commit ecfe10fa414a2c3df670420b384571b9f3895514 Author: ModelHub XC Date: Sun Jun 14 20:29:19 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: ramzanniaz331/llama3-8b-full-sft-v3 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..453f51d --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +library_name: transformers +license: other +base_model: ramzanniaz331/llama3.1-8b-8192-v3 +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: llama3_8b_full_sft_ramzan + results: [] +--- + + + +# llama3_8b_full_sft_ramzan + +This model is a fine-tuned version of [ramzanniaz331/llama3.1-8b-8192-v3](https://huggingface.co/ramzanniaz331/llama3.1-8b-8192-v3) on the ramzan_5k_batch_1, the ramzan_5k_batch_2, the ramzan_openhermes, the ramzan_metamath and the ramzan_aya_urdu datasets. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-06 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- gradient_accumulation_steps: 8 +- total_train_batch_size: 64 +- total_eval_batch_size: 64 +- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.03 +- num_epochs: 2.0 + +### Training results + + + +### Framework versions + +- Transformers 4.57.1 +- Pytorch 2.9.1+cu128 +- Datasets 4.0.0 +- Tokenizers 0.22.1 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..5cf4528 --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 2.0, + "total_flos": 25921569423360.0, + "train_loss": 0.9619188387709928, + "train_runtime": 4046.5288, + "train_samples_per_second": 10.494, + "train_steps_per_second": 0.164 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..9dd8030 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1 @@ +{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..4b4b357 --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 128001, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "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": false, + "transformers_version": "4.57.1", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..28e1ef5 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128009, + 128001 + ], + "pad_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.57.1" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..814c3c3 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555fd0e3a10b52c5aecc4afd6914393848ac60f927096325fd4e7cdf864fc6cf +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..df94bd1 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e91ce3ab76949f5e08cf7aab5e9c7269d87e3d21d696112ff58cd107f2da610 +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..bc86a90 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14bb668a2b817e4c6ebabf0fad284ee30a085c5301287357324e5738f507a1e0 +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..ba2aa94 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eb0431f6ce0191cbf8d30655365de0551f5ef7b477998f7e088cb913922970d +size 1168138808 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..58a7ef4 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,299 @@ +{ + "metadata": { + "total_parameters": 266240, + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..9d6f1d0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,32 @@ +{ + "additional_special_tokens": [ + { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } + ], + "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": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ca4f78c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2068 @@ +{ + "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": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|eom_id|>" + ], + "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": 131072, + "pad_token": "<|end_of_text|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..5cf4528 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 2.0, + "total_flos": 25921569423360.0, + "train_loss": 0.9619188387709928, + "train_runtime": 4046.5288, + "train_samples_per_second": 10.494, + "train_steps_per_second": 0.164 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..afdb070 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,133 @@ +{"current_steps": 5, "total_steps": 664, "loss": 1.451, "lr": 1.0000000000000002e-06, "epoch": 0.015071590052750565, "percentage": 0.75, "elapsed_time": "0:00:35", "remaining_time": "1:18:06"} +{"current_steps": 10, "total_steps": 664, "loss": 1.5943, "lr": 2.25e-06, "epoch": 0.03014318010550113, "percentage": 1.51, "elapsed_time": "0:01:06", "remaining_time": "1:12:27"} +{"current_steps": 15, "total_steps": 664, "loss": 1.4134, "lr": 3.5e-06, "epoch": 0.0452147701582517, "percentage": 2.26, "elapsed_time": "0:01:37", "remaining_time": "1:10:17"} +{"current_steps": 20, "total_steps": 664, "loss": 1.3789, "lr": 4.75e-06, "epoch": 0.06028636021100226, "percentage": 3.01, "elapsed_time": "0:02:08", "remaining_time": "1:08:54"} +{"current_steps": 25, "total_steps": 664, "loss": 1.4061, "lr": 4.999524068745182e-06, "epoch": 0.07535795026375283, "percentage": 3.77, "elapsed_time": "0:02:40", "remaining_time": "1:08:20"} +{"current_steps": 30, "total_steps": 664, "loss": 1.3465, "lr": 4.997590908585508e-06, "epoch": 0.0904295403165034, "percentage": 4.52, "elapsed_time": "0:03:09", "remaining_time": "1:06:36"} +{"current_steps": 35, "total_steps": 664, "loss": 1.3066, "lr": 4.994171922976349e-06, "epoch": 0.10550113036925396, "percentage": 5.27, "elapsed_time": "0:03:38", "remaining_time": "1:05:20"} +{"current_steps": 40, "total_steps": 664, "loss": 1.3024, "lr": 4.9892691458840415e-06, "epoch": 0.12057272042200452, "percentage": 6.02, "elapsed_time": "0:04:06", "remaining_time": "1:04:04"} +{"current_steps": 45, "total_steps": 664, "loss": 1.3222, "lr": 4.982885493987595e-06, "epoch": 0.1356443104747551, "percentage": 6.78, "elapsed_time": "0:04:37", "remaining_time": "1:03:34"} +{"current_steps": 50, "total_steps": 664, "loss": 1.3441, "lr": 4.975024764943549e-06, "epoch": 0.15071590052750566, "percentage": 7.53, "elapsed_time": "0:05:05", "remaining_time": "1:02:31"} +{"current_steps": 55, "total_steps": 664, "loss": 1.2827, "lr": 4.965691635126737e-06, "epoch": 0.1657874905802562, "percentage": 8.28, "elapsed_time": "0:05:34", "remaining_time": "1:01:40"} +{"current_steps": 60, "total_steps": 664, "loss": 1.2503, "lr": 4.95489165684829e-06, "epoch": 0.1808590806330068, "percentage": 9.04, "elapsed_time": "0:06:02", "remaining_time": "1:00:45"} +{"current_steps": 65, "total_steps": 664, "loss": 1.2252, "lr": 4.942631255052551e-06, "epoch": 0.19593067068575734, "percentage": 9.79, "elapsed_time": "0:06:29", "remaining_time": "0:59:52"} +{"current_steps": 70, "total_steps": 664, "loss": 1.2734, "lr": 4.928917723494854e-06, "epoch": 0.21100226073850792, "percentage": 10.54, "elapsed_time": "0:06:57", "remaining_time": "0:59:05"} +{"current_steps": 75, "total_steps": 664, "loss": 1.2101, "lr": 4.913759220402441e-06, "epoch": 0.22607385079125847, "percentage": 11.3, "elapsed_time": "0:07:25", "remaining_time": "0:58:17"} +{"current_steps": 80, "total_steps": 664, "loss": 1.2485, "lr": 4.897164763621104e-06, "epoch": 0.24114544084400905, "percentage": 12.05, "elapsed_time": "0:07:54", "remaining_time": "0:57:43"} +{"current_steps": 85, "total_steps": 664, "loss": 1.2243, "lr": 4.879144225250445e-06, "epoch": 0.2562170308967596, "percentage": 12.8, "elapsed_time": "0:08:25", "remaining_time": "0:57:26"} +{"current_steps": 90, "total_steps": 664, "loss": 1.2052, "lr": 4.859708325770919e-06, "epoch": 0.2712886209495102, "percentage": 13.55, "elapsed_time": "0:08:56", "remaining_time": "0:57:00"} +{"current_steps": 95, "total_steps": 664, "loss": 1.1686, "lr": 4.838868627666191e-06, "epoch": 0.2863602110022607, "percentage": 14.31, "elapsed_time": "0:09:23", "remaining_time": "0:56:17"} +{"current_steps": 100, "total_steps": 664, "loss": 1.1775, "lr": 4.81663752854457e-06, "epoch": 0.30143180105501133, "percentage": 15.06, "elapsed_time": "0:09:53", "remaining_time": "0:55:47"} +{"current_steps": 105, "total_steps": 664, "loss": 1.1722, "lr": 4.793028253763633e-06, "epoch": 0.3165033911077619, "percentage": 15.81, "elapsed_time": "0:10:24", "remaining_time": "0:55:22"} +{"current_steps": 110, "total_steps": 664, "loss": 1.1695, "lr": 4.768054848562411e-06, "epoch": 0.3315749811605124, "percentage": 16.57, "elapsed_time": "0:10:52", "remaining_time": "0:54:47"} +{"current_steps": 115, "total_steps": 664, "loss": 1.1841, "lr": 4.741732169705829e-06, "epoch": 0.346646571213263, "percentage": 17.32, "elapsed_time": "0:11:21", "remaining_time": "0:54:11"} +{"current_steps": 120, "total_steps": 664, "loss": 1.1757, "lr": 4.714075876646365e-06, "epoch": 0.3617181612660136, "percentage": 18.07, "elapsed_time": "0:11:55", "remaining_time": "0:54:01"} +{"current_steps": 125, "total_steps": 664, "loss": 1.1734, "lr": 4.6851024222081905e-06, "epoch": 0.37678975131876413, "percentage": 18.83, "elapsed_time": "0:12:22", "remaining_time": "0:53:22"} +{"current_steps": 130, "total_steps": 664, "loss": 1.127, "lr": 4.654829042799323e-06, "epoch": 0.3918613413715147, "percentage": 19.58, "elapsed_time": "0:12:51", "remaining_time": "0:52:47"} +{"current_steps": 135, "total_steps": 664, "loss": 1.2514, "lr": 4.62327374815763e-06, "epoch": 0.4069329314242653, "percentage": 20.33, "elapsed_time": "0:13:19", "remaining_time": "0:52:11"} +{"current_steps": 140, "total_steps": 664, "loss": 1.1873, "lr": 4.590455310636778e-06, "epoch": 0.42200452147701584, "percentage": 21.08, "elapsed_time": "0:13:47", "remaining_time": "0:51:38"} +{"current_steps": 145, "total_steps": 664, "loss": 1.1515, "lr": 4.556393254038486e-06, "epoch": 0.4370761115297664, "percentage": 21.84, "elapsed_time": "0:14:16", "remaining_time": "0:51:05"} +{"current_steps": 150, "total_steps": 664, "loss": 1.1197, "lr": 4.521107841997758e-06, "epoch": 0.45214770158251694, "percentage": 22.59, "elapsed_time": "0:14:46", "remaining_time": "0:50:37"} +{"current_steps": 155, "total_steps": 664, "loss": 1.1494, "lr": 4.48462006592797e-06, "epoch": 0.46721929163526754, "percentage": 23.34, "elapsed_time": "0:15:16", "remaining_time": "0:50:08"} +{"current_steps": 160, "total_steps": 664, "loss": 1.1292, "lr": 4.4469516325330055e-06, "epoch": 0.4822908816880181, "percentage": 24.1, "elapsed_time": "0:15:46", "remaining_time": "0:49:42"} +{"current_steps": 165, "total_steps": 664, "loss": 1.1195, "lr": 4.408124950893868e-06, "epoch": 0.49736247174076864, "percentage": 24.85, "elapsed_time": "0:16:14", "remaining_time": "0:49:07"} +{"current_steps": 170, "total_steps": 664, "loss": 1.1047, "lr": 4.368163119137437e-06, "epoch": 0.5124340617935192, "percentage": 25.6, "elapsed_time": "0:16:43", "remaining_time": "0:48:35"} +{"current_steps": 175, "total_steps": 664, "loss": 1.1689, "lr": 4.32708991069531e-06, "epoch": 0.5275056518462697, "percentage": 26.36, "elapsed_time": "0:17:12", "remaining_time": "0:48:04"} +{"current_steps": 180, "total_steps": 664, "loss": 0.9971, "lr": 4.284929760160917e-06, "epoch": 0.5425772418990203, "percentage": 27.11, "elapsed_time": "0:17:42", "remaining_time": "0:47:35"} +{"current_steps": 185, "total_steps": 664, "loss": 1.1245, "lr": 4.2417077487532835e-06, "epoch": 0.557648831951771, "percentage": 27.86, "elapsed_time": "0:18:12", "remaining_time": "0:47:08"} +{"current_steps": 190, "total_steps": 664, "loss": 1.1714, "lr": 4.197449589396131e-06, "epoch": 0.5727204220045214, "percentage": 28.61, "elapsed_time": "0:18:41", "remaining_time": "0:46:36"} +{"current_steps": 195, "total_steps": 664, "loss": 1.1634, "lr": 4.152181611421179e-06, "epoch": 0.587792012057272, "percentage": 29.37, "elapsed_time": "0:19:09", "remaining_time": "0:46:05"} +{"current_steps": 200, "total_steps": 664, "loss": 1.1021, "lr": 4.105930744904721e-06, "epoch": 0.6028636021100227, "percentage": 30.12, "elapsed_time": "0:19:38", "remaining_time": "0:45:34"} +{"current_steps": 205, "total_steps": 664, "loss": 1.1172, "lr": 4.058724504646834e-06, "epoch": 0.6179351921627732, "percentage": 30.87, "elapsed_time": "0:20:06", "remaining_time": "0:45:01"} +{"current_steps": 210, "total_steps": 664, "loss": 1.1375, "lr": 4.010590973802737e-06, "epoch": 0.6330067822155238, "percentage": 31.63, "elapsed_time": "0:20:34", "remaining_time": "0:44:28"} +{"current_steps": 215, "total_steps": 664, "loss": 1.1482, "lr": 3.961558787176012e-06, "epoch": 0.6480783722682742, "percentage": 32.38, "elapsed_time": "0:21:10", "remaining_time": "0:44:13"} +{"current_steps": 220, "total_steps": 664, "loss": 1.1041, "lr": 3.91165711418367e-06, "epoch": 0.6631499623210249, "percentage": 33.13, "elapsed_time": "0:21:38", "remaining_time": "0:43:40"} +{"current_steps": 225, "total_steps": 664, "loss": 1.1142, "lr": 3.860915641503161e-06, "epoch": 0.6782215523737755, "percentage": 33.89, "elapsed_time": "0:22:06", "remaining_time": "0:43:08"} +{"current_steps": 230, "total_steps": 664, "loss": 1.185, "lr": 3.809364555411667e-06, "epoch": 0.693293142426526, "percentage": 34.64, "elapsed_time": "0:22:34", "remaining_time": "0:42:34"} +{"current_steps": 235, "total_steps": 664, "loss": 1.1719, "lr": 3.75703452382818e-06, "epoch": 0.7083647324792766, "percentage": 35.39, "elapsed_time": "0:23:04", "remaining_time": "0:42:08"} +{"current_steps": 240, "total_steps": 664, "loss": 1.1238, "lr": 3.703956678069055e-06, "epoch": 0.7234363225320272, "percentage": 36.14, "elapsed_time": "0:23:32", "remaining_time": "0:41:35"} +{"current_steps": 245, "total_steps": 664, "loss": 1.0788, "lr": 3.650162594327881e-06, "epoch": 0.7385079125847777, "percentage": 36.9, "elapsed_time": "0:24:03", "remaining_time": "0:41:08"} +{"current_steps": 250, "total_steps": 664, "loss": 1.0756, "lr": 3.595684274890691e-06, "epoch": 0.7535795026375283, "percentage": 37.65, "elapsed_time": "0:24:37", "remaining_time": "0:40:47"} +{"current_steps": 255, "total_steps": 664, "loss": 1.1189, "lr": 3.5405541290976968e-06, "epoch": 0.7686510926902789, "percentage": 38.4, "elapsed_time": "0:25:07", "remaining_time": "0:40:18"} +{"current_steps": 260, "total_steps": 664, "loss": 1.0719, "lr": 3.4848049540628588e-06, "epoch": 0.7837226827430294, "percentage": 39.16, "elapsed_time": "0:25:36", "remaining_time": "0:39:46"} +{"current_steps": 265, "total_steps": 664, "loss": 1.1073, "lr": 3.4284699151627672e-06, "epoch": 0.79879427279578, "percentage": 39.91, "elapsed_time": "0:26:06", "remaining_time": "0:39:18"} +{"current_steps": 270, "total_steps": 664, "loss": 1.0891, "lr": 3.3715825263064493e-06, "epoch": 0.8138658628485306, "percentage": 40.66, "elapsed_time": "0:26:35", "remaining_time": "0:38:47"} +{"current_steps": 275, "total_steps": 664, "loss": 1.0003, "lr": 3.314176629997825e-06, "epoch": 0.8289374529012811, "percentage": 41.42, "elapsed_time": "0:27:02", "remaining_time": "0:38:15"} +{"current_steps": 280, "total_steps": 664, "loss": 1.1259, "lr": 3.25628637720269e-06, "epoch": 0.8440090429540317, "percentage": 42.17, "elapsed_time": "0:27:31", "remaining_time": "0:37:45"} +{"current_steps": 285, "total_steps": 664, "loss": 1.1505, "lr": 3.1979462070321817e-06, "epoch": 0.8590806330067822, "percentage": 42.92, "elapsed_time": "0:28:00", "remaining_time": "0:37:15"} +{"current_steps": 290, "total_steps": 664, "loss": 1.0636, "lr": 3.1391908262548382e-06, "epoch": 0.8741522230595328, "percentage": 43.67, "elapsed_time": "0:28:29", "remaining_time": "0:36:44"} +{"current_steps": 295, "total_steps": 664, "loss": 1.1475, "lr": 3.08005518864942e-06, "epoch": 0.8892238131122834, "percentage": 44.43, "elapsed_time": "0:28:58", "remaining_time": "0:36:14"} +{"current_steps": 300, "total_steps": 664, "loss": 1.0161, "lr": 3.0205744742107874e-06, "epoch": 0.9042954031650339, "percentage": 45.18, "elapsed_time": "0:29:26", "remaining_time": "0:35:43"} +{"current_steps": 305, "total_steps": 664, "loss": 1.0239, "lr": 2.9607840682211987e-06, "epoch": 0.9193669932177845, "percentage": 45.93, "elapsed_time": "0:29:56", "remaining_time": "0:35:14"} +{"current_steps": 310, "total_steps": 664, "loss": 1.0436, "lr": 2.900719540199484e-06, "epoch": 0.9344385832705351, "percentage": 46.69, "elapsed_time": "0:30:24", "remaining_time": "0:34:43"} +{"current_steps": 315, "total_steps": 664, "loss": 1.0982, "lr": 2.840416622740617e-06, "epoch": 0.9495101733232856, "percentage": 47.44, "elapsed_time": "0:30:52", "remaining_time": "0:34:12"} +{"current_steps": 320, "total_steps": 664, "loss": 1.1161, "lr": 2.7799111902582697e-06, "epoch": 0.9645817633760362, "percentage": 48.19, "elapsed_time": "0:31:23", "remaining_time": "0:33:44"} +{"current_steps": 325, "total_steps": 664, "loss": 1.066, "lr": 2.7192392376430014e-06, "epoch": 0.9796533534287868, "percentage": 48.95, "elapsed_time": "0:31:51", "remaining_time": "0:33:13"} +{"current_steps": 330, "total_steps": 664, "loss": 1.0798, "lr": 2.6584368588487727e-06, "epoch": 0.9947249434815373, "percentage": 49.7, "elapsed_time": "0:32:22", "remaining_time": "0:32:45"} +{"current_steps": 335, "total_steps": 664, "loss": 0.8717, "lr": 2.597540225420525e-06, "epoch": 1.0090429540316503, "percentage": 50.45, "elapsed_time": "0:32:49", "remaining_time": "0:32:14"} +{"current_steps": 340, "total_steps": 664, "loss": 0.7775, "lr": 2.5365855649756114e-06, "epoch": 1.0241145440844008, "percentage": 51.2, "elapsed_time": "0:33:23", "remaining_time": "0:31:48"} +{"current_steps": 345, "total_steps": 664, "loss": 0.8101, "lr": 2.475609139651855e-06, "epoch": 1.0391861341371516, "percentage": 51.96, "elapsed_time": "0:33:53", "remaining_time": "0:31:20"} +{"current_steps": 350, "total_steps": 664, "loss": 0.7067, "lr": 2.4146472245350804e-06, "epoch": 1.054257724189902, "percentage": 52.71, "elapsed_time": "0:34:23", "remaining_time": "0:30:51"} +{"current_steps": 355, "total_steps": 664, "loss": 0.7314, "lr": 2.353736086078941e-06, "epoch": 1.0693293142426525, "percentage": 53.46, "elapsed_time": "0:35:40", "remaining_time": "0:31:03"} +{"current_steps": 360, "total_steps": 664, "loss": 0.7813, "lr": 2.2929119605298787e-06, "epoch": 1.0844009042954033, "percentage": 54.22, "elapsed_time": "0:36:16", "remaining_time": "0:30:38"} +{"current_steps": 365, "total_steps": 664, "loss": 0.7792, "lr": 2.232211032370057e-06, "epoch": 1.0994724943481538, "percentage": 54.97, "elapsed_time": "0:36:46", "remaining_time": "0:30:07"} +{"current_steps": 370, "total_steps": 664, "loss": 0.8093, "lr": 2.1716694127910863e-06, "epoch": 1.1145440844009042, "percentage": 55.72, "elapsed_time": "0:37:16", "remaining_time": "0:29:37"} +{"current_steps": 375, "total_steps": 664, "loss": 0.7326, "lr": 2.1113231182113557e-06, "epoch": 1.129615674453655, "percentage": 56.48, "elapsed_time": "0:37:48", "remaining_time": "0:29:08"} +{"current_steps": 380, "total_steps": 664, "loss": 0.7069, "lr": 2.0512080488497353e-06, "epoch": 1.1446872645064055, "percentage": 57.23, "elapsed_time": "0:38:24", "remaining_time": "0:28:42"} +{"current_steps": 385, "total_steps": 664, "loss": 0.696, "lr": 1.991359967368416e-06, "epoch": 1.159758854559156, "percentage": 57.98, "elapsed_time": "0:38:56", "remaining_time": "0:28:12"} +{"current_steps": 390, "total_steps": 664, "loss": 0.7416, "lr": 1.9318144775975773e-06, "epoch": 1.1748304446119064, "percentage": 58.73, "elapsed_time": "0:39:25", "remaining_time": "0:27:41"} +{"current_steps": 395, "total_steps": 664, "loss": 0.7579, "lr": 1.8726070033545468e-06, "epoch": 1.1899020346646572, "percentage": 59.49, "elapsed_time": "0:39:54", "remaining_time": "0:27:10"} +{"current_steps": 400, "total_steps": 664, "loss": 0.7538, "lr": 1.8137727673700476e-06, "epoch": 1.2049736247174077, "percentage": 60.24, "elapsed_time": "0:40:28", "remaining_time": "0:26:42"} +{"current_steps": 405, "total_steps": 664, "loss": 0.7116, "lr": 1.7553467703340755e-06, "epoch": 1.2200452147701584, "percentage": 60.99, "elapsed_time": "0:40:58", "remaining_time": "0:26:12"} +{"current_steps": 410, "total_steps": 664, "loss": 0.7292, "lr": 1.697363770073866e-06, "epoch": 1.2351168048229089, "percentage": 61.75, "elapsed_time": "0:41:27", "remaining_time": "0:25:40"} +{"current_steps": 415, "total_steps": 664, "loss": 0.7165, "lr": 1.6398582608763457e-06, "epoch": 1.2501883948756594, "percentage": 62.5, "elapsed_time": "0:41:55", "remaining_time": "0:25:09"} +{"current_steps": 420, "total_steps": 664, "loss": 0.7987, "lr": 1.5828644529673592e-06, "epoch": 1.2652599849284099, "percentage": 63.25, "elapsed_time": "0:42:23", "remaining_time": "0:24:37"} +{"current_steps": 425, "total_steps": 664, "loss": 0.7438, "lr": 1.5264162521598893e-06, "epoch": 1.2803315749811606, "percentage": 64.01, "elapsed_time": "0:42:53", "remaining_time": "0:24:06"} +{"current_steps": 430, "total_steps": 664, "loss": 0.7239, "lr": 1.470547239683372e-06, "epoch": 1.295403165033911, "percentage": 64.76, "elapsed_time": "0:43:24", "remaining_time": "0:23:37"} +{"current_steps": 435, "total_steps": 664, "loss": 0.7571, "lr": 1.415290652206105e-06, "epoch": 1.3104747550866618, "percentage": 65.51, "elapsed_time": "0:43:53", "remaining_time": "0:23:06"} +{"current_steps": 440, "total_steps": 664, "loss": 0.7234, "lr": 1.3606793620626434e-06, "epoch": 1.3255463451394123, "percentage": 66.27, "elapsed_time": "0:44:23", "remaining_time": "0:22:35"} +{"current_steps": 445, "total_steps": 664, "loss": 0.7832, "lr": 1.3067458576979305e-06, "epoch": 1.3406179351921628, "percentage": 67.02, "elapsed_time": "0:44:58", "remaining_time": "0:22:07"} +{"current_steps": 450, "total_steps": 664, "loss": 0.7063, "lr": 1.2535222243398104e-06, "epoch": 1.3556895252449133, "percentage": 67.77, "elapsed_time": "0:45:27", "remaining_time": "0:21:37"} +{"current_steps": 455, "total_steps": 664, "loss": 0.7749, "lr": 1.2010401249114166e-06, "epoch": 1.370761115297664, "percentage": 68.52, "elapsed_time": "0:45:55", "remaining_time": "0:21:05"} +{"current_steps": 460, "total_steps": 664, "loss": 0.7036, "lr": 1.1493307811947887e-06, "epoch": 1.3858327053504145, "percentage": 69.28, "elapsed_time": "0:46:24", "remaining_time": "0:20:35"} +{"current_steps": 465, "total_steps": 664, "loss": 0.8069, "lr": 1.098424955256929e-06, "epoch": 1.400904295403165, "percentage": 70.03, "elapsed_time": "0:46:54", "remaining_time": "0:20:04"} +{"current_steps": 470, "total_steps": 664, "loss": 0.7826, "lr": 1.048352931149338e-06, "epoch": 1.4159758854559157, "percentage": 70.78, "elapsed_time": "0:47:23", "remaining_time": "0:19:33"} +{"current_steps": 475, "total_steps": 664, "loss": 0.7534, "lr": 9.991444968919318e-07, "epoch": 1.4310474755086662, "percentage": 71.54, "elapsed_time": "0:47:52", "remaining_time": "0:19:03"} +{"current_steps": 480, "total_steps": 664, "loss": 0.7342, "lr": 9.50828926752044e-07, "epoch": 1.4461190655614167, "percentage": 72.29, "elapsed_time": "0:48:22", "remaining_time": "0:18:32"} +{"current_steps": 485, "total_steps": 664, "loss": 0.7724, "lr": 9.034349638290643e-07, "epoch": 1.4611906556141672, "percentage": 73.04, "elapsed_time": "0:48:52", "remaining_time": "0:18:02"} +{"current_steps": 490, "total_steps": 664, "loss": 0.7172, "lr": 8.569908029550686e-07, "epoch": 1.4762622456669179, "percentage": 73.8, "elapsed_time": "0:49:21", "remaining_time": "0:17:31"} +{"current_steps": 495, "total_steps": 664, "loss": 0.7634, "lr": 8.115240739216182e-07, "epoch": 1.4913338357196684, "percentage": 74.55, "elapsed_time": "0:49:51", "remaining_time": "0:17:01"} +{"current_steps": 500, "total_steps": 664, "loss": 0.7434, "lr": 7.670618250426981e-07, "epoch": 1.506405425772419, "percentage": 75.3, "elapsed_time": "0:50:19", "remaining_time": "0:16:30"} +{"current_steps": 505, "total_steps": 664, "loss": 0.7432, "lr": 7.236305070635835e-07, "epoch": 1.5214770158251696, "percentage": 76.05, "elapsed_time": "0:50:49", "remaining_time": "0:15:59"} +{"current_steps": 510, "total_steps": 664, "loss": 0.6995, "lr": 6.812559574252006e-07, "epoch": 1.53654860587792, "percentage": 76.81, "elapsed_time": "0:51:18", "remaining_time": "0:15:29"} +{"current_steps": 515, "total_steps": 664, "loss": 0.7365, "lr": 6.399633848933434e-07, "epoch": 1.5516201959306706, "percentage": 77.56, "elapsed_time": "0:51:47", "remaining_time": "0:14:59"} +{"current_steps": 520, "total_steps": 664, "loss": 0.7731, "lr": 5.997773545618907e-07, "epoch": 1.5666917859834213, "percentage": 78.31, "elapsed_time": "0:52:16", "remaining_time": "0:14:28"} +{"current_steps": 525, "total_steps": 664, "loss": 0.7675, "lr": 5.607217732389503e-07, "epoch": 1.5817633760361718, "percentage": 79.07, "elapsed_time": "0:52:44", "remaining_time": "0:13:57"} +{"current_steps": 530, "total_steps": 664, "loss": 0.7298, "lr": 5.228198752246125e-07, "epoch": 1.5968349660889225, "percentage": 79.82, "elapsed_time": "0:53:13", "remaining_time": "0:13:27"} +{"current_steps": 535, "total_steps": 664, "loss": 0.8014, "lr": 4.860942084887868e-07, "epoch": 1.611906556141673, "percentage": 80.57, "elapsed_time": "0:53:44", "remaining_time": "0:12:57"} +{"current_steps": 540, "total_steps": 664, "loss": 0.7098, "lr": 4.505666212573367e-07, "epoch": 1.6269781461944235, "percentage": 81.33, "elapsed_time": "0:54:14", "remaining_time": "0:12:27"} +{"current_steps": 545, "total_steps": 664, "loss": 0.7197, "lr": 4.162582490144948e-07, "epoch": 1.642049736247174, "percentage": 82.08, "elapsed_time": "0:54:44", "remaining_time": "0:11:57"} +{"current_steps": 550, "total_steps": 664, "loss": 0.7375, "lr": 3.831895019292897e-07, "epoch": 1.6571213262999245, "percentage": 82.83, "elapsed_time": "0:55:15", "remaining_time": "0:11:27"} +{"current_steps": 555, "total_steps": 664, "loss": 0.7549, "lr": 3.5138005271346643e-07, "epoch": 1.6721929163526752, "percentage": 83.58, "elapsed_time": "0:55:46", "remaining_time": "0:10:57"} +{"current_steps": 560, "total_steps": 664, "loss": 0.7433, "lr": 3.208488249181216e-07, "epoch": 1.687264506405426, "percentage": 84.34, "elapsed_time": "0:56:15", "remaining_time": "0:10:26"} +{"current_steps": 565, "total_steps": 664, "loss": 0.7914, "lr": 2.9161398167602053e-07, "epoch": 1.7023360964581764, "percentage": 85.09, "elapsed_time": "0:56:46", "remaining_time": "0:09:56"} +{"current_steps": 570, "total_steps": 664, "loss": 0.7405, "lr": 2.6369291489628244e-07, "epoch": 1.717407686510927, "percentage": 85.84, "elapsed_time": "0:57:15", "remaining_time": "0:09:26"} +{"current_steps": 575, "total_steps": 664, "loss": 0.7149, "lr": 2.3710223491787643e-07, "epoch": 1.7324792765636774, "percentage": 86.6, "elapsed_time": "0:57:45", "remaining_time": "0:08:56"} +{"current_steps": 580, "total_steps": 664, "loss": 0.7274, "lr": 2.1185776062807307e-07, "epoch": 1.747550866616428, "percentage": 87.35, "elapsed_time": "0:58:16", "remaining_time": "0:08:26"} +{"current_steps": 585, "total_steps": 664, "loss": 0.7661, "lr": 1.8797451005173384e-07, "epoch": 1.7626224566691786, "percentage": 88.1, "elapsed_time": "0:58:47", "remaining_time": "0:07:56"} +{"current_steps": 590, "total_steps": 664, "loss": 0.7625, "lr": 1.654666914170361e-07, "epoch": 1.7776940467219293, "percentage": 88.86, "elapsed_time": "0:59:16", "remaining_time": "0:07:26"} +{"current_steps": 595, "total_steps": 664, "loss": 0.7985, "lr": 1.44347694702949e-07, "epoch": 1.7927656367746798, "percentage": 89.61, "elapsed_time": "0:59:49", "remaining_time": "0:06:56"} +{"current_steps": 600, "total_steps": 664, "loss": 0.7436, "lr": 1.24630083673489e-07, "epoch": 1.8078372268274303, "percentage": 90.36, "elapsed_time": "1:00:20", "remaining_time": "0:06:26"} +{"current_steps": 605, "total_steps": 664, "loss": 0.7608, "lr": 1.0632558840349333e-07, "epoch": 1.8229088168801808, "percentage": 91.11, "elapsed_time": "1:00:49", "remaining_time": "0:05:55"} +{"current_steps": 610, "total_steps": 664, "loss": 0.7131, "lr": 8.944509830035864e-08, "epoch": 1.8379804069329313, "percentage": 91.87, "elapsed_time": "1:01:20", "remaining_time": "0:05:25"} +{"current_steps": 615, "total_steps": 664, "loss": 0.7841, "lr": 7.399865562589315e-08, "epoch": 1.853051996985682, "percentage": 92.62, "elapsed_time": "1:01:48", "remaining_time": "0:04:55"} +{"current_steps": 620, "total_steps": 664, "loss": 0.7597, "lr": 5.999544952214192e-08, "epoch": 1.8681235870384325, "percentage": 93.37, "elapsed_time": "1:02:17", "remaining_time": "0:04:25"} +{"current_steps": 625, "total_steps": 664, "loss": 0.731, "lr": 4.7443810544734456e-08, "epoch": 1.8831951770911832, "percentage": 94.13, "elapsed_time": "1:02:45", "remaining_time": "0:03:54"} +{"current_steps": 630, "total_steps": 664, "loss": 0.7767, "lr": 3.635120570700784e-08, "epoch": 1.8982667671439337, "percentage": 94.88, "elapsed_time": "1:03:13", "remaining_time": "0:03:24"} +{"current_steps": 635, "total_steps": 664, "loss": 0.7445, "lr": 2.67242340378554e-08, "epoch": 1.9133383571966842, "percentage": 95.63, "elapsed_time": "1:03:45", "remaining_time": "0:02:54"} +{"current_steps": 640, "total_steps": 664, "loss": 0.7317, "lr": 1.856862265594117e-08, "epoch": 1.9284099472494347, "percentage": 96.39, "elapsed_time": "1:04:13", "remaining_time": "0:02:24"} +{"current_steps": 645, "total_steps": 664, "loss": 0.7479, "lr": 1.1889223362616664e-08, "epoch": 1.9434815373021854, "percentage": 97.14, "elapsed_time": "1:04:44", "remaining_time": "0:01:54"} +{"current_steps": 650, "total_steps": 664, "loss": 0.6665, "lr": 6.690009755569715e-09, "epoch": 1.958553127354936, "percentage": 97.89, "elapsed_time": "1:05:12", "remaining_time": "0:01:24"} +{"current_steps": 655, "total_steps": 664, "loss": 0.7905, "lr": 2.9740748649145778e-09, "epoch": 1.9736247174076866, "percentage": 98.64, "elapsed_time": "1:05:40", "remaining_time": "0:00:54"} +{"current_steps": 660, "total_steps": 664, "loss": 0.7328, "lr": 7.436293131396488e-10, "epoch": 1.9886963074604371, "percentage": 99.4, "elapsed_time": "1:06:11", "remaining_time": "0:00:24"} +{"current_steps": 664, "total_steps": 664, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "1:07:26", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..5c843c9 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,967 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.0, + "eval_steps": 500, + "global_step": 664, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.015071590052750565, + "grad_norm": 63.93290066194459, + "learning_rate": 1.0000000000000002e-06, + "loss": 1.451, + "step": 5 + }, + { + "epoch": 0.03014318010550113, + "grad_norm": 35.58752674721741, + "learning_rate": 2.25e-06, + "loss": 1.5943, + "step": 10 + }, + { + "epoch": 0.0452147701582517, + "grad_norm": 14.633818173823233, + "learning_rate": 3.5e-06, + "loss": 1.4134, + "step": 15 + }, + { + "epoch": 0.06028636021100226, + "grad_norm": 11.36624439106729, + "learning_rate": 4.75e-06, + "loss": 1.3789, + "step": 20 + }, + { + "epoch": 0.07535795026375283, + "grad_norm": 19.687207881604735, + "learning_rate": 4.999524068745182e-06, + "loss": 1.4061, + "step": 25 + }, + { + "epoch": 0.0904295403165034, + "grad_norm": 3.4721808953008786, + "learning_rate": 4.997590908585508e-06, + "loss": 1.3465, + "step": 30 + }, + { + "epoch": 0.10550113036925396, + "grad_norm": 3.7575390023993256, + "learning_rate": 4.994171922976349e-06, + "loss": 1.3066, + "step": 35 + }, + { + "epoch": 0.12057272042200452, + "grad_norm": 3.93945708920635, + "learning_rate": 4.9892691458840415e-06, + "loss": 1.3024, + "step": 40 + }, + { + "epoch": 0.1356443104747551, + "grad_norm": 5.745483553248285, + "learning_rate": 4.982885493987595e-06, + "loss": 1.3222, + "step": 45 + }, + { + "epoch": 0.15071590052750566, + "grad_norm": 3.556951637647764, + "learning_rate": 4.975024764943549e-06, + "loss": 1.3441, + "step": 50 + }, + { + "epoch": 0.1657874905802562, + "grad_norm": 2.837174059992352, + "learning_rate": 4.965691635126737e-06, + "loss": 1.2827, + "step": 55 + }, + { + "epoch": 0.1808590806330068, + "grad_norm": 3.041016464130793, + "learning_rate": 4.95489165684829e-06, + "loss": 1.2503, + "step": 60 + }, + { + "epoch": 0.19593067068575734, + "grad_norm": 2.9883733154892234, + "learning_rate": 4.942631255052551e-06, + "loss": 1.2252, + "step": 65 + }, + { + "epoch": 0.21100226073850792, + "grad_norm": 3.6954501199574636, + "learning_rate": 4.928917723494854e-06, + "loss": 1.2734, + "step": 70 + }, + { + "epoch": 0.22607385079125847, + "grad_norm": 8.370545215192237, + "learning_rate": 4.913759220402441e-06, + "loss": 1.2101, + "step": 75 + }, + { + "epoch": 0.24114544084400905, + "grad_norm": 28.432365965110936, + "learning_rate": 4.897164763621104e-06, + "loss": 1.2485, + "step": 80 + }, + { + "epoch": 0.2562170308967596, + "grad_norm": 4.715449035187671, + "learning_rate": 4.879144225250445e-06, + "loss": 1.2243, + "step": 85 + }, + { + "epoch": 0.2712886209495102, + "grad_norm": 2.9636386869143387, + "learning_rate": 4.859708325770919e-06, + "loss": 1.2052, + "step": 90 + }, + { + "epoch": 0.2863602110022607, + "grad_norm": 3.066981968094732, + "learning_rate": 4.838868627666191e-06, + "loss": 1.1686, + "step": 95 + }, + { + "epoch": 0.30143180105501133, + "grad_norm": 2.412797888960037, + "learning_rate": 4.81663752854457e-06, + "loss": 1.1775, + "step": 100 + }, + { + "epoch": 0.3165033911077619, + "grad_norm": 2.5140619073728105, + "learning_rate": 4.793028253763633e-06, + "loss": 1.1722, + "step": 105 + }, + { + "epoch": 0.3315749811605124, + "grad_norm": 2.493285093391174, + "learning_rate": 4.768054848562411e-06, + "loss": 1.1695, + "step": 110 + }, + { + "epoch": 0.346646571213263, + "grad_norm": 3.144530529949511, + "learning_rate": 4.741732169705829e-06, + "loss": 1.1841, + "step": 115 + }, + { + "epoch": 0.3617181612660136, + "grad_norm": 2.295823857057481, + "learning_rate": 4.714075876646365e-06, + "loss": 1.1757, + "step": 120 + }, + { + "epoch": 0.37678975131876413, + "grad_norm": 2.643471529827654, + "learning_rate": 4.6851024222081905e-06, + "loss": 1.1734, + "step": 125 + }, + { + "epoch": 0.3918613413715147, + "grad_norm": 2.9457088109557668, + "learning_rate": 4.654829042799323e-06, + "loss": 1.127, + "step": 130 + }, + { + "epoch": 0.4069329314242653, + "grad_norm": 3.0712069515731444, + "learning_rate": 4.62327374815763e-06, + "loss": 1.2514, + "step": 135 + }, + { + "epoch": 0.42200452147701584, + "grad_norm": 2.6973425645416174, + "learning_rate": 4.590455310636778e-06, + "loss": 1.1873, + "step": 140 + }, + { + "epoch": 0.4370761115297664, + "grad_norm": 2.6584776025168337, + "learning_rate": 4.556393254038486e-06, + "loss": 1.1515, + "step": 145 + }, + { + "epoch": 0.45214770158251694, + "grad_norm": 2.7834304414005753, + "learning_rate": 4.521107841997758e-06, + "loss": 1.1197, + "step": 150 + }, + { + "epoch": 0.46721929163526754, + "grad_norm": 3.0654410008265893, + "learning_rate": 4.48462006592797e-06, + "loss": 1.1494, + "step": 155 + }, + { + "epoch": 0.4822908816880181, + "grad_norm": 2.3584975942076487, + "learning_rate": 4.4469516325330055e-06, + "loss": 1.1292, + "step": 160 + }, + { + "epoch": 0.49736247174076864, + "grad_norm": 2.6296807819946766, + "learning_rate": 4.408124950893868e-06, + "loss": 1.1195, + "step": 165 + }, + { + "epoch": 0.5124340617935192, + "grad_norm": 2.810412992553872, + "learning_rate": 4.368163119137437e-06, + "loss": 1.1047, + "step": 170 + }, + { + "epoch": 0.5275056518462697, + "grad_norm": 2.7447890069275207, + "learning_rate": 4.32708991069531e-06, + "loss": 1.1689, + "step": 175 + }, + { + "epoch": 0.5425772418990203, + "grad_norm": 2.6925744340959104, + "learning_rate": 4.284929760160917e-06, + "loss": 0.9971, + "step": 180 + }, + { + "epoch": 0.557648831951771, + "grad_norm": 2.604938296467723, + "learning_rate": 4.2417077487532835e-06, + "loss": 1.1245, + "step": 185 + }, + { + "epoch": 0.5727204220045214, + "grad_norm": 2.9775634900633534, + "learning_rate": 4.197449589396131e-06, + "loss": 1.1714, + "step": 190 + }, + { + "epoch": 0.587792012057272, + "grad_norm": 2.7593158692455066, + "learning_rate": 4.152181611421179e-06, + "loss": 1.1634, + "step": 195 + }, + { + "epoch": 0.6028636021100227, + "grad_norm": 2.6974834987909357, + "learning_rate": 4.105930744904721e-06, + "loss": 1.1021, + "step": 200 + }, + { + "epoch": 0.6179351921627732, + "grad_norm": 2.872785492959392, + "learning_rate": 4.058724504646834e-06, + "loss": 1.1172, + "step": 205 + }, + { + "epoch": 0.6330067822155238, + "grad_norm": 2.562056324367801, + "learning_rate": 4.010590973802737e-06, + "loss": 1.1375, + "step": 210 + }, + { + "epoch": 0.6480783722682742, + "grad_norm": 2.2291085754732713, + "learning_rate": 3.961558787176012e-06, + "loss": 1.1482, + "step": 215 + }, + { + "epoch": 0.6631499623210249, + "grad_norm": 2.4045628734860687, + "learning_rate": 3.91165711418367e-06, + "loss": 1.1041, + "step": 220 + }, + { + "epoch": 0.6782215523737755, + "grad_norm": 3.3080421132480717, + "learning_rate": 3.860915641503161e-06, + "loss": 1.1142, + "step": 225 + }, + { + "epoch": 0.693293142426526, + "grad_norm": 3.245502012246857, + "learning_rate": 3.809364555411667e-06, + "loss": 1.185, + "step": 230 + }, + { + "epoch": 0.7083647324792766, + "grad_norm": 3.0888496819111726, + "learning_rate": 3.75703452382818e-06, + "loss": 1.1719, + "step": 235 + }, + { + "epoch": 0.7234363225320272, + "grad_norm": 3.1440323353252526, + "learning_rate": 3.703956678069055e-06, + "loss": 1.1238, + "step": 240 + }, + { + "epoch": 0.7385079125847777, + "grad_norm": 2.8116489290906723, + "learning_rate": 3.650162594327881e-06, + "loss": 1.0788, + "step": 245 + }, + { + "epoch": 0.7535795026375283, + "grad_norm": 2.6368140598692347, + "learning_rate": 3.595684274890691e-06, + "loss": 1.0756, + "step": 250 + }, + { + "epoch": 0.7686510926902789, + "grad_norm": 2.408558758625417, + "learning_rate": 3.5405541290976968e-06, + "loss": 1.1189, + "step": 255 + }, + { + "epoch": 0.7837226827430294, + "grad_norm": 2.897272560922028, + "learning_rate": 3.4848049540628588e-06, + "loss": 1.0719, + "step": 260 + }, + { + "epoch": 0.79879427279578, + "grad_norm": 2.606250228734567, + "learning_rate": 3.4284699151627672e-06, + "loss": 1.1073, + "step": 265 + }, + { + "epoch": 0.8138658628485306, + "grad_norm": 2.7496803732493276, + "learning_rate": 3.3715825263064493e-06, + "loss": 1.0891, + "step": 270 + }, + { + "epoch": 0.8289374529012811, + "grad_norm": 2.5362507404210146, + "learning_rate": 3.314176629997825e-06, + "loss": 1.0003, + "step": 275 + }, + { + "epoch": 0.8440090429540317, + "grad_norm": 2.930907397969813, + "learning_rate": 3.25628637720269e-06, + "loss": 1.1259, + "step": 280 + }, + { + "epoch": 0.8590806330067822, + "grad_norm": 2.339195373127568, + "learning_rate": 3.1979462070321817e-06, + "loss": 1.1505, + "step": 285 + }, + { + "epoch": 0.8741522230595328, + "grad_norm": 2.8349021987346266, + "learning_rate": 3.1391908262548382e-06, + "loss": 1.0636, + "step": 290 + }, + { + "epoch": 0.8892238131122834, + "grad_norm": 3.2284091736671905, + "learning_rate": 3.08005518864942e-06, + "loss": 1.1475, + "step": 295 + }, + { + "epoch": 0.9042954031650339, + "grad_norm": 2.6609799290676768, + "learning_rate": 3.0205744742107874e-06, + "loss": 1.0161, + "step": 300 + }, + { + "epoch": 0.9193669932177845, + "grad_norm": 2.5739173473029417, + "learning_rate": 2.9607840682211987e-06, + "loss": 1.0239, + "step": 305 + }, + { + "epoch": 0.9344385832705351, + "grad_norm": 2.937887898785162, + "learning_rate": 2.900719540199484e-06, + "loss": 1.0436, + "step": 310 + }, + { + "epoch": 0.9495101733232856, + "grad_norm": 2.7246531876982116, + "learning_rate": 2.840416622740617e-06, + "loss": 1.0982, + "step": 315 + }, + { + "epoch": 0.9645817633760362, + "grad_norm": 2.8889715233179456, + "learning_rate": 2.7799111902582697e-06, + "loss": 1.1161, + "step": 320 + }, + { + "epoch": 0.9796533534287868, + "grad_norm": 3.20559013895907, + "learning_rate": 2.7192392376430014e-06, + "loss": 1.066, + "step": 325 + }, + { + "epoch": 0.9947249434815373, + "grad_norm": 2.63714269591387, + "learning_rate": 2.6584368588487727e-06, + "loss": 1.0798, + "step": 330 + }, + { + "epoch": 1.0090429540316503, + "grad_norm": 2.8236476573888636, + "learning_rate": 2.597540225420525e-06, + "loss": 0.8717, + "step": 335 + }, + { + "epoch": 1.0241145440844008, + "grad_norm": 2.403622878308974, + "learning_rate": 2.5365855649756114e-06, + "loss": 0.7775, + "step": 340 + }, + { + "epoch": 1.0391861341371516, + "grad_norm": 3.1556330242872828, + "learning_rate": 2.475609139651855e-06, + "loss": 0.8101, + "step": 345 + }, + { + "epoch": 1.054257724189902, + "grad_norm": 2.8657604036527373, + "learning_rate": 2.4146472245350804e-06, + "loss": 0.7067, + "step": 350 + }, + { + "epoch": 1.0693293142426525, + "grad_norm": 2.845940606079971, + "learning_rate": 2.353736086078941e-06, + "loss": 0.7314, + "step": 355 + }, + { + "epoch": 1.0844009042954033, + "grad_norm": 2.6386252875863856, + "learning_rate": 2.2929119605298787e-06, + "loss": 0.7813, + "step": 360 + }, + { + "epoch": 1.0994724943481538, + "grad_norm": 2.9858658644648512, + "learning_rate": 2.232211032370057e-06, + "loss": 0.7792, + "step": 365 + }, + { + "epoch": 1.1145440844009042, + "grad_norm": 3.1704667094741428, + "learning_rate": 2.1716694127910863e-06, + "loss": 0.8093, + "step": 370 + }, + { + "epoch": 1.129615674453655, + "grad_norm": 2.438807649007062, + "learning_rate": 2.1113231182113557e-06, + "loss": 0.7326, + "step": 375 + }, + { + "epoch": 1.1446872645064055, + "grad_norm": 2.766081091730644, + "learning_rate": 2.0512080488497353e-06, + "loss": 0.7069, + "step": 380 + }, + { + "epoch": 1.159758854559156, + "grad_norm": 2.749798423974893, + "learning_rate": 1.991359967368416e-06, + "loss": 0.696, + "step": 385 + }, + { + "epoch": 1.1748304446119064, + "grad_norm": 2.9444307577352937, + "learning_rate": 1.9318144775975773e-06, + "loss": 0.7416, + "step": 390 + }, + { + "epoch": 1.1899020346646572, + "grad_norm": 3.04433007961317, + "learning_rate": 1.8726070033545468e-06, + "loss": 0.7579, + "step": 395 + }, + { + "epoch": 1.2049736247174077, + "grad_norm": 2.9541203492627517, + "learning_rate": 1.8137727673700476e-06, + "loss": 0.7538, + "step": 400 + }, + { + "epoch": 1.2200452147701584, + "grad_norm": 3.5431910354023497, + "learning_rate": 1.7553467703340755e-06, + "loss": 0.7116, + "step": 405 + }, + { + "epoch": 1.2351168048229089, + "grad_norm": 2.6008674886254486, + "learning_rate": 1.697363770073866e-06, + "loss": 0.7292, + "step": 410 + }, + { + "epoch": 1.2501883948756594, + "grad_norm": 2.498409384596954, + "learning_rate": 1.6398582608763457e-06, + "loss": 0.7165, + "step": 415 + }, + { + "epoch": 1.2652599849284099, + "grad_norm": 2.962253311649292, + "learning_rate": 1.5828644529673592e-06, + "loss": 0.7987, + "step": 420 + }, + { + "epoch": 1.2803315749811606, + "grad_norm": 2.862039009052619, + "learning_rate": 1.5264162521598893e-06, + "loss": 0.7438, + "step": 425 + }, + { + "epoch": 1.295403165033911, + "grad_norm": 2.6095190980853773, + "learning_rate": 1.470547239683372e-06, + "loss": 0.7239, + "step": 430 + }, + { + "epoch": 1.3104747550866618, + "grad_norm": 2.8744839745796575, + "learning_rate": 1.415290652206105e-06, + "loss": 0.7571, + "step": 435 + }, + { + "epoch": 1.3255463451394123, + "grad_norm": 2.7520999185916333, + "learning_rate": 1.3606793620626434e-06, + "loss": 0.7234, + "step": 440 + }, + { + "epoch": 1.3406179351921628, + "grad_norm": 2.7897554528675994, + "learning_rate": 1.3067458576979305e-06, + "loss": 0.7832, + "step": 445 + }, + { + "epoch": 1.3556895252449133, + "grad_norm": 2.5249576185058418, + "learning_rate": 1.2535222243398104e-06, + "loss": 0.7063, + "step": 450 + }, + { + "epoch": 1.370761115297664, + "grad_norm": 2.923951654007246, + "learning_rate": 1.2010401249114166e-06, + "loss": 0.7749, + "step": 455 + }, + { + "epoch": 1.3858327053504145, + "grad_norm": 2.659838061766203, + "learning_rate": 1.1493307811947887e-06, + "loss": 0.7036, + "step": 460 + }, + { + "epoch": 1.400904295403165, + "grad_norm": 2.567444585108736, + "learning_rate": 1.098424955256929e-06, + "loss": 0.8069, + "step": 465 + }, + { + "epoch": 1.4159758854559157, + "grad_norm": 2.9945953913555243, + "learning_rate": 1.048352931149338e-06, + "loss": 0.7826, + "step": 470 + }, + { + "epoch": 1.4310474755086662, + "grad_norm": 2.4443317776748605, + "learning_rate": 9.991444968919318e-07, + "loss": 0.7534, + "step": 475 + }, + { + "epoch": 1.4461190655614167, + "grad_norm": 3.0058692222092236, + "learning_rate": 9.50828926752044e-07, + "loss": 0.7342, + "step": 480 + }, + { + "epoch": 1.4611906556141672, + "grad_norm": 2.474430249938214, + "learning_rate": 9.034349638290643e-07, + "loss": 0.7724, + "step": 485 + }, + { + "epoch": 1.4762622456669179, + "grad_norm": 2.4876357050013485, + "learning_rate": 8.569908029550686e-07, + "loss": 0.7172, + "step": 490 + }, + { + "epoch": 1.4913338357196684, + "grad_norm": 2.9193635869573478, + "learning_rate": 8.115240739216182e-07, + "loss": 0.7634, + "step": 495 + }, + { + "epoch": 1.506405425772419, + "grad_norm": 2.9037368464731985, + "learning_rate": 7.670618250426981e-07, + "loss": 0.7434, + "step": 500 + }, + { + "epoch": 1.5214770158251696, + "grad_norm": 3.621843474966251, + "learning_rate": 7.236305070635835e-07, + "loss": 0.7432, + "step": 505 + }, + { + "epoch": 1.53654860587792, + "grad_norm": 3.172725821539682, + "learning_rate": 6.812559574252006e-07, + "loss": 0.6995, + "step": 510 + }, + { + "epoch": 1.5516201959306706, + "grad_norm": 3.127632922550285, + "learning_rate": 6.399633848933434e-07, + "loss": 0.7365, + "step": 515 + }, + { + "epoch": 1.5666917859834213, + "grad_norm": 3.0207209188886437, + "learning_rate": 5.997773545618907e-07, + "loss": 0.7731, + "step": 520 + }, + { + "epoch": 1.5817633760361718, + "grad_norm": 3.1229845348222693, + "learning_rate": 5.607217732389503e-07, + "loss": 0.7675, + "step": 525 + }, + { + "epoch": 1.5968349660889225, + "grad_norm": 2.556530267042756, + "learning_rate": 5.228198752246125e-07, + "loss": 0.7298, + "step": 530 + }, + { + "epoch": 1.611906556141673, + "grad_norm": 2.7122390573301134, + "learning_rate": 4.860942084887868e-07, + "loss": 0.8014, + "step": 535 + }, + { + "epoch": 1.6269781461944235, + "grad_norm": 2.5497358605686826, + "learning_rate": 4.505666212573367e-07, + "loss": 0.7098, + "step": 540 + }, + { + "epoch": 1.642049736247174, + "grad_norm": 2.451710015213246, + "learning_rate": 4.162582490144948e-07, + "loss": 0.7197, + "step": 545 + }, + { + "epoch": 1.6571213262999245, + "grad_norm": 2.4788034308159634, + "learning_rate": 3.831895019292897e-07, + "loss": 0.7375, + "step": 550 + }, + { + "epoch": 1.6721929163526752, + "grad_norm": 3.07406346872796, + "learning_rate": 3.5138005271346643e-07, + "loss": 0.7549, + "step": 555 + }, + { + "epoch": 1.687264506405426, + "grad_norm": 2.6118807822457115, + "learning_rate": 3.208488249181216e-07, + "loss": 0.7433, + "step": 560 + }, + { + "epoch": 1.7023360964581764, + "grad_norm": 3.0584684036169865, + "learning_rate": 2.9161398167602053e-07, + "loss": 0.7914, + "step": 565 + }, + { + "epoch": 1.717407686510927, + "grad_norm": 2.763834415959353, + "learning_rate": 2.6369291489628244e-07, + "loss": 0.7405, + "step": 570 + }, + { + "epoch": 1.7324792765636774, + "grad_norm": 2.1449947701115684, + "learning_rate": 2.3710223491787643e-07, + "loss": 0.7149, + "step": 575 + }, + { + "epoch": 1.747550866616428, + "grad_norm": 2.63033187099936, + "learning_rate": 2.1185776062807307e-07, + "loss": 0.7274, + "step": 580 + }, + { + "epoch": 1.7626224566691786, + "grad_norm": 2.8862953965332547, + "learning_rate": 1.8797451005173384e-07, + "loss": 0.7661, + "step": 585 + }, + { + "epoch": 1.7776940467219293, + "grad_norm": 2.7608278671213897, + "learning_rate": 1.654666914170361e-07, + "loss": 0.7625, + "step": 590 + }, + { + "epoch": 1.7927656367746798, + "grad_norm": 3.3490002122178, + "learning_rate": 1.44347694702949e-07, + "loss": 0.7985, + "step": 595 + }, + { + "epoch": 1.8078372268274303, + "grad_norm": 2.5636592675505545, + "learning_rate": 1.24630083673489e-07, + "loss": 0.7436, + "step": 600 + }, + { + "epoch": 1.8229088168801808, + "grad_norm": 2.895653387694223, + "learning_rate": 1.0632558840349333e-07, + "loss": 0.7608, + "step": 605 + }, + { + "epoch": 1.8379804069329313, + "grad_norm": 2.553919116507747, + "learning_rate": 8.944509830035864e-08, + "loss": 0.7131, + "step": 610 + }, + { + "epoch": 1.853051996985682, + "grad_norm": 2.849246844898084, + "learning_rate": 7.399865562589315e-08, + "loss": 0.7841, + "step": 615 + }, + { + "epoch": 1.8681235870384325, + "grad_norm": 3.01555827900457, + "learning_rate": 5.999544952214192e-08, + "loss": 0.7597, + "step": 620 + }, + { + "epoch": 1.8831951770911832, + "grad_norm": 2.5969187446302806, + "learning_rate": 4.7443810544734456e-08, + "loss": 0.731, + "step": 625 + }, + { + "epoch": 1.8982667671439337, + "grad_norm": 2.7609437293219288, + "learning_rate": 3.635120570700784e-08, + "loss": 0.7767, + "step": 630 + }, + { + "epoch": 1.9133383571966842, + "grad_norm": 2.6128372521247583, + "learning_rate": 2.67242340378554e-08, + "loss": 0.7445, + "step": 635 + }, + { + "epoch": 1.9284099472494347, + "grad_norm": 3.0201462908095302, + "learning_rate": 1.856862265594117e-08, + "loss": 0.7317, + "step": 640 + }, + { + "epoch": 1.9434815373021854, + "grad_norm": 3.1957975068044098, + "learning_rate": 1.1889223362616664e-08, + "loss": 0.7479, + "step": 645 + }, + { + "epoch": 1.958553127354936, + "grad_norm": 2.7277480748536274, + "learning_rate": 6.690009755569715e-09, + "loss": 0.6665, + "step": 650 + }, + { + "epoch": 1.9736247174076866, + "grad_norm": 2.6562010103303586, + "learning_rate": 2.9740748649145778e-09, + "loss": 0.7905, + "step": 655 + }, + { + "epoch": 1.9886963074604371, + "grad_norm": 2.719630315699159, + "learning_rate": 7.436293131396488e-10, + "loss": 0.7328, + "step": 660 + }, + { + "epoch": 2.0, + "step": 664, + "total_flos": 25921569423360.0, + "train_loss": 0.9619188387709928, + "train_runtime": 4046.5288, + "train_samples_per_second": 10.494, + "train_steps_per_second": 0.164 + } + ], + "logging_steps": 5, + "max_steps": 664, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 350, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 25921569423360.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..56ea7d7 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:481f7fc05ba1056c42dc28bfeb3e6a70395d108701196c1f04b97544959c12fb +size 8145 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..1b4c905 Binary files /dev/null and b/training_loss.png differ