994,
+      "grad_norm": 1.1940933465957642,
+      "learning_rate": 0.0001296551724137931,
+      "loss": 0.995,
+      "step": 95
+    },
+    {
+      "epoch": 0.13845621322256838,
+      "grad_norm": 1.1477693319320679,
+      "learning_rate": 0.00013655172413793104,
+      "loss": 0.9914,
+      "step": 100
+    },
+    {
+      "epoch": 0.14537902388369678,
+      "grad_norm": 0.9720847606658936,
+      "learning_rate": 0.00014344827586206896,
+      "loss": 0.9888,
+      "step": 105
+    },
+    {
+      "epoch": 0.1523018345448252,
+      "grad_norm": 0.9881941080093384,
+      "learning_rate": 0.0001503448275862069,
+      "loss": 1.0105,
+      "step": 110
+    },
+    {
+      "epoch": 0.1592246452059536,
+      "grad_norm": 0.8291202783584595,
+      "learning_rate": 0.00015724137931034485,
+      "loss": 1.0039,
+      "step": 115
+    },
+    {
+      "epoch": 0.16614745586708204,
+      "grad_norm": 2.3537802696228027,
+      "learning_rate": 0.00016413793103448276,
+      "loss": 0.9973,
+      "step": 120
+    },
+    {
+      "epoch": 0.17307026652821045,
+      "grad_norm": 10.804582595825195,
+      "learning_rate": 0.0001710344827586207,
+      "loss": 1.1009,
+      "step": 125
+    },
+    {
+      "epoch": 0.17999307718933888,
+      "grad_norm": 37.236934661865234,
+      "learning_rate": 0.00017793103448275862,
+      "loss": 1.7116,
+      "step": 130
+    },
+    {
+      "epoch": 0.18691588785046728,
+      "grad_norm": 2.900162935256958,
+      "learning_rate": 0.00018482758620689654,
+      "loss": 1.1986,
+      "step": 135
+    },
+    {
+      "epoch": 0.19383869851159571,
+      "grad_norm": 1.222854733467102,
+      "learning_rate": 0.0001917241379310345,
+      "loss": 1.0546,
+      "step": 140
+    },
+    {
+      "epoch": 0.20076150917272412,
+      "grad_norm": 1.0050123929977417,
+      "learning_rate": 0.00019862068965517243,
+      "loss": 1.0607,
+      "step": 145
+    },
+    {
+      "epoch": 0.20768431983385255,
+      "grad_norm": 1.7881501913070679,
+      "learning_rate": 0.0001999953208384105,
+      "loss": 1.1013,
+      "step": 150
+    },
+    {
+      "epoch": 0.21460713049498095,
+      "grad_norm": 1.2163009643554688,
+      "learning_rate": 0.0001999763124949378,
+      "loss": 1.06,
+      "step": 155
+    },
+    {
+      "epoch": 0.22152994115610938,
+      "grad_norm": 0.9521149396896362,
+      "learning_rate": 0.0001999426852993044,
+      "loss": 0.9803,
+      "step": 160
+    },
+    {
+      "epoch": 0.2284527518172378,
+      "grad_norm": 0.8825615644454956,
+      "learning_rate": 0.00019989444416858502,
+      "loss": 0.9539,
+      "step": 165
+    },
+    {
+      "epoch": 0.23537556247836622,
+      "grad_norm": 1.0269418954849243,
+      "learning_rate": 0.0001998315961567502,
+      "loss": 0.9898,
+      "step": 170
+    },
+    {
+      "epoch": 0.24229837313949462,
+      "grad_norm": 1.4703561067581177,
+      "learning_rate": 0.00019975415045363467,
+      "loss": 1.0,
+      "step": 175
+    },
+    {
+      "epoch": 0.24922118380062305,
+      "grad_norm": 3.445188045501709,
+      "learning_rate": 0.00019966211838359378,
+      "loss": 1.0302,
+      "step": 180
+    },
+    {
+      "epoch": 0.25614399446175146,
+      "grad_norm": 1.095542311668396,
+      "learning_rate": 0.00019955551340384743,
+      "loss": 1.0432,
+      "step": 185
+    },
+    {
+      "epoch": 0.2630668051228799,
+      "grad_norm": 3.0603744983673096,
+      "learning_rate": 0.00019943435110251248,
+      "loss": 1.0197,
+      "step": 190
+    },
+    {
+      "epoch": 0.2699896157840083,
+      "grad_norm": 4.020196914672852,
+      "learning_rate": 0.0001992986491963232,
+      "loss": 1.2696,
+      "step": 195
+    },
+    {
+      "epoch": 0.27691242644513675,
+      "grad_norm": 2.0897724628448486,
+      "learning_rate": 0.00019914842752804103,
+      "loss": 1.7173,
+      "step": 200
+    },
+    {
+      "epoch": 0.2838352371062651,
+      "grad_norm": 7.256534576416016,
+      "learning_rate": 0.00019898370806355263,
+      "loss": 1.1485,
+      "step": 205
+    },
+    {
+      "epoch": 0.29075804776739356,
+      "grad_norm": 1.7438695430755615,
+      "learning_rate": 0.00019880451488865836,
+      "loss": 1.1805,
+      "step": 210
+    },
+    {
+      "epoch": 0.297680858428522,
+      "grad_norm": 1.0164345502853394,
+      "learning_rate": 0.00019861087420555018,
+      "loss": 1.1521,
+      "step": 215
+    },
+    {
+      "epoch": 0.3046036690896504,
+      "grad_norm": 0.9694517850875854,
+      "learning_rate": 0.0001984028143289803,
+      "loss": 0.9914,
+      "step": 220
+    },
+    {
+      "epoch": 0.3115264797507788,
+      "grad_norm": 0.8658626079559326,
+      "learning_rate": 0.00019818036568212106,
+      "loss": 0.951,
+      "step": 225
+    },
+    {
+      "epoch": 0.3184492904119072,
+      "grad_norm": 0.6972668766975403,
+      "learning_rate": 0.00019794356079211604,
+      "loss": 0.9571,
+      "step": 230
+    },
+    {
+      "epoch": 0.32537210107303566,
+      "grad_norm": 0.8320409655570984,
+      "learning_rate": 0.00019769243428532422,
+      "loss": 0.9898,
+      "step": 235
+    },
+    {
+      "epoch": 0.3322949117341641,
+      "grad_norm": 0.7591261267662048,
+      "learning_rate": 0.00019742702288225652,
+      "loss": 0.9512,
+      "step": 240
+    },
+    {
+      "epoch": 0.33921772239529246,
+      "grad_norm": 1.5846096277236938,
+      "learning_rate": 0.00019714736539220648,
+      "loss": 0.9506,
+      "step": 245
+    },
+    {
+      "epoch": 0.3461405330564209,
+      "grad_norm": 0.6878282427787781,
+      "learning_rate": 0.00019685350270757555,
+      "loss": 0.9655,
+      "step": 250
+    },
+    {
+      "epoch": 0.3530633437175493,
+      "grad_norm": 0.6172508597373962,
+      "learning_rate": 0.0001965454777978936,
+      "loss": 0.9626,
+      "step": 255
+    },
+    {
+      "epoch": 0.35998615437867776,
+      "grad_norm": 0.6852116584777832,
+      "learning_rate": 0.00019622333570353567,
+      "loss": 0.9412,
+      "step": 260
+    },
+    {
+      "epoch": 0.36690896503980613,
+      "grad_norm": 0.6652204990386963,
+      "learning_rate": 0.00019588712352913625,
+      "loss": 0.9313,
+      "step": 265
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "grad_norm": 0.638995885848999,
+      "learning_rate": 0.00019553689043670127,
+      "loss": 0.9454,
+      "step": 270
+    },
+    {
+      "epoch": 0.380754586362063,
+      "grad_norm": 4.199680328369141,
+      "learning_rate": 0.00019517268763841962,
+      "loss": 0.9238,
+      "step": 275
+    },
+    {
+      "epoch": 0.38767739702319143,
+      "grad_norm": 0.6641167402267456,
+      "learning_rate": 0.00019479456838917473,
+      "loss": 0.9295,
+      "step": 280
+    },
+    {
+      "epoch": 0.39460020768431986,
+      "grad_norm": 0.6575414538383484,
+      "learning_rate": 0.0001944025879787574,
+      "loss": 0.9135,
+      "step": 285
+    },
+    {
+      "epoch": 0.40152301834544823,
+      "grad_norm": 0.6238983273506165,
+      "learning_rate": 0.0001939968037237812,
+      "loss": 0.9436,
+      "step": 290
+    },
+    {
+      "epoch": 0.40844582900657667,
+      "grad_norm": 0.587856650352478,
+      "learning_rate": 0.00019357727495930146,
+      "loss": 0.9264,
+      "step": 295
+    },
+    {
+      "epoch": 0.4153686396677051,
+      "grad_norm": 0.6809896230697632,
+      "learning_rate": 0.00019314406303013904,
+      "loss": 0.918,
+      "step": 300
+    },
+    {
+      "epoch": 0.42229145032883353,
+      "grad_norm": 0.6164669394493103,
+      "learning_rate": 0.00019269723128191048,
+      "loss": 0.9091,
+      "step": 305
+    },
+    {
+      "epoch": 0.4292142609899619,
+      "grad_norm": 0.5151002407073975,
+      "learning_rate": 0.00019223684505176517,
+      "loss": 0.9181,
+      "step": 310
+    },
+    {
+      "epoch": 0.43613707165109034,
+      "grad_norm": 2.156830310821533,
+      "learning_rate": 0.00019176297165883165,
+      "loss": 0.9445,
+      "step": 315
+    },
+    {
+      "epoch": 0.44305988231221877,
+      "grad_norm": 0.5134182572364807,
+      "learning_rate": 0.00019127568039437406,
+      "loss": 0.9116,
+      "step": 320
+    },
+    {
+      "epoch": 0.4499826929733472,
+      "grad_norm": 0.6247857809066772,
+      "learning_rate": 0.00019077504251166006,
+      "loss": 0.9073,
+      "step": 325
+    },
+    {
+      "epoch": 0.4569055036344756,
+      "grad_norm": 0.6191543340682983,
+      "learning_rate": 0.00019026113121554204,
+      "loss": 0.9038,
+      "step": 330
+    },
+    {
+      "epoch": 0.463828314295604,
+      "grad_norm": 0.5713596940040588,
+      "learning_rate": 0.00018973402165175268,
+      "loss": 0.9082,
+      "step": 335
+    },
+    {
+      "epoch": 0.47075112495673244,
+      "grad_norm": 0.524921178817749,
+      "learning_rate": 0.0001891937908959172,
+      "loss": 0.8912,
+      "step": 340
+    },
+    {
+      "epoch": 0.47767393561786087,
+      "grad_norm": 0.5696610808372498,
+      "learning_rate": 0.00018864051794228282,
+      "loss": 0.9034,
+      "step": 345
+    },
+    {
+      "epoch": 0.48459674627898924,
+      "grad_norm": 0.6064379215240479,
+      "learning_rate": 0.00018807428369216822,
+      "loss": 0.8678,
+      "step": 350
+    },
+    {
+      "epoch": 0.4915195569401177,
+      "grad_norm": 0.5061264634132385,
+      "learning_rate": 0.00018749517094213375,
+      "loss": 0.8718,
+      "step": 355
+    },
+    {
+      "epoch": 0.4984423676012461,
+      "grad_norm": 0.6122836470603943,
+      "learning_rate": 0.00018690326437187472,
+      "loss": 0.8837,
+      "step": 360
+    },
+    {
+      "epoch": 0.5053651782623745,
+      "grad_norm": 0.5305922031402588,
+      "learning_rate": 0.00018629865053183911,
+      "loss": 0.8754,
+      "step": 365
+    },
+    {
+      "epoch": 0.5122879889235029,
+      "grad_norm": 0.6255595088005066,
+      "learning_rate": 0.0001856814178305722,
+      "loss": 0.86,
+      "step": 370
+    },
+    {
+      "epoch": 0.5192107995846313,
+      "grad_norm": 0.49683791399002075,
+      "learning_rate": 0.00018505165652178893,
+      "loss": 0.8589,
+      "step": 375
+    },
+    {
+      "epoch": 0.5261336102457598,
+      "grad_norm": 0.5160537362098694,
+      "learning_rate": 0.00018440945869117675,
+      "loss": 0.8842,
+      "step": 380
+    },
+    {
+      "epoch": 0.5330564209068882,
+      "grad_norm": 0.4708365201950073,
+      "learning_rate": 0.00018375491824293067,
+      "loss": 0.8795,
+      "step": 385
+    },
+    {
+      "epoch": 0.5399792315680166,
+      "grad_norm": 0.47004085779190063,
+      "learning_rate": 0.00018308813088602227,
+      "loss": 0.8793,
+      "step": 390
+    },
+    {
+      "epoch": 0.5469020422291451,
+      "grad_norm": 0.5247258543968201,
+      "learning_rate": 0.00018240919412020466,
+      "loss": 0.859,
+      "step": 395
+    },
+    {
+      "epoch": 0.5538248528902735,
+      "grad_norm": 0.5026205778121948,
+      "learning_rate": 0.00018171820722175604,
+      "loss": 0.8764,
+      "step": 400
+    },
+    {
+      "epoch": 0.5607476635514018,
+      "grad_norm": 0.504045307636261,
+      "learning_rate": 0.00018101527122896293,
+      "loss": 0.8728,
+      "step": 405
+    },
+    {
+      "epoch": 0.5676704742125303,
+      "grad_norm": 0.5254899859428406,
+      "learning_rate": 0.0001803004889273463,
+      "loss": 0.8593,
+      "step": 410
+    },
+    {
+      "epoch": 0.5745932848736587,
+      "grad_norm": 0.46688538789749146,
+      "learning_rate": 0.0001795739648346317,
+      "loss": 0.8352,
+      "step": 415
+    },
+    {
+      "epoch": 0.5815160955347871,
+      "grad_norm": 0.48121586441993713,
+      "learning_rate": 0.00017883580518546647,
+      "loss": 0.8342,
+      "step": 420
+    },
+    {
+      "epoch": 0.5884389061959155,
+      "grad_norm": 0.5108678936958313,
+      "learning_rate": 0.00017808611791588584,
+      "loss": 0.8504,
+      "step": 425
+    },
+    {
+      "epoch": 0.595361716857044,
+      "grad_norm": 0.5048635005950928,
+      "learning_rate": 0.00017732501264752996,
+      "loss": 0.8389,
+      "step": 430
+    },
+    {
+      "epoch": 0.6022845275181724,
+      "grad_norm": 0.4736952781677246,
+      "learning_rate": 0.00017655260067161503,
+      "loss": 0.8625,
+      "step": 435
+    },
+    {
+      "epoch": 0.6092073381793008,
+      "grad_norm": 0.5057955980300903,
+      "learning_rate": 0.00017576899493265954,
+      "loss": 0.847,
+      "step": 440
+    },
+    {
+      "epoch": 0.6161301488404292,
+      "grad_norm": 0.4556281864643097,
+      "learning_rate": 0.00017497431001196943,
+      "loss": 0.849,
+      "step": 445
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.4683106541633606,
+      "learning_rate": 0.00017416866211088366,
+      "loss": 0.8554,
+      "step": 450
+    },
+    {
+      "epoch": 0.629975770162686,
+      "grad_norm": 0.5124343633651733,
+      "learning_rate": 0.00017335216903378267,
+      "loss": 0.8383,
+      "step": 455
+    },
+    {
+      "epoch": 0.6368985808238145,
+      "grad_norm": 0.5505478978157043,
+      "learning_rate": 0.00017252495017086296,
+      "loss": 0.8315,
+      "step": 460
+    },
+    {
+      "epoch": 0.6438213914849429,
+      "grad_norm": 0.486219197511673,
+      "learning_rate": 0.0001716871264806791,
+      "loss": 0.8476,
+      "step": 465
+    },
+    {
+      "epoch": 0.6507442021460713,
+      "grad_norm": 0.45981094241142273,
+      "learning_rate": 0.0001708388204724572,
+      "loss": 0.8453,
+      "step": 470
+    },
+    {
+      "epoch": 0.6576670128071997,
+      "grad_norm": 0.4615215063095093,
+      "learning_rate": 0.00016998015618818087,
+      "loss": 0.8579,
+      "step": 475
+    },
+    {
+      "epoch": 0.6645898234683282,
+      "grad_norm": 0.4511210024356842,
+      "learning_rate": 0.00016911125918445363,
+      "loss": 0.8384,
+      "step": 480
+    },
+    {
+      "epoch": 0.6715126341294566,
+      "grad_norm": 0.42190468311309814,
+      "learning_rate": 0.00016823225651413953,
+      "loss": 0.8265,
+      "step": 485
+    },
+    {
+      "epoch": 0.6784354447905849,
+      "grad_norm": 0.479647696018219,
+      "learning_rate": 0.00016734327670778508,
+      "loss": 0.8191,
+      "step": 490
+    },
+    {
+      "epoch": 0.6853582554517134,
+      "grad_norm": 0.608330249786377,
+      "learning_rate": 0.00016644444975482523,
+      "loss": 0.8149,
+      "step": 495
+    },
+    {
+      "epoch": 0.6922810661128418,
+      "grad_norm": 0.4981730580329895,
+      "learning_rate": 0.0001655359070845757,
+      "loss": 0.8219,
+      "step": 500
+    },
+    {
+      "epoch": 0.6992038767739702,
+      "grad_norm": 0.4622678756713867,
+      "learning_rate": 0.0001646177815470151,
+      "loss": 0.8246,
+      "step": 505
+    },
+    {
+      "epoch": 0.7061266874350987,
+      "grad_norm": 0.4577881693840027,
+      "learning_rate": 0.00016369020739335924,
+      "loss": 0.8066,
+      "step": 510
+    },
+    {
+      "epoch": 0.7130494980962271,
+      "grad_norm": 0.44852638244628906,
+      "learning_rate": 0.00016275332025643028,
+      "loss": 0.8216,
+      "step": 515
+    },
+    {
+      "epoch": 0.7199723087573555,
+      "grad_norm": 0.4342646300792694,
+      "learning_rate": 0.00016180725713082434,
+      "loss": 0.8273,
+      "step": 520
+    },
+    {
+      "epoch": 0.726895119418484,
+      "grad_norm": 0.5106623768806458,
+      "learning_rate": 0.0001608521563528795,
+      "loss": 0.8121,
+      "step": 525
+    },
+    {
+      "epoch": 0.7338179300796123,
+      "grad_norm": 0.45252540707588196,
+      "learning_rate": 0.00015988815758044792,
+      "loss": 0.8056,
+      "step": 530
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.4194222092628479,
+      "learning_rate": 0.00015891540177247467,
+      "loss": 0.8296,
+      "step": 535
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "grad_norm": 0.5437247157096863,
+      "learning_rate": 0.00015793403116838613,
+      "loss": 0.8201,
+      "step": 540
+    },
+    {
+      "epoch": 0.7545863620629976,
+      "grad_norm": 0.46110814809799194,
+      "learning_rate": 0.00015694418926729146,
+      "loss": 0.8049,
+      "step": 545
+    },
+    {
+      "epoch": 0.761509172724126,
+      "grad_norm": 0.4320140779018402,
+      "learning_rate": 0.00015594602080699956,
+      "loss": 0.8129,
+      "step": 550
+    },
+    {
+      "epoch": 0.7684319833852544,
+      "grad_norm": 0.5183108448982239,
+      "learning_rate": 0.00015493967174285512,
+      "loss": 0.8029,
+      "step": 555
+    },
+    {
+      "epoch": 0.7753547940463829,
+      "grad_norm": 0.40923014283180237,
+      "learning_rate": 0.00015392528922639662,
+      "loss": 0.8151,
+      "step": 560
+    },
+    {
+      "epoch": 0.7822776047075113,
+      "grad_norm": 0.4213641583919525,
+      "learning_rate": 0.00015290302158383923,
+      "loss": 0.8027,
+      "step": 565
+    },
+    {
+      "epoch": 0.7892004153686397,
+      "grad_norm": 0.4880472719669342,
+      "learning_rate": 0.0001518730182943862,
+      "loss": 0.805,
+      "step": 570
+    },
+    {
+      "epoch": 0.796123226029768,
+      "grad_norm": 0.41654378175735474,
+      "learning_rate": 0.0001508354299683715,
+      "loss": 0.8012,
+      "step": 575
+    },
+    {
+      "epoch": 0.8030460366908965,
+      "grad_norm": 0.46547961235046387,
+      "learning_rate": 0.0001497904083252371,
+      "loss": 0.8049,
+      "step": 580
+    },
+    {
+      "epoch": 0.8099688473520249,
+      "grad_norm": 0.41686978936195374,
+      "learning_rate": 0.00014873810617134806,
+      "loss": 0.7993,
+      "step": 585
+    },
+    {
+      "epoch": 0.8168916580131533,
+      "grad_norm": 0.4086816906929016,
+      "learning_rate": 0.00014767867737764876,
+      "loss": 0.7949,
+      "step": 590
+    },
+    {
+      "epoch": 0.8238144686742818,
+      "grad_norm": 0.43626415729522705,
+      "learning_rate": 0.0001466122768571633,
+      "loss": 0.8033,
+      "step": 595
+    },
+    {
+      "epoch": 0.8307372793354102,
+      "grad_norm": 0.42999717593193054,
+      "learning_rate": 0.0001455390605423437,
+      "loss": 0.8104,
+      "step": 600
+    },
+    {
+      "epoch": 0.8376600899965386,
+      "grad_norm": 0.5020118951797485,
+      "learning_rate": 0.00014445918536226904,
+      "loss": 0.7927,
+      "step": 605
+    },
+    {
+      "epoch": 0.8445829006576671,
+      "grad_norm": 0.48819220066070557,
+      "learning_rate": 0.00014337280921969858,
+      "loss": 0.7883,
+      "step": 610
+    },
+    {
+      "epoch": 0.8515057113187954,
+      "grad_norm": 0.4125864803791046,
+      "learning_rate": 0.0001422800909679829,
+      "loss": 0.7987,
+      "step": 615
+    },
+    {
+      "epoch": 0.8584285219799238,
+      "grad_norm": 0.48757144808769226,
+      "learning_rate": 0.00014118119038783588,
+      "loss": 0.7902,
+      "step": 620
+    },
+    {
+      "epoch": 0.8653513326410522,
+      "grad_norm": 0.47712209820747375,
+      "learning_rate": 0.00014007626816397087,
+      "loss": 0.8082,
+      "step": 625
+    },
+    {
+      "epoch": 0.8722741433021807,
+      "grad_norm": 0.4102008640766144,
+      "learning_rate": 0.00013896548586160503,
+      "loss": 0.7948,
+      "step": 630
+    },
+    {
+      "epoch": 0.8791969539633091,
+      "grad_norm": 0.4306066632270813,
+      "learning_rate": 0.00013784900590283473,
+      "loss": 0.7952,
+      "step": 635
+    },
+    {
+      "epoch": 0.8861197646244375,
+      "grad_norm": 0.42309749126434326,
+      "learning_rate": 0.00013672699154288569,
+      "loss": 0.7787,
+      "step": 640
+    },
+    {
+      "epoch": 0.893042575285566,
+      "grad_norm": 0.4400608539581299,
+      "learning_rate": 0.00013559960684624112,
+      "loss": 0.8045,
+      "step": 645
+    },
+    {
+      "epoch": 0.8999653859466944,
+      "grad_norm": 0.50711989402771,
+      "learning_rate": 0.0001344670166626519,
+      "loss": 0.7725,
+      "step": 650
+    },
+    {
+      "epoch": 0.9068881966078228,
+      "grad_norm": 0.45436131954193115,
+      "learning_rate": 0.0001333293866030317,
+      "loss": 0.7773,
+      "step": 655
+    },
+    {
+      "epoch": 0.9138110072689511,
+      "grad_norm": 0.40752795338630676,
+      "learning_rate": 0.0001321868830152407,
+      "loss": 0.7597,
+      "step": 660
+    },
+    {
+      "epoch": 0.9207338179300796,
+      "grad_norm": 0.43623602390289307,
+      "learning_rate": 0.00013103967295976179,
+      "loss": 0.7849,
+      "step": 665
+    },
+    {
+      "epoch": 0.927656628591208,
+      "grad_norm": 0.4025138318538666,
+      "learning_rate": 0.0001298879241852724,
+      "loss": 0.7823,
+      "step": 670
+    },
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.438235878944397,
+      "learning_rate": 0.0001287318051041159,
+      "loss": 0.7812,
+      "step": 675
+    },
+    {
+      "epoch": 0.9415022499134649,
+      "grad_norm": 0.4313248097896576,
+      "learning_rate": 0.00012757148476767553,
+      "loss": 0.7726,
+      "step": 680
+    },
+    {
+      "epoch": 0.9484250605745933,
+      "grad_norm": 0.40096625685691833,
+      "learning_rate": 0.0001264071328416555,
+      "loss": 0.7776,
+      "step": 685
+    },
+    {
+      "epoch": 0.9553478712357217,
+      "grad_norm": 0.39130938053131104,
+      "learning_rate": 0.00012523891958127168,
+      "loss": 0.7729,
+      "step": 690
+    },
+    {
+      "epoch": 0.9622706818968502,
+      "grad_norm": 0.4303322434425354,
+      "learning_rate": 0.0001240670158063565,
+      "loss": 0.7707,
+      "step": 695
+    },
+    {
+      "epoch": 0.9691934925579785,
+      "grad_norm": 0.3983173072338104,
+      "learning_rate": 0.00012289159287638105,
+      "loss": 0.7801,
+      "step": 700
+    },
+    {
+      "epoch": 0.9761163032191069,
+      "grad_norm": 0.40058690309524536,
+      "learning_rate": 0.00012171282266539845,
+      "loss": 0.7767,
+      "step": 705
+    },
+    {
+      "epoch": 0.9830391138802353,
+      "grad_norm": 0.4056876003742218,
+      "learning_rate": 0.00012053087753691172,
+      "loss": 0.7585,
+      "step": 710
+    },
+    {
+      "epoch": 0.9899619245413638,
+      "grad_norm": 0.4484279155731201,
+      "learning_rate": 0.00011934593031867038,
+      "loss": 0.7733,
+      "step": 715
+    },
+    {
+      "epoch": 0.9968847352024922,
+      "grad_norm": 0.38870301842689514,
+      "learning_rate": 0.00011815815427739911,
+      "loss": 0.7706,
+      "step": 720
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7746492028236389,
+      "eval_runtime": 60.0688,
+      "eval_samples_per_second": 34.444,
+      "eval_steps_per_second": 2.164,
+      "step": 723
+    },
+    {
+      "epoch": 1.0027691242644514,
+      "grad_norm": 0.41168180108070374,
+      "learning_rate": 0.00011696772309346182,
+      "loss": 0.6965,
+      "step": 725
+    },
+    {
+      "epoch": 1.0096919349255797,
+      "grad_norm": 0.4434298574924469,
+      "learning_rate": 0.0001157748108354659,
+      "loss": 0.5974,
+      "step": 730
+    },
+    {
+      "epoch": 1.0166147455867083,
+      "grad_norm": 0.3997260332107544,
+      "learning_rate": 0.00011457959193480925,
+      "loss": 0.5963,
+      "step": 735
+    },
+    {
+      "epoch": 1.0235375562478366,
+      "grad_norm": 0.4161541163921356,
+      "learning_rate": 0.00011338224116017423,
+      "loss": 0.5973,
+      "step": 740
+    },
+    {
+      "epoch": 1.0304603669089651,
+      "grad_norm": 0.6814983487129211,
+      "learning_rate": 0.00011218293359197267,
+      "loss": 0.5994,
+      "step": 745
+    },
+    {
+      "epoch": 1.0373831775700935,
+      "grad_norm": 0.4457721710205078,
+      "learning_rate": 0.00011098184459674484,
+      "loss": 0.5688,
+      "step": 750
+    },
+    {
+      "epoch": 1.0443059882312218,
+      "grad_norm": 0.41027259826660156,
+      "learning_rate": 0.00010977914980151691,
+      "loss": 0.5982,
+      "step": 755
+    },
+    {
+      "epoch": 1.0512287988923503,
+      "grad_norm": 0.41261303424835205,
+      "learning_rate": 0.00010857502506812029,
+      "loss": 0.5781,
+      "step": 760
+    },
+    {
+      "epoch": 1.0581516095534786,
+      "grad_norm": 0.3924131393432617,
+      "learning_rate": 0.00010736964646747629,
+      "loss": 0.578,
+      "step": 765
+    },
+    {
+      "epoch": 1.0650744202146072,
+      "grad_norm": 0.38322097063064575,
+      "learning_rate": 0.00010616319025385089,
+      "loss": 0.5979,
+      "step": 770
+    },
+    {
+      "epoch": 1.0719972308757355,
+      "grad_norm": 0.3903074562549591,
+      "learning_rate": 0.00010495583283908177,
+      "loss": 0.5887,
+      "step": 775
+    },
+    {
+      "epoch": 1.078920041536864,
+      "grad_norm": 0.40374380350112915,
+      "learning_rate": 0.00010374775076678332,
+      "loss": 0.5708,
+      "step": 780
+    },
+    {
+      "epoch": 1.0858428521979924,
+      "grad_norm": 0.41232338547706604,
+      "learning_rate": 0.00010253912068653146,
+      "loss": 0.5899,
+      "step": 785
+    },
+    {
+      "epoch": 1.092765662859121,
+      "grad_norm": 0.37063470482826233,
+      "learning_rate": 0.00010133011932803378,
+      "loss": 0.5792,
+      "step": 790
+    },
+    {
+      "epoch": 1.0996884735202492,
+      "grad_norm": 0.42684876918792725,
+      "learning_rate": 0.00010012092347528705,
+      "loss": 0.589,
+      "step": 795
+    },
+    {
+      "epoch": 1.1066112841813776,
+      "grad_norm": 0.4422379732131958,
+      "learning_rate": 9.891170994072793e-05,
+      "loss": 0.5821,
+      "step": 800
+    },
+    {
+      "epoch": 1.113534094842506,
+      "grad_norm": 0.4900904595851898,
+      "learning_rate": 9.770265553937831e-05,
+      "loss": 0.5807,
+      "step": 805
+    },
+    {
+      "epoch": 1.1204569055036344,
+      "grad_norm": 0.43178027868270874,
+      "learning_rate": 9.649393706299127e-05,
+      "loss": 0.5657,
+      "step": 810
+    },
+    {
+      "epoch": 1.127379716164763,
+      "grad_norm": 0.43203285336494446,
+      "learning_rate": 9.52857312541998e-05,
+      "loss": 0.5762,
+      "step": 815
+    },
+    {
+      "epoch": 1.1343025268258913,
+      "grad_norm": 0.41020694375038147,
+      "learning_rate": 9.407821478067304e-05,
+      "loss": 0.5682,
+      "step": 820
+    },
+    {
+      "epoch": 1.1412253374870198,
+      "grad_norm": 0.404141902923584,
+      "learning_rate": 9.287156420928342e-05,
+      "loss": 0.5701,
+      "step": 825
+    },
+    {
+      "epoch": 1.1481481481481481,
+      "grad_norm": 0.36725813150405884,
+      "learning_rate": 9.166595598028832e-05,
+      "loss": 0.5909,
+      "step": 830
+    },
+    {
+      "epoch": 1.1550709588092767,
+      "grad_norm": 0.40943267941474915,
+      "learning_rate": 9.046156638153056e-05,
+      "loss": 0.5683,
+      "step": 835
+    },
+    {
+      "epoch": 1.161993769470405,
+      "grad_norm": 0.3729795515537262,
+      "learning_rate": 8.925857152266103e-05,
+      "loss": 0.5716,
+      "step": 840
+    },
+    {
+      "epoch": 1.1689165801315333,
+      "grad_norm": 0.4161226451396942,
+      "learning_rate": 8.805714730938728e-05,
+      "loss": 0.5769,
+      "step": 845
+    },
+    {
+      "epoch": 1.1758393907926619,
+      "grad_norm": 0.3843950927257538,
+      "learning_rate": 8.685746941775219e-05,
+      "loss": 0.5678,
+      "step": 850
+    },
+    {
+      "epoch": 1.1827622014537902,
+      "grad_norm": 0.40685024857521057,
+      "learning_rate": 8.565971326844584e-05,
+      "loss": 0.5692,
+      "step": 855
+    },
+    {
+      "epoch": 1.1896850121149187,
+      "grad_norm": 0.40106266736984253,
+      "learning_rate": 8.44640540011553e-05,
+      "loss": 0.5738,
+      "step": 860
+    },
+    {
+      "epoch": 1.196607822776047,
+      "grad_norm": 0.4031878113746643,
+      "learning_rate": 8.327066644895469e-05,
+      "loss": 0.5712,
+      "step": 865
+    },
+    {
+      "epoch": 1.2035306334371756,
+      "grad_norm": 0.42471978068351746,
+      "learning_rate": 8.207972511274095e-05,
+      "loss": 0.5639,
+      "step": 870
+    },
+    {
+      "epoch": 1.210453444098304,
+      "grad_norm": 0.3819376528263092,
+      "learning_rate": 8.089140413571747e-05,
+      "loss": 0.5665,
+      "step": 875
+    },
+    {
+      "epoch": 1.2173762547594325,
+      "grad_norm": 0.43387338519096375,
+      "learning_rate": 7.970587727793051e-05,
+      "loss": 0.5593,
+      "step": 880
+    },
+    {
+      "epoch": 1.2242990654205608,
+      "grad_norm": 0.38693514466285706,
+      "learning_rate": 7.852331789086135e-05,
+      "loss": 0.5644,
+      "step": 885
+    },
+    {
+      "epoch": 1.231221876081689,
+      "grad_norm": 0.40408262610435486,
+      "learning_rate": 7.73438988920784e-05,
+      "loss": 0.5692,
+      "step": 890
+    },
+    {
+      "epoch": 1.2381446867428176,
+      "grad_norm": 0.4097476303577423,
+      "learning_rate": 7.616779273995252e-05,
+      "loss": 0.5719,
+      "step": 895
+    },
+    {
+      "epoch": 1.245067497403946,
+      "grad_norm": 0.40725842118263245,
+      "learning_rate": 7.499517140843968e-05,
+      "loss": 0.5652,
+      "step": 900
+    },
+    {
+      "epoch": 1.2519903080650745,
+      "grad_norm": 0.41550350189208984,
+      "learning_rate": 7.382620636193438e-05,
+      "loss": 0.5612,
+      "step": 905
+    },
+    {
+      "epoch": 1.2589131187262028,
+      "grad_norm": 0.4235980808734894,
+      "learning_rate": 7.266106853019759e-05,
+      "loss": 0.5597,
+      "step": 910
+    },
+    {
+      "epoch": 1.2658359293873311,
+      "grad_norm": 0.3927691876888275,
+      "learning_rate": 7.149992828336274e-05,
+      "loss": 0.5658,
+      "step": 915
+    },
+    {
+      "epoch": 1.2727587400484597,
+      "grad_norm": 0.4296377897262573,
+      "learning_rate": 7.034295540702397e-05,
+      "loss": 0.5591,
+      "step": 920
+    },
+    {
+      "epoch": 1.2796815507095882,
+      "grad_norm": 0.39783212542533875,
+      "learning_rate": 6.919031907740922e-05,
+      "loss": 0.5779,
+      "step": 925
+    },
+    {
+      "epoch": 1.2866043613707165,
+      "grad_norm": 0.4201776087284088,
+      "learning_rate": 6.804218783664288e-05,
+      "loss": 0.5715,
+      "step": 930
+    },
+    {
+      "epoch": 1.2935271720318449,
+      "grad_norm": 0.3674381673336029,
+      "learning_rate": 6.689872956810102e-05,
+      "loss": 0.5583,
+      "step": 935
+    },
+    {
+      "epoch": 1.3004499826929734,
+      "grad_norm": 0.39247825741767883,
+      "learning_rate": 6.5760111471863e-05,
+      "loss": 0.5574,
+      "step": 940
+    },
+    {
+      "epoch": 1.3073727933541017,
+      "grad_norm": 0.3951855003833771,
+      "learning_rate": 6.46265000402628e-05,
+      "loss": 0.5646,
+      "step": 945
+    },
+    {
+      "epoch": 1.3142956040152303,
+      "grad_norm": 0.37041106820106506,
+      "learning_rate": 6.349806103354417e-05,
+      "loss": 0.561,
+      "step": 950
+    },
+    {
+      "epoch": 1.3212184146763586,
+      "grad_norm": 0.4068072736263275,
+      "learning_rate": 6.23749594556226e-05,
+      "loss": 0.5555,
+      "step": 955
+    },
+    {
+      "epoch": 1.328141225337487,
+      "grad_norm": 0.3812420666217804,
+      "learning_rate": 6.125735952995775e-05,
+      "loss": 0.5606,
+      "step": 960
+    },
+    {
+      "epoch": 1.3350640359986155,
+      "grad_norm": 0.42359232902526855,
+      "learning_rate": 6.0145424675540394e-05,
+      "loss": 0.5557,
+      "step": 965
+    },
+    {
+      "epoch": 1.341986846659744,
+      "grad_norm": 0.3885987401008606,
+      "learning_rate": 5.9039317482996735e-05,
+      "loss": 0.5655,
+      "step": 970
+    },
+    {
+      "epoch": 1.3489096573208723,
+      "grad_norm": 0.3710838258266449,
+      "learning_rate": 5.793919969081374e-05,
+      "loss": 0.5445,
+      "step": 975
+    },
+    {
+      "epoch": 1.3558324679820006,
+      "grad_norm": 0.3927723169326782,
+      "learning_rate": 5.68452321616894e-05,
+      "loss": 0.5417,
+      "step": 980
+    },
+    {
+      "epoch": 1.3627552786431292,
+      "grad_norm": 0.39248526096343994,
+      "learning_rate": 5.5757574859010886e-05,
+      "loss": 0.5584,
+      "step": 985
+    },
+    {
+      "epoch": 1.3696780893042575,
+      "grad_norm": 0.4080273509025574,
+      "learning_rate": 5.467638682346403e-05,
+      "loss": 0.5412,
+      "step": 990
+    },
+    {
+      "epoch": 1.376600899965386,
+      "grad_norm": 0.3992749750614166,
+      "learning_rate": 5.3601826149777966e-05,
+      "loss": 0.5734,
+      "step": 995
+    },
+    {
+      "epoch": 1.3835237106265144,
+      "grad_norm": 0.37569689750671387,
+      "learning_rate": 5.25340499636082e-05,
+      "loss": 0.5538,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3904465212876427,
+      "grad_norm": 0.40693604946136475,
+      "learning_rate": 5.147321439856091e-05,
+      "loss": 0.557,
+      "step": 1005
+    },
+    {
+      "epoch": 1.3973693319487712,
+      "grad_norm": 0.35887908935546875,
+      "learning_rate": 5.041947457336274e-05,
+      "loss": 0.5589,
+      "step": 1010
+    },
+    {
+      "epoch": 1.4042921426098995,
+      "grad_norm": 0.36887434124946594,
+      "learning_rate": 4.937298456917889e-05,
+      "loss": 0.5357,
+      "step": 1015
+    },
+    {
+      "epoch": 1.411214953271028,
+      "grad_norm": 0.3944549262523651,
+      "learning_rate": 4.8333897407082896e-05,
+      "loss": 0.5465,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4181377639321564,
+      "grad_norm": 0.3607221841812134,
+      "learning_rate": 4.7302365025681206e-05,
+      "loss": 0.5553,
+      "step": 1025
+    },
+    {
+      "epoch": 1.425060574593285,
+      "grad_norm": 0.3826063275337219,
+      "learning_rate": 4.627853825889642e-05,
+      "loss": 0.5313,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4319833852544133,
+      "grad_norm": 0.3818247616291046,
+      "learning_rate": 4.526256681391192e-05,
+      "loss": 0.5486,
+      "step": 1035
+    },
+    {
+      "epoch": 1.4389061959155418,
+      "grad_norm": 0.40942633152008057,
+      "learning_rate": 4.4254599249281016e-05,
+      "loss": 0.5302,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4458290065766701,
+      "grad_norm": 0.40826553106307983,
+      "learning_rate": 4.3254782953204375e-05,
+      "loss": 0.5407,
+      "step": 1045
+    },
+    {
+      "epoch": 1.4527518172377984,
+      "grad_norm": 0.3731902241706848,
+      "learning_rate": 4.2263264121978505e-05,
+      "loss": 0.5471,
+      "step": 1050
+    },
+    {
+      "epoch": 1.459674627898927,
+      "grad_norm": 0.40096205472946167,
+      "learning_rate": 4.12801877386183e-05,
+      "loss": 0.536,
+      "step": 1055
+    },
+    {
+      "epoch": 1.4665974385600553,
+      "grad_norm": 0.374845415353775,
+      "learning_rate": 4.030569755165736e-05,
+      "loss": 0.546,
+      "step": 1060
+    },
+    {
+      "epoch": 1.4735202492211839,
+      "grad_norm": 0.3810202181339264,
+      "learning_rate": 3.9339936054128466e-05,
+      "loss": 0.5375,
+      "step": 1065
+    },
+    {
+      "epoch": 1.4804430598823122,
+      "grad_norm": 0.39244675636291504,
+      "learning_rate": 3.8383044462727826e-05,
+      "loss": 0.5306,
+      "step": 1070
+    },
+    {
+      "epoch": 1.4873658705434407,
+      "grad_norm": 0.40670761466026306,
+      "learning_rate": 3.7435162697166107e-05,
+      "loss": 0.5497,
+      "step": 1075
+    },
+    {
+      "epoch": 1.494288681204569,
+      "grad_norm": 0.4042389392852783,
+      "learning_rate": 3.649642935970859e-05,
+      "loss": 0.5541,
+      "step": 1080
+    },
+    {
+      "epoch": 1.5012114918656976,
+      "grad_norm": 0.39131784439086914,
+      "learning_rate": 3.556698171490871e-05,
+      "loss": 0.5415,
+      "step": 1085
+    },
+    {
+      "epoch": 1.508134302526826,
+      "grad_norm": 0.3889631927013397,
+      "learning_rate": 3.464695566953644e-05,
+      "loss": 0.5313,
+      "step": 1090
+    },
+    {
+      "epoch": 1.5150571131879542,
+      "grad_norm": 0.4033074975013733,
+      "learning_rate": 3.373648575270576e-05,
+      "loss": 0.538,
+      "step": 1095
+    },
+    {
+      "epoch": 1.5219799238490828,
+      "grad_norm": 0.36675384640693665,
+      "learning_rate": 3.283570509620344e-05,
+      "loss": 0.5443,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5289027345102113,
+      "grad_norm": 0.380545049905777,
+      "learning_rate": 3.1944745415021915e-05,
+      "loss": 0.5394,
+      "step": 1105
+    },
+    {
+      "epoch": 1.5358255451713396,
+      "grad_norm": 0.35882043838500977,
+      "learning_rate": 3.106373698809958e-05,
+      "loss": 0.5445,
+      "step": 1110
+    },
+    {
+      "epoch": 1.542748355832468,
+      "grad_norm": 0.3889442980289459,
+      "learning_rate": 3.0192808639271065e-05,
+      "loss": 0.5536,
+      "step": 1115
+    },
+    {
+      "epoch": 1.5496711664935963,
+      "grad_norm": 0.3797926902770996,
+      "learning_rate": 2.933208771843018e-05,
+      "loss": 0.5409,
+      "step": 1120
+    },
+    {
+      "epoch": 1.5565939771547248,
+      "grad_norm": 0.38983410596847534,
+      "learning_rate": 2.8481700082908268e-05,
+      "loss": 0.5347,
+      "step": 1125
+    },
+    {
+      "epoch": 1.5635167878158533,
+      "grad_norm": 0.39294636249542236,
+      "learning_rate": 2.7641770079071127e-05,
+      "loss": 0.5374,
+      "step": 1130
+    },
+    {
+      "epoch": 1.5704395984769817,
+      "grad_norm": 0.37386760115623474,
+      "learning_rate": 2.681242052413656e-05,
+      "loss": 0.5198,
+      "step": 1135
+    },
+    {
+      "epoch": 1.57736240913811,
+      "grad_norm": 0.41262131929397583,
+      "learning_rate": 2.59937726882158e-05,
+      "loss": 0.5231,
+      "step": 1140
+    },
+    {
+      "epoch": 1.5842852197992385,
+      "grad_norm": 0.4110383987426758,
+      "learning_rate": 2.5185946276580918e-05,
+      "loss": 0.5478,
+      "step": 1145
+    },
+    {
+      "epoch": 1.591208030460367,
+      "grad_norm": 0.3801433742046356,
+      "learning_rate": 2.4389059412161087e-05,
+      "loss": 0.5395,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5981308411214954,
+      "grad_norm": 0.37619632482528687,
+      "learning_rate": 2.3603228618270356e-05,
+      "loss": 0.5355,
+      "step": 1155
+    },
+    {
+      "epoch": 1.6050536517826237,
+      "grad_norm": 0.3852304220199585,
+      "learning_rate": 2.2828568801569283e-05,
+      "loss": 0.5133,
+      "step": 1160
+    },
+    {
+      "epoch": 1.611976462443752,
+      "grad_norm": 0.35891711711883545,
+      "learning_rate": 2.2065193235262782e-05,
+      "loss": 0.5114,
+      "step": 1165
+    },
+    {
+      "epoch": 1.6188992731048806,
+      "grad_norm": 0.3851226568222046,
+      "learning_rate": 2.1313213542537058e-05,
+      "loss": 0.5308,
+      "step": 1170
+    },
+    {
+      "epoch": 1.6258220837660091,
+      "grad_norm": 0.3977566659450531,
+      "learning_rate": 2.0572739680237717e-05,
+      "loss": 0.5459,
+      "step": 1175
+    },
+    {
+      "epoch": 1.6327448944271374,
+      "grad_norm": 0.3800656497478485,
+      "learning_rate": 1.984387992279153e-05,
+      "loss": 0.5479,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6396677050882658,
+      "grad_norm": 0.41137266159057617,
+      "learning_rate": 1.912674084637409e-05,
+      "loss": 0.5429,
+      "step": 1185
+    },
+    {
+      "epoch": 1.6465905157493943,
+      "grad_norm": 0.3646909296512604,
+      "learning_rate": 1.8421427313326046e-05,
+      "loss": 0.5212,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6535133264105226,
+      "grad_norm": 0.38323456048965454,
+      "learning_rate": 1.7728042456819704e-05,
+      "loss": 0.5419,
+      "step": 1195
+    },
+    {
+      "epoch": 1.6604361370716512,
+      "grad_norm": 0.3656870126724243,
+      "learning_rate": 1.7046687665778717e-05,
+      "loss": 0.523,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6673589477327795,
+      "grad_norm": 0.3620772957801819,
+      "learning_rate": 1.6377462570052438e-05,
+      "loss": 0.5203,
+      "step": 1205
+    },
+    {
+      "epoch": 1.6742817583939078,
+      "grad_norm": 0.4021745026111603,
+      "learning_rate": 1.5720465025847987e-05,
+      "loss": 0.5243,
+      "step": 1210
+    },
+    {
+      "epoch": 1.6812045690550363,
+      "grad_norm": 0.3713143467903137,
+      "learning_rate": 1.5075791101421166e-05,
+      "loss": 0.5251,
+      "step": 1215
+    },
+    {
+      "epoch": 1.6881273797161649,
+      "grad_norm": 0.3876360356807709,
+      "learning_rate": 1.4443535063029279e-05,
+      "loss": 0.5429,
+      "step": 1220
+    },
+    {
+      "epoch": 1.6950501903772932,
+      "grad_norm": 0.38543200492858887,
+      "learning_rate": 1.3823789361147044e-05,
+      "loss": 0.5178,
+      "step": 1225
+    },
+    {
+      "epoch": 1.7019730010384215,
+      "grad_norm": 0.39921507239341736,
+      "learning_rate": 1.3216644616948282e-05,
+      "loss": 0.5248,
+      "step": 1230
+    },
+    {
+      "epoch": 1.70889581169955,
+      "grad_norm": 0.36942583322525024,
+      "learning_rate": 1.2622189609054979e-05,
+      "loss": 0.5174,
+      "step": 1235
+    },
+    {
+      "epoch": 1.7158186223606784,
+      "grad_norm": 0.41628918051719666,
+      "learning_rate": 1.2040511260555831e-05,
+      "loss": 0.5253,
+      "step": 1240
+    },
+    {
+      "epoch": 1.722741433021807,
+      "grad_norm": 0.3788851797580719,
+      "learning_rate": 1.1471694626296049e-05,
+      "loss": 0.523,
+      "step": 1245
+    },
+    {
+      "epoch": 1.7296642436829353,
+      "grad_norm": 0.369893342256546,
+      "learning_rate": 1.0915822880440308e-05,
+      "loss": 0.5167,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7365870543440636,
+      "grad_norm": 0.37253957986831665,
+      "learning_rate": 1.037297730431085e-05,
+      "loss": 0.513,
+      "step": 1255
+    },
+    {
+      "epoch": 1.7435098650051921,
+      "grad_norm": 0.3707478940486908,
+      "learning_rate": 9.843237274502282e-06,
+      "loss": 0.5268,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7504326756663207,
+      "grad_norm": 0.38524284958839417,
+      "learning_rate": 9.326680251274777e-06,
+      "loss": 0.5357,
+      "step": 1265
+    },
+    {
+      "epoch": 1.757355486327449,
+      "grad_norm": 0.3852950930595398,
+      "learning_rate": 8.823381767227667e-06,
+      "loss": 0.5257,
+      "step": 1270
+    },
+    {
+      "epoch": 1.7642782969885773,
+      "grad_norm": 0.38060450553894043,
+      "learning_rate": 8.333415416254831e-06,
+      "loss": 0.527,
+      "step": 1275
+    },
+    {
+      "epoch": 1.7712011076497056,
+      "grad_norm": 0.3773637115955353,
+      "learning_rate": 7.856852842783547e-06,
+      "loss": 0.5161,
+      "step": 1280
+    },
+    {
+      "epoch": 1.7781239183108342,
+      "grad_norm": 0.3634498119354248,
+      "learning_rate": 7.393763731298387e-06,
+      "loss": 0.5116,
+      "step": 1285
+    },
+    {
+      "epoch": 1.7850467289719627,
+      "grad_norm": 0.3612436056137085,
+      "learning_rate": 6.944215796151765e-06,
+      "loss": 0.5153,
+      "step": 1290
+    },
+    {
+      "epoch": 1.791969539633091,
+      "grad_norm": 0.40675196051597595,
+      "learning_rate": 6.5082747716625255e-06,
+      "loss": 0.5276,
+      "step": 1295
+    },
+    {
+      "epoch": 1.7988923502942193,
+      "grad_norm": 0.3541720509529114,
+      "learning_rate": 6.086004402504098e-06,
+      "loss": 0.5096,
+      "step": 1300
+    },
+    {
+      "epoch": 1.8058151609553479,
+      "grad_norm": 0.38791441917419434,
+      "learning_rate": 5.6774664343834495e-06,
+      "loss": 0.5346,
+      "step": 1305
+    },
+    {
+      "epoch": 1.8127379716164764,
+      "grad_norm": 0.37747085094451904,
+      "learning_rate": 5.2827206050125585e-06,
+      "loss": 0.5218,
+      "step": 1310
+    },
+    {
+      "epoch": 1.8196607822776047,
+      "grad_norm": 0.3927886486053467,
+      "learning_rate": 4.9018246353732755e-06,
+      "loss": 0.5352,
+      "step": 1315
+    },
+    {
+      "epoch": 1.826583592938733,
+      "grad_norm": 0.3697344958782196,
+      "learning_rate": 4.534834221277262e-06,
+      "loss": 0.5143,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8335064035998614,
+      "grad_norm": 0.37708741426467896,
+      "learning_rate": 4.181803025221898e-06,
+      "loss": 0.5243,
+      "step": 1325
+    },
+    {
+      "epoch": 1.84042921426099,
+      "grad_norm": 0.3722737431526184,
+      "learning_rate": 3.842782668543599e-06,
+      "loss": 0.5211,
+      "step": 1330
+    },
+    {
+      "epoch": 1.8473520249221185,
+      "grad_norm": 0.347428560256958,
+      "learning_rate": 3.5178227238696347e-06,
+      "loss": 0.5123,
+      "step": 1335
+    },
+    {
+      "epoch": 1.8542748355832468,
+      "grad_norm": 0.3938564658164978,
+      "learning_rate": 3.2069707078694057e-06,
+      "loss": 0.5079,
+      "step": 1340
+    },
+    {
+      "epoch": 1.8611976462443751,
+      "grad_norm": 0.37338557839393616,
+      "learning_rate": 2.9102720743064527e-06,
+      "loss": 0.5287,
+      "step": 1345
+    },
+    {
+      "epoch": 1.8681204569055037,
+      "grad_norm": 0.3692079484462738,
+      "learning_rate": 2.6277702073919997e-06,
+      "loss": 0.5069,
+      "step": 1350
+    },
+    {
+      "epoch": 1.8750432675666322,
+      "grad_norm": 0.3760637938976288,
+      "learning_rate": 2.3595064154412374e-06,
+      "loss": 0.5129,
+      "step": 1355
+    },
+    {
+      "epoch": 1.8819660782277605,
+      "grad_norm": 0.38482972979545593,
+      "learning_rate": 2.1055199248330546e-06,
+      "loss": 0.5163,
+      "step": 1360
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.3872315585613251,
+      "learning_rate": 1.8658478742742625e-06,
+      "loss": 0.5157,
+      "step": 1365
+    },
+    {
+      "epoch": 1.8958116995500172,
+      "grad_norm": 0.3754504919052124,
+      "learning_rate": 1.6405253093690343e-06,
+      "loss": 0.5132,
+      "step": 1370
+    },
+    {
+      "epoch": 1.9027345102111457,
+      "grad_norm": 0.3796706199645996,
+      "learning_rate": 1.429585177494419e-06,
+      "loss": 0.5107,
+      "step": 1375
+    },
+    {
+      "epoch": 1.9096573208722742,
+      "grad_norm": 0.37216416001319885,
+      "learning_rate": 1.2330583229827053e-06,
+      "loss": 0.5228,
+      "step": 1380
+    },
+    {
+      "epoch": 1.9165801315334026,
+      "grad_norm": 0.3697955012321472,
+      "learning_rate": 1.0509734826112394e-06,
+      "loss": 0.5105,
+      "step": 1385
+    },
+    {
+      "epoch": 1.9235029421945309,
+      "grad_norm": 0.39311596751213074,
+      "learning_rate": 8.833572814004321e-07,
+      "loss": 0.5069,
+      "step": 1390
+    },
+    {
+      "epoch": 1.9304257528556594,
+      "grad_norm": 0.3675869405269623,
+      "learning_rate": 7.302342287205943e-07,
+      "loss": 0.511,
+      "step": 1395
+    },
+    {
+      "epoch": 1.937348563516788,
+      "grad_norm": 0.38679271936416626,
+      "learning_rate": 5.916267147080934e-07,
+      "loss": 0.5175,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9442713741779163,
+      "grad_norm": 0.3862612247467041,
+      "learning_rate": 4.6755500699138253e-07,
+      "loss": 0.5075,
+      "step": 1405
+    },
+    {
+      "epoch": 1.9511941848390446,
+      "grad_norm": 0.3884969651699066,
+      "learning_rate": 3.5803724772740523e-07,
+      "loss": 0.5132,
+      "step": 1410
+    },
+    {
+      "epoch": 1.958116995500173,
+      "grad_norm": 0.36823418736457825,
+      "learning_rate": 2.630894509488058e-07,
+      "loss": 0.5151,
+      "step": 1415
+    },
+    {
+      "epoch": 1.9650398061613015,
+      "grad_norm": 0.36939066648483276,
+      "learning_rate": 1.8272550022230272e-07,
+      "loss": 0.5128,
+      "step": 1420
+    },
+    {
+      "epoch": 1.97196261682243,
+      "grad_norm": 0.38535770773887634,
+      "learning_rate": 1.1695714661856816e-07,
+      "loss": 0.5019,
+      "step": 1425
+    },
+    {
+      "epoch": 1.9788854274835583,
+      "grad_norm": 0.3671540915966034,
+      "learning_rate": 6.579400699397998e-08,
+      "loss": 0.5135,
+      "step": 1430
+    },
+    {
+      "epoch": 1.9858082381446867,
+      "grad_norm": 0.36039796471595764,
+      "learning_rate": 2.9243562584402305e-08,
+      "loss": 0.525,
+      "step": 1435
+    },
+    {
+      "epoch": 1.9927310488058152,
+      "grad_norm": 0.3742762804031372,
+      "learning_rate": 7.311157911249478e-09,
+      "loss": 0.5266,
+      "step": 1440
+    },
+    {
+      "epoch": 1.9982692973347178,
+      "eval_loss": 0.7263619303703308,
+      "eval_runtime": 60.0642,
+      "eval_samples_per_second": 34.446,
+      "eval_steps_per_second": 2.164,
+      "step": 1444
+    },
+    {
+      "epoch": 1.9982692973347178,
+      "step": 1444,
+      "total_flos": 4.774796461726499e+18,
+      "train_loss": 0.7511481684000538,
+      "train_runtime": 11380.9982,
+      "train_samples_per_second": 8.122,
+      "train_steps_per_second": 0.127
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1444,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.774796461726499e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f69b66d816c2099f74805fb3fb5224381d74a293161d0078d22df01687bcaf
+size 7096