commit 807505246ef6a08970fdd22b4983804a39c0d8e3 Author: ModelHub XC Date: Fri Jul 17 05:29:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mlfoundations-dev/oh-dcft-v3.1-llama-3.1-nemotron-70b-qwen Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7aad060 --- /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 +merges.txt filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-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..55719cc --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +library_name: transformers +license: apache-2.0 +base_model: Qwen/Qwen2.5-7B +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: oh-dcft-v3.1-llama-3.1-nemotron-70b-qwen + results: [] +--- + + + +# oh-dcft-v3.1-llama-3.1-nemotron-70b-qwen + +This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the mlfoundations-dev/oh-dcft-v3.1-llama-3.1-nemotron-70b dataset. +It achieves the following results on the evaluation set: +- Loss: 0.5616 + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-06 +- train_batch_size: 8 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- gradient_accumulation_steps: 2 +- total_train_batch_size: 128 +- total_eval_batch_size: 64 +- 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: constant +- num_epochs: 3.0 + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:------:|:----:|:---------------:| +| 0.5712 | 0.9998 | 2228 | 0.5679 | +| 0.5079 | 2.0 | 4457 | 0.5560 | +| 0.4538 | 2.9993 | 6684 | 0.5616 | + + +### Framework versions + +- Transformers 4.46.1 +- Pytorch 2.3.0 +- Datasets 3.1.0 +- 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..7276760 --- /dev/null +++ b/all_results.json @@ -0,0 +1,12 @@ +{ + "epoch": 2.9993269015032533, + "eval_loss": 0.5616346001625061, + "eval_runtime": 560.2479, + "eval_samples_per_second": 26.792, + "eval_steps_per_second": 0.419, + "total_flos": 3503854586953728.0, + "train_loss": 0.5125751896649332, + "train_runtime": 89473.4361, + "train_samples_per_second": 9.562, + "train_steps_per_second": 0.075 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..f517eef --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "Qwen/Qwen2.5-7B", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 131072, + "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_mrope": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/configs.yaml b/configs.yaml new file mode 100644 index 0000000..954eafe --- /dev/null +++ b/configs.yaml @@ -0,0 +1,41 @@ +adam_beta1: '0.9' +adam_beta2: '0.999' +bf16: 'True' +cutoff_len: '2048' +dataset: mlfoundations-dev/oh-dcft-v3.1-llama-3.1-nemotron-70b +dataset_dir: ONLINE +ddp_timeout: '180000000' +deepspeed: /opt/ml/code/zero3.json +do_train: 'True' +enable_liger_kernel: 'False' +eval_strategy: epoch +finetuning_type: full +formatting: sharegpt +global_batch_size: '128' +gradient_accumulation_steps: '2' +gradient_checkpointing: 'True' +hub_model_id: mlfoundations-dev/oh-dcft-v3.1-llama-3.1-nemotron-70b-qwen +learning_rate: 5e-06 +logging_steps: '10' +lr_scheduler_type: constant +max_grad_norm: '1' +messages: conversations +model_name_or_path: Qwen/Qwen2.5-7B +neat_packing: 'True' +num_train_epochs: '3.0' +output_dir: /opt/ml/model +overwrite_cache: 'True' +overwrite_output_dir: 'True' +packing: 'True' +per_device_train_batch_size: '8' +plot_loss: 'True' +preprocessing_num_workers: '16' +push_to_db: 'True' +push_to_hub: 'True' +report_to: wandb +run_name: oh-dcft-v3.1-llama-3.1-nemotron-70b-qwen +save_strategy: epoch +stage: sft +template: qwen +val_size: '0.05' +weight_decay: '0.1' diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000..2eb0d91 --- /dev/null +++ b/eval_results.json @@ -0,0 +1,7 @@ +{ + "epoch": 2.9993269015032533, + "eval_loss": 0.5616346001625061, + "eval_runtime": 560.2479, + "eval_samples_per_second": 26.792, + "eval_steps_per_second": 0.419 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..504ff91 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "bos_token_id": 151643, + "eos_token_id": 151643, + "max_new_tokens": 2048, + "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..604da81 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a013298f6fa050270d28f6e0fdbc4b64ece2d6abe441a4f9b596234c757f9c0c +size 4877660776 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..afda37c --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbfac027a0e4c528324fcd20b1d0c740d85c02f48f2cb78c06a65d2d5e5382bc +size 4932751008 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..f6000d2 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f874f94e305c14b44538569af84e855b126c3fbf4afd74e6cde6326ff3b6ff4 +size 4330865200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..d653f9e --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1856d9632aa01fa4db3d6ce2eda1a1f8b9ec6d7c29c785d5c8bbd975ead9383 +size 1089994880 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..6ca5084 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,346 @@ +{ + "metadata": { + "total_size": 15231233024 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00003-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /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": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..51ebb3b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..d24b2b8 --- /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 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 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": "<|im_end|>", + "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..89f5ff7 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 2.9993269015032533, + "total_flos": 3503854586953728.0, + "train_loss": 0.5125751896649332, + "train_runtime": 89473.4361, + "train_samples_per_second": 9.562, + "train_steps_per_second": 0.075 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..4a63530 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,672 @@ +{"current_steps": 10, "total_steps": 6684, "loss": 0.7774, "lr": 5e-06, "epoch": 0.004487323311644604, "percentage": 0.15, "elapsed_time": "0:02:15", "remaining_time": "1 day, 1:06:17"} +{"current_steps": 20, "total_steps": 6684, "loss": 0.6958, "lr": 5e-06, "epoch": 0.008974646623289208, "percentage": 0.3, "elapsed_time": "0:04:26", "remaining_time": "1 day, 0:39:25"} +{"current_steps": 30, "total_steps": 6684, "loss": 0.6992, "lr": 5e-06, "epoch": 0.013461969934933812, "percentage": 0.45, "elapsed_time": "0:06:37", "remaining_time": "1 day, 0:28:49"} +{"current_steps": 40, "total_steps": 6684, "loss": 0.6749, "lr": 5e-06, "epoch": 0.017949293246578416, "percentage": 0.6, "elapsed_time": "0:08:48", "remaining_time": "1 day, 0:22:29"} +{"current_steps": 50, "total_steps": 6684, "loss": 0.7083, "lr": 5e-06, "epoch": 0.02243661655822302, "percentage": 0.75, "elapsed_time": "0:10:59", "remaining_time": "1 day, 0:17:49"} +{"current_steps": 60, "total_steps": 6684, "loss": 0.6846, "lr": 5e-06, "epoch": 0.026923939869867623, "percentage": 0.9, "elapsed_time": "0:13:10", "remaining_time": "1 day, 0:14:04"} +{"current_steps": 70, "total_steps": 6684, "loss": 0.6574, "lr": 5e-06, "epoch": 0.03141126318151223, "percentage": 1.05, "elapsed_time": "0:15:21", "remaining_time": "1 day, 0:10:39"} +{"current_steps": 80, "total_steps": 6684, "loss": 0.653, "lr": 5e-06, "epoch": 0.03589858649315683, "percentage": 1.2, "elapsed_time": "0:17:31", "remaining_time": "1 day, 0:07:13"} +{"current_steps": 90, "total_steps": 6684, "loss": 0.6452, "lr": 5e-06, "epoch": 0.04038590980480144, "percentage": 1.35, "elapsed_time": "0:19:42", "remaining_time": "1 day, 0:03:59"} +{"current_steps": 100, "total_steps": 6684, "loss": 0.6424, "lr": 5e-06, "epoch": 0.04487323311644604, "percentage": 1.5, "elapsed_time": "0:21:53", "remaining_time": "1 day, 0:01:05"} +{"current_steps": 110, "total_steps": 6684, "loss": 0.6325, "lr": 5e-06, "epoch": 0.049360556428090646, "percentage": 1.65, "elapsed_time": "0:24:03", "remaining_time": "23:58:13"} +{"current_steps": 120, "total_steps": 6684, "loss": 0.6389, "lr": 5e-06, "epoch": 0.05384787973973525, "percentage": 1.8, "elapsed_time": "0:26:14", "remaining_time": "23:55:34"} +{"current_steps": 130, "total_steps": 6684, "loss": 0.6394, "lr": 5e-06, "epoch": 0.058335203051379854, "percentage": 1.94, "elapsed_time": "0:28:25", "remaining_time": "23:52:56"} +{"current_steps": 140, "total_steps": 6684, "loss": 0.6487, "lr": 5e-06, "epoch": 0.06282252636302446, "percentage": 2.09, "elapsed_time": "0:30:35", "remaining_time": "23:50:18"} +{"current_steps": 150, "total_steps": 6684, "loss": 0.6535, "lr": 5e-06, "epoch": 0.06730984967466906, "percentage": 2.24, "elapsed_time": "0:32:46", "remaining_time": "23:47:49"} +{"current_steps": 160, "total_steps": 6684, "loss": 0.6613, "lr": 5e-06, "epoch": 0.07179717298631366, "percentage": 2.39, "elapsed_time": "0:34:57", "remaining_time": "23:45:17"} +{"current_steps": 170, "total_steps": 6684, "loss": 0.6357, "lr": 5e-06, "epoch": 0.07628449629795826, "percentage": 2.54, "elapsed_time": "0:37:08", "remaining_time": "23:42:54"} +{"current_steps": 180, "total_steps": 6684, "loss": 0.636, "lr": 5e-06, "epoch": 0.08077181960960288, "percentage": 2.69, "elapsed_time": "0:39:18", "remaining_time": "23:40:29"} +{"current_steps": 190, "total_steps": 6684, "loss": 0.6312, "lr": 5e-06, "epoch": 0.08525914292124748, "percentage": 2.84, "elapsed_time": "0:41:29", "remaining_time": "23:38:00"} +{"current_steps": 200, "total_steps": 6684, "loss": 0.6332, "lr": 5e-06, "epoch": 0.08974646623289208, "percentage": 2.99, "elapsed_time": "0:43:39", "remaining_time": "23:35:35"} +{"current_steps": 210, "total_steps": 6684, "loss": 0.6092, "lr": 5e-06, "epoch": 0.09423378954453668, "percentage": 3.14, "elapsed_time": "0:45:50", "remaining_time": "23:33:17"} +{"current_steps": 220, "total_steps": 6684, "loss": 0.6421, "lr": 5e-06, "epoch": 0.09872111285618129, "percentage": 3.29, "elapsed_time": "0:48:01", "remaining_time": "23:30:58"} +{"current_steps": 230, "total_steps": 6684, "loss": 0.6281, "lr": 5e-06, "epoch": 0.10320843616782589, "percentage": 3.44, "elapsed_time": "0:50:12", "remaining_time": "23:28:41"} +{"current_steps": 240, "total_steps": 6684, "loss": 0.6172, "lr": 5e-06, "epoch": 0.1076957594794705, "percentage": 3.59, "elapsed_time": "0:52:22", "remaining_time": "23:26:24"} +{"current_steps": 250, "total_steps": 6684, "loss": 0.6016, "lr": 5e-06, "epoch": 0.1121830827911151, "percentage": 3.74, "elapsed_time": "0:54:33", "remaining_time": "23:24:09"} +{"current_steps": 260, "total_steps": 6684, "loss": 0.6126, "lr": 5e-06, "epoch": 0.11667040610275971, "percentage": 3.89, "elapsed_time": "0:56:44", "remaining_time": "23:21:56"} +{"current_steps": 270, "total_steps": 6684, "loss": 0.6251, "lr": 5e-06, "epoch": 0.12115772941440431, "percentage": 4.04, "elapsed_time": "0:58:55", "remaining_time": "23:19:43"} +{"current_steps": 280, "total_steps": 6684, "loss": 0.625, "lr": 5e-06, "epoch": 0.12564505272604892, "percentage": 4.19, "elapsed_time": "1:01:06", "remaining_time": "23:17:31"} +{"current_steps": 290, "total_steps": 6684, "loss": 0.619, "lr": 5e-06, "epoch": 0.1301323760376935, "percentage": 4.34, "elapsed_time": "1:03:17", "remaining_time": "23:15:20"} +{"current_steps": 300, "total_steps": 6684, "loss": 0.6073, "lr": 5e-06, "epoch": 0.13461969934933812, "percentage": 4.49, "elapsed_time": "1:05:27", "remaining_time": "23:13:05"} +{"current_steps": 310, "total_steps": 6684, "loss": 0.6269, "lr": 5e-06, "epoch": 0.13910702266098274, "percentage": 4.64, "elapsed_time": "1:07:38", "remaining_time": "23:10:49"} +{"current_steps": 320, "total_steps": 6684, "loss": 0.6294, "lr": 5e-06, "epoch": 0.14359434597262732, "percentage": 4.79, "elapsed_time": "1:09:49", "remaining_time": "23:08:31"} +{"current_steps": 330, "total_steps": 6684, "loss": 0.6175, "lr": 5e-06, "epoch": 0.14808166928427194, "percentage": 4.94, "elapsed_time": "1:11:59", "remaining_time": "23:06:14"} +{"current_steps": 340, "total_steps": 6684, "loss": 0.6, "lr": 5e-06, "epoch": 0.15256899259591652, "percentage": 5.09, "elapsed_time": "1:14:10", "remaining_time": "23:03:57"} +{"current_steps": 350, "total_steps": 6684, "loss": 0.606, "lr": 5e-06, "epoch": 0.15705631590756114, "percentage": 5.24, "elapsed_time": "1:16:20", "remaining_time": "23:01:39"} +{"current_steps": 360, "total_steps": 6684, "loss": 0.5955, "lr": 5e-06, "epoch": 0.16154363921920575, "percentage": 5.39, "elapsed_time": "1:18:31", "remaining_time": "22:59:24"} +{"current_steps": 370, "total_steps": 6684, "loss": 0.5993, "lr": 5e-06, "epoch": 0.16603096253085034, "percentage": 5.54, "elapsed_time": "1:20:42", "remaining_time": "22:57:10"} +{"current_steps": 380, "total_steps": 6684, "loss": 0.5941, "lr": 5e-06, "epoch": 0.17051828584249495, "percentage": 5.69, "elapsed_time": "1:22:52", "remaining_time": "22:54:56"} +{"current_steps": 390, "total_steps": 6684, "loss": 0.6086, "lr": 5e-06, "epoch": 0.17500560915413957, "percentage": 5.83, "elapsed_time": "1:25:03", "remaining_time": "22:52:40"} +{"current_steps": 400, "total_steps": 6684, "loss": 0.6298, "lr": 5e-06, "epoch": 0.17949293246578416, "percentage": 5.98, "elapsed_time": "1:27:13", "remaining_time": "22:50:25"} +{"current_steps": 410, "total_steps": 6684, "loss": 0.6128, "lr": 5e-06, "epoch": 0.18398025577742877, "percentage": 6.13, "elapsed_time": "1:29:24", "remaining_time": "22:48:11"} +{"current_steps": 420, "total_steps": 6684, "loss": 0.6199, "lr": 5e-06, "epoch": 0.18846757908907336, "percentage": 6.28, "elapsed_time": "1:31:35", "remaining_time": "22:45:58"} +{"current_steps": 430, "total_steps": 6684, "loss": 0.6123, "lr": 5e-06, "epoch": 0.19295490240071797, "percentage": 6.43, "elapsed_time": "1:33:46", "remaining_time": "22:43:46"} +{"current_steps": 440, "total_steps": 6684, "loss": 0.632, "lr": 5e-06, "epoch": 0.19744222571236258, "percentage": 6.58, "elapsed_time": "1:35:57", "remaining_time": "22:41:37"} +{"current_steps": 450, "total_steps": 6684, "loss": 0.5918, "lr": 5e-06, "epoch": 0.20192954902400717, "percentage": 6.73, "elapsed_time": "1:38:07", "remaining_time": "22:39:25"} +{"current_steps": 460, "total_steps": 6684, "loss": 0.6151, "lr": 5e-06, "epoch": 0.20641687233565179, "percentage": 6.88, "elapsed_time": "1:40:18", "remaining_time": "22:37:14"} +{"current_steps": 470, "total_steps": 6684, "loss": 0.6059, "lr": 5e-06, "epoch": 0.2109041956472964, "percentage": 7.03, "elapsed_time": "1:42:29", "remaining_time": "22:35:06"} +{"current_steps": 480, "total_steps": 6684, "loss": 0.6135, "lr": 5e-06, "epoch": 0.215391518958941, "percentage": 7.18, "elapsed_time": "1:44:40", "remaining_time": "22:32:58"} +{"current_steps": 490, "total_steps": 6684, "loss": 0.5821, "lr": 5e-06, "epoch": 0.2198788422705856, "percentage": 7.33, "elapsed_time": "1:46:51", "remaining_time": "22:30:49"} +{"current_steps": 500, "total_steps": 6684, "loss": 0.6116, "lr": 5e-06, "epoch": 0.2243661655822302, "percentage": 7.48, "elapsed_time": "1:49:02", "remaining_time": "22:28:39"} +{"current_steps": 510, "total_steps": 6684, "loss": 0.5907, "lr": 5e-06, "epoch": 0.2288534888938748, "percentage": 7.63, "elapsed_time": "1:51:13", "remaining_time": "22:26:30"} +{"current_steps": 520, "total_steps": 6684, "loss": 0.6038, "lr": 5e-06, "epoch": 0.23334081220551942, "percentage": 7.78, "elapsed_time": "1:53:24", "remaining_time": "22:24:21"} +{"current_steps": 530, "total_steps": 6684, "loss": 0.6244, "lr": 5e-06, "epoch": 0.237828135517164, "percentage": 7.93, "elapsed_time": "1:55:35", "remaining_time": "22:22:11"} +{"current_steps": 540, "total_steps": 6684, "loss": 0.5981, "lr": 5e-06, "epoch": 0.24231545882880862, "percentage": 8.08, "elapsed_time": "1:57:46", "remaining_time": "22:20:02"} +{"current_steps": 550, "total_steps": 6684, "loss": 0.5908, "lr": 5e-06, "epoch": 0.24680278214045323, "percentage": 8.23, "elapsed_time": "1:59:57", "remaining_time": "22:17:50"} +{"current_steps": 560, "total_steps": 6684, "loss": 0.5683, "lr": 5e-06, "epoch": 0.25129010545209784, "percentage": 8.38, "elapsed_time": "2:02:08", "remaining_time": "22:15:38"} +{"current_steps": 570, "total_steps": 6684, "loss": 0.622, "lr": 5e-06, "epoch": 0.25577742876374243, "percentage": 8.53, "elapsed_time": "2:04:19", "remaining_time": "22:13:27"} +{"current_steps": 580, "total_steps": 6684, "loss": 0.5964, "lr": 5e-06, "epoch": 0.260264752075387, "percentage": 8.68, "elapsed_time": "2:06:29", "remaining_time": "22:11:16"} +{"current_steps": 590, "total_steps": 6684, "loss": 0.5894, "lr": 5e-06, "epoch": 0.26475207538703166, "percentage": 8.83, "elapsed_time": "2:08:40", "remaining_time": "22:09:05"} +{"current_steps": 600, "total_steps": 6684, "loss": 0.5879, "lr": 5e-06, "epoch": 0.26923939869867625, "percentage": 8.98, "elapsed_time": "2:10:51", "remaining_time": "22:06:53"} +{"current_steps": 610, "total_steps": 6684, "loss": 0.5821, "lr": 5e-06, "epoch": 0.27372672201032083, "percentage": 9.13, "elapsed_time": "2:13:02", "remaining_time": "22:04:42"} +{"current_steps": 620, "total_steps": 6684, "loss": 0.5988, "lr": 5e-06, "epoch": 0.2782140453219655, "percentage": 9.28, "elapsed_time": "2:15:12", "remaining_time": "22:02:29"} +{"current_steps": 630, "total_steps": 6684, "loss": 0.5984, "lr": 5e-06, "epoch": 0.28270136863361006, "percentage": 9.43, "elapsed_time": "2:17:23", "remaining_time": "22:00:16"} +{"current_steps": 640, "total_steps": 6684, "loss": 0.6093, "lr": 5e-06, "epoch": 0.28718869194525465, "percentage": 9.58, "elapsed_time": "2:19:34", "remaining_time": "21:58:04"} +{"current_steps": 650, "total_steps": 6684, "loss": 0.6061, "lr": 5e-06, "epoch": 0.29167601525689923, "percentage": 9.72, "elapsed_time": "2:21:44", "remaining_time": "21:55:51"} +{"current_steps": 660, "total_steps": 6684, "loss": 0.6119, "lr": 5e-06, "epoch": 0.2961633385685439, "percentage": 9.87, "elapsed_time": "2:23:55", "remaining_time": "21:53:39"} +{"current_steps": 670, "total_steps": 6684, "loss": 0.5866, "lr": 5e-06, "epoch": 0.30065066188018846, "percentage": 10.02, "elapsed_time": "2:26:06", "remaining_time": "21:51:27"} +{"current_steps": 680, "total_steps": 6684, "loss": 0.5856, "lr": 5e-06, "epoch": 0.30513798519183305, "percentage": 10.17, "elapsed_time": "2:28:17", "remaining_time": "21:49:16"} +{"current_steps": 690, "total_steps": 6684, "loss": 0.6159, "lr": 5e-06, "epoch": 0.3096253085034777, "percentage": 10.32, "elapsed_time": "2:30:27", "remaining_time": "21:47:04"} +{"current_steps": 700, "total_steps": 6684, "loss": 0.6026, "lr": 5e-06, "epoch": 0.3141126318151223, "percentage": 10.47, "elapsed_time": "2:32:38", "remaining_time": "21:44:54"} +{"current_steps": 710, "total_steps": 6684, "loss": 0.5728, "lr": 5e-06, "epoch": 0.31859995512676687, "percentage": 10.62, "elapsed_time": "2:34:49", "remaining_time": "21:42:42"} +{"current_steps": 720, "total_steps": 6684, "loss": 0.6193, "lr": 5e-06, "epoch": 0.3230872784384115, "percentage": 10.77, "elapsed_time": "2:37:00", "remaining_time": "21:40:31"} +{"current_steps": 730, "total_steps": 6684, "loss": 0.5901, "lr": 5e-06, "epoch": 0.3275746017500561, "percentage": 10.92, "elapsed_time": "2:39:11", "remaining_time": "21:38:21"} +{"current_steps": 740, "total_steps": 6684, "loss": 0.62, "lr": 5e-06, "epoch": 0.3320619250617007, "percentage": 11.07, "elapsed_time": "2:41:21", "remaining_time": "21:36:09"} +{"current_steps": 750, "total_steps": 6684, "loss": 0.5918, "lr": 5e-06, "epoch": 0.3365492483733453, "percentage": 11.22, "elapsed_time": "2:43:32", "remaining_time": "21:33:58"} +{"current_steps": 760, "total_steps": 6684, "loss": 0.584, "lr": 5e-06, "epoch": 0.3410365716849899, "percentage": 11.37, "elapsed_time": "2:45:43", "remaining_time": "21:31:49"} +{"current_steps": 770, "total_steps": 6684, "loss": 0.5826, "lr": 5e-06, "epoch": 0.3455238949966345, "percentage": 11.52, "elapsed_time": "2:47:54", "remaining_time": "21:29:39"} +{"current_steps": 780, "total_steps": 6684, "loss": 0.6246, "lr": 5e-06, "epoch": 0.35001121830827914, "percentage": 11.67, "elapsed_time": "2:50:05", "remaining_time": "21:27:30"} +{"current_steps": 790, "total_steps": 6684, "loss": 0.6169, "lr": 5e-06, "epoch": 0.3544985416199237, "percentage": 11.82, "elapsed_time": "2:52:16", "remaining_time": "21:25:20"} +{"current_steps": 800, "total_steps": 6684, "loss": 0.5911, "lr": 5e-06, "epoch": 0.3589858649315683, "percentage": 11.97, "elapsed_time": "2:54:27", "remaining_time": "21:23:10"} +{"current_steps": 810, "total_steps": 6684, "loss": 0.599, "lr": 5e-06, "epoch": 0.3634731882432129, "percentage": 12.12, "elapsed_time": "2:56:38", "remaining_time": "21:21:00"} +{"current_steps": 820, "total_steps": 6684, "loss": 0.6276, "lr": 5e-06, "epoch": 0.36796051155485754, "percentage": 12.27, "elapsed_time": "2:58:49", "remaining_time": "21:18:50"} +{"current_steps": 830, "total_steps": 6684, "loss": 0.5758, "lr": 5e-06, "epoch": 0.3724478348665021, "percentage": 12.42, "elapsed_time": "3:01:00", "remaining_time": "21:16:40"} +{"current_steps": 840, "total_steps": 6684, "loss": 0.5818, "lr": 5e-06, "epoch": 0.3769351581781467, "percentage": 12.57, "elapsed_time": "3:03:11", "remaining_time": "21:14:29"} +{"current_steps": 850, "total_steps": 6684, "loss": 0.5833, "lr": 5e-06, "epoch": 0.38142248148979135, "percentage": 12.72, "elapsed_time": "3:05:22", "remaining_time": "21:12:17"} +{"current_steps": 860, "total_steps": 6684, "loss": 0.5896, "lr": 5e-06, "epoch": 0.38590980480143594, "percentage": 12.87, "elapsed_time": "3:07:32", "remaining_time": "21:10:05"} +{"current_steps": 870, "total_steps": 6684, "loss": 0.6351, "lr": 5e-06, "epoch": 0.3903971281130805, "percentage": 13.02, "elapsed_time": "3:09:43", "remaining_time": "21:07:53"} +{"current_steps": 880, "total_steps": 6684, "loss": 0.6013, "lr": 5e-06, "epoch": 0.39488445142472517, "percentage": 13.17, "elapsed_time": "3:11:54", "remaining_time": "21:05:42"} +{"current_steps": 890, "total_steps": 6684, "loss": 0.5834, "lr": 5e-06, "epoch": 0.39937177473636976, "percentage": 13.32, "elapsed_time": "3:14:05", "remaining_time": "21:03:31"} +{"current_steps": 900, "total_steps": 6684, "loss": 0.5952, "lr": 5e-06, "epoch": 0.40385909804801434, "percentage": 13.46, "elapsed_time": "3:16:16", "remaining_time": "21:01:20"} +{"current_steps": 910, "total_steps": 6684, "loss": 0.5707, "lr": 5e-06, "epoch": 0.408346421359659, "percentage": 13.61, "elapsed_time": "3:18:26", "remaining_time": "20:59:10"} +{"current_steps": 920, "total_steps": 6684, "loss": 0.5963, "lr": 5e-06, "epoch": 0.41283374467130357, "percentage": 13.76, "elapsed_time": "3:20:37", "remaining_time": "20:56:59"} +{"current_steps": 930, "total_steps": 6684, "loss": 0.6116, "lr": 5e-06, "epoch": 0.41732106798294816, "percentage": 13.91, "elapsed_time": "3:22:48", "remaining_time": "20:54:48"} +{"current_steps": 940, "total_steps": 6684, "loss": 0.5949, "lr": 5e-06, "epoch": 0.4218083912945928, "percentage": 14.06, "elapsed_time": "3:24:59", "remaining_time": "20:52:37"} +{"current_steps": 950, "total_steps": 6684, "loss": 0.578, "lr": 5e-06, "epoch": 0.4262957146062374, "percentage": 14.21, "elapsed_time": "3:27:10", "remaining_time": "20:50:26"} +{"current_steps": 960, "total_steps": 6684, "loss": 0.5756, "lr": 5e-06, "epoch": 0.430783037917882, "percentage": 14.36, "elapsed_time": "3:29:21", "remaining_time": "20:48:15"} +{"current_steps": 970, "total_steps": 6684, "loss": 0.5773, "lr": 5e-06, "epoch": 0.4352703612295266, "percentage": 14.51, "elapsed_time": "3:31:32", "remaining_time": "20:46:05"} +{"current_steps": 980, "total_steps": 6684, "loss": 0.6106, "lr": 5e-06, "epoch": 0.4397576845411712, "percentage": 14.66, "elapsed_time": "3:33:42", "remaining_time": "20:43:54"} +{"current_steps": 990, "total_steps": 6684, "loss": 0.5867, "lr": 5e-06, "epoch": 0.4442450078528158, "percentage": 14.81, "elapsed_time": "3:35:53", "remaining_time": "20:41:44"} +{"current_steps": 1000, "total_steps": 6684, "loss": 0.5752, "lr": 5e-06, "epoch": 0.4487323311644604, "percentage": 14.96, "elapsed_time": "3:38:04", "remaining_time": "20:39:33"} +{"current_steps": 1010, "total_steps": 6684, "loss": 0.6077, "lr": 5e-06, "epoch": 0.453219654476105, "percentage": 15.11, "elapsed_time": "3:40:15", "remaining_time": "20:37:23"} +{"current_steps": 1020, "total_steps": 6684, "loss": 0.6021, "lr": 5e-06, "epoch": 0.4577069777877496, "percentage": 15.26, "elapsed_time": "3:42:26", "remaining_time": "20:35:12"} +{"current_steps": 1030, "total_steps": 6684, "loss": 0.5895, "lr": 5e-06, "epoch": 0.4621943010993942, "percentage": 15.41, "elapsed_time": "3:44:37", "remaining_time": "20:33:02"} +{"current_steps": 1040, "total_steps": 6684, "loss": 0.5904, "lr": 5e-06, "epoch": 0.46668162441103883, "percentage": 15.56, "elapsed_time": "3:46:48", "remaining_time": "20:30:50"} +{"current_steps": 1050, "total_steps": 6684, "loss": 0.5774, "lr": 5e-06, "epoch": 0.4711689477226834, "percentage": 15.71, "elapsed_time": "3:48:59", "remaining_time": "20:28:39"} +{"current_steps": 1060, "total_steps": 6684, "loss": 0.5936, "lr": 5e-06, "epoch": 0.475656271034328, "percentage": 15.86, "elapsed_time": "3:51:09", "remaining_time": "20:26:28"} +{"current_steps": 1070, "total_steps": 6684, "loss": 0.5762, "lr": 5e-06, "epoch": 0.48014359434597265, "percentage": 16.01, "elapsed_time": "3:53:20", "remaining_time": "20:24:17"} +{"current_steps": 1080, "total_steps": 6684, "loss": 0.5923, "lr": 5e-06, "epoch": 0.48463091765761723, "percentage": 16.16, "elapsed_time": "3:55:31", "remaining_time": "20:22:06"} +{"current_steps": 1090, "total_steps": 6684, "loss": 0.5893, "lr": 5e-06, "epoch": 0.4891182409692618, "percentage": 16.31, "elapsed_time": "3:57:42", "remaining_time": "20:19:55"} +{"current_steps": 1100, "total_steps": 6684, "loss": 0.5675, "lr": 5e-06, "epoch": 0.49360556428090646, "percentage": 16.46, "elapsed_time": "3:59:52", "remaining_time": "20:17:43"} +{"current_steps": 1110, "total_steps": 6684, "loss": 0.5702, "lr": 5e-06, "epoch": 0.49809288759255105, "percentage": 16.61, "elapsed_time": "4:02:03", "remaining_time": "20:15:31"} +{"current_steps": 1120, "total_steps": 6684, "loss": 0.5783, "lr": 5e-06, "epoch": 0.5025802109041957, "percentage": 16.76, "elapsed_time": "4:04:14", "remaining_time": "20:13:20"} +{"current_steps": 1130, "total_steps": 6684, "loss": 0.579, "lr": 5e-06, "epoch": 0.5070675342158403, "percentage": 16.91, "elapsed_time": "4:06:24", "remaining_time": "20:11:08"} +{"current_steps": 1140, "total_steps": 6684, "loss": 0.5824, "lr": 5e-06, "epoch": 0.5115548575274849, "percentage": 17.06, "elapsed_time": "4:08:35", "remaining_time": "20:08:57"} +{"current_steps": 1150, "total_steps": 6684, "loss": 0.5656, "lr": 5e-06, "epoch": 0.5160421808391294, "percentage": 17.21, "elapsed_time": "4:10:46", "remaining_time": "20:06:46"} +{"current_steps": 1160, "total_steps": 6684, "loss": 0.5874, "lr": 5e-06, "epoch": 0.520529504150774, "percentage": 17.35, "elapsed_time": "4:12:57", "remaining_time": "20:04:34"} +{"current_steps": 1170, "total_steps": 6684, "loss": 0.599, "lr": 5e-06, "epoch": 0.5250168274624186, "percentage": 17.5, "elapsed_time": "4:15:07", "remaining_time": "20:02:23"} +{"current_steps": 1180, "total_steps": 6684, "loss": 0.5657, "lr": 5e-06, "epoch": 0.5295041507740633, "percentage": 17.65, "elapsed_time": "4:17:18", "remaining_time": "20:00:12"} +{"current_steps": 1190, "total_steps": 6684, "loss": 0.5823, "lr": 5e-06, "epoch": 0.5339914740857079, "percentage": 17.8, "elapsed_time": "4:19:29", "remaining_time": "19:58:01"} +{"current_steps": 1200, "total_steps": 6684, "loss": 0.609, "lr": 5e-06, "epoch": 0.5384787973973525, "percentage": 17.95, "elapsed_time": "4:21:40", "remaining_time": "19:55:49"} +{"current_steps": 1210, "total_steps": 6684, "loss": 0.5757, "lr": 5e-06, "epoch": 0.5429661207089971, "percentage": 18.1, "elapsed_time": "4:23:51", "remaining_time": "19:53:39"} +{"current_steps": 1220, "total_steps": 6684, "loss": 0.5939, "lr": 5e-06, "epoch": 0.5474534440206417, "percentage": 18.25, "elapsed_time": "4:26:01", "remaining_time": "19:51:27"} +{"current_steps": 1230, "total_steps": 6684, "loss": 0.5702, "lr": 5e-06, "epoch": 0.5519407673322863, "percentage": 18.4, "elapsed_time": "4:28:12", "remaining_time": "19:49:16"} +{"current_steps": 1240, "total_steps": 6684, "loss": 0.5761, "lr": 5e-06, "epoch": 0.556428090643931, "percentage": 18.55, "elapsed_time": "4:30:23", "remaining_time": "19:47:06"} +{"current_steps": 1250, "total_steps": 6684, "loss": 0.57, "lr": 5e-06, "epoch": 0.5609154139555755, "percentage": 18.7, "elapsed_time": "4:32:34", "remaining_time": "19:44:55"} +{"current_steps": 1260, "total_steps": 6684, "loss": 0.5957, "lr": 5e-06, "epoch": 0.5654027372672201, "percentage": 18.85, "elapsed_time": "4:34:45", "remaining_time": "19:42:44"} +{"current_steps": 1270, "total_steps": 6684, "loss": 0.5913, "lr": 5e-06, "epoch": 0.5698900605788647, "percentage": 19.0, "elapsed_time": "4:36:55", "remaining_time": "19:40:32"} +{"current_steps": 1280, "total_steps": 6684, "loss": 0.5694, "lr": 5e-06, "epoch": 0.5743773838905093, "percentage": 19.15, "elapsed_time": "4:39:06", "remaining_time": "19:38:21"} +{"current_steps": 1290, "total_steps": 6684, "loss": 0.5679, "lr": 5e-06, "epoch": 0.5788647072021539, "percentage": 19.3, "elapsed_time": "4:41:17", "remaining_time": "19:36:10"} +{"current_steps": 1300, "total_steps": 6684, "loss": 0.5687, "lr": 5e-06, "epoch": 0.5833520305137985, "percentage": 19.45, "elapsed_time": "4:43:27", "remaining_time": "19:33:58"} +{"current_steps": 1310, "total_steps": 6684, "loss": 0.6019, "lr": 5e-06, "epoch": 0.5878393538254432, "percentage": 19.6, "elapsed_time": "4:45:38", "remaining_time": "19:31:46"} +{"current_steps": 1320, "total_steps": 6684, "loss": 0.5885, "lr": 5e-06, "epoch": 0.5923266771370878, "percentage": 19.75, "elapsed_time": "4:47:49", "remaining_time": "19:29:35"} +{"current_steps": 1330, "total_steps": 6684, "loss": 0.6015, "lr": 5e-06, "epoch": 0.5968140004487323, "percentage": 19.9, "elapsed_time": "4:49:59", "remaining_time": "19:27:24"} +{"current_steps": 1340, "total_steps": 6684, "loss": 0.5778, "lr": 5e-06, "epoch": 0.6013013237603769, "percentage": 20.05, "elapsed_time": "4:52:10", "remaining_time": "19:25:12"} +{"current_steps": 1350, "total_steps": 6684, "loss": 0.5577, "lr": 5e-06, "epoch": 0.6057886470720215, "percentage": 20.2, "elapsed_time": "4:54:21", "remaining_time": "19:23:01"} +{"current_steps": 1360, "total_steps": 6684, "loss": 0.5666, "lr": 5e-06, "epoch": 0.6102759703836661, "percentage": 20.35, "elapsed_time": "4:56:32", "remaining_time": "19:20:50"} +{"current_steps": 1370, "total_steps": 6684, "loss": 0.579, "lr": 5e-06, "epoch": 0.6147632936953108, "percentage": 20.5, "elapsed_time": "4:58:42", "remaining_time": "19:18:39"} +{"current_steps": 1380, "total_steps": 6684, "loss": 0.597, "lr": 5e-06, "epoch": 0.6192506170069554, "percentage": 20.65, "elapsed_time": "5:00:53", "remaining_time": "19:16:28"} +{"current_steps": 1390, "total_steps": 6684, "loss": 0.5764, "lr": 5e-06, "epoch": 0.6237379403186, "percentage": 20.8, "elapsed_time": "5:03:04", "remaining_time": "19:14:16"} +{"current_steps": 1400, "total_steps": 6684, "loss": 0.5834, "lr": 5e-06, "epoch": 0.6282252636302446, "percentage": 20.95, "elapsed_time": "5:05:14", "remaining_time": "19:12:05"} +{"current_steps": 1410, "total_steps": 6684, "loss": 0.565, "lr": 5e-06, "epoch": 0.6327125869418891, "percentage": 21.1, "elapsed_time": "5:07:25", "remaining_time": "19:09:54"} +{"current_steps": 1420, "total_steps": 6684, "loss": 0.5686, "lr": 5e-06, "epoch": 0.6371999102535337, "percentage": 21.24, "elapsed_time": "5:09:36", "remaining_time": "19:07:44"} +{"current_steps": 1430, "total_steps": 6684, "loss": 0.5591, "lr": 5e-06, "epoch": 0.6416872335651783, "percentage": 21.39, "elapsed_time": "5:11:47", "remaining_time": "19:05:33"} +{"current_steps": 1440, "total_steps": 6684, "loss": 0.5646, "lr": 5e-06, "epoch": 0.646174556876823, "percentage": 21.54, "elapsed_time": "5:13:58", "remaining_time": "19:03:22"} +{"current_steps": 1450, "total_steps": 6684, "loss": 0.5753, "lr": 5e-06, "epoch": 0.6506618801884676, "percentage": 21.69, "elapsed_time": "5:16:08", "remaining_time": "19:01:10"} +{"current_steps": 1460, "total_steps": 6684, "loss": 0.6129, "lr": 5e-06, "epoch": 0.6551492035001122, "percentage": 21.84, "elapsed_time": "5:18:19", "remaining_time": "18:58:59"} +{"current_steps": 1470, "total_steps": 6684, "loss": 0.5825, "lr": 5e-06, "epoch": 0.6596365268117568, "percentage": 21.99, "elapsed_time": "5:20:30", "remaining_time": "18:56:48"} +{"current_steps": 1480, "total_steps": 6684, "loss": 0.5832, "lr": 5e-06, "epoch": 0.6641238501234014, "percentage": 22.14, "elapsed_time": "5:22:41", "remaining_time": "18:54:37"} +{"current_steps": 1490, "total_steps": 6684, "loss": 0.6061, "lr": 5e-06, "epoch": 0.668611173435046, "percentage": 22.29, "elapsed_time": "5:24:51", "remaining_time": "18:52:26"} +{"current_steps": 1500, "total_steps": 6684, "loss": 0.579, "lr": 5e-06, "epoch": 0.6730984967466906, "percentage": 22.44, "elapsed_time": "5:27:02", "remaining_time": "18:50:15"} +{"current_steps": 1510, "total_steps": 6684, "loss": 0.5872, "lr": 5e-06, "epoch": 0.6775858200583352, "percentage": 22.59, "elapsed_time": "5:29:13", "remaining_time": "18:48:04"} +{"current_steps": 1520, "total_steps": 6684, "loss": 0.5694, "lr": 5e-06, "epoch": 0.6820731433699798, "percentage": 22.74, "elapsed_time": "5:31:24", "remaining_time": "18:45:53"} +{"current_steps": 1530, "total_steps": 6684, "loss": 0.5591, "lr": 5e-06, "epoch": 0.6865604666816244, "percentage": 22.89, "elapsed_time": "5:33:34", "remaining_time": "18:43:42"} +{"current_steps": 1540, "total_steps": 6684, "loss": 0.5543, "lr": 5e-06, "epoch": 0.691047789993269, "percentage": 23.04, "elapsed_time": "5:35:45", "remaining_time": "18:41:31"} +{"current_steps": 1550, "total_steps": 6684, "loss": 0.5584, "lr": 5e-06, "epoch": 0.6955351133049136, "percentage": 23.19, "elapsed_time": "5:37:56", "remaining_time": "18:39:20"} +{"current_steps": 1560, "total_steps": 6684, "loss": 0.5697, "lr": 5e-06, "epoch": 0.7000224366165583, "percentage": 23.34, "elapsed_time": "5:40:07", "remaining_time": "18:37:09"} +{"current_steps": 1570, "total_steps": 6684, "loss": 0.5913, "lr": 5e-06, "epoch": 0.7045097599282029, "percentage": 23.49, "elapsed_time": "5:42:17", "remaining_time": "18:34:58"} +{"current_steps": 1580, "total_steps": 6684, "loss": 0.5852, "lr": 5e-06, "epoch": 0.7089970832398474, "percentage": 23.64, "elapsed_time": "5:44:28", "remaining_time": "18:32:47"} +{"current_steps": 1590, "total_steps": 6684, "loss": 0.559, "lr": 5e-06, "epoch": 0.713484406551492, "percentage": 23.79, "elapsed_time": "5:46:39", "remaining_time": "18:30:36"} +{"current_steps": 1600, "total_steps": 6684, "loss": 0.5591, "lr": 5e-06, "epoch": 0.7179717298631366, "percentage": 23.94, "elapsed_time": "5:48:49", "remaining_time": "18:28:24"} +{"current_steps": 1610, "total_steps": 6684, "loss": 0.5757, "lr": 5e-06, "epoch": 0.7224590531747812, "percentage": 24.09, "elapsed_time": "5:51:00", "remaining_time": "18:26:13"} +{"current_steps": 1620, "total_steps": 6684, "loss": 0.5764, "lr": 5e-06, "epoch": 0.7269463764864258, "percentage": 24.24, "elapsed_time": "5:53:11", "remaining_time": "18:24:02"} +{"current_steps": 1630, "total_steps": 6684, "loss": 0.5726, "lr": 5e-06, "epoch": 0.7314336997980705, "percentage": 24.39, "elapsed_time": "5:55:22", "remaining_time": "18:21:51"} +{"current_steps": 1640, "total_steps": 6684, "loss": 0.5761, "lr": 5e-06, "epoch": 0.7359210231097151, "percentage": 24.54, "elapsed_time": "5:57:32", "remaining_time": "18:19:40"} +{"current_steps": 1650, "total_steps": 6684, "loss": 0.5892, "lr": 5e-06, "epoch": 0.7404083464213597, "percentage": 24.69, "elapsed_time": "5:59:43", "remaining_time": "18:17:29"} +{"current_steps": 1660, "total_steps": 6684, "loss": 0.5717, "lr": 5e-06, "epoch": 0.7448956697330043, "percentage": 24.84, "elapsed_time": "6:01:54", "remaining_time": "18:15:18"} +{"current_steps": 1670, "total_steps": 6684, "loss": 0.5817, "lr": 5e-06, "epoch": 0.7493829930446488, "percentage": 24.99, "elapsed_time": "6:04:05", "remaining_time": "18:13:07"} +{"current_steps": 1680, "total_steps": 6684, "loss": 0.5592, "lr": 5e-06, "epoch": 0.7538703163562934, "percentage": 25.13, "elapsed_time": "6:06:15", "remaining_time": "18:10:56"} +{"current_steps": 1690, "total_steps": 6684, "loss": 0.5862, "lr": 5e-06, "epoch": 0.7583576396679381, "percentage": 25.28, "elapsed_time": "6:08:26", "remaining_time": "18:08:45"} +{"current_steps": 1700, "total_steps": 6684, "loss": 0.5477, "lr": 5e-06, "epoch": 0.7628449629795827, "percentage": 25.43, "elapsed_time": "6:10:37", "remaining_time": "18:06:34"} +{"current_steps": 1710, "total_steps": 6684, "loss": 0.5515, "lr": 5e-06, "epoch": 0.7673322862912273, "percentage": 25.58, "elapsed_time": "6:12:48", "remaining_time": "18:04:23"} +{"current_steps": 1720, "total_steps": 6684, "loss": 0.5545, "lr": 5e-06, "epoch": 0.7718196096028719, "percentage": 25.73, "elapsed_time": "6:14:58", "remaining_time": "18:02:12"} +{"current_steps": 1730, "total_steps": 6684, "loss": 0.5638, "lr": 5e-06, "epoch": 0.7763069329145165, "percentage": 25.88, "elapsed_time": "6:17:09", "remaining_time": "18:00:01"} +{"current_steps": 1740, "total_steps": 6684, "loss": 0.5706, "lr": 5e-06, "epoch": 0.780794256226161, "percentage": 26.03, "elapsed_time": "6:19:20", "remaining_time": "17:57:51"} +{"current_steps": 1750, "total_steps": 6684, "loss": 0.5759, "lr": 5e-06, "epoch": 0.7852815795378058, "percentage": 26.18, "elapsed_time": "6:21:31", "remaining_time": "17:55:40"} +{"current_steps": 1760, "total_steps": 6684, "loss": 0.5618, "lr": 5e-06, "epoch": 0.7897689028494503, "percentage": 26.33, "elapsed_time": "6:23:42", "remaining_time": "17:53:29"} +{"current_steps": 1770, "total_steps": 6684, "loss": 0.5794, "lr": 5e-06, "epoch": 0.7942562261610949, "percentage": 26.48, "elapsed_time": "6:25:52", "remaining_time": "17:51:18"} +{"current_steps": 1780, "total_steps": 6684, "loss": 0.5725, "lr": 5e-06, "epoch": 0.7987435494727395, "percentage": 26.63, "elapsed_time": "6:28:03", "remaining_time": "17:49:07"} +{"current_steps": 1790, "total_steps": 6684, "loss": 0.5651, "lr": 5e-06, "epoch": 0.8032308727843841, "percentage": 26.78, "elapsed_time": "6:30:14", "remaining_time": "17:46:56"} +{"current_steps": 1800, "total_steps": 6684, "loss": 0.5575, "lr": 5e-06, "epoch": 0.8077181960960287, "percentage": 26.93, "elapsed_time": "6:32:25", "remaining_time": "17:44:46"} +{"current_steps": 1810, "total_steps": 6684, "loss": 0.5598, "lr": 5e-06, "epoch": 0.8122055194076733, "percentage": 27.08, "elapsed_time": "6:34:36", "remaining_time": "17:42:35"} +{"current_steps": 1820, "total_steps": 6684, "loss": 0.5598, "lr": 5e-06, "epoch": 0.816692842719318, "percentage": 27.23, "elapsed_time": "6:36:46", "remaining_time": "17:40:24"} +{"current_steps": 1830, "total_steps": 6684, "loss": 0.5723, "lr": 5e-06, "epoch": 0.8211801660309626, "percentage": 27.38, "elapsed_time": "6:38:57", "remaining_time": "17:38:14"} +{"current_steps": 1840, "total_steps": 6684, "loss": 0.5452, "lr": 5e-06, "epoch": 0.8256674893426071, "percentage": 27.53, "elapsed_time": "6:41:08", "remaining_time": "17:36:03"} +{"current_steps": 1850, "total_steps": 6684, "loss": 0.6093, "lr": 5e-06, "epoch": 0.8301548126542517, "percentage": 27.68, "elapsed_time": "6:43:19", "remaining_time": "17:33:53"} +{"current_steps": 1860, "total_steps": 6684, "loss": 0.5652, "lr": 5e-06, "epoch": 0.8346421359658963, "percentage": 27.83, "elapsed_time": "6:45:30", "remaining_time": "17:31:42"} +{"current_steps": 1870, "total_steps": 6684, "loss": 0.5578, "lr": 5e-06, "epoch": 0.8391294592775409, "percentage": 27.98, "elapsed_time": "6:47:41", "remaining_time": "17:29:31"} +{"current_steps": 1880, "total_steps": 6684, "loss": 0.5913, "lr": 5e-06, "epoch": 0.8436167825891856, "percentage": 28.13, "elapsed_time": "6:49:52", "remaining_time": "17:27:20"} +{"current_steps": 1890, "total_steps": 6684, "loss": 0.5506, "lr": 5e-06, "epoch": 0.8481041059008302, "percentage": 28.28, "elapsed_time": "6:52:02", "remaining_time": "17:25:09"} +{"current_steps": 1900, "total_steps": 6684, "loss": 0.5755, "lr": 5e-06, "epoch": 0.8525914292124748, "percentage": 28.43, "elapsed_time": "6:54:13", "remaining_time": "17:22:58"} +{"current_steps": 1910, "total_steps": 6684, "loss": 0.5705, "lr": 5e-06, "epoch": 0.8570787525241194, "percentage": 28.58, "elapsed_time": "6:56:24", "remaining_time": "17:20:47"} +{"current_steps": 1920, "total_steps": 6684, "loss": 0.5744, "lr": 5e-06, "epoch": 0.861566075835764, "percentage": 28.73, "elapsed_time": "6:58:34", "remaining_time": "17:18:36"} +{"current_steps": 1930, "total_steps": 6684, "loss": 0.5551, "lr": 5e-06, "epoch": 0.8660533991474085, "percentage": 28.87, "elapsed_time": "7:00:45", "remaining_time": "17:16:25"} +{"current_steps": 1940, "total_steps": 6684, "loss": 0.5724, "lr": 5e-06, "epoch": 0.8705407224590532, "percentage": 29.02, "elapsed_time": "7:02:56", "remaining_time": "17:14:14"} +{"current_steps": 1950, "total_steps": 6684, "loss": 0.5509, "lr": 5e-06, "epoch": 0.8750280457706978, "percentage": 29.17, "elapsed_time": "7:05:07", "remaining_time": "17:12:03"} +{"current_steps": 1960, "total_steps": 6684, "loss": 0.5712, "lr": 5e-06, "epoch": 0.8795153690823424, "percentage": 29.32, "elapsed_time": "7:07:18", "remaining_time": "17:09:52"} +{"current_steps": 1970, "total_steps": 6684, "loss": 0.5841, "lr": 5e-06, "epoch": 0.884002692393987, "percentage": 29.47, "elapsed_time": "7:09:28", "remaining_time": "17:07:42"} +{"current_steps": 1980, "total_steps": 6684, "loss": 0.5559, "lr": 5e-06, "epoch": 0.8884900157056316, "percentage": 29.62, "elapsed_time": "7:11:39", "remaining_time": "17:05:31"} +{"current_steps": 1990, "total_steps": 6684, "loss": 0.5424, "lr": 5e-06, "epoch": 0.8929773390172762, "percentage": 29.77, "elapsed_time": "7:13:50", "remaining_time": "17:03:20"} +{"current_steps": 2000, "total_steps": 6684, "loss": 0.5614, "lr": 5e-06, "epoch": 0.8974646623289207, "percentage": 29.92, "elapsed_time": "7:16:01", "remaining_time": "17:01:10"} +{"current_steps": 2010, "total_steps": 6684, "loss": 0.5756, "lr": 5e-06, "epoch": 0.9019519856405654, "percentage": 30.07, "elapsed_time": "7:18:12", "remaining_time": "16:58:59"} +{"current_steps": 2020, "total_steps": 6684, "loss": 0.5938, "lr": 5e-06, "epoch": 0.90643930895221, "percentage": 30.22, "elapsed_time": "7:20:23", "remaining_time": "16:56:48"} +{"current_steps": 2030, "total_steps": 6684, "loss": 0.5793, "lr": 5e-06, "epoch": 0.9109266322638546, "percentage": 30.37, "elapsed_time": "7:22:33", "remaining_time": "16:54:37"} +{"current_steps": 2040, "total_steps": 6684, "loss": 0.5702, "lr": 5e-06, "epoch": 0.9154139555754992, "percentage": 30.52, "elapsed_time": "7:24:44", "remaining_time": "16:52:26"} +{"current_steps": 2050, "total_steps": 6684, "loss": 0.5443, "lr": 5e-06, "epoch": 0.9199012788871438, "percentage": 30.67, "elapsed_time": "7:26:55", "remaining_time": "16:50:15"} +{"current_steps": 2060, "total_steps": 6684, "loss": 0.5726, "lr": 5e-06, "epoch": 0.9243886021987884, "percentage": 30.82, "elapsed_time": "7:29:05", "remaining_time": "16:48:04"} +{"current_steps": 2070, "total_steps": 6684, "loss": 0.5605, "lr": 5e-06, "epoch": 0.9288759255104331, "percentage": 30.97, "elapsed_time": "7:31:16", "remaining_time": "16:45:53"} +{"current_steps": 2080, "total_steps": 6684, "loss": 0.5799, "lr": 5e-06, "epoch": 0.9333632488220777, "percentage": 31.12, "elapsed_time": "7:33:27", "remaining_time": "16:43:43"} +{"current_steps": 2090, "total_steps": 6684, "loss": 0.5745, "lr": 5e-06, "epoch": 0.9378505721337222, "percentage": 31.27, "elapsed_time": "7:35:38", "remaining_time": "16:41:32"} +{"current_steps": 2100, "total_steps": 6684, "loss": 0.5465, "lr": 5e-06, "epoch": 0.9423378954453668, "percentage": 31.42, "elapsed_time": "7:37:49", "remaining_time": "16:39:21"} +{"current_steps": 2110, "total_steps": 6684, "loss": 0.5526, "lr": 5e-06, "epoch": 0.9468252187570114, "percentage": 31.57, "elapsed_time": "7:40:00", "remaining_time": "16:37:10"} +{"current_steps": 2120, "total_steps": 6684, "loss": 0.5737, "lr": 5e-06, "epoch": 0.951312542068656, "percentage": 31.72, "elapsed_time": "7:42:11", "remaining_time": "16:35:00"} +{"current_steps": 2130, "total_steps": 6684, "loss": 0.5493, "lr": 5e-06, "epoch": 0.9557998653803007, "percentage": 31.87, "elapsed_time": "7:44:21", "remaining_time": "16:32:49"} +{"current_steps": 2140, "total_steps": 6684, "loss": 0.5461, "lr": 5e-06, "epoch": 0.9602871886919453, "percentage": 32.02, "elapsed_time": "7:46:32", "remaining_time": "16:30:38"} +{"current_steps": 2150, "total_steps": 6684, "loss": 0.6057, "lr": 5e-06, "epoch": 0.9647745120035899, "percentage": 32.17, "elapsed_time": "7:48:43", "remaining_time": "16:28:27"} +{"current_steps": 2160, "total_steps": 6684, "loss": 0.5459, "lr": 5e-06, "epoch": 0.9692618353152345, "percentage": 32.32, "elapsed_time": "7:50:54", "remaining_time": "16:26:17"} +{"current_steps": 2170, "total_steps": 6684, "loss": 0.5471, "lr": 5e-06, "epoch": 0.973749158626879, "percentage": 32.47, "elapsed_time": "7:53:05", "remaining_time": "16:24:06"} +{"current_steps": 2180, "total_steps": 6684, "loss": 0.5689, "lr": 5e-06, "epoch": 0.9782364819385236, "percentage": 32.62, "elapsed_time": "7:55:16", "remaining_time": "16:21:55"} +{"current_steps": 2190, "total_steps": 6684, "loss": 0.5622, "lr": 5e-06, "epoch": 0.9827238052501682, "percentage": 32.76, "elapsed_time": "7:57:26", "remaining_time": "16:19:45"} +{"current_steps": 2200, "total_steps": 6684, "loss": 0.5519, "lr": 5e-06, "epoch": 0.9872111285618129, "percentage": 32.91, "elapsed_time": "7:59:37", "remaining_time": "16:17:34"} +{"current_steps": 2210, "total_steps": 6684, "loss": 0.5561, "lr": 5e-06, "epoch": 0.9916984518734575, "percentage": 33.06, "elapsed_time": "8:01:48", "remaining_time": "16:15:23"} +{"current_steps": 2220, "total_steps": 6684, "loss": 0.5712, "lr": 5e-06, "epoch": 0.9961857751851021, "percentage": 33.21, "elapsed_time": "8:03:59", "remaining_time": "16:13:12"} +{"current_steps": 2228, "total_steps": 6684, "eval_loss": 0.567927360534668, "epoch": 0.9997756338344178, "percentage": 33.33, "elapsed_time": "8:15:08", "remaining_time": "16:30:17"} +{"current_steps": 2230, "total_steps": 6684, "loss": 0.566, "lr": 5e-06, "epoch": 1.0006730984967467, "percentage": 33.36, "elapsed_time": "8:16:34", "remaining_time": "16:31:49"} +{"current_steps": 2240, "total_steps": 6684, "loss": 0.5081, "lr": 5e-06, "epoch": 1.0051604218083914, "percentage": 33.51, "elapsed_time": "8:18:45", "remaining_time": "16:29:30"} +{"current_steps": 2250, "total_steps": 6684, "loss": 0.4975, "lr": 5e-06, "epoch": 1.0096477451200359, "percentage": 33.66, "elapsed_time": "8:20:56", "remaining_time": "16:27:11"} +{"current_steps": 2260, "total_steps": 6684, "loss": 0.4866, "lr": 5e-06, "epoch": 1.0141350684316806, "percentage": 33.81, "elapsed_time": "8:23:07", "remaining_time": "16:24:52"} +{"current_steps": 2270, "total_steps": 6684, "loss": 0.4855, "lr": 5e-06, "epoch": 1.018622391743325, "percentage": 33.96, "elapsed_time": "8:25:18", "remaining_time": "16:22:33"} +{"current_steps": 2280, "total_steps": 6684, "loss": 0.5484, "lr": 5e-06, "epoch": 1.0231097150549697, "percentage": 34.11, "elapsed_time": "8:27:29", "remaining_time": "16:20:14"} +{"current_steps": 2290, "total_steps": 6684, "loss": 0.5021, "lr": 5e-06, "epoch": 1.0275970383666144, "percentage": 34.26, "elapsed_time": "8:29:39", "remaining_time": "16:17:56"} +{"current_steps": 2300, "total_steps": 6684, "loss": 0.541, "lr": 5e-06, "epoch": 1.032084361678259, "percentage": 34.41, "elapsed_time": "8:31:50", "remaining_time": "16:15:37"} +{"current_steps": 2310, "total_steps": 6684, "loss": 0.4939, "lr": 5e-06, "epoch": 1.0365716849899036, "percentage": 34.56, "elapsed_time": "8:34:01", "remaining_time": "16:13:19"} +{"current_steps": 2320, "total_steps": 6684, "loss": 0.4923, "lr": 5e-06, "epoch": 1.041059008301548, "percentage": 34.71, "elapsed_time": "8:36:12", "remaining_time": "16:11:00"} +{"current_steps": 2330, "total_steps": 6684, "loss": 0.5309, "lr": 5e-06, "epoch": 1.0455463316131928, "percentage": 34.86, "elapsed_time": "8:38:23", "remaining_time": "16:08:42"} +{"current_steps": 2340, "total_steps": 6684, "loss": 0.4871, "lr": 5e-06, "epoch": 1.0500336549248372, "percentage": 35.01, "elapsed_time": "8:40:34", "remaining_time": "16:06:24"} +{"current_steps": 2350, "total_steps": 6684, "loss": 0.5042, "lr": 5e-06, "epoch": 1.054520978236482, "percentage": 35.16, "elapsed_time": "8:42:45", "remaining_time": "16:04:05"} +{"current_steps": 2360, "total_steps": 6684, "loss": 0.5268, "lr": 5e-06, "epoch": 1.0590083015481266, "percentage": 35.31, "elapsed_time": "8:44:56", "remaining_time": "16:01:47"} +{"current_steps": 2370, "total_steps": 6684, "loss": 0.4849, "lr": 5e-06, "epoch": 1.0634956248597711, "percentage": 35.46, "elapsed_time": "8:47:07", "remaining_time": "15:59:29"} +{"current_steps": 2380, "total_steps": 6684, "loss": 0.4897, "lr": 5e-06, "epoch": 1.0679829481714158, "percentage": 35.61, "elapsed_time": "8:49:18", "remaining_time": "15:57:11"} +{"current_steps": 2390, "total_steps": 6684, "loss": 0.524, "lr": 5e-06, "epoch": 1.0724702714830603, "percentage": 35.76, "elapsed_time": "8:51:28", "remaining_time": "15:54:53"} +{"current_steps": 2400, "total_steps": 6684, "loss": 0.4881, "lr": 5e-06, "epoch": 1.076957594794705, "percentage": 35.91, "elapsed_time": "8:53:39", "remaining_time": "15:52:35"} +{"current_steps": 2410, "total_steps": 6684, "loss": 0.5297, "lr": 5e-06, "epoch": 1.0814449181063495, "percentage": 36.06, "elapsed_time": "8:55:50", "remaining_time": "15:50:17"} +{"current_steps": 2420, "total_steps": 6684, "loss": 0.5155, "lr": 5e-06, "epoch": 1.0859322414179942, "percentage": 36.21, "elapsed_time": "8:58:01", "remaining_time": "15:47:59"} +{"current_steps": 2430, "total_steps": 6684, "loss": 0.4981, "lr": 5e-06, "epoch": 1.0904195647296389, "percentage": 36.36, "elapsed_time": "9:00:12", "remaining_time": "15:45:42"} +{"current_steps": 2440, "total_steps": 6684, "loss": 0.5053, "lr": 5e-06, "epoch": 1.0949068880412833, "percentage": 36.51, "elapsed_time": "9:02:23", "remaining_time": "15:43:24"} +{"current_steps": 2450, "total_steps": 6684, "loss": 0.5056, "lr": 5e-06, "epoch": 1.099394211352928, "percentage": 36.65, "elapsed_time": "9:04:34", "remaining_time": "15:41:06"} +{"current_steps": 2460, "total_steps": 6684, "loss": 0.5204, "lr": 5e-06, "epoch": 1.1038815346645725, "percentage": 36.8, "elapsed_time": "9:06:45", "remaining_time": "15:38:49"} +{"current_steps": 2470, "total_steps": 6684, "loss": 0.5004, "lr": 5e-06, "epoch": 1.1083688579762172, "percentage": 36.95, "elapsed_time": "9:08:56", "remaining_time": "15:36:31"} +{"current_steps": 2480, "total_steps": 6684, "loss": 0.499, "lr": 5e-06, "epoch": 1.112856181287862, "percentage": 37.1, "elapsed_time": "9:11:07", "remaining_time": "15:34:13"} +{"current_steps": 2490, "total_steps": 6684, "loss": 0.4921, "lr": 5e-06, "epoch": 1.1173435045995064, "percentage": 37.25, "elapsed_time": "9:13:17", "remaining_time": "15:31:56"} +{"current_steps": 2500, "total_steps": 6684, "loss": 0.5108, "lr": 5e-06, "epoch": 1.121830827911151, "percentage": 37.4, "elapsed_time": "9:15:28", "remaining_time": "15:29:38"} +{"current_steps": 2510, "total_steps": 6684, "loss": 0.5003, "lr": 5e-06, "epoch": 1.1263181512227955, "percentage": 37.55, "elapsed_time": "9:17:39", "remaining_time": "15:27:21"} +{"current_steps": 2520, "total_steps": 6684, "loss": 0.475, "lr": 5e-06, "epoch": 1.1308054745344402, "percentage": 37.7, "elapsed_time": "9:19:50", "remaining_time": "15:25:03"} +{"current_steps": 2530, "total_steps": 6684, "loss": 0.5209, "lr": 5e-06, "epoch": 1.1352927978460847, "percentage": 37.85, "elapsed_time": "9:22:00", "remaining_time": "15:22:46"} +{"current_steps": 2540, "total_steps": 6684, "loss": 0.4916, "lr": 5e-06, "epoch": 1.1397801211577294, "percentage": 38.0, "elapsed_time": "9:24:11", "remaining_time": "15:20:28"} +{"current_steps": 2550, "total_steps": 6684, "loss": 0.5013, "lr": 5e-06, "epoch": 1.144267444469374, "percentage": 38.15, "elapsed_time": "9:26:22", "remaining_time": "15:18:11"} +{"current_steps": 2560, "total_steps": 6684, "loss": 0.5332, "lr": 5e-06, "epoch": 1.1487547677810186, "percentage": 38.3, "elapsed_time": "9:28:33", "remaining_time": "15:15:54"} +{"current_steps": 2570, "total_steps": 6684, "loss": 0.5048, "lr": 5e-06, "epoch": 1.1532420910926633, "percentage": 38.45, "elapsed_time": "9:30:43", "remaining_time": "15:13:36"} +{"current_steps": 2580, "total_steps": 6684, "loss": 0.5141, "lr": 5e-06, "epoch": 1.1577294144043078, "percentage": 38.6, "elapsed_time": "9:32:54", "remaining_time": "15:11:19"} +{"current_steps": 2590, "total_steps": 6684, "loss": 0.5144, "lr": 5e-06, "epoch": 1.1622167377159525, "percentage": 38.75, "elapsed_time": "9:35:05", "remaining_time": "15:09:02"} +{"current_steps": 2600, "total_steps": 6684, "loss": 0.5208, "lr": 5e-06, "epoch": 1.166704061027597, "percentage": 38.9, "elapsed_time": "9:37:16", "remaining_time": "15:06:45"} +{"current_steps": 2610, "total_steps": 6684, "loss": 0.4987, "lr": 5e-06, "epoch": 1.1711913843392416, "percentage": 39.05, "elapsed_time": "9:39:27", "remaining_time": "15:04:28"} +{"current_steps": 2620, "total_steps": 6684, "loss": 0.5132, "lr": 5e-06, "epoch": 1.1756787076508863, "percentage": 39.2, "elapsed_time": "9:41:38", "remaining_time": "15:02:11"} +{"current_steps": 2630, "total_steps": 6684, "loss": 0.496, "lr": 5e-06, "epoch": 1.1801660309625308, "percentage": 39.35, "elapsed_time": "9:43:49", "remaining_time": "14:59:55"} +{"current_steps": 2640, "total_steps": 6684, "loss": 0.4827, "lr": 5e-06, "epoch": 1.1846533542741755, "percentage": 39.5, "elapsed_time": "9:45:59", "remaining_time": "14:57:38"} +{"current_steps": 2650, "total_steps": 6684, "loss": 0.5073, "lr": 5e-06, "epoch": 1.18914067758582, "percentage": 39.65, "elapsed_time": "9:48:10", "remaining_time": "14:55:21"} +{"current_steps": 2660, "total_steps": 6684, "loss": 0.5422, "lr": 5e-06, "epoch": 1.1936280008974647, "percentage": 39.8, "elapsed_time": "9:50:21", "remaining_time": "14:53:04"} +{"current_steps": 2670, "total_steps": 6684, "loss": 0.519, "lr": 5e-06, "epoch": 1.1981153242091094, "percentage": 39.95, "elapsed_time": "9:52:32", "remaining_time": "14:50:48"} +{"current_steps": 2680, "total_steps": 6684, "loss": 0.497, "lr": 5e-06, "epoch": 1.2026026475207539, "percentage": 40.1, "elapsed_time": "9:54:43", "remaining_time": "14:48:31"} +{"current_steps": 2690, "total_steps": 6684, "loss": 0.5058, "lr": 5e-06, "epoch": 1.2070899708323986, "percentage": 40.25, "elapsed_time": "9:56:53", "remaining_time": "14:46:14"} +{"current_steps": 2700, "total_steps": 6684, "loss": 0.4958, "lr": 5e-06, "epoch": 1.211577294144043, "percentage": 40.39, "elapsed_time": "9:59:04", "remaining_time": "14:43:58"} +{"current_steps": 2710, "total_steps": 6684, "loss": 0.4948, "lr": 5e-06, "epoch": 1.2160646174556877, "percentage": 40.54, "elapsed_time": "10:01:15", "remaining_time": "14:41:42"} +{"current_steps": 2720, "total_steps": 6684, "loss": 0.4965, "lr": 5e-06, "epoch": 1.2205519407673322, "percentage": 40.69, "elapsed_time": "10:03:26", "remaining_time": "14:39:25"} +{"current_steps": 2730, "total_steps": 6684, "loss": 0.4772, "lr": 5e-06, "epoch": 1.225039264078977, "percentage": 40.84, "elapsed_time": "10:05:37", "remaining_time": "14:37:09"} +{"current_steps": 2740, "total_steps": 6684, "loss": 0.5273, "lr": 5e-06, "epoch": 1.2295265873906214, "percentage": 40.99, "elapsed_time": "10:07:48", "remaining_time": "14:34:52"} +{"current_steps": 2750, "total_steps": 6684, "loss": 0.5089, "lr": 5e-06, "epoch": 1.234013910702266, "percentage": 41.14, "elapsed_time": "10:09:58", "remaining_time": "14:32:36"} +{"current_steps": 2760, "total_steps": 6684, "loss": 0.4945, "lr": 5e-06, "epoch": 1.2385012340139108, "percentage": 41.29, "elapsed_time": "10:12:09", "remaining_time": "14:30:19"} +{"current_steps": 2770, "total_steps": 6684, "loss": 0.4884, "lr": 5e-06, "epoch": 1.2429885573255552, "percentage": 41.44, "elapsed_time": "10:14:20", "remaining_time": "14:28:03"} +{"current_steps": 2780, "total_steps": 6684, "loss": 0.505, "lr": 5e-06, "epoch": 1.2474758806372, "percentage": 41.59, "elapsed_time": "10:16:31", "remaining_time": "14:25:47"} +{"current_steps": 2790, "total_steps": 6684, "loss": 0.5335, "lr": 5e-06, "epoch": 1.2519632039488444, "percentage": 41.74, "elapsed_time": "10:18:41", "remaining_time": "14:23:31"} +{"current_steps": 2800, "total_steps": 6684, "loss": 0.477, "lr": 5e-06, "epoch": 1.2564505272604891, "percentage": 41.89, "elapsed_time": "10:20:52", "remaining_time": "14:21:14"} +{"current_steps": 2810, "total_steps": 6684, "loss": 0.4984, "lr": 5e-06, "epoch": 1.2609378505721338, "percentage": 42.04, "elapsed_time": "10:23:03", "remaining_time": "14:18:58"} +{"current_steps": 2820, "total_steps": 6684, "loss": 0.5073, "lr": 5e-06, "epoch": 1.2654251738837783, "percentage": 42.19, "elapsed_time": "10:25:14", "remaining_time": "14:16:42"} +{"current_steps": 2830, "total_steps": 6684, "loss": 0.4989, "lr": 5e-06, "epoch": 1.269912497195423, "percentage": 42.34, "elapsed_time": "10:27:25", "remaining_time": "14:14:26"} +{"current_steps": 2840, "total_steps": 6684, "loss": 0.5013, "lr": 5e-06, "epoch": 1.2743998205070675, "percentage": 42.49, "elapsed_time": "10:29:35", "remaining_time": "14:12:10"} +{"current_steps": 2850, "total_steps": 6684, "loss": 0.4843, "lr": 5e-06, "epoch": 1.2788871438187122, "percentage": 42.64, "elapsed_time": "10:31:46", "remaining_time": "14:09:54"} +{"current_steps": 2860, "total_steps": 6684, "loss": 0.5102, "lr": 5e-06, "epoch": 1.2833744671303569, "percentage": 42.79, "elapsed_time": "10:33:57", "remaining_time": "14:07:38"} +{"current_steps": 2870, "total_steps": 6684, "loss": 0.5308, "lr": 5e-06, "epoch": 1.2878617904420013, "percentage": 42.94, "elapsed_time": "10:36:08", "remaining_time": "14:05:22"} +{"current_steps": 2880, "total_steps": 6684, "loss": 0.5239, "lr": 5e-06, "epoch": 1.292349113753646, "percentage": 43.09, "elapsed_time": "10:38:18", "remaining_time": "14:03:06"} +{"current_steps": 2890, "total_steps": 6684, "loss": 0.5021, "lr": 5e-06, "epoch": 1.2968364370652905, "percentage": 43.24, "elapsed_time": "10:40:29", "remaining_time": "14:00:50"} +{"current_steps": 2900, "total_steps": 6684, "loss": 0.4941, "lr": 5e-06, "epoch": 1.3013237603769352, "percentage": 43.39, "elapsed_time": "10:42:40", "remaining_time": "13:58:34"} +{"current_steps": 2910, "total_steps": 6684, "loss": 0.505, "lr": 5e-06, "epoch": 1.30581108368858, "percentage": 43.54, "elapsed_time": "10:44:51", "remaining_time": "13:56:18"} +{"current_steps": 2920, "total_steps": 6684, "loss": 0.4912, "lr": 5e-06, "epoch": 1.3102984070002244, "percentage": 43.69, "elapsed_time": "10:47:01", "remaining_time": "13:54:03"} +{"current_steps": 2930, "total_steps": 6684, "loss": 0.4913, "lr": 5e-06, "epoch": 1.3147857303118688, "percentage": 43.84, "elapsed_time": "10:49:12", "remaining_time": "13:51:47"} +{"current_steps": 2940, "total_steps": 6684, "loss": 0.486, "lr": 5e-06, "epoch": 1.3192730536235135, "percentage": 43.99, "elapsed_time": "10:51:23", "remaining_time": "13:49:31"} +{"current_steps": 2950, "total_steps": 6684, "loss": 0.4908, "lr": 5e-06, "epoch": 1.3237603769351582, "percentage": 44.14, "elapsed_time": "10:53:34", "remaining_time": "13:47:16"} +{"current_steps": 2960, "total_steps": 6684, "loss": 0.5293, "lr": 5e-06, "epoch": 1.3282477002468027, "percentage": 44.28, "elapsed_time": "10:55:45", "remaining_time": "13:45:00"} +{"current_steps": 2970, "total_steps": 6684, "loss": 0.4739, "lr": 5e-06, "epoch": 1.3327350235584474, "percentage": 44.43, "elapsed_time": "10:57:56", "remaining_time": "13:42:45"} +{"current_steps": 2980, "total_steps": 6684, "loss": 0.482, "lr": 5e-06, "epoch": 1.337222346870092, "percentage": 44.58, "elapsed_time": "11:00:06", "remaining_time": "13:40:29"} +{"current_steps": 2990, "total_steps": 6684, "loss": 0.4936, "lr": 5e-06, "epoch": 1.3417096701817366, "percentage": 44.73, "elapsed_time": "11:02:17", "remaining_time": "13:38:14"} +{"current_steps": 3000, "total_steps": 6684, "loss": 0.4977, "lr": 5e-06, "epoch": 1.3461969934933813, "percentage": 44.88, "elapsed_time": "11:04:28", "remaining_time": "13:35:58"} +{"current_steps": 3010, "total_steps": 6684, "loss": 0.5232, "lr": 5e-06, "epoch": 1.3506843168050258, "percentage": 45.03, "elapsed_time": "11:06:39", "remaining_time": "13:33:43"} +{"current_steps": 3020, "total_steps": 6684, "loss": 0.5085, "lr": 5e-06, "epoch": 1.3551716401166705, "percentage": 45.18, "elapsed_time": "11:08:50", "remaining_time": "13:31:27"} +{"current_steps": 3030, "total_steps": 6684, "loss": 0.4971, "lr": 5e-06, "epoch": 1.359658963428315, "percentage": 45.33, "elapsed_time": "11:11:00", "remaining_time": "13:29:12"} +{"current_steps": 3040, "total_steps": 6684, "loss": 0.5122, "lr": 5e-06, "epoch": 1.3641462867399596, "percentage": 45.48, "elapsed_time": "11:13:11", "remaining_time": "13:26:56"} +{"current_steps": 3050, "total_steps": 6684, "loss": 0.5167, "lr": 5e-06, "epoch": 1.3686336100516043, "percentage": 45.63, "elapsed_time": "11:15:22", "remaining_time": "13:24:41"} +{"current_steps": 3060, "total_steps": 6684, "loss": 0.509, "lr": 5e-06, "epoch": 1.3731209333632488, "percentage": 45.78, "elapsed_time": "11:17:33", "remaining_time": "13:22:26"} +{"current_steps": 3070, "total_steps": 6684, "loss": 0.5103, "lr": 5e-06, "epoch": 1.3776082566748935, "percentage": 45.93, "elapsed_time": "11:19:44", "remaining_time": "13:20:10"} +{"current_steps": 3080, "total_steps": 6684, "loss": 0.5198, "lr": 5e-06, "epoch": 1.382095579986538, "percentage": 46.08, "elapsed_time": "11:21:54", "remaining_time": "13:17:55"} +{"current_steps": 3090, "total_steps": 6684, "loss": 0.5064, "lr": 5e-06, "epoch": 1.3865829032981827, "percentage": 46.23, "elapsed_time": "11:24:05", "remaining_time": "13:15:40"} +{"current_steps": 3100, "total_steps": 6684, "loss": 0.5012, "lr": 5e-06, "epoch": 1.3910702266098274, "percentage": 46.38, "elapsed_time": "11:26:16", "remaining_time": "13:13:25"} +{"current_steps": 3110, "total_steps": 6684, "loss": 0.4892, "lr": 5e-06, "epoch": 1.3955575499214719, "percentage": 46.53, "elapsed_time": "11:28:27", "remaining_time": "13:11:10"} +{"current_steps": 3120, "total_steps": 6684, "loss": 0.505, "lr": 5e-06, "epoch": 1.4000448732331163, "percentage": 46.68, "elapsed_time": "11:30:38", "remaining_time": "13:08:55"} +{"current_steps": 3130, "total_steps": 6684, "loss": 0.4866, "lr": 5e-06, "epoch": 1.404532196544761, "percentage": 46.83, "elapsed_time": "11:32:49", "remaining_time": "13:06:40"} +{"current_steps": 3140, "total_steps": 6684, "loss": 0.5056, "lr": 5e-06, "epoch": 1.4090195198564057, "percentage": 46.98, "elapsed_time": "11:35:00", "remaining_time": "13:04:25"} +{"current_steps": 3150, "total_steps": 6684, "loss": 0.5281, "lr": 5e-06, "epoch": 1.4135068431680502, "percentage": 47.13, "elapsed_time": "11:37:11", "remaining_time": "13:02:10"} +{"current_steps": 3160, "total_steps": 6684, "loss": 0.5207, "lr": 5e-06, "epoch": 1.417994166479695, "percentage": 47.28, "elapsed_time": "11:39:22", "remaining_time": "12:59:55"} +{"current_steps": 3170, "total_steps": 6684, "loss": 0.5298, "lr": 5e-06, "epoch": 1.4224814897913394, "percentage": 47.43, "elapsed_time": "11:41:33", "remaining_time": "12:57:41"} +{"current_steps": 3180, "total_steps": 6684, "loss": 0.5124, "lr": 5e-06, "epoch": 1.426968813102984, "percentage": 47.58, "elapsed_time": "11:43:44", "remaining_time": "12:55:26"} +{"current_steps": 3190, "total_steps": 6684, "loss": 0.4963, "lr": 5e-06, "epoch": 1.4314561364146288, "percentage": 47.73, "elapsed_time": "11:45:55", "remaining_time": "12:53:11"} +{"current_steps": 3200, "total_steps": 6684, "loss": 0.5054, "lr": 5e-06, "epoch": 1.4359434597262732, "percentage": 47.88, "elapsed_time": "11:48:06", "remaining_time": "12:50:56"} +{"current_steps": 3210, "total_steps": 6684, "loss": 0.5019, "lr": 5e-06, "epoch": 1.440430783037918, "percentage": 48.03, "elapsed_time": "11:50:17", "remaining_time": "12:48:41"} +{"current_steps": 3220, "total_steps": 6684, "loss": 0.4982, "lr": 5e-06, "epoch": 1.4449181063495624, "percentage": 48.17, "elapsed_time": "11:52:27", "remaining_time": "12:46:27"} +{"current_steps": 3230, "total_steps": 6684, "loss": 0.5147, "lr": 5e-06, "epoch": 1.4494054296612071, "percentage": 48.32, "elapsed_time": "11:54:38", "remaining_time": "12:44:12"} +{"current_steps": 3240, "total_steps": 6684, "loss": 0.5168, "lr": 5e-06, "epoch": 1.4538927529728518, "percentage": 48.47, "elapsed_time": "11:56:49", "remaining_time": "12:41:57"} +{"current_steps": 3250, "total_steps": 6684, "loss": 0.5223, "lr": 5e-06, "epoch": 1.4583800762844963, "percentage": 48.62, "elapsed_time": "11:59:00", "remaining_time": "12:39:43"} +{"current_steps": 3260, "total_steps": 6684, "loss": 0.5167, "lr": 5e-06, "epoch": 1.462867399596141, "percentage": 48.77, "elapsed_time": "12:01:11", "remaining_time": "12:37:28"} +{"current_steps": 3270, "total_steps": 6684, "loss": 0.4906, "lr": 5e-06, "epoch": 1.4673547229077855, "percentage": 48.92, "elapsed_time": "12:03:22", "remaining_time": "12:35:14"} +{"current_steps": 3280, "total_steps": 6684, "loss": 0.5063, "lr": 5e-06, "epoch": 1.4718420462194302, "percentage": 49.07, "elapsed_time": "12:05:33", "remaining_time": "12:32:59"} +{"current_steps": 3290, "total_steps": 6684, "loss": 0.4932, "lr": 5e-06, "epoch": 1.4763293695310746, "percentage": 49.22, "elapsed_time": "12:07:44", "remaining_time": "12:30:45"} +{"current_steps": 3300, "total_steps": 6684, "loss": 0.4976, "lr": 5e-06, "epoch": 1.4808166928427193, "percentage": 49.37, "elapsed_time": "12:09:55", "remaining_time": "12:28:30"} +{"current_steps": 3310, "total_steps": 6684, "loss": 0.5001, "lr": 5e-06, "epoch": 1.4853040161543638, "percentage": 49.52, "elapsed_time": "12:12:06", "remaining_time": "12:26:16"} +{"current_steps": 3320, "total_steps": 6684, "loss": 0.5157, "lr": 5e-06, "epoch": 1.4897913394660085, "percentage": 49.67, "elapsed_time": "12:14:17", "remaining_time": "12:24:01"} +{"current_steps": 3330, "total_steps": 6684, "loss": 0.5011, "lr": 5e-06, "epoch": 1.4942786627776532, "percentage": 49.82, "elapsed_time": "12:16:28", "remaining_time": "12:21:47"} +{"current_steps": 3340, "total_steps": 6684, "loss": 0.4988, "lr": 5e-06, "epoch": 1.4987659860892977, "percentage": 49.97, "elapsed_time": "12:18:39", "remaining_time": "12:19:32"} +{"current_steps": 3350, "total_steps": 6684, "loss": 0.5263, "lr": 5e-06, "epoch": 1.5032533094009424, "percentage": 50.12, "elapsed_time": "12:20:50", "remaining_time": "12:17:18"} +{"current_steps": 3360, "total_steps": 6684, "loss": 0.4995, "lr": 5e-06, "epoch": 1.5077406327125868, "percentage": 50.27, "elapsed_time": "12:23:01", "remaining_time": "12:15:04"} +{"current_steps": 3370, "total_steps": 6684, "loss": 0.4933, "lr": 5e-06, "epoch": 1.5122279560242315, "percentage": 50.42, "elapsed_time": "12:25:12", "remaining_time": "12:12:49"} +{"current_steps": 3380, "total_steps": 6684, "loss": 0.5068, "lr": 5e-06, "epoch": 1.5167152793358762, "percentage": 50.57, "elapsed_time": "12:27:23", "remaining_time": "12:10:35"} +{"current_steps": 3390, "total_steps": 6684, "loss": 0.5028, "lr": 5e-06, "epoch": 1.5212026026475207, "percentage": 50.72, "elapsed_time": "12:29:34", "remaining_time": "12:08:20"} +{"current_steps": 3400, "total_steps": 6684, "loss": 0.4992, "lr": 5e-06, "epoch": 1.5256899259591652, "percentage": 50.87, "elapsed_time": "12:31:45", "remaining_time": "12:06:06"} +{"current_steps": 3410, "total_steps": 6684, "loss": 0.4774, "lr": 5e-06, "epoch": 1.53017724927081, "percentage": 51.02, "elapsed_time": "12:33:56", "remaining_time": "12:03:52"} +{"current_steps": 3420, "total_steps": 6684, "loss": 0.5061, "lr": 5e-06, "epoch": 1.5346645725824546, "percentage": 51.17, "elapsed_time": "12:36:07", "remaining_time": "12:01:37"} +{"current_steps": 3430, "total_steps": 6684, "loss": 0.4999, "lr": 5e-06, "epoch": 1.5391518958940993, "percentage": 51.32, "elapsed_time": "12:38:18", "remaining_time": "11:59:23"} +{"current_steps": 3440, "total_steps": 6684, "loss": 0.5088, "lr": 5e-06, "epoch": 1.5436392192057438, "percentage": 51.47, "elapsed_time": "12:40:29", "remaining_time": "11:57:09"} +{"current_steps": 3450, "total_steps": 6684, "loss": 0.4818, "lr": 5e-06, "epoch": 1.5481265425173882, "percentage": 51.62, "elapsed_time": "12:42:39", "remaining_time": "11:54:54"} +{"current_steps": 3460, "total_steps": 6684, "loss": 0.4813, "lr": 5e-06, "epoch": 1.552613865829033, "percentage": 51.77, "elapsed_time": "12:44:50", "remaining_time": "11:52:40"} +{"current_steps": 3470, "total_steps": 6684, "loss": 0.5034, "lr": 5e-06, "epoch": 1.5571011891406776, "percentage": 51.92, "elapsed_time": "12:47:01", "remaining_time": "11:50:26"} +{"current_steps": 3480, "total_steps": 6684, "loss": 0.4968, "lr": 5e-06, "epoch": 1.5615885124523223, "percentage": 52.06, "elapsed_time": "12:49:12", "remaining_time": "11:48:12"} +{"current_steps": 3490, "total_steps": 6684, "loss": 0.4957, "lr": 5e-06, "epoch": 1.5660758357639668, "percentage": 52.21, "elapsed_time": "12:51:23", "remaining_time": "11:45:58"} +{"current_steps": 3500, "total_steps": 6684, "loss": 0.4945, "lr": 5e-06, "epoch": 1.5705631590756113, "percentage": 52.36, "elapsed_time": "12:53:34", "remaining_time": "11:43:44"} +{"current_steps": 3510, "total_steps": 6684, "loss": 0.5118, "lr": 5e-06, "epoch": 1.575050482387256, "percentage": 52.51, "elapsed_time": "12:55:45", "remaining_time": "11:41:30"} +{"current_steps": 3520, "total_steps": 6684, "loss": 0.5194, "lr": 5e-06, "epoch": 1.5795378056989007, "percentage": 52.66, "elapsed_time": "12:57:56", "remaining_time": "11:39:15"} +{"current_steps": 3530, "total_steps": 6684, "loss": 0.4857, "lr": 5e-06, "epoch": 1.5840251290105454, "percentage": 52.81, "elapsed_time": "13:00:07", "remaining_time": "11:37:01"} +{"current_steps": 3540, "total_steps": 6684, "loss": 0.4713, "lr": 5e-06, "epoch": 1.5885124523221898, "percentage": 52.96, "elapsed_time": "13:02:18", "remaining_time": "11:34:47"} +{"current_steps": 3550, "total_steps": 6684, "loss": 0.5297, "lr": 5e-06, "epoch": 1.5929997756338343, "percentage": 53.11, "elapsed_time": "13:04:29", "remaining_time": "11:32:33"} +{"current_steps": 3560, "total_steps": 6684, "loss": 0.4888, "lr": 5e-06, "epoch": 1.597487098945479, "percentage": 53.26, "elapsed_time": "13:06:40", "remaining_time": "11:30:19"} +{"current_steps": 3570, "total_steps": 6684, "loss": 0.4842, "lr": 5e-06, "epoch": 1.6019744222571237, "percentage": 53.41, "elapsed_time": "13:08:51", "remaining_time": "11:28:05"} +{"current_steps": 3580, "total_steps": 6684, "loss": 0.4943, "lr": 5e-06, "epoch": 1.6064617455687682, "percentage": 53.56, "elapsed_time": "13:11:02", "remaining_time": "11:25:51"} +{"current_steps": 3590, "total_steps": 6684, "loss": 0.5379, "lr": 5e-06, "epoch": 1.6109490688804127, "percentage": 53.71, "elapsed_time": "13:13:13", "remaining_time": "11:23:37"} +{"current_steps": 3600, "total_steps": 6684, "loss": 0.4859, "lr": 5e-06, "epoch": 1.6154363921920574, "percentage": 53.86, "elapsed_time": "13:15:23", "remaining_time": "11:21:23"} +{"current_steps": 3610, "total_steps": 6684, "loss": 0.5253, "lr": 5e-06, "epoch": 1.619923715503702, "percentage": 54.01, "elapsed_time": "13:17:34", "remaining_time": "11:19:09"} +{"current_steps": 3620, "total_steps": 6684, "loss": 0.5248, "lr": 5e-06, "epoch": 1.6244110388153468, "percentage": 54.16, "elapsed_time": "13:19:45", "remaining_time": "11:16:55"} +{"current_steps": 3630, "total_steps": 6684, "loss": 0.4947, "lr": 5e-06, "epoch": 1.6288983621269912, "percentage": 54.31, "elapsed_time": "13:21:56", "remaining_time": "11:14:41"} +{"current_steps": 3640, "total_steps": 6684, "loss": 0.4846, "lr": 5e-06, "epoch": 1.6333856854386357, "percentage": 54.46, "elapsed_time": "13:24:07", "remaining_time": "11:12:27"} +{"current_steps": 3650, "total_steps": 6684, "loss": 0.5178, "lr": 5e-06, "epoch": 1.6378730087502804, "percentage": 54.61, "elapsed_time": "13:26:18", "remaining_time": "11:10:13"} +{"current_steps": 3660, "total_steps": 6684, "loss": 0.5142, "lr": 5e-06, "epoch": 1.642360332061925, "percentage": 54.76, "elapsed_time": "13:28:29", "remaining_time": "11:07:59"} +{"current_steps": 3670, "total_steps": 6684, "loss": 0.5146, "lr": 5e-06, "epoch": 1.6468476553735698, "percentage": 54.91, "elapsed_time": "13:30:40", "remaining_time": "11:05:46"} +{"current_steps": 3680, "total_steps": 6684, "loss": 0.4942, "lr": 5e-06, "epoch": 1.6513349786852143, "percentage": 55.06, "elapsed_time": "13:32:51", "remaining_time": "11:03:32"} +{"current_steps": 3690, "total_steps": 6684, "loss": 0.5109, "lr": 5e-06, "epoch": 1.6558223019968588, "percentage": 55.21, "elapsed_time": "13:35:02", "remaining_time": "11:01:18"} +{"current_steps": 3700, "total_steps": 6684, "loss": 0.5189, "lr": 5e-06, "epoch": 1.6603096253085035, "percentage": 55.36, "elapsed_time": "13:37:13", "remaining_time": "10:59:04"} +{"current_steps": 3710, "total_steps": 6684, "loss": 0.498, "lr": 5e-06, "epoch": 1.6647969486201482, "percentage": 55.51, "elapsed_time": "13:39:24", "remaining_time": "10:56:50"} +{"current_steps": 3720, "total_steps": 6684, "loss": 0.4834, "lr": 5e-06, "epoch": 1.6692842719317929, "percentage": 55.66, "elapsed_time": "13:41:35", "remaining_time": "10:54:37"} +{"current_steps": 3730, "total_steps": 6684, "loss": 0.5418, "lr": 5e-06, "epoch": 1.6737715952434373, "percentage": 55.8, "elapsed_time": "13:43:45", "remaining_time": "10:52:23"} +{"current_steps": 3740, "total_steps": 6684, "loss": 0.508, "lr": 5e-06, "epoch": 1.6782589185550818, "percentage": 55.95, "elapsed_time": "13:45:56", "remaining_time": "10:50:09"} +{"current_steps": 3750, "total_steps": 6684, "loss": 0.4967, "lr": 5e-06, "epoch": 1.6827462418667265, "percentage": 56.1, "elapsed_time": "13:48:07", "remaining_time": "10:47:55"} +{"current_steps": 3760, "total_steps": 6684, "loss": 0.4933, "lr": 5e-06, "epoch": 1.6872335651783712, "percentage": 56.25, "elapsed_time": "13:50:18", "remaining_time": "10:45:41"} +{"current_steps": 3770, "total_steps": 6684, "loss": 0.4949, "lr": 5e-06, "epoch": 1.6917208884900157, "percentage": 56.4, "elapsed_time": "13:52:29", "remaining_time": "10:43:28"} +{"current_steps": 3780, "total_steps": 6684, "loss": 0.4966, "lr": 5e-06, "epoch": 1.6962082118016601, "percentage": 56.55, "elapsed_time": "13:54:40", "remaining_time": "10:41:14"} +{"current_steps": 3790, "total_steps": 6684, "loss": 0.5074, "lr": 5e-06, "epoch": 1.7006955351133048, "percentage": 56.7, "elapsed_time": "13:56:51", "remaining_time": "10:39:00"} +{"current_steps": 3800, "total_steps": 6684, "loss": 0.4896, "lr": 5e-06, "epoch": 1.7051828584249495, "percentage": 56.85, "elapsed_time": "13:59:02", "remaining_time": "10:36:47"} +{"current_steps": 3810, "total_steps": 6684, "loss": 0.5045, "lr": 5e-06, "epoch": 1.7096701817365942, "percentage": 57.0, "elapsed_time": "14:01:13", "remaining_time": "10:34:33"} +{"current_steps": 3820, "total_steps": 6684, "loss": 0.5089, "lr": 5e-06, "epoch": 1.7141575050482387, "percentage": 57.15, "elapsed_time": "14:03:24", "remaining_time": "10:32:19"} +{"current_steps": 3830, "total_steps": 6684, "loss": 0.4994, "lr": 5e-06, "epoch": 1.7186448283598832, "percentage": 57.3, "elapsed_time": "14:05:34", "remaining_time": "10:30:06"} +{"current_steps": 3840, "total_steps": 6684, "loss": 0.5025, "lr": 5e-06, "epoch": 1.723132151671528, "percentage": 57.45, "elapsed_time": "14:07:45", "remaining_time": "10:27:52"} +{"current_steps": 3850, "total_steps": 6684, "loss": 0.5041, "lr": 5e-06, "epoch": 1.7276194749831726, "percentage": 57.6, "elapsed_time": "14:09:56", "remaining_time": "10:25:38"} +{"current_steps": 3860, "total_steps": 6684, "loss": 0.505, "lr": 5e-06, "epoch": 1.7321067982948173, "percentage": 57.75, "elapsed_time": "14:12:07", "remaining_time": "10:23:25"} +{"current_steps": 3870, "total_steps": 6684, "loss": 0.4998, "lr": 5e-06, "epoch": 1.7365941216064618, "percentage": 57.9, "elapsed_time": "14:14:18", "remaining_time": "10:21:11"} +{"current_steps": 3880, "total_steps": 6684, "loss": 0.5203, "lr": 5e-06, "epoch": 1.7410814449181062, "percentage": 58.05, "elapsed_time": "14:16:29", "remaining_time": "10:18:58"} +{"current_steps": 3890, "total_steps": 6684, "loss": 0.4938, "lr": 5e-06, "epoch": 1.745568768229751, "percentage": 58.2, "elapsed_time": "14:18:40", "remaining_time": "10:16:44"} +{"current_steps": 3900, "total_steps": 6684, "loss": 0.5138, "lr": 5e-06, "epoch": 1.7500560915413956, "percentage": 58.35, "elapsed_time": "14:20:51", "remaining_time": "10:14:31"} +{"current_steps": 3910, "total_steps": 6684, "loss": 0.5019, "lr": 5e-06, "epoch": 1.75454341485304, "percentage": 58.5, "elapsed_time": "14:23:02", "remaining_time": "10:12:17"} +{"current_steps": 3920, "total_steps": 6684, "loss": 0.4941, "lr": 5e-06, "epoch": 1.7590307381646848, "percentage": 58.65, "elapsed_time": "14:25:13", "remaining_time": "10:10:04"} +{"current_steps": 3930, "total_steps": 6684, "loss": 0.5206, "lr": 5e-06, "epoch": 1.7635180614763293, "percentage": 58.8, "elapsed_time": "14:27:24", "remaining_time": "10:07:50"} +{"current_steps": 3940, "total_steps": 6684, "loss": 0.4974, "lr": 5e-06, "epoch": 1.768005384787974, "percentage": 58.95, "elapsed_time": "14:29:35", "remaining_time": "10:05:37"} +{"current_steps": 3950, "total_steps": 6684, "loss": 0.4939, "lr": 5e-06, "epoch": 1.7724927080996187, "percentage": 59.1, "elapsed_time": "14:31:46", "remaining_time": "10:03:23"} +{"current_steps": 3960, "total_steps": 6684, "loss": 0.5019, "lr": 5e-06, "epoch": 1.7769800314112632, "percentage": 59.25, "elapsed_time": "14:33:57", "remaining_time": "10:01:10"} +{"current_steps": 3970, "total_steps": 6684, "loss": 0.4852, "lr": 5e-06, "epoch": 1.7814673547229076, "percentage": 59.4, "elapsed_time": "14:36:08", "remaining_time": "9:58:57"} +{"current_steps": 3980, "total_steps": 6684, "loss": 0.5183, "lr": 5e-06, "epoch": 1.7859546780345523, "percentage": 59.55, "elapsed_time": "14:38:19", "remaining_time": "9:56:43"} +{"current_steps": 3990, "total_steps": 6684, "loss": 0.51, "lr": 5e-06, "epoch": 1.790442001346197, "percentage": 59.69, "elapsed_time": "14:40:30", "remaining_time": "9:54:30"} +{"current_steps": 4000, "total_steps": 6684, "loss": 0.504, "lr": 5e-06, "epoch": 1.7949293246578417, "percentage": 59.84, "elapsed_time": "14:42:41", "remaining_time": "9:52:17"} +{"current_steps": 4010, "total_steps": 6684, "loss": 0.494, "lr": 5e-06, "epoch": 1.7994166479694862, "percentage": 59.99, "elapsed_time": "14:44:52", "remaining_time": "9:50:03"} +{"current_steps": 4020, "total_steps": 6684, "loss": 0.5222, "lr": 5e-06, "epoch": 1.8039039712811307, "percentage": 60.14, "elapsed_time": "14:47:03", "remaining_time": "9:47:50"} +{"current_steps": 4030, "total_steps": 6684, "loss": 0.5047, "lr": 5e-06, "epoch": 1.8083912945927754, "percentage": 60.29, "elapsed_time": "14:49:14", "remaining_time": "9:45:36"} +{"current_steps": 4040, "total_steps": 6684, "loss": 0.5148, "lr": 5e-06, "epoch": 1.81287861790442, "percentage": 60.44, "elapsed_time": "14:51:25", "remaining_time": "9:43:23"} +{"current_steps": 4050, "total_steps": 6684, "loss": 0.4958, "lr": 5e-06, "epoch": 1.8173659412160648, "percentage": 60.59, "elapsed_time": "14:53:36", "remaining_time": "9:41:10"} +{"current_steps": 4060, "total_steps": 6684, "loss": 0.4887, "lr": 5e-06, "epoch": 1.8218532645277092, "percentage": 60.74, "elapsed_time": "14:55:46", "remaining_time": "9:38:56"} +{"current_steps": 4070, "total_steps": 6684, "loss": 0.5026, "lr": 5e-06, "epoch": 1.8263405878393537, "percentage": 60.89, "elapsed_time": "14:57:57", "remaining_time": "9:36:43"} +{"current_steps": 4080, "total_steps": 6684, "loss": 0.4802, "lr": 5e-06, "epoch": 1.8308279111509984, "percentage": 61.04, "elapsed_time": "15:00:08", "remaining_time": "9:34:30"} +{"current_steps": 4090, "total_steps": 6684, "loss": 0.4948, "lr": 5e-06, "epoch": 1.835315234462643, "percentage": 61.19, "elapsed_time": "15:02:19", "remaining_time": "9:32:17"} +{"current_steps": 4100, "total_steps": 6684, "loss": 0.4954, "lr": 5e-06, "epoch": 1.8398025577742876, "percentage": 61.34, "elapsed_time": "15:04:30", "remaining_time": "9:30:03"} +{"current_steps": 4110, "total_steps": 6684, "loss": 0.5215, "lr": 5e-06, "epoch": 1.8442898810859323, "percentage": 61.49, "elapsed_time": "15:06:41", "remaining_time": "9:27:50"} +{"current_steps": 4120, "total_steps": 6684, "loss": 0.4895, "lr": 5e-06, "epoch": 1.8487772043975768, "percentage": 61.64, "elapsed_time": "15:08:52", "remaining_time": "9:25:37"} +{"current_steps": 4130, "total_steps": 6684, "loss": 0.5029, "lr": 5e-06, "epoch": 1.8532645277092215, "percentage": 61.79, "elapsed_time": "15:11:03", "remaining_time": "9:23:24"} +{"current_steps": 4140, "total_steps": 6684, "loss": 0.4919, "lr": 5e-06, "epoch": 1.8577518510208662, "percentage": 61.94, "elapsed_time": "15:13:14", "remaining_time": "9:21:10"} +{"current_steps": 4150, "total_steps": 6684, "loss": 0.5034, "lr": 5e-06, "epoch": 1.8622391743325106, "percentage": 62.09, "elapsed_time": "15:15:25", "remaining_time": "9:18:57"} +{"current_steps": 4160, "total_steps": 6684, "loss": 0.5002, "lr": 5e-06, "epoch": 1.866726497644155, "percentage": 62.24, "elapsed_time": "15:17:36", "remaining_time": "9:16:44"} +{"current_steps": 4170, "total_steps": 6684, "loss": 0.505, "lr": 5e-06, "epoch": 1.8712138209557998, "percentage": 62.39, "elapsed_time": "15:19:47", "remaining_time": "9:14:31"} +{"current_steps": 4180, "total_steps": 6684, "loss": 0.5287, "lr": 5e-06, "epoch": 1.8757011442674445, "percentage": 62.54, "elapsed_time": "15:21:58", "remaining_time": "9:12:18"} +{"current_steps": 4190, "total_steps": 6684, "loss": 0.5205, "lr": 5e-06, "epoch": 1.8801884675790892, "percentage": 62.69, "elapsed_time": "15:24:09", "remaining_time": "9:10:04"} +{"current_steps": 4200, "total_steps": 6684, "loss": 0.4989, "lr": 5e-06, "epoch": 1.8846757908907337, "percentage": 62.84, "elapsed_time": "15:26:20", "remaining_time": "9:07:51"} +{"current_steps": 4210, "total_steps": 6684, "loss": 0.5154, "lr": 5e-06, "epoch": 1.8891631142023781, "percentage": 62.99, "elapsed_time": "15:28:31", "remaining_time": "9:05:38"} +{"current_steps": 4220, "total_steps": 6684, "loss": 0.5065, "lr": 5e-06, "epoch": 1.8936504375140228, "percentage": 63.14, "elapsed_time": "15:30:41", "remaining_time": "9:03:25"} +{"current_steps": 4230, "total_steps": 6684, "loss": 0.5001, "lr": 5e-06, "epoch": 1.8981377608256675, "percentage": 63.29, "elapsed_time": "15:32:52", "remaining_time": "9:01:12"} +{"current_steps": 4240, "total_steps": 6684, "loss": 0.4953, "lr": 5e-06, "epoch": 1.9026250841373122, "percentage": 63.44, "elapsed_time": "15:35:03", "remaining_time": "8:58:59"} +{"current_steps": 4250, "total_steps": 6684, "loss": 0.4881, "lr": 5e-06, "epoch": 1.9071124074489567, "percentage": 63.58, "elapsed_time": "15:37:14", "remaining_time": "8:56:45"} +{"current_steps": 4260, "total_steps": 6684, "loss": 0.498, "lr": 5e-06, "epoch": 1.9115997307606012, "percentage": 63.73, "elapsed_time": "15:39:25", "remaining_time": "8:54:32"} +{"current_steps": 4270, "total_steps": 6684, "loss": 0.5128, "lr": 5e-06, "epoch": 1.9160870540722459, "percentage": 63.88, "elapsed_time": "15:41:36", "remaining_time": "8:52:19"} +{"current_steps": 4280, "total_steps": 6684, "loss": 0.4942, "lr": 5e-06, "epoch": 1.9205743773838906, "percentage": 64.03, "elapsed_time": "15:43:47", "remaining_time": "8:50:06"} +{"current_steps": 4290, "total_steps": 6684, "loss": 0.5069, "lr": 5e-06, "epoch": 1.925061700695535, "percentage": 64.18, "elapsed_time": "15:45:58", "remaining_time": "8:47:53"} +{"current_steps": 4300, "total_steps": 6684, "loss": 0.5264, "lr": 5e-06, "epoch": 1.9295490240071798, "percentage": 64.33, "elapsed_time": "15:48:09", "remaining_time": "8:45:40"} +{"current_steps": 4310, "total_steps": 6684, "loss": 0.4944, "lr": 5e-06, "epoch": 1.9340363473188242, "percentage": 64.48, "elapsed_time": "15:50:20", "remaining_time": "8:43:27"} +{"current_steps": 4320, "total_steps": 6684, "loss": 0.5116, "lr": 5e-06, "epoch": 1.938523670630469, "percentage": 64.63, "elapsed_time": "15:52:31", "remaining_time": "8:41:14"} +{"current_steps": 4330, "total_steps": 6684, "loss": 0.5308, "lr": 5e-06, "epoch": 1.9430109939421136, "percentage": 64.78, "elapsed_time": "15:54:42", "remaining_time": "8:39:01"} +{"current_steps": 4340, "total_steps": 6684, "loss": 0.5038, "lr": 5e-06, "epoch": 1.947498317253758, "percentage": 64.93, "elapsed_time": "15:56:53", "remaining_time": "8:36:48"} +{"current_steps": 4350, "total_steps": 6684, "loss": 0.5391, "lr": 5e-06, "epoch": 1.9519856405654026, "percentage": 65.08, "elapsed_time": "15:59:04", "remaining_time": "8:34:35"} +{"current_steps": 4360, "total_steps": 6684, "loss": 0.4916, "lr": 5e-06, "epoch": 1.9564729638770473, "percentage": 65.23, "elapsed_time": "16:01:15", "remaining_time": "8:32:22"} +{"current_steps": 4370, "total_steps": 6684, "loss": 0.4959, "lr": 5e-06, "epoch": 1.960960287188692, "percentage": 65.38, "elapsed_time": "16:03:26", "remaining_time": "8:30:09"} +{"current_steps": 4380, "total_steps": 6684, "loss": 0.4851, "lr": 5e-06, "epoch": 1.9654476105003367, "percentage": 65.53, "elapsed_time": "16:05:37", "remaining_time": "8:27:56"} +{"current_steps": 4390, "total_steps": 6684, "loss": 0.5266, "lr": 5e-06, "epoch": 1.9699349338119811, "percentage": 65.68, "elapsed_time": "16:07:48", "remaining_time": "8:25:43"} +{"current_steps": 4400, "total_steps": 6684, "loss": 0.4978, "lr": 5e-06, "epoch": 1.9744222571236256, "percentage": 65.83, "elapsed_time": "16:09:59", "remaining_time": "8:23:30"} +{"current_steps": 4410, "total_steps": 6684, "loss": 0.4928, "lr": 5e-06, "epoch": 1.9789095804352703, "percentage": 65.98, "elapsed_time": "16:12:10", "remaining_time": "8:21:18"} +{"current_steps": 4420, "total_steps": 6684, "loss": 0.4989, "lr": 5e-06, "epoch": 1.983396903746915, "percentage": 66.13, "elapsed_time": "16:14:21", "remaining_time": "8:19:05"} +{"current_steps": 4430, "total_steps": 6684, "loss": 0.516, "lr": 5e-06, "epoch": 1.9878842270585597, "percentage": 66.28, "elapsed_time": "16:16:32", "remaining_time": "8:16:52"} +{"current_steps": 4440, "total_steps": 6684, "loss": 0.5309, "lr": 5e-06, "epoch": 1.9923715503702042, "percentage": 66.43, "elapsed_time": "16:18:43", "remaining_time": "8:14:39"} +{"current_steps": 4450, "total_steps": 6684, "loss": 0.5079, "lr": 5e-06, "epoch": 1.9968588736818487, "percentage": 66.58, "elapsed_time": "16:20:54", "remaining_time": "8:12:26"} +{"current_steps": 4457, "total_steps": 6684, "eval_loss": 0.5559915900230408, "epoch": 2.0, "percentage": 66.68, "elapsed_time": "16:31:44", "remaining_time": "8:15:32"} +{"current_steps": 4460, "total_steps": 6684, "loss": 0.489, "lr": 5e-06, "epoch": 2.0013461969934934, "percentage": 66.73, "elapsed_time": "16:33:32", "remaining_time": "8:15:25"} +{"current_steps": 4470, "total_steps": 6684, "loss": 0.4355, "lr": 5e-06, "epoch": 2.005833520305138, "percentage": 66.88, "elapsed_time": "16:35:43", "remaining_time": "8:13:10"} +{"current_steps": 4480, "total_steps": 6684, "loss": 0.4286, "lr": 5e-06, "epoch": 2.0103208436167828, "percentage": 67.03, "elapsed_time": "16:37:54", "remaining_time": "8:10:56"} +{"current_steps": 4490, "total_steps": 6684, "loss": 0.4383, "lr": 5e-06, "epoch": 2.014808166928427, "percentage": 67.18, "elapsed_time": "16:40:05", "remaining_time": "8:08:41"} +{"current_steps": 4500, "total_steps": 6684, "loss": 0.4392, "lr": 5e-06, "epoch": 2.0192954902400717, "percentage": 67.32, "elapsed_time": "16:42:16", "remaining_time": "8:06:26"} +{"current_steps": 4510, "total_steps": 6684, "loss": 0.4322, "lr": 5e-06, "epoch": 2.0237828135517164, "percentage": 67.47, "elapsed_time": "16:44:27", "remaining_time": "8:04:11"} +{"current_steps": 4520, "total_steps": 6684, "loss": 0.422, "lr": 5e-06, "epoch": 2.028270136863361, "percentage": 67.62, "elapsed_time": "16:46:38", "remaining_time": "8:01:56"} +{"current_steps": 4530, "total_steps": 6684, "loss": 0.4228, "lr": 5e-06, "epoch": 2.032757460175006, "percentage": 67.77, "elapsed_time": "16:48:49", "remaining_time": "7:59:41"} +{"current_steps": 4540, "total_steps": 6684, "loss": 0.4414, "lr": 5e-06, "epoch": 2.03724478348665, "percentage": 67.92, "elapsed_time": "16:51:00", "remaining_time": "7:57:26"} +{"current_steps": 4550, "total_steps": 6684, "loss": 0.4319, "lr": 5e-06, "epoch": 2.0417321067982948, "percentage": 68.07, "elapsed_time": "16:53:11", "remaining_time": "7:55:12"} +{"current_steps": 4560, "total_steps": 6684, "loss": 0.4184, "lr": 5e-06, "epoch": 2.0462194301099395, "percentage": 68.22, "elapsed_time": "16:55:23", "remaining_time": "7:52:57"} +{"current_steps": 4570, "total_steps": 6684, "loss": 0.4267, "lr": 5e-06, "epoch": 2.050706753421584, "percentage": 68.37, "elapsed_time": "16:57:34", "remaining_time": "7:50:42"} +{"current_steps": 4580, "total_steps": 6684, "loss": 0.4492, "lr": 5e-06, "epoch": 2.055194076733229, "percentage": 68.52, "elapsed_time": "16:59:45", "remaining_time": "7:48:27"} +{"current_steps": 4590, "total_steps": 6684, "loss": 0.4445, "lr": 5e-06, "epoch": 2.059681400044873, "percentage": 68.67, "elapsed_time": "17:01:56", "remaining_time": "7:46:12"} +{"current_steps": 4600, "total_steps": 6684, "loss": 0.4279, "lr": 5e-06, "epoch": 2.064168723356518, "percentage": 68.82, "elapsed_time": "17:04:07", "remaining_time": "7:43:58"} +{"current_steps": 4610, "total_steps": 6684, "loss": 0.476, "lr": 5e-06, "epoch": 2.0686560466681625, "percentage": 68.97, "elapsed_time": "17:06:17", "remaining_time": "7:41:43"} +{"current_steps": 4620, "total_steps": 6684, "loss": 0.4511, "lr": 5e-06, "epoch": 2.073143369979807, "percentage": 69.12, "elapsed_time": "17:08:28", "remaining_time": "7:39:28"} +{"current_steps": 4630, "total_steps": 6684, "loss": 0.4385, "lr": 5e-06, "epoch": 2.0776306932914514, "percentage": 69.27, "elapsed_time": "17:10:39", "remaining_time": "7:37:13"} +{"current_steps": 4640, "total_steps": 6684, "loss": 0.4409, "lr": 5e-06, "epoch": 2.082118016603096, "percentage": 69.42, "elapsed_time": "17:12:50", "remaining_time": "7:34:59"} +{"current_steps": 4650, "total_steps": 6684, "loss": 0.4235, "lr": 5e-06, "epoch": 2.086605339914741, "percentage": 69.57, "elapsed_time": "17:15:01", "remaining_time": "7:32:44"} +{"current_steps": 4660, "total_steps": 6684, "loss": 0.4367, "lr": 5e-06, "epoch": 2.0910926632263855, "percentage": 69.72, "elapsed_time": "17:17:12", "remaining_time": "7:30:29"} +{"current_steps": 4670, "total_steps": 6684, "loss": 0.4458, "lr": 5e-06, "epoch": 2.0955799865380302, "percentage": 69.87, "elapsed_time": "17:19:23", "remaining_time": "7:28:14"} +{"current_steps": 4680, "total_steps": 6684, "loss": 0.4415, "lr": 5e-06, "epoch": 2.1000673098496745, "percentage": 70.02, "elapsed_time": "17:21:33", "remaining_time": "7:26:00"} +{"current_steps": 4690, "total_steps": 6684, "loss": 0.4646, "lr": 5e-06, "epoch": 2.104554633161319, "percentage": 70.17, "elapsed_time": "17:23:44", "remaining_time": "7:23:45"} +{"current_steps": 4700, "total_steps": 6684, "loss": 0.4725, "lr": 5e-06, "epoch": 2.109041956472964, "percentage": 70.32, "elapsed_time": "17:25:55", "remaining_time": "7:21:31"} +{"current_steps": 4710, "total_steps": 6684, "loss": 0.4342, "lr": 5e-06, "epoch": 2.1135292797846086, "percentage": 70.47, "elapsed_time": "17:28:07", "remaining_time": "7:19:16"} +{"current_steps": 4720, "total_steps": 6684, "loss": 0.4226, "lr": 5e-06, "epoch": 2.1180166030962533, "percentage": 70.62, "elapsed_time": "17:30:18", "remaining_time": "7:17:01"} +{"current_steps": 4730, "total_steps": 6684, "loss": 0.4387, "lr": 5e-06, "epoch": 2.1225039264078975, "percentage": 70.77, "elapsed_time": "17:32:29", "remaining_time": "7:14:47"} +{"current_steps": 4740, "total_steps": 6684, "loss": 0.4343, "lr": 5e-06, "epoch": 2.1269912497195422, "percentage": 70.92, "elapsed_time": "17:34:40", "remaining_time": "7:12:33"} +{"current_steps": 4750, "total_steps": 6684, "loss": 0.452, "lr": 5e-06, "epoch": 2.131478573031187, "percentage": 71.07, "elapsed_time": "17:36:51", "remaining_time": "7:10:18"} +{"current_steps": 4760, "total_steps": 6684, "loss": 0.4405, "lr": 5e-06, "epoch": 2.1359658963428316, "percentage": 71.21, "elapsed_time": "17:39:02", "remaining_time": "7:08:04"} +{"current_steps": 4770, "total_steps": 6684, "loss": 0.4426, "lr": 5e-06, "epoch": 2.140453219654476, "percentage": 71.36, "elapsed_time": "17:41:13", "remaining_time": "7:05:49"} +{"current_steps": 4780, "total_steps": 6684, "loss": 0.4277, "lr": 5e-06, "epoch": 2.1449405429661206, "percentage": 71.51, "elapsed_time": "17:43:24", "remaining_time": "7:03:35"} +{"current_steps": 4790, "total_steps": 6684, "loss": 0.417, "lr": 5e-06, "epoch": 2.1494278662777653, "percentage": 71.66, "elapsed_time": "17:45:35", "remaining_time": "7:01:20"} +{"current_steps": 4800, "total_steps": 6684, "loss": 0.4432, "lr": 5e-06, "epoch": 2.15391518958941, "percentage": 71.81, "elapsed_time": "17:47:46", "remaining_time": "6:59:06"} +{"current_steps": 4810, "total_steps": 6684, "loss": 0.4211, "lr": 5e-06, "epoch": 2.1584025129010547, "percentage": 71.96, "elapsed_time": "17:49:57", "remaining_time": "6:56:51"} +{"current_steps": 4820, "total_steps": 6684, "loss": 0.4359, "lr": 5e-06, "epoch": 2.162889836212699, "percentage": 72.11, "elapsed_time": "17:52:09", "remaining_time": "6:54:37"} +{"current_steps": 4830, "total_steps": 6684, "loss": 0.438, "lr": 5e-06, "epoch": 2.1673771595243436, "percentage": 72.26, "elapsed_time": "17:54:20", "remaining_time": "6:52:23"} +{"current_steps": 4840, "total_steps": 6684, "loss": 0.4372, "lr": 5e-06, "epoch": 2.1718644828359883, "percentage": 72.41, "elapsed_time": "17:56:31", "remaining_time": "6:50:08"} +{"current_steps": 4850, "total_steps": 6684, "loss": 0.4247, "lr": 5e-06, "epoch": 2.176351806147633, "percentage": 72.56, "elapsed_time": "17:58:42", "remaining_time": "6:47:54"} +{"current_steps": 4860, "total_steps": 6684, "loss": 0.4439, "lr": 5e-06, "epoch": 2.1808391294592777, "percentage": 72.71, "elapsed_time": "18:00:53", "remaining_time": "6:45:40"} +{"current_steps": 4870, "total_steps": 6684, "loss": 0.4537, "lr": 5e-06, "epoch": 2.185326452770922, "percentage": 72.86, "elapsed_time": "18:03:04", "remaining_time": "6:43:25"} +{"current_steps": 4880, "total_steps": 6684, "loss": 0.4333, "lr": 5e-06, "epoch": 2.1898137760825667, "percentage": 73.01, "elapsed_time": "18:05:16", "remaining_time": "6:41:11"} +{"current_steps": 4890, "total_steps": 6684, "loss": 0.457, "lr": 5e-06, "epoch": 2.1943010993942114, "percentage": 73.16, "elapsed_time": "18:07:27", "remaining_time": "6:38:57"} +{"current_steps": 4900, "total_steps": 6684, "loss": 0.4537, "lr": 5e-06, "epoch": 2.198788422705856, "percentage": 73.31, "elapsed_time": "18:09:38", "remaining_time": "6:36:43"} +{"current_steps": 4910, "total_steps": 6684, "loss": 0.4417, "lr": 5e-06, "epoch": 2.2032757460175008, "percentage": 73.46, "elapsed_time": "18:11:49", "remaining_time": "6:34:28"} +{"current_steps": 4920, "total_steps": 6684, "loss": 0.4518, "lr": 5e-06, "epoch": 2.207763069329145, "percentage": 73.61, "elapsed_time": "18:14:00", "remaining_time": "6:32:14"} +{"current_steps": 4930, "total_steps": 6684, "loss": 0.4292, "lr": 5e-06, "epoch": 2.2122503926407897, "percentage": 73.76, "elapsed_time": "18:16:11", "remaining_time": "6:30:00"} +{"current_steps": 4940, "total_steps": 6684, "loss": 0.4337, "lr": 5e-06, "epoch": 2.2167377159524344, "percentage": 73.91, "elapsed_time": "18:18:22", "remaining_time": "6:27:46"} +{"current_steps": 4950, "total_steps": 6684, "loss": 0.4453, "lr": 5e-06, "epoch": 2.221225039264079, "percentage": 74.06, "elapsed_time": "18:20:33", "remaining_time": "6:25:31"} +{"current_steps": 4960, "total_steps": 6684, "loss": 0.46, "lr": 5e-06, "epoch": 2.225712362575724, "percentage": 74.21, "elapsed_time": "18:22:44", "remaining_time": "6:23:17"} +{"current_steps": 4970, "total_steps": 6684, "loss": 0.4452, "lr": 5e-06, "epoch": 2.230199685887368, "percentage": 74.36, "elapsed_time": "18:24:56", "remaining_time": "6:21:03"} +{"current_steps": 4980, "total_steps": 6684, "loss": 0.4324, "lr": 5e-06, "epoch": 2.2346870091990128, "percentage": 74.51, "elapsed_time": "18:27:07", "remaining_time": "6:18:49"} +{"current_steps": 4990, "total_steps": 6684, "loss": 0.4322, "lr": 5e-06, "epoch": 2.2391743325106575, "percentage": 74.66, "elapsed_time": "18:29:18", "remaining_time": "6:16:35"} +{"current_steps": 5000, "total_steps": 6684, "loss": 0.4229, "lr": 5e-06, "epoch": 2.243661655822302, "percentage": 74.81, "elapsed_time": "18:31:29", "remaining_time": "6:14:20"} +{"current_steps": 5010, "total_steps": 6684, "loss": 0.4177, "lr": 5e-06, "epoch": 2.2481489791339464, "percentage": 74.96, "elapsed_time": "18:33:40", "remaining_time": "6:12:06"} +{"current_steps": 5020, "total_steps": 6684, "loss": 0.4303, "lr": 5e-06, "epoch": 2.252636302445591, "percentage": 75.1, "elapsed_time": "18:35:51", "remaining_time": "6:09:52"} +{"current_steps": 5030, "total_steps": 6684, "loss": 0.4272, "lr": 5e-06, "epoch": 2.257123625757236, "percentage": 75.25, "elapsed_time": "18:38:02", "remaining_time": "6:07:38"} +{"current_steps": 5040, "total_steps": 6684, "loss": 0.456, "lr": 5e-06, "epoch": 2.2616109490688805, "percentage": 75.4, "elapsed_time": "18:40:13", "remaining_time": "6:05:24"} +{"current_steps": 5050, "total_steps": 6684, "loss": 0.4398, "lr": 5e-06, "epoch": 2.266098272380525, "percentage": 75.55, "elapsed_time": "18:42:24", "remaining_time": "6:03:10"} +{"current_steps": 5060, "total_steps": 6684, "loss": 0.4144, "lr": 5e-06, "epoch": 2.2705855956921694, "percentage": 75.7, "elapsed_time": "18:44:35", "remaining_time": "6:00:56"} +{"current_steps": 5070, "total_steps": 6684, "loss": 0.4433, "lr": 5e-06, "epoch": 2.275072919003814, "percentage": 75.85, "elapsed_time": "18:46:46", "remaining_time": "5:58:41"} +{"current_steps": 5080, "total_steps": 6684, "loss": 0.4606, "lr": 5e-06, "epoch": 2.279560242315459, "percentage": 76.0, "elapsed_time": "18:48:57", "remaining_time": "5:56:27"} +{"current_steps": 5090, "total_steps": 6684, "loss": 0.4237, "lr": 5e-06, "epoch": 2.2840475656271035, "percentage": 76.15, "elapsed_time": "18:51:08", "remaining_time": "5:54:13"} +{"current_steps": 5100, "total_steps": 6684, "loss": 0.426, "lr": 5e-06, "epoch": 2.288534888938748, "percentage": 76.3, "elapsed_time": "18:53:19", "remaining_time": "5:51:59"} +{"current_steps": 5110, "total_steps": 6684, "loss": 0.4451, "lr": 5e-06, "epoch": 2.2930222122503925, "percentage": 76.45, "elapsed_time": "18:55:30", "remaining_time": "5:49:45"} +{"current_steps": 5120, "total_steps": 6684, "loss": 0.4161, "lr": 5e-06, "epoch": 2.297509535562037, "percentage": 76.6, "elapsed_time": "18:57:41", "remaining_time": "5:47:31"} +{"current_steps": 5130, "total_steps": 6684, "loss": 0.4269, "lr": 5e-06, "epoch": 2.301996858873682, "percentage": 76.75, "elapsed_time": "18:59:52", "remaining_time": "5:45:17"} +{"current_steps": 5140, "total_steps": 6684, "loss": 0.4606, "lr": 5e-06, "epoch": 2.3064841821853266, "percentage": 76.9, "elapsed_time": "19:02:03", "remaining_time": "5:43:03"} +{"current_steps": 5150, "total_steps": 6684, "loss": 0.4325, "lr": 5e-06, "epoch": 2.310971505496971, "percentage": 77.05, "elapsed_time": "19:04:14", "remaining_time": "5:40:49"} +{"current_steps": 5160, "total_steps": 6684, "loss": 0.436, "lr": 5e-06, "epoch": 2.3154588288086155, "percentage": 77.2, "elapsed_time": "19:06:25", "remaining_time": "5:38:35"} +{"current_steps": 5170, "total_steps": 6684, "loss": 0.4271, "lr": 5e-06, "epoch": 2.3199461521202602, "percentage": 77.35, "elapsed_time": "19:08:36", "remaining_time": "5:36:21"} +{"current_steps": 5180, "total_steps": 6684, "loss": 0.4495, "lr": 5e-06, "epoch": 2.324433475431905, "percentage": 77.5, "elapsed_time": "19:10:47", "remaining_time": "5:34:07"} +{"current_steps": 5190, "total_steps": 6684, "loss": 0.4184, "lr": 5e-06, "epoch": 2.3289207987435496, "percentage": 77.65, "elapsed_time": "19:12:58", "remaining_time": "5:31:53"} +{"current_steps": 5200, "total_steps": 6684, "loss": 0.4536, "lr": 5e-06, "epoch": 2.333408122055194, "percentage": 77.8, "elapsed_time": "19:15:09", "remaining_time": "5:29:39"} +{"current_steps": 5210, "total_steps": 6684, "loss": 0.4247, "lr": 5e-06, "epoch": 2.3378954453668386, "percentage": 77.95, "elapsed_time": "19:17:20", "remaining_time": "5:27:25"} +{"current_steps": 5220, "total_steps": 6684, "loss": 0.446, "lr": 5e-06, "epoch": 2.3423827686784833, "percentage": 78.1, "elapsed_time": "19:19:31", "remaining_time": "5:25:12"} +{"current_steps": 5230, "total_steps": 6684, "loss": 0.4332, "lr": 5e-06, "epoch": 2.346870091990128, "percentage": 78.25, "elapsed_time": "19:21:42", "remaining_time": "5:22:58"} +{"current_steps": 5240, "total_steps": 6684, "loss": 0.4639, "lr": 5e-06, "epoch": 2.3513574153017727, "percentage": 78.4, "elapsed_time": "19:23:53", "remaining_time": "5:20:44"} +{"current_steps": 5250, "total_steps": 6684, "loss": 0.4363, "lr": 5e-06, "epoch": 2.355844738613417, "percentage": 78.55, "elapsed_time": "19:26:04", "remaining_time": "5:18:30"} +{"current_steps": 5260, "total_steps": 6684, "loss": 0.4216, "lr": 5e-06, "epoch": 2.3603320619250616, "percentage": 78.7, "elapsed_time": "19:28:16", "remaining_time": "5:16:16"} +{"current_steps": 5270, "total_steps": 6684, "loss": 0.4338, "lr": 5e-06, "epoch": 2.3648193852367063, "percentage": 78.85, "elapsed_time": "19:30:27", "remaining_time": "5:14:02"} +{"current_steps": 5280, "total_steps": 6684, "loss": 0.4239, "lr": 5e-06, "epoch": 2.369306708548351, "percentage": 78.99, "elapsed_time": "19:32:38", "remaining_time": "5:11:48"} +{"current_steps": 5290, "total_steps": 6684, "loss": 0.4475, "lr": 5e-06, "epoch": 2.3737940318599957, "percentage": 79.14, "elapsed_time": "19:34:49", "remaining_time": "5:09:35"} +{"current_steps": 5300, "total_steps": 6684, "loss": 0.4392, "lr": 5e-06, "epoch": 2.37828135517164, "percentage": 79.29, "elapsed_time": "19:37:00", "remaining_time": "5:07:21"} +{"current_steps": 5310, "total_steps": 6684, "loss": 0.4245, "lr": 5e-06, "epoch": 2.3827686784832847, "percentage": 79.44, "elapsed_time": "19:39:11", "remaining_time": "5:05:07"} +{"current_steps": 5320, "total_steps": 6684, "loss": 0.4358, "lr": 5e-06, "epoch": 2.3872560017949294, "percentage": 79.59, "elapsed_time": "19:41:22", "remaining_time": "5:02:53"} +{"current_steps": 5330, "total_steps": 6684, "loss": 0.4369, "lr": 5e-06, "epoch": 2.391743325106574, "percentage": 79.74, "elapsed_time": "19:43:34", "remaining_time": "5:00:39"} +{"current_steps": 5340, "total_steps": 6684, "loss": 0.4524, "lr": 5e-06, "epoch": 2.3962306484182188, "percentage": 79.89, "elapsed_time": "19:45:45", "remaining_time": "4:58:26"} +{"current_steps": 5350, "total_steps": 6684, "loss": 0.4625, "lr": 5e-06, "epoch": 2.400717971729863, "percentage": 80.04, "elapsed_time": "19:47:56", "remaining_time": "4:56:12"} +{"current_steps": 5360, "total_steps": 6684, "loss": 0.4434, "lr": 5e-06, "epoch": 2.4052052950415077, "percentage": 80.19, "elapsed_time": "19:50:07", "remaining_time": "4:53:58"} +{"current_steps": 5370, "total_steps": 6684, "loss": 0.4217, "lr": 5e-06, "epoch": 2.4096926183531524, "percentage": 80.34, "elapsed_time": "19:52:18", "remaining_time": "4:51:44"} +{"current_steps": 5380, "total_steps": 6684, "loss": 0.4487, "lr": 5e-06, "epoch": 2.414179941664797, "percentage": 80.49, "elapsed_time": "19:54:29", "remaining_time": "4:49:31"} +{"current_steps": 5390, "total_steps": 6684, "loss": 0.4352, "lr": 5e-06, "epoch": 2.418667264976442, "percentage": 80.64, "elapsed_time": "19:56:40", "remaining_time": "4:47:17"} +{"current_steps": 5400, "total_steps": 6684, "loss": 0.4288, "lr": 5e-06, "epoch": 2.423154588288086, "percentage": 80.79, "elapsed_time": "19:58:51", "remaining_time": "4:45:03"} +{"current_steps": 5410, "total_steps": 6684, "loss": 0.4741, "lr": 5e-06, "epoch": 2.4276419115997308, "percentage": 80.94, "elapsed_time": "20:01:02", "remaining_time": "4:42:50"} +{"current_steps": 5420, "total_steps": 6684, "loss": 0.4692, "lr": 5e-06, "epoch": 2.4321292349113754, "percentage": 81.09, "elapsed_time": "20:03:13", "remaining_time": "4:40:36"} +{"current_steps": 5430, "total_steps": 6684, "loss": 0.4508, "lr": 5e-06, "epoch": 2.43661655822302, "percentage": 81.24, "elapsed_time": "20:05:24", "remaining_time": "4:38:22"} +{"current_steps": 5440, "total_steps": 6684, "loss": 0.4275, "lr": 5e-06, "epoch": 2.4411038815346644, "percentage": 81.39, "elapsed_time": "20:07:36", "remaining_time": "4:36:08"} +{"current_steps": 5450, "total_steps": 6684, "loss": 0.448, "lr": 5e-06, "epoch": 2.445591204846309, "percentage": 81.54, "elapsed_time": "20:09:47", "remaining_time": "4:33:55"} +{"current_steps": 5460, "total_steps": 6684, "loss": 0.4346, "lr": 5e-06, "epoch": 2.450078528157954, "percentage": 81.69, "elapsed_time": "20:11:58", "remaining_time": "4:31:41"} +{"current_steps": 5470, "total_steps": 6684, "loss": 0.4399, "lr": 5e-06, "epoch": 2.4545658514695985, "percentage": 81.84, "elapsed_time": "20:14:09", "remaining_time": "4:29:28"} +{"current_steps": 5480, "total_steps": 6684, "loss": 0.4181, "lr": 5e-06, "epoch": 2.4590531747812427, "percentage": 81.99, "elapsed_time": "20:16:20", "remaining_time": "4:27:14"} +{"current_steps": 5490, "total_steps": 6684, "loss": 0.4585, "lr": 5e-06, "epoch": 2.4635404980928874, "percentage": 82.14, "elapsed_time": "20:18:31", "remaining_time": "4:25:00"} +{"current_steps": 5500, "total_steps": 6684, "loss": 0.457, "lr": 5e-06, "epoch": 2.468027821404532, "percentage": 82.29, "elapsed_time": "20:20:42", "remaining_time": "4:22:47"} +{"current_steps": 5510, "total_steps": 6684, "loss": 0.4385, "lr": 5e-06, "epoch": 2.472515144716177, "percentage": 82.44, "elapsed_time": "20:22:53", "remaining_time": "4:20:33"} +{"current_steps": 5520, "total_steps": 6684, "loss": 0.4827, "lr": 5e-06, "epoch": 2.4770024680278215, "percentage": 82.59, "elapsed_time": "20:25:04", "remaining_time": "4:18:19"} +{"current_steps": 5530, "total_steps": 6684, "loss": 0.4524, "lr": 5e-06, "epoch": 2.481489791339466, "percentage": 82.73, "elapsed_time": "20:27:15", "remaining_time": "4:16:06"} +{"current_steps": 5540, "total_steps": 6684, "loss": 0.4366, "lr": 5e-06, "epoch": 2.4859771146511105, "percentage": 82.88, "elapsed_time": "20:29:26", "remaining_time": "4:13:52"} +{"current_steps": 5550, "total_steps": 6684, "loss": 0.4487, "lr": 5e-06, "epoch": 2.490464437962755, "percentage": 83.03, "elapsed_time": "20:31:38", "remaining_time": "4:11:39"} +{"current_steps": 5560, "total_steps": 6684, "loss": 0.4318, "lr": 5e-06, "epoch": 2.4949517612744, "percentage": 83.18, "elapsed_time": "20:33:49", "remaining_time": "4:09:25"} +{"current_steps": 5570, "total_steps": 6684, "loss": 0.4362, "lr": 5e-06, "epoch": 2.4994390845860446, "percentage": 83.33, "elapsed_time": "20:36:00", "remaining_time": "4:07:12"} +{"current_steps": 5580, "total_steps": 6684, "loss": 0.4623, "lr": 5e-06, "epoch": 2.503926407897689, "percentage": 83.48, "elapsed_time": "20:38:11", "remaining_time": "4:04:58"} +{"current_steps": 5590, "total_steps": 6684, "loss": 0.4223, "lr": 5e-06, "epoch": 2.5084137312093335, "percentage": 83.63, "elapsed_time": "20:40:23", "remaining_time": "4:02:45"} +{"current_steps": 5600, "total_steps": 6684, "loss": 0.4371, "lr": 5e-06, "epoch": 2.5129010545209782, "percentage": 83.78, "elapsed_time": "20:42:34", "remaining_time": "4:00:31"} +{"current_steps": 5610, "total_steps": 6684, "loss": 0.4398, "lr": 5e-06, "epoch": 2.517388377832623, "percentage": 83.93, "elapsed_time": "20:44:45", "remaining_time": "3:58:18"} +{"current_steps": 5620, "total_steps": 6684, "loss": 0.4397, "lr": 5e-06, "epoch": 2.5218757011442676, "percentage": 84.08, "elapsed_time": "20:46:56", "remaining_time": "3:56:04"} +{"current_steps": 5630, "total_steps": 6684, "loss": 0.4542, "lr": 5e-06, "epoch": 2.526363024455912, "percentage": 84.23, "elapsed_time": "20:49:07", "remaining_time": "3:53:51"} +{"current_steps": 5640, "total_steps": 6684, "loss": 0.4277, "lr": 5e-06, "epoch": 2.5308503477675566, "percentage": 84.38, "elapsed_time": "20:51:18", "remaining_time": "3:51:37"} +{"current_steps": 5650, "total_steps": 6684, "loss": 0.4438, "lr": 5e-06, "epoch": 2.5353376710792013, "percentage": 84.53, "elapsed_time": "20:53:30", "remaining_time": "3:49:24"} +{"current_steps": 5660, "total_steps": 6684, "loss": 0.4477, "lr": 5e-06, "epoch": 2.539824994390846, "percentage": 84.68, "elapsed_time": "20:55:41", "remaining_time": "3:47:10"} +{"current_steps": 5670, "total_steps": 6684, "loss": 0.4513, "lr": 5e-06, "epoch": 2.5443123177024907, "percentage": 84.83, "elapsed_time": "20:57:52", "remaining_time": "3:44:57"} +{"current_steps": 5680, "total_steps": 6684, "loss": 0.4162, "lr": 5e-06, "epoch": 2.548799641014135, "percentage": 84.98, "elapsed_time": "21:00:03", "remaining_time": "3:42:43"} +{"current_steps": 5690, "total_steps": 6684, "loss": 0.4422, "lr": 5e-06, "epoch": 2.5532869643257796, "percentage": 85.13, "elapsed_time": "21:02:15", "remaining_time": "3:40:30"} +{"current_steps": 5700, "total_steps": 6684, "loss": 0.4508, "lr": 5e-06, "epoch": 2.5577742876374243, "percentage": 85.28, "elapsed_time": "21:04:26", "remaining_time": "3:38:16"} +{"current_steps": 5710, "total_steps": 6684, "loss": 0.4393, "lr": 5e-06, "epoch": 2.562261610949069, "percentage": 85.43, "elapsed_time": "21:06:37", "remaining_time": "3:36:03"} +{"current_steps": 5720, "total_steps": 6684, "loss": 0.4336, "lr": 5e-06, "epoch": 2.5667489342607137, "percentage": 85.58, "elapsed_time": "21:08:48", "remaining_time": "3:33:50"} +{"current_steps": 5730, "total_steps": 6684, "loss": 0.4273, "lr": 5e-06, "epoch": 2.571236257572358, "percentage": 85.73, "elapsed_time": "21:10:59", "remaining_time": "3:31:36"} +{"current_steps": 5740, "total_steps": 6684, "loss": 0.4468, "lr": 5e-06, "epoch": 2.5757235808840027, "percentage": 85.88, "elapsed_time": "21:13:11", "remaining_time": "3:29:23"} +{"current_steps": 5750, "total_steps": 6684, "loss": 0.4474, "lr": 5e-06, "epoch": 2.5802109041956474, "percentage": 86.03, "elapsed_time": "21:15:22", "remaining_time": "3:27:09"} +{"current_steps": 5760, "total_steps": 6684, "loss": 0.4345, "lr": 5e-06, "epoch": 2.584698227507292, "percentage": 86.18, "elapsed_time": "21:17:33", "remaining_time": "3:24:56"} +{"current_steps": 5770, "total_steps": 6684, "loss": 0.4311, "lr": 5e-06, "epoch": 2.5891855508189368, "percentage": 86.33, "elapsed_time": "21:19:44", "remaining_time": "3:22:43"} +{"current_steps": 5780, "total_steps": 6684, "loss": 0.4534, "lr": 5e-06, "epoch": 2.593672874130581, "percentage": 86.48, "elapsed_time": "21:21:55", "remaining_time": "3:20:29"} +{"current_steps": 5790, "total_steps": 6684, "loss": 0.451, "lr": 5e-06, "epoch": 2.5981601974422257, "percentage": 86.62, "elapsed_time": "21:24:06", "remaining_time": "3:18:16"} +{"current_steps": 5800, "total_steps": 6684, "loss": 0.4274, "lr": 5e-06, "epoch": 2.6026475207538704, "percentage": 86.77, "elapsed_time": "21:26:17", "remaining_time": "3:16:02"} +{"current_steps": 5810, "total_steps": 6684, "loss": 0.4361, "lr": 5e-06, "epoch": 2.6071348440655147, "percentage": 86.92, "elapsed_time": "21:28:29", "remaining_time": "3:13:49"} +{"current_steps": 5820, "total_steps": 6684, "loss": 0.4344, "lr": 5e-06, "epoch": 2.61162216737716, "percentage": 87.07, "elapsed_time": "21:30:40", "remaining_time": "3:11:36"} +{"current_steps": 5830, "total_steps": 6684, "loss": 0.443, "lr": 5e-06, "epoch": 2.616109490688804, "percentage": 87.22, "elapsed_time": "21:32:51", "remaining_time": "3:09:22"} +{"current_steps": 5840, "total_steps": 6684, "loss": 0.455, "lr": 5e-06, "epoch": 2.6205968140004487, "percentage": 87.37, "elapsed_time": "21:35:02", "remaining_time": "3:07:09"} +{"current_steps": 5850, "total_steps": 6684, "loss": 0.4338, "lr": 5e-06, "epoch": 2.6250841373120934, "percentage": 87.52, "elapsed_time": "21:37:13", "remaining_time": "3:04:56"} +{"current_steps": 5860, "total_steps": 6684, "loss": 0.458, "lr": 5e-06, "epoch": 2.6295714606237377, "percentage": 87.67, "elapsed_time": "21:39:24", "remaining_time": "3:02:42"} +{"current_steps": 5870, "total_steps": 6684, "loss": 0.4524, "lr": 5e-06, "epoch": 2.6340587839353824, "percentage": 87.82, "elapsed_time": "21:41:35", "remaining_time": "3:00:29"} +{"current_steps": 5880, "total_steps": 6684, "loss": 0.4399, "lr": 5e-06, "epoch": 2.638546107247027, "percentage": 87.97, "elapsed_time": "21:43:46", "remaining_time": "2:58:16"} +{"current_steps": 5890, "total_steps": 6684, "loss": 0.4385, "lr": 5e-06, "epoch": 2.643033430558672, "percentage": 88.12, "elapsed_time": "21:45:57", "remaining_time": "2:56:03"} +{"current_steps": 5900, "total_steps": 6684, "loss": 0.4601, "lr": 5e-06, "epoch": 2.6475207538703165, "percentage": 88.27, "elapsed_time": "21:48:09", "remaining_time": "2:53:49"} +{"current_steps": 5910, "total_steps": 6684, "loss": 0.4323, "lr": 5e-06, "epoch": 2.6520080771819607, "percentage": 88.42, "elapsed_time": "21:50:20", "remaining_time": "2:51:36"} +{"current_steps": 5920, "total_steps": 6684, "loss": 0.4479, "lr": 5e-06, "epoch": 2.6564954004936054, "percentage": 88.57, "elapsed_time": "21:52:31", "remaining_time": "2:49:23"} +{"current_steps": 5930, "total_steps": 6684, "loss": 0.4518, "lr": 5e-06, "epoch": 2.66098272380525, "percentage": 88.72, "elapsed_time": "21:54:42", "remaining_time": "2:47:09"} +{"current_steps": 5940, "total_steps": 6684, "loss": 0.4424, "lr": 5e-06, "epoch": 2.665470047116895, "percentage": 88.87, "elapsed_time": "21:56:53", "remaining_time": "2:44:56"} +{"current_steps": 5950, "total_steps": 6684, "loss": 0.4481, "lr": 5e-06, "epoch": 2.6699573704285395, "percentage": 89.02, "elapsed_time": "21:59:05", "remaining_time": "2:42:43"} +{"current_steps": 5960, "total_steps": 6684, "loss": 0.4438, "lr": 5e-06, "epoch": 2.674444693740184, "percentage": 89.17, "elapsed_time": "22:01:16", "remaining_time": "2:40:30"} +{"current_steps": 5970, "total_steps": 6684, "loss": 0.4417, "lr": 5e-06, "epoch": 2.6789320170518285, "percentage": 89.32, "elapsed_time": "22:03:27", "remaining_time": "2:38:16"} +{"current_steps": 5980, "total_steps": 6684, "loss": 0.462, "lr": 5e-06, "epoch": 2.683419340363473, "percentage": 89.47, "elapsed_time": "22:05:38", "remaining_time": "2:36:03"} +{"current_steps": 5990, "total_steps": 6684, "loss": 0.4385, "lr": 5e-06, "epoch": 2.687906663675118, "percentage": 89.62, "elapsed_time": "22:07:49", "remaining_time": "2:33:50"} +{"current_steps": 6000, "total_steps": 6684, "loss": 0.4419, "lr": 5e-06, "epoch": 2.6923939869867626, "percentage": 89.77, "elapsed_time": "22:10:01", "remaining_time": "2:31:37"} +{"current_steps": 6010, "total_steps": 6684, "loss": 0.435, "lr": 5e-06, "epoch": 2.696881310298407, "percentage": 89.92, "elapsed_time": "22:12:12", "remaining_time": "2:29:24"} +{"current_steps": 6020, "total_steps": 6684, "loss": 0.4324, "lr": 5e-06, "epoch": 2.7013686336100515, "percentage": 90.07, "elapsed_time": "22:14:23", "remaining_time": "2:27:10"} +{"current_steps": 6030, "total_steps": 6684, "loss": 0.4344, "lr": 5e-06, "epoch": 2.7058559569216962, "percentage": 90.22, "elapsed_time": "22:16:34", "remaining_time": "2:24:57"} +{"current_steps": 6040, "total_steps": 6684, "loss": 0.4373, "lr": 5e-06, "epoch": 2.710343280233341, "percentage": 90.37, "elapsed_time": "22:18:45", "remaining_time": "2:22:44"} +{"current_steps": 6050, "total_steps": 6684, "loss": 0.4317, "lr": 5e-06, "epoch": 2.7148306035449856, "percentage": 90.51, "elapsed_time": "22:20:57", "remaining_time": "2:20:31"} +{"current_steps": 6060, "total_steps": 6684, "loss": 0.4494, "lr": 5e-06, "epoch": 2.71931792685663, "percentage": 90.66, "elapsed_time": "22:23:08", "remaining_time": "2:18:18"} +{"current_steps": 6070, "total_steps": 6684, "loss": 0.4539, "lr": 5e-06, "epoch": 2.7238052501682746, "percentage": 90.81, "elapsed_time": "22:25:19", "remaining_time": "2:16:05"} +{"current_steps": 6080, "total_steps": 6684, "loss": 0.4391, "lr": 5e-06, "epoch": 2.7282925734799193, "percentage": 90.96, "elapsed_time": "22:27:30", "remaining_time": "2:13:51"} +{"current_steps": 6090, "total_steps": 6684, "loss": 0.449, "lr": 5e-06, "epoch": 2.732779896791564, "percentage": 91.11, "elapsed_time": "22:29:41", "remaining_time": "2:11:38"} +{"current_steps": 6100, "total_steps": 6684, "loss": 0.4301, "lr": 5e-06, "epoch": 2.7372672201032087, "percentage": 91.26, "elapsed_time": "22:31:52", "remaining_time": "2:09:25"} +{"current_steps": 6110, "total_steps": 6684, "loss": 0.4226, "lr": 5e-06, "epoch": 2.741754543414853, "percentage": 91.41, "elapsed_time": "22:34:03", "remaining_time": "2:07:12"} +{"current_steps": 6120, "total_steps": 6684, "loss": 0.4512, "lr": 5e-06, "epoch": 2.7462418667264976, "percentage": 91.56, "elapsed_time": "22:36:14", "remaining_time": "2:04:59"} +{"current_steps": 6130, "total_steps": 6684, "loss": 0.4434, "lr": 5e-06, "epoch": 2.7507291900381423, "percentage": 91.71, "elapsed_time": "22:38:25", "remaining_time": "2:02:46"} +{"current_steps": 6140, "total_steps": 6684, "loss": 0.4405, "lr": 5e-06, "epoch": 2.755216513349787, "percentage": 91.86, "elapsed_time": "22:40:36", "remaining_time": "2:00:32"} +{"current_steps": 6150, "total_steps": 6684, "loss": 0.4366, "lr": 5e-06, "epoch": 2.7597038366614317, "percentage": 92.01, "elapsed_time": "22:42:47", "remaining_time": "1:58:19"} +{"current_steps": 6160, "total_steps": 6684, "loss": 0.4414, "lr": 5e-06, "epoch": 2.764191159973076, "percentage": 92.16, "elapsed_time": "22:44:58", "remaining_time": "1:56:06"} +{"current_steps": 6170, "total_steps": 6684, "loss": 0.4534, "lr": 5e-06, "epoch": 2.7686784832847207, "percentage": 92.31, "elapsed_time": "22:47:08", "remaining_time": "1:53:53"} +{"current_steps": 6180, "total_steps": 6684, "loss": 0.4488, "lr": 5e-06, "epoch": 2.7731658065963654, "percentage": 92.46, "elapsed_time": "22:49:19", "remaining_time": "1:51:40"} +{"current_steps": 6190, "total_steps": 6684, "loss": 0.4331, "lr": 5e-06, "epoch": 2.7776531299080096, "percentage": 92.61, "elapsed_time": "22:51:30", "remaining_time": "1:49:27"} +{"current_steps": 6200, "total_steps": 6684, "loss": 0.442, "lr": 5e-06, "epoch": 2.7821404532196548, "percentage": 92.76, "elapsed_time": "22:53:41", "remaining_time": "1:47:14"} +{"current_steps": 6210, "total_steps": 6684, "loss": 0.4439, "lr": 5e-06, "epoch": 2.786627776531299, "percentage": 92.91, "elapsed_time": "22:55:52", "remaining_time": "1:45:01"} +{"current_steps": 6220, "total_steps": 6684, "loss": 0.4471, "lr": 5e-06, "epoch": 2.7911150998429437, "percentage": 93.06, "elapsed_time": "22:58:03", "remaining_time": "1:42:48"} +{"current_steps": 6230, "total_steps": 6684, "loss": 0.45, "lr": 5e-06, "epoch": 2.7956024231545884, "percentage": 93.21, "elapsed_time": "23:00:14", "remaining_time": "1:40:34"} +{"current_steps": 6240, "total_steps": 6684, "loss": 0.4369, "lr": 5e-06, "epoch": 2.8000897464662327, "percentage": 93.36, "elapsed_time": "23:02:25", "remaining_time": "1:38:21"} +{"current_steps": 6250, "total_steps": 6684, "loss": 0.4763, "lr": 5e-06, "epoch": 2.8045770697778774, "percentage": 93.51, "elapsed_time": "23:04:35", "remaining_time": "1:36:08"} +{"current_steps": 6260, "total_steps": 6684, "loss": 0.4363, "lr": 5e-06, "epoch": 2.809064393089522, "percentage": 93.66, "elapsed_time": "23:06:46", "remaining_time": "1:33:55"} +{"current_steps": 6270, "total_steps": 6684, "loss": 0.438, "lr": 5e-06, "epoch": 2.8135517164011667, "percentage": 93.81, "elapsed_time": "23:08:57", "remaining_time": "1:31:42"} +{"current_steps": 6280, "total_steps": 6684, "loss": 0.4295, "lr": 5e-06, "epoch": 2.8180390397128114, "percentage": 93.96, "elapsed_time": "23:11:08", "remaining_time": "1:29:29"} +{"current_steps": 6290, "total_steps": 6684, "loss": 0.448, "lr": 5e-06, "epoch": 2.8225263630244557, "percentage": 94.11, "elapsed_time": "23:13:19", "remaining_time": "1:27:16"} +{"current_steps": 6300, "total_steps": 6684, "loss": 0.4601, "lr": 5e-06, "epoch": 2.8270136863361004, "percentage": 94.25, "elapsed_time": "23:15:29", "remaining_time": "1:25:03"} +{"current_steps": 6310, "total_steps": 6684, "loss": 0.4256, "lr": 5e-06, "epoch": 2.831501009647745, "percentage": 94.4, "elapsed_time": "23:17:40", "remaining_time": "1:22:50"} +{"current_steps": 6320, "total_steps": 6684, "loss": 0.4461, "lr": 5e-06, "epoch": 2.83598833295939, "percentage": 94.55, "elapsed_time": "23:19:51", "remaining_time": "1:20:37"} +{"current_steps": 6330, "total_steps": 6684, "loss": 0.4312, "lr": 5e-06, "epoch": 2.8404756562710345, "percentage": 94.7, "elapsed_time": "23:22:02", "remaining_time": "1:18:24"} +{"current_steps": 6340, "total_steps": 6684, "loss": 0.4418, "lr": 5e-06, "epoch": 2.8449629795826787, "percentage": 94.85, "elapsed_time": "23:24:13", "remaining_time": "1:16:11"} +{"current_steps": 6350, "total_steps": 6684, "loss": 0.4449, "lr": 5e-06, "epoch": 2.8494503028943234, "percentage": 95.0, "elapsed_time": "23:26:24", "remaining_time": "1:13:58"} +{"current_steps": 6360, "total_steps": 6684, "loss": 0.4453, "lr": 5e-06, "epoch": 2.853937626205968, "percentage": 95.15, "elapsed_time": "23:28:35", "remaining_time": "1:11:45"} +{"current_steps": 6370, "total_steps": 6684, "loss": 0.4418, "lr": 5e-06, "epoch": 2.858424949517613, "percentage": 95.3, "elapsed_time": "23:30:46", "remaining_time": "1:09:32"} +{"current_steps": 6380, "total_steps": 6684, "loss": 0.4486, "lr": 5e-06, "epoch": 2.8629122728292575, "percentage": 95.45, "elapsed_time": "23:32:57", "remaining_time": "1:07:19"} +{"current_steps": 6390, "total_steps": 6684, "loss": 0.4305, "lr": 5e-06, "epoch": 2.867399596140902, "percentage": 95.6, "elapsed_time": "23:35:07", "remaining_time": "1:05:06"} +{"current_steps": 6400, "total_steps": 6684, "loss": 0.4421, "lr": 5e-06, "epoch": 2.8718869194525465, "percentage": 95.75, "elapsed_time": "23:37:18", "remaining_time": "1:02:53"} +{"current_steps": 6410, "total_steps": 6684, "loss": 0.4482, "lr": 5e-06, "epoch": 2.876374242764191, "percentage": 95.9, "elapsed_time": "23:39:29", "remaining_time": "1:00:40"} +{"current_steps": 6420, "total_steps": 6684, "loss": 0.4357, "lr": 5e-06, "epoch": 2.880861566075836, "percentage": 96.05, "elapsed_time": "23:41:40", "remaining_time": "0:58:27"} +{"current_steps": 6430, "total_steps": 6684, "loss": 0.4901, "lr": 5e-06, "epoch": 2.8853488893874806, "percentage": 96.2, "elapsed_time": "23:43:51", "remaining_time": "0:56:14"} +{"current_steps": 6440, "total_steps": 6684, "loss": 0.4523, "lr": 5e-06, "epoch": 2.889836212699125, "percentage": 96.35, "elapsed_time": "23:46:02", "remaining_time": "0:54:01"} +{"current_steps": 6450, "total_steps": 6684, "loss": 0.445, "lr": 5e-06, "epoch": 2.8943235360107695, "percentage": 96.5, "elapsed_time": "23:48:13", "remaining_time": "0:51:48"} +{"current_steps": 6460, "total_steps": 6684, "loss": 0.4396, "lr": 5e-06, "epoch": 2.8988108593224142, "percentage": 96.65, "elapsed_time": "23:50:24", "remaining_time": "0:49:35"} +{"current_steps": 6470, "total_steps": 6684, "loss": 0.4659, "lr": 5e-06, "epoch": 2.903298182634059, "percentage": 96.8, "elapsed_time": "23:52:35", "remaining_time": "0:47:23"} +{"current_steps": 6480, "total_steps": 6684, "loss": 0.4386, "lr": 5e-06, "epoch": 2.9077855059457036, "percentage": 96.95, "elapsed_time": "23:54:46", "remaining_time": "0:45:10"} +{"current_steps": 6490, "total_steps": 6684, "loss": 0.4498, "lr": 5e-06, "epoch": 2.912272829257348, "percentage": 97.1, "elapsed_time": "23:56:57", "remaining_time": "0:42:57"} +{"current_steps": 6500, "total_steps": 6684, "loss": 0.4447, "lr": 5e-06, "epoch": 2.9167601525689926, "percentage": 97.25, "elapsed_time": "23:59:08", "remaining_time": "0:40:44"} +{"current_steps": 6510, "total_steps": 6684, "loss": 0.4415, "lr": 5e-06, "epoch": 2.9212474758806373, "percentage": 97.4, "elapsed_time": "1 day, 0:01:19", "remaining_time": "0:38:31"} +{"current_steps": 6520, "total_steps": 6684, "loss": 0.4278, "lr": 5e-06, "epoch": 2.925734799192282, "percentage": 97.55, "elapsed_time": "1 day, 0:03:30", "remaining_time": "0:36:18"} +{"current_steps": 6530, "total_steps": 6684, "loss": 0.439, "lr": 5e-06, "epoch": 2.9302221225039267, "percentage": 97.7, "elapsed_time": "1 day, 0:05:41", "remaining_time": "0:34:05"} +{"current_steps": 6540, "total_steps": 6684, "loss": 0.4361, "lr": 5e-06, "epoch": 2.934709445815571, "percentage": 97.85, "elapsed_time": "1 day, 0:07:52", "remaining_time": "0:31:52"} +{"current_steps": 6550, "total_steps": 6684, "loss": 0.4621, "lr": 5e-06, "epoch": 2.9391967691272156, "percentage": 98.0, "elapsed_time": "1 day, 0:10:03", "remaining_time": "0:29:39"} +{"current_steps": 6560, "total_steps": 6684, "loss": 0.4646, "lr": 5e-06, "epoch": 2.9436840924388603, "percentage": 98.14, "elapsed_time": "1 day, 0:12:14", "remaining_time": "0:27:27"} +{"current_steps": 6570, "total_steps": 6684, "loss": 0.4658, "lr": 5e-06, "epoch": 2.9481714157505046, "percentage": 98.29, "elapsed_time": "1 day, 0:14:25", "remaining_time": "0:25:14"} +{"current_steps": 6580, "total_steps": 6684, "loss": 0.455, "lr": 5e-06, "epoch": 2.9526587390621493, "percentage": 98.44, "elapsed_time": "1 day, 0:16:36", "remaining_time": "0:23:01"} +{"current_steps": 6590, "total_steps": 6684, "loss": 0.4502, "lr": 5e-06, "epoch": 2.957146062373794, "percentage": 98.59, "elapsed_time": "1 day, 0:18:47", "remaining_time": "0:20:48"} +{"current_steps": 6600, "total_steps": 6684, "loss": 0.4846, "lr": 5e-06, "epoch": 2.9616333856854387, "percentage": 98.74, "elapsed_time": "1 day, 0:20:58", "remaining_time": "0:18:35"} +{"current_steps": 6610, "total_steps": 6684, "loss": 0.4374, "lr": 5e-06, "epoch": 2.9661207089970834, "percentage": 98.89, "elapsed_time": "1 day, 0:23:09", "remaining_time": "0:16:22"} +{"current_steps": 6620, "total_steps": 6684, "loss": 0.4568, "lr": 5e-06, "epoch": 2.9706080323087276, "percentage": 99.04, "elapsed_time": "1 day, 0:25:20", "remaining_time": "0:14:09"} +{"current_steps": 6630, "total_steps": 6684, "loss": 0.4543, "lr": 5e-06, "epoch": 2.9750953556203723, "percentage": 99.19, "elapsed_time": "1 day, 0:27:31", "remaining_time": "0:11:57"} +{"current_steps": 6640, "total_steps": 6684, "loss": 0.4413, "lr": 5e-06, "epoch": 2.979582678932017, "percentage": 99.34, "elapsed_time": "1 day, 0:29:42", "remaining_time": "0:09:44"} +{"current_steps": 6650, "total_steps": 6684, "loss": 0.4297, "lr": 5e-06, "epoch": 2.9840700022436617, "percentage": 99.49, "elapsed_time": "1 day, 0:31:53", "remaining_time": "0:07:31"} +{"current_steps": 6660, "total_steps": 6684, "loss": 0.4274, "lr": 5e-06, "epoch": 2.9885573255553064, "percentage": 99.64, "elapsed_time": "1 day, 0:34:04", "remaining_time": "0:05:18"} +{"current_steps": 6670, "total_steps": 6684, "loss": 0.4425, "lr": 5e-06, "epoch": 2.9930446488669507, "percentage": 99.79, "elapsed_time": "1 day, 0:36:15", "remaining_time": "0:03:05"} +{"current_steps": 6680, "total_steps": 6684, "loss": 0.4538, "lr": 5e-06, "epoch": 2.9975319721785953, "percentage": 99.94, "elapsed_time": "1 day, 0:38:26", "remaining_time": "0:00:53"} +{"current_steps": 6684, "total_steps": 6684, "eval_loss": 0.5616346001625061, "epoch": 2.9993269015032533, "percentage": 100.0, "elapsed_time": "1 day, 0:49:47", "remaining_time": "0:00:00"} +{"current_steps": 6684, "total_steps": 6684, "epoch": 2.9993269015032533, "percentage": 100.0, "elapsed_time": "1 day, 0:51:12", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..362080d --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,4742 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.9993269015032533, + "eval_steps": 500, + "global_step": 6684, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.004487323311644604, + "grad_norm": 1.3059244169345843, + "learning_rate": 5e-06, + "loss": 0.7774, + "step": 10 + }, + { + "epoch": 0.008974646623289208, + "grad_norm": 1.0232642607902347, + "learning_rate": 5e-06, + "loss": 0.6958, + "step": 20 + }, + { + "epoch": 0.013461969934933812, + "grad_norm": 0.8401058983048771, + "learning_rate": 5e-06, + "loss": 0.6992, + "step": 30 + }, + { + "epoch": 0.017949293246578416, + "grad_norm": 0.8139785554230714, + "learning_rate": 5e-06, + "loss": 0.6749, + "step": 40 + }, + { + "epoch": 0.02243661655822302, + "grad_norm": 0.8129256440286593, + "learning_rate": 5e-06, + "loss": 0.7083, + "step": 50 + }, + { + "epoch": 0.026923939869867623, + "grad_norm": 0.8418551736226986, + "learning_rate": 5e-06, + "loss": 0.6846, + "step": 60 + }, + { + "epoch": 0.03141126318151223, + "grad_norm": 0.7167670779403538, + "learning_rate": 5e-06, + "loss": 0.6574, + "step": 70 + }, + { + "epoch": 0.03589858649315683, + "grad_norm": 0.5953427667880735, + "learning_rate": 5e-06, + "loss": 0.653, + "step": 80 + }, + { + "epoch": 0.04038590980480144, + "grad_norm": 0.5652705295757201, + "learning_rate": 5e-06, + "loss": 0.6452, + "step": 90 + }, + { + "epoch": 0.04487323311644604, + "grad_norm": 0.5863707257105095, + "learning_rate": 5e-06, + "loss": 0.6424, + "step": 100 + }, + { + "epoch": 0.049360556428090646, + "grad_norm": 0.5827496122357744, + "learning_rate": 5e-06, + "loss": 0.6325, + "step": 110 + }, + { + "epoch": 0.05384787973973525, + "grad_norm": 0.5692209350328149, + "learning_rate": 5e-06, + "loss": 0.6389, + "step": 120 + }, + { + "epoch": 0.058335203051379854, + "grad_norm": 0.5801005846647308, + "learning_rate": 5e-06, + "loss": 0.6394, + "step": 130 + }, + { + "epoch": 0.06282252636302446, + "grad_norm": 0.6162942143257907, + "learning_rate": 5e-06, + "loss": 0.6487, + "step": 140 + }, + { + "epoch": 0.06730984967466906, + "grad_norm": 0.5910482239279874, + "learning_rate": 5e-06, + "loss": 0.6535, + "step": 150 + }, + { + "epoch": 0.07179717298631366, + "grad_norm": 0.5628620440134962, + "learning_rate": 5e-06, + "loss": 0.6613, + "step": 160 + }, + { + "epoch": 0.07628449629795826, + "grad_norm": 0.5853996899496572, + "learning_rate": 5e-06, + "loss": 0.6357, + "step": 170 + }, + { + "epoch": 0.08077181960960288, + "grad_norm": 0.5878540945448613, + "learning_rate": 5e-06, + "loss": 0.636, + "step": 180 + }, + { + "epoch": 0.08525914292124748, + "grad_norm": 0.5862646504872097, + "learning_rate": 5e-06, + "loss": 0.6312, + "step": 190 + }, + { + "epoch": 0.08974646623289208, + "grad_norm": 0.5673857464664466, + "learning_rate": 5e-06, + "loss": 0.6332, + "step": 200 + }, + { + "epoch": 0.09423378954453668, + "grad_norm": 0.6082706115579384, + "learning_rate": 5e-06, + "loss": 0.6092, + "step": 210 + }, + { + "epoch": 0.09872111285618129, + "grad_norm": 0.6196844470280329, + "learning_rate": 5e-06, + "loss": 0.6421, + "step": 220 + }, + { + "epoch": 0.10320843616782589, + "grad_norm": 0.5579066730260925, + "learning_rate": 5e-06, + "loss": 0.6281, + "step": 230 + }, + { + "epoch": 0.1076957594794705, + "grad_norm": 0.565529818208485, + "learning_rate": 5e-06, + "loss": 0.6172, + "step": 240 + }, + { + "epoch": 0.1121830827911151, + "grad_norm": 0.6071432928320446, + "learning_rate": 5e-06, + "loss": 0.6016, + "step": 250 + }, + { + "epoch": 0.11667040610275971, + "grad_norm": 0.6073563540142406, + "learning_rate": 5e-06, + "loss": 0.6126, + "step": 260 + }, + { + "epoch": 0.12115772941440431, + "grad_norm": 0.569801618469301, + "learning_rate": 5e-06, + "loss": 0.6251, + "step": 270 + }, + { + "epoch": 0.12564505272604892, + "grad_norm": 0.591367661084153, + "learning_rate": 5e-06, + "loss": 0.625, + "step": 280 + }, + { + "epoch": 0.1301323760376935, + "grad_norm": 0.5757700659124422, + "learning_rate": 5e-06, + "loss": 0.619, + "step": 290 + }, + { + "epoch": 0.13461969934933812, + "grad_norm": 0.564239118303286, + "learning_rate": 5e-06, + "loss": 0.6073, + "step": 300 + }, + { + "epoch": 0.13910702266098274, + "grad_norm": 0.5885189461499749, + "learning_rate": 5e-06, + "loss": 0.6269, + "step": 310 + }, + { + "epoch": 0.14359434597262732, + "grad_norm": 0.5563218966218223, + "learning_rate": 5e-06, + "loss": 0.6294, + "step": 320 + }, + { + "epoch": 0.14808166928427194, + "grad_norm": 0.6172338154521191, + "learning_rate": 5e-06, + "loss": 0.6175, + "step": 330 + }, + { + "epoch": 0.15256899259591652, + "grad_norm": 0.5746423605096699, + "learning_rate": 5e-06, + "loss": 0.6, + "step": 340 + }, + { + "epoch": 0.15705631590756114, + "grad_norm": 0.5780025404911214, + "learning_rate": 5e-06, + "loss": 0.606, + "step": 350 + }, + { + "epoch": 0.16154363921920575, + "grad_norm": 0.5700015689377997, + "learning_rate": 5e-06, + "loss": 0.5955, + "step": 360 + }, + { + "epoch": 0.16603096253085034, + "grad_norm": 0.5807610554503659, + "learning_rate": 5e-06, + "loss": 0.5993, + "step": 370 + }, + { + "epoch": 0.17051828584249495, + "grad_norm": 0.5588205610118117, + "learning_rate": 5e-06, + "loss": 0.5941, + "step": 380 + }, + { + "epoch": 0.17500560915413957, + "grad_norm": 0.571147485187563, + "learning_rate": 5e-06, + "loss": 0.6086, + "step": 390 + }, + { + "epoch": 0.17949293246578416, + "grad_norm": 0.5874218028496501, + "learning_rate": 5e-06, + "loss": 0.6298, + "step": 400 + }, + { + "epoch": 0.18398025577742877, + "grad_norm": 0.553081232586883, + "learning_rate": 5e-06, + "loss": 0.6128, + "step": 410 + }, + { + "epoch": 0.18846757908907336, + "grad_norm": 0.5922159817168337, + "learning_rate": 5e-06, + "loss": 0.6199, + "step": 420 + }, + { + "epoch": 0.19295490240071797, + "grad_norm": 0.5941689160082125, + "learning_rate": 5e-06, + "loss": 0.6123, + "step": 430 + }, + { + "epoch": 0.19744222571236258, + "grad_norm": 0.5837547863994649, + "learning_rate": 5e-06, + "loss": 0.632, + "step": 440 + }, + { + "epoch": 0.20192954902400717, + "grad_norm": 0.5493502840784451, + "learning_rate": 5e-06, + "loss": 0.5918, + "step": 450 + }, + { + "epoch": 0.20641687233565179, + "grad_norm": 0.5843347451961302, + "learning_rate": 5e-06, + "loss": 0.6151, + "step": 460 + }, + { + "epoch": 0.2109041956472964, + "grad_norm": 0.5417935808080204, + "learning_rate": 5e-06, + "loss": 0.6059, + "step": 470 + }, + { + "epoch": 0.215391518958941, + "grad_norm": 0.5698753919399157, + "learning_rate": 5e-06, + "loss": 0.6135, + "step": 480 + }, + { + "epoch": 0.2198788422705856, + "grad_norm": 0.5244740288157084, + "learning_rate": 5e-06, + "loss": 0.5821, + "step": 490 + }, + { + "epoch": 0.2243661655822302, + "grad_norm": 0.6029129072997347, + "learning_rate": 5e-06, + "loss": 0.6116, + "step": 500 + }, + { + "epoch": 0.2288534888938748, + "grad_norm": 0.543722899676561, + "learning_rate": 5e-06, + "loss": 0.5907, + "step": 510 + }, + { + "epoch": 0.23334081220551942, + "grad_norm": 0.5619984349965198, + "learning_rate": 5e-06, + "loss": 0.6038, + "step": 520 + }, + { + "epoch": 0.237828135517164, + "grad_norm": 0.5859927720447103, + "learning_rate": 5e-06, + "loss": 0.6244, + "step": 530 + }, + { + "epoch": 0.24231545882880862, + "grad_norm": 0.5583414821346395, + "learning_rate": 5e-06, + "loss": 0.5981, + "step": 540 + }, + { + "epoch": 0.24680278214045323, + "grad_norm": 0.5499638333486776, + "learning_rate": 5e-06, + "loss": 0.5908, + "step": 550 + }, + { + "epoch": 0.25129010545209784, + "grad_norm": 0.5826333088813789, + "learning_rate": 5e-06, + "loss": 0.5683, + "step": 560 + }, + { + "epoch": 0.25577742876374243, + "grad_norm": 0.5492837199828549, + "learning_rate": 5e-06, + "loss": 0.622, + "step": 570 + }, + { + "epoch": 0.260264752075387, + "grad_norm": 0.5829754943916923, + "learning_rate": 5e-06, + "loss": 0.5964, + "step": 580 + }, + { + "epoch": 0.26475207538703166, + "grad_norm": 0.5639030175066925, + "learning_rate": 5e-06, + "loss": 0.5894, + "step": 590 + }, + { + "epoch": 0.26923939869867625, + "grad_norm": 0.5840101964805389, + "learning_rate": 5e-06, + "loss": 0.5879, + "step": 600 + }, + { + "epoch": 0.27372672201032083, + "grad_norm": 0.5654294930486207, + "learning_rate": 5e-06, + "loss": 0.5821, + "step": 610 + }, + { + "epoch": 0.2782140453219655, + "grad_norm": 0.6015547946403642, + "learning_rate": 5e-06, + "loss": 0.5988, + "step": 620 + }, + { + "epoch": 0.28270136863361006, + "grad_norm": 0.5475239684469887, + "learning_rate": 5e-06, + "loss": 0.5984, + "step": 630 + }, + { + "epoch": 0.28718869194525465, + "grad_norm": 0.5984753640582714, + "learning_rate": 5e-06, + "loss": 0.6093, + "step": 640 + }, + { + "epoch": 0.29167601525689923, + "grad_norm": 0.5743058756802668, + "learning_rate": 5e-06, + "loss": 0.6061, + "step": 650 + }, + { + "epoch": 0.2961633385685439, + "grad_norm": 0.5643830386334935, + "learning_rate": 5e-06, + "loss": 0.6119, + "step": 660 + }, + { + "epoch": 0.30065066188018846, + "grad_norm": 0.6133686427622306, + "learning_rate": 5e-06, + "loss": 0.5866, + "step": 670 + }, + { + "epoch": 0.30513798519183305, + "grad_norm": 0.5891262468962493, + "learning_rate": 5e-06, + "loss": 0.5856, + "step": 680 + }, + { + "epoch": 0.3096253085034777, + "grad_norm": 0.5667738482065338, + "learning_rate": 5e-06, + "loss": 0.6159, + "step": 690 + }, + { + "epoch": 0.3141126318151223, + "grad_norm": 0.5659614870185288, + "learning_rate": 5e-06, + "loss": 0.6026, + "step": 700 + }, + { + "epoch": 0.31859995512676687, + "grad_norm": 0.5708631949188694, + "learning_rate": 5e-06, + "loss": 0.5728, + "step": 710 + }, + { + "epoch": 0.3230872784384115, + "grad_norm": 0.582979417517679, + "learning_rate": 5e-06, + "loss": 0.6193, + "step": 720 + }, + { + "epoch": 0.3275746017500561, + "grad_norm": 0.5945610104189938, + "learning_rate": 5e-06, + "loss": 0.5901, + "step": 730 + }, + { + "epoch": 0.3320619250617007, + "grad_norm": 0.5716342616547154, + "learning_rate": 5e-06, + "loss": 0.62, + "step": 740 + }, + { + "epoch": 0.3365492483733453, + "grad_norm": 0.5733402898671368, + "learning_rate": 5e-06, + "loss": 0.5918, + "step": 750 + }, + { + "epoch": 0.3410365716849899, + "grad_norm": 0.572434524506764, + "learning_rate": 5e-06, + "loss": 0.584, + "step": 760 + }, + { + "epoch": 0.3455238949966345, + "grad_norm": 0.5821520713178042, + "learning_rate": 5e-06, + "loss": 0.5826, + "step": 770 + }, + { + "epoch": 0.35001121830827914, + "grad_norm": 0.5502868561175508, + "learning_rate": 5e-06, + "loss": 0.6246, + "step": 780 + }, + { + "epoch": 0.3544985416199237, + "grad_norm": 0.5978195056323264, + "learning_rate": 5e-06, + "loss": 0.6169, + "step": 790 + }, + { + "epoch": 0.3589858649315683, + "grad_norm": 0.5838319332934967, + "learning_rate": 5e-06, + "loss": 0.5911, + "step": 800 + }, + { + "epoch": 0.3634731882432129, + "grad_norm": 0.572267142733801, + "learning_rate": 5e-06, + "loss": 0.599, + "step": 810 + }, + { + "epoch": 0.36796051155485754, + "grad_norm": 0.582203599292086, + "learning_rate": 5e-06, + "loss": 0.6276, + "step": 820 + }, + { + "epoch": 0.3724478348665021, + "grad_norm": 0.5828348677910858, + "learning_rate": 5e-06, + "loss": 0.5758, + "step": 830 + }, + { + "epoch": 0.3769351581781467, + "grad_norm": 0.6384385145884847, + "learning_rate": 5e-06, + "loss": 0.5818, + "step": 840 + }, + { + "epoch": 0.38142248148979135, + "grad_norm": 0.6063697413207821, + "learning_rate": 5e-06, + "loss": 0.5833, + "step": 850 + }, + { + "epoch": 0.38590980480143594, + "grad_norm": 0.5829350365562836, + "learning_rate": 5e-06, + "loss": 0.5896, + "step": 860 + }, + { + "epoch": 0.3903971281130805, + "grad_norm": 0.5533097693747884, + "learning_rate": 5e-06, + "loss": 0.6351, + "step": 870 + }, + { + "epoch": 0.39488445142472517, + "grad_norm": 0.560685123123169, + "learning_rate": 5e-06, + "loss": 0.6013, + "step": 880 + }, + { + "epoch": 0.39937177473636976, + "grad_norm": 0.5878919825433736, + "learning_rate": 5e-06, + "loss": 0.5834, + "step": 890 + }, + { + "epoch": 0.40385909804801434, + "grad_norm": 0.6071601416861148, + "learning_rate": 5e-06, + "loss": 0.5952, + "step": 900 + }, + { + "epoch": 0.408346421359659, + "grad_norm": 0.5743329576838876, + "learning_rate": 5e-06, + "loss": 0.5707, + "step": 910 + }, + { + "epoch": 0.41283374467130357, + "grad_norm": 0.5838548938969085, + "learning_rate": 5e-06, + "loss": 0.5963, + "step": 920 + }, + { + "epoch": 0.41732106798294816, + "grad_norm": 0.6266644917633146, + "learning_rate": 5e-06, + "loss": 0.6116, + "step": 930 + }, + { + "epoch": 0.4218083912945928, + "grad_norm": 0.5997476072987922, + "learning_rate": 5e-06, + "loss": 0.5949, + "step": 940 + }, + { + "epoch": 0.4262957146062374, + "grad_norm": 0.5325526105961608, + "learning_rate": 5e-06, + "loss": 0.578, + "step": 950 + }, + { + "epoch": 0.430783037917882, + "grad_norm": 0.5789065042536049, + "learning_rate": 5e-06, + "loss": 0.5756, + "step": 960 + }, + { + "epoch": 0.4352703612295266, + "grad_norm": 0.5810941623037826, + "learning_rate": 5e-06, + "loss": 0.5773, + "step": 970 + }, + { + "epoch": 0.4397576845411712, + "grad_norm": 0.5704375735854125, + "learning_rate": 5e-06, + "loss": 0.6106, + "step": 980 + }, + { + "epoch": 0.4442450078528158, + "grad_norm": 0.5807401734392655, + "learning_rate": 5e-06, + "loss": 0.5867, + "step": 990 + }, + { + "epoch": 0.4487323311644604, + "grad_norm": 0.5328866205208039, + "learning_rate": 5e-06, + "loss": 0.5752, + "step": 1000 + }, + { + "epoch": 0.453219654476105, + "grad_norm": 0.5872115159587232, + "learning_rate": 5e-06, + "loss": 0.6077, + "step": 1010 + }, + { + "epoch": 0.4577069777877496, + "grad_norm": 0.5467361495539828, + "learning_rate": 5e-06, + "loss": 0.6021, + "step": 1020 + }, + { + "epoch": 0.4621943010993942, + "grad_norm": 0.5824366492306351, + "learning_rate": 5e-06, + "loss": 0.5895, + "step": 1030 + }, + { + "epoch": 0.46668162441103883, + "grad_norm": 0.5730302930825869, + "learning_rate": 5e-06, + "loss": 0.5904, + "step": 1040 + }, + { + "epoch": 0.4711689477226834, + "grad_norm": 0.5741405557180129, + "learning_rate": 5e-06, + "loss": 0.5774, + "step": 1050 + }, + { + "epoch": 0.475656271034328, + "grad_norm": 0.550592306843404, + "learning_rate": 5e-06, + "loss": 0.5936, + "step": 1060 + }, + { + "epoch": 0.48014359434597265, + "grad_norm": 0.5833572077757988, + "learning_rate": 5e-06, + "loss": 0.5762, + "step": 1070 + }, + { + "epoch": 0.48463091765761723, + "grad_norm": 0.5737636703367411, + "learning_rate": 5e-06, + "loss": 0.5923, + "step": 1080 + }, + { + "epoch": 0.4891182409692618, + "grad_norm": 0.5871383202715521, + "learning_rate": 5e-06, + "loss": 0.5893, + "step": 1090 + }, + { + "epoch": 0.49360556428090646, + "grad_norm": 0.5749395258974863, + "learning_rate": 5e-06, + "loss": 0.5675, + "step": 1100 + }, + { + "epoch": 0.49809288759255105, + "grad_norm": 0.5977797308447645, + "learning_rate": 5e-06, + "loss": 0.5702, + "step": 1110 + }, + { + "epoch": 0.5025802109041957, + "grad_norm": 0.5693088698665462, + "learning_rate": 5e-06, + "loss": 0.5783, + "step": 1120 + }, + { + "epoch": 0.5070675342158403, + "grad_norm": 0.5666383038783265, + "learning_rate": 5e-06, + "loss": 0.579, + "step": 1130 + }, + { + "epoch": 0.5115548575274849, + "grad_norm": 0.5685405367124683, + "learning_rate": 5e-06, + "loss": 0.5824, + "step": 1140 + }, + { + "epoch": 0.5160421808391294, + "grad_norm": 0.6132416315716593, + "learning_rate": 5e-06, + "loss": 0.5656, + "step": 1150 + }, + { + "epoch": 0.520529504150774, + "grad_norm": 0.5517718231004817, + "learning_rate": 5e-06, + "loss": 0.5874, + "step": 1160 + }, + { + "epoch": 0.5250168274624186, + "grad_norm": 0.5387150051806513, + "learning_rate": 5e-06, + "loss": 0.599, + "step": 1170 + }, + { + "epoch": 0.5295041507740633, + "grad_norm": 0.5807000848606523, + "learning_rate": 5e-06, + "loss": 0.5657, + "step": 1180 + }, + { + "epoch": 0.5339914740857079, + "grad_norm": 0.5963571574776558, + "learning_rate": 5e-06, + "loss": 0.5823, + "step": 1190 + }, + { + "epoch": 0.5384787973973525, + "grad_norm": 0.5454964206038695, + "learning_rate": 5e-06, + "loss": 0.609, + "step": 1200 + }, + { + "epoch": 0.5429661207089971, + "grad_norm": 0.5727578636243832, + "learning_rate": 5e-06, + "loss": 0.5757, + "step": 1210 + }, + { + "epoch": 0.5474534440206417, + "grad_norm": 0.5942434570927121, + "learning_rate": 5e-06, + "loss": 0.5939, + "step": 1220 + }, + { + "epoch": 0.5519407673322863, + "grad_norm": 0.601970394484814, + "learning_rate": 5e-06, + "loss": 0.5702, + "step": 1230 + }, + { + "epoch": 0.556428090643931, + "grad_norm": 0.5683956652736455, + "learning_rate": 5e-06, + "loss": 0.5761, + "step": 1240 + }, + { + "epoch": 0.5609154139555755, + "grad_norm": 0.5484215866941293, + "learning_rate": 5e-06, + "loss": 0.57, + "step": 1250 + }, + { + "epoch": 0.5654027372672201, + "grad_norm": 0.5566860752701241, + "learning_rate": 5e-06, + "loss": 0.5957, + "step": 1260 + }, + { + "epoch": 0.5698900605788647, + "grad_norm": 0.6230757081721424, + "learning_rate": 5e-06, + "loss": 0.5913, + "step": 1270 + }, + { + "epoch": 0.5743773838905093, + "grad_norm": 0.5831220627839732, + "learning_rate": 5e-06, + "loss": 0.5694, + "step": 1280 + }, + { + "epoch": 0.5788647072021539, + "grad_norm": 0.5836944514712498, + "learning_rate": 5e-06, + "loss": 0.5679, + "step": 1290 + }, + { + "epoch": 0.5833520305137985, + "grad_norm": 0.5606507135283174, + "learning_rate": 5e-06, + "loss": 0.5687, + "step": 1300 + }, + { + "epoch": 0.5878393538254432, + "grad_norm": 0.6095163090362549, + "learning_rate": 5e-06, + "loss": 0.6019, + "step": 1310 + }, + { + "epoch": 0.5923266771370878, + "grad_norm": 0.59010448543007, + "learning_rate": 5e-06, + "loss": 0.5885, + "step": 1320 + }, + { + "epoch": 0.5968140004487323, + "grad_norm": 0.5880393988574679, + "learning_rate": 5e-06, + "loss": 0.6015, + "step": 1330 + }, + { + "epoch": 0.6013013237603769, + "grad_norm": 0.5951700057903788, + "learning_rate": 5e-06, + "loss": 0.5778, + "step": 1340 + }, + { + "epoch": 0.6057886470720215, + "grad_norm": 0.5520813189968636, + "learning_rate": 5e-06, + "loss": 0.5577, + "step": 1350 + }, + { + "epoch": 0.6102759703836661, + "grad_norm": 0.5706267699210373, + "learning_rate": 5e-06, + "loss": 0.5666, + "step": 1360 + }, + { + "epoch": 0.6147632936953108, + "grad_norm": 0.5873241252786081, + "learning_rate": 5e-06, + "loss": 0.579, + "step": 1370 + }, + { + "epoch": 0.6192506170069554, + "grad_norm": 0.5919098224825123, + "learning_rate": 5e-06, + "loss": 0.597, + "step": 1380 + }, + { + "epoch": 0.6237379403186, + "grad_norm": 0.5593146398046412, + "learning_rate": 5e-06, + "loss": 0.5764, + "step": 1390 + }, + { + "epoch": 0.6282252636302446, + "grad_norm": 0.5211444666215148, + "learning_rate": 5e-06, + "loss": 0.5834, + "step": 1400 + }, + { + "epoch": 0.6327125869418891, + "grad_norm": 0.5464287006558793, + "learning_rate": 5e-06, + "loss": 0.565, + "step": 1410 + }, + { + "epoch": 0.6371999102535337, + "grad_norm": 0.5955258518895813, + "learning_rate": 5e-06, + "loss": 0.5686, + "step": 1420 + }, + { + "epoch": 0.6416872335651783, + "grad_norm": 0.5950629609101662, + "learning_rate": 5e-06, + "loss": 0.5591, + "step": 1430 + }, + { + "epoch": 0.646174556876823, + "grad_norm": 0.5764649145742474, + "learning_rate": 5e-06, + "loss": 0.5646, + "step": 1440 + }, + { + "epoch": 0.6506618801884676, + "grad_norm": 0.5623492091421548, + "learning_rate": 5e-06, + "loss": 0.5753, + "step": 1450 + }, + { + "epoch": 0.6551492035001122, + "grad_norm": 0.5691792772789492, + "learning_rate": 5e-06, + "loss": 0.6129, + "step": 1460 + }, + { + "epoch": 0.6596365268117568, + "grad_norm": 0.5729790062068799, + "learning_rate": 5e-06, + "loss": 0.5825, + "step": 1470 + }, + { + "epoch": 0.6641238501234014, + "grad_norm": 0.5516413746220878, + "learning_rate": 5e-06, + "loss": 0.5832, + "step": 1480 + }, + { + "epoch": 0.668611173435046, + "grad_norm": 0.5952217543049041, + "learning_rate": 5e-06, + "loss": 0.6061, + "step": 1490 + }, + { + "epoch": 0.6730984967466906, + "grad_norm": 0.5430982582264119, + "learning_rate": 5e-06, + "loss": 0.579, + "step": 1500 + }, + { + "epoch": 0.6775858200583352, + "grad_norm": 0.5863720016018602, + "learning_rate": 5e-06, + "loss": 0.5872, + "step": 1510 + }, + { + "epoch": 0.6820731433699798, + "grad_norm": 0.5613897501209862, + "learning_rate": 5e-06, + "loss": 0.5694, + "step": 1520 + }, + { + "epoch": 0.6865604666816244, + "grad_norm": 0.5650891221037946, + "learning_rate": 5e-06, + "loss": 0.5591, + "step": 1530 + }, + { + "epoch": 0.691047789993269, + "grad_norm": 0.5648114046496064, + "learning_rate": 5e-06, + "loss": 0.5543, + "step": 1540 + }, + { + "epoch": 0.6955351133049136, + "grad_norm": 0.5403902955132622, + "learning_rate": 5e-06, + "loss": 0.5584, + "step": 1550 + }, + { + "epoch": 0.7000224366165583, + "grad_norm": 0.569377834200537, + "learning_rate": 5e-06, + "loss": 0.5697, + "step": 1560 + }, + { + "epoch": 0.7045097599282029, + "grad_norm": 0.5567609550962811, + "learning_rate": 5e-06, + "loss": 0.5913, + "step": 1570 + }, + { + "epoch": 0.7089970832398474, + "grad_norm": 0.5460331170553634, + "learning_rate": 5e-06, + "loss": 0.5852, + "step": 1580 + }, + { + "epoch": 0.713484406551492, + "grad_norm": 0.5804324166647036, + "learning_rate": 5e-06, + "loss": 0.559, + "step": 1590 + }, + { + "epoch": 0.7179717298631366, + "grad_norm": 0.5960848198273799, + "learning_rate": 5e-06, + "loss": 0.5591, + "step": 1600 + }, + { + "epoch": 0.7224590531747812, + "grad_norm": 0.5934788516849224, + "learning_rate": 5e-06, + "loss": 0.5757, + "step": 1610 + }, + { + "epoch": 0.7269463764864258, + "grad_norm": 0.5634154921972939, + "learning_rate": 5e-06, + "loss": 0.5764, + "step": 1620 + }, + { + "epoch": 0.7314336997980705, + "grad_norm": 0.5608877054747304, + "learning_rate": 5e-06, + "loss": 0.5726, + "step": 1630 + }, + { + "epoch": 0.7359210231097151, + "grad_norm": 0.5819040189686953, + "learning_rate": 5e-06, + "loss": 0.5761, + "step": 1640 + }, + { + "epoch": 0.7404083464213597, + "grad_norm": 0.5497077389456424, + "learning_rate": 5e-06, + "loss": 0.5892, + "step": 1650 + }, + { + "epoch": 0.7448956697330043, + "grad_norm": 0.5540304283341861, + "learning_rate": 5e-06, + "loss": 0.5717, + "step": 1660 + }, + { + "epoch": 0.7493829930446488, + "grad_norm": 0.555029973847418, + "learning_rate": 5e-06, + "loss": 0.5817, + "step": 1670 + }, + { + "epoch": 0.7538703163562934, + "grad_norm": 0.5656773354976847, + "learning_rate": 5e-06, + "loss": 0.5592, + "step": 1680 + }, + { + "epoch": 0.7583576396679381, + "grad_norm": 0.5614465252120793, + "learning_rate": 5e-06, + "loss": 0.5862, + "step": 1690 + }, + { + "epoch": 0.7628449629795827, + "grad_norm": 0.5971084841293993, + "learning_rate": 5e-06, + "loss": 0.5477, + "step": 1700 + }, + { + "epoch": 0.7673322862912273, + "grad_norm": 0.5602547594616473, + "learning_rate": 5e-06, + "loss": 0.5515, + "step": 1710 + }, + { + "epoch": 0.7718196096028719, + "grad_norm": 0.5761549476698519, + "learning_rate": 5e-06, + "loss": 0.5545, + "step": 1720 + }, + { + "epoch": 0.7763069329145165, + "grad_norm": 0.5623153462700364, + "learning_rate": 5e-06, + "loss": 0.5638, + "step": 1730 + }, + { + "epoch": 0.780794256226161, + "grad_norm": 0.5595040683918967, + "learning_rate": 5e-06, + "loss": 0.5706, + "step": 1740 + }, + { + "epoch": 0.7852815795378058, + "grad_norm": 0.6214567614298656, + "learning_rate": 5e-06, + "loss": 0.5759, + "step": 1750 + }, + { + "epoch": 0.7897689028494503, + "grad_norm": 0.5790695246671757, + "learning_rate": 5e-06, + "loss": 0.5618, + "step": 1760 + }, + { + "epoch": 0.7942562261610949, + "grad_norm": 0.5868799878975245, + "learning_rate": 5e-06, + "loss": 0.5794, + "step": 1770 + }, + { + "epoch": 0.7987435494727395, + "grad_norm": 0.5552402081587721, + "learning_rate": 5e-06, + "loss": 0.5725, + "step": 1780 + }, + { + "epoch": 0.8032308727843841, + "grad_norm": 0.5465116389934637, + "learning_rate": 5e-06, + "loss": 0.5651, + "step": 1790 + }, + { + "epoch": 0.8077181960960287, + "grad_norm": 0.5830251282771208, + "learning_rate": 5e-06, + "loss": 0.5575, + "step": 1800 + }, + { + "epoch": 0.8122055194076733, + "grad_norm": 0.5712510816652253, + "learning_rate": 5e-06, + "loss": 0.5598, + "step": 1810 + }, + { + "epoch": 0.816692842719318, + "grad_norm": 0.562885410999007, + "learning_rate": 5e-06, + "loss": 0.5598, + "step": 1820 + }, + { + "epoch": 0.8211801660309626, + "grad_norm": 0.5779523907871871, + "learning_rate": 5e-06, + "loss": 0.5723, + "step": 1830 + }, + { + "epoch": 0.8256674893426071, + "grad_norm": 0.5189856325650857, + "learning_rate": 5e-06, + "loss": 0.5452, + "step": 1840 + }, + { + "epoch": 0.8301548126542517, + "grad_norm": 0.5720061007902056, + "learning_rate": 5e-06, + "loss": 0.6093, + "step": 1850 + }, + { + "epoch": 0.8346421359658963, + "grad_norm": 0.5695943485875125, + "learning_rate": 5e-06, + "loss": 0.5652, + "step": 1860 + }, + { + "epoch": 0.8391294592775409, + "grad_norm": 0.5655340064627559, + "learning_rate": 5e-06, + "loss": 0.5578, + "step": 1870 + }, + { + "epoch": 0.8436167825891856, + "grad_norm": 0.6040653302056215, + "learning_rate": 5e-06, + "loss": 0.5913, + "step": 1880 + }, + { + "epoch": 0.8481041059008302, + "grad_norm": 0.5358932702911336, + "learning_rate": 5e-06, + "loss": 0.5506, + "step": 1890 + }, + { + "epoch": 0.8525914292124748, + "grad_norm": 0.5623759018768127, + "learning_rate": 5e-06, + "loss": 0.5755, + "step": 1900 + }, + { + "epoch": 0.8570787525241194, + "grad_norm": 0.5478233896665743, + "learning_rate": 5e-06, + "loss": 0.5705, + "step": 1910 + }, + { + "epoch": 0.861566075835764, + "grad_norm": 0.5581741180688066, + "learning_rate": 5e-06, + "loss": 0.5744, + "step": 1920 + }, + { + "epoch": 0.8660533991474085, + "grad_norm": 0.581165938497761, + "learning_rate": 5e-06, + "loss": 0.5551, + "step": 1930 + }, + { + "epoch": 0.8705407224590532, + "grad_norm": 0.5923735410956669, + "learning_rate": 5e-06, + "loss": 0.5724, + "step": 1940 + }, + { + "epoch": 0.8750280457706978, + "grad_norm": 0.5450424051736013, + "learning_rate": 5e-06, + "loss": 0.5509, + "step": 1950 + }, + { + "epoch": 0.8795153690823424, + "grad_norm": 0.6040204710835786, + "learning_rate": 5e-06, + "loss": 0.5712, + "step": 1960 + }, + { + "epoch": 0.884002692393987, + "grad_norm": 0.5655431066508525, + "learning_rate": 5e-06, + "loss": 0.5841, + "step": 1970 + }, + { + "epoch": 0.8884900157056316, + "grad_norm": 0.5648606449816002, + "learning_rate": 5e-06, + "loss": 0.5559, + "step": 1980 + }, + { + "epoch": 0.8929773390172762, + "grad_norm": 0.565947961900647, + "learning_rate": 5e-06, + "loss": 0.5424, + "step": 1990 + }, + { + "epoch": 0.8974646623289207, + "grad_norm": 0.5574359758809583, + "learning_rate": 5e-06, + "loss": 0.5614, + "step": 2000 + }, + { + "epoch": 0.9019519856405654, + "grad_norm": 0.5511165034666912, + "learning_rate": 5e-06, + "loss": 0.5756, + "step": 2010 + }, + { + "epoch": 0.90643930895221, + "grad_norm": 0.5700569987335933, + "learning_rate": 5e-06, + "loss": 0.5938, + "step": 2020 + }, + { + "epoch": 0.9109266322638546, + "grad_norm": 0.5586037159206011, + "learning_rate": 5e-06, + "loss": 0.5793, + "step": 2030 + }, + { + "epoch": 0.9154139555754992, + "grad_norm": 0.5621567704840573, + "learning_rate": 5e-06, + "loss": 0.5702, + "step": 2040 + }, + { + "epoch": 0.9199012788871438, + "grad_norm": 0.5706551688766498, + "learning_rate": 5e-06, + "loss": 0.5443, + "step": 2050 + }, + { + "epoch": 0.9243886021987884, + "grad_norm": 0.5532451823002996, + "learning_rate": 5e-06, + "loss": 0.5726, + "step": 2060 + }, + { + "epoch": 0.9288759255104331, + "grad_norm": 0.5485701610143561, + "learning_rate": 5e-06, + "loss": 0.5605, + "step": 2070 + }, + { + "epoch": 0.9333632488220777, + "grad_norm": 0.6047400972527601, + "learning_rate": 5e-06, + "loss": 0.5799, + "step": 2080 + }, + { + "epoch": 0.9378505721337222, + "grad_norm": 0.5428858709451123, + "learning_rate": 5e-06, + "loss": 0.5745, + "step": 2090 + }, + { + "epoch": 0.9423378954453668, + "grad_norm": 0.5524203935747322, + "learning_rate": 5e-06, + "loss": 0.5465, + "step": 2100 + }, + { + "epoch": 0.9468252187570114, + "grad_norm": 0.5515427513485951, + "learning_rate": 5e-06, + "loss": 0.5526, + "step": 2110 + }, + { + "epoch": 0.951312542068656, + "grad_norm": 0.5853063415860351, + "learning_rate": 5e-06, + "loss": 0.5737, + "step": 2120 + }, + { + "epoch": 0.9557998653803007, + "grad_norm": 0.5369290552095258, + "learning_rate": 5e-06, + "loss": 0.5493, + "step": 2130 + }, + { + "epoch": 0.9602871886919453, + "grad_norm": 0.5520734247548831, + "learning_rate": 5e-06, + "loss": 0.5461, + "step": 2140 + }, + { + "epoch": 0.9647745120035899, + "grad_norm": 0.5653346233403189, + "learning_rate": 5e-06, + "loss": 0.6057, + "step": 2150 + }, + { + "epoch": 0.9692618353152345, + "grad_norm": 0.582218445061444, + "learning_rate": 5e-06, + "loss": 0.5459, + "step": 2160 + }, + { + "epoch": 0.973749158626879, + "grad_norm": 0.5787212589606142, + "learning_rate": 5e-06, + "loss": 0.5471, + "step": 2170 + }, + { + "epoch": 0.9782364819385236, + "grad_norm": 0.5594191735315223, + "learning_rate": 5e-06, + "loss": 0.5689, + "step": 2180 + }, + { + "epoch": 0.9827238052501682, + "grad_norm": 0.5396068252067977, + "learning_rate": 5e-06, + "loss": 0.5622, + "step": 2190 + }, + { + "epoch": 0.9872111285618129, + "grad_norm": 0.5376425274574365, + "learning_rate": 5e-06, + "loss": 0.5519, + "step": 2200 + }, + { + "epoch": 0.9916984518734575, + "grad_norm": 0.5920263370787465, + "learning_rate": 5e-06, + "loss": 0.5561, + "step": 2210 + }, + { + "epoch": 0.9961857751851021, + "grad_norm": 0.580623876573116, + "learning_rate": 5e-06, + "loss": 0.5712, + "step": 2220 + }, + { + "epoch": 0.9997756338344178, + "eval_loss": 0.567927360534668, + "eval_runtime": 559.1888, + "eval_samples_per_second": 26.842, + "eval_steps_per_second": 0.42, + "step": 2228 + }, + { + "epoch": 1.0006730984967467, + "grad_norm": 0.5734872435921652, + "learning_rate": 5e-06, + "loss": 0.566, + "step": 2230 + }, + { + "epoch": 1.0051604218083914, + "grad_norm": 0.5741533955437085, + "learning_rate": 5e-06, + "loss": 0.5081, + "step": 2240 + }, + { + "epoch": 1.0096477451200359, + "grad_norm": 0.5286982651391207, + "learning_rate": 5e-06, + "loss": 0.4975, + "step": 2250 + }, + { + "epoch": 1.0141350684316806, + "grad_norm": 0.5565402789518736, + "learning_rate": 5e-06, + "loss": 0.4866, + "step": 2260 + }, + { + "epoch": 1.018622391743325, + "grad_norm": 0.5418393585734336, + "learning_rate": 5e-06, + "loss": 0.4855, + "step": 2270 + }, + { + "epoch": 1.0231097150549697, + "grad_norm": 0.5272758697526944, + "learning_rate": 5e-06, + "loss": 0.5484, + "step": 2280 + }, + { + "epoch": 1.0275970383666144, + "grad_norm": 0.5666635742640517, + "learning_rate": 5e-06, + "loss": 0.5021, + "step": 2290 + }, + { + "epoch": 1.032084361678259, + "grad_norm": 0.5482469107158694, + "learning_rate": 5e-06, + "loss": 0.541, + "step": 2300 + }, + { + "epoch": 1.0365716849899036, + "grad_norm": 0.5785689508918422, + "learning_rate": 5e-06, + "loss": 0.4939, + "step": 2310 + }, + { + "epoch": 1.041059008301548, + "grad_norm": 0.5479491492317479, + "learning_rate": 5e-06, + "loss": 0.4923, + "step": 2320 + }, + { + "epoch": 1.0455463316131928, + "grad_norm": 0.596193057255721, + "learning_rate": 5e-06, + "loss": 0.5309, + "step": 2330 + }, + { + "epoch": 1.0500336549248372, + "grad_norm": 0.5684218587581331, + "learning_rate": 5e-06, + "loss": 0.4871, + "step": 2340 + }, + { + "epoch": 1.054520978236482, + "grad_norm": 0.5501353350393796, + "learning_rate": 5e-06, + "loss": 0.5042, + "step": 2350 + }, + { + "epoch": 1.0590083015481266, + "grad_norm": 0.5651420414453633, + "learning_rate": 5e-06, + "loss": 0.5268, + "step": 2360 + }, + { + "epoch": 1.0634956248597711, + "grad_norm": 0.5556768039050937, + "learning_rate": 5e-06, + "loss": 0.4849, + "step": 2370 + }, + { + "epoch": 1.0679829481714158, + "grad_norm": 0.5177547386554735, + "learning_rate": 5e-06, + "loss": 0.4897, + "step": 2380 + }, + { + "epoch": 1.0724702714830603, + "grad_norm": 0.5651839563997499, + "learning_rate": 5e-06, + "loss": 0.524, + "step": 2390 + }, + { + "epoch": 1.076957594794705, + "grad_norm": 0.5326902266396754, + "learning_rate": 5e-06, + "loss": 0.4881, + "step": 2400 + }, + { + "epoch": 1.0814449181063495, + "grad_norm": 0.5628872446586874, + "learning_rate": 5e-06, + "loss": 0.5297, + "step": 2410 + }, + { + "epoch": 1.0859322414179942, + "grad_norm": 0.5477565748095592, + "learning_rate": 5e-06, + "loss": 0.5155, + "step": 2420 + }, + { + "epoch": 1.0904195647296389, + "grad_norm": 0.5156657552293519, + "learning_rate": 5e-06, + "loss": 0.4981, + "step": 2430 + }, + { + "epoch": 1.0949068880412833, + "grad_norm": 0.5499438723209844, + "learning_rate": 5e-06, + "loss": 0.5053, + "step": 2440 + }, + { + "epoch": 1.099394211352928, + "grad_norm": 0.5600071230838901, + "learning_rate": 5e-06, + "loss": 0.5056, + "step": 2450 + }, + { + "epoch": 1.1038815346645725, + "grad_norm": 0.5379185956294618, + "learning_rate": 5e-06, + "loss": 0.5204, + "step": 2460 + }, + { + "epoch": 1.1083688579762172, + "grad_norm": 0.5640271259467887, + "learning_rate": 5e-06, + "loss": 0.5004, + "step": 2470 + }, + { + "epoch": 1.112856181287862, + "grad_norm": 0.5502816116129311, + "learning_rate": 5e-06, + "loss": 0.499, + "step": 2480 + }, + { + "epoch": 1.1173435045995064, + "grad_norm": 0.5682876811264557, + "learning_rate": 5e-06, + "loss": 0.4921, + "step": 2490 + }, + { + "epoch": 1.121830827911151, + "grad_norm": 0.5421816523423539, + "learning_rate": 5e-06, + "loss": 0.5108, + "step": 2500 + }, + { + "epoch": 1.1263181512227955, + "grad_norm": 0.5105369153949931, + "learning_rate": 5e-06, + "loss": 0.5003, + "step": 2510 + }, + { + "epoch": 1.1308054745344402, + "grad_norm": 0.5588492929357224, + "learning_rate": 5e-06, + "loss": 0.475, + "step": 2520 + }, + { + "epoch": 1.1352927978460847, + "grad_norm": 0.5716988346827195, + "learning_rate": 5e-06, + "loss": 0.5209, + "step": 2530 + }, + { + "epoch": 1.1397801211577294, + "grad_norm": 0.5169436013613863, + "learning_rate": 5e-06, + "loss": 0.4916, + "step": 2540 + }, + { + "epoch": 1.144267444469374, + "grad_norm": 0.6145618845838399, + "learning_rate": 5e-06, + "loss": 0.5013, + "step": 2550 + }, + { + "epoch": 1.1487547677810186, + "grad_norm": 0.5444973960505051, + "learning_rate": 5e-06, + "loss": 0.5332, + "step": 2560 + }, + { + "epoch": 1.1532420910926633, + "grad_norm": 0.5520753016233167, + "learning_rate": 5e-06, + "loss": 0.5048, + "step": 2570 + }, + { + "epoch": 1.1577294144043078, + "grad_norm": 0.5750697187874539, + "learning_rate": 5e-06, + "loss": 0.5141, + "step": 2580 + }, + { + "epoch": 1.1622167377159525, + "grad_norm": 0.5747532663976821, + "learning_rate": 5e-06, + "loss": 0.5144, + "step": 2590 + }, + { + "epoch": 1.166704061027597, + "grad_norm": 0.5345651363842143, + "learning_rate": 5e-06, + "loss": 0.5208, + "step": 2600 + }, + { + "epoch": 1.1711913843392416, + "grad_norm": 0.5280475672990748, + "learning_rate": 5e-06, + "loss": 0.4987, + "step": 2610 + }, + { + "epoch": 1.1756787076508863, + "grad_norm": 0.6039148518875526, + "learning_rate": 5e-06, + "loss": 0.5132, + "step": 2620 + }, + { + "epoch": 1.1801660309625308, + "grad_norm": 0.5422913796982765, + "learning_rate": 5e-06, + "loss": 0.496, + "step": 2630 + }, + { + "epoch": 1.1846533542741755, + "grad_norm": 0.564401368588004, + "learning_rate": 5e-06, + "loss": 0.4827, + "step": 2640 + }, + { + "epoch": 1.18914067758582, + "grad_norm": 0.5373400269555145, + "learning_rate": 5e-06, + "loss": 0.5073, + "step": 2650 + }, + { + "epoch": 1.1936280008974647, + "grad_norm": 0.5314197538619471, + "learning_rate": 5e-06, + "loss": 0.5422, + "step": 2660 + }, + { + "epoch": 1.1981153242091094, + "grad_norm": 0.5166900359174719, + "learning_rate": 5e-06, + "loss": 0.519, + "step": 2670 + }, + { + "epoch": 1.2026026475207539, + "grad_norm": 0.5180554826133104, + "learning_rate": 5e-06, + "loss": 0.497, + "step": 2680 + }, + { + "epoch": 1.2070899708323986, + "grad_norm": 0.5323969904323123, + "learning_rate": 5e-06, + "loss": 0.5058, + "step": 2690 + }, + { + "epoch": 1.211577294144043, + "grad_norm": 0.5424465309236546, + "learning_rate": 5e-06, + "loss": 0.4958, + "step": 2700 + }, + { + "epoch": 1.2160646174556877, + "grad_norm": 0.5412841285613176, + "learning_rate": 5e-06, + "loss": 0.4948, + "step": 2710 + }, + { + "epoch": 1.2205519407673322, + "grad_norm": 0.5411400879988145, + "learning_rate": 5e-06, + "loss": 0.4965, + "step": 2720 + }, + { + "epoch": 1.225039264078977, + "grad_norm": 0.5659357562265832, + "learning_rate": 5e-06, + "loss": 0.4772, + "step": 2730 + }, + { + "epoch": 1.2295265873906214, + "grad_norm": 0.5512745847285553, + "learning_rate": 5e-06, + "loss": 0.5273, + "step": 2740 + }, + { + "epoch": 1.234013910702266, + "grad_norm": 0.5704497342942455, + "learning_rate": 5e-06, + "loss": 0.5089, + "step": 2750 + }, + { + "epoch": 1.2385012340139108, + "grad_norm": 0.5398045427001416, + "learning_rate": 5e-06, + "loss": 0.4945, + "step": 2760 + }, + { + "epoch": 1.2429885573255552, + "grad_norm": 0.5334476606303412, + "learning_rate": 5e-06, + "loss": 0.4884, + "step": 2770 + }, + { + "epoch": 1.2474758806372, + "grad_norm": 0.589924660616353, + "learning_rate": 5e-06, + "loss": 0.505, + "step": 2780 + }, + { + "epoch": 1.2519632039488444, + "grad_norm": 0.5585345752197195, + "learning_rate": 5e-06, + "loss": 0.5335, + "step": 2790 + }, + { + "epoch": 1.2564505272604891, + "grad_norm": 0.5654189187890049, + "learning_rate": 5e-06, + "loss": 0.477, + "step": 2800 + }, + { + "epoch": 1.2609378505721338, + "grad_norm": 0.5631419512470206, + "learning_rate": 5e-06, + "loss": 0.4984, + "step": 2810 + }, + { + "epoch": 1.2654251738837783, + "grad_norm": 0.5686873835040517, + "learning_rate": 5e-06, + "loss": 0.5073, + "step": 2820 + }, + { + "epoch": 1.269912497195423, + "grad_norm": 0.5503855071141434, + "learning_rate": 5e-06, + "loss": 0.4989, + "step": 2830 + }, + { + "epoch": 1.2743998205070675, + "grad_norm": 0.5620043676621576, + "learning_rate": 5e-06, + "loss": 0.5013, + "step": 2840 + }, + { + "epoch": 1.2788871438187122, + "grad_norm": 0.5502017343987001, + "learning_rate": 5e-06, + "loss": 0.4843, + "step": 2850 + }, + { + "epoch": 1.2833744671303569, + "grad_norm": 0.5377919239436089, + "learning_rate": 5e-06, + "loss": 0.5102, + "step": 2860 + }, + { + "epoch": 1.2878617904420013, + "grad_norm": 0.5423206907759274, + "learning_rate": 5e-06, + "loss": 0.5308, + "step": 2870 + }, + { + "epoch": 1.292349113753646, + "grad_norm": 0.553618965490239, + "learning_rate": 5e-06, + "loss": 0.5239, + "step": 2880 + }, + { + "epoch": 1.2968364370652905, + "grad_norm": 0.5712510750822322, + "learning_rate": 5e-06, + "loss": 0.5021, + "step": 2890 + }, + { + "epoch": 1.3013237603769352, + "grad_norm": 0.5634666949947841, + "learning_rate": 5e-06, + "loss": 0.4941, + "step": 2900 + }, + { + "epoch": 1.30581108368858, + "grad_norm": 0.568485750592611, + "learning_rate": 5e-06, + "loss": 0.505, + "step": 2910 + }, + { + "epoch": 1.3102984070002244, + "grad_norm": 0.5671935619893487, + "learning_rate": 5e-06, + "loss": 0.4912, + "step": 2920 + }, + { + "epoch": 1.3147857303118688, + "grad_norm": 0.5757679724498568, + "learning_rate": 5e-06, + "loss": 0.4913, + "step": 2930 + }, + { + "epoch": 1.3192730536235135, + "grad_norm": 0.5590352144821122, + "learning_rate": 5e-06, + "loss": 0.486, + "step": 2940 + }, + { + "epoch": 1.3237603769351582, + "grad_norm": 0.5445238317180622, + "learning_rate": 5e-06, + "loss": 0.4908, + "step": 2950 + }, + { + "epoch": 1.3282477002468027, + "grad_norm": 0.5380943498565294, + "learning_rate": 5e-06, + "loss": 0.5293, + "step": 2960 + }, + { + "epoch": 1.3327350235584474, + "grad_norm": 0.5573459369134599, + "learning_rate": 5e-06, + "loss": 0.4739, + "step": 2970 + }, + { + "epoch": 1.337222346870092, + "grad_norm": 0.5563120439249387, + "learning_rate": 5e-06, + "loss": 0.482, + "step": 2980 + }, + { + "epoch": 1.3417096701817366, + "grad_norm": 0.5545396609770007, + "learning_rate": 5e-06, + "loss": 0.4936, + "step": 2990 + }, + { + "epoch": 1.3461969934933813, + "grad_norm": 0.536222681258455, + "learning_rate": 5e-06, + "loss": 0.4977, + "step": 3000 + }, + { + "epoch": 1.3506843168050258, + "grad_norm": 0.5622333924200364, + "learning_rate": 5e-06, + "loss": 0.5232, + "step": 3010 + }, + { + "epoch": 1.3551716401166705, + "grad_norm": 0.5477326991210051, + "learning_rate": 5e-06, + "loss": 0.5085, + "step": 3020 + }, + { + "epoch": 1.359658963428315, + "grad_norm": 0.543317448941311, + "learning_rate": 5e-06, + "loss": 0.4971, + "step": 3030 + }, + { + "epoch": 1.3641462867399596, + "grad_norm": 0.5400423612006745, + "learning_rate": 5e-06, + "loss": 0.5122, + "step": 3040 + }, + { + "epoch": 1.3686336100516043, + "grad_norm": 0.5578167396365121, + "learning_rate": 5e-06, + "loss": 0.5167, + "step": 3050 + }, + { + "epoch": 1.3731209333632488, + "grad_norm": 0.5740701717143266, + "learning_rate": 5e-06, + "loss": 0.509, + "step": 3060 + }, + { + "epoch": 1.3776082566748935, + "grad_norm": 0.5570929052762126, + "learning_rate": 5e-06, + "loss": 0.5103, + "step": 3070 + }, + { + "epoch": 1.382095579986538, + "grad_norm": 0.5433927111213747, + "learning_rate": 5e-06, + "loss": 0.5198, + "step": 3080 + }, + { + "epoch": 1.3865829032981827, + "grad_norm": 0.5710035732297696, + "learning_rate": 5e-06, + "loss": 0.5064, + "step": 3090 + }, + { + "epoch": 1.3910702266098274, + "grad_norm": 0.5932400385935832, + "learning_rate": 5e-06, + "loss": 0.5012, + "step": 3100 + }, + { + "epoch": 1.3955575499214719, + "grad_norm": 0.545506710464315, + "learning_rate": 5e-06, + "loss": 0.4892, + "step": 3110 + }, + { + "epoch": 1.4000448732331163, + "grad_norm": 0.5752471090405673, + "learning_rate": 5e-06, + "loss": 0.505, + "step": 3120 + }, + { + "epoch": 1.404532196544761, + "grad_norm": 0.5628082472998481, + "learning_rate": 5e-06, + "loss": 0.4866, + "step": 3130 + }, + { + "epoch": 1.4090195198564057, + "grad_norm": 0.5755016704798377, + "learning_rate": 5e-06, + "loss": 0.5056, + "step": 3140 + }, + { + "epoch": 1.4135068431680502, + "grad_norm": 0.5280132793104151, + "learning_rate": 5e-06, + "loss": 0.5281, + "step": 3150 + }, + { + "epoch": 1.417994166479695, + "grad_norm": 0.5466619698880913, + "learning_rate": 5e-06, + "loss": 0.5207, + "step": 3160 + }, + { + "epoch": 1.4224814897913394, + "grad_norm": 0.5282843782818277, + "learning_rate": 5e-06, + "loss": 0.5298, + "step": 3170 + }, + { + "epoch": 1.426968813102984, + "grad_norm": 0.5734506299177996, + "learning_rate": 5e-06, + "loss": 0.5124, + "step": 3180 + }, + { + "epoch": 1.4314561364146288, + "grad_norm": 0.5344798626824697, + "learning_rate": 5e-06, + "loss": 0.4963, + "step": 3190 + }, + { + "epoch": 1.4359434597262732, + "grad_norm": 0.5473981763834849, + "learning_rate": 5e-06, + "loss": 0.5054, + "step": 3200 + }, + { + "epoch": 1.440430783037918, + "grad_norm": 0.5424308579398186, + "learning_rate": 5e-06, + "loss": 0.5019, + "step": 3210 + }, + { + "epoch": 1.4449181063495624, + "grad_norm": 0.5719832828803095, + "learning_rate": 5e-06, + "loss": 0.4982, + "step": 3220 + }, + { + "epoch": 1.4494054296612071, + "grad_norm": 0.5572404240421417, + "learning_rate": 5e-06, + "loss": 0.5147, + "step": 3230 + }, + { + "epoch": 1.4538927529728518, + "grad_norm": 0.5458124274523334, + "learning_rate": 5e-06, + "loss": 0.5168, + "step": 3240 + }, + { + "epoch": 1.4583800762844963, + "grad_norm": 0.5193755152140953, + "learning_rate": 5e-06, + "loss": 0.5223, + "step": 3250 + }, + { + "epoch": 1.462867399596141, + "grad_norm": 0.5233432783340276, + "learning_rate": 5e-06, + "loss": 0.5167, + "step": 3260 + }, + { + "epoch": 1.4673547229077855, + "grad_norm": 0.544740366629981, + "learning_rate": 5e-06, + "loss": 0.4906, + "step": 3270 + }, + { + "epoch": 1.4718420462194302, + "grad_norm": 0.5995125947333418, + "learning_rate": 5e-06, + "loss": 0.5063, + "step": 3280 + }, + { + "epoch": 1.4763293695310746, + "grad_norm": 0.5580064274640354, + "learning_rate": 5e-06, + "loss": 0.4932, + "step": 3290 + }, + { + "epoch": 1.4808166928427193, + "grad_norm": 0.5515028035867199, + "learning_rate": 5e-06, + "loss": 0.4976, + "step": 3300 + }, + { + "epoch": 1.4853040161543638, + "grad_norm": 0.5326953694404295, + "learning_rate": 5e-06, + "loss": 0.5001, + "step": 3310 + }, + { + "epoch": 1.4897913394660085, + "grad_norm": 0.5531717436070133, + "learning_rate": 5e-06, + "loss": 0.5157, + "step": 3320 + }, + { + "epoch": 1.4942786627776532, + "grad_norm": 0.5536934590854812, + "learning_rate": 5e-06, + "loss": 0.5011, + "step": 3330 + }, + { + "epoch": 1.4987659860892977, + "grad_norm": 0.537594784304719, + "learning_rate": 5e-06, + "loss": 0.4988, + "step": 3340 + }, + { + "epoch": 1.5032533094009424, + "grad_norm": 0.5325933270053125, + "learning_rate": 5e-06, + "loss": 0.5263, + "step": 3350 + }, + { + "epoch": 1.5077406327125868, + "grad_norm": 0.517841662464493, + "learning_rate": 5e-06, + "loss": 0.4995, + "step": 3360 + }, + { + "epoch": 1.5122279560242315, + "grad_norm": 0.5154921484724686, + "learning_rate": 5e-06, + "loss": 0.4933, + "step": 3370 + }, + { + "epoch": 1.5167152793358762, + "grad_norm": 0.5775973989195, + "learning_rate": 5e-06, + "loss": 0.5068, + "step": 3380 + }, + { + "epoch": 1.5212026026475207, + "grad_norm": 0.5854301357165765, + "learning_rate": 5e-06, + "loss": 0.5028, + "step": 3390 + }, + { + "epoch": 1.5256899259591652, + "grad_norm": 0.5438296714544919, + "learning_rate": 5e-06, + "loss": 0.4992, + "step": 3400 + }, + { + "epoch": 1.53017724927081, + "grad_norm": 0.5581750773098291, + "learning_rate": 5e-06, + "loss": 0.4774, + "step": 3410 + }, + { + "epoch": 1.5346645725824546, + "grad_norm": 0.5832173054693874, + "learning_rate": 5e-06, + "loss": 0.5061, + "step": 3420 + }, + { + "epoch": 1.5391518958940993, + "grad_norm": 0.5753758202144109, + "learning_rate": 5e-06, + "loss": 0.4999, + "step": 3430 + }, + { + "epoch": 1.5436392192057438, + "grad_norm": 0.544533713206346, + "learning_rate": 5e-06, + "loss": 0.5088, + "step": 3440 + }, + { + "epoch": 1.5481265425173882, + "grad_norm": 0.571084602500549, + "learning_rate": 5e-06, + "loss": 0.4818, + "step": 3450 + }, + { + "epoch": 1.552613865829033, + "grad_norm": 0.584923156106211, + "learning_rate": 5e-06, + "loss": 0.4813, + "step": 3460 + }, + { + "epoch": 1.5571011891406776, + "grad_norm": 0.5305219598557945, + "learning_rate": 5e-06, + "loss": 0.5034, + "step": 3470 + }, + { + "epoch": 1.5615885124523223, + "grad_norm": 0.5488575678648898, + "learning_rate": 5e-06, + "loss": 0.4968, + "step": 3480 + }, + { + "epoch": 1.5660758357639668, + "grad_norm": 0.5700887842489093, + "learning_rate": 5e-06, + "loss": 0.4957, + "step": 3490 + }, + { + "epoch": 1.5705631590756113, + "grad_norm": 0.5493679649855058, + "learning_rate": 5e-06, + "loss": 0.4945, + "step": 3500 + }, + { + "epoch": 1.575050482387256, + "grad_norm": 0.5791638763067023, + "learning_rate": 5e-06, + "loss": 0.5118, + "step": 3510 + }, + { + "epoch": 1.5795378056989007, + "grad_norm": 0.5916566338039917, + "learning_rate": 5e-06, + "loss": 0.5194, + "step": 3520 + }, + { + "epoch": 1.5840251290105454, + "grad_norm": 0.5570616792034053, + "learning_rate": 5e-06, + "loss": 0.4857, + "step": 3530 + }, + { + "epoch": 1.5885124523221898, + "grad_norm": 0.5461551153883559, + "learning_rate": 5e-06, + "loss": 0.4713, + "step": 3540 + }, + { + "epoch": 1.5929997756338343, + "grad_norm": 0.5515261498525429, + "learning_rate": 5e-06, + "loss": 0.5297, + "step": 3550 + }, + { + "epoch": 1.597487098945479, + "grad_norm": 0.57188102614297, + "learning_rate": 5e-06, + "loss": 0.4888, + "step": 3560 + }, + { + "epoch": 1.6019744222571237, + "grad_norm": 0.5171680954916367, + "learning_rate": 5e-06, + "loss": 0.4842, + "step": 3570 + }, + { + "epoch": 1.6064617455687682, + "grad_norm": 0.5756688858390624, + "learning_rate": 5e-06, + "loss": 0.4943, + "step": 3580 + }, + { + "epoch": 1.6109490688804127, + "grad_norm": 0.5749499103685126, + "learning_rate": 5e-06, + "loss": 0.5379, + "step": 3590 + }, + { + "epoch": 1.6154363921920574, + "grad_norm": 0.5351176936292328, + "learning_rate": 5e-06, + "loss": 0.4859, + "step": 3600 + }, + { + "epoch": 1.619923715503702, + "grad_norm": 0.5465963706973009, + "learning_rate": 5e-06, + "loss": 0.5253, + "step": 3610 + }, + { + "epoch": 1.6244110388153468, + "grad_norm": 0.5952713410678487, + "learning_rate": 5e-06, + "loss": 0.5248, + "step": 3620 + }, + { + "epoch": 1.6288983621269912, + "grad_norm": 0.5693133264089241, + "learning_rate": 5e-06, + "loss": 0.4947, + "step": 3630 + }, + { + "epoch": 1.6333856854386357, + "grad_norm": 0.532801262620042, + "learning_rate": 5e-06, + "loss": 0.4846, + "step": 3640 + }, + { + "epoch": 1.6378730087502804, + "grad_norm": 0.5731108270619412, + "learning_rate": 5e-06, + "loss": 0.5178, + "step": 3650 + }, + { + "epoch": 1.642360332061925, + "grad_norm": 0.5566162421839872, + "learning_rate": 5e-06, + "loss": 0.5142, + "step": 3660 + }, + { + "epoch": 1.6468476553735698, + "grad_norm": 0.5176692150882419, + "learning_rate": 5e-06, + "loss": 0.5146, + "step": 3670 + }, + { + "epoch": 1.6513349786852143, + "grad_norm": 0.5712166747441446, + "learning_rate": 5e-06, + "loss": 0.4942, + "step": 3680 + }, + { + "epoch": 1.6558223019968588, + "grad_norm": 0.5411076738264401, + "learning_rate": 5e-06, + "loss": 0.5109, + "step": 3690 + }, + { + "epoch": 1.6603096253085035, + "grad_norm": 0.5527323928497764, + "learning_rate": 5e-06, + "loss": 0.5189, + "step": 3700 + }, + { + "epoch": 1.6647969486201482, + "grad_norm": 0.5475126879488802, + "learning_rate": 5e-06, + "loss": 0.498, + "step": 3710 + }, + { + "epoch": 1.6692842719317929, + "grad_norm": 0.5226831637595657, + "learning_rate": 5e-06, + "loss": 0.4834, + "step": 3720 + }, + { + "epoch": 1.6737715952434373, + "grad_norm": 0.5378242696447812, + "learning_rate": 5e-06, + "loss": 0.5418, + "step": 3730 + }, + { + "epoch": 1.6782589185550818, + "grad_norm": 0.5949971573967483, + "learning_rate": 5e-06, + "loss": 0.508, + "step": 3740 + }, + { + "epoch": 1.6827462418667265, + "grad_norm": 0.5358908747440865, + "learning_rate": 5e-06, + "loss": 0.4967, + "step": 3750 + }, + { + "epoch": 1.6872335651783712, + "grad_norm": 0.5474090787609206, + "learning_rate": 5e-06, + "loss": 0.4933, + "step": 3760 + }, + { + "epoch": 1.6917208884900157, + "grad_norm": 0.5914274676963112, + "learning_rate": 5e-06, + "loss": 0.4949, + "step": 3770 + }, + { + "epoch": 1.6962082118016601, + "grad_norm": 0.5537449538419119, + "learning_rate": 5e-06, + "loss": 0.4966, + "step": 3780 + }, + { + "epoch": 1.7006955351133048, + "grad_norm": 0.5448028303916069, + "learning_rate": 5e-06, + "loss": 0.5074, + "step": 3790 + }, + { + "epoch": 1.7051828584249495, + "grad_norm": 0.5708643249016583, + "learning_rate": 5e-06, + "loss": 0.4896, + "step": 3800 + }, + { + "epoch": 1.7096701817365942, + "grad_norm": 0.5745684091394735, + "learning_rate": 5e-06, + "loss": 0.5045, + "step": 3810 + }, + { + "epoch": 1.7141575050482387, + "grad_norm": 0.5512474274982683, + "learning_rate": 5e-06, + "loss": 0.5089, + "step": 3820 + }, + { + "epoch": 1.7186448283598832, + "grad_norm": 0.5430706302627716, + "learning_rate": 5e-06, + "loss": 0.4994, + "step": 3830 + }, + { + "epoch": 1.723132151671528, + "grad_norm": 0.5556308718806792, + "learning_rate": 5e-06, + "loss": 0.5025, + "step": 3840 + }, + { + "epoch": 1.7276194749831726, + "grad_norm": 0.5451097170074302, + "learning_rate": 5e-06, + "loss": 0.5041, + "step": 3850 + }, + { + "epoch": 1.7321067982948173, + "grad_norm": 0.5482562609039291, + "learning_rate": 5e-06, + "loss": 0.505, + "step": 3860 + }, + { + "epoch": 1.7365941216064618, + "grad_norm": 0.5708328715347044, + "learning_rate": 5e-06, + "loss": 0.4998, + "step": 3870 + }, + { + "epoch": 1.7410814449181062, + "grad_norm": 0.5491007607865179, + "learning_rate": 5e-06, + "loss": 0.5203, + "step": 3880 + }, + { + "epoch": 1.745568768229751, + "grad_norm": 0.539262203178338, + "learning_rate": 5e-06, + "loss": 0.4938, + "step": 3890 + }, + { + "epoch": 1.7500560915413956, + "grad_norm": 0.587964940856532, + "learning_rate": 5e-06, + "loss": 0.5138, + "step": 3900 + }, + { + "epoch": 1.75454341485304, + "grad_norm": 0.603989953035275, + "learning_rate": 5e-06, + "loss": 0.5019, + "step": 3910 + }, + { + "epoch": 1.7590307381646848, + "grad_norm": 0.5936506149594802, + "learning_rate": 5e-06, + "loss": 0.4941, + "step": 3920 + }, + { + "epoch": 1.7635180614763293, + "grad_norm": 0.5461819280550173, + "learning_rate": 5e-06, + "loss": 0.5206, + "step": 3930 + }, + { + "epoch": 1.768005384787974, + "grad_norm": 0.5639017847680231, + "learning_rate": 5e-06, + "loss": 0.4974, + "step": 3940 + }, + { + "epoch": 1.7724927080996187, + "grad_norm": 0.5290104593192931, + "learning_rate": 5e-06, + "loss": 0.4939, + "step": 3950 + }, + { + "epoch": 1.7769800314112632, + "grad_norm": 0.5831983935779752, + "learning_rate": 5e-06, + "loss": 0.5019, + "step": 3960 + }, + { + "epoch": 1.7814673547229076, + "grad_norm": 0.5538657179797891, + "learning_rate": 5e-06, + "loss": 0.4852, + "step": 3970 + }, + { + "epoch": 1.7859546780345523, + "grad_norm": 0.568557365614838, + "learning_rate": 5e-06, + "loss": 0.5183, + "step": 3980 + }, + { + "epoch": 1.790442001346197, + "grad_norm": 0.5362764060596701, + "learning_rate": 5e-06, + "loss": 0.51, + "step": 3990 + }, + { + "epoch": 1.7949293246578417, + "grad_norm": 0.5592584139795364, + "learning_rate": 5e-06, + "loss": 0.504, + "step": 4000 + }, + { + "epoch": 1.7994166479694862, + "grad_norm": 0.555910637560083, + "learning_rate": 5e-06, + "loss": 0.494, + "step": 4010 + }, + { + "epoch": 1.8039039712811307, + "grad_norm": 0.551977757056201, + "learning_rate": 5e-06, + "loss": 0.5222, + "step": 4020 + }, + { + "epoch": 1.8083912945927754, + "grad_norm": 0.537652808354882, + "learning_rate": 5e-06, + "loss": 0.5047, + "step": 4030 + }, + { + "epoch": 1.81287861790442, + "grad_norm": 0.5606846471432076, + "learning_rate": 5e-06, + "loss": 0.5148, + "step": 4040 + }, + { + "epoch": 1.8173659412160648, + "grad_norm": 0.5316042317862866, + "learning_rate": 5e-06, + "loss": 0.4958, + "step": 4050 + }, + { + "epoch": 1.8218532645277092, + "grad_norm": 0.6009251472832223, + "learning_rate": 5e-06, + "loss": 0.4887, + "step": 4060 + }, + { + "epoch": 1.8263405878393537, + "grad_norm": 0.5833028652502357, + "learning_rate": 5e-06, + "loss": 0.5026, + "step": 4070 + }, + { + "epoch": 1.8308279111509984, + "grad_norm": 0.5303089821472199, + "learning_rate": 5e-06, + "loss": 0.4802, + "step": 4080 + }, + { + "epoch": 1.835315234462643, + "grad_norm": 0.5356894166936327, + "learning_rate": 5e-06, + "loss": 0.4948, + "step": 4090 + }, + { + "epoch": 1.8398025577742876, + "grad_norm": 0.5399931872531933, + "learning_rate": 5e-06, + "loss": 0.4954, + "step": 4100 + }, + { + "epoch": 1.8442898810859323, + "grad_norm": 0.562838831677771, + "learning_rate": 5e-06, + "loss": 0.5215, + "step": 4110 + }, + { + "epoch": 1.8487772043975768, + "grad_norm": 0.5767666769206414, + "learning_rate": 5e-06, + "loss": 0.4895, + "step": 4120 + }, + { + "epoch": 1.8532645277092215, + "grad_norm": 0.5290702500324674, + "learning_rate": 5e-06, + "loss": 0.5029, + "step": 4130 + }, + { + "epoch": 1.8577518510208662, + "grad_norm": 0.5308632664860179, + "learning_rate": 5e-06, + "loss": 0.4919, + "step": 4140 + }, + { + "epoch": 1.8622391743325106, + "grad_norm": 0.5413420247585403, + "learning_rate": 5e-06, + "loss": 0.5034, + "step": 4150 + }, + { + "epoch": 1.866726497644155, + "grad_norm": 0.5538840065119353, + "learning_rate": 5e-06, + "loss": 0.5002, + "step": 4160 + }, + { + "epoch": 1.8712138209557998, + "grad_norm": 0.5211702522584797, + "learning_rate": 5e-06, + "loss": 0.505, + "step": 4170 + }, + { + "epoch": 1.8757011442674445, + "grad_norm": 0.5446822204678821, + "learning_rate": 5e-06, + "loss": 0.5287, + "step": 4180 + }, + { + "epoch": 1.8801884675790892, + "grad_norm": 0.5561626601823235, + "learning_rate": 5e-06, + "loss": 0.5205, + "step": 4190 + }, + { + "epoch": 1.8846757908907337, + "grad_norm": 0.5537666305289907, + "learning_rate": 5e-06, + "loss": 0.4989, + "step": 4200 + }, + { + "epoch": 1.8891631142023781, + "grad_norm": 0.5685163585083653, + "learning_rate": 5e-06, + "loss": 0.5154, + "step": 4210 + }, + { + "epoch": 1.8936504375140228, + "grad_norm": 0.5451373353451423, + "learning_rate": 5e-06, + "loss": 0.5065, + "step": 4220 + }, + { + "epoch": 1.8981377608256675, + "grad_norm": 0.5518210301636858, + "learning_rate": 5e-06, + "loss": 0.5001, + "step": 4230 + }, + { + "epoch": 1.9026250841373122, + "grad_norm": 0.5470491973339323, + "learning_rate": 5e-06, + "loss": 0.4953, + "step": 4240 + }, + { + "epoch": 1.9071124074489567, + "grad_norm": 0.5402094383394249, + "learning_rate": 5e-06, + "loss": 0.4881, + "step": 4250 + }, + { + "epoch": 1.9115997307606012, + "grad_norm": 0.5356916841246723, + "learning_rate": 5e-06, + "loss": 0.498, + "step": 4260 + }, + { + "epoch": 1.9160870540722459, + "grad_norm": 0.6011677528029307, + "learning_rate": 5e-06, + "loss": 0.5128, + "step": 4270 + }, + { + "epoch": 1.9205743773838906, + "grad_norm": 0.533641599988238, + "learning_rate": 5e-06, + "loss": 0.4942, + "step": 4280 + }, + { + "epoch": 1.925061700695535, + "grad_norm": 0.561171129511058, + "learning_rate": 5e-06, + "loss": 0.5069, + "step": 4290 + }, + { + "epoch": 1.9295490240071798, + "grad_norm": 0.5648499086549563, + "learning_rate": 5e-06, + "loss": 0.5264, + "step": 4300 + }, + { + "epoch": 1.9340363473188242, + "grad_norm": 0.568255235637858, + "learning_rate": 5e-06, + "loss": 0.4944, + "step": 4310 + }, + { + "epoch": 1.938523670630469, + "grad_norm": 0.558570542074393, + "learning_rate": 5e-06, + "loss": 0.5116, + "step": 4320 + }, + { + "epoch": 1.9430109939421136, + "grad_norm": 0.5335131103567927, + "learning_rate": 5e-06, + "loss": 0.5308, + "step": 4330 + }, + { + "epoch": 1.947498317253758, + "grad_norm": 0.528601279188925, + "learning_rate": 5e-06, + "loss": 0.5038, + "step": 4340 + }, + { + "epoch": 1.9519856405654026, + "grad_norm": 0.5651768549322472, + "learning_rate": 5e-06, + "loss": 0.5391, + "step": 4350 + }, + { + "epoch": 1.9564729638770473, + "grad_norm": 0.5209641936278054, + "learning_rate": 5e-06, + "loss": 0.4916, + "step": 4360 + }, + { + "epoch": 1.960960287188692, + "grad_norm": 0.6121127336148168, + "learning_rate": 5e-06, + "loss": 0.4959, + "step": 4370 + }, + { + "epoch": 1.9654476105003367, + "grad_norm": 0.5295573811299278, + "learning_rate": 5e-06, + "loss": 0.4851, + "step": 4380 + }, + { + "epoch": 1.9699349338119811, + "grad_norm": 0.5768584348850149, + "learning_rate": 5e-06, + "loss": 0.5266, + "step": 4390 + }, + { + "epoch": 1.9744222571236256, + "grad_norm": 0.5174975104621315, + "learning_rate": 5e-06, + "loss": 0.4978, + "step": 4400 + }, + { + "epoch": 1.9789095804352703, + "grad_norm": 0.5546606880895456, + "learning_rate": 5e-06, + "loss": 0.4928, + "step": 4410 + }, + { + "epoch": 1.983396903746915, + "grad_norm": 0.5683833011043679, + "learning_rate": 5e-06, + "loss": 0.4989, + "step": 4420 + }, + { + "epoch": 1.9878842270585597, + "grad_norm": 0.537165046986452, + "learning_rate": 5e-06, + "loss": 0.516, + "step": 4430 + }, + { + "epoch": 1.9923715503702042, + "grad_norm": 0.5319744139724734, + "learning_rate": 5e-06, + "loss": 0.5309, + "step": 4440 + }, + { + "epoch": 1.9968588736818487, + "grad_norm": 0.5451938729099154, + "learning_rate": 5e-06, + "loss": 0.5079, + "step": 4450 + }, + { + "epoch": 2.0, + "eval_loss": 0.5559915900230408, + "eval_runtime": 559.3369, + "eval_samples_per_second": 26.835, + "eval_steps_per_second": 0.42, + "step": 4457 + }, + { + "epoch": 2.0013461969934934, + "grad_norm": 0.5652296466620075, + "learning_rate": 5e-06, + "loss": 0.489, + "step": 4460 + }, + { + "epoch": 2.005833520305138, + "grad_norm": 0.5447379459508764, + "learning_rate": 5e-06, + "loss": 0.4355, + "step": 4470 + }, + { + "epoch": 2.0103208436167828, + "grad_norm": 0.5178404377199393, + "learning_rate": 5e-06, + "loss": 0.4286, + "step": 4480 + }, + { + "epoch": 2.014808166928427, + "grad_norm": 0.5422732055965347, + "learning_rate": 5e-06, + "loss": 0.4383, + "step": 4490 + }, + { + "epoch": 2.0192954902400717, + "grad_norm": 0.535310702889713, + "learning_rate": 5e-06, + "loss": 0.4392, + "step": 4500 + }, + { + "epoch": 2.0237828135517164, + "grad_norm": 0.5465033381736284, + "learning_rate": 5e-06, + "loss": 0.4322, + "step": 4510 + }, + { + "epoch": 2.028270136863361, + "grad_norm": 0.5407880814912572, + "learning_rate": 5e-06, + "loss": 0.422, + "step": 4520 + }, + { + "epoch": 2.032757460175006, + "grad_norm": 0.5475175525712156, + "learning_rate": 5e-06, + "loss": 0.4228, + "step": 4530 + }, + { + "epoch": 2.03724478348665, + "grad_norm": 0.5305519155722267, + "learning_rate": 5e-06, + "loss": 0.4414, + "step": 4540 + }, + { + "epoch": 2.0417321067982948, + "grad_norm": 0.5525760243070599, + "learning_rate": 5e-06, + "loss": 0.4319, + "step": 4550 + }, + { + "epoch": 2.0462194301099395, + "grad_norm": 0.5380138271735849, + "learning_rate": 5e-06, + "loss": 0.4184, + "step": 4560 + }, + { + "epoch": 2.050706753421584, + "grad_norm": 0.5393541372377034, + "learning_rate": 5e-06, + "loss": 0.4267, + "step": 4570 + }, + { + "epoch": 2.055194076733229, + "grad_norm": 0.5280423864839874, + "learning_rate": 5e-06, + "loss": 0.4492, + "step": 4580 + }, + { + "epoch": 2.059681400044873, + "grad_norm": 0.5598943021301682, + "learning_rate": 5e-06, + "loss": 0.4445, + "step": 4590 + }, + { + "epoch": 2.064168723356518, + "grad_norm": 0.5110154136642925, + "learning_rate": 5e-06, + "loss": 0.4279, + "step": 4600 + }, + { + "epoch": 2.0686560466681625, + "grad_norm": 0.521113203676518, + "learning_rate": 5e-06, + "loss": 0.476, + "step": 4610 + }, + { + "epoch": 2.073143369979807, + "grad_norm": 0.509177043617814, + "learning_rate": 5e-06, + "loss": 0.4511, + "step": 4620 + }, + { + "epoch": 2.0776306932914514, + "grad_norm": 0.5204617332251407, + "learning_rate": 5e-06, + "loss": 0.4385, + "step": 4630 + }, + { + "epoch": 2.082118016603096, + "grad_norm": 0.5600686745711032, + "learning_rate": 5e-06, + "loss": 0.4409, + "step": 4640 + }, + { + "epoch": 2.086605339914741, + "grad_norm": 0.551649701345727, + "learning_rate": 5e-06, + "loss": 0.4235, + "step": 4650 + }, + { + "epoch": 2.0910926632263855, + "grad_norm": 0.555346212302441, + "learning_rate": 5e-06, + "loss": 0.4367, + "step": 4660 + }, + { + "epoch": 2.0955799865380302, + "grad_norm": 0.5333054935894155, + "learning_rate": 5e-06, + "loss": 0.4458, + "step": 4670 + }, + { + "epoch": 2.1000673098496745, + "grad_norm": 0.5663799977134729, + "learning_rate": 5e-06, + "loss": 0.4415, + "step": 4680 + }, + { + "epoch": 2.104554633161319, + "grad_norm": 0.5768162610420671, + "learning_rate": 5e-06, + "loss": 0.4646, + "step": 4690 + }, + { + "epoch": 2.109041956472964, + "grad_norm": 0.5204844232448562, + "learning_rate": 5e-06, + "loss": 0.4725, + "step": 4700 + }, + { + "epoch": 2.1135292797846086, + "grad_norm": 0.5462747740338038, + "learning_rate": 5e-06, + "loss": 0.4342, + "step": 4710 + }, + { + "epoch": 2.1180166030962533, + "grad_norm": 0.5308200939238422, + "learning_rate": 5e-06, + "loss": 0.4226, + "step": 4720 + }, + { + "epoch": 2.1225039264078975, + "grad_norm": 0.5689657779220455, + "learning_rate": 5e-06, + "loss": 0.4387, + "step": 4730 + }, + { + "epoch": 2.1269912497195422, + "grad_norm": 0.5261178859362788, + "learning_rate": 5e-06, + "loss": 0.4343, + "step": 4740 + }, + { + "epoch": 2.131478573031187, + "grad_norm": 0.5802820337415188, + "learning_rate": 5e-06, + "loss": 0.452, + "step": 4750 + }, + { + "epoch": 2.1359658963428316, + "grad_norm": 0.5660982173345542, + "learning_rate": 5e-06, + "loss": 0.4405, + "step": 4760 + }, + { + "epoch": 2.140453219654476, + "grad_norm": 0.5611165514102701, + "learning_rate": 5e-06, + "loss": 0.4426, + "step": 4770 + }, + { + "epoch": 2.1449405429661206, + "grad_norm": 0.5362977002914265, + "learning_rate": 5e-06, + "loss": 0.4277, + "step": 4780 + }, + { + "epoch": 2.1494278662777653, + "grad_norm": 0.5775247895144668, + "learning_rate": 5e-06, + "loss": 0.417, + "step": 4790 + }, + { + "epoch": 2.15391518958941, + "grad_norm": 0.5049281569355238, + "learning_rate": 5e-06, + "loss": 0.4432, + "step": 4800 + }, + { + "epoch": 2.1584025129010547, + "grad_norm": 0.5101798893420769, + "learning_rate": 5e-06, + "loss": 0.4211, + "step": 4810 + }, + { + "epoch": 2.162889836212699, + "grad_norm": 0.5297993400461247, + "learning_rate": 5e-06, + "loss": 0.4359, + "step": 4820 + }, + { + "epoch": 2.1673771595243436, + "grad_norm": 0.543138800578885, + "learning_rate": 5e-06, + "loss": 0.438, + "step": 4830 + }, + { + "epoch": 2.1718644828359883, + "grad_norm": 0.5405162833857642, + "learning_rate": 5e-06, + "loss": 0.4372, + "step": 4840 + }, + { + "epoch": 2.176351806147633, + "grad_norm": 0.5772194473884518, + "learning_rate": 5e-06, + "loss": 0.4247, + "step": 4850 + }, + { + "epoch": 2.1808391294592777, + "grad_norm": 0.5366732857273809, + "learning_rate": 5e-06, + "loss": 0.4439, + "step": 4860 + }, + { + "epoch": 2.185326452770922, + "grad_norm": 0.5728184560332118, + "learning_rate": 5e-06, + "loss": 0.4537, + "step": 4870 + }, + { + "epoch": 2.1898137760825667, + "grad_norm": 0.5397099116720598, + "learning_rate": 5e-06, + "loss": 0.4333, + "step": 4880 + }, + { + "epoch": 2.1943010993942114, + "grad_norm": 0.5303476384455712, + "learning_rate": 5e-06, + "loss": 0.457, + "step": 4890 + }, + { + "epoch": 2.198788422705856, + "grad_norm": 0.5325455890564232, + "learning_rate": 5e-06, + "loss": 0.4537, + "step": 4900 + }, + { + "epoch": 2.2032757460175008, + "grad_norm": 0.530437891891213, + "learning_rate": 5e-06, + "loss": 0.4417, + "step": 4910 + }, + { + "epoch": 2.207763069329145, + "grad_norm": 0.5237148221222313, + "learning_rate": 5e-06, + "loss": 0.4518, + "step": 4920 + }, + { + "epoch": 2.2122503926407897, + "grad_norm": 0.7599811908495089, + "learning_rate": 5e-06, + "loss": 0.4292, + "step": 4930 + }, + { + "epoch": 2.2167377159524344, + "grad_norm": 0.5679168932907183, + "learning_rate": 5e-06, + "loss": 0.4337, + "step": 4940 + }, + { + "epoch": 2.221225039264079, + "grad_norm": 0.5598357464655034, + "learning_rate": 5e-06, + "loss": 0.4453, + "step": 4950 + }, + { + "epoch": 2.225712362575724, + "grad_norm": 0.5974896598464358, + "learning_rate": 5e-06, + "loss": 0.46, + "step": 4960 + }, + { + "epoch": 2.230199685887368, + "grad_norm": 0.5483222823612722, + "learning_rate": 5e-06, + "loss": 0.4452, + "step": 4970 + }, + { + "epoch": 2.2346870091990128, + "grad_norm": 0.5624401258029339, + "learning_rate": 5e-06, + "loss": 0.4324, + "step": 4980 + }, + { + "epoch": 2.2391743325106575, + "grad_norm": 0.5454688396112486, + "learning_rate": 5e-06, + "loss": 0.4322, + "step": 4990 + }, + { + "epoch": 2.243661655822302, + "grad_norm": 0.5630702076751016, + "learning_rate": 5e-06, + "loss": 0.4229, + "step": 5000 + }, + { + "epoch": 2.2481489791339464, + "grad_norm": 0.5401237147561903, + "learning_rate": 5e-06, + "loss": 0.4177, + "step": 5010 + }, + { + "epoch": 2.252636302445591, + "grad_norm": 0.5424589473983259, + "learning_rate": 5e-06, + "loss": 0.4303, + "step": 5020 + }, + { + "epoch": 2.257123625757236, + "grad_norm": 0.5577033752080041, + "learning_rate": 5e-06, + "loss": 0.4272, + "step": 5030 + }, + { + "epoch": 2.2616109490688805, + "grad_norm": 0.5085433579295487, + "learning_rate": 5e-06, + "loss": 0.456, + "step": 5040 + }, + { + "epoch": 2.266098272380525, + "grad_norm": 0.5262218825649722, + "learning_rate": 5e-06, + "loss": 0.4398, + "step": 5050 + }, + { + "epoch": 2.2705855956921694, + "grad_norm": 0.5644024837435924, + "learning_rate": 5e-06, + "loss": 0.4144, + "step": 5060 + }, + { + "epoch": 2.275072919003814, + "grad_norm": 0.5830728870184229, + "learning_rate": 5e-06, + "loss": 0.4433, + "step": 5070 + }, + { + "epoch": 2.279560242315459, + "grad_norm": 0.5493777480947901, + "learning_rate": 5e-06, + "loss": 0.4606, + "step": 5080 + }, + { + "epoch": 2.2840475656271035, + "grad_norm": 0.5488762074369681, + "learning_rate": 5e-06, + "loss": 0.4237, + "step": 5090 + }, + { + "epoch": 2.288534888938748, + "grad_norm": 0.5265349880885405, + "learning_rate": 5e-06, + "loss": 0.426, + "step": 5100 + }, + { + "epoch": 2.2930222122503925, + "grad_norm": 0.5478130062869077, + "learning_rate": 5e-06, + "loss": 0.4451, + "step": 5110 + }, + { + "epoch": 2.297509535562037, + "grad_norm": 0.5167579957148292, + "learning_rate": 5e-06, + "loss": 0.4161, + "step": 5120 + }, + { + "epoch": 2.301996858873682, + "grad_norm": 0.537587588073114, + "learning_rate": 5e-06, + "loss": 0.4269, + "step": 5130 + }, + { + "epoch": 2.3064841821853266, + "grad_norm": 0.5351966570168155, + "learning_rate": 5e-06, + "loss": 0.4606, + "step": 5140 + }, + { + "epoch": 2.310971505496971, + "grad_norm": 0.5542030553459122, + "learning_rate": 5e-06, + "loss": 0.4325, + "step": 5150 + }, + { + "epoch": 2.3154588288086155, + "grad_norm": 0.5657224761819103, + "learning_rate": 5e-06, + "loss": 0.436, + "step": 5160 + }, + { + "epoch": 2.3199461521202602, + "grad_norm": 0.5189966523850335, + "learning_rate": 5e-06, + "loss": 0.4271, + "step": 5170 + }, + { + "epoch": 2.324433475431905, + "grad_norm": 0.5490822174982533, + "learning_rate": 5e-06, + "loss": 0.4495, + "step": 5180 + }, + { + "epoch": 2.3289207987435496, + "grad_norm": 0.5495336668696191, + "learning_rate": 5e-06, + "loss": 0.4184, + "step": 5190 + }, + { + "epoch": 2.333408122055194, + "grad_norm": 0.5404149701496175, + "learning_rate": 5e-06, + "loss": 0.4536, + "step": 5200 + }, + { + "epoch": 2.3378954453668386, + "grad_norm": 0.5495815706921072, + "learning_rate": 5e-06, + "loss": 0.4247, + "step": 5210 + }, + { + "epoch": 2.3423827686784833, + "grad_norm": 0.5223528149857176, + "learning_rate": 5e-06, + "loss": 0.446, + "step": 5220 + }, + { + "epoch": 2.346870091990128, + "grad_norm": 0.5320050485503626, + "learning_rate": 5e-06, + "loss": 0.4332, + "step": 5230 + }, + { + "epoch": 2.3513574153017727, + "grad_norm": 0.5299871177712144, + "learning_rate": 5e-06, + "loss": 0.4639, + "step": 5240 + }, + { + "epoch": 2.355844738613417, + "grad_norm": 0.5205906167014355, + "learning_rate": 5e-06, + "loss": 0.4363, + "step": 5250 + }, + { + "epoch": 2.3603320619250616, + "grad_norm": 0.5176082572897545, + "learning_rate": 5e-06, + "loss": 0.4216, + "step": 5260 + }, + { + "epoch": 2.3648193852367063, + "grad_norm": 0.5342565079745604, + "learning_rate": 5e-06, + "loss": 0.4338, + "step": 5270 + }, + { + "epoch": 2.369306708548351, + "grad_norm": 0.5803420836992969, + "learning_rate": 5e-06, + "loss": 0.4239, + "step": 5280 + }, + { + "epoch": 2.3737940318599957, + "grad_norm": 0.5287302044926194, + "learning_rate": 5e-06, + "loss": 0.4475, + "step": 5290 + }, + { + "epoch": 2.37828135517164, + "grad_norm": 0.5645792638215165, + "learning_rate": 5e-06, + "loss": 0.4392, + "step": 5300 + }, + { + "epoch": 2.3827686784832847, + "grad_norm": 0.5282020656735624, + "learning_rate": 5e-06, + "loss": 0.4245, + "step": 5310 + }, + { + "epoch": 2.3872560017949294, + "grad_norm": 0.5571286168651558, + "learning_rate": 5e-06, + "loss": 0.4358, + "step": 5320 + }, + { + "epoch": 2.391743325106574, + "grad_norm": 0.5551698031627329, + "learning_rate": 5e-06, + "loss": 0.4369, + "step": 5330 + }, + { + "epoch": 2.3962306484182188, + "grad_norm": 0.5387097738562745, + "learning_rate": 5e-06, + "loss": 0.4524, + "step": 5340 + }, + { + "epoch": 2.400717971729863, + "grad_norm": 0.546173575982491, + "learning_rate": 5e-06, + "loss": 0.4625, + "step": 5350 + }, + { + "epoch": 2.4052052950415077, + "grad_norm": 0.5495376681388755, + "learning_rate": 5e-06, + "loss": 0.4434, + "step": 5360 + }, + { + "epoch": 2.4096926183531524, + "grad_norm": 0.5377972436367183, + "learning_rate": 5e-06, + "loss": 0.4217, + "step": 5370 + }, + { + "epoch": 2.414179941664797, + "grad_norm": 0.5350882677408955, + "learning_rate": 5e-06, + "loss": 0.4487, + "step": 5380 + }, + { + "epoch": 2.418667264976442, + "grad_norm": 0.5517707610352112, + "learning_rate": 5e-06, + "loss": 0.4352, + "step": 5390 + }, + { + "epoch": 2.423154588288086, + "grad_norm": 0.567154096040849, + "learning_rate": 5e-06, + "loss": 0.4288, + "step": 5400 + }, + { + "epoch": 2.4276419115997308, + "grad_norm": 0.5373918223412871, + "learning_rate": 5e-06, + "loss": 0.4741, + "step": 5410 + }, + { + "epoch": 2.4321292349113754, + "grad_norm": 0.5327337280014666, + "learning_rate": 5e-06, + "loss": 0.4692, + "step": 5420 + }, + { + "epoch": 2.43661655822302, + "grad_norm": 0.5629600789156937, + "learning_rate": 5e-06, + "loss": 0.4508, + "step": 5430 + }, + { + "epoch": 2.4411038815346644, + "grad_norm": 0.5536985413385566, + "learning_rate": 5e-06, + "loss": 0.4275, + "step": 5440 + }, + { + "epoch": 2.445591204846309, + "grad_norm": 0.5312387011564881, + "learning_rate": 5e-06, + "loss": 0.448, + "step": 5450 + }, + { + "epoch": 2.450078528157954, + "grad_norm": 0.5538065322301513, + "learning_rate": 5e-06, + "loss": 0.4346, + "step": 5460 + }, + { + "epoch": 2.4545658514695985, + "grad_norm": 0.541885849026688, + "learning_rate": 5e-06, + "loss": 0.4399, + "step": 5470 + }, + { + "epoch": 2.4590531747812427, + "grad_norm": 0.5284552961380801, + "learning_rate": 5e-06, + "loss": 0.4181, + "step": 5480 + }, + { + "epoch": 2.4635404980928874, + "grad_norm": 0.5805304303114005, + "learning_rate": 5e-06, + "loss": 0.4585, + "step": 5490 + }, + { + "epoch": 2.468027821404532, + "grad_norm": 0.5451696084898805, + "learning_rate": 5e-06, + "loss": 0.457, + "step": 5500 + }, + { + "epoch": 2.472515144716177, + "grad_norm": 0.5556157590446383, + "learning_rate": 5e-06, + "loss": 0.4385, + "step": 5510 + }, + { + "epoch": 2.4770024680278215, + "grad_norm": 0.5158180051239353, + "learning_rate": 5e-06, + "loss": 0.4827, + "step": 5520 + }, + { + "epoch": 2.481489791339466, + "grad_norm": 0.5383037166066315, + "learning_rate": 5e-06, + "loss": 0.4524, + "step": 5530 + }, + { + "epoch": 2.4859771146511105, + "grad_norm": 0.5459360505156834, + "learning_rate": 5e-06, + "loss": 0.4366, + "step": 5540 + }, + { + "epoch": 2.490464437962755, + "grad_norm": 0.56460798618322, + "learning_rate": 5e-06, + "loss": 0.4487, + "step": 5550 + }, + { + "epoch": 2.4949517612744, + "grad_norm": 0.5242645705325473, + "learning_rate": 5e-06, + "loss": 0.4318, + "step": 5560 + }, + { + "epoch": 2.4994390845860446, + "grad_norm": 0.547149907690897, + "learning_rate": 5e-06, + "loss": 0.4362, + "step": 5570 + }, + { + "epoch": 2.503926407897689, + "grad_norm": 0.5402748092495164, + "learning_rate": 5e-06, + "loss": 0.4623, + "step": 5580 + }, + { + "epoch": 2.5084137312093335, + "grad_norm": 0.5222621859452697, + "learning_rate": 5e-06, + "loss": 0.4223, + "step": 5590 + }, + { + "epoch": 2.5129010545209782, + "grad_norm": 0.5310521022656224, + "learning_rate": 5e-06, + "loss": 0.4371, + "step": 5600 + }, + { + "epoch": 2.517388377832623, + "grad_norm": 0.5335126989409179, + "learning_rate": 5e-06, + "loss": 0.4398, + "step": 5610 + }, + { + "epoch": 2.5218757011442676, + "grad_norm": 0.5359705116070118, + "learning_rate": 5e-06, + "loss": 0.4397, + "step": 5620 + }, + { + "epoch": 2.526363024455912, + "grad_norm": 0.5489052783275447, + "learning_rate": 5e-06, + "loss": 0.4542, + "step": 5630 + }, + { + "epoch": 2.5308503477675566, + "grad_norm": 0.5470901455508153, + "learning_rate": 5e-06, + "loss": 0.4277, + "step": 5640 + }, + { + "epoch": 2.5353376710792013, + "grad_norm": 0.5346733284005247, + "learning_rate": 5e-06, + "loss": 0.4438, + "step": 5650 + }, + { + "epoch": 2.539824994390846, + "grad_norm": 0.5164803047551324, + "learning_rate": 5e-06, + "loss": 0.4477, + "step": 5660 + }, + { + "epoch": 2.5443123177024907, + "grad_norm": 0.5566837513995293, + "learning_rate": 5e-06, + "loss": 0.4513, + "step": 5670 + }, + { + "epoch": 2.548799641014135, + "grad_norm": 0.5699497948415865, + "learning_rate": 5e-06, + "loss": 0.4162, + "step": 5680 + }, + { + "epoch": 2.5532869643257796, + "grad_norm": 0.52545278326248, + "learning_rate": 5e-06, + "loss": 0.4422, + "step": 5690 + }, + { + "epoch": 2.5577742876374243, + "grad_norm": 0.5158599480336954, + "learning_rate": 5e-06, + "loss": 0.4508, + "step": 5700 + }, + { + "epoch": 2.562261610949069, + "grad_norm": 0.5517542572393412, + "learning_rate": 5e-06, + "loss": 0.4393, + "step": 5710 + }, + { + "epoch": 2.5667489342607137, + "grad_norm": 0.5405823805282446, + "learning_rate": 5e-06, + "loss": 0.4336, + "step": 5720 + }, + { + "epoch": 2.571236257572358, + "grad_norm": 0.5173834422219281, + "learning_rate": 5e-06, + "loss": 0.4273, + "step": 5730 + }, + { + "epoch": 2.5757235808840027, + "grad_norm": 0.5400412377561089, + "learning_rate": 5e-06, + "loss": 0.4468, + "step": 5740 + }, + { + "epoch": 2.5802109041956474, + "grad_norm": 0.5337516297281755, + "learning_rate": 5e-06, + "loss": 0.4474, + "step": 5750 + }, + { + "epoch": 2.584698227507292, + "grad_norm": 0.5527299364440325, + "learning_rate": 5e-06, + "loss": 0.4345, + "step": 5760 + }, + { + "epoch": 2.5891855508189368, + "grad_norm": 0.5315767138582382, + "learning_rate": 5e-06, + "loss": 0.4311, + "step": 5770 + }, + { + "epoch": 2.593672874130581, + "grad_norm": 0.5515892148242644, + "learning_rate": 5e-06, + "loss": 0.4534, + "step": 5780 + }, + { + "epoch": 2.5981601974422257, + "grad_norm": 0.5710350598486404, + "learning_rate": 5e-06, + "loss": 0.451, + "step": 5790 + }, + { + "epoch": 2.6026475207538704, + "grad_norm": 0.5592453853735161, + "learning_rate": 5e-06, + "loss": 0.4274, + "step": 5800 + }, + { + "epoch": 2.6071348440655147, + "grad_norm": 0.5791874292264974, + "learning_rate": 5e-06, + "loss": 0.4361, + "step": 5810 + }, + { + "epoch": 2.61162216737716, + "grad_norm": 0.5459606205708067, + "learning_rate": 5e-06, + "loss": 0.4344, + "step": 5820 + }, + { + "epoch": 2.616109490688804, + "grad_norm": 0.5263598745373247, + "learning_rate": 5e-06, + "loss": 0.443, + "step": 5830 + }, + { + "epoch": 2.6205968140004487, + "grad_norm": 0.5318408035767697, + "learning_rate": 5e-06, + "loss": 0.455, + "step": 5840 + }, + { + "epoch": 2.6250841373120934, + "grad_norm": 0.5621927236582933, + "learning_rate": 5e-06, + "loss": 0.4338, + "step": 5850 + }, + { + "epoch": 2.6295714606237377, + "grad_norm": 0.5443265572382032, + "learning_rate": 5e-06, + "loss": 0.458, + "step": 5860 + }, + { + "epoch": 2.6340587839353824, + "grad_norm": 0.5291943252034395, + "learning_rate": 5e-06, + "loss": 0.4524, + "step": 5870 + }, + { + "epoch": 2.638546107247027, + "grad_norm": 0.5344516122229699, + "learning_rate": 5e-06, + "loss": 0.4399, + "step": 5880 + }, + { + "epoch": 2.643033430558672, + "grad_norm": 0.5148344986062239, + "learning_rate": 5e-06, + "loss": 0.4385, + "step": 5890 + }, + { + "epoch": 2.6475207538703165, + "grad_norm": 0.517635318320743, + "learning_rate": 5e-06, + "loss": 0.4601, + "step": 5900 + }, + { + "epoch": 2.6520080771819607, + "grad_norm": 0.5517916805298932, + "learning_rate": 5e-06, + "loss": 0.4323, + "step": 5910 + }, + { + "epoch": 2.6564954004936054, + "grad_norm": 0.5611554225539297, + "learning_rate": 5e-06, + "loss": 0.4479, + "step": 5920 + }, + { + "epoch": 2.66098272380525, + "grad_norm": 0.5312102185907968, + "learning_rate": 5e-06, + "loss": 0.4518, + "step": 5930 + }, + { + "epoch": 2.665470047116895, + "grad_norm": 0.5492020012649198, + "learning_rate": 5e-06, + "loss": 0.4424, + "step": 5940 + }, + { + "epoch": 2.6699573704285395, + "grad_norm": 0.5253538068318323, + "learning_rate": 5e-06, + "loss": 0.4481, + "step": 5950 + }, + { + "epoch": 2.674444693740184, + "grad_norm": 0.5433459391246607, + "learning_rate": 5e-06, + "loss": 0.4438, + "step": 5960 + }, + { + "epoch": 2.6789320170518285, + "grad_norm": 0.5250296745067685, + "learning_rate": 5e-06, + "loss": 0.4417, + "step": 5970 + }, + { + "epoch": 2.683419340363473, + "grad_norm": 0.57845411310223, + "learning_rate": 5e-06, + "loss": 0.462, + "step": 5980 + }, + { + "epoch": 2.687906663675118, + "grad_norm": 0.5316069733603933, + "learning_rate": 5e-06, + "loss": 0.4385, + "step": 5990 + }, + { + "epoch": 2.6923939869867626, + "grad_norm": 0.5309938089529066, + "learning_rate": 5e-06, + "loss": 0.4419, + "step": 6000 + }, + { + "epoch": 2.696881310298407, + "grad_norm": 0.5562625161020116, + "learning_rate": 5e-06, + "loss": 0.435, + "step": 6010 + }, + { + "epoch": 2.7013686336100515, + "grad_norm": 0.5599859836426428, + "learning_rate": 5e-06, + "loss": 0.4324, + "step": 6020 + }, + { + "epoch": 2.7058559569216962, + "grad_norm": 0.5688105639070913, + "learning_rate": 5e-06, + "loss": 0.4344, + "step": 6030 + }, + { + "epoch": 2.710343280233341, + "grad_norm": 0.5626537832912196, + "learning_rate": 5e-06, + "loss": 0.4373, + "step": 6040 + }, + { + "epoch": 2.7148306035449856, + "grad_norm": 0.55324964941932, + "learning_rate": 5e-06, + "loss": 0.4317, + "step": 6050 + }, + { + "epoch": 2.71931792685663, + "grad_norm": 0.5401719719418708, + "learning_rate": 5e-06, + "loss": 0.4494, + "step": 6060 + }, + { + "epoch": 2.7238052501682746, + "grad_norm": 0.5150225135697268, + "learning_rate": 5e-06, + "loss": 0.4539, + "step": 6070 + }, + { + "epoch": 2.7282925734799193, + "grad_norm": 0.5740983627117513, + "learning_rate": 5e-06, + "loss": 0.4391, + "step": 6080 + }, + { + "epoch": 2.732779896791564, + "grad_norm": 0.5398182644675611, + "learning_rate": 5e-06, + "loss": 0.449, + "step": 6090 + }, + { + "epoch": 2.7372672201032087, + "grad_norm": 0.5443362706259044, + "learning_rate": 5e-06, + "loss": 0.4301, + "step": 6100 + }, + { + "epoch": 2.741754543414853, + "grad_norm": 0.5455257679601512, + "learning_rate": 5e-06, + "loss": 0.4226, + "step": 6110 + }, + { + "epoch": 2.7462418667264976, + "grad_norm": 0.5260931529295294, + "learning_rate": 5e-06, + "loss": 0.4512, + "step": 6120 + }, + { + "epoch": 2.7507291900381423, + "grad_norm": 0.5472643003685588, + "learning_rate": 5e-06, + "loss": 0.4434, + "step": 6130 + }, + { + "epoch": 2.755216513349787, + "grad_norm": 0.5579861053588995, + "learning_rate": 5e-06, + "loss": 0.4405, + "step": 6140 + }, + { + "epoch": 2.7597038366614317, + "grad_norm": 0.545878751971252, + "learning_rate": 5e-06, + "loss": 0.4366, + "step": 6150 + }, + { + "epoch": 2.764191159973076, + "grad_norm": 0.532094976762934, + "learning_rate": 5e-06, + "loss": 0.4414, + "step": 6160 + }, + { + "epoch": 2.7686784832847207, + "grad_norm": 0.5836755224967016, + "learning_rate": 5e-06, + "loss": 0.4534, + "step": 6170 + }, + { + "epoch": 2.7731658065963654, + "grad_norm": 0.5342141820947959, + "learning_rate": 5e-06, + "loss": 0.4488, + "step": 6180 + }, + { + "epoch": 2.7776531299080096, + "grad_norm": 0.565521800045049, + "learning_rate": 5e-06, + "loss": 0.4331, + "step": 6190 + }, + { + "epoch": 2.7821404532196548, + "grad_norm": 0.5230804833062074, + "learning_rate": 5e-06, + "loss": 0.442, + "step": 6200 + }, + { + "epoch": 2.786627776531299, + "grad_norm": 0.5470772975018182, + "learning_rate": 5e-06, + "loss": 0.4439, + "step": 6210 + }, + { + "epoch": 2.7911150998429437, + "grad_norm": 0.5450425972085206, + "learning_rate": 5e-06, + "loss": 0.4471, + "step": 6220 + }, + { + "epoch": 2.7956024231545884, + "grad_norm": 0.5083879580994983, + "learning_rate": 5e-06, + "loss": 0.45, + "step": 6230 + }, + { + "epoch": 2.8000897464662327, + "grad_norm": 0.538016313129477, + "learning_rate": 5e-06, + "loss": 0.4369, + "step": 6240 + }, + { + "epoch": 2.8045770697778774, + "grad_norm": 0.5582050739389205, + "learning_rate": 5e-06, + "loss": 0.4763, + "step": 6250 + }, + { + "epoch": 2.809064393089522, + "grad_norm": 0.5349488919272378, + "learning_rate": 5e-06, + "loss": 0.4363, + "step": 6260 + }, + { + "epoch": 2.8135517164011667, + "grad_norm": 0.5264389993349703, + "learning_rate": 5e-06, + "loss": 0.438, + "step": 6270 + }, + { + "epoch": 2.8180390397128114, + "grad_norm": 0.5498499847639682, + "learning_rate": 5e-06, + "loss": 0.4295, + "step": 6280 + }, + { + "epoch": 2.8225263630244557, + "grad_norm": 0.5449602025844419, + "learning_rate": 5e-06, + "loss": 0.448, + "step": 6290 + }, + { + "epoch": 2.8270136863361004, + "grad_norm": 0.5396372393247543, + "learning_rate": 5e-06, + "loss": 0.4601, + "step": 6300 + }, + { + "epoch": 2.831501009647745, + "grad_norm": 0.5285660625062669, + "learning_rate": 5e-06, + "loss": 0.4256, + "step": 6310 + }, + { + "epoch": 2.83598833295939, + "grad_norm": 0.5338101430481593, + "learning_rate": 5e-06, + "loss": 0.4461, + "step": 6320 + }, + { + "epoch": 2.8404756562710345, + "grad_norm": 0.5464049325628102, + "learning_rate": 5e-06, + "loss": 0.4312, + "step": 6330 + }, + { + "epoch": 2.8449629795826787, + "grad_norm": 0.5462792499593093, + "learning_rate": 5e-06, + "loss": 0.4418, + "step": 6340 + }, + { + "epoch": 2.8494503028943234, + "grad_norm": 0.5516791871027837, + "learning_rate": 5e-06, + "loss": 0.4449, + "step": 6350 + }, + { + "epoch": 2.853937626205968, + "grad_norm": 0.5576513237004156, + "learning_rate": 5e-06, + "loss": 0.4453, + "step": 6360 + }, + { + "epoch": 2.858424949517613, + "grad_norm": 0.5368302048584942, + "learning_rate": 5e-06, + "loss": 0.4418, + "step": 6370 + }, + { + "epoch": 2.8629122728292575, + "grad_norm": 0.5166792247647458, + "learning_rate": 5e-06, + "loss": 0.4486, + "step": 6380 + }, + { + "epoch": 2.867399596140902, + "grad_norm": 0.5283542555206898, + "learning_rate": 5e-06, + "loss": 0.4305, + "step": 6390 + }, + { + "epoch": 2.8718869194525465, + "grad_norm": 0.5745921221883099, + "learning_rate": 5e-06, + "loss": 0.4421, + "step": 6400 + }, + { + "epoch": 2.876374242764191, + "grad_norm": 0.5610874860309188, + "learning_rate": 5e-06, + "loss": 0.4482, + "step": 6410 + }, + { + "epoch": 2.880861566075836, + "grad_norm": 0.562508114298865, + "learning_rate": 5e-06, + "loss": 0.4357, + "step": 6420 + }, + { + "epoch": 2.8853488893874806, + "grad_norm": 0.5404474497571172, + "learning_rate": 5e-06, + "loss": 0.4901, + "step": 6430 + }, + { + "epoch": 2.889836212699125, + "grad_norm": 0.5731369450030108, + "learning_rate": 5e-06, + "loss": 0.4523, + "step": 6440 + }, + { + "epoch": 2.8943235360107695, + "grad_norm": 0.5283239685292113, + "learning_rate": 5e-06, + "loss": 0.445, + "step": 6450 + }, + { + "epoch": 2.8988108593224142, + "grad_norm": 0.555347180047328, + "learning_rate": 5e-06, + "loss": 0.4396, + "step": 6460 + }, + { + "epoch": 2.903298182634059, + "grad_norm": 0.5337754968953309, + "learning_rate": 5e-06, + "loss": 0.4659, + "step": 6470 + }, + { + "epoch": 2.9077855059457036, + "grad_norm": 0.5482307100875392, + "learning_rate": 5e-06, + "loss": 0.4386, + "step": 6480 + }, + { + "epoch": 2.912272829257348, + "grad_norm": 0.5137780447940196, + "learning_rate": 5e-06, + "loss": 0.4498, + "step": 6490 + }, + { + "epoch": 2.9167601525689926, + "grad_norm": 0.5410402939710804, + "learning_rate": 5e-06, + "loss": 0.4447, + "step": 6500 + }, + { + "epoch": 2.9212474758806373, + "grad_norm": 0.5512710516362269, + "learning_rate": 5e-06, + "loss": 0.4415, + "step": 6510 + }, + { + "epoch": 2.925734799192282, + "grad_norm": 0.5378334272814395, + "learning_rate": 5e-06, + "loss": 0.4278, + "step": 6520 + }, + { + "epoch": 2.9302221225039267, + "grad_norm": 0.5525646027445259, + "learning_rate": 5e-06, + "loss": 0.439, + "step": 6530 + }, + { + "epoch": 2.934709445815571, + "grad_norm": 0.573171926611343, + "learning_rate": 5e-06, + "loss": 0.4361, + "step": 6540 + }, + { + "epoch": 2.9391967691272156, + "grad_norm": 0.5217333672218816, + "learning_rate": 5e-06, + "loss": 0.4621, + "step": 6550 + }, + { + "epoch": 2.9436840924388603, + "grad_norm": 0.5342154460861862, + "learning_rate": 5e-06, + "loss": 0.4646, + "step": 6560 + }, + { + "epoch": 2.9481714157505046, + "grad_norm": 0.5545259487380719, + "learning_rate": 5e-06, + "loss": 0.4658, + "step": 6570 + }, + { + "epoch": 2.9526587390621493, + "grad_norm": 0.5469560259016665, + "learning_rate": 5e-06, + "loss": 0.455, + "step": 6580 + }, + { + "epoch": 2.957146062373794, + "grad_norm": 0.5483835668636673, + "learning_rate": 5e-06, + "loss": 0.4502, + "step": 6590 + }, + { + "epoch": 2.9616333856854387, + "grad_norm": 0.614582634766974, + "learning_rate": 5e-06, + "loss": 0.4846, + "step": 6600 + }, + { + "epoch": 2.9661207089970834, + "grad_norm": 0.5262842688899035, + "learning_rate": 5e-06, + "loss": 0.4374, + "step": 6610 + }, + { + "epoch": 2.9706080323087276, + "grad_norm": 0.5571152950087439, + "learning_rate": 5e-06, + "loss": 0.4568, + "step": 6620 + }, + { + "epoch": 2.9750953556203723, + "grad_norm": 0.5654247741253923, + "learning_rate": 5e-06, + "loss": 0.4543, + "step": 6630 + }, + { + "epoch": 2.979582678932017, + "grad_norm": 0.5557134515495112, + "learning_rate": 5e-06, + "loss": 0.4413, + "step": 6640 + }, + { + "epoch": 2.9840700022436617, + "grad_norm": 0.5100342280894994, + "learning_rate": 5e-06, + "loss": 0.4297, + "step": 6650 + }, + { + "epoch": 2.9885573255553064, + "grad_norm": 0.5717765932430845, + "learning_rate": 5e-06, + "loss": 0.4274, + "step": 6660 + }, + { + "epoch": 2.9930446488669507, + "grad_norm": 0.5179292681178803, + "learning_rate": 5e-06, + "loss": 0.4425, + "step": 6670 + }, + { + "epoch": 2.9975319721785953, + "grad_norm": 0.5427917144920164, + "learning_rate": 5e-06, + "loss": 0.4538, + "step": 6680 + }, + { + "epoch": 2.9993269015032533, + "eval_loss": 0.5616346001625061, + "eval_runtime": 559.8562, + "eval_samples_per_second": 26.81, + "eval_steps_per_second": 0.42, + "step": 6684 + }, + { + "epoch": 2.9993269015032533, + "step": 6684, + "total_flos": 3503854586953728.0, + "train_loss": 0.5125751896649332, + "train_runtime": 89473.4361, + "train_samples_per_second": 9.562, + "train_steps_per_second": 0.075 + } + ], + "logging_steps": 10, + "max_steps": 6684, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "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": 3503854586953728.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..41ebb9f --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e69d7f187dae02fe6d412f45c5548a2d2dd27f904c8320f0a04c6b2e6e4dab +size 7224 diff --git a/training_eval_loss.png b/training_eval_loss.png new file mode 100644 index 0000000..bb1ef39 Binary files /dev/null and b/training_eval_loss.png differ diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..27ae38d 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