commit f556e592f070d9885192a2b231123d408205069b Author: ModelHub XC Date: Fri May 29 16:09:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: wassname/llama-3.2-3b-sft Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz 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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2534f50 --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +base_model: tanliboy/Llama-3.2-3B +datasets: +- wassname/ultrachat_200k_filtered +library_name: transformers +model_name: llama-3.2-3b-sft +tags: +- generated_from_trainer +- alignment-handbook +licence: license +--- + +# Model Card for llama-3.2-3b-sft + +This model is a fine-tuned version of [tanliboy/Llama-3.2-3B](https://huggingface.co/tanliboy/Llama-3.2-3B) on the [['wassname/ultrachat_200k_filtered']](https://huggingface.co/datasets/['wassname/ultrachat_200k_filtered']) dataset. +It has been trained using [TRL](https://github.com/huggingface/trl). + + +Why? because experiments with DPO require a SFT model, this means you can't use base or instruction tuned you need an intermediate model such as https://huggingface.co/allenai/Olmo-3-7B-Think-SFT + +## 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="None", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + +[Visualize in Weights & Biases](https://wandb.ai/wassname/huggingface/runs/82mx7iry) + +This model was trained with SFT. + +### Framework versions + +- TRL: 0.12.1 +- Transformers: 4.52.4 +- Pytorch: 2.7.0 +- Datasets: 3.6.0 +- Tokenizers: 0.21.1 + +## 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}} +} +``` \ No newline at end of file diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..03047ae --- /dev/null +++ b/all_results.json @@ -0,0 +1,14 @@ +{ + "epoch": 1.0, + "eval_loss": 1.1679222583770752, + "eval_runtime": 577.8173, + "eval_samples": 13187, + "eval_samples_per_second": 11.824, + "eval_steps_per_second": 3.942, + "total_flos": 2.1312002805936947e+18, + "train_loss": 1.184760999939929, + "train_runtime": 31570.962, + "train_samples": 117772, + "train_samples_per_second": 1.949, + "train_steps_per_second": 0.122 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..39bd0c9 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,5 @@ +{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|> + +'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|> + +' }}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..8cac94b --- /dev/null +++ b/config.json @@ -0,0 +1,39 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 24, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.52.4", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000..0b73a76 --- /dev/null +++ b/eval_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 1.0, + "eval_loss": 1.1679222583770752, + "eval_runtime": 577.8173, + "eval_samples": 13187, + "eval_samples_per_second": 11.824, + "eval_steps_per_second": 3.942 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..bdc177f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.52.4" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..baa4416 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87454adfa9087bb99a9c16f37028aa9b4d5cf0ff96a9661e283f3e6b9de9ad30 +size 4965799096 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..1eedfec --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff6705b01f45224d77d9251e47d524e407423886f0749849c0cec72529218f7d +size 1459729952 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d3a1f0f --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,261 @@ +{ + "metadata": { + "total_size": 6425499648 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..e926562 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,33 @@ +{ + "additional_special_tokens": [ + "<|start_of_thinking|>", + "<|end_of_thinking|>", + "<|start_of_tools|>", + "<|end_of_tools|>", + "<|start_of_tool_calls|>", + "<|end_of_tool_calls|>", + "<|start_of_tool_results|>", + "<|end_of_tool_results|>" + ], + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..7eab83e --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f9cda4d9f8a47b66946a890ac3d4923666dad6e7909609db38a7778694344d +size 17209945 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..10a2e58 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2073 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|start_of_thinking|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|end_of_thinking|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|start_of_tools|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|end_of_tools|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|start_of_tool_calls|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|end_of_tool_calls|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|start_of_tool_results|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|end_of_tool_results|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|start_of_thinking|>", + "<|end_of_thinking|>", + "<|start_of_tools|>", + "<|end_of_tools|>", + "<|start_of_tool_calls|>", + "<|end_of_tool_calls|>", + "<|start_of_tool_results|>", + "<|end_of_tool_results|>" + ], + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 2048, + "pad_token": "<|finetune_right_pad_id|>", + "tokenizer_class": "PreTrainedTokenizer" +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..10a0d93 --- /dev/null +++ b/train_results.json @@ -0,0 +1,9 @@ +{ + "epoch": 1.0, + "total_flos": 2.1312002805936947e+18, + "train_loss": 1.184760999939929, + "train_runtime": 31570.962, + "train_samples": 117772, + "train_samples_per_second": 1.949, + "train_steps_per_second": 0.122 +} \ No newline at end of file diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..b585a33 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,5585 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 200, + "global_step": 3846, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.000260035754916301, + "grad_norm": 5.25, + "learning_rate": 0.0, + "loss": 1.5204, + "step": 1 + }, + { + "epoch": 0.001300178774581505, + "grad_norm": 5.6875, + "learning_rate": 2.077922077922078e-07, + "loss": 1.6753, + "step": 5 + }, + { + "epoch": 0.00260035754916301, + "grad_norm": 8.5, + "learning_rate": 4.675324675324676e-07, + "loss": 1.5933, + "step": 10 + }, + { + "epoch": 0.0039005363237445147, + "grad_norm": 18.25, + "learning_rate": 7.272727272727273e-07, + "loss": 1.5821, + "step": 15 + }, + { + "epoch": 0.00520071509832602, + "grad_norm": 6.15625, + "learning_rate": 9.870129870129872e-07, + "loss": 1.5405, + "step": 20 + }, + { + "epoch": 0.006500893872907525, + "grad_norm": 5.25, + "learning_rate": 1.2467532467532468e-06, + "loss": 1.6146, + "step": 25 + }, + { + "epoch": 0.0078010726474890294, + "grad_norm": 4.15625, + "learning_rate": 1.5064935064935066e-06, + "loss": 1.5282, + "step": 30 + }, + { + "epoch": 0.009101251422070534, + "grad_norm": 4.5625, + "learning_rate": 1.7662337662337665e-06, + "loss": 1.6264, + "step": 35 + }, + { + "epoch": 0.01040143019665204, + "grad_norm": 4.75, + "learning_rate": 2.0259740259740263e-06, + "loss": 1.53, + "step": 40 + }, + { + "epoch": 0.011701608971233545, + "grad_norm": 4.53125, + "learning_rate": 2.285714285714286e-06, + "loss": 1.5046, + "step": 45 + }, + { + "epoch": 0.01300178774581505, + "grad_norm": 3.5, + "learning_rate": 2.5454545454545456e-06, + "loss": 1.5772, + "step": 50 + }, + { + "epoch": 0.014301966520396555, + "grad_norm": 2.84375, + "learning_rate": 2.8051948051948052e-06, + "loss": 1.5543, + "step": 55 + }, + { + "epoch": 0.015602145294978059, + "grad_norm": 2.84375, + "learning_rate": 3.0649350649350653e-06, + "loss": 1.5663, + "step": 60 + }, + { + "epoch": 0.016902324069559563, + "grad_norm": 2.40625, + "learning_rate": 3.324675324675325e-06, + "loss": 1.5217, + "step": 65 + }, + { + "epoch": 0.01820250284414107, + "grad_norm": 2.15625, + "learning_rate": 3.584415584415585e-06, + "loss": 1.4673, + "step": 70 + }, + { + "epoch": 0.019502681618722574, + "grad_norm": 2.6875, + "learning_rate": 3.844155844155845e-06, + "loss": 1.5448, + "step": 75 + }, + { + "epoch": 0.02080286039330408, + "grad_norm": 2.40625, + "learning_rate": 4.103896103896105e-06, + "loss": 1.515, + "step": 80 + }, + { + "epoch": 0.022103039167885585, + "grad_norm": 2.15625, + "learning_rate": 4.363636363636364e-06, + "loss": 1.5072, + "step": 85 + }, + { + "epoch": 0.02340321794246709, + "grad_norm": 2.140625, + "learning_rate": 4.623376623376624e-06, + "loss": 1.4343, + "step": 90 + }, + { + "epoch": 0.024703396717048593, + "grad_norm": 1.984375, + "learning_rate": 4.883116883116883e-06, + "loss": 1.4416, + "step": 95 + }, + { + "epoch": 0.0260035754916301, + "grad_norm": 2.109375, + "learning_rate": 5.142857142857142e-06, + "loss": 1.4342, + "step": 100 + }, + { + "epoch": 0.027303754266211604, + "grad_norm": 1.9765625, + "learning_rate": 5.4025974025974024e-06, + "loss": 1.4649, + "step": 105 + }, + { + "epoch": 0.02860393304079311, + "grad_norm": 1.671875, + "learning_rate": 5.6623376623376625e-06, + "loss": 1.3714, + "step": 110 + }, + { + "epoch": 0.029904111815374616, + "grad_norm": 1.859375, + "learning_rate": 5.9220779220779226e-06, + "loss": 1.4987, + "step": 115 + }, + { + "epoch": 0.031204290589956118, + "grad_norm": 1.734375, + "learning_rate": 6.181818181818182e-06, + "loss": 1.3712, + "step": 120 + }, + { + "epoch": 0.03250446936453762, + "grad_norm": 1.765625, + "learning_rate": 6.441558441558442e-06, + "loss": 1.3568, + "step": 125 + }, + { + "epoch": 0.033804648139119126, + "grad_norm": 1.84375, + "learning_rate": 6.701298701298702e-06, + "loss": 1.3799, + "step": 130 + }, + { + "epoch": 0.035104826913700635, + "grad_norm": 1.71875, + "learning_rate": 6.961038961038962e-06, + "loss": 1.2913, + "step": 135 + }, + { + "epoch": 0.03640500568828214, + "grad_norm": 1.734375, + "learning_rate": 7.220779220779221e-06, + "loss": 1.3968, + "step": 140 + }, + { + "epoch": 0.037705184462863646, + "grad_norm": 1.734375, + "learning_rate": 7.480519480519481e-06, + "loss": 1.3804, + "step": 145 + }, + { + "epoch": 0.03900536323744515, + "grad_norm": 1.796875, + "learning_rate": 7.74025974025974e-06, + "loss": 1.3666, + "step": 150 + }, + { + "epoch": 0.04030554201202665, + "grad_norm": 1.796875, + "learning_rate": 8.000000000000001e-06, + "loss": 1.3184, + "step": 155 + }, + { + "epoch": 0.04160572078660816, + "grad_norm": 1.671875, + "learning_rate": 8.25974025974026e-06, + "loss": 1.2788, + "step": 160 + }, + { + "epoch": 0.04290589956118966, + "grad_norm": 1.828125, + "learning_rate": 8.51948051948052e-06, + "loss": 1.3343, + "step": 165 + }, + { + "epoch": 0.04420607833577117, + "grad_norm": 1.859375, + "learning_rate": 8.779220779220779e-06, + "loss": 1.3861, + "step": 170 + }, + { + "epoch": 0.04550625711035267, + "grad_norm": 1.7421875, + "learning_rate": 9.03896103896104e-06, + "loss": 1.2976, + "step": 175 + }, + { + "epoch": 0.04680643588493418, + "grad_norm": 4.125, + "learning_rate": 9.298701298701299e-06, + "loss": 1.2974, + "step": 180 + }, + { + "epoch": 0.048106614659515684, + "grad_norm": 1.6015625, + "learning_rate": 9.558441558441558e-06, + "loss": 1.2776, + "step": 185 + }, + { + "epoch": 0.049406793434097186, + "grad_norm": 1.8671875, + "learning_rate": 9.81818181818182e-06, + "loss": 1.3431, + "step": 190 + }, + { + "epoch": 0.050706972208678695, + "grad_norm": 1.6640625, + "learning_rate": 1.0077922077922078e-05, + "loss": 1.2846, + "step": 195 + }, + { + "epoch": 0.0520071509832602, + "grad_norm": 1.7265625, + "learning_rate": 1.0337662337662338e-05, + "loss": 1.284, + "step": 200 + }, + { + "epoch": 0.0520071509832602, + "eval_loss": 1.294779896736145, + "eval_runtime": 577.8458, + "eval_samples_per_second": 11.823, + "eval_steps_per_second": 3.942, + "step": 200 + }, + { + "epoch": 0.05330732975784171, + "grad_norm": 1.6328125, + "learning_rate": 1.0597402597402597e-05, + "loss": 1.3109, + "step": 205 + }, + { + "epoch": 0.05460750853242321, + "grad_norm": 1.609375, + "learning_rate": 1.0857142857142858e-05, + "loss": 1.2279, + "step": 210 + }, + { + "epoch": 0.05590768730700471, + "grad_norm": 1.4921875, + "learning_rate": 1.1116883116883117e-05, + "loss": 1.244, + "step": 215 + }, + { + "epoch": 0.05720786608158622, + "grad_norm": 1.5625, + "learning_rate": 1.1376623376623376e-05, + "loss": 1.288, + "step": 220 + }, + { + "epoch": 0.05850804485616772, + "grad_norm": 1.65625, + "learning_rate": 1.1636363636363637e-05, + "loss": 1.2457, + "step": 225 + }, + { + "epoch": 0.05980822363074923, + "grad_norm": 1.515625, + "learning_rate": 1.1896103896103896e-05, + "loss": 1.2354, + "step": 230 + }, + { + "epoch": 0.06110840240533073, + "grad_norm": 1.5, + "learning_rate": 1.2155844155844157e-05, + "loss": 1.2379, + "step": 235 + }, + { + "epoch": 0.062408581179912236, + "grad_norm": 1.4765625, + "learning_rate": 1.2415584415584416e-05, + "loss": 1.2707, + "step": 240 + }, + { + "epoch": 0.06370875995449374, + "grad_norm": 2.09375, + "learning_rate": 1.2675324675324676e-05, + "loss": 1.3032, + "step": 245 + }, + { + "epoch": 0.06500893872907525, + "grad_norm": 1.640625, + "learning_rate": 1.2935064935064937e-05, + "loss": 1.2676, + "step": 250 + }, + { + "epoch": 0.06630911750365676, + "grad_norm": 1.4140625, + "learning_rate": 1.3194805194805196e-05, + "loss": 1.311, + "step": 255 + }, + { + "epoch": 0.06760929627823825, + "grad_norm": 1.6171875, + "learning_rate": 1.3454545454545455e-05, + "loss": 1.2658, + "step": 260 + }, + { + "epoch": 0.06890947505281976, + "grad_norm": 1.40625, + "learning_rate": 1.3714285714285716e-05, + "loss": 1.2508, + "step": 265 + }, + { + "epoch": 0.07020965382740127, + "grad_norm": 1.4296875, + "learning_rate": 1.3974025974025975e-05, + "loss": 1.2345, + "step": 270 + }, + { + "epoch": 0.07150983260198278, + "grad_norm": 2.265625, + "learning_rate": 1.4233766233766236e-05, + "loss": 1.2223, + "step": 275 + }, + { + "epoch": 0.07281001137656427, + "grad_norm": 1.40625, + "learning_rate": 1.4493506493506495e-05, + "loss": 1.2487, + "step": 280 + }, + { + "epoch": 0.07411019015114578, + "grad_norm": 1.453125, + "learning_rate": 1.4753246753246754e-05, + "loss": 1.1905, + "step": 285 + }, + { + "epoch": 0.07541036892572729, + "grad_norm": 1.5859375, + "learning_rate": 1.5012987012987015e-05, + "loss": 1.3005, + "step": 290 + }, + { + "epoch": 0.07671054770030879, + "grad_norm": 1.4453125, + "learning_rate": 1.5272727272727276e-05, + "loss": 1.28, + "step": 295 + }, + { + "epoch": 0.0780107264748903, + "grad_norm": 1.5625, + "learning_rate": 1.5532467532467534e-05, + "loss": 1.2268, + "step": 300 + }, + { + "epoch": 0.0793109052494718, + "grad_norm": 1.59375, + "learning_rate": 1.5792207792207795e-05, + "loss": 1.2504, + "step": 305 + }, + { + "epoch": 0.0806110840240533, + "grad_norm": 1.359375, + "learning_rate": 1.6051948051948056e-05, + "loss": 1.2441, + "step": 310 + }, + { + "epoch": 0.08191126279863481, + "grad_norm": 1.4453125, + "learning_rate": 1.6311688311688313e-05, + "loss": 1.2219, + "step": 315 + }, + { + "epoch": 0.08321144157321632, + "grad_norm": 1.578125, + "learning_rate": 1.6571428571428574e-05, + "loss": 1.2467, + "step": 320 + }, + { + "epoch": 0.08451162034779783, + "grad_norm": 1.3984375, + "learning_rate": 1.683116883116883e-05, + "loss": 1.2455, + "step": 325 + }, + { + "epoch": 0.08581179912237932, + "grad_norm": 1.5390625, + "learning_rate": 1.7090909090909092e-05, + "loss": 1.1899, + "step": 330 + }, + { + "epoch": 0.08711197789696083, + "grad_norm": 1.34375, + "learning_rate": 1.735064935064935e-05, + "loss": 1.2434, + "step": 335 + }, + { + "epoch": 0.08841215667154234, + "grad_norm": 1.3671875, + "learning_rate": 1.761038961038961e-05, + "loss": 1.2047, + "step": 340 + }, + { + "epoch": 0.08971233544612384, + "grad_norm": 1.484375, + "learning_rate": 1.7870129870129872e-05, + "loss": 1.2164, + "step": 345 + }, + { + "epoch": 0.09101251422070535, + "grad_norm": 1.6328125, + "learning_rate": 1.812987012987013e-05, + "loss": 1.2265, + "step": 350 + }, + { + "epoch": 0.09231269299528685, + "grad_norm": 1.40625, + "learning_rate": 1.838961038961039e-05, + "loss": 1.243, + "step": 355 + }, + { + "epoch": 0.09361287176986836, + "grad_norm": 1.6640625, + "learning_rate": 1.864935064935065e-05, + "loss": 1.2475, + "step": 360 + }, + { + "epoch": 0.09491305054444986, + "grad_norm": 1.4453125, + "learning_rate": 1.8909090909090912e-05, + "loss": 1.2459, + "step": 365 + }, + { + "epoch": 0.09621322931903137, + "grad_norm": 1.4375, + "learning_rate": 1.916883116883117e-05, + "loss": 1.2937, + "step": 370 + }, + { + "epoch": 0.09751340809361288, + "grad_norm": 1.5234375, + "learning_rate": 1.942857142857143e-05, + "loss": 1.2286, + "step": 375 + }, + { + "epoch": 0.09881358686819437, + "grad_norm": 1.390625, + "learning_rate": 1.968831168831169e-05, + "loss": 1.2505, + "step": 380 + }, + { + "epoch": 0.10011376564277588, + "grad_norm": 1.5546875, + "learning_rate": 1.994805194805195e-05, + "loss": 1.2724, + "step": 385 + }, + { + "epoch": 0.10141394441735739, + "grad_norm": 1.453125, + "learning_rate": 1.9999934084726765e-05, + "loss": 1.221, + "step": 390 + }, + { + "epoch": 0.10271412319193889, + "grad_norm": 1.5625, + "learning_rate": 1.9999666305418534e-05, + "loss": 1.3084, + "step": 395 + }, + { + "epoch": 0.1040143019665204, + "grad_norm": 1.453125, + "learning_rate": 1.999919254788234e-05, + "loss": 1.239, + "step": 400 + }, + { + "epoch": 0.1040143019665204, + "eval_loss": 1.2270315885543823, + "eval_runtime": 577.8859, + "eval_samples_per_second": 11.822, + "eval_steps_per_second": 3.942, + "step": 400 + }, + { + "epoch": 0.1053144807411019, + "grad_norm": 1.4921875, + "learning_rate": 1.999851282187689e-05, + "loss": 1.2416, + "step": 405 + }, + { + "epoch": 0.10661465951568341, + "grad_norm": 1.421875, + "learning_rate": 1.9997627141403514e-05, + "loss": 1.2305, + "step": 410 + }, + { + "epoch": 0.10791483829026491, + "grad_norm": 1.4140625, + "learning_rate": 1.9996535524705926e-05, + "loss": 1.1928, + "step": 415 + }, + { + "epoch": 0.10921501706484642, + "grad_norm": 1.5078125, + "learning_rate": 1.999523799426979e-05, + "loss": 1.2644, + "step": 420 + }, + { + "epoch": 0.11051519583942793, + "grad_norm": 1.5078125, + "learning_rate": 1.9993734576822303e-05, + "loss": 1.2157, + "step": 425 + }, + { + "epoch": 0.11181537461400942, + "grad_norm": 1.328125, + "learning_rate": 1.9992025303331632e-05, + "loss": 1.2573, + "step": 430 + }, + { + "epoch": 0.11311555338859093, + "grad_norm": 1.390625, + "learning_rate": 1.9990110209006258e-05, + "loss": 1.2262, + "step": 435 + }, + { + "epoch": 0.11441573216317244, + "grad_norm": 1.4375, + "learning_rate": 1.998798933329427e-05, + "loss": 1.2127, + "step": 440 + }, + { + "epoch": 0.11571591093775394, + "grad_norm": 1.3828125, + "learning_rate": 1.998566271988255e-05, + "loss": 1.1727, + "step": 445 + }, + { + "epoch": 0.11701608971233544, + "grad_norm": 1.3984375, + "learning_rate": 1.998313041669587e-05, + "loss": 1.2352, + "step": 450 + }, + { + "epoch": 0.11831626848691695, + "grad_norm": 1.4609375, + "learning_rate": 1.99803924758959e-05, + "loss": 1.1963, + "step": 455 + }, + { + "epoch": 0.11961644726149846, + "grad_norm": 1.4609375, + "learning_rate": 1.9977448953880144e-05, + "loss": 1.2486, + "step": 460 + }, + { + "epoch": 0.12091662603607996, + "grad_norm": 1.34375, + "learning_rate": 1.9974299911280766e-05, + "loss": 1.1692, + "step": 465 + }, + { + "epoch": 0.12221680481066147, + "grad_norm": 1.40625, + "learning_rate": 1.9970945412963356e-05, + "loss": 1.1331, + "step": 470 + }, + { + "epoch": 0.12351698358524298, + "grad_norm": 1.4921875, + "learning_rate": 1.9967385528025577e-05, + "loss": 1.1713, + "step": 475 + }, + { + "epoch": 0.12481716235982447, + "grad_norm": 1.3828125, + "learning_rate": 1.9963620329795762e-05, + "loss": 1.1785, + "step": 480 + }, + { + "epoch": 0.12611734113440598, + "grad_norm": 1.3828125, + "learning_rate": 1.9959649895831378e-05, + "loss": 1.2178, + "step": 485 + }, + { + "epoch": 0.12741751990898748, + "grad_norm": 1.375, + "learning_rate": 1.9955474307917453e-05, + "loss": 1.2124, + "step": 490 + }, + { + "epoch": 0.128717698683569, + "grad_norm": 1.4765625, + "learning_rate": 1.995109365206488e-05, + "loss": 1.2345, + "step": 495 + }, + { + "epoch": 0.1300178774581505, + "grad_norm": 1.453125, + "learning_rate": 1.9946508018508637e-05, + "loss": 1.2402, + "step": 500 + }, + { + "epoch": 0.131318056232732, + "grad_norm": 1.390625, + "learning_rate": 1.9941717501705945e-05, + "loss": 1.241, + "step": 505 + }, + { + "epoch": 0.1326182350073135, + "grad_norm": 1.4140625, + "learning_rate": 1.9936722200334312e-05, + "loss": 1.1926, + "step": 510 + }, + { + "epoch": 0.133918413781895, + "grad_norm": 1.3671875, + "learning_rate": 1.9931522217289512e-05, + "loss": 1.1603, + "step": 515 + }, + { + "epoch": 0.1352185925564765, + "grad_norm": 1.4375, + "learning_rate": 1.9926117659683437e-05, + "loss": 1.2126, + "step": 520 + }, + { + "epoch": 0.13651877133105803, + "grad_norm": 1.359375, + "learning_rate": 1.992050863884193e-05, + "loss": 1.2186, + "step": 525 + }, + { + "epoch": 0.13781895010563952, + "grad_norm": 1.4765625, + "learning_rate": 1.991469527030246e-05, + "loss": 1.1917, + "step": 530 + }, + { + "epoch": 0.13911912888022104, + "grad_norm": 1.578125, + "learning_rate": 1.9908677673811764e-05, + "loss": 1.1894, + "step": 535 + }, + { + "epoch": 0.14041930765480254, + "grad_norm": 1.40625, + "learning_rate": 1.9902455973323352e-05, + "loss": 1.1932, + "step": 540 + }, + { + "epoch": 0.14171948642938403, + "grad_norm": 1.4140625, + "learning_rate": 1.9896030296994996e-05, + "loss": 1.2742, + "step": 545 + }, + { + "epoch": 0.14301966520396556, + "grad_norm": 1.3359375, + "learning_rate": 1.988940077718605e-05, + "loss": 1.234, + "step": 550 + }, + { + "epoch": 0.14431984397854705, + "grad_norm": 1.390625, + "learning_rate": 1.9882567550454747e-05, + "loss": 1.2243, + "step": 555 + }, + { + "epoch": 0.14562002275312855, + "grad_norm": 1.4765625, + "learning_rate": 1.9875530757555377e-05, + "loss": 1.1907, + "step": 560 + }, + { + "epoch": 0.14692020152771007, + "grad_norm": 1.3515625, + "learning_rate": 1.986829054343539e-05, + "loss": 1.2344, + "step": 565 + }, + { + "epoch": 0.14822038030229157, + "grad_norm": 1.3515625, + "learning_rate": 1.9860847057232407e-05, + "loss": 1.142, + "step": 570 + }, + { + "epoch": 0.14952055907687306, + "grad_norm": 1.40625, + "learning_rate": 1.9853200452271157e-05, + "loss": 1.1788, + "step": 575 + }, + { + "epoch": 0.15082073785145458, + "grad_norm": 1.3828125, + "learning_rate": 1.9845350886060314e-05, + "loss": 1.1476, + "step": 580 + }, + { + "epoch": 0.15212091662603608, + "grad_norm": 1.34375, + "learning_rate": 1.9837298520289238e-05, + "loss": 1.1865, + "step": 585 + }, + { + "epoch": 0.15342109540061757, + "grad_norm": 1.359375, + "learning_rate": 1.9829043520824676e-05, + "loss": 1.258, + "step": 590 + }, + { + "epoch": 0.1547212741751991, + "grad_norm": 1.3203125, + "learning_rate": 1.9820586057707314e-05, + "loss": 1.1719, + "step": 595 + }, + { + "epoch": 0.1560214529497806, + "grad_norm": 1.3203125, + "learning_rate": 1.9811926305148292e-05, + "loss": 1.2676, + "step": 600 + }, + { + "epoch": 0.1560214529497806, + "eval_loss": 1.2073785066604614, + "eval_runtime": 578.0178, + "eval_samples_per_second": 11.82, + "eval_steps_per_second": 3.941, + "step": 600 + }, + { + "epoch": 0.1573216317243621, + "grad_norm": 1.421875, + "learning_rate": 1.980306444152561e-05, + "loss": 1.2199, + "step": 605 + }, + { + "epoch": 0.1586218104989436, + "grad_norm": 1.34375, + "learning_rate": 1.979400064938046e-05, + "loss": 1.2054, + "step": 610 + }, + { + "epoch": 0.1599219892735251, + "grad_norm": 1.390625, + "learning_rate": 1.9784735115413453e-05, + "loss": 1.1933, + "step": 615 + }, + { + "epoch": 0.1612221680481066, + "grad_norm": 1.40625, + "learning_rate": 1.9775268030480785e-05, + "loss": 1.1606, + "step": 620 + }, + { + "epoch": 0.16252234682268812, + "grad_norm": 1.3984375, + "learning_rate": 1.97655995895903e-05, + "loss": 1.2031, + "step": 625 + }, + { + "epoch": 0.16382252559726962, + "grad_norm": 1.3671875, + "learning_rate": 1.975572999189748e-05, + "loss": 1.17, + "step": 630 + }, + { + "epoch": 0.16512270437185114, + "grad_norm": 1.2890625, + "learning_rate": 1.974565944070133e-05, + "loss": 1.1652, + "step": 635 + }, + { + "epoch": 0.16642288314643264, + "grad_norm": 1.3984375, + "learning_rate": 1.9735388143440203e-05, + "loss": 1.2398, + "step": 640 + }, + { + "epoch": 0.16772306192101413, + "grad_norm": 1.3046875, + "learning_rate": 1.972491631168752e-05, + "loss": 1.1702, + "step": 645 + }, + { + "epoch": 0.16902324069559566, + "grad_norm": 1.46875, + "learning_rate": 1.971424416114741e-05, + "loss": 1.2149, + "step": 650 + }, + { + "epoch": 0.17032341947017715, + "grad_norm": 1.4609375, + "learning_rate": 1.9703371911650278e-05, + "loss": 1.1942, + "step": 655 + }, + { + "epoch": 0.17162359824475865, + "grad_norm": 1.3984375, + "learning_rate": 1.9692299787148265e-05, + "loss": 1.2498, + "step": 660 + }, + { + "epoch": 0.17292377701934017, + "grad_norm": 1.3515625, + "learning_rate": 1.968102801571064e-05, + "loss": 1.2154, + "step": 665 + }, + { + "epoch": 0.17422395579392166, + "grad_norm": 1.390625, + "learning_rate": 1.96695568295191e-05, + "loss": 1.1647, + "step": 670 + }, + { + "epoch": 0.17552413456850316, + "grad_norm": 1.5703125, + "learning_rate": 1.965788646486299e-05, + "loss": 1.1973, + "step": 675 + }, + { + "epoch": 0.17682431334308468, + "grad_norm": 1.375, + "learning_rate": 1.964601716213444e-05, + "loss": 1.1358, + "step": 680 + }, + { + "epoch": 0.17812449211766618, + "grad_norm": 1.375, + "learning_rate": 1.9633949165823395e-05, + "loss": 1.2036, + "step": 685 + }, + { + "epoch": 0.17942467089224767, + "grad_norm": 1.3671875, + "learning_rate": 1.9621682724512606e-05, + "loss": 1.1692, + "step": 690 + }, + { + "epoch": 0.1807248496668292, + "grad_norm": 1.390625, + "learning_rate": 1.9609218090872488e-05, + "loss": 1.2024, + "step": 695 + }, + { + "epoch": 0.1820250284414107, + "grad_norm": 1.2890625, + "learning_rate": 1.9596555521655918e-05, + "loss": 1.132, + "step": 700 + }, + { + "epoch": 0.1833252072159922, + "grad_norm": 1.3359375, + "learning_rate": 1.9583695277692965e-05, + "loss": 1.1681, + "step": 705 + }, + { + "epoch": 0.1846253859905737, + "grad_norm": 1.28125, + "learning_rate": 1.957063762388549e-05, + "loss": 1.2149, + "step": 710 + }, + { + "epoch": 0.1859255647651552, + "grad_norm": 1.4140625, + "learning_rate": 1.955738282920171e-05, + "loss": 1.2244, + "step": 715 + }, + { + "epoch": 0.18722574353973673, + "grad_norm": 1.4296875, + "learning_rate": 1.9543931166670638e-05, + "loss": 1.2104, + "step": 720 + }, + { + "epoch": 0.18852592231431822, + "grad_norm": 1.328125, + "learning_rate": 1.9530282913376497e-05, + "loss": 1.1897, + "step": 725 + }, + { + "epoch": 0.18982610108889972, + "grad_norm": 1.3359375, + "learning_rate": 1.9516438350452966e-05, + "loss": 1.1736, + "step": 730 + }, + { + "epoch": 0.19112627986348124, + "grad_norm": 1.3125, + "learning_rate": 1.9502397763077406e-05, + "loss": 1.1593, + "step": 735 + }, + { + "epoch": 0.19242645863806274, + "grad_norm": 1.4453125, + "learning_rate": 1.9488161440465007e-05, + "loss": 1.1957, + "step": 740 + }, + { + "epoch": 0.19372663741264423, + "grad_norm": 1.4375, + "learning_rate": 1.9473729675862807e-05, + "loss": 1.1894, + "step": 745 + }, + { + "epoch": 0.19502681618722575, + "grad_norm": 1.375, + "learning_rate": 1.945910276654365e-05, + "loss": 1.205, + "step": 750 + }, + { + "epoch": 0.19632699496180725, + "grad_norm": 1.359375, + "learning_rate": 1.9444281013800075e-05, + "loss": 1.1771, + "step": 755 + }, + { + "epoch": 0.19762717373638874, + "grad_norm": 1.3984375, + "learning_rate": 1.9429264722938113e-05, + "loss": 1.2281, + "step": 760 + }, + { + "epoch": 0.19892735251097027, + "grad_norm": 1.25, + "learning_rate": 1.941405420327098e-05, + "loss": 1.1867, + "step": 765 + }, + { + "epoch": 0.20022753128555176, + "grad_norm": 1.3359375, + "learning_rate": 1.939864976811272e-05, + "loss": 1.1832, + "step": 770 + }, + { + "epoch": 0.20152771006013326, + "grad_norm": 1.3125, + "learning_rate": 1.9383051734771747e-05, + "loss": 1.2205, + "step": 775 + }, + { + "epoch": 0.20282788883471478, + "grad_norm": 1.3125, + "learning_rate": 1.936726042454431e-05, + "loss": 1.1497, + "step": 780 + }, + { + "epoch": 0.20412806760929628, + "grad_norm": 1.453125, + "learning_rate": 1.9351276162707873e-05, + "loss": 1.228, + "step": 785 + }, + { + "epoch": 0.20542824638387777, + "grad_norm": 1.2734375, + "learning_rate": 1.933509927851442e-05, + "loss": 1.1728, + "step": 790 + }, + { + "epoch": 0.2067284251584593, + "grad_norm": 1.375, + "learning_rate": 1.9318730105183654e-05, + "loss": 1.1638, + "step": 795 + }, + { + "epoch": 0.2080286039330408, + "grad_norm": 1.421875, + "learning_rate": 1.9302168979896162e-05, + "loss": 1.1911, + "step": 800 + }, + { + "epoch": 0.2080286039330408, + "eval_loss": 1.1971442699432373, + "eval_runtime": 577.9872, + "eval_samples_per_second": 11.82, + "eval_steps_per_second": 3.941, + "step": 800 + }, + { + "epoch": 0.20932878270762229, + "grad_norm": 1.3203125, + "learning_rate": 1.928541624378646e-05, + "loss": 1.1981, + "step": 805 + }, + { + "epoch": 0.2106289614822038, + "grad_norm": 1.3125, + "learning_rate": 1.9268472241935944e-05, + "loss": 1.1914, + "step": 810 + }, + { + "epoch": 0.2119291402567853, + "grad_norm": 1.4453125, + "learning_rate": 1.925133732336581e-05, + "loss": 1.2269, + "step": 815 + }, + { + "epoch": 0.21322931903136683, + "grad_norm": 1.40625, + "learning_rate": 1.923401184102985e-05, + "loss": 1.1337, + "step": 820 + }, + { + "epoch": 0.21452949780594832, + "grad_norm": 1.4140625, + "learning_rate": 1.9216496151807197e-05, + "loss": 1.2179, + "step": 825 + }, + { + "epoch": 0.21582967658052982, + "grad_norm": 1.3671875, + "learning_rate": 1.9198790616494942e-05, + "loss": 1.1693, + "step": 830 + }, + { + "epoch": 0.21712985535511134, + "grad_norm": 1.5078125, + "learning_rate": 1.918089559980074e-05, + "loss": 1.1724, + "step": 835 + }, + { + "epoch": 0.21843003412969283, + "grad_norm": 1.5078125, + "learning_rate": 1.9162811470335273e-05, + "loss": 1.2139, + "step": 840 + }, + { + "epoch": 0.21973021290427433, + "grad_norm": 1.359375, + "learning_rate": 1.914453860060467e-05, + "loss": 1.1259, + "step": 845 + }, + { + "epoch": 0.22103039167885585, + "grad_norm": 1.3828125, + "learning_rate": 1.912607736700281e-05, + "loss": 1.1635, + "step": 850 + }, + { + "epoch": 0.22233057045343735, + "grad_norm": 1.4140625, + "learning_rate": 1.910742814980362e-05, + "loss": 1.2043, + "step": 855 + }, + { + "epoch": 0.22363074922801884, + "grad_norm": 1.3515625, + "learning_rate": 1.9088591333153177e-05, + "loss": 1.1439, + "step": 860 + }, + { + "epoch": 0.22493092800260037, + "grad_norm": 1.296875, + "learning_rate": 1.906956730506184e-05, + "loss": 1.1846, + "step": 865 + }, + { + "epoch": 0.22623110677718186, + "grad_norm": 1.40625, + "learning_rate": 1.9050356457396253e-05, + "loss": 1.1619, + "step": 870 + }, + { + "epoch": 0.22753128555176336, + "grad_norm": 1.375, + "learning_rate": 1.9030959185871252e-05, + "loss": 1.1945, + "step": 875 + }, + { + "epoch": 0.22883146432634488, + "grad_norm": 1.40625, + "learning_rate": 1.9011375890041727e-05, + "loss": 1.1457, + "step": 880 + }, + { + "epoch": 0.23013164310092638, + "grad_norm": 1.3828125, + "learning_rate": 1.8991606973294402e-05, + "loss": 1.1881, + "step": 885 + }, + { + "epoch": 0.23143182187550787, + "grad_norm": 1.4765625, + "learning_rate": 1.897165284283951e-05, + "loss": 1.2191, + "step": 890 + }, + { + "epoch": 0.2327320006500894, + "grad_norm": 1.3515625, + "learning_rate": 1.8951513909702406e-05, + "loss": 1.1946, + "step": 895 + }, + { + "epoch": 0.2340321794246709, + "grad_norm": 1.359375, + "learning_rate": 1.893119058871511e-05, + "loss": 1.1576, + "step": 900 + }, + { + "epoch": 0.23533235819925238, + "grad_norm": 1.3984375, + "learning_rate": 1.891068329850776e-05, + "loss": 1.2013, + "step": 905 + }, + { + "epoch": 0.2366325369738339, + "grad_norm": 1.4375, + "learning_rate": 1.8889992461499974e-05, + "loss": 1.2041, + "step": 910 + }, + { + "epoch": 0.2379327157484154, + "grad_norm": 1.3515625, + "learning_rate": 1.8869118503892173e-05, + "loss": 1.1634, + "step": 915 + }, + { + "epoch": 0.23923289452299693, + "grad_norm": 1.390625, + "learning_rate": 1.8848061855656786e-05, + "loss": 1.2705, + "step": 920 + }, + { + "epoch": 0.24053307329757842, + "grad_norm": 1.328125, + "learning_rate": 1.882682295052939e-05, + "loss": 1.1535, + "step": 925 + }, + { + "epoch": 0.24183325207215992, + "grad_norm": 1.3125, + "learning_rate": 1.8805402225999795e-05, + "loss": 1.1677, + "step": 930 + }, + { + "epoch": 0.24313343084674144, + "grad_norm": 1.3359375, + "learning_rate": 1.8783800123303008e-05, + "loss": 1.1444, + "step": 935 + }, + { + "epoch": 0.24443360962132293, + "grad_norm": 1.375, + "learning_rate": 1.8762017087410162e-05, + "loss": 1.184, + "step": 940 + }, + { + "epoch": 0.24573378839590443, + "grad_norm": 1.3515625, + "learning_rate": 1.8740053567019344e-05, + "loss": 1.1915, + "step": 945 + }, + { + "epoch": 0.24703396717048595, + "grad_norm": 1.3203125, + "learning_rate": 1.871791001454635e-05, + "loss": 1.0851, + "step": 950 + }, + { + "epoch": 0.24833414594506745, + "grad_norm": 1.3671875, + "learning_rate": 1.8695586886115372e-05, + "loss": 1.2117, + "step": 955 + }, + { + "epoch": 0.24963432471964894, + "grad_norm": 1.2578125, + "learning_rate": 1.86730846415496e-05, + "loss": 1.1424, + "step": 960 + }, + { + "epoch": 0.25093450349423047, + "grad_norm": 1.3359375, + "learning_rate": 1.865040374436174e-05, + "loss": 1.1457, + "step": 965 + }, + { + "epoch": 0.25223468226881196, + "grad_norm": 1.3125, + "learning_rate": 1.862754466174449e-05, + "loss": 1.1142, + "step": 970 + }, + { + "epoch": 0.25353486104339346, + "grad_norm": 1.3671875, + "learning_rate": 1.8604507864560895e-05, + "loss": 1.1479, + "step": 975 + }, + { + "epoch": 0.25483503981797495, + "grad_norm": 1.3515625, + "learning_rate": 1.858129382733465e-05, + "loss": 1.1608, + "step": 980 + }, + { + "epoch": 0.2561352185925565, + "grad_norm": 1.3046875, + "learning_rate": 1.855790302824034e-05, + "loss": 1.1776, + "step": 985 + }, + { + "epoch": 0.257435397367138, + "grad_norm": 1.390625, + "learning_rate": 1.8534335949093586e-05, + "loss": 1.1316, + "step": 990 + }, + { + "epoch": 0.2587355761417195, + "grad_norm": 1.3828125, + "learning_rate": 1.8510593075341093e-05, + "loss": 1.2005, + "step": 995 + }, + { + "epoch": 0.260035754916301, + "grad_norm": 1.3671875, + "learning_rate": 1.84866748960507e-05, + "loss": 1.1766, + "step": 1000 + }, + { + "epoch": 0.260035754916301, + "eval_loss": 1.1860284805297852, + "eval_runtime": 578.04, + "eval_samples_per_second": 11.819, + "eval_steps_per_second": 3.941, + "step": 1000 + }, + { + "epoch": 0.2613359336908825, + "grad_norm": 1.5, + "learning_rate": 1.846258190390125e-05, + "loss": 1.1841, + "step": 1005 + }, + { + "epoch": 0.262636112465464, + "grad_norm": 1.3671875, + "learning_rate": 1.8438314595172502e-05, + "loss": 1.1468, + "step": 1010 + }, + { + "epoch": 0.26393629124004553, + "grad_norm": 1.3515625, + "learning_rate": 1.8413873469734856e-05, + "loss": 1.1377, + "step": 1015 + }, + { + "epoch": 0.265236470014627, + "grad_norm": 1.34375, + "learning_rate": 1.8389259031039083e-05, + "loss": 1.0577, + "step": 1020 + }, + { + "epoch": 0.2665366487892085, + "grad_norm": 1.421875, + "learning_rate": 1.8364471786105946e-05, + "loss": 1.1714, + "step": 1025 + }, + { + "epoch": 0.26783682756379, + "grad_norm": 1.609375, + "learning_rate": 1.833951224551576e-05, + "loss": 1.1308, + "step": 1030 + }, + { + "epoch": 0.2691370063383715, + "grad_norm": 1.328125, + "learning_rate": 1.8314380923397884e-05, + "loss": 1.129, + "step": 1035 + }, + { + "epoch": 0.270437185112953, + "grad_norm": 1.359375, + "learning_rate": 1.82890783374201e-05, + "loss": 1.2, + "step": 1040 + }, + { + "epoch": 0.27173736388753456, + "grad_norm": 1.3828125, + "learning_rate": 1.8263605008777995e-05, + "loss": 1.1621, + "step": 1045 + }, + { + "epoch": 0.27303754266211605, + "grad_norm": 1.3046875, + "learning_rate": 1.823796146218418e-05, + "loss": 1.1301, + "step": 1050 + }, + { + "epoch": 0.27433772143669755, + "grad_norm": 1.3125, + "learning_rate": 1.821214822585751e-05, + "loss": 1.1889, + "step": 1055 + }, + { + "epoch": 0.27563790021127904, + "grad_norm": 1.3046875, + "learning_rate": 1.81861658315122e-05, + "loss": 1.1556, + "step": 1060 + }, + { + "epoch": 0.27693807898586054, + "grad_norm": 1.6640625, + "learning_rate": 1.8160014814346854e-05, + "loss": 1.141, + "step": 1065 + }, + { + "epoch": 0.2782382577604421, + "grad_norm": 1.375, + "learning_rate": 1.813369571303348e-05, + "loss": 1.219, + "step": 1070 + }, + { + "epoch": 0.2795384365350236, + "grad_norm": 1.3359375, + "learning_rate": 1.8107209069706342e-05, + "loss": 1.1646, + "step": 1075 + }, + { + "epoch": 0.2808386153096051, + "grad_norm": 1.34375, + "learning_rate": 1.8080555429950832e-05, + "loss": 1.1884, + "step": 1080 + }, + { + "epoch": 0.2821387940841866, + "grad_norm": 1.3359375, + "learning_rate": 1.8053735342792227e-05, + "loss": 1.1783, + "step": 1085 + }, + { + "epoch": 0.28343897285876807, + "grad_norm": 1.296875, + "learning_rate": 1.8026749360684358e-05, + "loss": 1.2179, + "step": 1090 + }, + { + "epoch": 0.28473915163334956, + "grad_norm": 1.390625, + "learning_rate": 1.7999598039498255e-05, + "loss": 1.1706, + "step": 1095 + }, + { + "epoch": 0.2860393304079311, + "grad_norm": 1.515625, + "learning_rate": 1.7972281938510678e-05, + "loss": 1.1852, + "step": 1100 + }, + { + "epoch": 0.2873395091825126, + "grad_norm": 1.359375, + "learning_rate": 1.7944801620392617e-05, + "loss": 1.1764, + "step": 1105 + }, + { + "epoch": 0.2886396879570941, + "grad_norm": 1.2734375, + "learning_rate": 1.791715765119768e-05, + "loss": 1.1539, + "step": 1110 + }, + { + "epoch": 0.2899398667316756, + "grad_norm": 1.328125, + "learning_rate": 1.788935060035045e-05, + "loss": 1.1427, + "step": 1115 + }, + { + "epoch": 0.2912400455062571, + "grad_norm": 1.296875, + "learning_rate": 1.7861381040634745e-05, + "loss": 1.1732, + "step": 1120 + }, + { + "epoch": 0.2925402242808386, + "grad_norm": 1.3359375, + "learning_rate": 1.7833249548181822e-05, + "loss": 1.1609, + "step": 1125 + }, + { + "epoch": 0.29384040305542014, + "grad_norm": 1.3046875, + "learning_rate": 1.780495670245852e-05, + "loss": 1.1417, + "step": 1130 + }, + { + "epoch": 0.29514058183000164, + "grad_norm": 1.375, + "learning_rate": 1.7776503086255306e-05, + "loss": 1.1847, + "step": 1135 + }, + { + "epoch": 0.29644076060458313, + "grad_norm": 1.3671875, + "learning_rate": 1.774788928567428e-05, + "loss": 1.1358, + "step": 1140 + }, + { + "epoch": 0.2977409393791646, + "grad_norm": 1.34375, + "learning_rate": 1.7719115890117108e-05, + "loss": 1.1387, + "step": 1145 + }, + { + "epoch": 0.2990411181537461, + "grad_norm": 1.484375, + "learning_rate": 1.7690183492272868e-05, + "loss": 1.2286, + "step": 1150 + }, + { + "epoch": 0.3003412969283277, + "grad_norm": 1.5234375, + "learning_rate": 1.7661092688105847e-05, + "loss": 1.1997, + "step": 1155 + }, + { + "epoch": 0.30164147570290917, + "grad_norm": 1.3515625, + "learning_rate": 1.763184407684328e-05, + "loss": 1.1797, + "step": 1160 + }, + { + "epoch": 0.30294165447749066, + "grad_norm": 1.375, + "learning_rate": 1.7602438260962977e-05, + "loss": 1.1671, + "step": 1165 + }, + { + "epoch": 0.30424183325207216, + "grad_norm": 1.3359375, + "learning_rate": 1.7572875846180934e-05, + "loss": 1.1743, + "step": 1170 + }, + { + "epoch": 0.30554201202665365, + "grad_norm": 1.390625, + "learning_rate": 1.7543157441438858e-05, + "loss": 1.1965, + "step": 1175 + }, + { + "epoch": 0.30684219080123515, + "grad_norm": 1.359375, + "learning_rate": 1.7513283658891606e-05, + "loss": 1.1047, + "step": 1180 + }, + { + "epoch": 0.3081423695758167, + "grad_norm": 1.3046875, + "learning_rate": 1.7483255113894587e-05, + "loss": 1.1886, + "step": 1185 + }, + { + "epoch": 0.3094425483503982, + "grad_norm": 1.296875, + "learning_rate": 1.74530724249911e-05, + "loss": 1.1184, + "step": 1190 + }, + { + "epoch": 0.3107427271249797, + "grad_norm": 2.046875, + "learning_rate": 1.7422736213899563e-05, + "loss": 1.1979, + "step": 1195 + }, + { + "epoch": 0.3120429058995612, + "grad_norm": 1.2734375, + "learning_rate": 1.7392247105500733e-05, + "loss": 1.1083, + "step": 1200 + }, + { + "epoch": 0.3120429058995612, + "eval_loss": 1.1814509630203247, + "eval_runtime": 578.0545, + "eval_samples_per_second": 11.819, + "eval_steps_per_second": 3.941, + "step": 1200 + }, + { + "epoch": 0.3133430846741427, + "grad_norm": 1.46875, + "learning_rate": 1.7361605727824814e-05, + "loss": 1.2137, + "step": 1205 + }, + { + "epoch": 0.3146432634487242, + "grad_norm": 1.3984375, + "learning_rate": 1.7330812712038535e-05, + "loss": 1.2345, + "step": 1210 + }, + { + "epoch": 0.3159434422233057, + "grad_norm": 1.390625, + "learning_rate": 1.7299868692432147e-05, + "loss": 1.1602, + "step": 1215 + }, + { + "epoch": 0.3172436209978872, + "grad_norm": 1.453125, + "learning_rate": 1.7268774306406354e-05, + "loss": 1.2263, + "step": 1220 + }, + { + "epoch": 0.3185437997724687, + "grad_norm": 1.3125, + "learning_rate": 1.723753019445918e-05, + "loss": 1.1895, + "step": 1225 + }, + { + "epoch": 0.3198439785470502, + "grad_norm": 1.359375, + "learning_rate": 1.7206137000172777e-05, + "loss": 1.1771, + "step": 1230 + }, + { + "epoch": 0.3211441573216317, + "grad_norm": 1.3046875, + "learning_rate": 1.7174595370200188e-05, + "loss": 1.1801, + "step": 1235 + }, + { + "epoch": 0.3224443360962132, + "grad_norm": 1.4765625, + "learning_rate": 1.7142905954251986e-05, + "loss": 1.1529, + "step": 1240 + }, + { + "epoch": 0.32374451487079475, + "grad_norm": 1.3515625, + "learning_rate": 1.7111069405082937e-05, + "loss": 1.2316, + "step": 1245 + }, + { + "epoch": 0.32504469364537625, + "grad_norm": 1.234375, + "learning_rate": 1.7079086378478518e-05, + "loss": 1.1408, + "step": 1250 + }, + { + "epoch": 0.32634487241995774, + "grad_norm": 1.328125, + "learning_rate": 1.7046957533241427e-05, + "loss": 1.1577, + "step": 1255 + }, + { + "epoch": 0.32764505119453924, + "grad_norm": 1.3125, + "learning_rate": 1.7014683531178015e-05, + "loss": 1.1236, + "step": 1260 + }, + { + "epoch": 0.32894522996912073, + "grad_norm": 1.3203125, + "learning_rate": 1.698226503708463e-05, + "loss": 1.1672, + "step": 1265 + }, + { + "epoch": 0.3302454087437023, + "grad_norm": 1.328125, + "learning_rate": 1.694970271873396e-05, + "loss": 1.1739, + "step": 1270 + }, + { + "epoch": 0.3315455875182838, + "grad_norm": 1.359375, + "learning_rate": 1.6916997246861253e-05, + "loss": 1.1744, + "step": 1275 + }, + { + "epoch": 0.3328457662928653, + "grad_norm": 1.34375, + "learning_rate": 1.6884149295150495e-05, + "loss": 1.2045, + "step": 1280 + }, + { + "epoch": 0.33414594506744677, + "grad_norm": 1.34375, + "learning_rate": 1.6851159540220558e-05, + "loss": 1.1179, + "step": 1285 + }, + { + "epoch": 0.33544612384202827, + "grad_norm": 1.3125, + "learning_rate": 1.6818028661611242e-05, + "loss": 1.2262, + "step": 1290 + }, + { + "epoch": 0.33674630261660976, + "grad_norm": 1.4140625, + "learning_rate": 1.6784757341769288e-05, + "loss": 1.1726, + "step": 1295 + }, + { + "epoch": 0.3380464813911913, + "grad_norm": 1.328125, + "learning_rate": 1.6751346266034315e-05, + "loss": 1.1737, + "step": 1300 + }, + { + "epoch": 0.3393466601657728, + "grad_norm": 1.4921875, + "learning_rate": 1.671779612262471e-05, + "loss": 1.1418, + "step": 1305 + }, + { + "epoch": 0.3406468389403543, + "grad_norm": 1.34375, + "learning_rate": 1.6684107602623438e-05, + "loss": 1.1819, + "step": 1310 + }, + { + "epoch": 0.3419470177149358, + "grad_norm": 1.3828125, + "learning_rate": 1.6650281399963818e-05, + "loss": 1.1842, + "step": 1315 + }, + { + "epoch": 0.3432471964895173, + "grad_norm": 1.3671875, + "learning_rate": 1.661631821141523e-05, + "loss": 1.1729, + "step": 1320 + }, + { + "epoch": 0.3445473752640988, + "grad_norm": 1.3984375, + "learning_rate": 1.6582218736568766e-05, + "loss": 1.2309, + "step": 1325 + }, + { + "epoch": 0.34584755403868034, + "grad_norm": 1.3046875, + "learning_rate": 1.65479836778228e-05, + "loss": 1.1648, + "step": 1330 + }, + { + "epoch": 0.34714773281326183, + "grad_norm": 1.40625, + "learning_rate": 1.6513613740368534e-05, + "loss": 1.215, + "step": 1335 + }, + { + "epoch": 0.34844791158784333, + "grad_norm": 1.3125, + "learning_rate": 1.6479109632175482e-05, + "loss": 1.12, + "step": 1340 + }, + { + "epoch": 0.3497480903624248, + "grad_norm": 1.2421875, + "learning_rate": 1.6444472063976858e-05, + "loss": 1.102, + "step": 1345 + }, + { + "epoch": 0.3510482691370063, + "grad_norm": 1.3046875, + "learning_rate": 1.6409701749254966e-05, + "loss": 1.1744, + "step": 1350 + }, + { + "epoch": 0.35234844791158787, + "grad_norm": 1.3046875, + "learning_rate": 1.6374799404226486e-05, + "loss": 1.1909, + "step": 1355 + }, + { + "epoch": 0.35364862668616937, + "grad_norm": 1.34375, + "learning_rate": 1.633976574782773e-05, + "loss": 1.2021, + "step": 1360 + }, + { + "epoch": 0.35494880546075086, + "grad_norm": 1.5234375, + "learning_rate": 1.6304601501699823e-05, + "loss": 1.1905, + "step": 1365 + }, + { + "epoch": 0.35624898423533236, + "grad_norm": 1.3359375, + "learning_rate": 1.6269307390173844e-05, + "loss": 1.1524, + "step": 1370 + }, + { + "epoch": 0.35754916300991385, + "grad_norm": 1.453125, + "learning_rate": 1.6233884140255917e-05, + "loss": 1.1761, + "step": 1375 + }, + { + "epoch": 0.35884934178449535, + "grad_norm": 1.34375, + "learning_rate": 1.61983324816122e-05, + "loss": 1.1735, + "step": 1380 + }, + { + "epoch": 0.3601495205590769, + "grad_norm": 1.75, + "learning_rate": 1.6162653146553907e-05, + "loss": 1.1371, + "step": 1385 + }, + { + "epoch": 0.3614496993336584, + "grad_norm": 1.390625, + "learning_rate": 1.6126846870022176e-05, + "loss": 1.1505, + "step": 1390 + }, + { + "epoch": 0.3627498781082399, + "grad_norm": 1.328125, + "learning_rate": 1.6090914389572964e-05, + "loss": 1.1551, + "step": 1395 + }, + { + "epoch": 0.3640500568828214, + "grad_norm": 1.3203125, + "learning_rate": 1.605485644536183e-05, + "loss": 1.2159, + "step": 1400 + }, + { + "epoch": 0.3640500568828214, + "eval_loss": 1.1779258251190186, + "eval_runtime": 577.7202, + "eval_samples_per_second": 11.826, + "eval_steps_per_second": 3.943, + "step": 1400 + }, + { + "epoch": 0.3653502356574029, + "grad_norm": 1.390625, + "learning_rate": 1.6018673780128704e-05, + "loss": 1.1869, + "step": 1405 + }, + { + "epoch": 0.3666504144319844, + "grad_norm": 1.328125, + "learning_rate": 1.5982367139182588e-05, + "loss": 1.2128, + "step": 1410 + }, + { + "epoch": 0.3679505932065659, + "grad_norm": 1.3359375, + "learning_rate": 1.5945937270386192e-05, + "loss": 1.1418, + "step": 1415 + }, + { + "epoch": 0.3692507719811474, + "grad_norm": 1.3359375, + "learning_rate": 1.5909384924140535e-05, + "loss": 1.1597, + "step": 1420 + }, + { + "epoch": 0.3705509507557289, + "grad_norm": 1.4296875, + "learning_rate": 1.5872710853369498e-05, + "loss": 1.1802, + "step": 1425 + }, + { + "epoch": 0.3718511295303104, + "grad_norm": 1.703125, + "learning_rate": 1.5835915813504293e-05, + "loss": 1.1699, + "step": 1430 + }, + { + "epoch": 0.3731513083048919, + "grad_norm": 1.375, + "learning_rate": 1.579900056246793e-05, + "loss": 1.1655, + "step": 1435 + }, + { + "epoch": 0.37445148707947346, + "grad_norm": 1.328125, + "learning_rate": 1.576196586065958e-05, + "loss": 1.1901, + "step": 1440 + }, + { + "epoch": 0.37575166585405495, + "grad_norm": 1.3515625, + "learning_rate": 1.5724812470938923e-05, + "loss": 1.1667, + "step": 1445 + }, + { + "epoch": 0.37705184462863645, + "grad_norm": 1.2734375, + "learning_rate": 1.5687541158610437e-05, + "loss": 1.1392, + "step": 1450 + }, + { + "epoch": 0.37835202340321794, + "grad_norm": 1.359375, + "learning_rate": 1.5650152691407625e-05, + "loss": 1.1604, + "step": 1455 + }, + { + "epoch": 0.37965220217779944, + "grad_norm": 1.3125, + "learning_rate": 1.5612647839477205e-05, + "loss": 1.1651, + "step": 1460 + }, + { + "epoch": 0.38095238095238093, + "grad_norm": 1.3515625, + "learning_rate": 1.557502737536326e-05, + "loss": 1.1835, + "step": 1465 + }, + { + "epoch": 0.3822525597269625, + "grad_norm": 1.328125, + "learning_rate": 1.55372920739913e-05, + "loss": 1.1055, + "step": 1470 + }, + { + "epoch": 0.383552738501544, + "grad_norm": 1.359375, + "learning_rate": 1.54994427126523e-05, + "loss": 1.2111, + "step": 1475 + }, + { + "epoch": 0.3848529172761255, + "grad_norm": 1.3984375, + "learning_rate": 1.546148007098673e-05, + "loss": 1.1328, + "step": 1480 + }, + { + "epoch": 0.38615309605070697, + "grad_norm": 1.3515625, + "learning_rate": 1.5423404930968444e-05, + "loss": 1.1878, + "step": 1485 + }, + { + "epoch": 0.38745327482528846, + "grad_norm": 1.2734375, + "learning_rate": 1.53852180768886e-05, + "loss": 1.1724, + "step": 1490 + }, + { + "epoch": 0.38875345359986996, + "grad_norm": 1.328125, + "learning_rate": 1.53469202953395e-05, + "loss": 1.1638, + "step": 1495 + }, + { + "epoch": 0.3900536323744515, + "grad_norm": 1.2890625, + "learning_rate": 1.5308512375198388e-05, + "loss": 1.2015, + "step": 1500 + }, + { + "epoch": 0.391353811149033, + "grad_norm": 1.375, + "learning_rate": 1.5269995107611197e-05, + "loss": 1.1696, + "step": 1505 + }, + { + "epoch": 0.3926539899236145, + "grad_norm": 1.3125, + "learning_rate": 1.523136928597625e-05, + "loss": 1.1485, + "step": 1510 + }, + { + "epoch": 0.393954168698196, + "grad_norm": 1.3671875, + "learning_rate": 1.5192635705927932e-05, + "loss": 1.1349, + "step": 1515 + }, + { + "epoch": 0.3952543474727775, + "grad_norm": 1.296875, + "learning_rate": 1.5153795165320284e-05, + "loss": 1.2, + "step": 1520 + }, + { + "epoch": 0.396554526247359, + "grad_norm": 1.34375, + "learning_rate": 1.5114848464210572e-05, + "loss": 1.1329, + "step": 1525 + }, + { + "epoch": 0.39785470502194054, + "grad_norm": 1.3515625, + "learning_rate": 1.5075796404842819e-05, + "loss": 1.1924, + "step": 1530 + }, + { + "epoch": 0.39915488379652203, + "grad_norm": 1.3203125, + "learning_rate": 1.5036639791631264e-05, + "loss": 1.1772, + "step": 1535 + }, + { + "epoch": 0.4004550625711035, + "grad_norm": 1.328125, + "learning_rate": 1.4997379431143806e-05, + "loss": 1.1209, + "step": 1540 + }, + { + "epoch": 0.401755241345685, + "grad_norm": 1.3125, + "learning_rate": 1.4958016132085371e-05, + "loss": 1.1651, + "step": 1545 + }, + { + "epoch": 0.4030554201202665, + "grad_norm": 1.3515625, + "learning_rate": 1.491855070528128e-05, + "loss": 1.1517, + "step": 1550 + }, + { + "epoch": 0.40435559889484807, + "grad_norm": 1.3671875, + "learning_rate": 1.4878983963660532e-05, + "loss": 1.1456, + "step": 1555 + }, + { + "epoch": 0.40565577766942956, + "grad_norm": 1.3515625, + "learning_rate": 1.4839316722239047e-05, + "loss": 1.2196, + "step": 1560 + }, + { + "epoch": 0.40695595644401106, + "grad_norm": 1.3203125, + "learning_rate": 1.4799549798102909e-05, + "loss": 1.1362, + "step": 1565 + }, + { + "epoch": 0.40825613521859255, + "grad_norm": 1.359375, + "learning_rate": 1.4759684010391503e-05, + "loss": 1.1681, + "step": 1570 + }, + { + "epoch": 0.40955631399317405, + "grad_norm": 1.296875, + "learning_rate": 1.4719720180280665e-05, + "loss": 1.1182, + "step": 1575 + }, + { + "epoch": 0.41085649276775554, + "grad_norm": 1.3359375, + "learning_rate": 1.4679659130965751e-05, + "loss": 1.2005, + "step": 1580 + }, + { + "epoch": 0.4121566715423371, + "grad_norm": 1.3515625, + "learning_rate": 1.46395016876447e-05, + "loss": 1.1363, + "step": 1585 + }, + { + "epoch": 0.4134568503169186, + "grad_norm": 1.3359375, + "learning_rate": 1.4599248677501007e-05, + "loss": 1.1791, + "step": 1590 + }, + { + "epoch": 0.4147570290915001, + "grad_norm": 2.78125, + "learning_rate": 1.4558900929686718e-05, + "loss": 1.1162, + "step": 1595 + }, + { + "epoch": 0.4160572078660816, + "grad_norm": 1.3359375, + "learning_rate": 1.4518459275305321e-05, + "loss": 1.248, + "step": 1600 + }, + { + "epoch": 0.4160572078660816, + "eval_loss": 1.1750705242156982, + "eval_runtime": 577.3745, + "eval_samples_per_second": 11.833, + "eval_steps_per_second": 3.945, + "step": 1600 + }, + { + "epoch": 0.4173573866406631, + "grad_norm": 1.3203125, + "learning_rate": 1.4477924547394649e-05, + "loss": 1.1601, + "step": 1605 + }, + { + "epoch": 0.41865756541524457, + "grad_norm": 1.40625, + "learning_rate": 1.4437297580909703e-05, + "loss": 1.1764, + "step": 1610 + }, + { + "epoch": 0.4199577441898261, + "grad_norm": 1.2734375, + "learning_rate": 1.4396579212705467e-05, + "loss": 1.193, + "step": 1615 + }, + { + "epoch": 0.4212579229644076, + "grad_norm": 1.3203125, + "learning_rate": 1.4355770281519657e-05, + "loss": 1.1243, + "step": 1620 + }, + { + "epoch": 0.4225581017389891, + "grad_norm": 1.3125, + "learning_rate": 1.4314871627955466e-05, + "loss": 1.1671, + "step": 1625 + }, + { + "epoch": 0.4238582805135706, + "grad_norm": 1.2890625, + "learning_rate": 1.4273884094464218e-05, + "loss": 1.1673, + "step": 1630 + }, + { + "epoch": 0.4251584592881521, + "grad_norm": 1.328125, + "learning_rate": 1.4232808525328037e-05, + "loss": 1.1627, + "step": 1635 + }, + { + "epoch": 0.42645863806273365, + "grad_norm": 1.2890625, + "learning_rate": 1.4191645766642458e-05, + "loss": 1.1335, + "step": 1640 + }, + { + "epoch": 0.42775881683731515, + "grad_norm": 1.2890625, + "learning_rate": 1.4150396666298976e-05, + "loss": 1.1656, + "step": 1645 + }, + { + "epoch": 0.42905899561189664, + "grad_norm": 1.40625, + "learning_rate": 1.4109062073967606e-05, + "loss": 1.1479, + "step": 1650 + }, + { + "epoch": 0.43035917438647814, + "grad_norm": 1.296875, + "learning_rate": 1.4067642841079372e-05, + "loss": 1.1742, + "step": 1655 + }, + { + "epoch": 0.43165935316105963, + "grad_norm": 1.4140625, + "learning_rate": 1.4026139820808756e-05, + "loss": 1.0978, + "step": 1660 + }, + { + "epoch": 0.43295953193564113, + "grad_norm": 1.3125, + "learning_rate": 1.3984553868056147e-05, + "loss": 1.157, + "step": 1665 + }, + { + "epoch": 0.4342597107102227, + "grad_norm": 1.296875, + "learning_rate": 1.394288583943022e-05, + "loss": 1.192, + "step": 1670 + }, + { + "epoch": 0.4355598894848042, + "grad_norm": 1.546875, + "learning_rate": 1.3901136593230275e-05, + "loss": 1.1656, + "step": 1675 + }, + { + "epoch": 0.43686006825938567, + "grad_norm": 1.34375, + "learning_rate": 1.3859306989428594e-05, + "loss": 1.1592, + "step": 1680 + }, + { + "epoch": 0.43816024703396717, + "grad_norm": 1.34375, + "learning_rate": 1.381739788965269e-05, + "loss": 1.1105, + "step": 1685 + }, + { + "epoch": 0.43946042580854866, + "grad_norm": 1.3125, + "learning_rate": 1.3775410157167581e-05, + "loss": 1.1577, + "step": 1690 + }, + { + "epoch": 0.44076060458313016, + "grad_norm": 1.7890625, + "learning_rate": 1.3733344656858006e-05, + "loss": 1.1232, + "step": 1695 + }, + { + "epoch": 0.4420607833577117, + "grad_norm": 1.3515625, + "learning_rate": 1.3691202255210589e-05, + "loss": 1.1988, + "step": 1700 + }, + { + "epoch": 0.4433609621322932, + "grad_norm": 1.3046875, + "learning_rate": 1.3648983820296028e-05, + "loss": 1.1351, + "step": 1705 + }, + { + "epoch": 0.4446611409068747, + "grad_norm": 1.2890625, + "learning_rate": 1.3606690221751185e-05, + "loss": 1.1691, + "step": 1710 + }, + { + "epoch": 0.4459613196814562, + "grad_norm": 1.4140625, + "learning_rate": 1.3564322330761172e-05, + "loss": 1.1539, + "step": 1715 + }, + { + "epoch": 0.4472614984560377, + "grad_norm": 1.6875, + "learning_rate": 1.3521881020041424e-05, + "loss": 1.2068, + "step": 1720 + }, + { + "epoch": 0.4485616772306192, + "grad_norm": 1.2578125, + "learning_rate": 1.347936716381972e-05, + "loss": 1.1514, + "step": 1725 + }, + { + "epoch": 0.44986185600520073, + "grad_norm": 1.2578125, + "learning_rate": 1.3436781637818142e-05, + "loss": 1.1453, + "step": 1730 + }, + { + "epoch": 0.45116203477978223, + "grad_norm": 1.3046875, + "learning_rate": 1.3394125319235094e-05, + "loss": 1.1573, + "step": 1735 + }, + { + "epoch": 0.4524622135543637, + "grad_norm": 1.390625, + "learning_rate": 1.3351399086727181e-05, + "loss": 1.1841, + "step": 1740 + }, + { + "epoch": 0.4537623923289452, + "grad_norm": 1.359375, + "learning_rate": 1.3308603820391142e-05, + "loss": 1.1869, + "step": 1745 + }, + { + "epoch": 0.4550625711035267, + "grad_norm": 1.359375, + "learning_rate": 1.3265740401745701e-05, + "loss": 1.1788, + "step": 1750 + }, + { + "epoch": 0.45636274987810826, + "grad_norm": 1.3515625, + "learning_rate": 1.3222809713713422e-05, + "loss": 1.1538, + "step": 1755 + }, + { + "epoch": 0.45766292865268976, + "grad_norm": 1.9375, + "learning_rate": 1.317981264060252e-05, + "loss": 1.1333, + "step": 1760 + }, + { + "epoch": 0.45896310742727126, + "grad_norm": 1.484375, + "learning_rate": 1.3136750068088646e-05, + "loss": 1.1902, + "step": 1765 + }, + { + "epoch": 0.46026328620185275, + "grad_norm": 1.5703125, + "learning_rate": 1.309362288319663e-05, + "loss": 1.0974, + "step": 1770 + }, + { + "epoch": 0.46156346497643425, + "grad_norm": 1.296875, + "learning_rate": 1.3050431974282235e-05, + "loss": 1.1717, + "step": 1775 + }, + { + "epoch": 0.46286364375101574, + "grad_norm": 1.375, + "learning_rate": 1.3007178231013833e-05, + "loss": 1.1546, + "step": 1780 + }, + { + "epoch": 0.4641638225255973, + "grad_norm": 1.390625, + "learning_rate": 1.2963862544354093e-05, + "loss": 1.1782, + "step": 1785 + }, + { + "epoch": 0.4654640013001788, + "grad_norm": 1.328125, + "learning_rate": 1.2920485806541633e-05, + "loss": 1.1684, + "step": 1790 + }, + { + "epoch": 0.4667641800747603, + "grad_norm": 1.453125, + "learning_rate": 1.2877048911072618e-05, + "loss": 1.1934, + "step": 1795 + }, + { + "epoch": 0.4680643588493418, + "grad_norm": 1.3359375, + "learning_rate": 1.283355275268239e-05, + "loss": 1.1644, + "step": 1800 + }, + { + "epoch": 0.4680643588493418, + "eval_loss": 1.1729602813720703, + "eval_runtime": 577.3935, + "eval_samples_per_second": 11.832, + "eval_steps_per_second": 3.945, + "step": 1800 + }, + { + "epoch": 0.4693645376239233, + "grad_norm": 1.296875, + "learning_rate": 1.2789998227327001e-05, + "loss": 1.1698, + "step": 1805 + }, + { + "epoch": 0.47066471639850477, + "grad_norm": 1.3125, + "learning_rate": 1.274638623216479e-05, + "loss": 1.1127, + "step": 1810 + }, + { + "epoch": 0.4719648951730863, + "grad_norm": 1.2734375, + "learning_rate": 1.2702717665537877e-05, + "loss": 1.1298, + "step": 1815 + }, + { + "epoch": 0.4732650739476678, + "grad_norm": 1.3359375, + "learning_rate": 1.2658993426953684e-05, + "loss": 1.179, + "step": 1820 + }, + { + "epoch": 0.4745652527222493, + "grad_norm": 1.3203125, + "learning_rate": 1.2615214417066373e-05, + "loss": 1.2056, + "step": 1825 + }, + { + "epoch": 0.4758654314968308, + "grad_norm": 1.25, + "learning_rate": 1.257138153765833e-05, + "loss": 1.1546, + "step": 1830 + }, + { + "epoch": 0.4771656102714123, + "grad_norm": 1.2734375, + "learning_rate": 1.2527495691621568e-05, + "loss": 1.1705, + "step": 1835 + }, + { + "epoch": 0.47846578904599385, + "grad_norm": 1.328125, + "learning_rate": 1.2483557782939126e-05, + "loss": 1.1299, + "step": 1840 + }, + { + "epoch": 0.47976596782057535, + "grad_norm": 1.4765625, + "learning_rate": 1.2439568716666468e-05, + "loss": 1.142, + "step": 1845 + }, + { + "epoch": 0.48106614659515684, + "grad_norm": 1.3046875, + "learning_rate": 1.239552939891282e-05, + "loss": 1.1879, + "step": 1850 + }, + { + "epoch": 0.48236632536973834, + "grad_norm": 1.4140625, + "learning_rate": 1.2351440736822517e-05, + "loss": 1.186, + "step": 1855 + }, + { + "epoch": 0.48366650414431983, + "grad_norm": 1.34375, + "learning_rate": 1.2307303638556314e-05, + "loss": 1.2062, + "step": 1860 + }, + { + "epoch": 0.4849666829189013, + "grad_norm": 1.25, + "learning_rate": 1.2263119013272676e-05, + "loss": 1.1163, + "step": 1865 + }, + { + "epoch": 0.4862668616934829, + "grad_norm": 1.265625, + "learning_rate": 1.2218887771109054e-05, + "loss": 1.1832, + "step": 1870 + }, + { + "epoch": 0.48756704046806437, + "grad_norm": 1.328125, + "learning_rate": 1.217461082316314e-05, + "loss": 1.1123, + "step": 1875 + }, + { + "epoch": 0.48886721924264587, + "grad_norm": 1.3125, + "learning_rate": 1.21302890814741e-05, + "loss": 1.1759, + "step": 1880 + }, + { + "epoch": 0.49016739801722736, + "grad_norm": 1.2890625, + "learning_rate": 1.2085923459003776e-05, + "loss": 1.1703, + "step": 1885 + }, + { + "epoch": 0.49146757679180886, + "grad_norm": 1.515625, + "learning_rate": 1.2041514869617895e-05, + "loss": 1.1375, + "step": 1890 + }, + { + "epoch": 0.49276775556639035, + "grad_norm": 1.421875, + "learning_rate": 1.1997064228067237e-05, + "loss": 1.1785, + "step": 1895 + }, + { + "epoch": 0.4940679343409719, + "grad_norm": 1.4609375, + "learning_rate": 1.195257244996879e-05, + "loss": 1.1617, + "step": 1900 + }, + { + "epoch": 0.4953681131155534, + "grad_norm": 1.3984375, + "learning_rate": 1.1908040451786903e-05, + "loss": 1.1691, + "step": 1905 + }, + { + "epoch": 0.4966682918901349, + "grad_norm": 1.3203125, + "learning_rate": 1.1863469150814388e-05, + "loss": 1.1731, + "step": 1910 + }, + { + "epoch": 0.4979684706647164, + "grad_norm": 1.3671875, + "learning_rate": 1.1818859465153643e-05, + "loss": 1.1272, + "step": 1915 + }, + { + "epoch": 0.4992686494392979, + "grad_norm": 1.359375, + "learning_rate": 1.177421231369773e-05, + "loss": 1.1913, + "step": 1920 + }, + { + "epoch": 0.5005688282138794, + "grad_norm": 1.3203125, + "learning_rate": 1.1729528616111449e-05, + "loss": 1.158, + "step": 1925 + }, + { + "epoch": 0.5018690069884609, + "grad_norm": 1.2890625, + "learning_rate": 1.1684809292812405e-05, + "loss": 1.2267, + "step": 1930 + }, + { + "epoch": 0.5031691857630424, + "grad_norm": 1.3203125, + "learning_rate": 1.164005526495203e-05, + "loss": 1.1303, + "step": 1935 + }, + { + "epoch": 0.5044693645376239, + "grad_norm": 1.3984375, + "learning_rate": 1.1595267454396622e-05, + "loss": 1.1648, + "step": 1940 + }, + { + "epoch": 0.5057695433122055, + "grad_norm": 1.2890625, + "learning_rate": 1.1550446783708349e-05, + "loss": 1.1854, + "step": 1945 + }, + { + "epoch": 0.5070697220867869, + "grad_norm": 1.34375, + "learning_rate": 1.1505594176126255e-05, + "loss": 1.1947, + "step": 1950 + }, + { + "epoch": 0.5083699008613685, + "grad_norm": 1.40625, + "learning_rate": 1.1460710555547232e-05, + "loss": 1.1526, + "step": 1955 + }, + { + "epoch": 0.5096700796359499, + "grad_norm": 2.0, + "learning_rate": 1.1415796846506993e-05, + "loss": 1.104, + "step": 1960 + }, + { + "epoch": 0.5109702584105315, + "grad_norm": 1.3515625, + "learning_rate": 1.1370853974161032e-05, + "loss": 1.1826, + "step": 1965 + }, + { + "epoch": 0.512270437185113, + "grad_norm": 1.34375, + "learning_rate": 1.1325882864265558e-05, + "loss": 1.16, + "step": 1970 + }, + { + "epoch": 0.5135706159596944, + "grad_norm": 1.3046875, + "learning_rate": 1.128088444315844e-05, + "loss": 1.1895, + "step": 1975 + }, + { + "epoch": 0.514870794734276, + "grad_norm": 1.3203125, + "learning_rate": 1.1235859637740105e-05, + "loss": 1.1841, + "step": 1980 + }, + { + "epoch": 0.5161709735088574, + "grad_norm": 1.421875, + "learning_rate": 1.1190809375454472e-05, + "loss": 1.1491, + "step": 1985 + }, + { + "epoch": 0.517471152283439, + "grad_norm": 1.2890625, + "learning_rate": 1.1145734584269826e-05, + "loss": 1.1759, + "step": 1990 + }, + { + "epoch": 0.5187713310580204, + "grad_norm": 1.3359375, + "learning_rate": 1.1100636192659702e-05, + "loss": 1.1424, + "step": 1995 + }, + { + "epoch": 0.520071509832602, + "grad_norm": 1.3359375, + "learning_rate": 1.1055515129583787e-05, + "loss": 1.1479, + "step": 2000 + }, + { + "epoch": 0.520071509832602, + "eval_loss": 1.1712779998779297, + "eval_runtime": 588.6026, + "eval_samples_per_second": 11.607, + "eval_steps_per_second": 3.87, + "step": 2000 + }, + { + "epoch": 0.5213716886071835, + "grad_norm": 1.296875, + "learning_rate": 1.1010372324468756e-05, + "loss": 1.1576, + "step": 2005 + }, + { + "epoch": 0.522671867381765, + "grad_norm": 1.328125, + "learning_rate": 1.0965208707189134e-05, + "loss": 1.1916, + "step": 2010 + }, + { + "epoch": 0.5239720461563465, + "grad_norm": 1.3125, + "learning_rate": 1.0920025208048157e-05, + "loss": 1.1546, + "step": 2015 + }, + { + "epoch": 0.525272224930928, + "grad_norm": 1.359375, + "learning_rate": 1.0874822757758585e-05, + "loss": 1.1511, + "step": 2020 + }, + { + "epoch": 0.5265724037055095, + "grad_norm": 1.2421875, + "learning_rate": 1.082960228742355e-05, + "loss": 1.1292, + "step": 2025 + }, + { + "epoch": 0.5278725824800911, + "grad_norm": 1.375, + "learning_rate": 1.0784364728517374e-05, + "loss": 1.1967, + "step": 2030 + }, + { + "epoch": 0.5291727612546725, + "grad_norm": 1.296875, + "learning_rate": 1.073911101286637e-05, + "loss": 1.1418, + "step": 2035 + }, + { + "epoch": 0.530472940029254, + "grad_norm": 1.3203125, + "learning_rate": 1.0693842072629657e-05, + "loss": 1.1617, + "step": 2040 + }, + { + "epoch": 0.5317731188038355, + "grad_norm": 1.3359375, + "learning_rate": 1.0648558840279967e-05, + "loss": 1.1569, + "step": 2045 + }, + { + "epoch": 0.533073297578417, + "grad_norm": 1.375, + "learning_rate": 1.0603262248584416e-05, + "loss": 1.1853, + "step": 2050 + }, + { + "epoch": 0.5343734763529986, + "grad_norm": 1.3203125, + "learning_rate": 1.0557953230585309e-05, + "loss": 1.1583, + "step": 2055 + }, + { + "epoch": 0.53567365512758, + "grad_norm": 1.3671875, + "learning_rate": 1.0512632719580917e-05, + "loss": 1.1792, + "step": 2060 + }, + { + "epoch": 0.5369738339021616, + "grad_norm": 1.3203125, + "learning_rate": 1.0467301649106243e-05, + "loss": 1.1767, + "step": 2065 + }, + { + "epoch": 0.538274012676743, + "grad_norm": 1.3125, + "learning_rate": 1.0421960952913806e-05, + "loss": 1.165, + "step": 2070 + }, + { + "epoch": 0.5395741914513246, + "grad_norm": 1.3828125, + "learning_rate": 1.0376611564954391e-05, + "loss": 1.1523, + "step": 2075 + }, + { + "epoch": 0.540874370225906, + "grad_norm": 1.390625, + "learning_rate": 1.0331254419357833e-05, + "loss": 1.1779, + "step": 2080 + }, + { + "epoch": 0.5421745490004876, + "grad_norm": 1.5078125, + "learning_rate": 1.028589045041375e-05, + "loss": 1.1025, + "step": 2085 + }, + { + "epoch": 0.5434747277750691, + "grad_norm": 1.2734375, + "learning_rate": 1.0240520592552321e-05, + "loss": 1.13, + "step": 2090 + }, + { + "epoch": 0.5447749065496506, + "grad_norm": 1.359375, + "learning_rate": 1.0195145780325021e-05, + "loss": 1.1924, + "step": 2095 + }, + { + "epoch": 0.5460750853242321, + "grad_norm": 1.5546875, + "learning_rate": 1.0149766948385387e-05, + "loss": 1.1454, + "step": 2100 + }, + { + "epoch": 0.5473752640988135, + "grad_norm": 1.3515625, + "learning_rate": 1.0104385031469746e-05, + "loss": 1.147, + "step": 2105 + }, + { + "epoch": 0.5486754428733951, + "grad_norm": 1.328125, + "learning_rate": 1.005900096437797e-05, + "loss": 1.1673, + "step": 2110 + }, + { + "epoch": 0.5499756216479766, + "grad_norm": 1.3046875, + "learning_rate": 1.0013615681954231e-05, + "loss": 1.1619, + "step": 2115 + }, + { + "epoch": 0.5512758004225581, + "grad_norm": 1.3671875, + "learning_rate": 9.96823011906773e-06, + "loss": 1.1852, + "step": 2120 + }, + { + "epoch": 0.5525759791971396, + "grad_norm": 1.34375, + "learning_rate": 9.922845210593445e-06, + "loss": 1.1982, + "step": 2125 + }, + { + "epoch": 0.5538761579717211, + "grad_norm": 1.3046875, + "learning_rate": 9.877461891392874e-06, + "loss": 1.1411, + "step": 2130 + }, + { + "epoch": 0.5551763367463026, + "grad_norm": 1.3359375, + "learning_rate": 9.832081096294775e-06, + "loss": 1.1854, + "step": 2135 + }, + { + "epoch": 0.5564765155208842, + "grad_norm": 1.25, + "learning_rate": 9.786703760075924e-06, + "loss": 1.1622, + "step": 2140 + }, + { + "epoch": 0.5577766942954656, + "grad_norm": 1.3359375, + "learning_rate": 9.741330817441832e-06, + "loss": 1.0954, + "step": 2145 + }, + { + "epoch": 0.5590768730700472, + "grad_norm": 1.3203125, + "learning_rate": 9.695963203007526e-06, + "loss": 1.1648, + "step": 2150 + }, + { + "epoch": 0.5603770518446286, + "grad_norm": 1.265625, + "learning_rate": 9.650601851278271e-06, + "loss": 1.1763, + "step": 2155 + }, + { + "epoch": 0.5616772306192102, + "grad_norm": 1.328125, + "learning_rate": 9.60524769663033e-06, + "loss": 1.2054, + "step": 2160 + }, + { + "epoch": 0.5629774093937916, + "grad_norm": 1.328125, + "learning_rate": 9.559901673291725e-06, + "loss": 1.083, + "step": 2165 + }, + { + "epoch": 0.5642775881683731, + "grad_norm": 1.4296875, + "learning_rate": 9.51456471532297e-06, + "loss": 1.1765, + "step": 2170 + }, + { + "epoch": 0.5655777669429547, + "grad_norm": 1.3515625, + "learning_rate": 9.469237756597854e-06, + "loss": 1.1779, + "step": 2175 + }, + { + "epoch": 0.5668779457175361, + "grad_norm": 1.3671875, + "learning_rate": 9.423921730784201e-06, + "loss": 1.172, + "step": 2180 + }, + { + "epoch": 0.5681781244921177, + "grad_norm": 1.515625, + "learning_rate": 9.378617571324631e-06, + "loss": 1.1612, + "step": 2185 + }, + { + "epoch": 0.5694783032666991, + "grad_norm": 1.3046875, + "learning_rate": 9.333326211417327e-06, + "loss": 1.1727, + "step": 2190 + }, + { + "epoch": 0.5707784820412807, + "grad_norm": 1.34375, + "learning_rate": 9.288048583996831e-06, + "loss": 1.1389, + "step": 2195 + }, + { + "epoch": 0.5720786608158622, + "grad_norm": 1.2890625, + "learning_rate": 9.242785621714807e-06, + "loss": 1.1292, + "step": 2200 + }, + { + "epoch": 0.5720786608158622, + "eval_loss": 1.1700196266174316, + "eval_runtime": 578.4636, + "eval_samples_per_second": 11.811, + "eval_steps_per_second": 3.938, + "step": 2200 + }, + { + "epoch": 0.5733788395904437, + "grad_norm": 1.2265625, + "learning_rate": 9.197538256920845e-06, + "loss": 1.1811, + "step": 2205 + }, + { + "epoch": 0.5746790183650252, + "grad_norm": 1.34375, + "learning_rate": 9.152307421643248e-06, + "loss": 1.1209, + "step": 2210 + }, + { + "epoch": 0.5759791971396067, + "grad_norm": 1.3671875, + "learning_rate": 9.107094047569836e-06, + "loss": 1.1806, + "step": 2215 + }, + { + "epoch": 0.5772793759141882, + "grad_norm": 1.2890625, + "learning_rate": 9.061899066028755e-06, + "loss": 1.1631, + "step": 2220 + }, + { + "epoch": 0.5785795546887698, + "grad_norm": 1.3125, + "learning_rate": 9.016723407969297e-06, + "loss": 1.219, + "step": 2225 + }, + { + "epoch": 0.5798797334633512, + "grad_norm": 1.328125, + "learning_rate": 8.971568003942701e-06, + "loss": 1.2102, + "step": 2230 + }, + { + "epoch": 0.5811799122379327, + "grad_norm": 1.3984375, + "learning_rate": 8.926433784083022e-06, + "loss": 1.1547, + "step": 2235 + }, + { + "epoch": 0.5824800910125142, + "grad_norm": 1.6953125, + "learning_rate": 8.881321678087948e-06, + "loss": 1.1607, + "step": 2240 + }, + { + "epoch": 0.5837802697870957, + "grad_norm": 1.3125, + "learning_rate": 8.83623261519965e-06, + "loss": 1.1417, + "step": 2245 + }, + { + "epoch": 0.5850804485616772, + "grad_norm": 1.2890625, + "learning_rate": 8.791167524185651e-06, + "loss": 1.1859, + "step": 2250 + }, + { + "epoch": 0.5863806273362587, + "grad_norm": 1.3125, + "learning_rate": 8.746127333319679e-06, + "loss": 1.1413, + "step": 2255 + }, + { + "epoch": 0.5876808061108403, + "grad_norm": 1.3203125, + "learning_rate": 8.701112970362569e-06, + "loss": 1.1803, + "step": 2260 + }, + { + "epoch": 0.5889809848854217, + "grad_norm": 1.359375, + "learning_rate": 8.65612536254313e-06, + "loss": 1.1832, + "step": 2265 + }, + { + "epoch": 0.5902811636600033, + "grad_norm": 1.328125, + "learning_rate": 8.611165436539062e-06, + "loss": 1.1154, + "step": 2270 + }, + { + "epoch": 0.5915813424345847, + "grad_norm": 1.34375, + "learning_rate": 8.566234118457857e-06, + "loss": 1.1777, + "step": 2275 + }, + { + "epoch": 0.5928815212091663, + "grad_norm": 1.53125, + "learning_rate": 8.52133233381773e-06, + "loss": 1.2159, + "step": 2280 + }, + { + "epoch": 0.5941816999837478, + "grad_norm": 1.328125, + "learning_rate": 8.476461007528538e-06, + "loss": 1.1776, + "step": 2285 + }, + { + "epoch": 0.5954818787583293, + "grad_norm": 1.3046875, + "learning_rate": 8.431621063872759e-06, + "loss": 1.1542, + "step": 2290 + }, + { + "epoch": 0.5967820575329108, + "grad_norm": 1.3203125, + "learning_rate": 8.386813426486427e-06, + "loss": 1.132, + "step": 2295 + }, + { + "epoch": 0.5980822363074922, + "grad_norm": 1.34375, + "learning_rate": 8.342039018340114e-06, + "loss": 1.1944, + "step": 2300 + }, + { + "epoch": 0.5993824150820738, + "grad_norm": 1.203125, + "learning_rate": 8.297298761719923e-06, + "loss": 1.0801, + "step": 2305 + }, + { + "epoch": 0.6006825938566553, + "grad_norm": 1.2890625, + "learning_rate": 8.252593578208485e-06, + "loss": 1.1818, + "step": 2310 + }, + { + "epoch": 0.6019827726312368, + "grad_norm": 1.40625, + "learning_rate": 8.207924388665971e-06, + "loss": 1.1598, + "step": 2315 + }, + { + "epoch": 0.6032829514058183, + "grad_norm": 1.2734375, + "learning_rate": 8.16329211321114e-06, + "loss": 1.1533, + "step": 2320 + }, + { + "epoch": 0.6045831301803998, + "grad_norm": 1.453125, + "learning_rate": 8.118697671202373e-06, + "loss": 1.1676, + "step": 2325 + }, + { + "epoch": 0.6058833089549813, + "grad_norm": 1.265625, + "learning_rate": 8.074141981218731e-06, + "loss": 1.1403, + "step": 2330 + }, + { + "epoch": 0.6071834877295628, + "grad_norm": 1.2734375, + "learning_rate": 8.029625961041058e-06, + "loss": 1.1452, + "step": 2335 + }, + { + "epoch": 0.6084836665041443, + "grad_norm": 1.3203125, + "learning_rate": 7.985150527633034e-06, + "loss": 1.1834, + "step": 2340 + }, + { + "epoch": 0.6097838452787259, + "grad_norm": 1.3515625, + "learning_rate": 7.940716597122331e-06, + "loss": 1.1147, + "step": 2345 + }, + { + "epoch": 0.6110840240533073, + "grad_norm": 1.3203125, + "learning_rate": 7.896325084781723e-06, + "loss": 1.1177, + "step": 2350 + }, + { + "epoch": 0.6123842028278889, + "grad_norm": 1.296875, + "learning_rate": 7.85197690501022e-06, + "loss": 1.1552, + "step": 2355 + }, + { + "epoch": 0.6136843816024703, + "grad_norm": 1.359375, + "learning_rate": 7.807672971314258e-06, + "loss": 1.1636, + "step": 2360 + }, + { + "epoch": 0.6149845603770518, + "grad_norm": 1.3125, + "learning_rate": 7.763414196288868e-06, + "loss": 1.1521, + "step": 2365 + }, + { + "epoch": 0.6162847391516334, + "grad_norm": 1.3125, + "learning_rate": 7.71920149159887e-06, + "loss": 1.1818, + "step": 2370 + }, + { + "epoch": 0.6175849179262148, + "grad_norm": 1.3203125, + "learning_rate": 7.67503576796011e-06, + "loss": 1.1336, + "step": 2375 + }, + { + "epoch": 0.6188850967007964, + "grad_norm": 1.3203125, + "learning_rate": 7.630917935120703e-06, + "loss": 1.1676, + "step": 2380 + }, + { + "epoch": 0.6201852754753778, + "grad_norm": 3.125, + "learning_rate": 7.586848901842271e-06, + "loss": 1.1335, + "step": 2385 + }, + { + "epoch": 0.6214854542499594, + "grad_norm": 1.3828125, + "learning_rate": 7.54282957588125e-06, + "loss": 1.1636, + "step": 2390 + }, + { + "epoch": 0.6227856330245408, + "grad_norm": 1.296875, + "learning_rate": 7.498860863970163e-06, + "loss": 1.1389, + "step": 2395 + }, + { + "epoch": 0.6240858117991224, + "grad_norm": 1.3671875, + "learning_rate": 7.454943671798976e-06, + "loss": 1.1441, + "step": 2400 + }, + { + "epoch": 0.6240858117991224, + "eval_loss": 1.1691473722457886, + "eval_runtime": 577.5415, + "eval_samples_per_second": 11.829, + "eval_steps_per_second": 3.944, + "step": 2400 + }, + { + "epoch": 0.6253859905737039, + "grad_norm": 1.34375, + "learning_rate": 7.411078903996417e-06, + "loss": 1.1497, + "step": 2405 + }, + { + "epoch": 0.6266861693482854, + "grad_norm": 1.2734375, + "learning_rate": 7.367267464111349e-06, + "loss": 1.1678, + "step": 2410 + }, + { + "epoch": 0.6279863481228669, + "grad_norm": 1.3984375, + "learning_rate": 7.323510254594162e-06, + "loss": 1.1213, + "step": 2415 + }, + { + "epoch": 0.6292865268974484, + "grad_norm": 1.5546875, + "learning_rate": 7.279808176778185e-06, + "loss": 1.2333, + "step": 2420 + }, + { + "epoch": 0.6305867056720299, + "grad_norm": 1.390625, + "learning_rate": 7.2361621308611055e-06, + "loss": 1.1808, + "step": 2425 + }, + { + "epoch": 0.6318868844466115, + "grad_norm": 1.3359375, + "learning_rate": 7.192573015886446e-06, + "loss": 1.1564, + "step": 2430 + }, + { + "epoch": 0.6331870632211929, + "grad_norm": 1.4375, + "learning_rate": 7.149041729725033e-06, + "loss": 1.1548, + "step": 2435 + }, + { + "epoch": 0.6344872419957744, + "grad_norm": 1.3203125, + "learning_rate": 7.1055691690565094e-06, + "loss": 1.1565, + "step": 2440 + }, + { + "epoch": 0.6357874207703559, + "grad_norm": 1.390625, + "learning_rate": 7.062156229350856e-06, + "loss": 1.1174, + "step": 2445 + }, + { + "epoch": 0.6370875995449374, + "grad_norm": 1.296875, + "learning_rate": 7.018803804849956e-06, + "loss": 1.2232, + "step": 2450 + }, + { + "epoch": 0.638387778319519, + "grad_norm": 1.2734375, + "learning_rate": 6.975512788549159e-06, + "loss": 1.1557, + "step": 2455 + }, + { + "epoch": 0.6396879570941004, + "grad_norm": 1.3046875, + "learning_rate": 6.932284072178907e-06, + "loss": 1.165, + "step": 2460 + }, + { + "epoch": 0.640988135868682, + "grad_norm": 1.3359375, + "learning_rate": 6.889118546186357e-06, + "loss": 1.1225, + "step": 2465 + }, + { + "epoch": 0.6422883146432634, + "grad_norm": 1.515625, + "learning_rate": 6.846017099717028e-06, + "loss": 1.1471, + "step": 2470 + }, + { + "epoch": 0.643588493417845, + "grad_norm": 1.3046875, + "learning_rate": 6.802980620596512e-06, + "loss": 1.1728, + "step": 2475 + }, + { + "epoch": 0.6448886721924264, + "grad_norm": 1.296875, + "learning_rate": 6.76000999531215e-06, + "loss": 1.1687, + "step": 2480 + }, + { + "epoch": 0.646188850967008, + "grad_norm": 1.28125, + "learning_rate": 6.717106108994809e-06, + "loss": 1.1786, + "step": 2485 + }, + { + "epoch": 0.6474890297415895, + "grad_norm": 1.3046875, + "learning_rate": 6.6742698454006275e-06, + "loss": 1.141, + "step": 2490 + }, + { + "epoch": 0.648789208516171, + "grad_norm": 1.3203125, + "learning_rate": 6.6315020868928135e-06, + "loss": 1.173, + "step": 2495 + }, + { + "epoch": 0.6500893872907525, + "grad_norm": 1.265625, + "learning_rate": 6.588803714423479e-06, + "loss": 1.1473, + "step": 2500 + }, + { + "epoch": 0.6513895660653339, + "grad_norm": 1.3828125, + "learning_rate": 6.546175607515486e-06, + "loss": 1.1715, + "step": 2505 + }, + { + "epoch": 0.6526897448399155, + "grad_norm": 1.296875, + "learning_rate": 6.5036186442443175e-06, + "loss": 1.1714, + "step": 2510 + }, + { + "epoch": 0.653989923614497, + "grad_norm": 1.3125, + "learning_rate": 6.461133701220019e-06, + "loss": 1.1497, + "step": 2515 + }, + { + "epoch": 0.6552901023890785, + "grad_norm": 1.3125, + "learning_rate": 6.418721653569123e-06, + "loss": 1.1169, + "step": 2520 + }, + { + "epoch": 0.65659028116366, + "grad_norm": 1.359375, + "learning_rate": 6.376383374916621e-06, + "loss": 1.1773, + "step": 2525 + }, + { + "epoch": 0.6578904599382415, + "grad_norm": 1.359375, + "learning_rate": 6.334119737367978e-06, + "loss": 1.1745, + "step": 2530 + }, + { + "epoch": 0.659190638712823, + "grad_norm": 1.296875, + "learning_rate": 6.291931611491159e-06, + "loss": 1.1896, + "step": 2535 + }, + { + "epoch": 0.6604908174874046, + "grad_norm": 1.3671875, + "learning_rate": 6.249819866298703e-06, + "loss": 1.1269, + "step": 2540 + }, + { + "epoch": 0.661790996261986, + "grad_norm": 1.265625, + "learning_rate": 6.207785369229822e-06, + "loss": 1.1391, + "step": 2545 + }, + { + "epoch": 0.6630911750365676, + "grad_norm": 1.3359375, + "learning_rate": 6.165828986132531e-06, + "loss": 1.1687, + "step": 2550 + }, + { + "epoch": 0.664391353811149, + "grad_norm": 1.3515625, + "learning_rate": 6.123951581245815e-06, + "loss": 1.2048, + "step": 2555 + }, + { + "epoch": 0.6656915325857305, + "grad_norm": 1.2890625, + "learning_rate": 6.082154017181825e-06, + "loss": 1.1827, + "step": 2560 + }, + { + "epoch": 0.666991711360312, + "grad_norm": 1.28125, + "learning_rate": 6.0404371549081046e-06, + "loss": 1.1623, + "step": 2565 + }, + { + "epoch": 0.6682918901348935, + "grad_norm": 1.2890625, + "learning_rate": 5.998801853729865e-06, + "loss": 1.1126, + "step": 2570 + }, + { + "epoch": 0.6695920689094751, + "grad_norm": 1.3671875, + "learning_rate": 5.957248971272285e-06, + "loss": 1.1112, + "step": 2575 + }, + { + "epoch": 0.6708922476840565, + "grad_norm": 1.3125, + "learning_rate": 5.915779363462832e-06, + "loss": 1.1893, + "step": 2580 + }, + { + "epoch": 0.6721924264586381, + "grad_norm": 1.3203125, + "learning_rate": 5.874393884513644e-06, + "loss": 1.1891, + "step": 2585 + }, + { + "epoch": 0.6734926052332195, + "grad_norm": 1.2578125, + "learning_rate": 5.833093386903933e-06, + "loss": 1.1045, + "step": 2590 + }, + { + "epoch": 0.6747927840078011, + "grad_norm": 1.2578125, + "learning_rate": 5.791878721362416e-06, + "loss": 1.219, + "step": 2595 + }, + { + "epoch": 0.6760929627823826, + "grad_norm": 1.390625, + "learning_rate": 5.750750736849795e-06, + "loss": 1.169, + "step": 2600 + }, + { + "epoch": 0.6760929627823826, + "eval_loss": 1.1685597896575928, + "eval_runtime": 577.6155, + "eval_samples_per_second": 11.828, + "eval_steps_per_second": 3.944, + "step": 2600 + }, + { + "epoch": 0.6773931415569641, + "grad_norm": 1.3125, + "learning_rate": 5.709710280541288e-06, + "loss": 1.1884, + "step": 2605 + }, + { + "epoch": 0.6786933203315456, + "grad_norm": 1.3125, + "learning_rate": 5.668758197809142e-06, + "loss": 1.1738, + "step": 2610 + }, + { + "epoch": 0.679993499106127, + "grad_norm": 1.3046875, + "learning_rate": 5.627895332205253e-06, + "loss": 1.1211, + "step": 2615 + }, + { + "epoch": 0.6812936778807086, + "grad_norm": 1.3984375, + "learning_rate": 5.587122525443771e-06, + "loss": 1.1684, + "step": 2620 + }, + { + "epoch": 0.6825938566552902, + "grad_norm": 1.3515625, + "learning_rate": 5.546440617383768e-06, + "loss": 1.1769, + "step": 2625 + }, + { + "epoch": 0.6838940354298716, + "grad_norm": 1.2578125, + "learning_rate": 5.5058504460119475e-06, + "loss": 1.134, + "step": 2630 + }, + { + "epoch": 0.6851942142044531, + "grad_norm": 1.3125, + "learning_rate": 5.4653528474253596e-06, + "loss": 1.1147, + "step": 2635 + }, + { + "epoch": 0.6864943929790346, + "grad_norm": 1.3515625, + "learning_rate": 5.4249486558142065e-06, + "loss": 1.2026, + "step": 2640 + }, + { + "epoch": 0.6877945717536161, + "grad_norm": 1.375, + "learning_rate": 5.384638703444636e-06, + "loss": 1.1563, + "step": 2645 + }, + { + "epoch": 0.6890947505281976, + "grad_norm": 1.296875, + "learning_rate": 5.3444238206416135e-06, + "loss": 1.1765, + "step": 2650 + }, + { + "epoch": 0.6903949293027791, + "grad_norm": 1.421875, + "learning_rate": 5.304304835771803e-06, + "loss": 1.1534, + "step": 2655 + }, + { + "epoch": 0.6916951080773607, + "grad_norm": 1.359375, + "learning_rate": 5.264282575226534e-06, + "loss": 1.1435, + "step": 2660 + }, + { + "epoch": 0.6929952868519421, + "grad_norm": 1.390625, + "learning_rate": 5.224357863404739e-06, + "loss": 1.1568, + "step": 2665 + }, + { + "epoch": 0.6942954656265237, + "grad_norm": 1.28125, + "learning_rate": 5.1845315226960035e-06, + "loss": 1.1412, + "step": 2670 + }, + { + "epoch": 0.6955956444011051, + "grad_norm": 1.25, + "learning_rate": 5.144804373463607e-06, + "loss": 1.1559, + "step": 2675 + }, + { + "epoch": 0.6968958231756867, + "grad_norm": 1.3984375, + "learning_rate": 5.105177234027639e-06, + "loss": 1.1444, + "step": 2680 + }, + { + "epoch": 0.6981960019502682, + "grad_norm": 1.3203125, + "learning_rate": 5.0656509206481355e-06, + "loss": 1.1654, + "step": 2685 + }, + { + "epoch": 0.6994961807248496, + "grad_norm": 1.515625, + "learning_rate": 5.026226247508258e-06, + "loss": 1.2098, + "step": 2690 + }, + { + "epoch": 0.7007963594994312, + "grad_norm": 1.4140625, + "learning_rate": 4.986904026697544e-06, + "loss": 1.1362, + "step": 2695 + }, + { + "epoch": 0.7020965382740126, + "grad_norm": 1.2578125, + "learning_rate": 4.947685068195157e-06, + "loss": 1.1308, + "step": 2700 + }, + { + "epoch": 0.7033967170485942, + "grad_norm": 1.28125, + "learning_rate": 4.908570179853209e-06, + "loss": 1.1441, + "step": 2705 + }, + { + "epoch": 0.7046968958231757, + "grad_norm": 1.3671875, + "learning_rate": 4.869560167380123e-06, + "loss": 1.2202, + "step": 2710 + }, + { + "epoch": 0.7059970745977572, + "grad_norm": 1.3046875, + "learning_rate": 4.830655834324044e-06, + "loss": 1.1379, + "step": 2715 + }, + { + "epoch": 0.7072972533723387, + "grad_norm": 1.34375, + "learning_rate": 4.791857982056267e-06, + "loss": 1.1414, + "step": 2720 + }, + { + "epoch": 0.7085974321469202, + "grad_norm": 1.3046875, + "learning_rate": 4.753167409754744e-06, + "loss": 1.1287, + "step": 2725 + }, + { + "epoch": 0.7098976109215017, + "grad_norm": 1.3203125, + "learning_rate": 4.714584914387632e-06, + "loss": 1.2116, + "step": 2730 + }, + { + "epoch": 0.7111977896960832, + "grad_norm": 1.2578125, + "learning_rate": 4.676111290696837e-06, + "loss": 1.1359, + "step": 2735 + }, + { + "epoch": 0.7124979684706647, + "grad_norm": 1.34375, + "learning_rate": 4.6377473311817025e-06, + "loss": 1.1473, + "step": 2740 + }, + { + "epoch": 0.7137981472452463, + "grad_norm": 1.375, + "learning_rate": 4.599493826082626e-06, + "loss": 1.1692, + "step": 2745 + }, + { + "epoch": 0.7150983260198277, + "grad_norm": 1.28125, + "learning_rate": 4.561351563364833e-06, + "loss": 1.1306, + "step": 2750 + }, + { + "epoch": 0.7163985047944093, + "grad_norm": 1.4375, + "learning_rate": 4.523321328702101e-06, + "loss": 1.1438, + "step": 2755 + }, + { + "epoch": 0.7176986835689907, + "grad_norm": 1.265625, + "learning_rate": 4.48540390546061e-06, + "loss": 1.1375, + "step": 2760 + }, + { + "epoch": 0.7189988623435722, + "grad_norm": 1.3203125, + "learning_rate": 4.447600074682781e-06, + "loss": 1.1413, + "step": 2765 + }, + { + "epoch": 0.7202990411181538, + "grad_norm": 1.375, + "learning_rate": 4.4099106150712134e-06, + "loss": 1.1749, + "step": 2770 + }, + { + "epoch": 0.7215992198927352, + "grad_norm": 1.2890625, + "learning_rate": 4.372336302972622e-06, + "loss": 1.155, + "step": 2775 + }, + { + "epoch": 0.7228993986673168, + "grad_norm": 1.5703125, + "learning_rate": 4.334877912361851e-06, + "loss": 1.1569, + "step": 2780 + }, + { + "epoch": 0.7241995774418982, + "grad_norm": 1.296875, + "learning_rate": 4.297536214825951e-06, + "loss": 1.1328, + "step": 2785 + }, + { + "epoch": 0.7254997562164798, + "grad_norm": 1.296875, + "learning_rate": 4.260311979548245e-06, + "loss": 1.1654, + "step": 2790 + }, + { + "epoch": 0.7267999349910613, + "grad_norm": 1.296875, + "learning_rate": 4.2232059732925305e-06, + "loss": 1.174, + "step": 2795 + }, + { + "epoch": 0.7281001137656428, + "grad_norm": 1.3125, + "learning_rate": 4.186218960387247e-06, + "loss": 1.123, + "step": 2800 + }, + { + "epoch": 0.7281001137656428, + "eval_loss": 1.1681982278823853, + "eval_runtime": 577.5234, + "eval_samples_per_second": 11.83, + "eval_steps_per_second": 3.944, + "step": 2800 + }, + { + "epoch": 0.7294002925402243, + "grad_norm": 1.3671875, + "learning_rate": 4.1493517027097644e-06, + "loss": 1.1895, + "step": 2805 + }, + { + "epoch": 0.7307004713148058, + "grad_norm": 1.265625, + "learning_rate": 4.112604959670655e-06, + "loss": 1.1323, + "step": 2810 + }, + { + "epoch": 0.7320006500893873, + "grad_norm": 1.28125, + "learning_rate": 4.075979488198092e-06, + "loss": 1.1629, + "step": 2815 + }, + { + "epoch": 0.7333008288639687, + "grad_norm": 1.328125, + "learning_rate": 4.039476042722205e-06, + "loss": 1.1688, + "step": 2820 + }, + { + "epoch": 0.7346010076385503, + "grad_norm": 1.3203125, + "learning_rate": 4.003095375159598e-06, + "loss": 1.124, + "step": 2825 + }, + { + "epoch": 0.7359011864131318, + "grad_norm": 1.3203125, + "learning_rate": 3.966838234897817e-06, + "loss": 1.1642, + "step": 2830 + }, + { + "epoch": 0.7372013651877133, + "grad_norm": 1.421875, + "learning_rate": 3.930705368779931e-06, + "loss": 1.1488, + "step": 2835 + }, + { + "epoch": 0.7385015439622948, + "grad_norm": 1.3203125, + "learning_rate": 3.894697521089161e-06, + "loss": 1.1468, + "step": 2840 + }, + { + "epoch": 0.7398017227368763, + "grad_norm": 1.3671875, + "learning_rate": 3.858815433533509e-06, + "loss": 1.1851, + "step": 2845 + }, + { + "epoch": 0.7411019015114578, + "grad_norm": 1.3359375, + "learning_rate": 3.82305984523053e-06, + "loss": 1.2236, + "step": 2850 + }, + { + "epoch": 0.7424020802860394, + "grad_norm": 1.3203125, + "learning_rate": 3.7874314926920664e-06, + "loss": 1.1327, + "step": 2855 + }, + { + "epoch": 0.7437022590606208, + "grad_norm": 1.28125, + "learning_rate": 3.751931109809105e-06, + "loss": 1.1473, + "step": 2860 + }, + { + "epoch": 0.7450024378352024, + "grad_norm": 1.2890625, + "learning_rate": 3.716559427836639e-06, + "loss": 1.1859, + "step": 2865 + }, + { + "epoch": 0.7463026166097838, + "grad_norm": 1.3359375, + "learning_rate": 3.681317175378627e-06, + "loss": 1.2249, + "step": 2870 + }, + { + "epoch": 0.7476027953843654, + "grad_norm": 1.5, + "learning_rate": 3.646205078372952e-06, + "loss": 1.1738, + "step": 2875 + }, + { + "epoch": 0.7489029741589469, + "grad_norm": 1.328125, + "learning_rate": 3.6112238600765104e-06, + "loss": 1.1335, + "step": 2880 + }, + { + "epoch": 0.7502031529335283, + "grad_norm": 1.34375, + "learning_rate": 3.576374241050279e-06, + "loss": 1.1776, + "step": 2885 + }, + { + "epoch": 0.7515033317081099, + "grad_norm": 1.3671875, + "learning_rate": 3.5416569391444857e-06, + "loss": 1.1905, + "step": 2890 + }, + { + "epoch": 0.7528035104826913, + "grad_norm": 1.46875, + "learning_rate": 3.5070726694838376e-06, + "loss": 1.1748, + "step": 2895 + }, + { + "epoch": 0.7541036892572729, + "grad_norm": 1.3046875, + "learning_rate": 3.4726221444527496e-06, + "loss": 1.1324, + "step": 2900 + }, + { + "epoch": 0.7554038680318543, + "grad_norm": 1.234375, + "learning_rate": 3.438306073680724e-06, + "loss": 1.1313, + "step": 2905 + }, + { + "epoch": 0.7567040468064359, + "grad_norm": 1.3125, + "learning_rate": 3.404125164027684e-06, + "loss": 1.1154, + "step": 2910 + }, + { + "epoch": 0.7580042255810174, + "grad_norm": 1.34375, + "learning_rate": 3.370080119569451e-06, + "loss": 1.1652, + "step": 2915 + }, + { + "epoch": 0.7593044043555989, + "grad_norm": 1.3828125, + "learning_rate": 3.3361716415832147e-06, + "loss": 1.1534, + "step": 2920 + }, + { + "epoch": 0.7606045831301804, + "grad_norm": 1.25, + "learning_rate": 3.30240042853311e-06, + "loss": 1.1351, + "step": 2925 + }, + { + "epoch": 0.7619047619047619, + "grad_norm": 1.3671875, + "learning_rate": 3.2687671760558016e-06, + "loss": 1.0693, + "step": 2930 + }, + { + "epoch": 0.7632049406793434, + "grad_norm": 1.296875, + "learning_rate": 3.235272576946191e-06, + "loss": 1.1752, + "step": 2935 + }, + { + "epoch": 0.764505119453925, + "grad_norm": 1.3359375, + "learning_rate": 3.2019173211431154e-06, + "loss": 1.1319, + "step": 2940 + }, + { + "epoch": 0.7658052982285064, + "grad_norm": 1.2421875, + "learning_rate": 3.168702095715146e-06, + "loss": 1.1176, + "step": 2945 + }, + { + "epoch": 0.767105477003088, + "grad_norm": 1.296875, + "learning_rate": 3.135627584846449e-06, + "loss": 1.1512, + "step": 2950 + }, + { + "epoch": 0.7684056557776694, + "grad_norm": 1.28125, + "learning_rate": 3.102694469822668e-06, + "loss": 1.1601, + "step": 2955 + }, + { + "epoch": 0.769705834552251, + "grad_norm": 1.2578125, + "learning_rate": 3.0699034290169073e-06, + "loss": 1.1384, + "step": 2960 + }, + { + "epoch": 0.7710060133268324, + "grad_norm": 1.40625, + "learning_rate": 3.037255137875751e-06, + "loss": 1.1272, + "step": 2965 + }, + { + "epoch": 0.7723061921014139, + "grad_norm": 1.3203125, + "learning_rate": 3.004750268905363e-06, + "loss": 1.1597, + "step": 2970 + }, + { + "epoch": 0.7736063708759955, + "grad_norm": 1.375, + "learning_rate": 2.9723894916576103e-06, + "loss": 1.1599, + "step": 2975 + }, + { + "epoch": 0.7749065496505769, + "grad_norm": 1.3125, + "learning_rate": 2.940173472716301e-06, + "loss": 1.1005, + "step": 2980 + }, + { + "epoch": 0.7762067284251585, + "grad_norm": 1.359375, + "learning_rate": 2.908102875683415e-06, + "loss": 1.173, + "step": 2985 + }, + { + "epoch": 0.7775069071997399, + "grad_norm": 1.28125, + "learning_rate": 2.8761783611654826e-06, + "loss": 1.1409, + "step": 2990 + }, + { + "epoch": 0.7788070859743215, + "grad_norm": 1.3359375, + "learning_rate": 2.8444005867599343e-06, + "loss": 1.1506, + "step": 2995 + }, + { + "epoch": 0.780107264748903, + "grad_norm": 1.234375, + "learning_rate": 2.8127702070415787e-06, + "loss": 1.0825, + "step": 3000 + }, + { + "epoch": 0.780107264748903, + "eval_loss": 1.1680325269699097, + "eval_runtime": 577.7067, + "eval_samples_per_second": 11.826, + "eval_steps_per_second": 3.943, + "step": 3000 + }, + { + "epoch": 0.7814074435234845, + "grad_norm": 1.296875, + "learning_rate": 2.781287873549119e-06, + "loss": 1.1626, + "step": 3005 + }, + { + "epoch": 0.782707622298066, + "grad_norm": 1.2890625, + "learning_rate": 2.7499542347717166e-06, + "loss": 1.1208, + "step": 3010 + }, + { + "epoch": 0.7840078010726474, + "grad_norm": 1.453125, + "learning_rate": 2.71876993613565e-06, + "loss": 1.1578, + "step": 3015 + }, + { + "epoch": 0.785307979847229, + "grad_norm": 1.3125, + "learning_rate": 2.687735619991009e-06, + "loss": 1.166, + "step": 3020 + }, + { + "epoch": 0.7866081586218105, + "grad_norm": 1.390625, + "learning_rate": 2.6568519255984736e-06, + "loss": 1.1816, + "step": 3025 + }, + { + "epoch": 0.787908337396392, + "grad_norm": 1.34375, + "learning_rate": 2.6261194891161325e-06, + "loss": 1.1414, + "step": 3030 + }, + { + "epoch": 0.7892085161709735, + "grad_norm": 1.265625, + "learning_rate": 2.5955389435863953e-06, + "loss": 1.1011, + "step": 3035 + }, + { + "epoch": 0.790508694945555, + "grad_norm": 1.4140625, + "learning_rate": 2.5651109189229375e-06, + "loss": 1.1629, + "step": 3040 + }, + { + "epoch": 0.7918088737201365, + "grad_norm": 1.359375, + "learning_rate": 2.5348360418977334e-06, + "loss": 1.1627, + "step": 3045 + }, + { + "epoch": 0.793109052494718, + "grad_norm": 1.3984375, + "learning_rate": 2.5047149361281462e-06, + "loss": 1.1426, + "step": 3050 + }, + { + "epoch": 0.7944092312692995, + "grad_norm": 1.328125, + "learning_rate": 2.4747482220640764e-06, + "loss": 1.1909, + "step": 3055 + }, + { + "epoch": 0.7957094100438811, + "grad_norm": 1.3203125, + "learning_rate": 2.4449365169751916e-06, + "loss": 1.2272, + "step": 3060 + }, + { + "epoch": 0.7970095888184625, + "grad_norm": 1.34375, + "learning_rate": 2.4152804349382007e-06, + "loss": 1.1961, + "step": 3065 + }, + { + "epoch": 0.7983097675930441, + "grad_norm": 1.3046875, + "learning_rate": 2.3857805868242103e-06, + "loss": 1.1709, + "step": 3070 + }, + { + "epoch": 0.7996099463676255, + "grad_norm": 1.4453125, + "learning_rate": 2.3564375802861383e-06, + "loss": 1.1964, + "step": 3075 + }, + { + "epoch": 0.800910125142207, + "grad_norm": 1.328125, + "learning_rate": 2.32725201974621e-06, + "loss": 1.1836, + "step": 3080 + }, + { + "epoch": 0.8022103039167886, + "grad_norm": 1.328125, + "learning_rate": 2.2982245063834828e-06, + "loss": 1.1997, + "step": 3085 + }, + { + "epoch": 0.80351048269137, + "grad_norm": 1.2578125, + "learning_rate": 2.2693556381214934e-06, + "loss": 1.1136, + "step": 3090 + }, + { + "epoch": 0.8048106614659516, + "grad_norm": 1.2890625, + "learning_rate": 2.240646009615912e-06, + "loss": 1.1887, + "step": 3095 + }, + { + "epoch": 0.806110840240533, + "grad_norm": 1.3359375, + "learning_rate": 2.212096212242316e-06, + "loss": 1.1503, + "step": 3100 + }, + { + "epoch": 0.8074110190151146, + "grad_norm": 1.34375, + "learning_rate": 2.1837068340839964e-06, + "loss": 1.1761, + "step": 3105 + }, + { + "epoch": 0.8087111977896961, + "grad_norm": 1.390625, + "learning_rate": 2.155478459919843e-06, + "loss": 1.1851, + "step": 3110 + }, + { + "epoch": 0.8100113765642776, + "grad_norm": 1.2734375, + "learning_rate": 2.127411671212315e-06, + "loss": 1.1357, + "step": 3115 + }, + { + "epoch": 0.8113115553388591, + "grad_norm": 1.3046875, + "learning_rate": 2.09950704609544e-06, + "loss": 1.1792, + "step": 3120 + }, + { + "epoch": 0.8126117341134406, + "grad_norm": 1.3203125, + "learning_rate": 2.071765159362924e-06, + "loss": 1.1707, + "step": 3125 + }, + { + "epoch": 0.8139119128880221, + "grad_norm": 1.265625, + "learning_rate": 2.044186582456298e-06, + "loss": 1.1201, + "step": 3130 + }, + { + "epoch": 0.8152120916626036, + "grad_norm": 1.25, + "learning_rate": 2.016771883453165e-06, + "loss": 1.1181, + "step": 3135 + }, + { + "epoch": 0.8165122704371851, + "grad_norm": 1.40625, + "learning_rate": 1.9895216270554764e-06, + "loss": 1.1251, + "step": 3140 + }, + { + "epoch": 0.8178124492117667, + "grad_norm": 1.3984375, + "learning_rate": 1.9624363745779184e-06, + "loss": 1.17, + "step": 3145 + }, + { + "epoch": 0.8191126279863481, + "grad_norm": 1.296875, + "learning_rate": 1.935516683936338e-06, + "loss": 1.1976, + "step": 3150 + }, + { + "epoch": 0.8204128067609296, + "grad_norm": 1.2734375, + "learning_rate": 1.908763109636257e-06, + "loss": 1.1667, + "step": 3155 + }, + { + "epoch": 0.8217129855355111, + "grad_norm": 1.3203125, + "learning_rate": 1.8821762027614464e-06, + "loss": 1.1874, + "step": 3160 + }, + { + "epoch": 0.8230131643100926, + "grad_norm": 1.28125, + "learning_rate": 1.8557565109625753e-06, + "loss": 1.1837, + "step": 3165 + }, + { + "epoch": 0.8243133430846742, + "grad_norm": 1.296875, + "learning_rate": 1.8295045784459386e-06, + "loss": 1.0932, + "step": 3170 + }, + { + "epoch": 0.8256135218592556, + "grad_norm": 1.2890625, + "learning_rate": 1.8034209459622288e-06, + "loss": 1.1958, + "step": 3175 + }, + { + "epoch": 0.8269137006338372, + "grad_norm": 1.2890625, + "learning_rate": 1.7775061507954239e-06, + "loss": 1.1478, + "step": 3180 + }, + { + "epoch": 0.8282138794084186, + "grad_norm": 1.3203125, + "learning_rate": 1.7517607267516845e-06, + "loss": 1.2405, + "step": 3185 + }, + { + "epoch": 0.8295140581830002, + "grad_norm": 1.453125, + "learning_rate": 1.7261852041483961e-06, + "loss": 1.1547, + "step": 3190 + }, + { + "epoch": 0.8308142369575817, + "grad_norm": 1.3046875, + "learning_rate": 1.7007801098032162e-06, + "loss": 1.2307, + "step": 3195 + }, + { + "epoch": 0.8321144157321632, + "grad_norm": 1.3671875, + "learning_rate": 1.6755459670232454e-06, + "loss": 1.2208, + "step": 3200 + }, + { + "epoch": 0.8321144157321632, + "eval_loss": 1.1679521799087524, + "eval_runtime": 577.5831, + "eval_samples_per_second": 11.829, + "eval_steps_per_second": 3.944, + "step": 3200 + }, + { + "epoch": 0.8334145945067447, + "grad_norm": 1.3984375, + "learning_rate": 1.6504832955942251e-06, + "loss": 1.1363, + "step": 3205 + }, + { + "epoch": 0.8347147732813262, + "grad_norm": 1.2734375, + "learning_rate": 1.6255926117698485e-06, + "loss": 1.2079, + "step": 3210 + }, + { + "epoch": 0.8360149520559077, + "grad_norm": 1.3359375, + "learning_rate": 1.6008744282611189e-06, + "loss": 1.205, + "step": 3215 + }, + { + "epoch": 0.8373151308304891, + "grad_norm": 1.3671875, + "learning_rate": 1.576329254225788e-06, + "loss": 1.1157, + "step": 3220 + }, + { + "epoch": 0.8386153096050707, + "grad_norm": 1.28125, + "learning_rate": 1.551957595257878e-06, + "loss": 1.1672, + "step": 3225 + }, + { + "epoch": 0.8399154883796522, + "grad_norm": 1.3046875, + "learning_rate": 1.527759953377247e-06, + "loss": 1.1382, + "step": 3230 + }, + { + "epoch": 0.8412156671542337, + "grad_norm": 1.25, + "learning_rate": 1.5037368270192765e-06, + "loss": 1.145, + "step": 3235 + }, + { + "epoch": 0.8425158459288152, + "grad_norm": 1.3203125, + "learning_rate": 1.4798887110245686e-06, + "loss": 1.1859, + "step": 3240 + }, + { + "epoch": 0.8438160247033967, + "grad_norm": 1.34375, + "learning_rate": 1.4562160966287886e-06, + "loss": 1.1264, + "step": 3245 + }, + { + "epoch": 0.8451162034779782, + "grad_norm": 1.34375, + "learning_rate": 1.4327194714525217e-06, + "loss": 1.121, + "step": 3250 + }, + { + "epoch": 0.8464163822525598, + "grad_norm": 1.296875, + "learning_rate": 1.4093993194912437e-06, + "loss": 1.1104, + "step": 3255 + }, + { + "epoch": 0.8477165610271412, + "grad_norm": 1.3359375, + "learning_rate": 1.3862561211053405e-06, + "loss": 1.1791, + "step": 3260 + }, + { + "epoch": 0.8490167398017228, + "grad_norm": 1.3203125, + "learning_rate": 1.3632903530102171e-06, + "loss": 1.1554, + "step": 3265 + }, + { + "epoch": 0.8503169185763042, + "grad_norm": 1.3046875, + "learning_rate": 1.3405024882664808e-06, + "loss": 1.1313, + "step": 3270 + }, + { + "epoch": 0.8516170973508858, + "grad_norm": 1.296875, + "learning_rate": 1.3178929962701981e-06, + "loss": 1.16, + "step": 3275 + }, + { + "epoch": 0.8529172761254673, + "grad_norm": 1.3046875, + "learning_rate": 1.2954623427432177e-06, + "loss": 1.1518, + "step": 3280 + }, + { + "epoch": 0.8542174549000487, + "grad_norm": 1.46875, + "learning_rate": 1.2732109897235822e-06, + "loss": 1.1473, + "step": 3285 + }, + { + "epoch": 0.8555176336746303, + "grad_norm": 1.2890625, + "learning_rate": 1.2511393955560192e-06, + "loss": 1.1437, + "step": 3290 + }, + { + "epoch": 0.8568178124492117, + "grad_norm": 1.3515625, + "learning_rate": 1.229248014882476e-06, + "loss": 1.1226, + "step": 3295 + }, + { + "epoch": 0.8581179912237933, + "grad_norm": 1.328125, + "learning_rate": 1.207537298632787e-06, + "loss": 1.1858, + "step": 3300 + }, + { + "epoch": 0.8594181699983747, + "grad_norm": 1.3671875, + "learning_rate": 1.1860076940153575e-06, + "loss": 1.1549, + "step": 3305 + }, + { + "epoch": 0.8607183487729563, + "grad_norm": 2.15625, + "learning_rate": 1.1646596445079705e-06, + "loss": 1.1501, + "step": 3310 + }, + { + "epoch": 0.8620185275475378, + "grad_norm": 1.3046875, + "learning_rate": 1.1434935898486377e-06, + "loss": 1.1422, + "step": 3315 + }, + { + "epoch": 0.8633187063221193, + "grad_norm": 1.3125, + "learning_rate": 1.1225099660265526e-06, + "loss": 1.1394, + "step": 3320 + }, + { + "epoch": 0.8646188850967008, + "grad_norm": 1.2890625, + "learning_rate": 1.1017092052731004e-06, + "loss": 1.1111, + "step": 3325 + }, + { + "epoch": 0.8659190638712823, + "grad_norm": 1.390625, + "learning_rate": 1.0810917360529681e-06, + "loss": 1.2065, + "step": 3330 + }, + { + "epoch": 0.8672192426458638, + "grad_norm": 1.296875, + "learning_rate": 1.0606579830553009e-06, + "loss": 1.1393, + "step": 3335 + }, + { + "epoch": 0.8685194214204454, + "grad_norm": 1.3125, + "learning_rate": 1.0404083671849674e-06, + "loss": 1.1753, + "step": 3340 + }, + { + "epoch": 0.8698196001950268, + "grad_norm": 1.3828125, + "learning_rate": 1.0203433055538904e-06, + "loss": 1.1847, + "step": 3345 + }, + { + "epoch": 0.8711197789696083, + "grad_norm": 1.3125, + "learning_rate": 1.0004632114724388e-06, + "loss": 1.1618, + "step": 3350 + }, + { + "epoch": 0.8724199577441898, + "grad_norm": 1.4453125, + "learning_rate": 9.807684944409368e-07, + "loss": 1.1432, + "step": 3355 + }, + { + "epoch": 0.8737201365187713, + "grad_norm": 1.3125, + "learning_rate": 9.61259560141211e-07, + "loss": 1.2046, + "step": 3360 + }, + { + "epoch": 0.8750203152933529, + "grad_norm": 1.34375, + "learning_rate": 9.419368104282467e-07, + "loss": 1.1266, + "step": 3365 + }, + { + "epoch": 0.8763204940679343, + "grad_norm": 1.3046875, + "learning_rate": 9.228006433218961e-07, + "loss": 1.1734, + "step": 3370 + }, + { + "epoch": 0.8776206728425159, + "grad_norm": 1.3671875, + "learning_rate": 9.038514529986941e-07, + "loss": 1.1328, + "step": 3375 + }, + { + "epoch": 0.8789208516170973, + "grad_norm": 1.6171875, + "learning_rate": 8.850896297837275e-07, + "loss": 1.2079, + "step": 3380 + }, + { + "epoch": 0.8802210303916789, + "grad_norm": 1.265625, + "learning_rate": 8.665155601426046e-07, + "loss": 1.1265, + "step": 3385 + }, + { + "epoch": 0.8815212091662603, + "grad_norm": 1.296875, + "learning_rate": 8.481296266734873e-07, + "loss": 1.141, + "step": 3390 + }, + { + "epoch": 0.8828213879408419, + "grad_norm": 1.3125, + "learning_rate": 8.299322080992112e-07, + "loss": 1.183, + "step": 3395 + }, + { + "epoch": 0.8841215667154234, + "grad_norm": 1.3203125, + "learning_rate": 8.119236792594897e-07, + "loss": 1.129, + "step": 3400 + }, + { + "epoch": 0.8841215667154234, + "eval_loss": 1.1679151058197021, + "eval_runtime": 577.5628, + "eval_samples_per_second": 11.829, + "eval_steps_per_second": 3.944, + "step": 3400 + }, + { + "epoch": 0.8854217454900049, + "grad_norm": 1.3203125, + "learning_rate": 7.94104411103187e-07, + "loss": 1.1262, + "step": 3405 + }, + { + "epoch": 0.8867219242645864, + "grad_norm": 1.296875, + "learning_rate": 7.764747706806786e-07, + "loss": 1.1873, + "step": 3410 + }, + { + "epoch": 0.8880221030391678, + "grad_norm": 1.34375, + "learning_rate": 7.59035121136289e-07, + "loss": 1.2039, + "step": 3415 + }, + { + "epoch": 0.8893222818137494, + "grad_norm": 1.3515625, + "learning_rate": 7.417858217008222e-07, + "loss": 1.1622, + "step": 3420 + }, + { + "epoch": 0.8906224605883309, + "grad_norm": 1.2890625, + "learning_rate": 7.247272276841422e-07, + "loss": 1.1862, + "step": 3425 + }, + { + "epoch": 0.8919226393629124, + "grad_norm": 1.3515625, + "learning_rate": 7.07859690467877e-07, + "loss": 1.1924, + "step": 3430 + }, + { + "epoch": 0.8932228181374939, + "grad_norm": 1.3515625, + "learning_rate": 6.911835574981573e-07, + "loss": 1.1518, + "step": 3435 + }, + { + "epoch": 0.8945229969120754, + "grad_norm": 1.296875, + "learning_rate": 6.746991722784813e-07, + "loss": 1.1507, + "step": 3440 + }, + { + "epoch": 0.8958231756866569, + "grad_norm": 1.296875, + "learning_rate": 6.584068743626238e-07, + "loss": 1.16, + "step": 3445 + }, + { + "epoch": 0.8971233544612384, + "grad_norm": 1.2890625, + "learning_rate": 6.423069993476483e-07, + "loss": 1.1328, + "step": 3450 + }, + { + "epoch": 0.8984235332358199, + "grad_norm": 1.3125, + "learning_rate": 6.263998788669956e-07, + "loss": 1.1424, + "step": 3455 + }, + { + "epoch": 0.8997237120104015, + "grad_norm": 1.3125, + "learning_rate": 6.106858405836491e-07, + "loss": 1.0907, + "step": 3460 + }, + { + "epoch": 0.9010238907849829, + "grad_norm": 1.296875, + "learning_rate": 5.951652081833836e-07, + "loss": 1.2033, + "step": 3465 + }, + { + "epoch": 0.9023240695595645, + "grad_norm": 1.3359375, + "learning_rate": 5.79838301368103e-07, + "loss": 1.2056, + "step": 3470 + }, + { + "epoch": 0.9036242483341459, + "grad_norm": 1.328125, + "learning_rate": 5.647054358492554e-07, + "loss": 1.1362, + "step": 3475 + }, + { + "epoch": 0.9049244271087274, + "grad_norm": 1.3359375, + "learning_rate": 5.497669233413227e-07, + "loss": 1.1422, + "step": 3480 + }, + { + "epoch": 0.906224605883309, + "grad_norm": 1.3359375, + "learning_rate": 5.350230715554105e-07, + "loss": 1.2309, + "step": 3485 + }, + { + "epoch": 0.9075247846578904, + "grad_norm": 1.3515625, + "learning_rate": 5.20474184192894e-07, + "loss": 1.1572, + "step": 3490 + }, + { + "epoch": 0.908824963432472, + "grad_norm": 1.3515625, + "learning_rate": 5.061205609391807e-07, + "loss": 1.1473, + "step": 3495 + }, + { + "epoch": 0.9101251422070534, + "grad_norm": 1.328125, + "learning_rate": 4.919624974575254e-07, + "loss": 1.1713, + "step": 3500 + }, + { + "epoch": 0.911425320981635, + "grad_norm": 1.3515625, + "learning_rate": 4.78000285382939e-07, + "loss": 1.1811, + "step": 3505 + }, + { + "epoch": 0.9127254997562165, + "grad_norm": 1.3046875, + "learning_rate": 4.642342123161925e-07, + "loss": 1.1762, + "step": 3510 + }, + { + "epoch": 0.914025678530798, + "grad_norm": 1.3046875, + "learning_rate": 4.5066456181788063e-07, + "loss": 1.1077, + "step": 3515 + }, + { + "epoch": 0.9153258573053795, + "grad_norm": 1.4140625, + "learning_rate": 4.372916134025873e-07, + "loss": 1.1273, + "step": 3520 + }, + { + "epoch": 0.916626036079961, + "grad_norm": 1.2890625, + "learning_rate": 4.241156425331239e-07, + "loss": 1.1142, + "step": 3525 + }, + { + "epoch": 0.9179262148545425, + "grad_norm": 1.2578125, + "learning_rate": 4.111369206148641e-07, + "loss": 1.136, + "step": 3530 + }, + { + "epoch": 0.919226393629124, + "grad_norm": 1.3125, + "learning_rate": 3.983557149901396e-07, + "loss": 1.1332, + "step": 3535 + }, + { + "epoch": 0.9205265724037055, + "grad_norm": 1.3046875, + "learning_rate": 3.857722889327464e-07, + "loss": 1.1709, + "step": 3540 + }, + { + "epoch": 0.921826751178287, + "grad_norm": 1.4140625, + "learning_rate": 3.73386901642514e-07, + "loss": 1.1097, + "step": 3545 + }, + { + "epoch": 0.9231269299528685, + "grad_norm": 1.3046875, + "learning_rate": 3.6119980823996705e-07, + "loss": 1.1426, + "step": 3550 + }, + { + "epoch": 0.92442710872745, + "grad_norm": 1.3359375, + "learning_rate": 3.492112597610742e-07, + "loss": 1.132, + "step": 3555 + }, + { + "epoch": 0.9257272875020315, + "grad_norm": 1.2890625, + "learning_rate": 3.374215031520711e-07, + "loss": 1.1641, + "step": 3560 + }, + { + "epoch": 0.927027466276613, + "grad_norm": 1.2734375, + "learning_rate": 3.258307812643813e-07, + "loss": 1.1326, + "step": 3565 + }, + { + "epoch": 0.9283276450511946, + "grad_norm": 1.328125, + "learning_rate": 3.1443933284960535e-07, + "loss": 1.1717, + "step": 3570 + }, + { + "epoch": 0.929627823825776, + "grad_norm": 1.3671875, + "learning_rate": 3.032473925546109e-07, + "loss": 1.1891, + "step": 3575 + }, + { + "epoch": 0.9309280026003576, + "grad_norm": 1.3203125, + "learning_rate": 2.9225519091669153e-07, + "loss": 1.1511, + "step": 3580 + }, + { + "epoch": 0.932228181374939, + "grad_norm": 1.3203125, + "learning_rate": 2.8146295435882767e-07, + "loss": 1.1461, + "step": 3585 + }, + { + "epoch": 0.9335283601495206, + "grad_norm": 1.3671875, + "learning_rate": 2.7087090518501004e-07, + "loss": 1.1733, + "step": 3590 + }, + { + "epoch": 0.9348285389241021, + "grad_norm": 1.2890625, + "learning_rate": 2.604792615756735e-07, + "loss": 1.1656, + "step": 3595 + }, + { + "epoch": 0.9361287176986836, + "grad_norm": 1.2734375, + "learning_rate": 2.502882375831939e-07, + "loss": 1.1435, + "step": 3600 + }, + { + "epoch": 0.9361287176986836, + "eval_loss": 1.1679141521453857, + "eval_runtime": 577.8338, + "eval_samples_per_second": 11.823, + "eval_steps_per_second": 3.942, + "step": 3600 + }, + { + "epoch": 0.9374288964732651, + "grad_norm": 1.296875, + "learning_rate": 2.4029804312748264e-07, + "loss": 1.1184, + "step": 3605 + }, + { + "epoch": 0.9387290752478465, + "grad_norm": 1.296875, + "learning_rate": 2.3050888399166026e-07, + "loss": 1.2475, + "step": 3610 + }, + { + "epoch": 0.9400292540224281, + "grad_norm": 1.2421875, + "learning_rate": 2.2092096181782208e-07, + "loss": 1.1822, + "step": 3615 + }, + { + "epoch": 0.9413294327970095, + "grad_norm": 1.2578125, + "learning_rate": 2.115344741028813e-07, + "loss": 1.1474, + "step": 3620 + }, + { + "epoch": 0.9426296115715911, + "grad_norm": 1.3203125, + "learning_rate": 2.0234961419449693e-07, + "loss": 1.1979, + "step": 3625 + }, + { + "epoch": 0.9439297903461726, + "grad_norm": 1.2890625, + "learning_rate": 1.9336657128710467e-07, + "loss": 1.1783, + "step": 3630 + }, + { + "epoch": 0.9452299691207541, + "grad_norm": 1.3203125, + "learning_rate": 1.8458553041799998e-07, + "loss": 1.1873, + "step": 3635 + }, + { + "epoch": 0.9465301478953356, + "grad_norm": 1.3125, + "learning_rate": 1.7600667246354452e-07, + "loss": 1.1468, + "step": 3640 + }, + { + "epoch": 0.9478303266699171, + "grad_norm": 1.3125, + "learning_rate": 1.6763017413542916e-07, + "loss": 1.1716, + "step": 3645 + }, + { + "epoch": 0.9491305054444986, + "grad_norm": 1.3515625, + "learning_rate": 1.5945620797704343e-07, + "loss": 1.1424, + "step": 3650 + }, + { + "epoch": 0.9504306842190802, + "grad_norm": 1.359375, + "learning_rate": 1.5148494235990963e-07, + "loss": 1.1885, + "step": 3655 + }, + { + "epoch": 0.9517308629936616, + "grad_norm": 1.3359375, + "learning_rate": 1.437165414802244e-07, + "loss": 1.1242, + "step": 3660 + }, + { + "epoch": 0.9530310417682432, + "grad_norm": 1.4453125, + "learning_rate": 1.3615116535547146e-07, + "loss": 1.1875, + "step": 3665 + }, + { + "epoch": 0.9543312205428246, + "grad_norm": 1.328125, + "learning_rate": 1.2878896982112755e-07, + "loss": 1.1149, + "step": 3670 + }, + { + "epoch": 0.9556313993174061, + "grad_norm": 1.2890625, + "learning_rate": 1.2163010652745387e-07, + "loss": 1.1524, + "step": 3675 + }, + { + "epoch": 0.9569315780919877, + "grad_norm": 1.359375, + "learning_rate": 1.146747229363665e-07, + "loss": 1.1703, + "step": 3680 + }, + { + "epoch": 0.9582317568665691, + "grad_norm": 1.328125, + "learning_rate": 1.0792296231840748e-07, + "loss": 1.199, + "step": 3685 + }, + { + "epoch": 0.9595319356411507, + "grad_norm": 1.3515625, + "learning_rate": 1.0137496374978407e-07, + "loss": 1.1646, + "step": 3690 + }, + { + "epoch": 0.9608321144157321, + "grad_norm": 1.515625, + "learning_rate": 9.503086210951306e-08, + "loss": 1.1367, + "step": 3695 + }, + { + "epoch": 0.9621322931903137, + "grad_norm": 1.5, + "learning_rate": 8.889078807663542e-08, + "loss": 1.1301, + "step": 3700 + }, + { + "epoch": 0.9634324719648951, + "grad_norm": 1.3046875, + "learning_rate": 8.295486812752829e-08, + "loss": 1.1291, + "step": 3705 + }, + { + "epoch": 0.9647326507394767, + "grad_norm": 1.7734375, + "learning_rate": 7.722322453330045e-08, + "loss": 1.1076, + "step": 3710 + }, + { + "epoch": 0.9660328295140582, + "grad_norm": 1.2734375, + "learning_rate": 7.16959753572699e-08, + "loss": 1.1985, + "step": 3715 + }, + { + "epoch": 0.9673330082886397, + "grad_norm": 1.296875, + "learning_rate": 6.637323445253475e-08, + "loss": 1.1227, + "step": 3720 + }, + { + "epoch": 0.9686331870632212, + "grad_norm": 1.328125, + "learning_rate": 6.125511145962715e-08, + "loss": 1.125, + "step": 3725 + }, + { + "epoch": 0.9699333658378027, + "grad_norm": 1.3671875, + "learning_rate": 5.634171180425641e-08, + "loss": 1.1624, + "step": 3730 + }, + { + "epoch": 0.9712335446123842, + "grad_norm": 1.421875, + "learning_rate": 5.163313669513392e-08, + "loss": 1.1263, + "step": 3735 + }, + { + "epoch": 0.9725337233869658, + "grad_norm": 1.3359375, + "learning_rate": 4.712948312189491e-08, + "loss": 1.2215, + "step": 3740 + }, + { + "epoch": 0.9738339021615472, + "grad_norm": 1.359375, + "learning_rate": 4.283084385309e-08, + "loss": 1.127, + "step": 3745 + }, + { + "epoch": 0.9751340809361287, + "grad_norm": 1.3203125, + "learning_rate": 3.873730743428561e-08, + "loss": 1.1148, + "step": 3750 + }, + { + "epoch": 0.9764342597107102, + "grad_norm": 1.3671875, + "learning_rate": 3.484895818623213e-08, + "loss": 1.1234, + "step": 3755 + }, + { + "epoch": 0.9777344384852917, + "grad_norm": 1.453125, + "learning_rate": 3.116587620313194e-08, + "loss": 1.1412, + "step": 3760 + }, + { + "epoch": 0.9790346172598733, + "grad_norm": 1.2734375, + "learning_rate": 2.76881373509863e-08, + "loss": 1.0984, + "step": 3765 + }, + { + "epoch": 0.9803347960344547, + "grad_norm": 1.2734375, + "learning_rate": 2.4415813266034373e-08, + "loss": 1.1885, + "step": 3770 + }, + { + "epoch": 0.9816349748090363, + "grad_norm": 1.375, + "learning_rate": 2.1348971353277738e-08, + "loss": 1.1402, + "step": 3775 + }, + { + "epoch": 0.9829351535836177, + "grad_norm": 1.296875, + "learning_rate": 1.848767478508928e-08, + "loss": 1.1229, + "step": 3780 + }, + { + "epoch": 0.9842353323581993, + "grad_norm": 1.34375, + "learning_rate": 1.5831982499915355e-08, + "loss": 1.2113, + "step": 3785 + }, + { + "epoch": 0.9855355111327807, + "grad_norm": 1.328125, + "learning_rate": 1.3381949201062283e-08, + "loss": 1.1621, + "step": 3790 + }, + { + "epoch": 0.9868356899073623, + "grad_norm": 1.3359375, + "learning_rate": 1.1137625355565063e-08, + "loss": 1.1413, + "step": 3795 + }, + { + "epoch": 0.9881358686819438, + "grad_norm": 1.4140625, + "learning_rate": 9.099057193150406e-09, + "loss": 1.2007, + "step": 3800 + }, + { + "epoch": 0.9881358686819438, + "eval_loss": 1.1679197549819946, + "eval_runtime": 577.8185, + "eval_samples_per_second": 11.824, + "eval_steps_per_second": 3.942, + "step": 3800 + }, + { + "epoch": 0.9894360474565252, + "grad_norm": 1.3046875, + "learning_rate": 7.266286705286396e-09, + "loss": 1.1516, + "step": 3805 + }, + { + "epoch": 0.9907362262311068, + "grad_norm": 1.4375, + "learning_rate": 5.6393516443131735e-09, + "loss": 1.1979, + "step": 3810 + }, + { + "epoch": 0.9920364050056882, + "grad_norm": 1.3046875, + "learning_rate": 4.218285522670229e-09, + "loss": 1.14, + "step": 3815 + }, + { + "epoch": 0.9933365837802698, + "grad_norm": 1.2421875, + "learning_rate": 3.003117612202511e-09, + "loss": 1.1325, + "step": 3820 + }, + { + "epoch": 0.9946367625548513, + "grad_norm": 1.2578125, + "learning_rate": 1.9938729435586833e-09, + "loss": 1.173, + "step": 3825 + }, + { + "epoch": 0.9959369413294328, + "grad_norm": 1.2578125, + "learning_rate": 1.190572305673765e-09, + "loss": 1.1441, + "step": 3830 + }, + { + "epoch": 0.9972371201040143, + "grad_norm": 1.3046875, + "learning_rate": 5.932322453461315e-10, + "loss": 1.1291, + "step": 3835 + }, + { + "epoch": 0.9985372988785958, + "grad_norm": 1.2890625, + "learning_rate": 2.0186506689001682e-10, + "loss": 1.1295, + "step": 3840 + }, + { + "epoch": 0.9998374776531773, + "grad_norm": 1.2734375, + "learning_rate": 1.647883188682364e-11, + "loss": 1.1633, + "step": 3845 + }, + { + "epoch": 1.0, + "step": 3846, + "total_flos": 2.1312002805936947e+18, + "train_loss": 1.184760999939929, + "train_runtime": 31570.962, + "train_samples_per_second": 1.949, + "train_steps_per_second": 0.122 + } + ], + "logging_steps": 5, + "max_steps": 3846, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 1000000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 2.1312002805936947e+18, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..6835d68 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e24f1da2fc924795181e388629647e671e164c2199d6e0d3e850e723bde916d +size 6097