commit 40ad0e13b73b7d1eec82e0c337435692e1538741 Author: ModelHub XC Date: Sat Sep 19 19:06:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mlfoundations-dev/c1_math_0d_4s_1k Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52424d7 --- /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 + +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +training_args.bin 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-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00003-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..9ce40aa --- /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: c1_math_0d_4s_1k + results: [] +--- + + + +# c1_math_0d_4s_1k + +This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/c1_math_0d_4s_1k 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: 2e-05 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 16 +- gradient_accumulation_steps: 6 +- total_train_batch_size: 96 +- total_eval_batch_size: 128 +- optimizer: Use OptimizerNames.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: 7.0 + +### Training results + + + +### Framework versions + +- Transformers 4.46.1 +- Pytorch 2.6.0a0+ecf3bae40a.nv25.01 +- Datasets 3.5.0 +- 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..f25f0b2 --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 6.666666666666667, + "total_flos": 2.3990446016220365e+17, + "train_loss": 0.4939488410949707, + "train_runtime": 2825.0166, + "train_samples_per_second": 2.478, + "train_steps_per_second": 0.025 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a916f0b --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 152064 +} 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..51de204 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f1317f06f0a15ce06a18e351f1e1267a8a4ddec9f5a484f25cb29f5c4991a4c +size 4877660776 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..9eb9ac6 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:805383c8ba1a7471e6181570dd5de7de24976db65be3c771aad1ac37a2cb1a0b +size 4932751008 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..ddcf072 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a07c4ee21ccbd74e6875ee6b8f1fc99464c2bf84c99766de1f9a4b6982731e0 +size 4330865200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..9d36d87 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c50cd4f38d985c2e4a494e6791cf5774bb9f923ec0ba8e080d0c1610bc9396a +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/runs/Apr26_23-29-38_jpbot-001-15.jupiter.internal/events.out.tfevents.1745703028.jpbot-001-15.jupiter.internal.1537050.0 b/runs/Apr26_23-29-38_jpbot-001-15.jupiter.internal/events.out.tfevents.1745703028.jpbot-001-15.jupiter.internal.1537050.0 new file mode 100644 index 0000000..8e8a327 --- /dev/null +++ b/runs/Apr26_23-29-38_jpbot-001-15.jupiter.internal/events.out.tfevents.1745703028.jpbot-001-15.jupiter.internal.1537050.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16727f413c55204babc8220a5cc343fc33427d30aa1cb6b41d345e43c48fe906 +size 20352 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/start_end.json b/start_end.json new file mode 100644 index 0000000..ca7a8c6 --- /dev/null +++ b/start_end.json @@ -0,0 +1 @@ +{"start_time": "2025-04-26 23:29:38", "end_time": "2025-04-27 00:17:39"} \ No newline at end of file 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..f25f0b2 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 6.666666666666667, + "total_flos": 2.3990446016220365e+17, + "train_loss": 0.4939488410949707, + "train_runtime": 2825.0166, + "train_samples_per_second": 2.478, + "train_steps_per_second": 0.025 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..9750bcb --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,71 @@ +{"current_steps": 1, "total_steps": 70, "loss": 0.8419, "lr": 2.8571428571428573e-06, "epoch": 0.09523809523809523, "percentage": 1.43, "elapsed_time": "0:00:46", "remaining_time": "0:53:47"} +{"current_steps": 2, "total_steps": 70, "loss": 0.8347, "lr": 5.7142857142857145e-06, "epoch": 0.19047619047619047, "percentage": 2.86, "elapsed_time": "0:01:24", "remaining_time": "0:47:53"} +{"current_steps": 3, "total_steps": 70, "loss": 0.7892, "lr": 8.571428571428571e-06, "epoch": 0.2857142857142857, "percentage": 4.29, "elapsed_time": "0:02:02", "remaining_time": "0:45:34"} +{"current_steps": 4, "total_steps": 70, "loss": 0.7191, "lr": 1.1428571428571429e-05, "epoch": 0.38095238095238093, "percentage": 5.71, "elapsed_time": "0:02:37", "remaining_time": "0:43:24"} +{"current_steps": 5, "total_steps": 70, "loss": 0.7275, "lr": 1.4285714285714287e-05, "epoch": 0.47619047619047616, "percentage": 7.14, "elapsed_time": "0:03:14", "remaining_time": "0:42:02"} +{"current_steps": 6, "total_steps": 70, "loss": 0.7245, "lr": 1.7142857142857142e-05, "epoch": 0.5714285714285714, "percentage": 8.57, "elapsed_time": "0:03:51", "remaining_time": "0:41:05"} +{"current_steps": 7, "total_steps": 70, "loss": 0.6869, "lr": 2e-05, "epoch": 0.6666666666666666, "percentage": 10.0, "elapsed_time": "0:04:28", "remaining_time": "0:40:17"} +{"current_steps": 8, "total_steps": 70, "loss": 0.6701, "lr": 1.9987569212189224e-05, "epoch": 0.7619047619047619, "percentage": 11.43, "elapsed_time": "0:05:07", "remaining_time": "0:39:43"} +{"current_steps": 9, "total_steps": 70, "loss": 0.6473, "lr": 1.9950307753654016e-05, "epoch": 0.8571428571428571, "percentage": 12.86, "elapsed_time": "0:05:45", "remaining_time": "0:39:02"} +{"current_steps": 10, "total_steps": 70, "loss": 0.6124, "lr": 1.9888308262251286e-05, "epoch": 0.9523809523809523, "percentage": 14.29, "elapsed_time": "0:06:23", "remaining_time": "0:38:22"} +{"current_steps": 11, "total_steps": 70, "loss": 0.9323, "lr": 1.9801724878485438e-05, "epoch": 1.0476190476190477, "percentage": 15.71, "elapsed_time": "0:07:22", "remaining_time": "0:39:33"} +{"current_steps": 12, "total_steps": 70, "loss": 0.5877, "lr": 1.969077286229078e-05, "epoch": 1.1428571428571428, "percentage": 17.14, "elapsed_time": "0:08:01", "remaining_time": "0:38:47"} +{"current_steps": 13, "total_steps": 70, "loss": 0.5601, "lr": 1.955572805786141e-05, "epoch": 1.2380952380952381, "percentage": 18.57, "elapsed_time": "0:08:37", "remaining_time": "0:37:49"} +{"current_steps": 14, "total_steps": 70, "loss": 0.5828, "lr": 1.9396926207859085e-05, "epoch": 1.3333333333333333, "percentage": 20.0, "elapsed_time": "0:09:15", "remaining_time": "0:37:03"} +{"current_steps": 15, "total_steps": 70, "loss": 0.5557, "lr": 1.921476211870408e-05, "epoch": 1.4285714285714286, "percentage": 21.43, "elapsed_time": "0:09:55", "remaining_time": "0:36:24"} +{"current_steps": 16, "total_steps": 70, "loss": 0.5344, "lr": 1.900968867902419e-05, "epoch": 1.5238095238095237, "percentage": 22.86, "elapsed_time": "0:10:31", "remaining_time": "0:35:30"} +{"current_steps": 17, "total_steps": 70, "loss": 0.5558, "lr": 1.8782215733702286e-05, "epoch": 1.619047619047619, "percentage": 24.29, "elapsed_time": "0:11:08", "remaining_time": "0:34:43"} +{"current_steps": 18, "total_steps": 70, "loss": 0.5179, "lr": 1.8532908816321557e-05, "epoch": 1.7142857142857144, "percentage": 25.71, "elapsed_time": "0:11:45", "remaining_time": "0:33:57"} +{"current_steps": 19, "total_steps": 70, "loss": 0.529, "lr": 1.826238774315995e-05, "epoch": 1.8095238095238095, "percentage": 27.14, "elapsed_time": "0:12:24", "remaining_time": "0:33:18"} +{"current_steps": 20, "total_steps": 70, "loss": 0.528, "lr": 1.7971325072229227e-05, "epoch": 1.9047619047619047, "percentage": 28.57, "elapsed_time": "0:13:00", "remaining_time": "0:32:32"} +{"current_steps": 21, "total_steps": 70, "loss": 0.7894, "lr": 1.766044443118978e-05, "epoch": 2.0, "percentage": 30.0, "elapsed_time": "0:13:38", "remaining_time": "0:31:50"} +{"current_steps": 22, "total_steps": 70, "loss": 0.4923, "lr": 1.7330518718298263e-05, "epoch": 2.0952380952380953, "percentage": 31.43, "elapsed_time": "0:14:39", "remaining_time": "0:31:59"} +{"current_steps": 23, "total_steps": 70, "loss": 0.4884, "lr": 1.698236818086073e-05, "epoch": 2.1904761904761907, "percentage": 32.86, "elapsed_time": "0:15:16", "remaining_time": "0:31:13"} +{"current_steps": 24, "total_steps": 70, "loss": 0.4665, "lr": 1.6616858375968596e-05, "epoch": 2.2857142857142856, "percentage": 34.29, "elapsed_time": "0:15:56", "remaining_time": "0:30:33"} +{"current_steps": 25, "total_steps": 70, "loss": 0.4782, "lr": 1.6234898018587336e-05, "epoch": 2.380952380952381, "percentage": 35.71, "elapsed_time": "0:16:33", "remaining_time": "0:29:47"} +{"current_steps": 26, "total_steps": 70, "loss": 0.4858, "lr": 1.5837436722347902e-05, "epoch": 2.4761904761904763, "percentage": 37.14, "elapsed_time": "0:17:11", "remaining_time": "0:29:05"} +{"current_steps": 27, "total_steps": 70, "loss": 0.4796, "lr": 1.5425462638657597e-05, "epoch": 2.571428571428571, "percentage": 38.57, "elapsed_time": "0:17:48", "remaining_time": "0:28:21"} +{"current_steps": 28, "total_steps": 70, "loss": 0.4516, "lr": 1.5000000000000002e-05, "epoch": 2.6666666666666665, "percentage": 40.0, "elapsed_time": "0:18:25", "remaining_time": "0:27:38"} +{"current_steps": 29, "total_steps": 70, "loss": 0.4749, "lr": 1.4562106573531632e-05, "epoch": 2.761904761904762, "percentage": 41.43, "elapsed_time": "0:19:00", "remaining_time": "0:26:52"} +{"current_steps": 30, "total_steps": 70, "loss": 0.467, "lr": 1.4112871031306118e-05, "epoch": 2.857142857142857, "percentage": 42.86, "elapsed_time": "0:19:38", "remaining_time": "0:26:10"} +{"current_steps": 31, "total_steps": 70, "loss": 0.4706, "lr": 1.3653410243663953e-05, "epoch": 2.9523809523809526, "percentage": 44.29, "elapsed_time": "0:20:16", "remaining_time": "0:25:30"} +{"current_steps": 32, "total_steps": 70, "loss": 0.6569, "lr": 1.3184866502516846e-05, "epoch": 3.0476190476190474, "percentage": 45.71, "elapsed_time": "0:21:13", "remaining_time": "0:25:12"} +{"current_steps": 33, "total_steps": 70, "loss": 0.4292, "lr": 1.2708404681430054e-05, "epoch": 3.142857142857143, "percentage": 47.14, "elapsed_time": "0:21:53", "remaining_time": "0:24:32"} +{"current_steps": 34, "total_steps": 70, "loss": 0.4378, "lr": 1.2225209339563144e-05, "epoch": 3.238095238095238, "percentage": 48.57, "elapsed_time": "0:22:30", "remaining_time": "0:23:49"} +{"current_steps": 35, "total_steps": 70, "loss": 0.4262, "lr": 1.1736481776669307e-05, "epoch": 3.3333333333333335, "percentage": 50.0, "elapsed_time": "0:23:07", "remaining_time": "0:23:07"} +{"current_steps": 36, "total_steps": 70, "loss": 0.4253, "lr": 1.1243437046474854e-05, "epoch": 3.4285714285714284, "percentage": 51.43, "elapsed_time": "0:23:44", "remaining_time": "0:22:25"} +{"current_steps": 37, "total_steps": 70, "loss": 0.4342, "lr": 1.0747300935864245e-05, "epoch": 3.5238095238095237, "percentage": 52.86, "elapsed_time": "0:24:22", "remaining_time": "0:21:44"} +{"current_steps": 38, "total_steps": 70, "loss": 0.4293, "lr": 1.0249306917380731e-05, "epoch": 3.619047619047619, "percentage": 54.29, "elapsed_time": "0:25:00", "remaining_time": "0:21:03"} +{"current_steps": 39, "total_steps": 70, "loss": 0.416, "lr": 9.750693082619274e-06, "epoch": 3.7142857142857144, "percentage": 55.71, "elapsed_time": "0:25:36", "remaining_time": "0:20:21"} +{"current_steps": 40, "total_steps": 70, "loss": 0.423, "lr": 9.252699064135759e-06, "epoch": 3.8095238095238093, "percentage": 57.14, "elapsed_time": "0:26:15", "remaining_time": "0:19:41"} +{"current_steps": 41, "total_steps": 70, "loss": 0.4052, "lr": 8.756562953525151e-06, "epoch": 3.9047619047619047, "percentage": 58.57, "elapsed_time": "0:26:53", "remaining_time": "0:19:01"} +{"current_steps": 42, "total_steps": 70, "loss": 0.6213, "lr": 8.263518223330698e-06, "epoch": 4.0, "percentage": 60.0, "elapsed_time": "0:27:30", "remaining_time": "0:18:20"} +{"current_steps": 43, "total_steps": 70, "loss": 0.3984, "lr": 7.774790660436857e-06, "epoch": 4.095238095238095, "percentage": 61.43, "elapsed_time": "0:28:27", "remaining_time": "0:17:52"} +{"current_steps": 44, "total_steps": 70, "loss": 0.3867, "lr": 7.291595318569951e-06, "epoch": 4.190476190476191, "percentage": 62.86, "elapsed_time": "0:29:04", "remaining_time": "0:17:10"} +{"current_steps": 45, "total_steps": 70, "loss": 0.3847, "lr": 6.815133497483157e-06, "epoch": 4.285714285714286, "percentage": 64.29, "elapsed_time": "0:29:45", "remaining_time": "0:16:31"} +{"current_steps": 46, "total_steps": 70, "loss": 0.381, "lr": 6.34658975633605e-06, "epoch": 4.380952380952381, "percentage": 65.71, "elapsed_time": "0:30:24", "remaining_time": "0:15:52"} +{"current_steps": 47, "total_steps": 70, "loss": 0.3844, "lr": 5.887128968693887e-06, "epoch": 4.476190476190476, "percentage": 67.14, "elapsed_time": "0:31:02", "remaining_time": "0:15:11"} +{"current_steps": 48, "total_steps": 70, "loss": 0.3874, "lr": 5.43789342646837e-06, "epoch": 4.571428571428571, "percentage": 68.57, "elapsed_time": "0:31:36", "remaining_time": "0:14:29"} +{"current_steps": 49, "total_steps": 70, "loss": 0.3778, "lr": 5.000000000000003e-06, "epoch": 4.666666666666667, "percentage": 70.0, "elapsed_time": "0:32:13", "remaining_time": "0:13:48"} +{"current_steps": 50, "total_steps": 70, "loss": 0.3994, "lr": 4.5745373613424075e-06, "epoch": 4.761904761904762, "percentage": 71.43, "elapsed_time": "0:32:49", "remaining_time": "0:13:07"} +{"current_steps": 51, "total_steps": 70, "loss": 0.3827, "lr": 4.162563277652104e-06, "epoch": 4.857142857142857, "percentage": 72.86, "elapsed_time": "0:33:25", "remaining_time": "0:12:26"} +{"current_steps": 52, "total_steps": 70, "loss": 0.3892, "lr": 3.7651019814126656e-06, "epoch": 4.9523809523809526, "percentage": 74.29, "elapsed_time": "0:34:03", "remaining_time": "0:11:47"} +{"current_steps": 53, "total_steps": 70, "loss": 0.5468, "lr": 3.3831416240314085e-06, "epoch": 5.0476190476190474, "percentage": 75.71, "elapsed_time": "0:34:56", "remaining_time": "0:11:12"} +{"current_steps": 54, "total_steps": 70, "loss": 0.3634, "lr": 3.017631819139273e-06, "epoch": 5.142857142857143, "percentage": 77.14, "elapsed_time": "0:35:33", "remaining_time": "0:10:32"} +{"current_steps": 55, "total_steps": 70, "loss": 0.3698, "lr": 2.669481281701739e-06, "epoch": 5.238095238095238, "percentage": 78.57, "elapsed_time": "0:36:11", "remaining_time": "0:09:52"} +{"current_steps": 56, "total_steps": 70, "loss": 0.3714, "lr": 2.339555568810221e-06, "epoch": 5.333333333333333, "percentage": 80.0, "elapsed_time": "0:36:48", "remaining_time": "0:09:12"} +{"current_steps": 57, "total_steps": 70, "loss": 0.3626, "lr": 2.0286749277707783e-06, "epoch": 5.428571428571429, "percentage": 81.43, "elapsed_time": "0:37:26", "remaining_time": "0:08:32"} +{"current_steps": 58, "total_steps": 70, "loss": 0.3656, "lr": 1.7376122568400533e-06, "epoch": 5.523809523809524, "percentage": 82.86, "elapsed_time": "0:38:04", "remaining_time": "0:07:52"} +{"current_steps": 59, "total_steps": 70, "loss": 0.3574, "lr": 1.467091183678444e-06, "epoch": 5.619047619047619, "percentage": 84.29, "elapsed_time": "0:38:44", "remaining_time": "0:07:13"} +{"current_steps": 60, "total_steps": 70, "loss": 0.365, "lr": 1.2177842662977136e-06, "epoch": 5.714285714285714, "percentage": 85.71, "elapsed_time": "0:39:20", "remaining_time": "0:06:33"} +{"current_steps": 61, "total_steps": 70, "loss": 0.3644, "lr": 9.903113209758098e-07, "epoch": 5.809523809523809, "percentage": 87.14, "elapsed_time": "0:39:56", "remaining_time": "0:05:53"} +{"current_steps": 62, "total_steps": 70, "loss": 0.3682, "lr": 7.852378812959227e-07, "epoch": 5.904761904761905, "percentage": 88.57, "elapsed_time": "0:40:33", "remaining_time": "0:05:13"} +{"current_steps": 63, "total_steps": 70, "loss": 0.5551, "lr": 6.030737921409169e-07, "epoch": 6.0, "percentage": 90.0, "elapsed_time": "0:41:10", "remaining_time": "0:04:34"} +{"current_steps": 64, "total_steps": 70, "loss": 0.3659, "lr": 4.4427194213859216e-07, "epoch": 6.095238095238095, "percentage": 91.43, "elapsed_time": "0:42:12", "remaining_time": "0:03:57"} +{"current_steps": 65, "total_steps": 70, "loss": 0.3638, "lr": 3.0922713770922155e-07, "epoch": 6.190476190476191, "percentage": 92.86, "elapsed_time": "0:42:49", "remaining_time": "0:03:17"} +{"current_steps": 66, "total_steps": 70, "loss": 0.3584, "lr": 1.9827512151456175e-07, "epoch": 6.285714285714286, "percentage": 94.29, "elapsed_time": "0:43:27", "remaining_time": "0:02:38"} +{"current_steps": 67, "total_steps": 70, "loss": 0.3661, "lr": 1.1169173774871478e-07, "epoch": 6.380952380952381, "percentage": 95.71, "elapsed_time": "0:44:04", "remaining_time": "0:01:58"} +{"current_steps": 68, "total_steps": 70, "loss": 0.3676, "lr": 4.9692246345985905e-08, "epoch": 6.476190476190476, "percentage": 97.14, "elapsed_time": "0:44:42", "remaining_time": "0:01:18"} +{"current_steps": 69, "total_steps": 70, "loss": 0.3518, "lr": 1.2430787810776556e-08, "epoch": 6.571428571428571, "percentage": 98.57, "elapsed_time": "0:45:21", "remaining_time": "0:00:39"} +{"current_steps": 70, "total_steps": 70, "loss": 0.3555, "lr": 0.0, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:45:59", "remaining_time": "0:00:00"} +{"current_steps": 70, "total_steps": 70, "epoch": 6.666666666666667, "percentage": 100.0, "elapsed_time": "0:47:03", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..8c4018f --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,532 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 6.666666666666667, + "eval_steps": 500, + "global_step": 70, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.09523809523809523, + "grad_norm": 6.605348131730995, + "learning_rate": 2.8571428571428573e-06, + "loss": 0.8419, + "step": 1 + }, + { + "epoch": 0.19047619047619047, + "grad_norm": 6.421236878123063, + "learning_rate": 5.7142857142857145e-06, + "loss": 0.8347, + "step": 2 + }, + { + "epoch": 0.2857142857142857, + "grad_norm": 5.6301912031095, + "learning_rate": 8.571428571428571e-06, + "loss": 0.7892, + "step": 3 + }, + { + "epoch": 0.38095238095238093, + "grad_norm": 2.3481103388632967, + "learning_rate": 1.1428571428571429e-05, + "loss": 0.7191, + "step": 4 + }, + { + "epoch": 0.47619047619047616, + "grad_norm": 3.77462144106806, + "learning_rate": 1.4285714285714287e-05, + "loss": 0.7275, + "step": 5 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 4.145002917098403, + "learning_rate": 1.7142857142857142e-05, + "loss": 0.7245, + "step": 6 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 4.160357161281431, + "learning_rate": 2e-05, + "loss": 0.6869, + "step": 7 + }, + { + "epoch": 0.7619047619047619, + "grad_norm": 2.530895080447052, + "learning_rate": 1.9987569212189224e-05, + "loss": 0.6701, + "step": 8 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 2.2651868042761207, + "learning_rate": 1.9950307753654016e-05, + "loss": 0.6473, + "step": 9 + }, + { + "epoch": 0.9523809523809523, + "grad_norm": 2.017603532790786, + "learning_rate": 1.9888308262251286e-05, + "loss": 0.6124, + "step": 10 + }, + { + "epoch": 1.0476190476190477, + "grad_norm": 2.142230908069242, + "learning_rate": 1.9801724878485438e-05, + "loss": 0.9323, + "step": 11 + }, + { + "epoch": 1.1428571428571428, + "grad_norm": 1.192411410964399, + "learning_rate": 1.969077286229078e-05, + "loss": 0.5877, + "step": 12 + }, + { + "epoch": 1.2380952380952381, + "grad_norm": 1.1055427383462693, + "learning_rate": 1.955572805786141e-05, + "loss": 0.5601, + "step": 13 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 1.0654694223469574, + "learning_rate": 1.9396926207859085e-05, + "loss": 0.5828, + "step": 14 + }, + { + "epoch": 1.4285714285714286, + "grad_norm": 0.9654479013607004, + "learning_rate": 1.921476211870408e-05, + "loss": 0.5557, + "step": 15 + }, + { + "epoch": 1.5238095238095237, + "grad_norm": 0.8914056609525524, + "learning_rate": 1.900968867902419e-05, + "loss": 0.5344, + "step": 16 + }, + { + "epoch": 1.619047619047619, + "grad_norm": 0.9774447718066034, + "learning_rate": 1.8782215733702286e-05, + "loss": 0.5558, + "step": 17 + }, + { + "epoch": 1.7142857142857144, + "grad_norm": 0.7790629886541486, + "learning_rate": 1.8532908816321557e-05, + "loss": 0.5179, + "step": 18 + }, + { + "epoch": 1.8095238095238095, + "grad_norm": 0.8202964518997443, + "learning_rate": 1.826238774315995e-05, + "loss": 0.529, + "step": 19 + }, + { + "epoch": 1.9047619047619047, + "grad_norm": 0.8155377516615383, + "learning_rate": 1.7971325072229227e-05, + "loss": 0.528, + "step": 20 + }, + { + "epoch": 2.0, + "grad_norm": 1.0671953476376677, + "learning_rate": 1.766044443118978e-05, + "loss": 0.7894, + "step": 21 + }, + { + "epoch": 2.0952380952380953, + "grad_norm": 0.5021207833915019, + "learning_rate": 1.7330518718298263e-05, + "loss": 0.4923, + "step": 22 + }, + { + "epoch": 2.1904761904761907, + "grad_norm": 0.6991883919562059, + "learning_rate": 1.698236818086073e-05, + "loss": 0.4884, + "step": 23 + }, + { + "epoch": 2.2857142857142856, + "grad_norm": 0.5720037808635232, + "learning_rate": 1.6616858375968596e-05, + "loss": 0.4665, + "step": 24 + }, + { + "epoch": 2.380952380952381, + "grad_norm": 0.5458417578805382, + "learning_rate": 1.6234898018587336e-05, + "loss": 0.4782, + "step": 25 + }, + { + "epoch": 2.4761904761904763, + "grad_norm": 0.7366558111251066, + "learning_rate": 1.5837436722347902e-05, + "loss": 0.4858, + "step": 26 + }, + { + "epoch": 2.571428571428571, + "grad_norm": 0.5385737455534967, + "learning_rate": 1.5425462638657597e-05, + "loss": 0.4796, + "step": 27 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.47977596305770687, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.4516, + "step": 28 + }, + { + "epoch": 2.761904761904762, + "grad_norm": 0.5155484599482115, + "learning_rate": 1.4562106573531632e-05, + "loss": 0.4749, + "step": 29 + }, + { + "epoch": 2.857142857142857, + "grad_norm": 0.44464289664292356, + "learning_rate": 1.4112871031306118e-05, + "loss": 0.467, + "step": 30 + }, + { + "epoch": 2.9523809523809526, + "grad_norm": 0.5523193408133361, + "learning_rate": 1.3653410243663953e-05, + "loss": 0.4706, + "step": 31 + }, + { + "epoch": 3.0476190476190474, + "grad_norm": 0.5264144060681053, + "learning_rate": 1.3184866502516846e-05, + "loss": 0.6569, + "step": 32 + }, + { + "epoch": 3.142857142857143, + "grad_norm": 0.41126779074862735, + "learning_rate": 1.2708404681430054e-05, + "loss": 0.4292, + "step": 33 + }, + { + "epoch": 3.238095238095238, + "grad_norm": 0.4490298708496658, + "learning_rate": 1.2225209339563144e-05, + "loss": 0.4378, + "step": 34 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.3886114013945829, + "learning_rate": 1.1736481776669307e-05, + "loss": 0.4262, + "step": 35 + }, + { + "epoch": 3.4285714285714284, + "grad_norm": 0.38569867397130814, + "learning_rate": 1.1243437046474854e-05, + "loss": 0.4253, + "step": 36 + }, + { + "epoch": 3.5238095238095237, + "grad_norm": 0.32667953259390436, + "learning_rate": 1.0747300935864245e-05, + "loss": 0.4342, + "step": 37 + }, + { + "epoch": 3.619047619047619, + "grad_norm": 0.34387926938768176, + "learning_rate": 1.0249306917380731e-05, + "loss": 0.4293, + "step": 38 + }, + { + "epoch": 3.7142857142857144, + "grad_norm": 0.37550697839247893, + "learning_rate": 9.750693082619274e-06, + "loss": 0.416, + "step": 39 + }, + { + "epoch": 3.8095238095238093, + "grad_norm": 0.3339790028645127, + "learning_rate": 9.252699064135759e-06, + "loss": 0.423, + "step": 40 + }, + { + "epoch": 3.9047619047619047, + "grad_norm": 0.30613589011704845, + "learning_rate": 8.756562953525151e-06, + "loss": 0.4052, + "step": 41 + }, + { + "epoch": 4.0, + "grad_norm": 0.5533136576839677, + "learning_rate": 8.263518223330698e-06, + "loss": 0.6213, + "step": 42 + }, + { + "epoch": 4.095238095238095, + "grad_norm": 0.31266304108004894, + "learning_rate": 7.774790660436857e-06, + "loss": 0.3984, + "step": 43 + }, + { + "epoch": 4.190476190476191, + "grad_norm": 0.333588488447849, + "learning_rate": 7.291595318569951e-06, + "loss": 0.3867, + "step": 44 + }, + { + "epoch": 4.285714285714286, + "grad_norm": 0.3460065169199803, + "learning_rate": 6.815133497483157e-06, + "loss": 0.3847, + "step": 45 + }, + { + "epoch": 4.380952380952381, + "grad_norm": 0.30272468877509284, + "learning_rate": 6.34658975633605e-06, + "loss": 0.381, + "step": 46 + }, + { + "epoch": 4.476190476190476, + "grad_norm": 0.3046448293769283, + "learning_rate": 5.887128968693887e-06, + "loss": 0.3844, + "step": 47 + }, + { + "epoch": 4.571428571428571, + "grad_norm": 0.280969582851044, + "learning_rate": 5.43789342646837e-06, + "loss": 0.3874, + "step": 48 + }, + { + "epoch": 4.666666666666667, + "grad_norm": 0.2984012316645626, + "learning_rate": 5.000000000000003e-06, + "loss": 0.3778, + "step": 49 + }, + { + "epoch": 4.761904761904762, + "grad_norm": 0.30139527047552517, + "learning_rate": 4.5745373613424075e-06, + "loss": 0.3994, + "step": 50 + }, + { + "epoch": 4.857142857142857, + "grad_norm": 0.24709339303111982, + "learning_rate": 4.162563277652104e-06, + "loss": 0.3827, + "step": 51 + }, + { + "epoch": 4.9523809523809526, + "grad_norm": 0.25286199068075177, + "learning_rate": 3.7651019814126656e-06, + "loss": 0.3892, + "step": 52 + }, + { + "epoch": 5.0476190476190474, + "grad_norm": 0.3897706495957114, + "learning_rate": 3.3831416240314085e-06, + "loss": 0.5468, + "step": 53 + }, + { + "epoch": 5.142857142857143, + "grad_norm": 0.2720027061358551, + "learning_rate": 3.017631819139273e-06, + "loss": 0.3634, + "step": 54 + }, + { + "epoch": 5.238095238095238, + "grad_norm": 0.23340708465551444, + "learning_rate": 2.669481281701739e-06, + "loss": 0.3698, + "step": 55 + }, + { + "epoch": 5.333333333333333, + "grad_norm": 0.24284971158342084, + "learning_rate": 2.339555568810221e-06, + "loss": 0.3714, + "step": 56 + }, + { + "epoch": 5.428571428571429, + "grad_norm": 0.24573930825254336, + "learning_rate": 2.0286749277707783e-06, + "loss": 0.3626, + "step": 57 + }, + { + "epoch": 5.523809523809524, + "grad_norm": 0.24228391477999003, + "learning_rate": 1.7376122568400533e-06, + "loss": 0.3656, + "step": 58 + }, + { + "epoch": 5.619047619047619, + "grad_norm": 0.2424674393246646, + "learning_rate": 1.467091183678444e-06, + "loss": 0.3574, + "step": 59 + }, + { + "epoch": 5.714285714285714, + "grad_norm": 0.2260500547448982, + "learning_rate": 1.2177842662977136e-06, + "loss": 0.365, + "step": 60 + }, + { + "epoch": 5.809523809523809, + "grad_norm": 0.23262274251274268, + "learning_rate": 9.903113209758098e-07, + "loss": 0.3644, + "step": 61 + }, + { + "epoch": 5.904761904761905, + "grad_norm": 0.24328065113087025, + "learning_rate": 7.852378812959227e-07, + "loss": 0.3682, + "step": 62 + }, + { + "epoch": 6.0, + "grad_norm": 0.3542176555963666, + "learning_rate": 6.030737921409169e-07, + "loss": 0.5551, + "step": 63 + }, + { + "epoch": 6.095238095238095, + "grad_norm": 0.20725527246794545, + "learning_rate": 4.4427194213859216e-07, + "loss": 0.3659, + "step": 64 + }, + { + "epoch": 6.190476190476191, + "grad_norm": 0.20871665612226104, + "learning_rate": 3.0922713770922155e-07, + "loss": 0.3638, + "step": 65 + }, + { + "epoch": 6.285714285714286, + "grad_norm": 0.20911819934603798, + "learning_rate": 1.9827512151456175e-07, + "loss": 0.3584, + "step": 66 + }, + { + "epoch": 6.380952380952381, + "grad_norm": 0.2119088624352818, + "learning_rate": 1.1169173774871478e-07, + "loss": 0.3661, + "step": 67 + }, + { + "epoch": 6.476190476190476, + "grad_norm": 0.20643899236666943, + "learning_rate": 4.9692246345985905e-08, + "loss": 0.3676, + "step": 68 + }, + { + "epoch": 6.571428571428571, + "grad_norm": 0.20106120319449272, + "learning_rate": 1.2430787810776556e-08, + "loss": 0.3518, + "step": 69 + }, + { + "epoch": 6.666666666666667, + "grad_norm": 0.20675993672406334, + "learning_rate": 0.0, + "loss": 0.3555, + "step": 70 + }, + { + "epoch": 6.666666666666667, + "step": 70, + "total_flos": 2.3990446016220365e+17, + "train_loss": 0.4939488410949707, + "train_runtime": 2825.0166, + "train_samples_per_second": 2.478, + "train_steps_per_second": 0.025 + } + ], + "logging_steps": 1, + "max_steps": 70, + "num_input_tokens_seen": 0, + "num_train_epochs": 7, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 2.3990446016220365e+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..e284273 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b3aaa72adb5ca152091c7f0b9747f06847a390382e97fcbf05aff9ec813b1f8 +size 7352 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..8a8ad5d Binary files /dev/null and b/training_loss.png differ 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