commit fe0ddac44e3d02cfee4475376697539db05f75f8 Author: ModelHub XC Date: Thu Sep 17 09:34:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mlfoundations-dev/c1_science_nod_16s_3k Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fdf5d23 --- /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 + +training_args.bin filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors 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..67d2b17 --- /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_science_nod_16s_3k + results: [] +--- + + + +# c1_science_nod_16s_3k + +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_science_nod_16s_3k 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..1355fcb --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 7.0, + "total_flos": 3.564705674208215e+17, + "train_loss": 0.3959881691705613, + "train_runtime": 6616.9312, + "train_samples_per_second": 3.343, + "train_steps_per_second": 0.035 +} \ 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..7412f2d --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31084ecc41c28a8ecf11e9cf046c224c28fd4598ca0dc01da753ada60fe66bbf +size 4877660776 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..74978e6 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:970a51df31a0cb9005cd1f94384c1c76b72f7a0080ef68556fd684ef612e8f26 +size 4932751008 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..f6a5aff --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e101e266ed18262584dccac5156e4af269aceafa063d6b0b02e8ad4a8bdd0277 +size 4330865200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..5e60801 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f86007d76168d110ef9464d3369086a54e49ca588589e6df01887ad7d2205f27 +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/Apr27_04-26-44_jpbot-001-10.jupiter.internal/events.out.tfevents.1745720837.jpbot-001-10.jupiter.internal.1548249.0 b/runs/Apr27_04-26-44_jpbot-001-10.jupiter.internal/events.out.tfevents.1745720837.jpbot-001-10.jupiter.internal.1548249.0 new file mode 100644 index 0000000..58e3558 --- /dev/null +++ b/runs/Apr27_04-26-44_jpbot-001-10.jupiter.internal/events.out.tfevents.1745720837.jpbot-001-10.jupiter.internal.1548249.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a7fa74790f603d2318f6d2d4f0568a6f120887f71eb5d58245a2a3299df6748 +size 54121 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..9ca397b --- /dev/null +++ b/start_end.json @@ -0,0 +1 @@ +{"start_time": "2025-04-27 04:26:44", "end_time": "2025-04-27 06:17:40"} \ 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..1355fcb --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 7.0, + "total_flos": 3.564705674208215e+17, + "train_loss": 0.3959881691705613, + "train_runtime": 6616.9312, + "train_samples_per_second": 3.343, + "train_steps_per_second": 0.035 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..c47d22c --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,232 @@ +{"current_steps": 1, "total_steps": 231, "loss": 0.9888, "lr": 8.333333333333333e-07, "epoch": 0.030303030303030304, "percentage": 0.43, "elapsed_time": "0:00:34", "remaining_time": "2:12:09"} +{"current_steps": 2, "total_steps": 231, "loss": 1.0105, "lr": 1.6666666666666667e-06, "epoch": 0.06060606060606061, "percentage": 0.87, "elapsed_time": "0:01:03", "remaining_time": "2:00:43"} +{"current_steps": 3, "total_steps": 231, "loss": 0.984, "lr": 2.5e-06, "epoch": 0.09090909090909091, "percentage": 1.3, "elapsed_time": "0:01:40", "remaining_time": "2:07:15"} +{"current_steps": 4, "total_steps": 231, "loss": 0.9786, "lr": 3.3333333333333333e-06, "epoch": 0.12121212121212122, "percentage": 1.73, "elapsed_time": "0:02:06", "remaining_time": "1:59:52"} +{"current_steps": 5, "total_steps": 231, "loss": 1.0105, "lr": 4.166666666666667e-06, "epoch": 0.15151515151515152, "percentage": 2.16, "elapsed_time": "0:02:39", "remaining_time": "1:59:49"} +{"current_steps": 6, "total_steps": 231, "loss": 0.8871, "lr": 5e-06, "epoch": 0.18181818181818182, "percentage": 2.6, "elapsed_time": "0:03:05", "remaining_time": "1:55:46"} +{"current_steps": 7, "total_steps": 231, "loss": 0.862, "lr": 5.833333333333334e-06, "epoch": 0.21212121212121213, "percentage": 3.03, "elapsed_time": "0:03:34", "remaining_time": "1:54:31"} +{"current_steps": 8, "total_steps": 231, "loss": 0.9222, "lr": 6.666666666666667e-06, "epoch": 0.24242424242424243, "percentage": 3.46, "elapsed_time": "0:04:06", "remaining_time": "1:54:43"} +{"current_steps": 9, "total_steps": 231, "loss": 0.88, "lr": 7.500000000000001e-06, "epoch": 0.2727272727272727, "percentage": 3.9, "elapsed_time": "0:04:34", "remaining_time": "1:52:55"} +{"current_steps": 10, "total_steps": 231, "loss": 0.873, "lr": 8.333333333333334e-06, "epoch": 0.30303030303030304, "percentage": 4.33, "elapsed_time": "0:04:57", "remaining_time": "1:49:44"} +{"current_steps": 11, "total_steps": 231, "loss": 0.8166, "lr": 9.166666666666666e-06, "epoch": 0.3333333333333333, "percentage": 4.76, "elapsed_time": "0:05:29", "remaining_time": "1:49:57"} +{"current_steps": 12, "total_steps": 231, "loss": 0.9013, "lr": 1e-05, "epoch": 0.36363636363636365, "percentage": 5.19, "elapsed_time": "0:06:02", "remaining_time": "1:50:12"} +{"current_steps": 13, "total_steps": 231, "loss": 0.7934, "lr": 1.0833333333333334e-05, "epoch": 0.3939393939393939, "percentage": 5.63, "elapsed_time": "0:06:38", "remaining_time": "1:51:18"} +{"current_steps": 14, "total_steps": 231, "loss": 0.8134, "lr": 1.1666666666666668e-05, "epoch": 0.42424242424242425, "percentage": 6.06, "elapsed_time": "0:07:06", "remaining_time": "1:50:04"} +{"current_steps": 15, "total_steps": 231, "loss": 0.7884, "lr": 1.25e-05, "epoch": 0.45454545454545453, "percentage": 6.49, "elapsed_time": "0:07:35", "remaining_time": "1:49:16"} +{"current_steps": 16, "total_steps": 231, "loss": 0.7986, "lr": 1.3333333333333333e-05, "epoch": 0.48484848484848486, "percentage": 6.93, "elapsed_time": "0:08:04", "remaining_time": "1:48:34"} +{"current_steps": 17, "total_steps": 231, "loss": 0.7553, "lr": 1.416666666666667e-05, "epoch": 0.5151515151515151, "percentage": 7.36, "elapsed_time": "0:08:35", "remaining_time": "1:48:09"} +{"current_steps": 18, "total_steps": 231, "loss": 0.7819, "lr": 1.5000000000000002e-05, "epoch": 0.5454545454545454, "percentage": 7.79, "elapsed_time": "0:09:04", "remaining_time": "1:47:24"} +{"current_steps": 19, "total_steps": 231, "loss": 0.757, "lr": 1.5833333333333333e-05, "epoch": 0.5757575757575758, "percentage": 8.23, "elapsed_time": "0:09:33", "remaining_time": "1:46:35"} +{"current_steps": 20, "total_steps": 231, "loss": 0.7117, "lr": 1.6666666666666667e-05, "epoch": 0.6060606060606061, "percentage": 8.66, "elapsed_time": "0:10:07", "remaining_time": "1:46:53"} +{"current_steps": 21, "total_steps": 231, "loss": 0.7214, "lr": 1.7500000000000002e-05, "epoch": 0.6363636363636364, "percentage": 9.09, "elapsed_time": "0:10:38", "remaining_time": "1:46:28"} +{"current_steps": 22, "total_steps": 231, "loss": 0.7587, "lr": 1.8333333333333333e-05, "epoch": 0.6666666666666666, "percentage": 9.52, "elapsed_time": "0:11:06", "remaining_time": "1:45:35"} +{"current_steps": 23, "total_steps": 231, "loss": 0.6967, "lr": 1.916666666666667e-05, "epoch": 0.696969696969697, "percentage": 9.96, "elapsed_time": "0:11:39", "remaining_time": "1:45:22"} +{"current_steps": 24, "total_steps": 231, "loss": 0.7407, "lr": 2e-05, "epoch": 0.7272727272727273, "percentage": 10.39, "elapsed_time": "0:12:06", "remaining_time": "1:44:29"} +{"current_steps": 25, "total_steps": 231, "loss": 0.741, "lr": 1.999884834944106e-05, "epoch": 0.7575757575757576, "percentage": 10.82, "elapsed_time": "0:12:30", "remaining_time": "1:43:03"} +{"current_steps": 26, "total_steps": 231, "loss": 0.7249, "lr": 1.9995393663024054e-05, "epoch": 0.7878787878787878, "percentage": 11.26, "elapsed_time": "0:13:00", "remaining_time": "1:42:37"} +{"current_steps": 27, "total_steps": 231, "loss": 0.6793, "lr": 1.9989636736467278e-05, "epoch": 0.8181818181818182, "percentage": 11.69, "elapsed_time": "0:13:30", "remaining_time": "1:42:05"} +{"current_steps": 28, "total_steps": 231, "loss": 0.6822, "lr": 1.9981578895764272e-05, "epoch": 0.8484848484848485, "percentage": 12.12, "elapsed_time": "0:13:57", "remaining_time": "1:41:14"} +{"current_steps": 29, "total_steps": 231, "loss": 0.7035, "lr": 1.9971221996878395e-05, "epoch": 0.8787878787878788, "percentage": 12.55, "elapsed_time": "0:14:29", "remaining_time": "1:40:58"} +{"current_steps": 30, "total_steps": 231, "loss": 0.7038, "lr": 1.9958568425315316e-05, "epoch": 0.9090909090909091, "percentage": 12.99, "elapsed_time": "0:14:55", "remaining_time": "1:40:00"} +{"current_steps": 31, "total_steps": 231, "loss": 0.6911, "lr": 1.9943621095573588e-05, "epoch": 0.9393939393939394, "percentage": 13.42, "elapsed_time": "0:15:21", "remaining_time": "1:39:07"} +{"current_steps": 32, "total_steps": 231, "loss": 0.679, "lr": 1.9926383450473344e-05, "epoch": 0.9696969696969697, "percentage": 13.85, "elapsed_time": "0:15:48", "remaining_time": "1:38:15"} +{"current_steps": 33, "total_steps": 231, "loss": 0.6661, "lr": 1.9906859460363307e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "0:16:11", "remaining_time": "1:37:11"} +{"current_steps": 34, "total_steps": 231, "loss": 0.6344, "lr": 1.9885053622206305e-05, "epoch": 1.0303030303030303, "percentage": 14.72, "elapsed_time": "0:17:06", "remaining_time": "1:39:06"} +{"current_steps": 35, "total_steps": 231, "loss": 0.6168, "lr": 1.986097095854347e-05, "epoch": 1.0606060606060606, "percentage": 15.15, "elapsed_time": "0:17:36", "remaining_time": "1:38:34"} +{"current_steps": 36, "total_steps": 231, "loss": 0.6138, "lr": 1.9834617016337424e-05, "epoch": 1.0909090909090908, "percentage": 15.58, "elapsed_time": "0:18:08", "remaining_time": "1:38:13"} +{"current_steps": 37, "total_steps": 231, "loss": 0.6027, "lr": 1.9805997865694616e-05, "epoch": 1.121212121212121, "percentage": 16.02, "elapsed_time": "0:18:37", "remaining_time": "1:37:41"} +{"current_steps": 38, "total_steps": 231, "loss": 0.6063, "lr": 1.9775120098467212e-05, "epoch": 1.1515151515151516, "percentage": 16.45, "elapsed_time": "0:19:00", "remaining_time": "1:36:30"} +{"current_steps": 39, "total_steps": 231, "loss": 0.6487, "lr": 1.9741990826734793e-05, "epoch": 1.1818181818181819, "percentage": 16.88, "elapsed_time": "0:19:27", "remaining_time": "1:35:48"} +{"current_steps": 40, "total_steps": 231, "loss": 0.6125, "lr": 1.970661768116622e-05, "epoch": 1.2121212121212122, "percentage": 17.32, "elapsed_time": "0:19:52", "remaining_time": "1:34:55"} +{"current_steps": 41, "total_steps": 231, "loss": 0.6375, "lr": 1.9669008809262064e-05, "epoch": 1.2424242424242424, "percentage": 17.75, "elapsed_time": "0:20:21", "remaining_time": "1:34:20"} +{"current_steps": 42, "total_steps": 231, "loss": 0.6064, "lr": 1.9629172873477995e-05, "epoch": 1.2727272727272727, "percentage": 18.18, "elapsed_time": "0:20:51", "remaining_time": "1:33:50"} +{"current_steps": 43, "total_steps": 231, "loss": 0.5929, "lr": 1.9587119049229558e-05, "epoch": 1.303030303030303, "percentage": 18.61, "elapsed_time": "0:21:20", "remaining_time": "1:33:19"} +{"current_steps": 44, "total_steps": 231, "loss": 0.5862, "lr": 1.954285702277879e-05, "epoch": 1.3333333333333333, "percentage": 19.05, "elapsed_time": "0:21:45", "remaining_time": "1:32:27"} +{"current_steps": 45, "total_steps": 231, "loss": 0.6165, "lr": 1.9496396989003195e-05, "epoch": 1.3636363636363638, "percentage": 19.48, "elapsed_time": "0:22:13", "remaining_time": "1:31:52"} +{"current_steps": 46, "total_steps": 231, "loss": 0.6011, "lr": 1.944774964904754e-05, "epoch": 1.393939393939394, "percentage": 19.91, "elapsed_time": "0:22:43", "remaining_time": "1:31:21"} +{"current_steps": 47, "total_steps": 231, "loss": 0.6157, "lr": 1.9396926207859085e-05, "epoch": 1.4242424242424243, "percentage": 20.35, "elapsed_time": "0:23:08", "remaining_time": "1:30:35"} +{"current_steps": 48, "total_steps": 231, "loss": 0.5794, "lr": 1.9343938371606714e-05, "epoch": 1.4545454545454546, "percentage": 20.78, "elapsed_time": "0:23:39", "remaining_time": "1:30:10"} +{"current_steps": 49, "total_steps": 231, "loss": 0.6099, "lr": 1.9288798344984673e-05, "epoch": 1.4848484848484849, "percentage": 21.21, "elapsed_time": "0:24:07", "remaining_time": "1:29:36"} +{"current_steps": 50, "total_steps": 231, "loss": 0.6181, "lr": 1.9231518828401458e-05, "epoch": 1.5151515151515151, "percentage": 21.65, "elapsed_time": "0:24:35", "remaining_time": "1:29:02"} +{"current_steps": 51, "total_steps": 231, "loss": 0.6061, "lr": 1.917211301505453e-05, "epoch": 1.5454545454545454, "percentage": 22.08, "elapsed_time": "0:25:03", "remaining_time": "1:28:25"} +{"current_steps": 52, "total_steps": 231, "loss": 0.577, "lr": 1.911059458789152e-05, "epoch": 1.5757575757575757, "percentage": 22.51, "elapsed_time": "0:25:33", "remaining_time": "1:27:58"} +{"current_steps": 53, "total_steps": 231, "loss": 0.633, "lr": 1.9046977716458627e-05, "epoch": 1.606060606060606, "percentage": 22.94, "elapsed_time": "0:26:00", "remaining_time": "1:27:19"} +{"current_steps": 54, "total_steps": 231, "loss": 0.5868, "lr": 1.8981277053636963e-05, "epoch": 1.6363636363636362, "percentage": 23.38, "elapsed_time": "0:26:26", "remaining_time": "1:26:40"} +{"current_steps": 55, "total_steps": 231, "loss": 0.5837, "lr": 1.891350773226754e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "0:26:52", "remaining_time": "1:25:59"} +{"current_steps": 56, "total_steps": 231, "loss": 0.6058, "lr": 1.8843685361665724e-05, "epoch": 1.696969696969697, "percentage": 24.24, "elapsed_time": "0:27:18", "remaining_time": "1:25:20"} +{"current_steps": 57, "total_steps": 231, "loss": 0.6108, "lr": 1.8771826024025944e-05, "epoch": 1.7272727272727273, "percentage": 24.68, "elapsed_time": "0:27:47", "remaining_time": "1:24:51"} +{"current_steps": 58, "total_steps": 231, "loss": 0.6089, "lr": 1.8697946270717468e-05, "epoch": 1.7575757575757576, "percentage": 25.11, "elapsed_time": "0:28:11", "remaining_time": "1:24:06"} +{"current_steps": 59, "total_steps": 231, "loss": 0.5978, "lr": 1.8622063118472135e-05, "epoch": 1.7878787878787878, "percentage": 25.54, "elapsed_time": "0:28:40", "remaining_time": "1:23:34"} +{"current_steps": 60, "total_steps": 231, "loss": 0.5784, "lr": 1.8544194045464888e-05, "epoch": 1.8181818181818183, "percentage": 25.97, "elapsed_time": "0:29:09", "remaining_time": "1:23:06"} +{"current_steps": 61, "total_steps": 231, "loss": 0.5652, "lr": 1.8464356987288012e-05, "epoch": 1.8484848484848486, "percentage": 26.41, "elapsed_time": "0:29:40", "remaining_time": "1:22:40"} +{"current_steps": 62, "total_steps": 231, "loss": 0.5551, "lr": 1.8382570332820045e-05, "epoch": 1.878787878787879, "percentage": 26.84, "elapsed_time": "0:30:03", "remaining_time": "1:21:56"} +{"current_steps": 63, "total_steps": 231, "loss": 0.5993, "lr": 1.8298852919990254e-05, "epoch": 1.9090909090909092, "percentage": 27.27, "elapsed_time": "0:30:27", "remaining_time": "1:21:12"} +{"current_steps": 64, "total_steps": 231, "loss": 0.6061, "lr": 1.821322403143969e-05, "epoch": 1.9393939393939394, "percentage": 27.71, "elapsed_time": "0:30:52", "remaining_time": "1:20:33"} +{"current_steps": 65, "total_steps": 231, "loss": 0.539, "lr": 1.812570339007983e-05, "epoch": 1.9696969696969697, "percentage": 28.14, "elapsed_time": "0:31:21", "remaining_time": "1:20:05"} +{"current_steps": 66, "total_steps": 231, "loss": 0.5604, "lr": 1.8036311154549783e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "0:31:50", "remaining_time": "1:19:37"} +{"current_steps": 67, "total_steps": 231, "loss": 0.4949, "lr": 1.7945067914573147e-05, "epoch": 2.0303030303030303, "percentage": 29.0, "elapsed_time": "0:32:45", "remaining_time": "1:20:10"} +{"current_steps": 68, "total_steps": 231, "loss": 0.4799, "lr": 1.7851994686215592e-05, "epoch": 2.0606060606060606, "percentage": 29.44, "elapsed_time": "0:33:12", "remaining_time": "1:19:35"} +{"current_steps": 69, "total_steps": 231, "loss": 0.4757, "lr": 1.77571129070442e-05, "epoch": 2.090909090909091, "percentage": 29.87, "elapsed_time": "0:33:38", "remaining_time": "1:18:58"} +{"current_steps": 70, "total_steps": 231, "loss": 0.45, "lr": 1.766044443118978e-05, "epoch": 2.121212121212121, "percentage": 30.3, "elapsed_time": "0:34:05", "remaining_time": "1:18:23"} +{"current_steps": 71, "total_steps": 231, "loss": 0.4652, "lr": 1.7562011524313187e-05, "epoch": 2.1515151515151514, "percentage": 30.74, "elapsed_time": "0:34:35", "remaining_time": "1:17:56"} +{"current_steps": 72, "total_steps": 231, "loss": 0.4853, "lr": 1.7461836858476858e-05, "epoch": 2.1818181818181817, "percentage": 31.17, "elapsed_time": "0:35:03", "remaining_time": "1:17:24"} +{"current_steps": 73, "total_steps": 231, "loss": 0.4642, "lr": 1.7359943506922775e-05, "epoch": 2.212121212121212, "percentage": 31.6, "elapsed_time": "0:35:32", "remaining_time": "1:16:55"} +{"current_steps": 74, "total_steps": 231, "loss": 0.4558, "lr": 1.725635493875799e-05, "epoch": 2.242424242424242, "percentage": 32.03, "elapsed_time": "0:35:55", "remaining_time": "1:16:13"} +{"current_steps": 75, "total_steps": 231, "loss": 0.448, "lr": 1.7151095013548996e-05, "epoch": 2.2727272727272725, "percentage": 32.47, "elapsed_time": "0:36:26", "remaining_time": "1:15:48"} +{"current_steps": 76, "total_steps": 231, "loss": 0.4539, "lr": 1.7044187975826126e-05, "epoch": 2.303030303030303, "percentage": 32.9, "elapsed_time": "0:36:57", "remaining_time": "1:15:23"} +{"current_steps": 77, "total_steps": 231, "loss": 0.4505, "lr": 1.693565844949933e-05, "epoch": 2.3333333333333335, "percentage": 33.33, "elapsed_time": "0:37:23", "remaining_time": "1:14:47"} +{"current_steps": 78, "total_steps": 231, "loss": 0.4683, "lr": 1.6825531432186545e-05, "epoch": 2.3636363636363638, "percentage": 33.77, "elapsed_time": "0:37:53", "remaining_time": "1:14:19"} +{"current_steps": 79, "total_steps": 231, "loss": 0.4446, "lr": 1.671383228945597e-05, "epoch": 2.393939393939394, "percentage": 34.2, "elapsed_time": "0:38:18", "remaining_time": "1:13:43"} +{"current_steps": 80, "total_steps": 231, "loss": 0.4697, "lr": 1.6600586748983642e-05, "epoch": 2.4242424242424243, "percentage": 34.63, "elapsed_time": "0:38:48", "remaining_time": "1:13:15"} +{"current_steps": 81, "total_steps": 231, "loss": 0.4585, "lr": 1.648582089462756e-05, "epoch": 2.4545454545454546, "percentage": 35.06, "elapsed_time": "0:39:11", "remaining_time": "1:12:35"} +{"current_steps": 82, "total_steps": 231, "loss": 0.4643, "lr": 1.6369561160419783e-05, "epoch": 2.484848484848485, "percentage": 35.5, "elapsed_time": "0:39:40", "remaining_time": "1:12:04"} +{"current_steps": 83, "total_steps": 231, "loss": 0.4602, "lr": 1.625183432447789e-05, "epoch": 2.515151515151515, "percentage": 35.93, "elapsed_time": "0:40:07", "remaining_time": "1:11:33"} +{"current_steps": 84, "total_steps": 231, "loss": 0.4655, "lr": 1.6132667502837164e-05, "epoch": 2.5454545454545454, "percentage": 36.36, "elapsed_time": "0:40:36", "remaining_time": "1:11:04"} +{"current_steps": 85, "total_steps": 231, "loss": 0.4538, "lr": 1.6012088143204953e-05, "epoch": 2.5757575757575757, "percentage": 36.8, "elapsed_time": "0:41:10", "remaining_time": "1:10:43"} +{"current_steps": 86, "total_steps": 231, "loss": 0.458, "lr": 1.589012401863864e-05, "epoch": 2.606060606060606, "percentage": 37.23, "elapsed_time": "0:41:38", "remaining_time": "1:10:12"} +{"current_steps": 87, "total_steps": 231, "loss": 0.4493, "lr": 1.5766803221148676e-05, "epoch": 2.6363636363636362, "percentage": 37.66, "elapsed_time": "0:42:04", "remaining_time": "1:09:39"} +{"current_steps": 88, "total_steps": 231, "loss": 0.4686, "lr": 1.5642154155228124e-05, "epoch": 2.6666666666666665, "percentage": 38.1, "elapsed_time": "0:42:31", "remaining_time": "1:09:06"} +{"current_steps": 89, "total_steps": 231, "loss": 0.4583, "lr": 1.5516205531310272e-05, "epoch": 2.6969696969696972, "percentage": 38.53, "elapsed_time": "0:42:57", "remaining_time": "1:08:32"} +{"current_steps": 90, "total_steps": 231, "loss": 0.4425, "lr": 1.538898635915576e-05, "epoch": 2.7272727272727275, "percentage": 38.96, "elapsed_time": "0:43:26", "remaining_time": "1:08:03"} +{"current_steps": 91, "total_steps": 231, "loss": 0.4464, "lr": 1.526052594117071e-05, "epoch": 2.757575757575758, "percentage": 39.39, "elapsed_time": "0:43:53", "remaining_time": "1:07:31"} +{"current_steps": 92, "total_steps": 231, "loss": 0.4436, "lr": 1.513085386565758e-05, "epoch": 2.787878787878788, "percentage": 39.83, "elapsed_time": "0:44:27", "remaining_time": "1:07:10"} +{"current_steps": 93, "total_steps": 231, "loss": 0.4591, "lr": 1.5000000000000002e-05, "epoch": 2.8181818181818183, "percentage": 40.26, "elapsed_time": "0:44:55", "remaining_time": "1:06:40"} +{"current_steps": 94, "total_steps": 231, "loss": 0.4721, "lr": 1.4867994483783485e-05, "epoch": 2.8484848484848486, "percentage": 40.69, "elapsed_time": "0:45:22", "remaining_time": "1:06:07"} +{"current_steps": 95, "total_steps": 231, "loss": 0.4649, "lr": 1.4734867721853341e-05, "epoch": 2.878787878787879, "percentage": 41.13, "elapsed_time": "0:45:50", "remaining_time": "1:05:37"} +{"current_steps": 96, "total_steps": 231, "loss": 0.4814, "lr": 1.4600650377311523e-05, "epoch": 2.909090909090909, "percentage": 41.56, "elapsed_time": "0:46:20", "remaining_time": "1:05:10"} +{"current_steps": 97, "total_steps": 231, "loss": 0.4503, "lr": 1.4465373364454001e-05, "epoch": 2.9393939393939394, "percentage": 41.99, "elapsed_time": "0:46:48", "remaining_time": "1:04:39"} +{"current_steps": 98, "total_steps": 231, "loss": 0.4387, "lr": 1.4329067841650274e-05, "epoch": 2.9696969696969697, "percentage": 42.42, "elapsed_time": "0:47:15", "remaining_time": "1:04:07"} +{"current_steps": 99, "total_steps": 231, "loss": 0.4538, "lr": 1.4191765204166643e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "0:47:37", "remaining_time": "1:03:30"} +{"current_steps": 100, "total_steps": 231, "loss": 0.3659, "lr": 1.4053497076934948e-05, "epoch": 3.0303030303030303, "percentage": 43.29, "elapsed_time": "0:48:25", "remaining_time": "1:03:26"} +{"current_steps": 101, "total_steps": 231, "loss": 0.3641, "lr": 1.3914295307268396e-05, "epoch": 3.0606060606060606, "percentage": 43.72, "elapsed_time": "0:48:52", "remaining_time": "1:02:54"} +{"current_steps": 102, "total_steps": 231, "loss": 0.3546, "lr": 1.3774191957526144e-05, "epoch": 3.090909090909091, "percentage": 44.16, "elapsed_time": "0:49:19", "remaining_time": "1:02:22"} +{"current_steps": 103, "total_steps": 231, "loss": 0.3555, "lr": 1.3633219297728415e-05, "epoch": 3.121212121212121, "percentage": 44.59, "elapsed_time": "0:49:46", "remaining_time": "1:01:50"} +{"current_steps": 104, "total_steps": 231, "loss": 0.3413, "lr": 1.3491409798123687e-05, "epoch": 3.1515151515151514, "percentage": 45.02, "elapsed_time": "0:50:18", "remaining_time": "1:01:26"} +{"current_steps": 105, "total_steps": 231, "loss": 0.3495, "lr": 1.3348796121709862e-05, "epoch": 3.1818181818181817, "percentage": 45.45, "elapsed_time": "0:50:42", "remaining_time": "1:00:50"} +{"current_steps": 106, "total_steps": 231, "loss": 0.3461, "lr": 1.3205411116710973e-05, "epoch": 3.212121212121212, "percentage": 45.89, "elapsed_time": "0:51:08", "remaining_time": "1:00:18"} +{"current_steps": 107, "total_steps": 231, "loss": 0.3422, "lr": 1.3061287809011243e-05, "epoch": 3.242424242424242, "percentage": 46.32, "elapsed_time": "0:51:40", "remaining_time": "0:59:53"} +{"current_steps": 108, "total_steps": 231, "loss": 0.3297, "lr": 1.291645939454825e-05, "epoch": 3.2727272727272725, "percentage": 46.75, "elapsed_time": "0:52:06", "remaining_time": "0:59:20"} +{"current_steps": 109, "total_steps": 231, "loss": 0.3369, "lr": 1.277095923166689e-05, "epoch": 3.303030303030303, "percentage": 47.19, "elapsed_time": "0:52:33", "remaining_time": "0:58:50"} +{"current_steps": 110, "total_steps": 231, "loss": 0.3432, "lr": 1.2624820833435939e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "0:53:04", "remaining_time": "0:58:22"} +{"current_steps": 111, "total_steps": 231, "loss": 0.3225, "lr": 1.2478077859929e-05, "epoch": 3.3636363636363638, "percentage": 48.05, "elapsed_time": "0:53:30", "remaining_time": "0:57:50"} +{"current_steps": 112, "total_steps": 231, "loss": 0.3335, "lr": 1.2330764110471567e-05, "epoch": 3.393939393939394, "percentage": 48.48, "elapsed_time": "0:53:51", "remaining_time": "0:57:12"} +{"current_steps": 113, "total_steps": 231, "loss": 0.3318, "lr": 1.2182913515856016e-05, "epoch": 3.4242424242424243, "percentage": 48.92, "elapsed_time": "0:54:18", "remaining_time": "0:56:43"} +{"current_steps": 114, "total_steps": 231, "loss": 0.3494, "lr": 1.2034560130526341e-05, "epoch": 3.4545454545454546, "percentage": 49.35, "elapsed_time": "0:54:48", "remaining_time": "0:56:15"} +{"current_steps": 115, "total_steps": 231, "loss": 0.3275, "lr": 1.1885738124734359e-05, "epoch": 3.484848484848485, "percentage": 49.78, "elapsed_time": "0:55:18", "remaining_time": "0:55:47"} +{"current_steps": 116, "total_steps": 231, "loss": 0.3572, "lr": 1.1736481776669307e-05, "epoch": 3.515151515151515, "percentage": 50.22, "elapsed_time": "0:55:47", "remaining_time": "0:55:18"} +{"current_steps": 117, "total_steps": 231, "loss": 0.3451, "lr": 1.1586825464562515e-05, "epoch": 3.5454545454545454, "percentage": 50.65, "elapsed_time": "0:56:17", "remaining_time": "0:54:50"} +{"current_steps": 118, "total_steps": 231, "loss": 0.3544, "lr": 1.1436803658769082e-05, "epoch": 3.5757575757575757, "percentage": 51.08, "elapsed_time": "0:56:44", "remaining_time": "0:54:19"} +{"current_steps": 119, "total_steps": 231, "loss": 0.3193, "lr": 1.1286450913828313e-05, "epoch": 3.606060606060606, "percentage": 51.52, "elapsed_time": "0:57:13", "remaining_time": "0:53:51"} +{"current_steps": 120, "total_steps": 231, "loss": 0.3453, "lr": 1.113580186050475e-05, "epoch": 3.6363636363636362, "percentage": 51.95, "elapsed_time": "0:57:39", "remaining_time": "0:53:19"} +{"current_steps": 121, "total_steps": 231, "loss": 0.3395, "lr": 1.0984891197811686e-05, "epoch": 3.6666666666666665, "percentage": 52.38, "elapsed_time": "0:58:07", "remaining_time": "0:52:50"} +{"current_steps": 122, "total_steps": 231, "loss": 0.3281, "lr": 1.0833753685018935e-05, "epoch": 3.6969696969696972, "percentage": 52.81, "elapsed_time": "0:58:34", "remaining_time": "0:52:20"} +{"current_steps": 123, "total_steps": 231, "loss": 0.3402, "lr": 1.0682424133646712e-05, "epoch": 3.7272727272727275, "percentage": 53.25, "elapsed_time": "0:59:00", "remaining_time": "0:51:48"} +{"current_steps": 124, "total_steps": 231, "loss": 0.3336, "lr": 1.0530937399447496e-05, "epoch": 3.757575757575758, "percentage": 53.68, "elapsed_time": "0:59:22", "remaining_time": "0:51:13"} +{"current_steps": 125, "total_steps": 231, "loss": 0.347, "lr": 1.0379328374377715e-05, "epoch": 3.787878787878788, "percentage": 54.11, "elapsed_time": "0:59:45", "remaining_time": "0:50:40"} +{"current_steps": 126, "total_steps": 231, "loss": 0.3479, "lr": 1.0227631978561057e-05, "epoch": 3.8181818181818183, "percentage": 54.55, "elapsed_time": "1:00:21", "remaining_time": "0:50:17"} +{"current_steps": 127, "total_steps": 231, "loss": 0.345, "lr": 1.0075883152245334e-05, "epoch": 3.8484848484848486, "percentage": 54.98, "elapsed_time": "1:00:46", "remaining_time": "0:49:46"} +{"current_steps": 128, "total_steps": 231, "loss": 0.3178, "lr": 9.92411684775467e-06, "epoch": 3.878787878787879, "percentage": 55.41, "elapsed_time": "1:01:13", "remaining_time": "0:49:15"} +{"current_steps": 129, "total_steps": 231, "loss": 0.3395, "lr": 9.772368021438943e-06, "epoch": 3.909090909090909, "percentage": 55.84, "elapsed_time": "1:01:38", "remaining_time": "0:48:44"} +{"current_steps": 130, "total_steps": 231, "loss": 0.3375, "lr": 9.620671625622287e-06, "epoch": 3.9393939393939394, "percentage": 56.28, "elapsed_time": "1:02:08", "remaining_time": "0:48:16"} +{"current_steps": 131, "total_steps": 231, "loss": 0.3341, "lr": 9.469062600552509e-06, "epoch": 3.9696969696969697, "percentage": 56.71, "elapsed_time": "1:02:31", "remaining_time": "0:47:43"} +{"current_steps": 132, "total_steps": 231, "loss": 0.3234, "lr": 9.317575866353293e-06, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "1:03:01", "remaining_time": "0:47:15"} +{"current_steps": 133, "total_steps": 231, "loss": 0.2627, "lr": 9.166246314981066e-06, "epoch": 4.03030303030303, "percentage": 57.58, "elapsed_time": "1:03:47", "remaining_time": "0:47:00"} +{"current_steps": 134, "total_steps": 231, "loss": 0.26, "lr": 9.015108802188314e-06, "epoch": 4.0606060606060606, "percentage": 58.01, "elapsed_time": "1:04:16", "remaining_time": "0:46:31"} +{"current_steps": 135, "total_steps": 231, "loss": 0.2552, "lr": 8.86419813949525e-06, "epoch": 4.090909090909091, "percentage": 58.44, "elapsed_time": "1:04:40", "remaining_time": "0:45:59"} +{"current_steps": 136, "total_steps": 231, "loss": 0.2405, "lr": 8.71354908617169e-06, "epoch": 4.121212121212121, "percentage": 58.87, "elapsed_time": "1:05:08", "remaining_time": "0:45:29"} +{"current_steps": 137, "total_steps": 231, "loss": 0.2572, "lr": 8.56319634123092e-06, "epoch": 4.151515151515151, "percentage": 59.31, "elapsed_time": "1:05:40", "remaining_time": "0:45:03"} +{"current_steps": 138, "total_steps": 231, "loss": 0.224, "lr": 8.413174535437486e-06, "epoch": 4.181818181818182, "percentage": 59.74, "elapsed_time": "1:06:04", "remaining_time": "0:44:31"} +{"current_steps": 139, "total_steps": 231, "loss": 0.2409, "lr": 8.263518223330698e-06, "epoch": 4.212121212121212, "percentage": 60.17, "elapsed_time": "1:06:31", "remaining_time": "0:44:02"} +{"current_steps": 140, "total_steps": 231, "loss": 0.2375, "lr": 8.114261875265643e-06, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "1:06:56", "remaining_time": "0:43:30"} +{"current_steps": 141, "total_steps": 231, "loss": 0.2547, "lr": 7.965439869473664e-06, "epoch": 4.2727272727272725, "percentage": 61.04, "elapsed_time": "1:07:24", "remaining_time": "0:43:01"} +{"current_steps": 142, "total_steps": 231, "loss": 0.2483, "lr": 7.817086484143987e-06, "epoch": 4.303030303030303, "percentage": 61.47, "elapsed_time": "1:07:50", "remaining_time": "0:42:30"} +{"current_steps": 143, "total_steps": 231, "loss": 0.2383, "lr": 7.669235889528436e-06, "epoch": 4.333333333333333, "percentage": 61.9, "elapsed_time": "1:08:17", "remaining_time": "0:42:01"} +{"current_steps": 144, "total_steps": 231, "loss": 0.2337, "lr": 7.521922140071003e-06, "epoch": 4.363636363636363, "percentage": 62.34, "elapsed_time": "1:08:46", "remaining_time": "0:41:32"} +{"current_steps": 145, "total_steps": 231, "loss": 0.2416, "lr": 7.375179166564062e-06, "epoch": 4.393939393939394, "percentage": 62.77, "elapsed_time": "1:09:19", "remaining_time": "0:41:07"} +{"current_steps": 146, "total_steps": 231, "loss": 0.2352, "lr": 7.2290407683331154e-06, "epoch": 4.424242424242424, "percentage": 63.2, "elapsed_time": "1:09:49", "remaining_time": "0:40:39"} +{"current_steps": 147, "total_steps": 231, "loss": 0.2248, "lr": 7.0835406054517505e-06, "epoch": 4.454545454545454, "percentage": 63.64, "elapsed_time": "1:10:18", "remaining_time": "0:40:10"} +{"current_steps": 148, "total_steps": 231, "loss": 0.2446, "lr": 6.93871219098876e-06, "epoch": 4.484848484848484, "percentage": 64.07, "elapsed_time": "1:10:44", "remaining_time": "0:39:40"} +{"current_steps": 149, "total_steps": 231, "loss": 0.2389, "lr": 6.79458888328903e-06, "epoch": 4.515151515151516, "percentage": 64.5, "elapsed_time": "1:11:10", "remaining_time": "0:39:09"} +{"current_steps": 150, "total_steps": 231, "loss": 0.2574, "lr": 6.651203878290139e-06, "epoch": 4.545454545454545, "percentage": 64.94, "elapsed_time": "1:11:43", "remaining_time": "0:38:43"} +{"current_steps": 151, "total_steps": 231, "loss": 0.2376, "lr": 6.508590201876317e-06, "epoch": 4.575757575757576, "percentage": 65.37, "elapsed_time": "1:12:11", "remaining_time": "0:38:15"} +{"current_steps": 152, "total_steps": 231, "loss": 0.2559, "lr": 6.366780702271589e-06, "epoch": 4.606060606060606, "percentage": 65.8, "elapsed_time": "1:12:44", "remaining_time": "0:37:48"} +{"current_steps": 153, "total_steps": 231, "loss": 0.2514, "lr": 6.225808042473857e-06, "epoch": 4.636363636363637, "percentage": 66.23, "elapsed_time": "1:13:06", "remaining_time": "0:37:16"} +{"current_steps": 154, "total_steps": 231, "loss": 0.2362, "lr": 6.085704692731609e-06, "epoch": 4.666666666666667, "percentage": 66.67, "elapsed_time": "1:13:31", "remaining_time": "0:36:45"} +{"current_steps": 155, "total_steps": 231, "loss": 0.2323, "lr": 5.946502923065054e-06, "epoch": 4.696969696969697, "percentage": 67.1, "elapsed_time": "1:13:56", "remaining_time": "0:36:15"} +{"current_steps": 156, "total_steps": 231, "loss": 0.2407, "lr": 5.8082347958333625e-06, "epoch": 4.7272727272727275, "percentage": 67.53, "elapsed_time": "1:14:24", "remaining_time": "0:35:46"} +{"current_steps": 157, "total_steps": 231, "loss": 0.2424, "lr": 5.670932158349732e-06, "epoch": 4.757575757575758, "percentage": 67.97, "elapsed_time": "1:14:57", "remaining_time": "0:35:19"} +{"current_steps": 158, "total_steps": 231, "loss": 0.2375, "lr": 5.534626635546e-06, "epoch": 4.787878787878788, "percentage": 68.4, "elapsed_time": "1:15:30", "remaining_time": "0:34:52"} +{"current_steps": 159, "total_steps": 231, "loss": 0.2308, "lr": 5.399349622688479e-06, "epoch": 4.818181818181818, "percentage": 68.83, "elapsed_time": "1:15:52", "remaining_time": "0:34:21"} +{"current_steps": 160, "total_steps": 231, "loss": 0.234, "lr": 5.2651322781466606e-06, "epoch": 4.848484848484849, "percentage": 69.26, "elapsed_time": "1:16:21", "remaining_time": "0:33:52"} +{"current_steps": 161, "total_steps": 231, "loss": 0.2426, "lr": 5.132005516216512e-06, "epoch": 4.878787878787879, "percentage": 69.7, "elapsed_time": "1:16:46", "remaining_time": "0:33:22"} +{"current_steps": 162, "total_steps": 231, "loss": 0.2258, "lr": 5.000000000000003e-06, "epoch": 4.909090909090909, "percentage": 70.13, "elapsed_time": "1:17:15", "remaining_time": "0:32:54"} +{"current_steps": 163, "total_steps": 231, "loss": 0.2457, "lr": 4.869146134342426e-06, "epoch": 4.9393939393939394, "percentage": 70.56, "elapsed_time": "1:17:42", "remaining_time": "0:32:25"} +{"current_steps": 164, "total_steps": 231, "loss": 0.2447, "lr": 4.739474058829288e-06, "epoch": 4.96969696969697, "percentage": 71.0, "elapsed_time": "1:18:07", "remaining_time": "0:31:55"} +{"current_steps": 165, "total_steps": 231, "loss": 0.2394, "lr": 4.611013640844245e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:18:31", "remaining_time": "0:31:24"} +{"current_steps": 166, "total_steps": 231, "loss": 0.1735, "lr": 4.483794468689728e-06, "epoch": 5.03030303030303, "percentage": 71.86, "elapsed_time": "1:19:19", "remaining_time": "0:31:03"} +{"current_steps": 167, "total_steps": 231, "loss": 0.1903, "lr": 4.357845844771881e-06, "epoch": 5.0606060606060606, "percentage": 72.29, "elapsed_time": "1:19:44", "remaining_time": "0:30:33"} +{"current_steps": 168, "total_steps": 231, "loss": 0.1752, "lr": 4.2331967788513295e-06, "epoch": 5.090909090909091, "percentage": 72.73, "elapsed_time": "1:20:12", "remaining_time": "0:30:04"} +{"current_steps": 169, "total_steps": 231, "loss": 0.1688, "lr": 4.109875981361363e-06, "epoch": 5.121212121212121, "percentage": 73.16, "elapsed_time": "1:20:41", "remaining_time": "0:29:36"} +{"current_steps": 170, "total_steps": 231, "loss": 0.1782, "lr": 3.987911856795047e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:21:06", "remaining_time": "0:29:06"} +{"current_steps": 171, "total_steps": 231, "loss": 0.1692, "lr": 3.867332497162836e-06, "epoch": 5.181818181818182, "percentage": 74.03, "elapsed_time": "1:21:38", "remaining_time": "0:28:38"} +{"current_steps": 172, "total_steps": 231, "loss": 0.1818, "lr": 3.748165675522113e-06, "epoch": 5.212121212121212, "percentage": 74.46, "elapsed_time": "1:22:07", "remaining_time": "0:28:10"} +{"current_steps": 173, "total_steps": 231, "loss": 0.1816, "lr": 3.630438839580217e-06, "epoch": 5.242424242424242, "percentage": 74.89, "elapsed_time": "1:22:29", "remaining_time": "0:27:39"} +{"current_steps": 174, "total_steps": 231, "loss": 0.1691, "lr": 3.5141791053724405e-06, "epoch": 5.2727272727272725, "percentage": 75.32, "elapsed_time": "1:22:56", "remaining_time": "0:27:10"} +{"current_steps": 175, "total_steps": 231, "loss": 0.1825, "lr": 3.399413251016359e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1:23:21", "remaining_time": "0:26:40"} +{"current_steps": 176, "total_steps": 231, "loss": 0.1784, "lr": 3.2861677105440335e-06, "epoch": 5.333333333333333, "percentage": 76.19, "elapsed_time": "1:23:49", "remaining_time": "0:26:11"} +{"current_steps": 177, "total_steps": 231, "loss": 0.1698, "lr": 3.174468567813461e-06, "epoch": 5.363636363636363, "percentage": 76.62, "elapsed_time": "1:24:12", "remaining_time": "0:25:41"} +{"current_steps": 178, "total_steps": 231, "loss": 0.1855, "lr": 3.0643415505006733e-06, "epoch": 5.393939393939394, "percentage": 77.06, "elapsed_time": "1:24:46", "remaining_time": "0:25:14"} +{"current_steps": 179, "total_steps": 231, "loss": 0.1835, "lr": 2.9558120241738786e-06, "epoch": 5.424242424242424, "percentage": 77.49, "elapsed_time": "1:25:15", "remaining_time": "0:24:45"} +{"current_steps": 180, "total_steps": 231, "loss": 0.1801, "lr": 2.8489049864510053e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "1:25:42", "remaining_time": "0:24:16"} +{"current_steps": 181, "total_steps": 231, "loss": 0.1727, "lr": 2.7436450612420098e-06, "epoch": 5.484848484848484, "percentage": 78.35, "elapsed_time": "1:26:09", "remaining_time": "0:23:48"} +{"current_steps": 182, "total_steps": 231, "loss": 0.176, "lr": 2.640056493077231e-06, "epoch": 5.515151515151516, "percentage": 78.79, "elapsed_time": "1:26:41", "remaining_time": "0:23:20"} +{"current_steps": 183, "total_steps": 231, "loss": 0.1879, "lr": 2.5381631415231455e-06, "epoch": 5.545454545454545, "percentage": 79.22, "elapsed_time": "1:27:14", "remaining_time": "0:22:52"} +{"current_steps": 184, "total_steps": 231, "loss": 0.1791, "lr": 2.4379884756868167e-06, "epoch": 5.575757575757576, "percentage": 79.65, "elapsed_time": "1:27:43", "remaining_time": "0:22:24"} +{"current_steps": 185, "total_steps": 231, "loss": 0.1798, "lr": 2.339555568810221e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "1:28:10", "remaining_time": "0:21:55"} +{"current_steps": 186, "total_steps": 231, "loss": 0.1879, "lr": 2.2428870929558012e-06, "epoch": 5.636363636363637, "percentage": 80.52, "elapsed_time": "1:28:37", "remaining_time": "0:21:26"} +{"current_steps": 187, "total_steps": 231, "loss": 0.1757, "lr": 2.1480053137844115e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "1:29:08", "remaining_time": "0:20:58"} +{"current_steps": 188, "total_steps": 231, "loss": 0.177, "lr": 2.054932085426856e-06, "epoch": 5.696969696969697, "percentage": 81.39, "elapsed_time": "1:29:36", "remaining_time": "0:20:29"} +{"current_steps": 189, "total_steps": 231, "loss": 0.1691, "lr": 1.963688845450218e-06, "epoch": 5.7272727272727275, "percentage": 81.82, "elapsed_time": "1:30:04", "remaining_time": "0:20:00"} +{"current_steps": 190, "total_steps": 231, "loss": 0.1729, "lr": 1.8742966099201699e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "1:30:34", "remaining_time": "0:19:32"} +{"current_steps": 191, "total_steps": 231, "loss": 0.1687, "lr": 1.7867759685603115e-06, "epoch": 5.787878787878788, "percentage": 82.68, "elapsed_time": "1:31:06", "remaining_time": "0:19:04"} +{"current_steps": 192, "total_steps": 231, "loss": 0.1811, "lr": 1.7011470800097496e-06, "epoch": 5.818181818181818, "percentage": 83.12, "elapsed_time": "1:31:35", "remaining_time": "0:18:36"} +{"current_steps": 193, "total_steps": 231, "loss": 0.1808, "lr": 1.6174296671799571e-06, "epoch": 5.848484848484849, "percentage": 83.55, "elapsed_time": "1:31:59", "remaining_time": "0:18:06"} +{"current_steps": 194, "total_steps": 231, "loss": 0.1692, "lr": 1.5356430127119915e-06, "epoch": 5.878787878787879, "percentage": 83.98, "elapsed_time": "1:32:23", "remaining_time": "0:17:37"} +{"current_steps": 195, "total_steps": 231, "loss": 0.1809, "lr": 1.4558059545351144e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "1:32:49", "remaining_time": "0:17:08"} +{"current_steps": 196, "total_steps": 231, "loss": 0.1695, "lr": 1.3779368815278648e-06, "epoch": 5.9393939393939394, "percentage": 84.85, "elapsed_time": "1:33:14", "remaining_time": "0:16:38"} +{"current_steps": 197, "total_steps": 231, "loss": 0.1795, "lr": 1.302053729282533e-06, "epoch": 5.96969696969697, "percentage": 85.28, "elapsed_time": "1:33:44", "remaining_time": "0:16:10"} +{"current_steps": 198, "total_steps": 231, "loss": 0.1638, "lr": 1.2281739759740575e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "1:34:08", "remaining_time": "0:15:41"} +{"current_steps": 199, "total_steps": 231, "loss": 0.1534, "lr": 1.156314638334277e-06, "epoch": 6.03030303030303, "percentage": 86.15, "elapsed_time": "1:35:02", "remaining_time": "0:15:17"} +{"current_steps": 200, "total_steps": 231, "loss": 0.1432, "lr": 1.086492267732462e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "1:35:28", "remaining_time": "0:14:47"} +{"current_steps": 201, "total_steps": 231, "loss": 0.1367, "lr": 1.01872294636304e-06, "epoch": 6.090909090909091, "percentage": 87.01, "elapsed_time": "1:35:55", "remaining_time": "0:14:18"} +{"current_steps": 202, "total_steps": 231, "loss": 0.1561, "lr": 9.530222835413739e-07, "epoch": 6.121212121212121, "percentage": 87.45, "elapsed_time": "1:36:21", "remaining_time": "0:13:49"} +{"current_steps": 203, "total_steps": 231, "loss": 0.1542, "lr": 8.894054121084839e-07, "epoch": 6.151515151515151, "percentage": 87.88, "elapsed_time": "1:36:45", "remaining_time": "0:13:20"} +{"current_steps": 204, "total_steps": 231, "loss": 0.1508, "lr": 8.278869849454718e-07, "epoch": 6.181818181818182, "percentage": 88.31, "elapsed_time": "1:37:12", "remaining_time": "0:12:51"} +{"current_steps": 205, "total_steps": 231, "loss": 0.1435, "lr": 7.684811715985429e-07, "epoch": 6.212121212121212, "percentage": 88.74, "elapsed_time": "1:37:36", "remaining_time": "0:12:22"} +{"current_steps": 206, "total_steps": 231, "loss": 0.1436, "lr": 7.1120165501533e-07, "epoch": 6.242424242424242, "percentage": 89.18, "elapsed_time": "1:38:02", "remaining_time": "0:11:53"} +{"current_steps": 207, "total_steps": 231, "loss": 0.1441, "lr": 6.560616283932897e-07, "epoch": 6.2727272727272725, "percentage": 89.61, "elapsed_time": "1:38:28", "remaining_time": "0:11:25"} +{"current_steps": 208, "total_steps": 231, "loss": 0.1418, "lr": 6.030737921409169e-07, "epoch": 6.303030303030303, "percentage": 90.04, "elapsed_time": "1:38:46", "remaining_time": "0:10:55"} +{"current_steps": 209, "total_steps": 231, "loss": 0.1446, "lr": 5.522503509524591e-07, "epoch": 6.333333333333333, "percentage": 90.48, "elapsed_time": "1:39:15", "remaining_time": "0:10:26"} +{"current_steps": 210, "total_steps": 231, "loss": 0.164, "lr": 5.036030109968082e-07, "epoch": 6.363636363636363, "percentage": 90.91, "elapsed_time": "1:39:48", "remaining_time": "0:09:58"} +{"current_steps": 211, "total_steps": 231, "loss": 0.1457, "lr": 4.5714297722121105e-07, "epoch": 6.393939393939394, "percentage": 91.34, "elapsed_time": "1:40:18", "remaining_time": "0:09:30"} +{"current_steps": 212, "total_steps": 231, "loss": 0.1494, "lr": 4.128809507704445e-07, "epoch": 6.424242424242424, "percentage": 91.77, "elapsed_time": "1:40:49", "remaining_time": "0:09:02"} +{"current_steps": 213, "total_steps": 231, "loss": 0.1574, "lr": 3.708271265220087e-07, "epoch": 6.454545454545454, "percentage": 92.21, "elapsed_time": "1:41:23", "remaining_time": "0:08:34"} +{"current_steps": 214, "total_steps": 231, "loss": 0.1331, "lr": 3.309911907379393e-07, "epoch": 6.484848484848484, "percentage": 92.64, "elapsed_time": "1:41:47", "remaining_time": "0:08:05"} +{"current_steps": 215, "total_steps": 231, "loss": 0.1526, "lr": 2.9338231883378365e-07, "epoch": 6.515151515151516, "percentage": 93.07, "elapsed_time": "1:42:13", "remaining_time": "0:07:36"} +{"current_steps": 216, "total_steps": 231, "loss": 0.1376, "lr": 2.5800917326521013e-07, "epoch": 6.545454545454545, "percentage": 93.51, "elapsed_time": "1:42:36", "remaining_time": "0:07:07"} +{"current_steps": 217, "total_steps": 231, "loss": 0.1438, "lr": 2.248799015327907e-07, "epoch": 6.575757575757576, "percentage": 93.94, "elapsed_time": "1:43:11", "remaining_time": "0:06:39"} +{"current_steps": 218, "total_steps": 231, "loss": 0.1377, "lr": 1.9400213430538773e-07, "epoch": 6.606060606060606, "percentage": 94.37, "elapsed_time": "1:43:40", "remaining_time": "0:06:10"} +{"current_steps": 219, "total_steps": 231, "loss": 0.1427, "lr": 1.6538298366257975e-07, "epoch": 6.636363636363637, "percentage": 94.81, "elapsed_time": "1:44:02", "remaining_time": "0:05:42"} +{"current_steps": 220, "total_steps": 231, "loss": 0.1625, "lr": 1.3902904145653094e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "1:44:33", "remaining_time": "0:05:13"} +{"current_steps": 221, "total_steps": 231, "loss": 0.1488, "lr": 1.1494637779369766e-07, "epoch": 6.696969696969697, "percentage": 95.67, "elapsed_time": "1:44:56", "remaining_time": "0:04:44"} +{"current_steps": 222, "total_steps": 231, "loss": 0.1482, "lr": 9.314053963669245e-08, "epoch": 6.7272727272727275, "percentage": 96.1, "elapsed_time": "1:45:22", "remaining_time": "0:04:16"} +{"current_steps": 223, "total_steps": 231, "loss": 0.1475, "lr": 7.361654952665608e-08, "epoch": 6.757575757575758, "percentage": 96.54, "elapsed_time": "1:45:49", "remaining_time": "0:03:47"} +{"current_steps": 224, "total_steps": 231, "loss": 0.1452, "lr": 5.637890442641403e-08, "epoch": 6.787878787878788, "percentage": 96.97, "elapsed_time": "1:46:20", "remaining_time": "0:03:19"} +{"current_steps": 225, "total_steps": 231, "loss": 0.159, "lr": 4.143157468468717e-08, "epoch": 6.818181818181818, "percentage": 97.4, "elapsed_time": "1:46:48", "remaining_time": "0:02:50"} +{"current_steps": 226, "total_steps": 231, "loss": 0.1412, "lr": 2.8778003121607834e-08, "epoch": 6.848484848484849, "percentage": 97.84, "elapsed_time": "1:47:14", "remaining_time": "0:02:22"} +{"current_steps": 227, "total_steps": 231, "loss": 0.1603, "lr": 1.8421104235727406e-08, "epoch": 6.878787878787879, "percentage": 98.27, "elapsed_time": "1:47:43", "remaining_time": "0:01:53"} +{"current_steps": 228, "total_steps": 231, "loss": 0.1396, "lr": 1.0363263532724433e-08, "epoch": 6.909090909090909, "percentage": 98.7, "elapsed_time": "1:48:09", "remaining_time": "0:01:25"} +{"current_steps": 229, "total_steps": 231, "loss": 0.1491, "lr": 4.606336975948589e-09, "epoch": 6.9393939393939394, "percentage": 99.13, "elapsed_time": "1:48:35", "remaining_time": "0:00:56"} +{"current_steps": 230, "total_steps": 231, "loss": 0.1509, "lr": 1.1516505589381777e-09, "epoch": 6.96969696969697, "percentage": 99.57, "elapsed_time": "1:48:57", "remaining_time": "0:00:28"} +{"current_steps": 231, "total_steps": 231, "loss": 0.1549, "lr": 0.0, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "1:49:25", "remaining_time": "0:00:00"} +{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "1:50:15", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..d109dbc --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,1659 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 7.0, + "eval_steps": 500, + "global_step": 231, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.030303030303030304, + "grad_norm": 6.133312490270507, + "learning_rate": 8.333333333333333e-07, + "loss": 0.9888, + "step": 1 + }, + { + "epoch": 0.06060606060606061, + "grad_norm": 6.312267353299651, + "learning_rate": 1.6666666666666667e-06, + "loss": 1.0105, + "step": 2 + }, + { + "epoch": 0.09090909090909091, + "grad_norm": 6.208055389022369, + "learning_rate": 2.5e-06, + "loss": 0.984, + "step": 3 + }, + { + "epoch": 0.12121212121212122, + "grad_norm": 5.675461956735031, + "learning_rate": 3.3333333333333333e-06, + "loss": 0.9786, + "step": 4 + }, + { + "epoch": 0.15151515151515152, + "grad_norm": 4.66177066597852, + "learning_rate": 4.166666666666667e-06, + "loss": 1.0105, + "step": 5 + }, + { + "epoch": 0.18181818181818182, + "grad_norm": 2.293639946463445, + "learning_rate": 5e-06, + "loss": 0.8871, + "step": 6 + }, + { + "epoch": 0.21212121212121213, + "grad_norm": 1.9003604297261614, + "learning_rate": 5.833333333333334e-06, + "loss": 0.862, + "step": 7 + }, + { + "epoch": 0.24242424242424243, + "grad_norm": 4.34057790860278, + "learning_rate": 6.666666666666667e-06, + "loss": 0.9222, + "step": 8 + }, + { + "epoch": 0.2727272727272727, + "grad_norm": 4.481914051352927, + "learning_rate": 7.500000000000001e-06, + "loss": 0.88, + "step": 9 + }, + { + "epoch": 0.30303030303030304, + "grad_norm": 4.54495940680815, + "learning_rate": 8.333333333333334e-06, + "loss": 0.873, + "step": 10 + }, + { + "epoch": 0.3333333333333333, + "grad_norm": 3.7670378642227913, + "learning_rate": 9.166666666666666e-06, + "loss": 0.8166, + "step": 11 + }, + { + "epoch": 0.36363636363636365, + "grad_norm": 3.8526941144194042, + "learning_rate": 1e-05, + "loss": 0.9013, + "step": 12 + }, + { + "epoch": 0.3939393939393939, + "grad_norm": 2.461756702762672, + "learning_rate": 1.0833333333333334e-05, + "loss": 0.7934, + "step": 13 + }, + { + "epoch": 0.42424242424242425, + "grad_norm": 2.020047328008979, + "learning_rate": 1.1666666666666668e-05, + "loss": 0.8134, + "step": 14 + }, + { + "epoch": 0.45454545454545453, + "grad_norm": 2.339950318674221, + "learning_rate": 1.25e-05, + "loss": 0.7884, + "step": 15 + }, + { + "epoch": 0.48484848484848486, + "grad_norm": 2.3738008055129898, + "learning_rate": 1.3333333333333333e-05, + "loss": 0.7986, + "step": 16 + }, + { + "epoch": 0.5151515151515151, + "grad_norm": 2.08368208039381, + "learning_rate": 1.416666666666667e-05, + "loss": 0.7553, + "step": 17 + }, + { + "epoch": 0.5454545454545454, + "grad_norm": 1.5151847330974046, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.7819, + "step": 18 + }, + { + "epoch": 0.5757575757575758, + "grad_norm": 1.4130438397580987, + "learning_rate": 1.5833333333333333e-05, + "loss": 0.757, + "step": 19 + }, + { + "epoch": 0.6060606060606061, + "grad_norm": 1.5602523903739551, + "learning_rate": 1.6666666666666667e-05, + "loss": 0.7117, + "step": 20 + }, + { + "epoch": 0.6363636363636364, + "grad_norm": 1.1219040774993525, + "learning_rate": 1.7500000000000002e-05, + "loss": 0.7214, + "step": 21 + }, + { + "epoch": 0.6666666666666666, + "grad_norm": 1.225922434964794, + "learning_rate": 1.8333333333333333e-05, + "loss": 0.7587, + "step": 22 + }, + { + "epoch": 0.696969696969697, + "grad_norm": 1.1494919772986516, + "learning_rate": 1.916666666666667e-05, + "loss": 0.6967, + "step": 23 + }, + { + "epoch": 0.7272727272727273, + "grad_norm": 1.1189446177809441, + "learning_rate": 2e-05, + "loss": 0.7407, + "step": 24 + }, + { + "epoch": 0.7575757575757576, + "grad_norm": 0.8390109807203933, + "learning_rate": 1.999884834944106e-05, + "loss": 0.741, + "step": 25 + }, + { + "epoch": 0.7878787878787878, + "grad_norm": 1.007712076574321, + "learning_rate": 1.9995393663024054e-05, + "loss": 0.7249, + "step": 26 + }, + { + "epoch": 0.8181818181818182, + "grad_norm": 0.7348503701924564, + "learning_rate": 1.9989636736467278e-05, + "loss": 0.6793, + "step": 27 + }, + { + "epoch": 0.8484848484848485, + "grad_norm": 0.8109780365875735, + "learning_rate": 1.9981578895764272e-05, + "loss": 0.6822, + "step": 28 + }, + { + "epoch": 0.8787878787878788, + "grad_norm": 0.9304526383993851, + "learning_rate": 1.9971221996878395e-05, + "loss": 0.7035, + "step": 29 + }, + { + "epoch": 0.9090909090909091, + "grad_norm": 0.8529935025494286, + "learning_rate": 1.9958568425315316e-05, + "loss": 0.7038, + "step": 30 + }, + { + "epoch": 0.9393939393939394, + "grad_norm": 0.7556881934557372, + "learning_rate": 1.9943621095573588e-05, + "loss": 0.6911, + "step": 31 + }, + { + "epoch": 0.9696969696969697, + "grad_norm": 0.7735812382379526, + "learning_rate": 1.9926383450473344e-05, + "loss": 0.679, + "step": 32 + }, + { + "epoch": 1.0, + "grad_norm": 0.6923641401736521, + "learning_rate": 1.9906859460363307e-05, + "loss": 0.6661, + "step": 33 + }, + { + "epoch": 1.0303030303030303, + "grad_norm": 0.6826580303946777, + "learning_rate": 1.9885053622206305e-05, + "loss": 0.6344, + "step": 34 + }, + { + "epoch": 1.0606060606060606, + "grad_norm": 0.6878400013541692, + "learning_rate": 1.986097095854347e-05, + "loss": 0.6168, + "step": 35 + }, + { + "epoch": 1.0909090909090908, + "grad_norm": 0.6308834404286537, + "learning_rate": 1.9834617016337424e-05, + "loss": 0.6138, + "step": 36 + }, + { + "epoch": 1.121212121212121, + "grad_norm": 0.8855682900976705, + "learning_rate": 1.9805997865694616e-05, + "loss": 0.6027, + "step": 37 + }, + { + "epoch": 1.1515151515151516, + "grad_norm": 0.650276286498742, + "learning_rate": 1.9775120098467212e-05, + "loss": 0.6063, + "step": 38 + }, + { + "epoch": 1.1818181818181819, + "grad_norm": 0.9241353438375617, + "learning_rate": 1.9741990826734793e-05, + "loss": 0.6487, + "step": 39 + }, + { + "epoch": 1.2121212121212122, + "grad_norm": 0.6131304185741522, + "learning_rate": 1.970661768116622e-05, + "loss": 0.6125, + "step": 40 + }, + { + "epoch": 1.2424242424242424, + "grad_norm": 0.9638298028620941, + "learning_rate": 1.9669008809262064e-05, + "loss": 0.6375, + "step": 41 + }, + { + "epoch": 1.2727272727272727, + "grad_norm": 0.6864083028962933, + "learning_rate": 1.9629172873477995e-05, + "loss": 0.6064, + "step": 42 + }, + { + "epoch": 1.303030303030303, + "grad_norm": 0.6541942252236372, + "learning_rate": 1.9587119049229558e-05, + "loss": 0.5929, + "step": 43 + }, + { + "epoch": 1.3333333333333333, + "grad_norm": 0.591616863460495, + "learning_rate": 1.954285702277879e-05, + "loss": 0.5862, + "step": 44 + }, + { + "epoch": 1.3636363636363638, + "grad_norm": 0.5788113217386186, + "learning_rate": 1.9496396989003195e-05, + "loss": 0.6165, + "step": 45 + }, + { + "epoch": 1.393939393939394, + "grad_norm": 0.5825389483651302, + "learning_rate": 1.944774964904754e-05, + "loss": 0.6011, + "step": 46 + }, + { + "epoch": 1.4242424242424243, + "grad_norm": 0.5950620245349484, + "learning_rate": 1.9396926207859085e-05, + "loss": 0.6157, + "step": 47 + }, + { + "epoch": 1.4545454545454546, + "grad_norm": 0.548727099377894, + "learning_rate": 1.9343938371606714e-05, + "loss": 0.5794, + "step": 48 + }, + { + "epoch": 1.4848484848484849, + "grad_norm": 0.5785459402189005, + "learning_rate": 1.9288798344984673e-05, + "loss": 0.6099, + "step": 49 + }, + { + "epoch": 1.5151515151515151, + "grad_norm": 0.6969881421938213, + "learning_rate": 1.9231518828401458e-05, + "loss": 0.6181, + "step": 50 + }, + { + "epoch": 1.5454545454545454, + "grad_norm": 0.6014346704940163, + "learning_rate": 1.917211301505453e-05, + "loss": 0.6061, + "step": 51 + }, + { + "epoch": 1.5757575757575757, + "grad_norm": 0.557203444582592, + "learning_rate": 1.911059458789152e-05, + "loss": 0.577, + "step": 52 + }, + { + "epoch": 1.606060606060606, + "grad_norm": 0.6238802409413811, + "learning_rate": 1.9046977716458627e-05, + "loss": 0.633, + "step": 53 + }, + { + "epoch": 1.6363636363636362, + "grad_norm": 0.5908668210103087, + "learning_rate": 1.8981277053636963e-05, + "loss": 0.5868, + "step": 54 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 0.6377646074733742, + "learning_rate": 1.891350773226754e-05, + "loss": 0.5837, + "step": 55 + }, + { + "epoch": 1.696969696969697, + "grad_norm": 0.6706654613912634, + "learning_rate": 1.8843685361665724e-05, + "loss": 0.6058, + "step": 56 + }, + { + "epoch": 1.7272727272727273, + "grad_norm": 0.7135082134395438, + "learning_rate": 1.8771826024025944e-05, + "loss": 0.6108, + "step": 57 + }, + { + "epoch": 1.7575757575757576, + "grad_norm": 0.6613757784482449, + "learning_rate": 1.8697946270717468e-05, + "loss": 0.6089, + "step": 58 + }, + { + "epoch": 1.7878787878787878, + "grad_norm": 0.5892114524066855, + "learning_rate": 1.8622063118472135e-05, + "loss": 0.5978, + "step": 59 + }, + { + "epoch": 1.8181818181818183, + "grad_norm": 0.613752632598102, + "learning_rate": 1.8544194045464888e-05, + "loss": 0.5784, + "step": 60 + }, + { + "epoch": 1.8484848484848486, + "grad_norm": 0.6533078225121903, + "learning_rate": 1.8464356987288012e-05, + "loss": 0.5652, + "step": 61 + }, + { + "epoch": 1.878787878787879, + "grad_norm": 0.5268805797122355, + "learning_rate": 1.8382570332820045e-05, + "loss": 0.5551, + "step": 62 + }, + { + "epoch": 1.9090909090909092, + "grad_norm": 0.5718376684652964, + "learning_rate": 1.8298852919990254e-05, + "loss": 0.5993, + "step": 63 + }, + { + "epoch": 1.9393939393939394, + "grad_norm": 0.5681556224844309, + "learning_rate": 1.821322403143969e-05, + "loss": 0.6061, + "step": 64 + }, + { + "epoch": 1.9696969696969697, + "grad_norm": 0.5160510923850339, + "learning_rate": 1.812570339007983e-05, + "loss": 0.539, + "step": 65 + }, + { + "epoch": 2.0, + "grad_norm": 0.5808021119660712, + "learning_rate": 1.8036311154549783e-05, + "loss": 0.5604, + "step": 66 + }, + { + "epoch": 2.0303030303030303, + "grad_norm": 0.6969394228030072, + "learning_rate": 1.7945067914573147e-05, + "loss": 0.4949, + "step": 67 + }, + { + "epoch": 2.0606060606060606, + "grad_norm": 0.5831869434691073, + "learning_rate": 1.7851994686215592e-05, + "loss": 0.4799, + "step": 68 + }, + { + "epoch": 2.090909090909091, + "grad_norm": 0.8189090133243225, + "learning_rate": 1.77571129070442e-05, + "loss": 0.4757, + "step": 69 + }, + { + "epoch": 2.121212121212121, + "grad_norm": 0.6924137717196174, + "learning_rate": 1.766044443118978e-05, + "loss": 0.45, + "step": 70 + }, + { + "epoch": 2.1515151515151514, + "grad_norm": 0.5579284812500711, + "learning_rate": 1.7562011524313187e-05, + "loss": 0.4652, + "step": 71 + }, + { + "epoch": 2.1818181818181817, + "grad_norm": 0.7280937667428176, + "learning_rate": 1.7461836858476858e-05, + "loss": 0.4853, + "step": 72 + }, + { + "epoch": 2.212121212121212, + "grad_norm": 0.5542550746479272, + "learning_rate": 1.7359943506922775e-05, + "loss": 0.4642, + "step": 73 + }, + { + "epoch": 2.242424242424242, + "grad_norm": 0.6427517726580945, + "learning_rate": 1.725635493875799e-05, + "loss": 0.4558, + "step": 74 + }, + { + "epoch": 2.2727272727272725, + "grad_norm": 0.5769363799510141, + "learning_rate": 1.7151095013548996e-05, + "loss": 0.448, + "step": 75 + }, + { + "epoch": 2.303030303030303, + "grad_norm": 0.6236420369243885, + "learning_rate": 1.7044187975826126e-05, + "loss": 0.4539, + "step": 76 + }, + { + "epoch": 2.3333333333333335, + "grad_norm": 0.5495637430654123, + "learning_rate": 1.693565844949933e-05, + "loss": 0.4505, + "step": 77 + }, + { + "epoch": 2.3636363636363638, + "grad_norm": 0.6462062247160016, + "learning_rate": 1.6825531432186545e-05, + "loss": 0.4683, + "step": 78 + }, + { + "epoch": 2.393939393939394, + "grad_norm": 0.4938607242900449, + "learning_rate": 1.671383228945597e-05, + "loss": 0.4446, + "step": 79 + }, + { + "epoch": 2.4242424242424243, + "grad_norm": 0.7982112275998522, + "learning_rate": 1.6600586748983642e-05, + "loss": 0.4697, + "step": 80 + }, + { + "epoch": 2.4545454545454546, + "grad_norm": 0.5745468299818484, + "learning_rate": 1.648582089462756e-05, + "loss": 0.4585, + "step": 81 + }, + { + "epoch": 2.484848484848485, + "grad_norm": 0.5564417346991974, + "learning_rate": 1.6369561160419783e-05, + "loss": 0.4643, + "step": 82 + }, + { + "epoch": 2.515151515151515, + "grad_norm": 0.49905270942102536, + "learning_rate": 1.625183432447789e-05, + "loss": 0.4602, + "step": 83 + }, + { + "epoch": 2.5454545454545454, + "grad_norm": 0.4796081226277374, + "learning_rate": 1.6132667502837164e-05, + "loss": 0.4655, + "step": 84 + }, + { + "epoch": 2.5757575757575757, + "grad_norm": 0.4927738870874845, + "learning_rate": 1.6012088143204953e-05, + "loss": 0.4538, + "step": 85 + }, + { + "epoch": 2.606060606060606, + "grad_norm": 0.5180099965159457, + "learning_rate": 1.589012401863864e-05, + "loss": 0.458, + "step": 86 + }, + { + "epoch": 2.6363636363636362, + "grad_norm": 0.5296320750810951, + "learning_rate": 1.5766803221148676e-05, + "loss": 0.4493, + "step": 87 + }, + { + "epoch": 2.6666666666666665, + "grad_norm": 0.5733112965300271, + "learning_rate": 1.5642154155228124e-05, + "loss": 0.4686, + "step": 88 + }, + { + "epoch": 2.6969696969696972, + "grad_norm": 0.5741347142903017, + "learning_rate": 1.5516205531310272e-05, + "loss": 0.4583, + "step": 89 + }, + { + "epoch": 2.7272727272727275, + "grad_norm": 0.48174318336790667, + "learning_rate": 1.538898635915576e-05, + "loss": 0.4425, + "step": 90 + }, + { + "epoch": 2.757575757575758, + "grad_norm": 0.5590385352635306, + "learning_rate": 1.526052594117071e-05, + "loss": 0.4464, + "step": 91 + }, + { + "epoch": 2.787878787878788, + "grad_norm": 0.485518620325785, + "learning_rate": 1.513085386565758e-05, + "loss": 0.4436, + "step": 92 + }, + { + "epoch": 2.8181818181818183, + "grad_norm": 0.49380448272343497, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.4591, + "step": 93 + }, + { + "epoch": 2.8484848484848486, + "grad_norm": 0.5571812552248251, + "learning_rate": 1.4867994483783485e-05, + "loss": 0.4721, + "step": 94 + }, + { + "epoch": 2.878787878787879, + "grad_norm": 0.5230295468295674, + "learning_rate": 1.4734867721853341e-05, + "loss": 0.4649, + "step": 95 + }, + { + "epoch": 2.909090909090909, + "grad_norm": 0.5089127017794696, + "learning_rate": 1.4600650377311523e-05, + "loss": 0.4814, + "step": 96 + }, + { + "epoch": 2.9393939393939394, + "grad_norm": 0.5105539748113577, + "learning_rate": 1.4465373364454001e-05, + "loss": 0.4503, + "step": 97 + }, + { + "epoch": 2.9696969696969697, + "grad_norm": 0.45069990743245353, + "learning_rate": 1.4329067841650274e-05, + "loss": 0.4387, + "step": 98 + }, + { + "epoch": 3.0, + "grad_norm": 0.5033861625442646, + "learning_rate": 1.4191765204166643e-05, + "loss": 0.4538, + "step": 99 + }, + { + "epoch": 3.0303030303030303, + "grad_norm": 0.7754730175625122, + "learning_rate": 1.4053497076934948e-05, + "loss": 0.3659, + "step": 100 + }, + { + "epoch": 3.0606060606060606, + "grad_norm": 0.5140533227089905, + "learning_rate": 1.3914295307268396e-05, + "loss": 0.3641, + "step": 101 + }, + { + "epoch": 3.090909090909091, + "grad_norm": 0.9403979311007741, + "learning_rate": 1.3774191957526144e-05, + "loss": 0.3546, + "step": 102 + }, + { + "epoch": 3.121212121212121, + "grad_norm": 0.8010927180149187, + "learning_rate": 1.3633219297728415e-05, + "loss": 0.3555, + "step": 103 + }, + { + "epoch": 3.1515151515151514, + "grad_norm": 0.6970449984340281, + "learning_rate": 1.3491409798123687e-05, + "loss": 0.3413, + "step": 104 + }, + { + "epoch": 3.1818181818181817, + "grad_norm": 0.6812848683097438, + "learning_rate": 1.3348796121709862e-05, + "loss": 0.3495, + "step": 105 + }, + { + "epoch": 3.212121212121212, + "grad_norm": 0.7872828399093813, + "learning_rate": 1.3205411116710973e-05, + "loss": 0.3461, + "step": 106 + }, + { + "epoch": 3.242424242424242, + "grad_norm": 0.6352287831348774, + "learning_rate": 1.3061287809011243e-05, + "loss": 0.3422, + "step": 107 + }, + { + "epoch": 3.2727272727272725, + "grad_norm": 0.5371263304613854, + "learning_rate": 1.291645939454825e-05, + "loss": 0.3297, + "step": 108 + }, + { + "epoch": 3.303030303030303, + "grad_norm": 0.6106232841146089, + "learning_rate": 1.277095923166689e-05, + "loss": 0.3369, + "step": 109 + }, + { + "epoch": 3.3333333333333335, + "grad_norm": 0.5764495175042285, + "learning_rate": 1.2624820833435939e-05, + "loss": 0.3432, + "step": 110 + }, + { + "epoch": 3.3636363636363638, + "grad_norm": 0.5189044479833499, + "learning_rate": 1.2478077859929e-05, + "loss": 0.3225, + "step": 111 + }, + { + "epoch": 3.393939393939394, + "grad_norm": 0.5420009037776947, + "learning_rate": 1.2330764110471567e-05, + "loss": 0.3335, + "step": 112 + }, + { + "epoch": 3.4242424242424243, + "grad_norm": 0.4862496515664332, + "learning_rate": 1.2182913515856016e-05, + "loss": 0.3318, + "step": 113 + }, + { + "epoch": 3.4545454545454546, + "grad_norm": 0.5090167554828083, + "learning_rate": 1.2034560130526341e-05, + "loss": 0.3494, + "step": 114 + }, + { + "epoch": 3.484848484848485, + "grad_norm": 0.4911623919328435, + "learning_rate": 1.1885738124734359e-05, + "loss": 0.3275, + "step": 115 + }, + { + "epoch": 3.515151515151515, + "grad_norm": 0.5045605919032637, + "learning_rate": 1.1736481776669307e-05, + "loss": 0.3572, + "step": 116 + }, + { + "epoch": 3.5454545454545454, + "grad_norm": 0.504947761060277, + "learning_rate": 1.1586825464562515e-05, + "loss": 0.3451, + "step": 117 + }, + { + "epoch": 3.5757575757575757, + "grad_norm": 0.4882425876038978, + "learning_rate": 1.1436803658769082e-05, + "loss": 0.3544, + "step": 118 + }, + { + "epoch": 3.606060606060606, + "grad_norm": 0.4850349784810182, + "learning_rate": 1.1286450913828313e-05, + "loss": 0.3193, + "step": 119 + }, + { + "epoch": 3.6363636363636362, + "grad_norm": 0.5320436358006013, + "learning_rate": 1.113580186050475e-05, + "loss": 0.3453, + "step": 120 + }, + { + "epoch": 3.6666666666666665, + "grad_norm": 0.4825025254463151, + "learning_rate": 1.0984891197811686e-05, + "loss": 0.3395, + "step": 121 + }, + { + "epoch": 3.6969696969696972, + "grad_norm": 0.47238049685696304, + "learning_rate": 1.0833753685018935e-05, + "loss": 0.3281, + "step": 122 + }, + { + "epoch": 3.7272727272727275, + "grad_norm": 0.5347752627285653, + "learning_rate": 1.0682424133646712e-05, + "loss": 0.3402, + "step": 123 + }, + { + "epoch": 3.757575757575758, + "grad_norm": 0.4948810103681615, + "learning_rate": 1.0530937399447496e-05, + "loss": 0.3336, + "step": 124 + }, + { + "epoch": 3.787878787878788, + "grad_norm": 0.5191359531791342, + "learning_rate": 1.0379328374377715e-05, + "loss": 0.347, + "step": 125 + }, + { + "epoch": 3.8181818181818183, + "grad_norm": 0.4176553849951949, + "learning_rate": 1.0227631978561057e-05, + "loss": 0.3479, + "step": 126 + }, + { + "epoch": 3.8484848484848486, + "grad_norm": 0.5299308743413071, + "learning_rate": 1.0075883152245334e-05, + "loss": 0.345, + "step": 127 + }, + { + "epoch": 3.878787878787879, + "grad_norm": 0.46549440438780987, + "learning_rate": 9.92411684775467e-06, + "loss": 0.3178, + "step": 128 + }, + { + "epoch": 3.909090909090909, + "grad_norm": 0.4758499117360986, + "learning_rate": 9.772368021438943e-06, + "loss": 0.3395, + "step": 129 + }, + { + "epoch": 3.9393939393939394, + "grad_norm": 0.44324711245538406, + "learning_rate": 9.620671625622287e-06, + "loss": 0.3375, + "step": 130 + }, + { + "epoch": 3.9696969696969697, + "grad_norm": 0.47116040531641634, + "learning_rate": 9.469062600552509e-06, + "loss": 0.3341, + "step": 131 + }, + { + "epoch": 4.0, + "grad_norm": 0.43818067708802083, + "learning_rate": 9.317575866353293e-06, + "loss": 0.3234, + "step": 132 + }, + { + "epoch": 4.03030303030303, + "grad_norm": 0.737485769336963, + "learning_rate": 9.166246314981066e-06, + "loss": 0.2627, + "step": 133 + }, + { + "epoch": 4.0606060606060606, + "grad_norm": 0.5529080776552364, + "learning_rate": 9.015108802188314e-06, + "loss": 0.26, + "step": 134 + }, + { + "epoch": 4.090909090909091, + "grad_norm": 0.48080243212121565, + "learning_rate": 8.86419813949525e-06, + "loss": 0.2552, + "step": 135 + }, + { + "epoch": 4.121212121212121, + "grad_norm": 0.7350512487406256, + "learning_rate": 8.71354908617169e-06, + "loss": 0.2405, + "step": 136 + }, + { + "epoch": 4.151515151515151, + "grad_norm": 0.7784132067101827, + "learning_rate": 8.56319634123092e-06, + "loss": 0.2572, + "step": 137 + }, + { + "epoch": 4.181818181818182, + "grad_norm": 0.46727652708176803, + "learning_rate": 8.413174535437486e-06, + "loss": 0.224, + "step": 138 + }, + { + "epoch": 4.212121212121212, + "grad_norm": 0.512190716791503, + "learning_rate": 8.263518223330698e-06, + "loss": 0.2409, + "step": 139 + }, + { + "epoch": 4.242424242424242, + "grad_norm": 0.6123196750859912, + "learning_rate": 8.114261875265643e-06, + "loss": 0.2375, + "step": 140 + }, + { + "epoch": 4.2727272727272725, + "grad_norm": 0.5069870710442763, + "learning_rate": 7.965439869473664e-06, + "loss": 0.2547, + "step": 141 + }, + { + "epoch": 4.303030303030303, + "grad_norm": 0.4849101223324498, + "learning_rate": 7.817086484143987e-06, + "loss": 0.2483, + "step": 142 + }, + { + "epoch": 4.333333333333333, + "grad_norm": 0.48073299903189964, + "learning_rate": 7.669235889528436e-06, + "loss": 0.2383, + "step": 143 + }, + { + "epoch": 4.363636363636363, + "grad_norm": 0.5040942298901941, + "learning_rate": 7.521922140071003e-06, + "loss": 0.2337, + "step": 144 + }, + { + "epoch": 4.393939393939394, + "grad_norm": 0.5174058357260617, + "learning_rate": 7.375179166564062e-06, + "loss": 0.2416, + "step": 145 + }, + { + "epoch": 4.424242424242424, + "grad_norm": 0.5263164387363304, + "learning_rate": 7.2290407683331154e-06, + "loss": 0.2352, + "step": 146 + }, + { + "epoch": 4.454545454545454, + "grad_norm": 0.48585757237463617, + "learning_rate": 7.0835406054517505e-06, + "loss": 0.2248, + "step": 147 + }, + { + "epoch": 4.484848484848484, + "grad_norm": 0.456902311560064, + "learning_rate": 6.93871219098876e-06, + "loss": 0.2446, + "step": 148 + }, + { + "epoch": 4.515151515151516, + "grad_norm": 0.4647131059560458, + "learning_rate": 6.79458888328903e-06, + "loss": 0.2389, + "step": 149 + }, + { + "epoch": 4.545454545454545, + "grad_norm": 0.43264056127979783, + "learning_rate": 6.651203878290139e-06, + "loss": 0.2574, + "step": 150 + }, + { + "epoch": 4.575757575757576, + "grad_norm": 0.45526716122106875, + "learning_rate": 6.508590201876317e-06, + "loss": 0.2376, + "step": 151 + }, + { + "epoch": 4.606060606060606, + "grad_norm": 0.46874751338386467, + "learning_rate": 6.366780702271589e-06, + "loss": 0.2559, + "step": 152 + }, + { + "epoch": 4.636363636363637, + "grad_norm": 0.457100921015383, + "learning_rate": 6.225808042473857e-06, + "loss": 0.2514, + "step": 153 + }, + { + "epoch": 4.666666666666667, + "grad_norm": 0.4605869515605553, + "learning_rate": 6.085704692731609e-06, + "loss": 0.2362, + "step": 154 + }, + { + "epoch": 4.696969696969697, + "grad_norm": 0.4473331033802291, + "learning_rate": 5.946502923065054e-06, + "loss": 0.2323, + "step": 155 + }, + { + "epoch": 4.7272727272727275, + "grad_norm": 0.42628612014612893, + "learning_rate": 5.8082347958333625e-06, + "loss": 0.2407, + "step": 156 + }, + { + "epoch": 4.757575757575758, + "grad_norm": 0.41450115644914304, + "learning_rate": 5.670932158349732e-06, + "loss": 0.2424, + "step": 157 + }, + { + "epoch": 4.787878787878788, + "grad_norm": 0.4055025538345423, + "learning_rate": 5.534626635546e-06, + "loss": 0.2375, + "step": 158 + }, + { + "epoch": 4.818181818181818, + "grad_norm": 0.44529585756329015, + "learning_rate": 5.399349622688479e-06, + "loss": 0.2308, + "step": 159 + }, + { + "epoch": 4.848484848484849, + "grad_norm": 0.4471917638100028, + "learning_rate": 5.2651322781466606e-06, + "loss": 0.234, + "step": 160 + }, + { + "epoch": 4.878787878787879, + "grad_norm": 0.4223307232900756, + "learning_rate": 5.132005516216512e-06, + "loss": 0.2426, + "step": 161 + }, + { + "epoch": 4.909090909090909, + "grad_norm": 0.4372133744429308, + "learning_rate": 5.000000000000003e-06, + "loss": 0.2258, + "step": 162 + }, + { + "epoch": 4.9393939393939394, + "grad_norm": 0.4420625006970779, + "learning_rate": 4.869146134342426e-06, + "loss": 0.2457, + "step": 163 + }, + { + "epoch": 4.96969696969697, + "grad_norm": 0.41903834567451254, + "learning_rate": 4.739474058829288e-06, + "loss": 0.2447, + "step": 164 + }, + { + "epoch": 5.0, + "grad_norm": 0.41220312098219003, + "learning_rate": 4.611013640844245e-06, + "loss": 0.2394, + "step": 165 + }, + { + "epoch": 5.03030303030303, + "grad_norm": 0.6003100588562155, + "learning_rate": 4.483794468689728e-06, + "loss": 0.1735, + "step": 166 + }, + { + "epoch": 5.0606060606060606, + "grad_norm": 0.5648306970051146, + "learning_rate": 4.357845844771881e-06, + "loss": 0.1903, + "step": 167 + }, + { + "epoch": 5.090909090909091, + "grad_norm": 0.42700456514849605, + "learning_rate": 4.2331967788513295e-06, + "loss": 0.1752, + "step": 168 + }, + { + "epoch": 5.121212121212121, + "grad_norm": 0.42202181300842884, + "learning_rate": 4.109875981361363e-06, + "loss": 0.1688, + "step": 169 + }, + { + "epoch": 5.151515151515151, + "grad_norm": 0.5838409787441209, + "learning_rate": 3.987911856795047e-06, + "loss": 0.1782, + "step": 170 + }, + { + "epoch": 5.181818181818182, + "grad_norm": 0.6457145473441536, + "learning_rate": 3.867332497162836e-06, + "loss": 0.1692, + "step": 171 + }, + { + "epoch": 5.212121212121212, + "grad_norm": 0.5629897276540763, + "learning_rate": 3.748165675522113e-06, + "loss": 0.1818, + "step": 172 + }, + { + "epoch": 5.242424242424242, + "grad_norm": 0.4578791065982633, + "learning_rate": 3.630438839580217e-06, + "loss": 0.1816, + "step": 173 + }, + { + "epoch": 5.2727272727272725, + "grad_norm": 0.4244633490788637, + "learning_rate": 3.5141791053724405e-06, + "loss": 0.1691, + "step": 174 + }, + { + "epoch": 5.303030303030303, + "grad_norm": 0.43707284617669917, + "learning_rate": 3.399413251016359e-06, + "loss": 0.1825, + "step": 175 + }, + { + "epoch": 5.333333333333333, + "grad_norm": 0.4660244768094549, + "learning_rate": 3.2861677105440335e-06, + "loss": 0.1784, + "step": 176 + }, + { + "epoch": 5.363636363636363, + "grad_norm": 0.45078401522152955, + "learning_rate": 3.174468567813461e-06, + "loss": 0.1698, + "step": 177 + }, + { + "epoch": 5.393939393939394, + "grad_norm": 0.4465656518722392, + "learning_rate": 3.0643415505006733e-06, + "loss": 0.1855, + "step": 178 + }, + { + "epoch": 5.424242424242424, + "grad_norm": 0.43625841204668764, + "learning_rate": 2.9558120241738786e-06, + "loss": 0.1835, + "step": 179 + }, + { + "epoch": 5.454545454545454, + "grad_norm": 0.40736478162641304, + "learning_rate": 2.8489049864510053e-06, + "loss": 0.1801, + "step": 180 + }, + { + "epoch": 5.484848484848484, + "grad_norm": 0.3747193980913415, + "learning_rate": 2.7436450612420098e-06, + "loss": 0.1727, + "step": 181 + }, + { + "epoch": 5.515151515151516, + "grad_norm": 0.39608234441553114, + "learning_rate": 2.640056493077231e-06, + "loss": 0.176, + "step": 182 + }, + { + "epoch": 5.545454545454545, + "grad_norm": 0.41959398355677646, + "learning_rate": 2.5381631415231455e-06, + "loss": 0.1879, + "step": 183 + }, + { + "epoch": 5.575757575757576, + "grad_norm": 0.4254934910328529, + "learning_rate": 2.4379884756868167e-06, + "loss": 0.1791, + "step": 184 + }, + { + "epoch": 5.606060606060606, + "grad_norm": 0.4124792487276637, + "learning_rate": 2.339555568810221e-06, + "loss": 0.1798, + "step": 185 + }, + { + "epoch": 5.636363636363637, + "grad_norm": 0.40905699809266405, + "learning_rate": 2.2428870929558012e-06, + "loss": 0.1879, + "step": 186 + }, + { + "epoch": 5.666666666666667, + "grad_norm": 0.439209399354481, + "learning_rate": 2.1480053137844115e-06, + "loss": 0.1757, + "step": 187 + }, + { + "epoch": 5.696969696969697, + "grad_norm": 0.38866717217479696, + "learning_rate": 2.054932085426856e-06, + "loss": 0.177, + "step": 188 + }, + { + "epoch": 5.7272727272727275, + "grad_norm": 0.3877198550366768, + "learning_rate": 1.963688845450218e-06, + "loss": 0.1691, + "step": 189 + }, + { + "epoch": 5.757575757575758, + "grad_norm": 0.38937605220810684, + "learning_rate": 1.8742966099201699e-06, + "loss": 0.1729, + "step": 190 + }, + { + "epoch": 5.787878787878788, + "grad_norm": 0.3931967989696538, + "learning_rate": 1.7867759685603115e-06, + "loss": 0.1687, + "step": 191 + }, + { + "epoch": 5.818181818181818, + "grad_norm": 0.4063426644619139, + "learning_rate": 1.7011470800097496e-06, + "loss": 0.1811, + "step": 192 + }, + { + "epoch": 5.848484848484849, + "grad_norm": 0.3987773436262393, + "learning_rate": 1.6174296671799571e-06, + "loss": 0.1808, + "step": 193 + }, + { + "epoch": 5.878787878787879, + "grad_norm": 0.42485860526619407, + "learning_rate": 1.5356430127119915e-06, + "loss": 0.1692, + "step": 194 + }, + { + "epoch": 5.909090909090909, + "grad_norm": 0.3865913121103735, + "learning_rate": 1.4558059545351144e-06, + "loss": 0.1809, + "step": 195 + }, + { + "epoch": 5.9393939393939394, + "grad_norm": 0.4087920786517138, + "learning_rate": 1.3779368815278648e-06, + "loss": 0.1695, + "step": 196 + }, + { + "epoch": 5.96969696969697, + "grad_norm": 0.3774266154893843, + "learning_rate": 1.302053729282533e-06, + "loss": 0.1795, + "step": 197 + }, + { + "epoch": 6.0, + "grad_norm": 0.4076951621470744, + "learning_rate": 1.2281739759740575e-06, + "loss": 0.1638, + "step": 198 + }, + { + "epoch": 6.03030303030303, + "grad_norm": 0.45466301759345923, + "learning_rate": 1.156314638334277e-06, + "loss": 0.1534, + "step": 199 + }, + { + "epoch": 6.0606060606060606, + "grad_norm": 0.4323237765282992, + "learning_rate": 1.086492267732462e-06, + "loss": 0.1432, + "step": 200 + }, + { + "epoch": 6.090909090909091, + "grad_norm": 0.39898281711174816, + "learning_rate": 1.01872294636304e-06, + "loss": 0.1367, + "step": 201 + }, + { + "epoch": 6.121212121212121, + "grad_norm": 0.3557934068122329, + "learning_rate": 9.530222835413739e-07, + "loss": 0.1561, + "step": 202 + }, + { + "epoch": 6.151515151515151, + "grad_norm": 0.38265274333153265, + "learning_rate": 8.894054121084839e-07, + "loss": 0.1542, + "step": 203 + }, + { + "epoch": 6.181818181818182, + "grad_norm": 0.33626439767237964, + "learning_rate": 8.278869849454718e-07, + "loss": 0.1508, + "step": 204 + }, + { + "epoch": 6.212121212121212, + "grad_norm": 0.3480623394329382, + "learning_rate": 7.684811715985429e-07, + "loss": 0.1435, + "step": 205 + }, + { + "epoch": 6.242424242424242, + "grad_norm": 0.3637611567267387, + "learning_rate": 7.1120165501533e-07, + "loss": 0.1436, + "step": 206 + }, + { + "epoch": 6.2727272727272725, + "grad_norm": 0.3756095538107021, + "learning_rate": 6.560616283932897e-07, + "loss": 0.1441, + "step": 207 + }, + { + "epoch": 6.303030303030303, + "grad_norm": 0.4233715419677722, + "learning_rate": 6.030737921409169e-07, + "loss": 0.1418, + "step": 208 + }, + { + "epoch": 6.333333333333333, + "grad_norm": 0.3959442236720861, + "learning_rate": 5.522503509524591e-07, + "loss": 0.1446, + "step": 209 + }, + { + "epoch": 6.363636363636363, + "grad_norm": 0.40746572697437256, + "learning_rate": 5.036030109968082e-07, + "loss": 0.164, + "step": 210 + }, + { + "epoch": 6.393939393939394, + "grad_norm": 0.3579587142573846, + "learning_rate": 4.5714297722121105e-07, + "loss": 0.1457, + "step": 211 + }, + { + "epoch": 6.424242424242424, + "grad_norm": 0.3917891786740035, + "learning_rate": 4.128809507704445e-07, + "loss": 0.1494, + "step": 212 + }, + { + "epoch": 6.454545454545454, + "grad_norm": 0.3545953463168816, + "learning_rate": 3.708271265220087e-07, + "loss": 0.1574, + "step": 213 + }, + { + "epoch": 6.484848484848484, + "grad_norm": 0.37736081342197736, + "learning_rate": 3.309911907379393e-07, + "loss": 0.1331, + "step": 214 + }, + { + "epoch": 6.515151515151516, + "grad_norm": 0.3634374777293854, + "learning_rate": 2.9338231883378365e-07, + "loss": 0.1526, + "step": 215 + }, + { + "epoch": 6.545454545454545, + "grad_norm": 0.3447428712429749, + "learning_rate": 2.5800917326521013e-07, + "loss": 0.1376, + "step": 216 + }, + { + "epoch": 6.575757575757576, + "grad_norm": 0.32300415105179925, + "learning_rate": 2.248799015327907e-07, + "loss": 0.1438, + "step": 217 + }, + { + "epoch": 6.606060606060606, + "grad_norm": 0.37766546336053336, + "learning_rate": 1.9400213430538773e-07, + "loss": 0.1377, + "step": 218 + }, + { + "epoch": 6.636363636363637, + "grad_norm": 0.3711273450161272, + "learning_rate": 1.6538298366257975e-07, + "loss": 0.1427, + "step": 219 + }, + { + "epoch": 6.666666666666667, + "grad_norm": 0.3435986132162903, + "learning_rate": 1.3902904145653094e-07, + "loss": 0.1625, + "step": 220 + }, + { + "epoch": 6.696969696969697, + "grad_norm": 0.3706546368143587, + "learning_rate": 1.1494637779369766e-07, + "loss": 0.1488, + "step": 221 + }, + { + "epoch": 6.7272727272727275, + "grad_norm": 0.36327877692558397, + "learning_rate": 9.314053963669245e-08, + "loss": 0.1482, + "step": 222 + }, + { + "epoch": 6.757575757575758, + "grad_norm": 0.35086010775673443, + "learning_rate": 7.361654952665608e-08, + "loss": 0.1475, + "step": 223 + }, + { + "epoch": 6.787878787878788, + "grad_norm": 0.34960714594014297, + "learning_rate": 5.637890442641403e-08, + "loss": 0.1452, + "step": 224 + }, + { + "epoch": 6.818181818181818, + "grad_norm": 0.33896142149612296, + "learning_rate": 4.143157468468717e-08, + "loss": 0.159, + "step": 225 + }, + { + "epoch": 6.848484848484849, + "grad_norm": 0.368104373375551, + "learning_rate": 2.8778003121607834e-08, + "loss": 0.1412, + "step": 226 + }, + { + "epoch": 6.878787878787879, + "grad_norm": 0.3548934214749664, + "learning_rate": 1.8421104235727406e-08, + "loss": 0.1603, + "step": 227 + }, + { + "epoch": 6.909090909090909, + "grad_norm": 0.36193246085450276, + "learning_rate": 1.0363263532724433e-08, + "loss": 0.1396, + "step": 228 + }, + { + "epoch": 6.9393939393939394, + "grad_norm": 0.37277919425792433, + "learning_rate": 4.606336975948589e-09, + "loss": 0.1491, + "step": 229 + }, + { + "epoch": 6.96969696969697, + "grad_norm": 0.35083940737519065, + "learning_rate": 1.1516505589381777e-09, + "loss": 0.1509, + "step": 230 + }, + { + "epoch": 7.0, + "grad_norm": 0.3804132675555632, + "learning_rate": 0.0, + "loss": 0.1549, + "step": 231 + }, + { + "epoch": 7.0, + "step": 231, + "total_flos": 3.564705674208215e+17, + "train_loss": 0.3959881691705613, + "train_runtime": 6616.9312, + "train_samples_per_second": 3.343, + "train_steps_per_second": 0.035 + } + ], + "logging_steps": 1, + "max_steps": 231, + "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": 3.564705674208215e+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..fda3778 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:336660983f9bc822a6fe8597d904f51b128557dcd9cefc25b4a7e31897524429 +size 7352 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..8e13433 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