commit d29c2c2fb7eab0b93bd8107d2877a3e4ace515f3 Author: ModelHub XC Date: Wed Jun 3 05:20:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mlfoundations-dev/mlfoundations-dev_code-stratos-unverified-scaled-0_25_stratos_7b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..14d8ccb --- /dev/null +++ b/.gitattributes @@ -0,0 +1,56 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +vocab.json filter=lfs diff=lfs merge=lfs -text +training_args.bin filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..f3933ea --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +library_name: transformers +license: other +base_model: Qwen/Qwen2.5-7B-Instruct +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: mlfoundations-dev_code-stratos-unverified-scaled-0.25_stratos_7b + results: [] +--- + + + +# mlfoundations-dev_code-stratos-unverified-scaled-0.25_stratos_7b + +This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/code-stratos-unverified-scaled-0.25 dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 1e-05 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 48 +- gradient_accumulation_steps: 2 +- total_train_batch_size: 96 +- total_eval_batch_size: 384 +- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 3.0 + +### Training results + + + +### Framework versions + +- Transformers 4.46.1 +- Pytorch 2.5.0a0+b465a5843b.nv24.09 +- Datasets 3.0.2 +- Tokenizers 0.20.3 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..1985c2c --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 3.0, + "total_flos": 2.3644419613786112e+17, + "train_loss": 0.6642100642888974, + "train_runtime": 3868.2988, + "train_samples_per_second": 3.859, + "train_steps_per_second": 0.04 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..27de0e0 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "/p/data1/mmlaion/marianna/models/Qwen/Qwen2.5-7B-Instruct", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/configs.yaml b/configs.yaml new file mode 100644 index 0000000..9a0e425 --- /dev/null +++ b/configs.yaml @@ -0,0 +1,38 @@ +assistant_tag: assistant +bf16: true +content_tag: value +cutoff_len: 16384 +dataset: /p/data1/mmlaion/marianna/lf_datasets/mlfoundations-dev/code-stratos-unverified-scaled-0.25 +dataset_dir: ONLINE +ddp_timeout: 180000000 +deepspeed: dcft/train/zero3_offload.json +do_train: true +enable_liger_kernel: true +finetuning_type: full +formatting: sharegpt +global_batch_size: 96 +gradient_accumulation_steps: 2 +hub_model_id: mlfoundations-dev/mlfoundations-dev_code-stratos-unverified-scaled-0_25_stratos_7b +learning_rate: 1.0e-05 +logging_steps: 1 +lr_scheduler_type: cosine +max_samples: 1000000 +messages: conversations +model_name_or_path: Qwen/Qwen2.5-7B-Instruct +num_train_epochs: 3.0 +output_dir: /p/data1/mmlaion/marianna/dcft_checkpoints/mlfoundations-dev_code-stratos-unverified-scaled-0.25_stratos_7b +overwrite_cache: true +per_device_train_batch_size: 1 +plot_loss: true +preprocessing_num_workers: 16 +push_to_db: false +push_to_hub: false +report_to: wandb +role_tag: from +run_name: Bespoke-Stratos-17k +save_steps: 100 +stage: sft +template: qwen25 +use_unsloth_gc: true +user_tag: user +warmup_ratio: 0.1 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a753841 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.46.1" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..f84a1a8 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f821fd601c7bec325ddddc6556f7c649c7318433ed20ed9e8d541e97f35ffb0 +size 4877660776 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..7337125 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:325108f641db27951d94b47341c945aafcb4dff886042fd61d7b65a63ad968a2 +size 4932751008 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..f98f6dc --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd02f6e5fb7ba995a646df641f8a52c4a71624c047135a3d75e36ded8fc93afe +size 4330865200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..40e07d2 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8def9d4486efce7bbdc645db2d7618ccb6d29adbcc7e2c6e97c2b7dfd42cfac +size 1089994880 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..6ca5084 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,346 @@ +{ + "metadata": { + "total_size": 15231233024 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00003-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..17305b3 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..51ebb3b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b84f53a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,208 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..1985c2c --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 3.0, + "total_flos": 2.3644419613786112e+17, + "train_loss": 0.6642100642888974, + "train_runtime": 3868.2988, + "train_samples_per_second": 3.859, + "train_steps_per_second": 0.04 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..5ee7546 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,157 @@ +{"current_steps": 1, "total_steps": 156, "loss": 1.0467, "lr": 6.25e-07, "epoch": 0.019230769230769232, "percentage": 0.64, "elapsed_time": "0:00:30", "remaining_time": "1:18:11"} +{"current_steps": 2, "total_steps": 156, "loss": 1.035, "lr": 1.25e-06, "epoch": 0.038461538461538464, "percentage": 1.28, "elapsed_time": "0:00:54", "remaining_time": "1:10:15"} +{"current_steps": 3, "total_steps": 156, "loss": 1.0379, "lr": 1.8750000000000003e-06, "epoch": 0.057692307692307696, "percentage": 1.92, "elapsed_time": "0:01:18", "remaining_time": "1:06:47"} +{"current_steps": 4, "total_steps": 156, "loss": 1.0497, "lr": 2.5e-06, "epoch": 0.07692307692307693, "percentage": 2.56, "elapsed_time": "0:01:44", "remaining_time": "1:06:14"} +{"current_steps": 5, "total_steps": 156, "loss": 1.0217, "lr": 3.125e-06, "epoch": 0.09615384615384616, "percentage": 3.21, "elapsed_time": "0:02:10", "remaining_time": "1:05:39"} +{"current_steps": 6, "total_steps": 156, "loss": 0.9747, "lr": 3.7500000000000005e-06, "epoch": 0.11538461538461539, "percentage": 3.85, "elapsed_time": "0:02:36", "remaining_time": "1:05:16"} +{"current_steps": 7, "total_steps": 156, "loss": 0.9507, "lr": 4.3750000000000005e-06, "epoch": 0.1346153846153846, "percentage": 4.49, "elapsed_time": "0:03:02", "remaining_time": "1:04:55"} +{"current_steps": 8, "total_steps": 156, "loss": 0.9473, "lr": 5e-06, "epoch": 0.15384615384615385, "percentage": 5.13, "elapsed_time": "0:03:29", "remaining_time": "1:04:35"} +{"current_steps": 9, "total_steps": 156, "loss": 0.9369, "lr": 5.625e-06, "epoch": 0.17307692307692307, "percentage": 5.77, "elapsed_time": "0:03:55", "remaining_time": "1:04:07"} +{"current_steps": 10, "total_steps": 156, "loss": 0.9425, "lr": 6.25e-06, "epoch": 0.19230769230769232, "percentage": 6.41, "elapsed_time": "0:04:21", "remaining_time": "1:03:36"} +{"current_steps": 11, "total_steps": 156, "loss": 0.9044, "lr": 6.875e-06, "epoch": 0.21153846153846154, "percentage": 7.05, "elapsed_time": "0:04:46", "remaining_time": "1:02:58"} +{"current_steps": 12, "total_steps": 156, "loss": 0.8622, "lr": 7.500000000000001e-06, "epoch": 0.23076923076923078, "percentage": 7.69, "elapsed_time": "0:05:13", "remaining_time": "1:02:44"} +{"current_steps": 13, "total_steps": 156, "loss": 0.858, "lr": 8.125000000000001e-06, "epoch": 0.25, "percentage": 8.33, "elapsed_time": "0:05:40", "remaining_time": "1:02:22"} +{"current_steps": 14, "total_steps": 156, "loss": 0.8479, "lr": 8.750000000000001e-06, "epoch": 0.2692307692307692, "percentage": 8.97, "elapsed_time": "0:06:06", "remaining_time": "1:01:54"} +{"current_steps": 15, "total_steps": 156, "loss": 0.8085, "lr": 9.375000000000001e-06, "epoch": 0.28846153846153844, "percentage": 9.62, "elapsed_time": "0:06:31", "remaining_time": "1:01:16"} +{"current_steps": 16, "total_steps": 156, "loss": 0.8253, "lr": 1e-05, "epoch": 0.3076923076923077, "percentage": 10.26, "elapsed_time": "0:06:53", "remaining_time": "1:00:18"} +{"current_steps": 17, "total_steps": 156, "loss": 0.7737, "lr": 9.998741174712534e-06, "epoch": 0.3269230769230769, "percentage": 10.9, "elapsed_time": "0:07:19", "remaining_time": "0:59:54"} +{"current_steps": 18, "total_steps": 156, "loss": 0.7872, "lr": 9.994965332706574e-06, "epoch": 0.34615384615384615, "percentage": 11.54, "elapsed_time": "0:07:45", "remaining_time": "0:59:29"} +{"current_steps": 19, "total_steps": 156, "loss": 0.7565, "lr": 9.98867437523228e-06, "epoch": 0.36538461538461536, "percentage": 12.18, "elapsed_time": "0:08:10", "remaining_time": "0:58:54"} +{"current_steps": 20, "total_steps": 156, "loss": 0.7616, "lr": 9.979871469976197e-06, "epoch": 0.38461538461538464, "percentage": 12.82, "elapsed_time": "0:08:34", "remaining_time": "0:58:20"} +{"current_steps": 21, "total_steps": 156, "loss": 0.7438, "lr": 9.968561049466214e-06, "epoch": 0.40384615384615385, "percentage": 13.46, "elapsed_time": "0:09:01", "remaining_time": "0:57:59"} +{"current_steps": 22, "total_steps": 156, "loss": 0.747, "lr": 9.954748808839675e-06, "epoch": 0.4230769230769231, "percentage": 14.1, "elapsed_time": "0:09:25", "remaining_time": "0:57:23"} +{"current_steps": 23, "total_steps": 156, "loss": 0.7425, "lr": 9.938441702975689e-06, "epoch": 0.4423076923076923, "percentage": 14.74, "elapsed_time": "0:09:51", "remaining_time": "0:56:58"} +{"current_steps": 24, "total_steps": 156, "loss": 0.7223, "lr": 9.91964794299315e-06, "epoch": 0.46153846153846156, "percentage": 15.38, "elapsed_time": "0:10:15", "remaining_time": "0:56:25"} +{"current_steps": 25, "total_steps": 156, "loss": 0.7254, "lr": 9.898376992116179e-06, "epoch": 0.4807692307692308, "percentage": 16.03, "elapsed_time": "0:10:41", "remaining_time": "0:56:03"} +{"current_steps": 26, "total_steps": 156, "loss": 0.705, "lr": 9.874639560909118e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:11:05", "remaining_time": "0:55:25"} +{"current_steps": 27, "total_steps": 156, "loss": 0.7097, "lr": 9.848447601883436e-06, "epoch": 0.5192307692307693, "percentage": 17.31, "elapsed_time": "0:11:31", "remaining_time": "0:55:04"} +{"current_steps": 28, "total_steps": 156, "loss": 0.7087, "lr": 9.819814303479268e-06, "epoch": 0.5384615384615384, "percentage": 17.95, "elapsed_time": "0:11:57", "remaining_time": "0:54:38"} +{"current_steps": 29, "total_steps": 156, "loss": 0.7106, "lr": 9.788754083424654e-06, "epoch": 0.5576923076923077, "percentage": 18.59, "elapsed_time": "0:12:21", "remaining_time": "0:54:09"} +{"current_steps": 30, "total_steps": 156, "loss": 0.7004, "lr": 9.755282581475769e-06, "epoch": 0.5769230769230769, "percentage": 19.23, "elapsed_time": "0:12:47", "remaining_time": "0:53:44"} +{"current_steps": 31, "total_steps": 156, "loss": 0.7029, "lr": 9.719416651541839e-06, "epoch": 0.5961538461538461, "percentage": 19.87, "elapsed_time": "0:13:12", "remaining_time": "0:53:14"} +{"current_steps": 32, "total_steps": 156, "loss": 0.702, "lr": 9.681174353198687e-06, "epoch": 0.6153846153846154, "percentage": 20.51, "elapsed_time": "0:13:35", "remaining_time": "0:52:41"} +{"current_steps": 33, "total_steps": 156, "loss": 0.7126, "lr": 9.640574942595195e-06, "epoch": 0.6346153846153846, "percentage": 21.15, "elapsed_time": "0:14:01", "remaining_time": "0:52:15"} +{"current_steps": 34, "total_steps": 156, "loss": 0.6879, "lr": 9.597638862757255e-06, "epoch": 0.6538461538461539, "percentage": 21.79, "elapsed_time": "0:14:26", "remaining_time": "0:51:50"} +{"current_steps": 35, "total_steps": 156, "loss": 0.7112, "lr": 9.552387733294081e-06, "epoch": 0.6730769230769231, "percentage": 22.44, "elapsed_time": "0:14:52", "remaining_time": "0:51:24"} +{"current_steps": 36, "total_steps": 156, "loss": 0.6787, "lr": 9.504844339512096e-06, "epoch": 0.6923076923076923, "percentage": 23.08, "elapsed_time": "0:15:18", "remaining_time": "0:51:00"} +{"current_steps": 37, "total_steps": 156, "loss": 0.6876, "lr": 9.45503262094184e-06, "epoch": 0.7115384615384616, "percentage": 23.72, "elapsed_time": "0:15:44", "remaining_time": "0:50:37"} +{"current_steps": 38, "total_steps": 156, "loss": 0.6943, "lr": 9.40297765928369e-06, "epoch": 0.7307692307692307, "percentage": 24.36, "elapsed_time": "0:16:07", "remaining_time": "0:50:05"} +{"current_steps": 39, "total_steps": 156, "loss": 0.6842, "lr": 9.348705665778479e-06, "epoch": 0.75, "percentage": 25.0, "elapsed_time": "0:16:31", "remaining_time": "0:49:35"} +{"current_steps": 40, "total_steps": 156, "loss": 0.6676, "lr": 9.292243968009332e-06, "epoch": 0.7692307692307693, "percentage": 25.64, "elapsed_time": "0:16:54", "remaining_time": "0:49:02"} +{"current_steps": 41, "total_steps": 156, "loss": 0.6693, "lr": 9.233620996141421e-06, "epoch": 0.7884615384615384, "percentage": 26.28, "elapsed_time": "0:17:18", "remaining_time": "0:48:33"} +{"current_steps": 42, "total_steps": 156, "loss": 0.6685, "lr": 9.172866268606514e-06, "epoch": 0.8076923076923077, "percentage": 26.92, "elapsed_time": "0:17:42", "remaining_time": "0:48:04"} +{"current_steps": 43, "total_steps": 156, "loss": 0.6766, "lr": 9.110010377239552e-06, "epoch": 0.8269230769230769, "percentage": 27.56, "elapsed_time": "0:18:08", "remaining_time": "0:47:40"} +{"current_steps": 44, "total_steps": 156, "loss": 0.6821, "lr": 9.045084971874738e-06, "epoch": 0.8461538461538461, "percentage": 28.21, "elapsed_time": "0:18:31", "remaining_time": "0:47:08"} +{"current_steps": 45, "total_steps": 156, "loss": 0.6683, "lr": 8.978122744408905e-06, "epoch": 0.8653846153846154, "percentage": 28.85, "elapsed_time": "0:18:55", "remaining_time": "0:46:41"} +{"current_steps": 46, "total_steps": 156, "loss": 0.6788, "lr": 8.90915741234015e-06, "epoch": 0.8846153846153846, "percentage": 29.49, "elapsed_time": "0:19:18", "remaining_time": "0:46:10"} +{"current_steps": 47, "total_steps": 156, "loss": 0.66, "lr": 8.838223701790057e-06, "epoch": 0.9038461538461539, "percentage": 30.13, "elapsed_time": "0:19:41", "remaining_time": "0:45:40"} +{"current_steps": 48, "total_steps": 156, "loss": 0.6581, "lr": 8.765357330018056e-06, "epoch": 0.9230769230769231, "percentage": 30.77, "elapsed_time": "0:20:05", "remaining_time": "0:45:11"} +{"current_steps": 49, "total_steps": 156, "loss": 0.6627, "lr": 8.690594987436705e-06, "epoch": 0.9423076923076923, "percentage": 31.41, "elapsed_time": "0:20:29", "remaining_time": "0:44:45"} +{"current_steps": 50, "total_steps": 156, "loss": 0.6598, "lr": 8.613974319136959e-06, "epoch": 0.9615384615384616, "percentage": 32.05, "elapsed_time": "0:20:54", "remaining_time": "0:44:20"} +{"current_steps": 51, "total_steps": 156, "loss": 0.665, "lr": 8.535533905932739e-06, "epoch": 0.9807692307692307, "percentage": 32.69, "elapsed_time": "0:21:18", "remaining_time": "0:43:52"} +{"current_steps": 52, "total_steps": 156, "loss": 0.6737, "lr": 8.455313244934324e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:21:42", "remaining_time": "0:43:24"} +{"current_steps": 53, "total_steps": 156, "loss": 0.6544, "lr": 8.373352729660373e-06, "epoch": 1.0192307692307692, "percentage": 33.97, "elapsed_time": "0:22:06", "remaining_time": "0:42:57"} +{"current_steps": 54, "total_steps": 156, "loss": 0.631, "lr": 8.289693629698564e-06, "epoch": 1.0384615384615385, "percentage": 34.62, "elapsed_time": "0:22:30", "remaining_time": "0:42:31"} +{"current_steps": 55, "total_steps": 156, "loss": 0.6275, "lr": 8.204378069925121e-06, "epoch": 1.0576923076923077, "percentage": 35.26, "elapsed_time": "0:22:56", "remaining_time": "0:42:06"} +{"current_steps": 56, "total_steps": 156, "loss": 0.6379, "lr": 8.117449009293668e-06, "epoch": 1.0769230769230769, "percentage": 35.9, "elapsed_time": "0:23:20", "remaining_time": "0:41:40"} +{"current_steps": 57, "total_steps": 156, "loss": 0.6209, "lr": 8.0289502192041e-06, "epoch": 1.0961538461538463, "percentage": 36.54, "elapsed_time": "0:23:44", "remaining_time": "0:41:14"} +{"current_steps": 58, "total_steps": 156, "loss": 0.6324, "lr": 7.938926261462366e-06, "epoch": 1.1153846153846154, "percentage": 37.18, "elapsed_time": "0:24:10", "remaining_time": "0:40:50"} +{"current_steps": 59, "total_steps": 156, "loss": 0.6463, "lr": 7.84742246584226e-06, "epoch": 1.1346153846153846, "percentage": 37.82, "elapsed_time": "0:24:36", "remaining_time": "0:40:27"} +{"current_steps": 60, "total_steps": 156, "loss": 0.6315, "lr": 7.754484907260513e-06, "epoch": 1.1538461538461537, "percentage": 38.46, "elapsed_time": "0:25:01", "remaining_time": "0:40:02"} +{"current_steps": 61, "total_steps": 156, "loss": 0.641, "lr": 7.660160382576683e-06, "epoch": 1.1730769230769231, "percentage": 39.1, "elapsed_time": "0:25:26", "remaining_time": "0:39:37"} +{"current_steps": 62, "total_steps": 156, "loss": 0.6246, "lr": 7.564496387029532e-06, "epoch": 1.1923076923076923, "percentage": 39.74, "elapsed_time": "0:25:51", "remaining_time": "0:39:12"} +{"current_steps": 63, "total_steps": 156, "loss": 0.6314, "lr": 7.467541090321735e-06, "epoch": 1.2115384615384615, "percentage": 40.38, "elapsed_time": "0:26:15", "remaining_time": "0:38:45"} +{"current_steps": 64, "total_steps": 156, "loss": 0.6186, "lr": 7.369343312364994e-06, "epoch": 1.2307692307692308, "percentage": 41.03, "elapsed_time": "0:26:39", "remaining_time": "0:38:19"} +{"current_steps": 65, "total_steps": 156, "loss": 0.6357, "lr": 7.269952498697734e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:27:05", "remaining_time": "0:37:56"} +{"current_steps": 66, "total_steps": 156, "loss": 0.6415, "lr": 7.169418695587791e-06, "epoch": 1.2692307692307692, "percentage": 42.31, "elapsed_time": "0:27:29", "remaining_time": "0:37:29"} +{"current_steps": 67, "total_steps": 156, "loss": 0.6248, "lr": 7.067792524832604e-06, "epoch": 1.2884615384615383, "percentage": 42.95, "elapsed_time": "0:27:55", "remaining_time": "0:37:05"} +{"current_steps": 68, "total_steps": 156, "loss": 0.6218, "lr": 6.965125158269619e-06, "epoch": 1.3076923076923077, "percentage": 43.59, "elapsed_time": "0:28:19", "remaining_time": "0:36:39"} +{"current_steps": 69, "total_steps": 156, "loss": 0.629, "lr": 6.8614682920097265e-06, "epoch": 1.3269230769230769, "percentage": 44.23, "elapsed_time": "0:28:44", "remaining_time": "0:36:14"} +{"current_steps": 70, "total_steps": 156, "loss": 0.6283, "lr": 6.7568741204067145e-06, "epoch": 1.3461538461538463, "percentage": 44.87, "elapsed_time": "0:29:09", "remaining_time": "0:35:49"} +{"current_steps": 71, "total_steps": 156, "loss": 0.6251, "lr": 6.651395309775837e-06, "epoch": 1.3653846153846154, "percentage": 45.51, "elapsed_time": "0:29:34", "remaining_time": "0:35:24"} +{"current_steps": 72, "total_steps": 156, "loss": 0.6194, "lr": 6.545084971874738e-06, "epoch": 1.3846153846153846, "percentage": 46.15, "elapsed_time": "0:29:58", "remaining_time": "0:34:58"} +{"current_steps": 73, "total_steps": 156, "loss": 0.624, "lr": 6.437996637160086e-06, "epoch": 1.4038461538461537, "percentage": 46.79, "elapsed_time": "0:30:21", "remaining_time": "0:34:31"} +{"current_steps": 74, "total_steps": 156, "loss": 0.6245, "lr": 6.330184227833376e-06, "epoch": 1.4230769230769231, "percentage": 47.44, "elapsed_time": "0:30:45", "remaining_time": "0:34:04"} +{"current_steps": 75, "total_steps": 156, "loss": 0.6153, "lr": 6.2217020306894705e-06, "epoch": 1.4423076923076923, "percentage": 48.08, "elapsed_time": "0:31:09", "remaining_time": "0:33:39"} +{"current_steps": 76, "total_steps": 156, "loss": 0.6387, "lr": 6.112604669781572e-06, "epoch": 1.4615384615384617, "percentage": 48.72, "elapsed_time": "0:31:35", "remaining_time": "0:33:15"} +{"current_steps": 77, "total_steps": 156, "loss": 0.6281, "lr": 6.002947078916365e-06, "epoch": 1.4807692307692308, "percentage": 49.36, "elapsed_time": "0:31:59", "remaining_time": "0:32:49"} +{"current_steps": 78, "total_steps": 156, "loss": 0.6193, "lr": 5.892784473993184e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:32:26", "remaining_time": "0:32:26"} +{"current_steps": 79, "total_steps": 156, "loss": 0.6061, "lr": 5.782172325201155e-06, "epoch": 1.5192307692307692, "percentage": 50.64, "elapsed_time": "0:32:51", "remaining_time": "0:32:01"} +{"current_steps": 80, "total_steps": 156, "loss": 0.603, "lr": 5.671166329088278e-06, "epoch": 1.5384615384615383, "percentage": 51.28, "elapsed_time": "0:33:15", "remaining_time": "0:31:36"} +{"current_steps": 81, "total_steps": 156, "loss": 0.6384, "lr": 5.559822380516539e-06, "epoch": 1.5576923076923077, "percentage": 51.92, "elapsed_time": "0:33:40", "remaining_time": "0:31:10"} +{"current_steps": 82, "total_steps": 156, "loss": 0.6201, "lr": 5.448196544517168e-06, "epoch": 1.5769230769230769, "percentage": 52.56, "elapsed_time": "0:34:04", "remaining_time": "0:30:45"} +{"current_steps": 83, "total_steps": 156, "loss": 0.6219, "lr": 5.336345028060199e-06, "epoch": 1.5961538461538463, "percentage": 53.21, "elapsed_time": "0:34:27", "remaining_time": "0:30:18"} +{"current_steps": 84, "total_steps": 156, "loss": 0.619, "lr": 5.224324151752575e-06, "epoch": 1.6153846153846154, "percentage": 53.85, "elapsed_time": "0:34:53", "remaining_time": "0:29:54"} +{"current_steps": 85, "total_steps": 156, "loss": 0.6353, "lr": 5.112190321479026e-06, "epoch": 1.6346153846153846, "percentage": 54.49, "elapsed_time": "0:35:15", "remaining_time": "0:29:27"} +{"current_steps": 86, "total_steps": 156, "loss": 0.6309, "lr": 5e-06, "epoch": 1.6538461538461537, "percentage": 55.13, "elapsed_time": "0:35:40", "remaining_time": "0:29:02"} +{"current_steps": 87, "total_steps": 156, "loss": 0.6306, "lr": 4.887809678520976e-06, "epoch": 1.6730769230769231, "percentage": 55.77, "elapsed_time": "0:36:04", "remaining_time": "0:28:36"} +{"current_steps": 88, "total_steps": 156, "loss": 0.6247, "lr": 4.775675848247427e-06, "epoch": 1.6923076923076923, "percentage": 56.41, "elapsed_time": "0:36:24", "remaining_time": "0:28:07"} +{"current_steps": 89, "total_steps": 156, "loss": 0.6243, "lr": 4.663654971939802e-06, "epoch": 1.7115384615384617, "percentage": 57.05, "elapsed_time": "0:36:50", "remaining_time": "0:27:44"} +{"current_steps": 90, "total_steps": 156, "loss": 0.6181, "lr": 4.551803455482833e-06, "epoch": 1.7307692307692308, "percentage": 57.69, "elapsed_time": "0:37:15", "remaining_time": "0:27:19"} +{"current_steps": 91, "total_steps": 156, "loss": 0.6434, "lr": 4.4401776194834615e-06, "epoch": 1.75, "percentage": 58.33, "elapsed_time": "0:37:39", "remaining_time": "0:26:53"} +{"current_steps": 92, "total_steps": 156, "loss": 0.6248, "lr": 4.3288336709117246e-06, "epoch": 1.7692307692307692, "percentage": 58.97, "elapsed_time": "0:38:03", "remaining_time": "0:26:28"} +{"current_steps": 93, "total_steps": 156, "loss": 0.6305, "lr": 4.217827674798845e-06, "epoch": 1.7884615384615383, "percentage": 59.62, "elapsed_time": "0:38:27", "remaining_time": "0:26:03"} +{"current_steps": 94, "total_steps": 156, "loss": 0.6209, "lr": 4.107215526006818e-06, "epoch": 1.8076923076923077, "percentage": 60.26, "elapsed_time": "0:38:50", "remaining_time": "0:25:37"} +{"current_steps": 95, "total_steps": 156, "loss": 0.6148, "lr": 3.997052921083637e-06, "epoch": 1.8269230769230769, "percentage": 60.9, "elapsed_time": "0:39:14", "remaining_time": "0:25:12"} +{"current_steps": 96, "total_steps": 156, "loss": 0.6293, "lr": 3.887395330218429e-06, "epoch": 1.8461538461538463, "percentage": 61.54, "elapsed_time": "0:39:40", "remaining_time": "0:24:47"} +{"current_steps": 97, "total_steps": 156, "loss": 0.6114, "lr": 3.778297969310529e-06, "epoch": 1.8653846153846154, "percentage": 62.18, "elapsed_time": "0:40:05", "remaining_time": "0:24:23"} +{"current_steps": 98, "total_steps": 156, "loss": 0.6167, "lr": 3.669815772166625e-06, "epoch": 1.8846153846153846, "percentage": 62.82, "elapsed_time": "0:40:30", "remaining_time": "0:23:58"} +{"current_steps": 99, "total_steps": 156, "loss": 0.6031, "lr": 3.562003362839914e-06, "epoch": 1.9038461538461537, "percentage": 63.46, "elapsed_time": "0:40:53", "remaining_time": "0:23:32"} +{"current_steps": 100, "total_steps": 156, "loss": 0.6085, "lr": 3.4549150281252635e-06, "epoch": 1.9230769230769231, "percentage": 64.1, "elapsed_time": "0:41:18", "remaining_time": "0:23:07"} +{"current_steps": 101, "total_steps": 156, "loss": 0.6071, "lr": 3.3486046902241663e-06, "epoch": 1.9423076923076923, "percentage": 64.74, "elapsed_time": "0:42:07", "remaining_time": "0:22:56"} +{"current_steps": 102, "total_steps": 156, "loss": 0.6268, "lr": 3.2431258795932863e-06, "epoch": 1.9615384615384617, "percentage": 65.38, "elapsed_time": "0:42:30", "remaining_time": "0:22:30"} +{"current_steps": 103, "total_steps": 156, "loss": 0.6142, "lr": 3.1385317079902743e-06, "epoch": 1.9807692307692308, "percentage": 66.03, "elapsed_time": "0:42:54", "remaining_time": "0:22:04"} +{"current_steps": 104, "total_steps": 156, "loss": 0.6343, "lr": 3.0348748417303826e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:43:17", "remaining_time": "0:21:38"} +{"current_steps": 105, "total_steps": 156, "loss": 0.6071, "lr": 2.932207475167398e-06, "epoch": 2.019230769230769, "percentage": 67.31, "elapsed_time": "0:43:43", "remaining_time": "0:21:14"} +{"current_steps": 106, "total_steps": 156, "loss": 0.5926, "lr": 2.83058130441221e-06, "epoch": 2.0384615384615383, "percentage": 67.95, "elapsed_time": "0:44:08", "remaining_time": "0:20:49"} +{"current_steps": 107, "total_steps": 156, "loss": 0.6021, "lr": 2.7300475013022666e-06, "epoch": 2.0576923076923075, "percentage": 68.59, "elapsed_time": "0:44:32", "remaining_time": "0:20:23"} +{"current_steps": 108, "total_steps": 156, "loss": 0.5946, "lr": 2.6306566876350072e-06, "epoch": 2.076923076923077, "percentage": 69.23, "elapsed_time": "0:44:56", "remaining_time": "0:19:58"} +{"current_steps": 109, "total_steps": 156, "loss": 0.5968, "lr": 2.532458909678266e-06, "epoch": 2.0961538461538463, "percentage": 69.87, "elapsed_time": "0:45:20", "remaining_time": "0:19:33"} +{"current_steps": 110, "total_steps": 156, "loss": 0.586, "lr": 2.43550361297047e-06, "epoch": 2.1153846153846154, "percentage": 70.51, "elapsed_time": "0:45:44", "remaining_time": "0:19:07"} +{"current_steps": 111, "total_steps": 156, "loss": 0.588, "lr": 2.339839617423318e-06, "epoch": 2.1346153846153846, "percentage": 71.15, "elapsed_time": "0:46:08", "remaining_time": "0:18:42"} +{"current_steps": 112, "total_steps": 156, "loss": 0.5875, "lr": 2.245515092739488e-06, "epoch": 2.1538461538461537, "percentage": 71.79, "elapsed_time": "0:46:32", "remaining_time": "0:18:16"} +{"current_steps": 113, "total_steps": 156, "loss": 0.5922, "lr": 2.1525775341577404e-06, "epoch": 2.173076923076923, "percentage": 72.44, "elapsed_time": "0:46:57", "remaining_time": "0:17:52"} +{"current_steps": 114, "total_steps": 156, "loss": 0.6045, "lr": 2.061073738537635e-06, "epoch": 2.1923076923076925, "percentage": 73.08, "elapsed_time": "0:47:22", "remaining_time": "0:17:27"} +{"current_steps": 115, "total_steps": 156, "loss": 0.5879, "lr": 1.971049780795901e-06, "epoch": 2.2115384615384617, "percentage": 73.72, "elapsed_time": "0:47:47", "remaining_time": "0:17:02"} +{"current_steps": 116, "total_steps": 156, "loss": 0.5974, "lr": 1.8825509907063328e-06, "epoch": 2.230769230769231, "percentage": 74.36, "elapsed_time": "0:48:12", "remaining_time": "0:16:37"} +{"current_steps": 117, "total_steps": 156, "loss": 0.5905, "lr": 1.7956219300748796e-06, "epoch": 2.25, "percentage": 75.0, "elapsed_time": "0:48:35", "remaining_time": "0:16:11"} +{"current_steps": 118, "total_steps": 156, "loss": 0.5813, "lr": 1.7103063703014372e-06, "epoch": 2.269230769230769, "percentage": 75.64, "elapsed_time": "0:48:58", "remaining_time": "0:15:46"} +{"current_steps": 119, "total_steps": 156, "loss": 0.5798, "lr": 1.6266472703396286e-06, "epoch": 2.2884615384615383, "percentage": 76.28, "elapsed_time": "0:49:23", "remaining_time": "0:15:21"} +{"current_steps": 120, "total_steps": 156, "loss": 0.5973, "lr": 1.544686755065677e-06, "epoch": 2.3076923076923075, "percentage": 76.92, "elapsed_time": "0:49:46", "remaining_time": "0:14:56"} +{"current_steps": 121, "total_steps": 156, "loss": 0.5915, "lr": 1.4644660940672628e-06, "epoch": 2.326923076923077, "percentage": 77.56, "elapsed_time": "0:50:10", "remaining_time": "0:14:30"} +{"current_steps": 122, "total_steps": 156, "loss": 0.6004, "lr": 1.3860256808630429e-06, "epoch": 2.3461538461538463, "percentage": 78.21, "elapsed_time": "0:50:35", "remaining_time": "0:14:05"} +{"current_steps": 123, "total_steps": 156, "loss": 0.6029, "lr": 1.3094050125632973e-06, "epoch": 2.3653846153846154, "percentage": 78.85, "elapsed_time": "0:50:59", "remaining_time": "0:13:40"} +{"current_steps": 124, "total_steps": 156, "loss": 0.6025, "lr": 1.234642669981946e-06, "epoch": 2.3846153846153846, "percentage": 79.49, "elapsed_time": "0:51:23", "remaining_time": "0:13:15"} +{"current_steps": 125, "total_steps": 156, "loss": 0.5737, "lr": 1.1617762982099446e-06, "epoch": 2.4038461538461537, "percentage": 80.13, "elapsed_time": "0:51:47", "remaining_time": "0:12:50"} +{"current_steps": 126, "total_steps": 156, "loss": 0.5701, "lr": 1.0908425876598512e-06, "epoch": 2.423076923076923, "percentage": 80.77, "elapsed_time": "0:52:11", "remaining_time": "0:12:25"} +{"current_steps": 127, "total_steps": 156, "loss": 0.604, "lr": 1.0218772555910955e-06, "epoch": 2.4423076923076925, "percentage": 81.41, "elapsed_time": "0:52:33", "remaining_time": "0:12:00"} +{"current_steps": 128, "total_steps": 156, "loss": 0.6136, "lr": 9.549150281252633e-07, "epoch": 2.4615384615384617, "percentage": 82.05, "elapsed_time": "0:52:56", "remaining_time": "0:11:34"} +{"current_steps": 129, "total_steps": 156, "loss": 0.5856, "lr": 8.899896227604509e-07, "epoch": 2.480769230769231, "percentage": 82.69, "elapsed_time": "0:53:20", "remaining_time": "0:11:09"} +{"current_steps": 130, "total_steps": 156, "loss": 0.5907, "lr": 8.271337313934869e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:53:42", "remaining_time": "0:10:44"} +{"current_steps": 131, "total_steps": 156, "loss": 0.5904, "lr": 7.663790038585794e-07, "epoch": 2.519230769230769, "percentage": 83.97, "elapsed_time": "0:54:05", "remaining_time": "0:10:19"} +{"current_steps": 132, "total_steps": 156, "loss": 0.5775, "lr": 7.077560319906696e-07, "epoch": 2.5384615384615383, "percentage": 84.62, "elapsed_time": "0:54:30", "remaining_time": "0:09:54"} +{"current_steps": 133, "total_steps": 156, "loss": 0.5878, "lr": 6.512943342215234e-07, "epoch": 2.5576923076923075, "percentage": 85.26, "elapsed_time": "0:54:52", "remaining_time": "0:09:29"} +{"current_steps": 134, "total_steps": 156, "loss": 0.601, "lr": 5.9702234071631e-07, "epoch": 2.5769230769230766, "percentage": 85.9, "elapsed_time": "0:55:16", "remaining_time": "0:09:04"} +{"current_steps": 135, "total_steps": 156, "loss": 0.5926, "lr": 5.449673790581611e-07, "epoch": 2.5961538461538463, "percentage": 86.54, "elapsed_time": "0:55:40", "remaining_time": "0:08:39"} +{"current_steps": 136, "total_steps": 156, "loss": 0.5772, "lr": 4.951556604879049e-07, "epoch": 2.6153846153846154, "percentage": 87.18, "elapsed_time": "0:56:03", "remaining_time": "0:08:14"} +{"current_steps": 137, "total_steps": 156, "loss": 0.5895, "lr": 4.4761226670592074e-07, "epoch": 2.6346153846153846, "percentage": 87.82, "elapsed_time": "0:56:26", "remaining_time": "0:07:49"} +{"current_steps": 138, "total_steps": 156, "loss": 0.5984, "lr": 4.0236113724274716e-07, "epoch": 2.6538461538461537, "percentage": 88.46, "elapsed_time": "0:56:49", "remaining_time": "0:07:24"} +{"current_steps": 139, "total_steps": 156, "loss": 0.5967, "lr": 3.5942505740480583e-07, "epoch": 2.6730769230769234, "percentage": 89.1, "elapsed_time": "0:57:13", "remaining_time": "0:06:59"} +{"current_steps": 140, "total_steps": 156, "loss": 0.6131, "lr": 3.18825646801314e-07, "epoch": 2.6923076923076925, "percentage": 89.74, "elapsed_time": "0:57:36", "remaining_time": "0:06:35"} +{"current_steps": 141, "total_steps": 156, "loss": 0.5952, "lr": 2.8058334845816214e-07, "epoch": 2.7115384615384617, "percentage": 90.38, "elapsed_time": "0:58:01", "remaining_time": "0:06:10"} +{"current_steps": 142, "total_steps": 156, "loss": 0.6009, "lr": 2.447174185242324e-07, "epoch": 2.730769230769231, "percentage": 91.03, "elapsed_time": "0:58:27", "remaining_time": "0:05:45"} +{"current_steps": 143, "total_steps": 156, "loss": 0.6009, "lr": 2.1124591657534776e-07, "epoch": 2.75, "percentage": 91.67, "elapsed_time": "0:58:52", "remaining_time": "0:05:21"} +{"current_steps": 144, "total_steps": 156, "loss": 0.5979, "lr": 1.801856965207338e-07, "epoch": 2.769230769230769, "percentage": 92.31, "elapsed_time": "0:59:16", "remaining_time": "0:04:56"} +{"current_steps": 145, "total_steps": 156, "loss": 0.5747, "lr": 1.5155239811656562e-07, "epoch": 2.7884615384615383, "percentage": 92.95, "elapsed_time": "0:59:38", "remaining_time": "0:04:31"} +{"current_steps": 146, "total_steps": 156, "loss": 0.5994, "lr": 1.253604390908819e-07, "epoch": 2.8076923076923075, "percentage": 93.59, "elapsed_time": "1:00:02", "remaining_time": "0:04:06"} +{"current_steps": 147, "total_steps": 156, "loss": 0.5913, "lr": 1.0162300788382263e-07, "epoch": 2.8269230769230766, "percentage": 94.23, "elapsed_time": "1:00:25", "remaining_time": "0:03:41"} +{"current_steps": 148, "total_steps": 156, "loss": 0.5829, "lr": 8.035205700685167e-08, "epoch": 2.8461538461538463, "percentage": 94.87, "elapsed_time": "1:00:50", "remaining_time": "0:03:17"} +{"current_steps": 149, "total_steps": 156, "loss": 0.5927, "lr": 6.15582970243117e-08, "epoch": 2.8653846153846154, "percentage": 95.51, "elapsed_time": "1:01:15", "remaining_time": "0:02:52"} +{"current_steps": 150, "total_steps": 156, "loss": 0.5781, "lr": 4.52511911603265e-08, "epoch": 2.8846153846153846, "percentage": 96.15, "elapsed_time": "1:01:39", "remaining_time": "0:02:27"} +{"current_steps": 151, "total_steps": 156, "loss": 0.6044, "lr": 3.143895053378698e-08, "epoch": 2.9038461538461537, "percentage": 96.79, "elapsed_time": "1:02:01", "remaining_time": "0:02:03"} +{"current_steps": 152, "total_steps": 156, "loss": 0.5993, "lr": 2.012853002380466e-08, "epoch": 2.9230769230769234, "percentage": 97.44, "elapsed_time": "1:02:25", "remaining_time": "0:01:38"} +{"current_steps": 153, "total_steps": 156, "loss": 0.5933, "lr": 1.132562476771959e-08, "epoch": 2.9423076923076925, "percentage": 98.08, "elapsed_time": "1:02:49", "remaining_time": "0:01:13"} +{"current_steps": 154, "total_steps": 156, "loss": 0.5813, "lr": 5.034667293427053e-09, "epoch": 2.9615384615384617, "percentage": 98.72, "elapsed_time": "1:03:14", "remaining_time": "0:00:49"} +{"current_steps": 155, "total_steps": 156, "loss": 0.5851, "lr": 1.2588252874673469e-09, "epoch": 2.980769230769231, "percentage": 99.36, "elapsed_time": "1:03:38", "remaining_time": "0:00:24"} +{"current_steps": 156, "total_steps": 156, "loss": 0.5678, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:04:03", "remaining_time": "0:00:00"} +{"current_steps": 156, "total_steps": 156, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:04:23", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..4b86e67 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,1134 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 156, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.019230769230769232, + "grad_norm": 6.756826400756836, + "learning_rate": 6.25e-07, + "loss": 1.0467, + "step": 1 + }, + { + "epoch": 0.038461538461538464, + "grad_norm": 6.748652935028076, + "learning_rate": 1.25e-06, + "loss": 1.035, + "step": 2 + }, + { + "epoch": 0.057692307692307696, + "grad_norm": 6.735743999481201, + "learning_rate": 1.8750000000000003e-06, + "loss": 1.0379, + "step": 3 + }, + { + "epoch": 0.07692307692307693, + "grad_norm": 6.658365726470947, + "learning_rate": 2.5e-06, + "loss": 1.0497, + "step": 4 + }, + { + "epoch": 0.09615384615384616, + "grad_norm": 6.092031955718994, + "learning_rate": 3.125e-06, + "loss": 1.0217, + "step": 5 + }, + { + "epoch": 0.11538461538461539, + "grad_norm": 4.476426124572754, + "learning_rate": 3.7500000000000005e-06, + "loss": 0.9747, + "step": 6 + }, + { + "epoch": 0.1346153846153846, + "grad_norm": 2.8898186683654785, + "learning_rate": 4.3750000000000005e-06, + "loss": 0.9507, + "step": 7 + }, + { + "epoch": 0.15384615384615385, + "grad_norm": 2.6818649768829346, + "learning_rate": 5e-06, + "loss": 0.9473, + "step": 8 + }, + { + "epoch": 0.17307692307692307, + "grad_norm": 4.384618759155273, + "learning_rate": 5.625e-06, + "loss": 0.9369, + "step": 9 + }, + { + "epoch": 0.19230769230769232, + "grad_norm": 4.5409979820251465, + "learning_rate": 6.25e-06, + "loss": 0.9425, + "step": 10 + }, + { + "epoch": 0.21153846153846154, + "grad_norm": 4.295501232147217, + "learning_rate": 6.875e-06, + "loss": 0.9044, + "step": 11 + }, + { + "epoch": 0.23076923076923078, + "grad_norm": 3.13700795173645, + "learning_rate": 7.500000000000001e-06, + "loss": 0.8622, + "step": 12 + }, + { + "epoch": 0.25, + "grad_norm": 2.9523777961730957, + "learning_rate": 8.125000000000001e-06, + "loss": 0.858, + "step": 13 + }, + { + "epoch": 0.2692307692307692, + "grad_norm": 2.254493474960327, + "learning_rate": 8.750000000000001e-06, + "loss": 0.8479, + "step": 14 + }, + { + "epoch": 0.28846153846153844, + "grad_norm": 1.5103687047958374, + "learning_rate": 9.375000000000001e-06, + "loss": 0.8085, + "step": 15 + }, + { + "epoch": 0.3076923076923077, + "grad_norm": 1.515587329864502, + "learning_rate": 1e-05, + "loss": 0.8253, + "step": 16 + }, + { + "epoch": 0.3269230769230769, + "grad_norm": 1.5592089891433716, + "learning_rate": 9.998741174712534e-06, + "loss": 0.7737, + "step": 17 + }, + { + "epoch": 0.34615384615384615, + "grad_norm": 1.36715567111969, + "learning_rate": 9.994965332706574e-06, + "loss": 0.7872, + "step": 18 + }, + { + "epoch": 0.36538461538461536, + "grad_norm": 1.0765823125839233, + "learning_rate": 9.98867437523228e-06, + "loss": 0.7565, + "step": 19 + }, + { + "epoch": 0.38461538461538464, + "grad_norm": 1.1925386190414429, + "learning_rate": 9.979871469976197e-06, + "loss": 0.7616, + "step": 20 + }, + { + "epoch": 0.40384615384615385, + "grad_norm": 1.0839797258377075, + "learning_rate": 9.968561049466214e-06, + "loss": 0.7438, + "step": 21 + }, + { + "epoch": 0.4230769230769231, + "grad_norm": 0.8592272996902466, + "learning_rate": 9.954748808839675e-06, + "loss": 0.747, + "step": 22 + }, + { + "epoch": 0.4423076923076923, + "grad_norm": 0.8572734594345093, + "learning_rate": 9.938441702975689e-06, + "loss": 0.7425, + "step": 23 + }, + { + "epoch": 0.46153846153846156, + "grad_norm": 1.0244359970092773, + "learning_rate": 9.91964794299315e-06, + "loss": 0.7223, + "step": 24 + }, + { + "epoch": 0.4807692307692308, + "grad_norm": 0.9166272878646851, + "learning_rate": 9.898376992116179e-06, + "loss": 0.7254, + "step": 25 + }, + { + "epoch": 0.5, + "grad_norm": 0.8023123741149902, + "learning_rate": 9.874639560909118e-06, + "loss": 0.705, + "step": 26 + }, + { + "epoch": 0.5192307692307693, + "grad_norm": 0.7520763874053955, + "learning_rate": 9.848447601883436e-06, + "loss": 0.7097, + "step": 27 + }, + { + "epoch": 0.5384615384615384, + "grad_norm": 0.7471436262130737, + "learning_rate": 9.819814303479268e-06, + "loss": 0.7087, + "step": 28 + }, + { + "epoch": 0.5576923076923077, + "grad_norm": 0.8560906648635864, + "learning_rate": 9.788754083424654e-06, + "loss": 0.7106, + "step": 29 + }, + { + "epoch": 0.5769230769230769, + "grad_norm": 0.7833404541015625, + "learning_rate": 9.755282581475769e-06, + "loss": 0.7004, + "step": 30 + }, + { + "epoch": 0.5961538461538461, + "grad_norm": 0.6619976758956909, + "learning_rate": 9.719416651541839e-06, + "loss": 0.7029, + "step": 31 + }, + { + "epoch": 0.6153846153846154, + "grad_norm": 0.7908540368080139, + "learning_rate": 9.681174353198687e-06, + "loss": 0.702, + "step": 32 + }, + { + "epoch": 0.6346153846153846, + "grad_norm": 0.7704586386680603, + "learning_rate": 9.640574942595195e-06, + "loss": 0.7126, + "step": 33 + }, + { + "epoch": 0.6538461538461539, + "grad_norm": 0.6045657992362976, + "learning_rate": 9.597638862757255e-06, + "loss": 0.6879, + "step": 34 + }, + { + "epoch": 0.6730769230769231, + "grad_norm": 0.6769744157791138, + "learning_rate": 9.552387733294081e-06, + "loss": 0.7112, + "step": 35 + }, + { + "epoch": 0.6923076923076923, + "grad_norm": 0.70807945728302, + "learning_rate": 9.504844339512096e-06, + "loss": 0.6787, + "step": 36 + }, + { + "epoch": 0.7115384615384616, + "grad_norm": 0.5988538861274719, + "learning_rate": 9.45503262094184e-06, + "loss": 0.6876, + "step": 37 + }, + { + "epoch": 0.7307692307692307, + "grad_norm": 0.6042438745498657, + "learning_rate": 9.40297765928369e-06, + "loss": 0.6943, + "step": 38 + }, + { + "epoch": 0.75, + "grad_norm": 0.6781715154647827, + "learning_rate": 9.348705665778479e-06, + "loss": 0.6842, + "step": 39 + }, + { + "epoch": 0.7692307692307693, + "grad_norm": 0.6857075691223145, + "learning_rate": 9.292243968009332e-06, + "loss": 0.6676, + "step": 40 + }, + { + "epoch": 0.7884615384615384, + "grad_norm": 0.5267153978347778, + "learning_rate": 9.233620996141421e-06, + "loss": 0.6693, + "step": 41 + }, + { + "epoch": 0.8076923076923077, + "grad_norm": 0.5316743850708008, + "learning_rate": 9.172866268606514e-06, + "loss": 0.6685, + "step": 42 + }, + { + "epoch": 0.8269230769230769, + "grad_norm": 0.7179816961288452, + "learning_rate": 9.110010377239552e-06, + "loss": 0.6766, + "step": 43 + }, + { + "epoch": 0.8461538461538461, + "grad_norm": 0.6035124659538269, + "learning_rate": 9.045084971874738e-06, + "loss": 0.6821, + "step": 44 + }, + { + "epoch": 0.8653846153846154, + "grad_norm": 0.7270795702934265, + "learning_rate": 8.978122744408905e-06, + "loss": 0.6683, + "step": 45 + }, + { + "epoch": 0.8846153846153846, + "grad_norm": 0.5073479413986206, + "learning_rate": 8.90915741234015e-06, + "loss": 0.6788, + "step": 46 + }, + { + "epoch": 0.9038461538461539, + "grad_norm": 0.5434288382530212, + "learning_rate": 8.838223701790057e-06, + "loss": 0.66, + "step": 47 + }, + { + "epoch": 0.9230769230769231, + "grad_norm": 0.6094857454299927, + "learning_rate": 8.765357330018056e-06, + "loss": 0.6581, + "step": 48 + }, + { + "epoch": 0.9423076923076923, + "grad_norm": 0.46337971091270447, + "learning_rate": 8.690594987436705e-06, + "loss": 0.6627, + "step": 49 + }, + { + "epoch": 0.9615384615384616, + "grad_norm": 0.6698839068412781, + "learning_rate": 8.613974319136959e-06, + "loss": 0.6598, + "step": 50 + }, + { + "epoch": 0.9807692307692307, + "grad_norm": 0.4814399480819702, + "learning_rate": 8.535533905932739e-06, + "loss": 0.665, + "step": 51 + }, + { + "epoch": 1.0, + "grad_norm": 0.5604783296585083, + "learning_rate": 8.455313244934324e-06, + "loss": 0.6737, + "step": 52 + }, + { + "epoch": 1.0192307692307692, + "grad_norm": 0.5326887369155884, + "learning_rate": 8.373352729660373e-06, + "loss": 0.6544, + "step": 53 + }, + { + "epoch": 1.0384615384615385, + "grad_norm": 0.518214762210846, + "learning_rate": 8.289693629698564e-06, + "loss": 0.631, + "step": 54 + }, + { + "epoch": 1.0576923076923077, + "grad_norm": 0.539520263671875, + "learning_rate": 8.204378069925121e-06, + "loss": 0.6275, + "step": 55 + }, + { + "epoch": 1.0769230769230769, + "grad_norm": 0.5140302181243896, + "learning_rate": 8.117449009293668e-06, + "loss": 0.6379, + "step": 56 + }, + { + "epoch": 1.0961538461538463, + "grad_norm": 0.7126110792160034, + "learning_rate": 8.0289502192041e-06, + "loss": 0.6209, + "step": 57 + }, + { + "epoch": 1.1153846153846154, + "grad_norm": 0.5747066140174866, + "learning_rate": 7.938926261462366e-06, + "loss": 0.6324, + "step": 58 + }, + { + "epoch": 1.1346153846153846, + "grad_norm": 0.6441423296928406, + "learning_rate": 7.84742246584226e-06, + "loss": 0.6463, + "step": 59 + }, + { + "epoch": 1.1538461538461537, + "grad_norm": 0.5559582710266113, + "learning_rate": 7.754484907260513e-06, + "loss": 0.6315, + "step": 60 + }, + { + "epoch": 1.1730769230769231, + "grad_norm": 0.5032030344009399, + "learning_rate": 7.660160382576683e-06, + "loss": 0.641, + "step": 61 + }, + { + "epoch": 1.1923076923076923, + "grad_norm": 0.5290240049362183, + "learning_rate": 7.564496387029532e-06, + "loss": 0.6246, + "step": 62 + }, + { + "epoch": 1.2115384615384615, + "grad_norm": 0.47469562292099, + "learning_rate": 7.467541090321735e-06, + "loss": 0.6314, + "step": 63 + }, + { + "epoch": 1.2307692307692308, + "grad_norm": 0.6516867876052856, + "learning_rate": 7.369343312364994e-06, + "loss": 0.6186, + "step": 64 + }, + { + "epoch": 1.25, + "grad_norm": 0.4732189476490021, + "learning_rate": 7.269952498697734e-06, + "loss": 0.6357, + "step": 65 + }, + { + "epoch": 1.2692307692307692, + "grad_norm": 0.5501453280448914, + "learning_rate": 7.169418695587791e-06, + "loss": 0.6415, + "step": 66 + }, + { + "epoch": 1.2884615384615383, + "grad_norm": 0.49621427059173584, + "learning_rate": 7.067792524832604e-06, + "loss": 0.6248, + "step": 67 + }, + { + "epoch": 1.3076923076923077, + "grad_norm": 0.4925438463687897, + "learning_rate": 6.965125158269619e-06, + "loss": 0.6218, + "step": 68 + }, + { + "epoch": 1.3269230769230769, + "grad_norm": 0.5866847038269043, + "learning_rate": 6.8614682920097265e-06, + "loss": 0.629, + "step": 69 + }, + { + "epoch": 1.3461538461538463, + "grad_norm": 0.5412906408309937, + "learning_rate": 6.7568741204067145e-06, + "loss": 0.6283, + "step": 70 + }, + { + "epoch": 1.3653846153846154, + "grad_norm": 0.5679116249084473, + "learning_rate": 6.651395309775837e-06, + "loss": 0.6251, + "step": 71 + }, + { + "epoch": 1.3846153846153846, + "grad_norm": 0.46475809812545776, + "learning_rate": 6.545084971874738e-06, + "loss": 0.6194, + "step": 72 + }, + { + "epoch": 1.4038461538461537, + "grad_norm": 0.6032177805900574, + "learning_rate": 6.437996637160086e-06, + "loss": 0.624, + "step": 73 + }, + { + "epoch": 1.4230769230769231, + "grad_norm": 0.4972044825553894, + "learning_rate": 6.330184227833376e-06, + "loss": 0.6245, + "step": 74 + }, + { + "epoch": 1.4423076923076923, + "grad_norm": 0.49976637959480286, + "learning_rate": 6.2217020306894705e-06, + "loss": 0.6153, + "step": 75 + }, + { + "epoch": 1.4615384615384617, + "grad_norm": 0.5510290861129761, + "learning_rate": 6.112604669781572e-06, + "loss": 0.6387, + "step": 76 + }, + { + "epoch": 1.4807692307692308, + "grad_norm": 0.5240339636802673, + "learning_rate": 6.002947078916365e-06, + "loss": 0.6281, + "step": 77 + }, + { + "epoch": 1.5, + "grad_norm": 0.5085740089416504, + "learning_rate": 5.892784473993184e-06, + "loss": 0.6193, + "step": 78 + }, + { + "epoch": 1.5192307692307692, + "grad_norm": 0.47661781311035156, + "learning_rate": 5.782172325201155e-06, + "loss": 0.6061, + "step": 79 + }, + { + "epoch": 1.5384615384615383, + "grad_norm": 0.4540369510650635, + "learning_rate": 5.671166329088278e-06, + "loss": 0.603, + "step": 80 + }, + { + "epoch": 1.5576923076923077, + "grad_norm": 0.48901426792144775, + "learning_rate": 5.559822380516539e-06, + "loss": 0.6384, + "step": 81 + }, + { + "epoch": 1.5769230769230769, + "grad_norm": 0.49942049384117126, + "learning_rate": 5.448196544517168e-06, + "loss": 0.6201, + "step": 82 + }, + { + "epoch": 1.5961538461538463, + "grad_norm": 0.4124830365180969, + "learning_rate": 5.336345028060199e-06, + "loss": 0.6219, + "step": 83 + }, + { + "epoch": 1.6153846153846154, + "grad_norm": 0.44156306982040405, + "learning_rate": 5.224324151752575e-06, + "loss": 0.619, + "step": 84 + }, + { + "epoch": 1.6346153846153846, + "grad_norm": 0.4886167049407959, + "learning_rate": 5.112190321479026e-06, + "loss": 0.6353, + "step": 85 + }, + { + "epoch": 1.6538461538461537, + "grad_norm": 0.4457215666770935, + "learning_rate": 5e-06, + "loss": 0.6309, + "step": 86 + }, + { + "epoch": 1.6730769230769231, + "grad_norm": 0.37990936636924744, + "learning_rate": 4.887809678520976e-06, + "loss": 0.6306, + "step": 87 + }, + { + "epoch": 1.6923076923076923, + "grad_norm": 0.48935168981552124, + "learning_rate": 4.775675848247427e-06, + "loss": 0.6247, + "step": 88 + }, + { + "epoch": 1.7115384615384617, + "grad_norm": 0.43845734000205994, + "learning_rate": 4.663654971939802e-06, + "loss": 0.6243, + "step": 89 + }, + { + "epoch": 1.7307692307692308, + "grad_norm": 0.38639092445373535, + "learning_rate": 4.551803455482833e-06, + "loss": 0.6181, + "step": 90 + }, + { + "epoch": 1.75, + "grad_norm": 0.4700919985771179, + "learning_rate": 4.4401776194834615e-06, + "loss": 0.6434, + "step": 91 + }, + { + "epoch": 1.7692307692307692, + "grad_norm": 0.4569476544857025, + "learning_rate": 4.3288336709117246e-06, + "loss": 0.6248, + "step": 92 + }, + { + "epoch": 1.7884615384615383, + "grad_norm": 0.42245760560035706, + "learning_rate": 4.217827674798845e-06, + "loss": 0.6305, + "step": 93 + }, + { + "epoch": 1.8076923076923077, + "grad_norm": 0.48794662952423096, + "learning_rate": 4.107215526006818e-06, + "loss": 0.6209, + "step": 94 + }, + { + "epoch": 1.8269230769230769, + "grad_norm": 0.5091656446456909, + "learning_rate": 3.997052921083637e-06, + "loss": 0.6148, + "step": 95 + }, + { + "epoch": 1.8461538461538463, + "grad_norm": 0.46186864376068115, + "learning_rate": 3.887395330218429e-06, + "loss": 0.6293, + "step": 96 + }, + { + "epoch": 1.8653846153846154, + "grad_norm": 0.409128338098526, + "learning_rate": 3.778297969310529e-06, + "loss": 0.6114, + "step": 97 + }, + { + "epoch": 1.8846153846153846, + "grad_norm": 0.44377630949020386, + "learning_rate": 3.669815772166625e-06, + "loss": 0.6167, + "step": 98 + }, + { + "epoch": 1.9038461538461537, + "grad_norm": 0.6437395811080933, + "learning_rate": 3.562003362839914e-06, + "loss": 0.6031, + "step": 99 + }, + { + "epoch": 1.9230769230769231, + "grad_norm": 0.44504550099372864, + "learning_rate": 3.4549150281252635e-06, + "loss": 0.6085, + "step": 100 + }, + { + "epoch": 1.9423076923076923, + "grad_norm": 0.4889739453792572, + "learning_rate": 3.3486046902241663e-06, + "loss": 0.6071, + "step": 101 + }, + { + "epoch": 1.9615384615384617, + "grad_norm": 0.6323836445808411, + "learning_rate": 3.2431258795932863e-06, + "loss": 0.6268, + "step": 102 + }, + { + "epoch": 1.9807692307692308, + "grad_norm": 0.47047120332717896, + "learning_rate": 3.1385317079902743e-06, + "loss": 0.6142, + "step": 103 + }, + { + "epoch": 2.0, + "grad_norm": 0.385359525680542, + "learning_rate": 3.0348748417303826e-06, + "loss": 0.6343, + "step": 104 + }, + { + "epoch": 2.019230769230769, + "grad_norm": 0.4017738699913025, + "learning_rate": 2.932207475167398e-06, + "loss": 0.6071, + "step": 105 + }, + { + "epoch": 2.0384615384615383, + "grad_norm": 0.4930027723312378, + "learning_rate": 2.83058130441221e-06, + "loss": 0.5926, + "step": 106 + }, + { + "epoch": 2.0576923076923075, + "grad_norm": 0.41167354583740234, + "learning_rate": 2.7300475013022666e-06, + "loss": 0.6021, + "step": 107 + }, + { + "epoch": 2.076923076923077, + "grad_norm": 0.43824106454849243, + "learning_rate": 2.6306566876350072e-06, + "loss": 0.5946, + "step": 108 + }, + { + "epoch": 2.0961538461538463, + "grad_norm": 0.42565321922302246, + "learning_rate": 2.532458909678266e-06, + "loss": 0.5968, + "step": 109 + }, + { + "epoch": 2.1153846153846154, + "grad_norm": 0.4275932013988495, + "learning_rate": 2.43550361297047e-06, + "loss": 0.586, + "step": 110 + }, + { + "epoch": 2.1346153846153846, + "grad_norm": 0.40257298946380615, + "learning_rate": 2.339839617423318e-06, + "loss": 0.588, + "step": 111 + }, + { + "epoch": 2.1538461538461537, + "grad_norm": 0.3709084987640381, + "learning_rate": 2.245515092739488e-06, + "loss": 0.5875, + "step": 112 + }, + { + "epoch": 2.173076923076923, + "grad_norm": 0.34968435764312744, + "learning_rate": 2.1525775341577404e-06, + "loss": 0.5922, + "step": 113 + }, + { + "epoch": 2.1923076923076925, + "grad_norm": 0.3987502157688141, + "learning_rate": 2.061073738537635e-06, + "loss": 0.6045, + "step": 114 + }, + { + "epoch": 2.2115384615384617, + "grad_norm": 0.3902794122695923, + "learning_rate": 1.971049780795901e-06, + "loss": 0.5879, + "step": 115 + }, + { + "epoch": 2.230769230769231, + "grad_norm": 0.39212530851364136, + "learning_rate": 1.8825509907063328e-06, + "loss": 0.5974, + "step": 116 + }, + { + "epoch": 2.25, + "grad_norm": 0.3752593994140625, + "learning_rate": 1.7956219300748796e-06, + "loss": 0.5905, + "step": 117 + }, + { + "epoch": 2.269230769230769, + "grad_norm": 0.3571646213531494, + "learning_rate": 1.7103063703014372e-06, + "loss": 0.5813, + "step": 118 + }, + { + "epoch": 2.2884615384615383, + "grad_norm": 0.3796848952770233, + "learning_rate": 1.6266472703396286e-06, + "loss": 0.5798, + "step": 119 + }, + { + "epoch": 2.3076923076923075, + "grad_norm": 0.38161250948905945, + "learning_rate": 1.544686755065677e-06, + "loss": 0.5973, + "step": 120 + }, + { + "epoch": 2.326923076923077, + "grad_norm": 0.3628106415271759, + "learning_rate": 1.4644660940672628e-06, + "loss": 0.5915, + "step": 121 + }, + { + "epoch": 2.3461538461538463, + "grad_norm": 0.3747085928916931, + "learning_rate": 1.3860256808630429e-06, + "loss": 0.6004, + "step": 122 + }, + { + "epoch": 2.3653846153846154, + "grad_norm": 0.3763367831707001, + "learning_rate": 1.3094050125632973e-06, + "loss": 0.6029, + "step": 123 + }, + { + "epoch": 2.3846153846153846, + "grad_norm": 0.32238879799842834, + "learning_rate": 1.234642669981946e-06, + "loss": 0.6025, + "step": 124 + }, + { + "epoch": 2.4038461538461537, + "grad_norm": 0.37101826071739197, + "learning_rate": 1.1617762982099446e-06, + "loss": 0.5737, + "step": 125 + }, + { + "epoch": 2.423076923076923, + "grad_norm": 0.34124448895454407, + "learning_rate": 1.0908425876598512e-06, + "loss": 0.5701, + "step": 126 + }, + { + "epoch": 2.4423076923076925, + "grad_norm": 0.34349343180656433, + "learning_rate": 1.0218772555910955e-06, + "loss": 0.604, + "step": 127 + }, + { + "epoch": 2.4615384615384617, + "grad_norm": 0.36411768198013306, + "learning_rate": 9.549150281252633e-07, + "loss": 0.6136, + "step": 128 + }, + { + "epoch": 2.480769230769231, + "grad_norm": 0.3538264036178589, + "learning_rate": 8.899896227604509e-07, + "loss": 0.5856, + "step": 129 + }, + { + "epoch": 2.5, + "grad_norm": 0.35449934005737305, + "learning_rate": 8.271337313934869e-07, + "loss": 0.5907, + "step": 130 + }, + { + "epoch": 2.519230769230769, + "grad_norm": 0.31669095158576965, + "learning_rate": 7.663790038585794e-07, + "loss": 0.5904, + "step": 131 + }, + { + "epoch": 2.5384615384615383, + "grad_norm": 0.3434077501296997, + "learning_rate": 7.077560319906696e-07, + "loss": 0.5775, + "step": 132 + }, + { + "epoch": 2.5576923076923075, + "grad_norm": 0.3626374900341034, + "learning_rate": 6.512943342215234e-07, + "loss": 0.5878, + "step": 133 + }, + { + "epoch": 2.5769230769230766, + "grad_norm": 0.3235149681568146, + "learning_rate": 5.9702234071631e-07, + "loss": 0.601, + "step": 134 + }, + { + "epoch": 2.5961538461538463, + "grad_norm": 0.3342594802379608, + "learning_rate": 5.449673790581611e-07, + "loss": 0.5926, + "step": 135 + }, + { + "epoch": 2.6153846153846154, + "grad_norm": 0.3404471278190613, + "learning_rate": 4.951556604879049e-07, + "loss": 0.5772, + "step": 136 + }, + { + "epoch": 2.6346153846153846, + "grad_norm": 0.3687044680118561, + "learning_rate": 4.4761226670592074e-07, + "loss": 0.5895, + "step": 137 + }, + { + "epoch": 2.6538461538461537, + "grad_norm": 0.3606056571006775, + "learning_rate": 4.0236113724274716e-07, + "loss": 0.5984, + "step": 138 + }, + { + "epoch": 2.6730769230769234, + "grad_norm": 0.3252229392528534, + "learning_rate": 3.5942505740480583e-07, + "loss": 0.5967, + "step": 139 + }, + { + "epoch": 2.6923076923076925, + "grad_norm": 0.3195320963859558, + "learning_rate": 3.18825646801314e-07, + "loss": 0.6131, + "step": 140 + }, + { + "epoch": 2.7115384615384617, + "grad_norm": 0.33670124411582947, + "learning_rate": 2.8058334845816214e-07, + "loss": 0.5952, + "step": 141 + }, + { + "epoch": 2.730769230769231, + "grad_norm": 0.3292597532272339, + "learning_rate": 2.447174185242324e-07, + "loss": 0.6009, + "step": 142 + }, + { + "epoch": 2.75, + "grad_norm": 0.31205758452415466, + "learning_rate": 2.1124591657534776e-07, + "loss": 0.6009, + "step": 143 + }, + { + "epoch": 2.769230769230769, + "grad_norm": 0.3304506540298462, + "learning_rate": 1.801856965207338e-07, + "loss": 0.5979, + "step": 144 + }, + { + "epoch": 2.7884615384615383, + "grad_norm": 0.33979734778404236, + "learning_rate": 1.5155239811656562e-07, + "loss": 0.5747, + "step": 145 + }, + { + "epoch": 2.8076923076923075, + "grad_norm": 0.37355899810791016, + "learning_rate": 1.253604390908819e-07, + "loss": 0.5994, + "step": 146 + }, + { + "epoch": 2.8269230769230766, + "grad_norm": 0.3773685693740845, + "learning_rate": 1.0162300788382263e-07, + "loss": 0.5913, + "step": 147 + }, + { + "epoch": 2.8461538461538463, + "grad_norm": 0.31100109219551086, + "learning_rate": 8.035205700685167e-08, + "loss": 0.5829, + "step": 148 + }, + { + "epoch": 2.8653846153846154, + "grad_norm": 0.31232011318206787, + "learning_rate": 6.15582970243117e-08, + "loss": 0.5927, + "step": 149 + }, + { + "epoch": 2.8846153846153846, + "grad_norm": 0.3333931267261505, + "learning_rate": 4.52511911603265e-08, + "loss": 0.5781, + "step": 150 + }, + { + "epoch": 2.9038461538461537, + "grad_norm": 0.31353145837783813, + "learning_rate": 3.143895053378698e-08, + "loss": 0.6044, + "step": 151 + }, + { + "epoch": 2.9230769230769234, + "grad_norm": 0.33146995306015015, + "learning_rate": 2.012853002380466e-08, + "loss": 0.5993, + "step": 152 + }, + { + "epoch": 2.9423076923076925, + "grad_norm": 0.31752604246139526, + "learning_rate": 1.132562476771959e-08, + "loss": 0.5933, + "step": 153 + }, + { + "epoch": 2.9615384615384617, + "grad_norm": 0.32748833298683167, + "learning_rate": 5.034667293427053e-09, + "loss": 0.5813, + "step": 154 + }, + { + "epoch": 2.980769230769231, + "grad_norm": 0.3221939206123352, + "learning_rate": 1.2588252874673469e-09, + "loss": 0.5851, + "step": 155 + }, + { + "epoch": 3.0, + "grad_norm": 0.34672605991363525, + "learning_rate": 0.0, + "loss": 0.5678, + "step": 156 + }, + { + "epoch": 3.0, + "step": 156, + "total_flos": 2.3644419613786112e+17, + "train_loss": 0.6642100642888974, + "train_runtime": 3868.2988, + "train_samples_per_second": 3.859, + "train_steps_per_second": 0.04 + } + ], + "logging_steps": 1, + "max_steps": 156, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 2.3644419613786112e+17, + "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..30781af --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaada0908d64496e7827ef7f12c442b82c59478829e950d7a1ebfc2941480f00 +size 7608 diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833