commit 139ce33163801bce0821c037ed58d49515060df2 Author: ModelHub XC Date: Sat Jun 20 18:14:20 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: formalmathatepfl/Qwen3-8B-finetuned Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..94f963f --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +library_name: transformers +license: other +base_model: Qwen/Qwen3-8B +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: sft_qwen3_8b_correct + results: [] +--- + + + +# sft_qwen3_8b_correct + +This model is a fine-tuned version of Qwen/Qwen3-8B. + +## 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: 0.0001 +- train_batch_size: 2 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 4 +- gradient_accumulation_steps: 2 +- total_train_batch_size: 16 +- total_eval_batch_size: 32 +- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 0.03 +- num_epochs: 1.0 + +### Training results + + + +### Framework versions + +- Transformers 5.2.0 +- Pytorch 2.6.0+cu124 +- Datasets 4.0.0 +- Tokenizers 0.22.2 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..a02d20c --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 1.0, + "total_flos": 5228992760119296.0, + "train_loss": 0.07239722475082117, + "train_runtime": 152754.4145, + "train_samples_per_second": 1.13, + "train_steps_per_second": 0.071 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# 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" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\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" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a8e7a96 --- /dev/null +++ b/config.json @@ -0,0 +1,71 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.2.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..1701c94 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.2.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..4680fb9 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c20c825b387f5826952f12ee4b2720097c528d023f7ef55ed7dec044e00c5d1 +size 16381517208 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c7afbed --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..271320b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": true, + "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..a02d20c --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 1.0, + "total_flos": 5228992760119296.0, + "train_loss": 0.07239722475082117, + "train_runtime": 152754.4145, + "train_samples_per_second": 1.13, + "train_steps_per_second": 0.071 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..8b960c6 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,540 @@ +{"current_steps": 20, "total_steps": 10787, "loss": 2.011005401611328, "lr": 5.864197530864198e-06, "epoch": 0.00185416956380661, "percentage": 0.19, "elapsed_time": "0:04:43", "remaining_time": "1 day, 18:25:17"} +{"current_steps": 40, "total_steps": 10787, "loss": 0.5124849319458008, "lr": 1.2037037037037037e-05, "epoch": 0.00370833912761322, "percentage": 0.37, "elapsed_time": "0:09:25", "remaining_time": "1 day, 18:11:04"} +{"current_steps": 60, "total_steps": 10787, "loss": 0.22042126655578614, "lr": 1.8209876543209877e-05, "epoch": 0.00556250869141983, "percentage": 0.56, "elapsed_time": "0:14:06", "remaining_time": "1 day, 18:02:39"} +{"current_steps": 80, "total_steps": 10787, "loss": 0.14981963634490966, "lr": 2.438271604938272e-05, "epoch": 0.00741667825522644, "percentage": 0.74, "elapsed_time": "0:18:48", "remaining_time": "1 day, 17:56:28"} +{"current_steps": 100, "total_steps": 10787, "loss": 0.12978166341781616, "lr": 3.055555555555556e-05, "epoch": 0.00927084781903305, "percentage": 0.93, "elapsed_time": "0:23:29", "remaining_time": "1 day, 17:51:00"} +{"current_steps": 120, "total_steps": 10787, "loss": 0.11404435634613037, "lr": 3.67283950617284e-05, "epoch": 0.01112501738283966, "percentage": 1.11, "elapsed_time": "0:28:11", "remaining_time": "1 day, 17:45:32"} +{"current_steps": 140, "total_steps": 10787, "loss": 0.1076289176940918, "lr": 4.290123456790124e-05, "epoch": 0.01297918694664627, "percentage": 1.3, "elapsed_time": "0:32:52", "remaining_time": "1 day, 17:40:07"} +{"current_steps": 160, "total_steps": 10787, "loss": 0.10596754550933837, "lr": 4.9074074074074075e-05, "epoch": 0.01483335651045288, "percentage": 1.48, "elapsed_time": "0:37:33", "remaining_time": "1 day, 17:34:58"} +{"current_steps": 180, "total_steps": 10787, "loss": 0.100307297706604, "lr": 5.524691358024692e-05, "epoch": 0.016687526074259492, "percentage": 1.67, "elapsed_time": "0:42:15", "remaining_time": "1 day, 17:30:11"} +{"current_steps": 200, "total_steps": 10787, "loss": 0.0976285457611084, "lr": 6.141975308641975e-05, "epoch": 0.0185416956380661, "percentage": 1.85, "elapsed_time": "0:46:57", "remaining_time": "1 day, 17:25:31"} +{"current_steps": 220, "total_steps": 10787, "loss": 0.09554426670074463, "lr": 6.759259259259259e-05, "epoch": 0.020395865201872712, "percentage": 2.04, "elapsed_time": "0:51:38", "remaining_time": "1 day, 17:20:37"} +{"current_steps": 240, "total_steps": 10787, "loss": 0.09421352148056031, "lr": 7.376543209876543e-05, "epoch": 0.02225003476567932, "percentage": 2.22, "elapsed_time": "0:56:20", "remaining_time": "1 day, 17:15:48"} +{"current_steps": 260, "total_steps": 10787, "loss": 0.0942450761795044, "lr": 7.993827160493828e-05, "epoch": 0.024104204329485932, "percentage": 2.41, "elapsed_time": "1:01:01", "remaining_time": "1 day, 17:11:02"} +{"current_steps": 280, "total_steps": 10787, "loss": 0.09581634402275085, "lr": 8.611111111111112e-05, "epoch": 0.02595837389329254, "percentage": 2.6, "elapsed_time": "1:05:43", "remaining_time": "1 day, 17:06:12"} +{"current_steps": 300, "total_steps": 10787, "loss": 0.09313751459121704, "lr": 9.228395061728396e-05, "epoch": 0.027812543457099152, "percentage": 2.78, "elapsed_time": "1:10:24", "remaining_time": "1 day, 17:01:28"} +{"current_steps": 320, "total_steps": 10787, "loss": 0.09234297275543213, "lr": 9.84567901234568e-05, "epoch": 0.02966671302090576, "percentage": 2.97, "elapsed_time": "1:15:06", "remaining_time": "1 day, 16:56:46"} +{"current_steps": 340, "total_steps": 10787, "loss": 0.08958485126495361, "lr": 9.999949288192827e-05, "epoch": 0.03152088258471237, "percentage": 3.15, "elapsed_time": "1:19:48", "remaining_time": "1 day, 16:52:04"} +{"current_steps": 360, "total_steps": 10787, "loss": 0.0907970130443573, "lr": 9.99972390445745e-05, "epoch": 0.033375052148518984, "percentage": 3.34, "elapsed_time": "1:24:30", "remaining_time": "1 day, 16:47:27"} +{"current_steps": 380, "total_steps": 10787, "loss": 0.08801476955413819, "lr": 9.999318222267878e-05, "epoch": 0.03522922171232559, "percentage": 3.52, "elapsed_time": "1:29:11", "remaining_time": "1 day, 16:42:44"} +{"current_steps": 400, "total_steps": 10787, "loss": 0.09476873278617859, "lr": 9.99873225625369e-05, "epoch": 0.0370833912761322, "percentage": 3.71, "elapsed_time": "1:33:53", "remaining_time": "1 day, 16:37:57"} +{"current_steps": 420, "total_steps": 10787, "loss": 0.09878499507904052, "lr": 9.997966027545811e-05, "epoch": 0.03893756083993881, "percentage": 3.89, "elapsed_time": "1:38:34", "remaining_time": "1 day, 16:33:14"} +{"current_steps": 440, "total_steps": 10787, "loss": 0.0894039511680603, "lr": 9.997019563775733e-05, "epoch": 0.040791730403745424, "percentage": 4.08, "elapsed_time": "1:43:16", "remaining_time": "1 day, 16:28:27"} +{"current_steps": 460, "total_steps": 10787, "loss": 0.0881020188331604, "lr": 9.995892899074535e-05, "epoch": 0.04264589996755203, "percentage": 4.26, "elapsed_time": "1:47:57", "remaining_time": "1 day, 16:23:41"} +{"current_steps": 480, "total_steps": 10787, "loss": 0.0859219789505005, "lr": 9.994586074071638e-05, "epoch": 0.04450006953135864, "percentage": 4.45, "elapsed_time": "1:52:39", "remaining_time": "1 day, 16:18:57"} +{"current_steps": 500, "total_steps": 10787, "loss": 0.08542002439498901, "lr": 9.993099135893353e-05, "epoch": 0.046354239095165256, "percentage": 4.64, "elapsed_time": "1:57:20", "remaining_time": "1 day, 16:14:13"} +{"current_steps": 520, "total_steps": 10787, "loss": 0.08334171175956726, "lr": 9.991432138161169e-05, "epoch": 0.048208408658971864, "percentage": 4.82, "elapsed_time": "2:02:02", "remaining_time": "1 day, 16:09:27"} +{"current_steps": 540, "total_steps": 10787, "loss": 0.08618338704109192, "lr": 9.989585140989832e-05, "epoch": 0.05006257822277847, "percentage": 5.01, "elapsed_time": "2:06:43", "remaining_time": "1 day, 16:04:42"} +{"current_steps": 560, "total_steps": 10787, "loss": 0.08432861566543579, "lr": 9.987558210985163e-05, "epoch": 0.05191674778658508, "percentage": 5.19, "elapsed_time": "2:11:24", "remaining_time": "1 day, 15:59:58"} +{"current_steps": 580, "total_steps": 10787, "loss": 0.08541926145553588, "lr": 9.98535142124167e-05, "epoch": 0.053770917350391696, "percentage": 5.38, "elapsed_time": "2:16:06", "remaining_time": "1 day, 15:55:16"} +{"current_steps": 600, "total_steps": 10787, "loss": 0.08227111101150512, "lr": 9.982964851339902e-05, "epoch": 0.055625086914198305, "percentage": 5.56, "elapsed_time": "2:20:47", "remaining_time": "1 day, 15:50:28"} +{"current_steps": 620, "total_steps": 10787, "loss": 0.08189270496368409, "lr": 9.980398587343585e-05, "epoch": 0.05747925647800491, "percentage": 5.75, "elapsed_time": "2:25:29", "remaining_time": "1 day, 15:45:46"} +{"current_steps": 640, "total_steps": 10787, "loss": 0.08317902684211731, "lr": 9.977652721796516e-05, "epoch": 0.05933342604181152, "percentage": 5.93, "elapsed_time": "2:30:10", "remaining_time": "1 day, 15:40:59"} +{"current_steps": 660, "total_steps": 10787, "loss": 0.08244485855102539, "lr": 9.974727353719224e-05, "epoch": 0.061187595605618136, "percentage": 6.12, "elapsed_time": "2:34:52", "remaining_time": "1 day, 15:36:17"} +{"current_steps": 680, "total_steps": 10787, "loss": 0.08294405937194824, "lr": 9.971622588605402e-05, "epoch": 0.06304176516942474, "percentage": 6.3, "elapsed_time": "2:39:33", "remaining_time": "1 day, 15:31:33"} +{"current_steps": 700, "total_steps": 10787, "loss": 0.08182405829429626, "lr": 9.968338538418107e-05, "epoch": 0.06489593473323135, "percentage": 6.49, "elapsed_time": "2:44:14", "remaining_time": "1 day, 15:26:47"} +{"current_steps": 720, "total_steps": 10787, "loss": 0.0813271701335907, "lr": 9.96487532158571e-05, "epoch": 0.06675010429703797, "percentage": 6.67, "elapsed_time": "2:48:56", "remaining_time": "1 day, 15:22:02"} +{"current_steps": 740, "total_steps": 10787, "loss": 0.08164938688278198, "lr": 9.961233062997633e-05, "epoch": 0.06860427386084457, "percentage": 6.86, "elapsed_time": "2:53:37", "remaining_time": "1 day, 15:17:14"} +{"current_steps": 760, "total_steps": 10787, "loss": 0.08256611824035645, "lr": 9.957411893999851e-05, "epoch": 0.07045844342465118, "percentage": 7.05, "elapsed_time": "2:58:18", "remaining_time": "1 day, 15:12:27"} +{"current_steps": 780, "total_steps": 10787, "loss": 0.08092707395553589, "lr": 9.953411952390146e-05, "epoch": 0.0723126129884578, "percentage": 7.23, "elapsed_time": "3:02:59", "remaining_time": "1 day, 15:07:41"} +{"current_steps": 800, "total_steps": 10787, "loss": 0.0815312385559082, "lr": 9.949233382413139e-05, "epoch": 0.0741667825522644, "percentage": 7.42, "elapsed_time": "3:07:40", "remaining_time": "1 day, 15:02:55"} +{"current_steps": 820, "total_steps": 10787, "loss": 0.07997688055038452, "lr": 9.944876334755093e-05, "epoch": 0.07602095211607102, "percentage": 7.6, "elapsed_time": "3:12:21", "remaining_time": "1 day, 14:58:06"} +{"current_steps": 840, "total_steps": 10787, "loss": 0.07891923189163208, "lr": 9.940340966538476e-05, "epoch": 0.07787512167987762, "percentage": 7.79, "elapsed_time": "3:17:02", "remaining_time": "1 day, 14:53:17"} +{"current_steps": 860, "total_steps": 10787, "loss": 0.08197757005691528, "lr": 9.935627441316296e-05, "epoch": 0.07972929124368423, "percentage": 7.97, "elapsed_time": "3:21:43", "remaining_time": "1 day, 14:48:27"} +{"current_steps": 880, "total_steps": 10787, "loss": 0.0796918511390686, "lr": 9.930735929066198e-05, "epoch": 0.08158346080749085, "percentage": 8.16, "elapsed_time": "3:26:24", "remaining_time": "1 day, 14:43:38"} +{"current_steps": 900, "total_steps": 10787, "loss": 0.08107801675796508, "lr": 9.925666606184343e-05, "epoch": 0.08343763037129745, "percentage": 8.34, "elapsed_time": "3:31:04", "remaining_time": "1 day, 14:38:51"} +{"current_steps": 920, "total_steps": 10787, "loss": 0.08010420799255372, "lr": 9.920419655479045e-05, "epoch": 0.08529179993510407, "percentage": 8.53, "elapsed_time": "3:35:46", "remaining_time": "1 day, 14:34:05"} +{"current_steps": 940, "total_steps": 10787, "loss": 0.07916066646575928, "lr": 9.91499526616417e-05, "epoch": 0.08714596949891068, "percentage": 8.71, "elapsed_time": "3:40:26", "remaining_time": "1 day, 14:29:19"} +{"current_steps": 960, "total_steps": 10787, "loss": 0.0791887640953064, "lr": 9.909393633852318e-05, "epoch": 0.08900013906271728, "percentage": 8.9, "elapsed_time": "3:45:08", "remaining_time": "1 day, 14:24:34"} +{"current_steps": 980, "total_steps": 10787, "loss": 0.07827670574188232, "lr": 9.903614960547778e-05, "epoch": 0.0908543086265239, "percentage": 9.09, "elapsed_time": "3:49:49", "remaining_time": "1 day, 14:19:50"} +{"current_steps": 1000, "total_steps": 10787, "loss": 0.07974874973297119, "lr": 9.897659454639227e-05, "epoch": 0.09270847819033051, "percentage": 9.27, "elapsed_time": "3:54:30", "remaining_time": "1 day, 14:15:06"} +{"current_steps": 1020, "total_steps": 10787, "loss": 0.07780462503433228, "lr": 9.891527330892226e-05, "epoch": 0.09456264775413711, "percentage": 9.46, "elapsed_time": "4:00:32", "remaining_time": "1 day, 14:23:22"} +{"current_steps": 1040, "total_steps": 10787, "loss": 0.07922825217247009, "lr": 9.885218810441474e-05, "epoch": 0.09641681731794373, "percentage": 9.64, "elapsed_time": "4:05:13", "remaining_time": "1 day, 14:18:20"} +{"current_steps": 1060, "total_steps": 10787, "loss": 0.07735201120376586, "lr": 9.878734120782831e-05, "epoch": 0.09827098688175033, "percentage": 9.83, "elapsed_time": "4:09:55", "remaining_time": "1 day, 14:13:26"} +{"current_steps": 1080, "total_steps": 10787, "loss": 0.07676548957824707, "lr": 9.872073495765111e-05, "epoch": 0.10012515644555695, "percentage": 10.01, "elapsed_time": "4:14:37", "remaining_time": "1 day, 14:08:30"} +{"current_steps": 1100, "total_steps": 10787, "loss": 0.0770105242729187, "lr": 9.865237175581656e-05, "epoch": 0.10197932600936356, "percentage": 10.2, "elapsed_time": "4:19:18", "remaining_time": "1 day, 14:03:32"} +{"current_steps": 1120, "total_steps": 10787, "loss": 0.07735653519630432, "lr": 9.858225406761677e-05, "epoch": 0.10383349557317016, "percentage": 10.38, "elapsed_time": "4:23:59", "remaining_time": "1 day, 13:58:34"} +{"current_steps": 1140, "total_steps": 10787, "loss": 0.07819046974182128, "lr": 9.851038442161347e-05, "epoch": 0.10568766513697678, "percentage": 10.57, "elapsed_time": "4:28:40", "remaining_time": "1 day, 13:53:38"} +{"current_steps": 1160, "total_steps": 10787, "loss": 0.07668208479881286, "lr": 9.843676540954699e-05, "epoch": 0.10754183470078339, "percentage": 10.75, "elapsed_time": "4:33:21", "remaining_time": "1 day, 13:48:42"} +{"current_steps": 1180, "total_steps": 10787, "loss": 0.07516925930976867, "lr": 9.836139968624276e-05, "epoch": 0.10939600426459, "percentage": 10.94, "elapsed_time": "4:38:03", "remaining_time": "1 day, 13:43:47"} +{"current_steps": 1200, "total_steps": 10787, "loss": 0.07837026715278625, "lr": 9.828428996951556e-05, "epoch": 0.11125017382839661, "percentage": 11.12, "elapsed_time": "4:42:44", "remaining_time": "1 day, 13:38:54"} +{"current_steps": 1220, "total_steps": 10787, "loss": 0.07502893805503845, "lr": 9.820543904007143e-05, "epoch": 0.11310434339220321, "percentage": 11.31, "elapsed_time": "4:47:26", "remaining_time": "1 day, 13:34:01"} +{"current_steps": 1240, "total_steps": 10787, "loss": 0.07647337913513183, "lr": 9.812484974140757e-05, "epoch": 0.11495851295600983, "percentage": 11.5, "elapsed_time": "4:52:07", "remaining_time": "1 day, 13:29:08"} +{"current_steps": 1260, "total_steps": 10787, "loss": 0.07538799047470093, "lr": 9.804252497970961e-05, "epoch": 0.11681268251981644, "percentage": 11.68, "elapsed_time": "4:56:49", "remaining_time": "1 day, 13:24:18"} +{"current_steps": 1280, "total_steps": 10787, "loss": 0.0785320520401001, "lr": 9.795846772374698e-05, "epoch": 0.11866685208362304, "percentage": 11.87, "elapsed_time": "5:01:30", "remaining_time": "1 day, 13:19:27"} +{"current_steps": 1300, "total_steps": 10787, "loss": 0.14148486852645875, "lr": 9.787268100476571e-05, "epoch": 0.12052102164742966, "percentage": 12.05, "elapsed_time": "5:06:12", "remaining_time": "1 day, 13:14:35"} +{"current_steps": 1320, "total_steps": 10787, "loss": 0.09106227159500122, "lr": 9.778516791637918e-05, "epoch": 0.12237519121123627, "percentage": 12.24, "elapsed_time": "5:10:53", "remaining_time": "1 day, 13:09:45"} +{"current_steps": 1340, "total_steps": 10787, "loss": 0.10610485076904297, "lr": 9.769593161445658e-05, "epoch": 0.12422936077504287, "percentage": 12.42, "elapsed_time": "5:15:35", "remaining_time": "1 day, 13:04:54"} +{"current_steps": 1360, "total_steps": 10787, "loss": 0.09194117784500122, "lr": 9.760497531700905e-05, "epoch": 0.12608353033884948, "percentage": 12.61, "elapsed_time": "5:20:16", "remaining_time": "1 day, 13:00:04"} +{"current_steps": 1380, "total_steps": 10787, "loss": 0.08373166918754578, "lr": 9.751230230407368e-05, "epoch": 0.1279376999026561, "percentage": 12.79, "elapsed_time": "5:24:58", "remaining_time": "1 day, 12:55:13"} +{"current_steps": 1400, "total_steps": 10787, "loss": 0.07780111432075501, "lr": 9.741791591759523e-05, "epoch": 0.1297918694664627, "percentage": 12.98, "elapsed_time": "5:29:39", "remaining_time": "1 day, 12:50:23"} +{"current_steps": 1420, "total_steps": 10787, "loss": 0.08092001676559449, "lr": 9.732181956130555e-05, "epoch": 0.1316460390302693, "percentage": 13.16, "elapsed_time": "5:34:21", "remaining_time": "1 day, 12:45:32"} +{"current_steps": 1440, "total_steps": 10787, "loss": 0.07920002937316895, "lr": 9.722401670060088e-05, "epoch": 0.13350020859407594, "percentage": 13.35, "elapsed_time": "5:39:02", "remaining_time": "1 day, 12:40:44"} +{"current_steps": 1460, "total_steps": 10787, "loss": 0.07667785882949829, "lr": 9.712451086241689e-05, "epoch": 0.13535437815788254, "percentage": 13.53, "elapsed_time": "5:43:43", "remaining_time": "1 day, 12:35:53"} +{"current_steps": 1480, "total_steps": 10787, "loss": 0.07909265160560608, "lr": 9.702330563510153e-05, "epoch": 0.13720854772168914, "percentage": 13.72, "elapsed_time": "5:48:25", "remaining_time": "1 day, 12:31:03"} +{"current_steps": 1500, "total_steps": 10787, "loss": 0.07624268531799316, "lr": 9.69204046682855e-05, "epoch": 0.13906271728549577, "percentage": 13.91, "elapsed_time": "5:53:06", "remaining_time": "1 day, 12:26:13"} +{"current_steps": 1520, "total_steps": 10787, "loss": 0.07816213369369507, "lr": 9.681581167275077e-05, "epoch": 0.14091688684930237, "percentage": 14.09, "elapsed_time": "5:57:48", "remaining_time": "1 day, 12:21:24"} +{"current_steps": 1540, "total_steps": 10787, "loss": 0.07695078253746032, "lr": 9.670953042029669e-05, "epoch": 0.14277105641310897, "percentage": 14.28, "elapsed_time": "6:02:29", "remaining_time": "1 day, 12:16:36"} +{"current_steps": 1560, "total_steps": 10787, "loss": 0.07489546537399291, "lr": 9.6601564743604e-05, "epoch": 0.1446252259769156, "percentage": 14.46, "elapsed_time": "6:07:10", "remaining_time": "1 day, 12:11:46"} +{"current_steps": 1580, "total_steps": 10787, "loss": 0.0800896406173706, "lr": 9.649191853609665e-05, "epoch": 0.1464793955407222, "percentage": 14.65, "elapsed_time": "6:11:52", "remaining_time": "1 day, 12:06:57"} +{"current_steps": 1600, "total_steps": 10787, "loss": 0.11360986232757568, "lr": 9.638059575180127e-05, "epoch": 0.1483335651045288, "percentage": 14.83, "elapsed_time": "6:16:33", "remaining_time": "1 day, 12:02:10"} +{"current_steps": 1620, "total_steps": 10787, "loss": 0.08856036067008972, "lr": 9.626760040520475e-05, "epoch": 0.15018773466833543, "percentage": 15.02, "elapsed_time": "6:21:15", "remaining_time": "1 day, 11:57:22"} +{"current_steps": 1640, "total_steps": 10787, "loss": 0.08102580308914184, "lr": 9.615293657110937e-05, "epoch": 0.15204190423214203, "percentage": 15.2, "elapsed_time": "6:25:56", "remaining_time": "1 day, 11:52:35"} +{"current_steps": 1660, "total_steps": 10787, "loss": 0.08062328100204467, "lr": 9.603660838448584e-05, "epoch": 0.15389607379594863, "percentage": 15.39, "elapsed_time": "6:30:38", "remaining_time": "1 day, 11:47:48"} +{"current_steps": 1680, "total_steps": 10787, "loss": 0.08349821567535401, "lr": 9.591862004032429e-05, "epoch": 0.15575024335975524, "percentage": 15.57, "elapsed_time": "6:35:20", "remaining_time": "1 day, 11:43:02"} +{"current_steps": 1700, "total_steps": 10787, "loss": 0.0809329867362976, "lr": 9.579897579348282e-05, "epoch": 0.15760441292356187, "percentage": 15.76, "elapsed_time": "6:40:01", "remaining_time": "1 day, 11:38:16"} +{"current_steps": 1720, "total_steps": 10787, "loss": 0.07894476652145385, "lr": 9.567767995853429e-05, "epoch": 0.15945858248736847, "percentage": 15.95, "elapsed_time": "6:44:43", "remaining_time": "1 day, 11:33:31"} +{"current_steps": 1740, "total_steps": 10787, "loss": 0.07519868612289429, "lr": 9.555473690961051e-05, "epoch": 0.16131275205117507, "percentage": 16.13, "elapsed_time": "6:49:25", "remaining_time": "1 day, 11:28:44"} +{"current_steps": 1760, "total_steps": 10787, "loss": 0.0785559892654419, "lr": 9.543015108024463e-05, "epoch": 0.1631669216149817, "percentage": 16.32, "elapsed_time": "6:54:06", "remaining_time": "1 day, 11:23:58"} +{"current_steps": 1780, "total_steps": 10787, "loss": 0.07550161480903625, "lr": 9.530392696321126e-05, "epoch": 0.1650210911787883, "percentage": 16.5, "elapsed_time": "6:58:48", "remaining_time": "1 day, 11:19:11"} +{"current_steps": 1800, "total_steps": 10787, "loss": 0.07608571052551269, "lr": 9.517606911036433e-05, "epoch": 0.1668752607425949, "percentage": 16.69, "elapsed_time": "7:03:29", "remaining_time": "1 day, 11:14:26"} +{"current_steps": 1820, "total_steps": 10787, "loss": 0.07413275241851806, "lr": 9.504658213247316e-05, "epoch": 0.16872943030640153, "percentage": 16.87, "elapsed_time": "7:08:11", "remaining_time": "1 day, 11:09:40"} +{"current_steps": 1840, "total_steps": 10787, "loss": 0.07561180591583253, "lr": 9.491547069905593e-05, "epoch": 0.17058359987020813, "percentage": 17.06, "elapsed_time": "7:12:53", "remaining_time": "1 day, 11:04:54"} +{"current_steps": 1860, "total_steps": 10787, "loss": 0.07366191148757935, "lr": 9.478273953821149e-05, "epoch": 0.17243776943401473, "percentage": 17.24, "elapsed_time": "7:17:34", "remaining_time": "1 day, 11:00:09"} +{"current_steps": 1880, "total_steps": 10787, "loss": 0.07775602340698243, "lr": 9.464839343644878e-05, "epoch": 0.17429193899782136, "percentage": 17.43, "elapsed_time": "7:22:16", "remaining_time": "1 day, 10:55:24"} +{"current_steps": 1900, "total_steps": 10787, "loss": 0.07233434915542603, "lr": 9.451243723851421e-05, "epoch": 0.17614610856162796, "percentage": 17.61, "elapsed_time": "7:26:58", "remaining_time": "1 day, 10:50:38"} +{"current_steps": 1920, "total_steps": 10787, "loss": 0.07621219754219055, "lr": 9.437487584721698e-05, "epoch": 0.17800027812543456, "percentage": 17.8, "elapsed_time": "7:31:39", "remaining_time": "1 day, 10:45:52"} +{"current_steps": 1940, "total_steps": 10787, "loss": 0.07463518381118775, "lr": 9.423571422325223e-05, "epoch": 0.1798544476892412, "percentage": 17.98, "elapsed_time": "7:36:21", "remaining_time": "1 day, 10:41:06"} +{"current_steps": 1960, "total_steps": 10787, "loss": 0.07639362812042236, "lr": 9.409495738502226e-05, "epoch": 0.1817086172530478, "percentage": 18.17, "elapsed_time": "7:41:02", "remaining_time": "1 day, 10:36:21"} +{"current_steps": 1980, "total_steps": 10787, "loss": 0.07541184425354004, "lr": 9.39526104084554e-05, "epoch": 0.1835627868168544, "percentage": 18.36, "elapsed_time": "7:45:44", "remaining_time": "1 day, 10:31:36"} +{"current_steps": 2000, "total_steps": 10787, "loss": 0.07277128696441651, "lr": 9.380867842682305e-05, "epoch": 0.18541695638066102, "percentage": 18.54, "elapsed_time": "7:50:25", "remaining_time": "1 day, 10:26:50"} +{"current_steps": 2020, "total_steps": 10787, "loss": 0.07344133853912353, "lr": 9.366316663055462e-05, "epoch": 0.18727112594446763, "percentage": 18.73, "elapsed_time": "7:56:31", "remaining_time": "1 day, 10:28:09"} +{"current_steps": 2040, "total_steps": 10787, "loss": 0.0730777382850647, "lr": 9.351608026705023e-05, "epoch": 0.18912529550827423, "percentage": 18.91, "elapsed_time": "8:01:12", "remaining_time": "1 day, 10:23:18"} +{"current_steps": 2060, "total_steps": 10787, "loss": 0.07285230755805969, "lr": 9.336742464049157e-05, "epoch": 0.19097946507208083, "percentage": 19.1, "elapsed_time": "8:05:53", "remaining_time": "1 day, 10:18:27"} +{"current_steps": 2080, "total_steps": 10787, "loss": 0.07300975322723388, "lr": 9.32172051116506e-05, "epoch": 0.19283363463588746, "percentage": 19.28, "elapsed_time": "8:10:35", "remaining_time": "1 day, 10:13:36"} +{"current_steps": 2100, "total_steps": 10787, "loss": 0.07422054409980774, "lr": 9.306542709769622e-05, "epoch": 0.19468780419969406, "percentage": 19.47, "elapsed_time": "8:15:16", "remaining_time": "1 day, 10:08:45"} +{"current_steps": 2120, "total_steps": 10787, "loss": 0.07437876462936402, "lr": 9.291209607199892e-05, "epoch": 0.19654197376350066, "percentage": 19.65, "elapsed_time": "8:19:57", "remaining_time": "1 day, 10:03:55"} +{"current_steps": 2140, "total_steps": 10787, "loss": 0.0755193829536438, "lr": 9.275721756393339e-05, "epoch": 0.1983961433273073, "percentage": 19.84, "elapsed_time": "8:24:38", "remaining_time": "1 day, 9:59:06"} +{"current_steps": 2160, "total_steps": 10787, "loss": 0.07785636186599731, "lr": 9.260079715867917e-05, "epoch": 0.2002503128911139, "percentage": 20.02, "elapsed_time": "8:29:20", "remaining_time": "1 day, 9:54:17"} +{"current_steps": 2180, "total_steps": 10787, "loss": 0.07767927646636963, "lr": 9.244284049701923e-05, "epoch": 0.2021044824549205, "percentage": 20.21, "elapsed_time": "8:34:01", "remaining_time": "1 day, 9:49:26"} +{"current_steps": 2200, "total_steps": 10787, "loss": 0.07524172067642212, "lr": 9.228335327513644e-05, "epoch": 0.20395865201872712, "percentage": 20.39, "elapsed_time": "8:38:42", "remaining_time": "1 day, 9:44:37"} +{"current_steps": 2220, "total_steps": 10787, "loss": 0.07576064467430114, "lr": 9.212234124440831e-05, "epoch": 0.20581282158253372, "percentage": 20.58, "elapsed_time": "8:43:23", "remaining_time": "1 day, 9:39:47"} +{"current_steps": 2240, "total_steps": 10787, "loss": 0.07323854565620422, "lr": 9.195981021119955e-05, "epoch": 0.20766699114634032, "percentage": 20.77, "elapsed_time": "8:48:04", "remaining_time": "1 day, 9:34:57"} +{"current_steps": 2260, "total_steps": 10787, "loss": 0.07339696884155274, "lr": 9.179576603665258e-05, "epoch": 0.20952116071014695, "percentage": 20.95, "elapsed_time": "8:52:46", "remaining_time": "1 day, 9:30:08"} +{"current_steps": 2280, "total_steps": 10787, "loss": 0.07229110598564148, "lr": 9.163021463647628e-05, "epoch": 0.21137533027395355, "percentage": 21.14, "elapsed_time": "8:57:27", "remaining_time": "1 day, 9:25:19"} +{"current_steps": 2300, "total_steps": 10787, "loss": 0.07312118411064147, "lr": 9.146316198073263e-05, "epoch": 0.21322949983776016, "percentage": 21.32, "elapsed_time": "9:02:08", "remaining_time": "1 day, 9:20:31"} +{"current_steps": 2320, "total_steps": 10787, "loss": 0.07265024781227111, "lr": 9.129461409362141e-05, "epoch": 0.21508366940156678, "percentage": 21.51, "elapsed_time": "9:06:50", "remaining_time": "1 day, 9:15:44"} +{"current_steps": 2340, "total_steps": 10787, "loss": 0.07265085577964783, "lr": 9.112457705326292e-05, "epoch": 0.2169378389653734, "percentage": 21.69, "elapsed_time": "9:11:31", "remaining_time": "1 day, 9:10:56"} +{"current_steps": 2360, "total_steps": 10787, "loss": 0.07184367179870606, "lr": 9.095305699147889e-05, "epoch": 0.21879200852918, "percentage": 21.88, "elapsed_time": "9:16:13", "remaining_time": "1 day, 9:06:07"} +{"current_steps": 2380, "total_steps": 10787, "loss": 0.07540631890296937, "lr": 9.078006009357125e-05, "epoch": 0.22064617809298662, "percentage": 22.06, "elapsed_time": "9:20:54", "remaining_time": "1 day, 9:01:18"} +{"current_steps": 2400, "total_steps": 10787, "loss": 0.07418131828308105, "lr": 9.060559259809915e-05, "epoch": 0.22250034765679322, "percentage": 22.25, "elapsed_time": "9:25:35", "remaining_time": "1 day, 8:56:29"} +{"current_steps": 2420, "total_steps": 10787, "loss": 0.0729554533958435, "lr": 9.042966079665397e-05, "epoch": 0.22435451722059982, "percentage": 22.43, "elapsed_time": "9:30:16", "remaining_time": "1 day, 8:51:42"} +{"current_steps": 2440, "total_steps": 10787, "loss": 0.07194913625717163, "lr": 9.025227103363238e-05, "epoch": 0.22620868678440642, "percentage": 22.62, "elapsed_time": "9:34:58", "remaining_time": "1 day, 8:46:54"} +{"current_steps": 2460, "total_steps": 10787, "loss": 0.07399054765701293, "lr": 9.007342970600762e-05, "epoch": 0.22806285634821305, "percentage": 22.81, "elapsed_time": "9:39:40", "remaining_time": "1 day, 8:42:09"} +{"current_steps": 2480, "total_steps": 10787, "loss": 0.07210756540298462, "lr": 8.989314326309885e-05, "epoch": 0.22991702591201965, "percentage": 22.99, "elapsed_time": "9:44:21", "remaining_time": "1 day, 8:37:22"} +{"current_steps": 2500, "total_steps": 10787, "loss": 0.07364898920059204, "lr": 8.971141820633842e-05, "epoch": 0.23177119547582625, "percentage": 23.18, "elapsed_time": "9:49:03", "remaining_time": "1 day, 8:32:35"} +{"current_steps": 2520, "total_steps": 10787, "loss": 0.07184793949127197, "lr": 8.95282610890376e-05, "epoch": 0.23362536503963288, "percentage": 23.36, "elapsed_time": "9:53:44", "remaining_time": "1 day, 8:27:48"} +{"current_steps": 2540, "total_steps": 10787, "loss": 0.07045998573303222, "lr": 8.934367851615009e-05, "epoch": 0.23547953460343948, "percentage": 23.55, "elapsed_time": "9:58:26", "remaining_time": "1 day, 8:23:01"} +{"current_steps": 2560, "total_steps": 10787, "loss": 0.07100774049758911, "lr": 8.9157677144034e-05, "epoch": 0.23733370416724608, "percentage": 23.73, "elapsed_time": "10:03:07", "remaining_time": "1 day, 8:18:15"} +{"current_steps": 2580, "total_steps": 10787, "loss": 0.07279749512672425, "lr": 8.897026368021167e-05, "epoch": 0.2391878737310527, "percentage": 23.92, "elapsed_time": "10:07:50", "remaining_time": "1 day, 8:13:31"} +{"current_steps": 2600, "total_steps": 10787, "loss": 0.07153629064559937, "lr": 8.878144488312786e-05, "epoch": 0.24104204329485932, "percentage": 24.1, "elapsed_time": "10:12:31", "remaining_time": "1 day, 8:08:45"} +{"current_steps": 2620, "total_steps": 10787, "loss": 0.07133421301841736, "lr": 8.859122756190601e-05, "epoch": 0.24289621285866592, "percentage": 24.29, "elapsed_time": "10:17:13", "remaining_time": "1 day, 8:03:59"} +{"current_steps": 2640, "total_steps": 10787, "loss": 0.07275062203407287, "lr": 8.83996185761027e-05, "epoch": 0.24475038242247255, "percentage": 24.47, "elapsed_time": "10:21:55", "remaining_time": "1 day, 7:59:14"} +{"current_steps": 2660, "total_steps": 10787, "loss": 0.07059406042098999, "lr": 8.820662483546027e-05, "epoch": 0.24660455198627915, "percentage": 24.66, "elapsed_time": "10:26:37", "remaining_time": "1 day, 7:54:29"} +{"current_steps": 2680, "total_steps": 10787, "loss": 0.07081823348999024, "lr": 8.801225329965764e-05, "epoch": 0.24845872155008575, "percentage": 24.84, "elapsed_time": "10:31:18", "remaining_time": "1 day, 7:49:43"} +{"current_steps": 2700, "total_steps": 10787, "loss": 0.07319986224174499, "lr": 8.781651097805936e-05, "epoch": 0.2503128911138924, "percentage": 25.03, "elapsed_time": "10:36:00", "remaining_time": "1 day, 7:44:57"} +{"current_steps": 2720, "total_steps": 10787, "loss": 0.07124414443969726, "lr": 8.76194049294628e-05, "epoch": 0.25216706067769895, "percentage": 25.22, "elapsed_time": "10:40:41", "remaining_time": "1 day, 7:40:11"} +{"current_steps": 2740, "total_steps": 10787, "loss": 0.07674325704574585, "lr": 8.742094226184365e-05, "epoch": 0.2540212302415056, "percentage": 25.4, "elapsed_time": "10:45:23", "remaining_time": "1 day, 7:35:26"} +{"current_steps": 2760, "total_steps": 10787, "loss": 0.07280395030975342, "lr": 8.722113013209954e-05, "epoch": 0.2558753998053122, "percentage": 25.59, "elapsed_time": "10:50:05", "remaining_time": "1 day, 7:30:40"} +{"current_steps": 2780, "total_steps": 10787, "loss": 0.07572759985923767, "lr": 8.701997574579196e-05, "epoch": 0.2577295693691188, "percentage": 25.77, "elapsed_time": "10:54:46", "remaining_time": "1 day, 7:25:54"} +{"current_steps": 2800, "total_steps": 10787, "loss": 0.07128249406814575, "lr": 8.681748635688645e-05, "epoch": 0.2595837389329254, "percentage": 25.96, "elapsed_time": "10:59:28", "remaining_time": "1 day, 7:21:09"} +{"current_steps": 2820, "total_steps": 10787, "loss": 0.07258655428886414, "lr": 8.661366926749101e-05, "epoch": 0.26143790849673204, "percentage": 26.14, "elapsed_time": "11:04:10", "remaining_time": "1 day, 7:16:24"} +{"current_steps": 2840, "total_steps": 10787, "loss": 0.07168116569519042, "lr": 8.640853182759274e-05, "epoch": 0.2632920780605386, "percentage": 26.33, "elapsed_time": "11:08:52", "remaining_time": "1 day, 7:11:39"} +{"current_steps": 2860, "total_steps": 10787, "loss": 0.07134959697723389, "lr": 8.620208143479276e-05, "epoch": 0.26514624762434524, "percentage": 26.51, "elapsed_time": "11:13:33", "remaining_time": "1 day, 7:06:53"} +{"current_steps": 2880, "total_steps": 10787, "loss": 0.07181867361068725, "lr": 8.59943255340395e-05, "epoch": 0.2670004171881519, "percentage": 26.7, "elapsed_time": "11:18:15", "remaining_time": "1 day, 7:02:08"} +{"current_steps": 2900, "total_steps": 10787, "loss": 0.07058979272842407, "lr": 8.578527161736027e-05, "epoch": 0.26885458675195845, "percentage": 26.88, "elapsed_time": "11:22:56", "remaining_time": "1 day, 6:57:23"} +{"current_steps": 2920, "total_steps": 10787, "loss": 0.06852529644966125, "lr": 8.557492722359091e-05, "epoch": 0.2707087563157651, "percentage": 27.07, "elapsed_time": "11:27:38", "remaining_time": "1 day, 6:52:37"} +{"current_steps": 2940, "total_steps": 10787, "loss": 0.07001596689224243, "lr": 8.53632999381041e-05, "epoch": 0.2725629258795717, "percentage": 27.26, "elapsed_time": "11:32:20", "remaining_time": "1 day, 6:47:52"} +{"current_steps": 2960, "total_steps": 10787, "loss": 0.07448661923408509, "lr": 8.515039739253576e-05, "epoch": 0.2744170954433783, "percentage": 27.44, "elapsed_time": "11:37:01", "remaining_time": "1 day, 6:43:06"} +{"current_steps": 2980, "total_steps": 10787, "loss": 0.07278544902801513, "lr": 8.493622726450981e-05, "epoch": 0.2762712650071849, "percentage": 27.63, "elapsed_time": "11:41:42", "remaining_time": "1 day, 6:38:21"} +{"current_steps": 3000, "total_steps": 10787, "loss": 0.06984232664108277, "lr": 8.472079727736128e-05, "epoch": 0.27812543457099154, "percentage": 27.81, "elapsed_time": "11:46:24", "remaining_time": "1 day, 6:33:35"} +{"current_steps": 3020, "total_steps": 10787, "loss": 0.07119113206863403, "lr": 8.450411519985794e-05, "epoch": 0.2799796041347981, "percentage": 28.0, "elapsed_time": "11:52:38", "remaining_time": "1 day, 6:32:48"} +{"current_steps": 3040, "total_steps": 10787, "loss": 0.0721335768699646, "lr": 8.428618884592001e-05, "epoch": 0.28183377369860474, "percentage": 28.18, "elapsed_time": "11:57:20", "remaining_time": "1 day, 6:28:01"} +{"current_steps": 3060, "total_steps": 10787, "loss": 0.07185147404670715, "lr": 8.406702607433833e-05, "epoch": 0.28368794326241137, "percentage": 28.37, "elapsed_time": "12:02:01", "remaining_time": "1 day, 6:23:14"} +{"current_steps": 3080, "total_steps": 10787, "loss": 0.06987054347991943, "lr": 8.384663478849116e-05, "epoch": 0.28554211282621794, "percentage": 28.55, "elapsed_time": "12:06:43", "remaining_time": "1 day, 6:18:26"} +{"current_steps": 3100, "total_steps": 10787, "loss": 0.07024177312850952, "lr": 8.362502293605898e-05, "epoch": 0.28739628239002457, "percentage": 28.74, "elapsed_time": "12:11:24", "remaining_time": "1 day, 6:13:39"} +{"current_steps": 3120, "total_steps": 10787, "loss": 0.07095595598220825, "lr": 8.340219850873794e-05, "epoch": 0.2892504519538312, "percentage": 28.92, "elapsed_time": "12:16:06", "remaining_time": "1 day, 6:08:52"} +{"current_steps": 3140, "total_steps": 10787, "loss": 0.07078310251235961, "lr": 8.317816954195175e-05, "epoch": 0.2911046215176378, "percentage": 29.11, "elapsed_time": "12:20:47", "remaining_time": "1 day, 6:04:05"} +{"current_steps": 3160, "total_steps": 10787, "loss": 0.07231824398040772, "lr": 8.295294411456176e-05, "epoch": 0.2929587910814444, "percentage": 29.29, "elapsed_time": "12:25:29", "remaining_time": "1 day, 5:59:19"} +{"current_steps": 3180, "total_steps": 10787, "loss": 0.07037442922592163, "lr": 8.272653034857577e-05, "epoch": 0.29481296064525103, "percentage": 29.48, "elapsed_time": "12:30:11", "remaining_time": "1 day, 5:54:32"} +{"current_steps": 3200, "total_steps": 10787, "loss": 0.07160881757736207, "lr": 8.249893640885505e-05, "epoch": 0.2966671302090576, "percentage": 29.67, "elapsed_time": "12:34:52", "remaining_time": "1 day, 5:49:45"} +{"current_steps": 3220, "total_steps": 10787, "loss": 0.07143862247467041, "lr": 8.227017050281987e-05, "epoch": 0.29852129977286423, "percentage": 29.85, "elapsed_time": "12:39:33", "remaining_time": "1 day, 5:44:58"} +{"current_steps": 3240, "total_steps": 10787, "loss": 0.07265503406524658, "lr": 8.204024088015363e-05, "epoch": 0.30037546933667086, "percentage": 30.04, "elapsed_time": "12:44:15", "remaining_time": "1 day, 5:40:11"} +{"current_steps": 3260, "total_steps": 10787, "loss": 0.07018079757690429, "lr": 8.180915583250532e-05, "epoch": 0.30222963890047744, "percentage": 30.22, "elapsed_time": "12:48:56", "remaining_time": "1 day, 5:35:24"} +{"current_steps": 3280, "total_steps": 10787, "loss": 0.07140896916389465, "lr": 8.157692369319045e-05, "epoch": 0.30408380846428407, "percentage": 30.41, "elapsed_time": "12:53:37", "remaining_time": "1 day, 5:30:37"} +{"current_steps": 3300, "total_steps": 10787, "loss": 0.07040358781814575, "lr": 8.134355283689063e-05, "epoch": 0.3059379780280907, "percentage": 30.59, "elapsed_time": "12:58:19", "remaining_time": "1 day, 5:25:50"} +{"current_steps": 3320, "total_steps": 10787, "loss": 0.07193192243576049, "lr": 8.110905167935147e-05, "epoch": 0.30779214759189727, "percentage": 30.78, "elapsed_time": "13:03:00", "remaining_time": "1 day, 5:21:04"} +{"current_steps": 3340, "total_steps": 10787, "loss": 0.07015389204025269, "lr": 8.087342867707918e-05, "epoch": 0.3096463171557039, "percentage": 30.96, "elapsed_time": "13:07:42", "remaining_time": "1 day, 5:16:17"} +{"current_steps": 3360, "total_steps": 10787, "loss": 0.06960692405700683, "lr": 8.063669232703559e-05, "epoch": 0.31150048671951047, "percentage": 31.15, "elapsed_time": "13:12:23", "remaining_time": "1 day, 5:11:31"} +{"current_steps": 3380, "total_steps": 10787, "loss": 0.06944797039031983, "lr": 8.03988511663317e-05, "epoch": 0.3133546562833171, "percentage": 31.33, "elapsed_time": "13:17:05", "remaining_time": "1 day, 5:06:45"} +{"current_steps": 3400, "total_steps": 10787, "loss": 0.06993094086647034, "lr": 8.015991377191984e-05, "epoch": 0.31520882584712373, "percentage": 31.52, "elapsed_time": "13:21:47", "remaining_time": "1 day, 5:01:59"} +{"current_steps": 3420, "total_steps": 10787, "loss": 0.06836211681365967, "lr": 7.991988876028437e-05, "epoch": 0.3170629954109303, "percentage": 31.7, "elapsed_time": "13:26:28", "remaining_time": "1 day, 4:57:13"} +{"current_steps": 3440, "total_steps": 10787, "loss": 0.0685504674911499, "lr": 7.967878478713097e-05, "epoch": 0.31891716497473693, "percentage": 31.89, "elapsed_time": "13:31:10", "remaining_time": "1 day, 4:52:27"} +{"current_steps": 3460, "total_steps": 10787, "loss": 0.06650092601776122, "lr": 7.943661054707448e-05, "epoch": 0.32077133453854356, "percentage": 32.08, "elapsed_time": "13:35:51", "remaining_time": "1 day, 4:47:41"} +{"current_steps": 3480, "total_steps": 10787, "loss": 0.0690037727355957, "lr": 7.919337477332536e-05, "epoch": 0.32262550410235014, "percentage": 32.26, "elapsed_time": "13:40:33", "remaining_time": "1 day, 4:42:56"} +{"current_steps": 3500, "total_steps": 10787, "loss": 0.06971213817596436, "lr": 7.894908623737478e-05, "epoch": 0.32447967366615676, "percentage": 32.45, "elapsed_time": "13:45:15", "remaining_time": "1 day, 4:38:10"} +{"current_steps": 3520, "total_steps": 10787, "loss": 0.06895116567611695, "lr": 7.870375374867827e-05, "epoch": 0.3263338432299634, "percentage": 32.63, "elapsed_time": "13:49:56", "remaining_time": "1 day, 4:33:25"} +{"current_steps": 3540, "total_steps": 10787, "loss": 0.07218914031982422, "lr": 7.845738615433804e-05, "epoch": 0.32818801279376997, "percentage": 32.82, "elapsed_time": "13:54:38", "remaining_time": "1 day, 4:28:40"} +{"current_steps": 3560, "total_steps": 10787, "loss": 0.06853553056716918, "lr": 7.820999233878398e-05, "epoch": 0.3300421823575766, "percentage": 33.0, "elapsed_time": "13:59:20", "remaining_time": "1 day, 4:23:55"} +{"current_steps": 3580, "total_steps": 10787, "loss": 0.06862747669219971, "lr": 7.796158122345322e-05, "epoch": 0.3318963519213832, "percentage": 33.19, "elapsed_time": "14:04:02", "remaining_time": "1 day, 4:19:10"} +{"current_steps": 3600, "total_steps": 10787, "loss": 0.07211055755615234, "lr": 7.771216176646844e-05, "epoch": 0.3337505214851898, "percentage": 33.37, "elapsed_time": "14:08:44", "remaining_time": "1 day, 4:14:24"} +{"current_steps": 3620, "total_steps": 10787, "loss": 0.0689316987991333, "lr": 7.746174296231482e-05, "epoch": 0.33560469104899643, "percentage": 33.56, "elapsed_time": "14:13:26", "remaining_time": "1 day, 4:09:39"} +{"current_steps": 3640, "total_steps": 10787, "loss": 0.06952942609786987, "lr": 7.721033384151568e-05, "epoch": 0.33745886061280306, "percentage": 33.74, "elapsed_time": "14:18:07", "remaining_time": "1 day, 4:04:54"} +{"current_steps": 3660, "total_steps": 10787, "loss": 0.0695588767528534, "lr": 7.69579434703068e-05, "epoch": 0.33931303017660963, "percentage": 33.93, "elapsed_time": "14:22:49", "remaining_time": "1 day, 4:00:09"} +{"current_steps": 3680, "total_steps": 10787, "loss": 0.07019612789154053, "lr": 7.670458095030955e-05, "epoch": 0.34116719974041626, "percentage": 34.12, "elapsed_time": "14:27:31", "remaining_time": "1 day, 3:55:24"} +{"current_steps": 3700, "total_steps": 10787, "loss": 0.07074885964393615, "lr": 7.645025541820254e-05, "epoch": 0.3430213693042229, "percentage": 34.3, "elapsed_time": "14:32:13", "remaining_time": "1 day, 3:50:39"} +{"current_steps": 3720, "total_steps": 10787, "loss": 0.06914512515068054, "lr": 7.619497604539232e-05, "epoch": 0.34487553886802946, "percentage": 34.49, "elapsed_time": "14:36:55", "remaining_time": "1 day, 3:45:54"} +{"current_steps": 3740, "total_steps": 10787, "loss": 0.06664897799491883, "lr": 7.593875203768247e-05, "epoch": 0.3467297084318361, "percentage": 34.67, "elapsed_time": "14:41:36", "remaining_time": "1 day, 3:41:09"} +{"current_steps": 3760, "total_steps": 10787, "loss": 0.06811505556106567, "lr": 7.568159263494171e-05, "epoch": 0.3485838779956427, "percentage": 34.86, "elapsed_time": "14:46:18", "remaining_time": "1 day, 3:36:24"} +{"current_steps": 3780, "total_steps": 10787, "loss": 0.06916459798812866, "lr": 7.542350711077068e-05, "epoch": 0.3504380475594493, "percentage": 35.04, "elapsed_time": "14:51:00", "remaining_time": "1 day, 3:31:39"} +{"current_steps": 3800, "total_steps": 10787, "loss": 0.06800092458724975, "lr": 7.516450477216749e-05, "epoch": 0.3522922171232559, "percentage": 35.23, "elapsed_time": "14:55:41", "remaining_time": "1 day, 3:26:54"} +{"current_steps": 3820, "total_steps": 10787, "loss": 0.06905245780944824, "lr": 7.49045949591922e-05, "epoch": 0.35414638668706255, "percentage": 35.41, "elapsed_time": "15:00:23", "remaining_time": "1 day, 3:22:09"} +{"current_steps": 3840, "total_steps": 10787, "loss": 0.0688902497291565, "lr": 7.464378704462984e-05, "epoch": 0.3560005562508691, "percentage": 35.6, "elapsed_time": "15:05:05", "remaining_time": "1 day, 3:17:25"} +{"current_steps": 3860, "total_steps": 10787, "loss": 0.06842745542526245, "lr": 7.438209043365249e-05, "epoch": 0.35785472581467576, "percentage": 35.78, "elapsed_time": "15:09:47", "remaining_time": "1 day, 3:12:40"} +{"current_steps": 3880, "total_steps": 10787, "loss": 0.06902355551719666, "lr": 7.41195145634802e-05, "epoch": 0.3597088953784824, "percentage": 35.97, "elapsed_time": "15:14:29", "remaining_time": "1 day, 3:07:55"} +{"current_steps": 3900, "total_steps": 10787, "loss": 0.0672761082649231, "lr": 7.385606890304052e-05, "epoch": 0.36156306494228896, "percentage": 36.15, "elapsed_time": "15:19:11", "remaining_time": "1 day, 3:03:11"} +{"current_steps": 3920, "total_steps": 10787, "loss": 0.06806289553642272, "lr": 7.359176295262711e-05, "epoch": 0.3634172345060956, "percentage": 36.34, "elapsed_time": "15:23:52", "remaining_time": "1 day, 2:58:25"} +{"current_steps": 3940, "total_steps": 10787, "loss": 0.06858486533164979, "lr": 7.332660624355715e-05, "epoch": 0.3652714040699022, "percentage": 36.53, "elapsed_time": "15:28:34", "remaining_time": "1 day, 2:53:41"} +{"current_steps": 3960, "total_steps": 10787, "loss": 0.06711235046386718, "lr": 7.306060833782759e-05, "epoch": 0.3671255736337088, "percentage": 36.71, "elapsed_time": "15:33:16", "remaining_time": "1 day, 2:48:56"} +{"current_steps": 3980, "total_steps": 10787, "loss": 0.07175731658935547, "lr": 7.279377882777036e-05, "epoch": 0.3689797431975154, "percentage": 36.9, "elapsed_time": "15:37:57", "remaining_time": "1 day, 2:44:11"} +{"current_steps": 4000, "total_steps": 10787, "loss": 0.06841775178909301, "lr": 7.252612733570642e-05, "epoch": 0.37083391276132205, "percentage": 37.08, "elapsed_time": "15:42:39", "remaining_time": "1 day, 2:39:27"} +{"current_steps": 4020, "total_steps": 10787, "loss": 0.06980134844779969, "lr": 7.225766351359881e-05, "epoch": 0.3726880823251286, "percentage": 37.27, "elapsed_time": "15:48:51", "remaining_time": "1 day, 2:37:15"} +{"current_steps": 4040, "total_steps": 10787, "loss": 0.06585143804550171, "lr": 7.198839704270454e-05, "epoch": 0.37454225188893525, "percentage": 37.45, "elapsed_time": "15:53:33", "remaining_time": "1 day, 2:32:29"} +{"current_steps": 4060, "total_steps": 10787, "loss": 0.06848374009132385, "lr": 7.171833763322553e-05, "epoch": 0.3763964214527419, "percentage": 37.64, "elapsed_time": "15:58:15", "remaining_time": "1 day, 2:27:43"} +{"current_steps": 4080, "total_steps": 10787, "loss": 0.06790245175361634, "lr": 7.144749502395832e-05, "epoch": 0.37825059101654845, "percentage": 37.82, "elapsed_time": "16:02:56", "remaining_time": "1 day, 2:22:57"} +{"current_steps": 4100, "total_steps": 10787, "loss": 0.06954320073127747, "lr": 7.1175878981943e-05, "epoch": 0.3801047605803551, "percentage": 38.01, "elapsed_time": "16:07:38", "remaining_time": "1 day, 2:18:12"} +{"current_steps": 4120, "total_steps": 10787, "loss": 0.06869494915008545, "lr": 7.090349930211094e-05, "epoch": 0.38195893014416166, "percentage": 38.19, "elapsed_time": "16:12:20", "remaining_time": "1 day, 2:13:26"} +{"current_steps": 4140, "total_steps": 10787, "loss": 0.06774266958236694, "lr": 7.063036580693159e-05, "epoch": 0.3838130997079683, "percentage": 38.38, "elapsed_time": "16:17:02", "remaining_time": "1 day, 2:08:41"} +{"current_steps": 4160, "total_steps": 10787, "loss": 0.06900098323822021, "lr": 7.035648834605821e-05, "epoch": 0.3856672692717749, "percentage": 38.56, "elapsed_time": "16:21:44", "remaining_time": "1 day, 2:03:56"} +{"current_steps": 4180, "total_steps": 10787, "loss": 0.06982098817825318, "lr": 7.008187679597276e-05, "epoch": 0.3875214388355815, "percentage": 38.75, "elapsed_time": "16:26:26", "remaining_time": "1 day, 1:59:10"} +{"current_steps": 4200, "total_steps": 10787, "loss": 0.06795721054077149, "lr": 6.980654105962965e-05, "epoch": 0.3893756083993881, "percentage": 38.94, "elapsed_time": "16:31:07", "remaining_time": "1 day, 1:54:25"} +{"current_steps": 4220, "total_steps": 10787, "loss": 0.07044395208358764, "lr": 6.95304910660987e-05, "epoch": 0.39122977796319475, "percentage": 39.12, "elapsed_time": "16:35:49", "remaining_time": "1 day, 1:49:40"} +{"current_steps": 4240, "total_steps": 10787, "loss": 0.06826889514923096, "lr": 6.9253736770207e-05, "epoch": 0.3930839475270013, "percentage": 39.31, "elapsed_time": "16:40:31", "remaining_time": "1 day, 1:44:54"} +{"current_steps": 4260, "total_steps": 10787, "loss": 0.06704115867614746, "lr": 6.897628815218004e-05, "epoch": 0.39493811709080795, "percentage": 39.49, "elapsed_time": "16:45:12", "remaining_time": "1 day, 1:40:09"} +{"current_steps": 4280, "total_steps": 10787, "loss": 0.06963608860969543, "lr": 6.869815521728167e-05, "epoch": 0.3967922866546146, "percentage": 39.68, "elapsed_time": "16:49:54", "remaining_time": "1 day, 1:35:23"} +{"current_steps": 4300, "total_steps": 10787, "loss": 0.07049011588096618, "lr": 6.841934799545337e-05, "epoch": 0.39864645621842115, "percentage": 39.86, "elapsed_time": "16:54:36", "remaining_time": "1 day, 1:30:38"} +{"current_steps": 4320, "total_steps": 10787, "loss": 0.06666951179504395, "lr": 6.813987654095258e-05, "epoch": 0.4005006257822278, "percentage": 40.05, "elapsed_time": "16:59:18", "remaining_time": "1 day, 1:25:53"} +{"current_steps": 4340, "total_steps": 10787, "loss": 0.06822763085365295, "lr": 6.785975093199001e-05, "epoch": 0.4023547953460344, "percentage": 40.23, "elapsed_time": "17:04:00", "remaining_time": "1 day, 1:21:08"} +{"current_steps": 4360, "total_steps": 10787, "loss": 0.06750587821006775, "lr": 6.757898127036638e-05, "epoch": 0.404208964909841, "percentage": 40.42, "elapsed_time": "17:08:42", "remaining_time": "1 day, 1:16:23"} +{"current_steps": 4380, "total_steps": 10787, "loss": 0.06976407766342163, "lr": 6.729757768110792e-05, "epoch": 0.4060631344736476, "percentage": 40.6, "elapsed_time": "17:13:23", "remaining_time": "1 day, 1:11:38"} +{"current_steps": 4400, "total_steps": 10787, "loss": 0.06885499358177186, "lr": 6.701555031210148e-05, "epoch": 0.40791730403745424, "percentage": 40.79, "elapsed_time": "17:18:05", "remaining_time": "1 day, 1:06:53"} +{"current_steps": 4420, "total_steps": 10787, "loss": 0.06657370328903198, "lr": 6.673290933372835e-05, "epoch": 0.4097714736012608, "percentage": 40.98, "elapsed_time": "17:22:47", "remaining_time": "1 day, 1:02:07"} +{"current_steps": 4440, "total_steps": 10787, "loss": 0.06978561878204345, "lr": 6.644966493849768e-05, "epoch": 0.41162564316506745, "percentage": 41.16, "elapsed_time": "17:27:28", "remaining_time": "1 day, 0:57:22"} +{"current_steps": 4460, "total_steps": 10787, "loss": 0.06789119243621826, "lr": 6.61658273406788e-05, "epoch": 0.4134798127288741, "percentage": 41.35, "elapsed_time": "17:32:10", "remaining_time": "1 day, 0:52:37"} +{"current_steps": 4480, "total_steps": 10787, "loss": 0.06801660060882568, "lr": 6.588140677593293e-05, "epoch": 0.41533398229268065, "percentage": 41.53, "elapsed_time": "17:36:51", "remaining_time": "1 day, 0:47:51"} +{"current_steps": 4500, "total_steps": 10787, "loss": 0.0674366295337677, "lr": 6.55964135009441e-05, "epoch": 0.4171881518564873, "percentage": 41.72, "elapsed_time": "17:41:33", "remaining_time": "1 day, 0:43:06"} +{"current_steps": 4520, "total_steps": 10787, "loss": 0.06703794598579407, "lr": 6.531085779304918e-05, "epoch": 0.4190423214202939, "percentage": 41.9, "elapsed_time": "17:46:14", "remaining_time": "1 day, 0:38:21"} +{"current_steps": 4540, "total_steps": 10787, "loss": 0.06836413145065308, "lr": 6.502474994986734e-05, "epoch": 0.4208964909841005, "percentage": 42.09, "elapsed_time": "17:50:56", "remaining_time": "1 day, 0:33:36"} +{"current_steps": 4560, "total_steps": 10787, "loss": 0.06563597917556763, "lr": 6.473810028892865e-05, "epoch": 0.4227506605479071, "percentage": 42.27, "elapsed_time": "17:55:37", "remaining_time": "1 day, 0:28:50"} +{"current_steps": 4580, "total_steps": 10787, "loss": 0.06778264045715332, "lr": 6.445091914730213e-05, "epoch": 0.42460483011171374, "percentage": 42.46, "elapsed_time": "18:00:19", "remaining_time": "1 day, 0:24:05"} +{"current_steps": 4600, "total_steps": 10787, "loss": 0.06670353412628174, "lr": 6.416321688122278e-05, "epoch": 0.4264589996755203, "percentage": 42.64, "elapsed_time": "18:05:00", "remaining_time": "1 day, 0:19:19"} +{"current_steps": 4620, "total_steps": 10787, "loss": 0.06842938661575318, "lr": 6.387500386571827e-05, "epoch": 0.42831316923932694, "percentage": 42.83, "elapsed_time": "18:09:41", "remaining_time": "1 day, 0:14:34"} +{"current_steps": 4640, "total_steps": 10787, "loss": 0.06564785242080688, "lr": 6.358629049423477e-05, "epoch": 0.43016733880313357, "percentage": 43.01, "elapsed_time": "18:14:23", "remaining_time": "1 day, 0:09:49"} +{"current_steps": 4660, "total_steps": 10787, "loss": 0.06799172163009644, "lr": 6.329708717826209e-05, "epoch": 0.43202150836694014, "percentage": 43.2, "elapsed_time": "18:19:04", "remaining_time": "1 day, 0:05:04"} +{"current_steps": 4680, "total_steps": 10787, "loss": 0.06615757346153259, "lr": 6.30074043469583e-05, "epoch": 0.4338756779307468, "percentage": 43.39, "elapsed_time": "18:23:45", "remaining_time": "1 day, 0:00:19"} +{"current_steps": 4700, "total_steps": 10787, "loss": 0.06634211540222168, "lr": 6.271725244677357e-05, "epoch": 0.4357298474945534, "percentage": 43.57, "elapsed_time": "18:28:27", "remaining_time": "23:55:33"} +{"current_steps": 4720, "total_steps": 10787, "loss": 0.06808164119720458, "lr": 6.24266419410735e-05, "epoch": 0.43758401705836, "percentage": 43.76, "elapsed_time": "18:33:08", "remaining_time": "23:50:48"} +{"current_steps": 4740, "total_steps": 10787, "loss": 0.06660630106925965, "lr": 6.213558330976177e-05, "epoch": 0.4394381866221666, "percentage": 43.94, "elapsed_time": "18:37:49", "remaining_time": "23:46:03"} +{"current_steps": 4760, "total_steps": 10787, "loss": 0.06852835416793823, "lr": 6.184408704890221e-05, "epoch": 0.44129235618597323, "percentage": 44.13, "elapsed_time": "18:42:31", "remaining_time": "23:41:18"} +{"current_steps": 4780, "total_steps": 10787, "loss": 0.0657484233379364, "lr": 6.155216367034035e-05, "epoch": 0.4431465257497798, "percentage": 44.31, "elapsed_time": "18:47:12", "remaining_time": "23:36:33"} +{"current_steps": 4800, "total_steps": 10787, "loss": 0.06651111841201782, "lr": 6.125982370132428e-05, "epoch": 0.44500069531358644, "percentage": 44.5, "elapsed_time": "18:51:54", "remaining_time": "23:31:49"} +{"current_steps": 4820, "total_steps": 10787, "loss": 0.06592975258827209, "lr": 6.0967077684124996e-05, "epoch": 0.446854864877393, "percentage": 44.68, "elapsed_time": "18:56:35", "remaining_time": "23:27:04"} +{"current_steps": 4840, "total_steps": 10787, "loss": 0.06635326147079468, "lr": 6.067393617565633e-05, "epoch": 0.44870903444119964, "percentage": 44.87, "elapsed_time": "19:01:17", "remaining_time": "23:22:19"} +{"current_steps": 4860, "total_steps": 10787, "loss": 0.06596879959106446, "lr": 6.03804097470942e-05, "epoch": 0.45056320400500627, "percentage": 45.05, "elapsed_time": "19:05:58", "remaining_time": "23:17:33"} +{"current_steps": 4880, "total_steps": 10787, "loss": 0.06706082224845886, "lr": 6.008650898349536e-05, "epoch": 0.45241737356881284, "percentage": 45.24, "elapsed_time": "19:10:39", "remaining_time": "23:12:49"} +{"current_steps": 4900, "total_steps": 10787, "loss": 0.06731083393096923, "lr": 5.9792244483415717e-05, "epoch": 0.45427154313261947, "percentage": 45.43, "elapsed_time": "19:15:21", "remaining_time": "23:08:04"} +{"current_steps": 4920, "total_steps": 10787, "loss": 0.06804193258285522, "lr": 5.9497626858528156e-05, "epoch": 0.4561257126964261, "percentage": 45.61, "elapsed_time": "19:20:02", "remaining_time": "23:03:19"} +{"current_steps": 4940, "total_steps": 10787, "loss": 0.06767497062683106, "lr": 5.92026667332398e-05, "epoch": 0.4579798822602327, "percentage": 45.8, "elapsed_time": "19:24:44", "remaining_time": "22:58:35"} +{"current_steps": 4960, "total_steps": 10787, "loss": 0.06706864833831787, "lr": 5.890737474430892e-05, "epoch": 0.4598340518240393, "percentage": 45.98, "elapsed_time": "19:29:25", "remaining_time": "22:53:50"} +{"current_steps": 4980, "total_steps": 10787, "loss": 0.06532019376754761, "lr": 5.8611761540461386e-05, "epoch": 0.46168822138784593, "percentage": 46.17, "elapsed_time": "19:34:07", "remaining_time": "22:49:05"} +{"current_steps": 5000, "total_steps": 10787, "loss": 0.0650861382484436, "lr": 5.831583778200656e-05, "epoch": 0.4635423909516525, "percentage": 46.35, "elapsed_time": "19:38:48", "remaining_time": "22:44:21"} +{"current_steps": 5020, "total_steps": 10787, "loss": 0.06561164855957032, "lr": 5.801961414045299e-05, "epoch": 0.46539656051545913, "percentage": 46.54, "elapsed_time": "19:45:02", "remaining_time": "22:41:22"} +{"current_steps": 5040, "total_steps": 10787, "loss": 0.06795594096183777, "lr": 5.772310129812345e-05, "epoch": 0.46725073007926576, "percentage": 46.72, "elapsed_time": "19:49:43", "remaining_time": "22:36:36"} +{"current_steps": 5060, "total_steps": 10787, "loss": 0.06659960150718688, "lr": 5.742630994776982e-05, "epoch": 0.46910489964307234, "percentage": 46.91, "elapsed_time": "19:54:24", "remaining_time": "22:31:51"} +{"current_steps": 5080, "total_steps": 10787, "loss": 0.06613020896911621, "lr": 5.712925079218741e-05, "epoch": 0.47095906920687897, "percentage": 47.09, "elapsed_time": "19:59:06", "remaining_time": "22:27:05"} +{"current_steps": 5100, "total_steps": 10787, "loss": 0.06645833253860474, "lr": 5.683193454382909e-05, "epoch": 0.4728132387706856, "percentage": 47.28, "elapsed_time": "20:03:47", "remaining_time": "22:22:20"} +{"current_steps": 5120, "total_steps": 10787, "loss": 0.06557634472846985, "lr": 5.6534371924418913e-05, "epoch": 0.47466740833449217, "percentage": 47.46, "elapsed_time": "20:08:28", "remaining_time": "22:17:35"} +{"current_steps": 5140, "total_steps": 10787, "loss": 0.06667708158493042, "lr": 5.623657366456545e-05, "epoch": 0.4765215778982988, "percentage": 47.65, "elapsed_time": "20:13:10", "remaining_time": "22:12:50"} +{"current_steps": 5160, "total_steps": 10787, "loss": 0.06924290657043457, "lr": 5.59385505033749e-05, "epoch": 0.4783757474621054, "percentage": 47.84, "elapsed_time": "20:17:51", "remaining_time": "22:08:04"} +{"current_steps": 5180, "total_steps": 10787, "loss": 0.06771377325057984, "lr": 5.564031318806376e-05, "epoch": 0.480229917025912, "percentage": 48.02, "elapsed_time": "20:22:32", "remaining_time": "22:03:19"} +{"current_steps": 5200, "total_steps": 10787, "loss": 0.06644275188446044, "lr": 5.534187247357131e-05, "epoch": 0.48208408658971863, "percentage": 48.21, "elapsed_time": "20:27:14", "remaining_time": "21:58:34"} +{"current_steps": 5220, "total_steps": 10787, "loss": 0.06886463165283203, "lr": 5.504323912217171e-05, "epoch": 0.48393825615352526, "percentage": 48.39, "elapsed_time": "20:31:55", "remaining_time": "21:53:49"} +{"current_steps": 5240, "total_steps": 10787, "loss": 0.06803133487701415, "lr": 5.474442390308598e-05, "epoch": 0.48579242571733183, "percentage": 48.58, "elapsed_time": "20:36:37", "remaining_time": "21:49:04"} +{"current_steps": 5260, "total_steps": 10787, "loss": 0.06640726327896118, "lr": 5.444543759209354e-05, "epoch": 0.48764659528113846, "percentage": 48.76, "elapsed_time": "20:41:19", "remaining_time": "21:44:19"} +{"current_steps": 5280, "total_steps": 10787, "loss": 0.06845622062683106, "lr": 5.414629097114371e-05, "epoch": 0.4895007648449451, "percentage": 48.95, "elapsed_time": "20:46:00", "remaining_time": "21:39:34"} +{"current_steps": 5300, "total_steps": 10787, "loss": 0.06699745655059815, "lr": 5.384699482796686e-05, "epoch": 0.49135493440875166, "percentage": 49.13, "elapsed_time": "20:50:41", "remaining_time": "21:34:49"} +{"current_steps": 5320, "total_steps": 10787, "loss": 0.06719425320625305, "lr": 5.354755995568534e-05, "epoch": 0.4932091039725583, "percentage": 49.32, "elapsed_time": "20:55:23", "remaining_time": "21:30:04"} +{"current_steps": 5340, "total_steps": 10787, "loss": 0.06554273366928101, "lr": 5.3247997152424366e-05, "epoch": 0.4950632735363649, "percentage": 49.5, "elapsed_time": "21:00:04", "remaining_time": "21:25:19"} +{"current_steps": 5360, "total_steps": 10787, "loss": 0.0648796796798706, "lr": 5.2948317220922506e-05, "epoch": 0.4969174431001715, "percentage": 49.69, "elapsed_time": "21:04:46", "remaining_time": "21:20:34"} +{"current_steps": 5380, "total_steps": 10787, "loss": 0.06562695503234864, "lr": 5.26485309681422e-05, "epoch": 0.4987716126639781, "percentage": 49.87, "elapsed_time": "21:09:27", "remaining_time": "21:15:49"} +{"current_steps": 5400, "total_steps": 10787, "loss": 0.06633292436599732, "lr": 5.2348649204879993e-05, "epoch": 0.5006257822277848, "percentage": 50.06, "elapsed_time": "21:14:08", "remaining_time": "21:11:04"} +{"current_steps": 5420, "total_steps": 10787, "loss": 0.06479262113571167, "lr": 5.204868274537673e-05, "epoch": 0.5024799517915913, "percentage": 50.25, "elapsed_time": "21:18:50", "remaining_time": "21:06:19"} +{"current_steps": 5440, "total_steps": 10787, "loss": 0.0654104232788086, "lr": 5.1748642406927506e-05, "epoch": 0.5043341213553979, "percentage": 50.43, "elapsed_time": "21:23:31", "remaining_time": "21:01:34"} +{"current_steps": 5460, "total_steps": 10787, "loss": 0.06632285118103028, "lr": 5.1448539009491635e-05, "epoch": 0.5061882909192046, "percentage": 50.62, "elapsed_time": "21:28:12", "remaining_time": "20:56:50"} +{"current_steps": 5480, "total_steps": 10787, "loss": 0.06753811836242676, "lr": 5.114838337530244e-05, "epoch": 0.5080424604830112, "percentage": 50.8, "elapsed_time": "21:32:53", "remaining_time": "20:52:05"} +{"current_steps": 5500, "total_steps": 10787, "loss": 0.06613025069236755, "lr": 5.084818632847701e-05, "epoch": 0.5098966300468177, "percentage": 50.99, "elapsed_time": "21:37:35", "remaining_time": "20:47:20"} +{"current_steps": 5520, "total_steps": 10787, "loss": 0.06611216068267822, "lr": 5.054795869462581e-05, "epoch": 0.5117507996106244, "percentage": 51.17, "elapsed_time": "21:42:17", "remaining_time": "20:42:35"} +{"current_steps": 5540, "total_steps": 10787, "loss": 0.06571578383445739, "lr": 5.024771130046234e-05, "epoch": 0.513604969174431, "percentage": 51.36, "elapsed_time": "21:46:58", "remaining_time": "20:37:51"} +{"current_steps": 5560, "total_steps": 10787, "loss": 0.06566253900527955, "lr": 4.994745497341269e-05, "epoch": 0.5154591387382376, "percentage": 51.54, "elapsed_time": "21:51:40", "remaining_time": "20:33:06"} +{"current_steps": 5580, "total_steps": 10787, "loss": 0.06430123448371887, "lr": 4.964720054122509e-05, "epoch": 0.5173133083020443, "percentage": 51.73, "elapsed_time": "21:56:21", "remaining_time": "20:28:22"} +{"current_steps": 5600, "total_steps": 10787, "loss": 0.06554259061813354, "lr": 4.934695883157943e-05, "epoch": 0.5191674778658508, "percentage": 51.91, "elapsed_time": "22:01:03", "remaining_time": "20:23:37"} +{"current_steps": 5620, "total_steps": 10787, "loss": 0.06661000251770019, "lr": 4.9046740671696804e-05, "epoch": 0.5210216474296574, "percentage": 52.1, "elapsed_time": "22:05:45", "remaining_time": "20:18:53"} +{"current_steps": 5640, "total_steps": 10787, "loss": 0.0648884654045105, "lr": 4.874655688794908e-05, "epoch": 0.5228758169934641, "percentage": 52.29, "elapsed_time": "22:10:26", "remaining_time": "20:14:08"} +{"current_steps": 5660, "total_steps": 10787, "loss": 0.06492191553115845, "lr": 4.844641830546842e-05, "epoch": 0.5247299865572707, "percentage": 52.47, "elapsed_time": "22:15:07", "remaining_time": "20:09:23"} +{"current_steps": 5680, "total_steps": 10787, "loss": 0.06522760391235352, "lr": 4.8146335747757e-05, "epoch": 0.5265841561210772, "percentage": 52.66, "elapsed_time": "22:19:48", "remaining_time": "20:04:39"} +{"current_steps": 5700, "total_steps": 10787, "loss": 0.06443318128585815, "lr": 4.784632003629662e-05, "epoch": 0.5284383256848839, "percentage": 52.84, "elapsed_time": "22:24:29", "remaining_time": "19:59:54"} +{"current_steps": 5720, "total_steps": 10787, "loss": 0.06498017311096191, "lr": 4.754638199015851e-05, "epoch": 0.5302924952486905, "percentage": 53.03, "elapsed_time": "22:29:10", "remaining_time": "19:55:09"} +{"current_steps": 5740, "total_steps": 10787, "loss": 0.0655935525894165, "lr": 4.724653242561314e-05, "epoch": 0.5321466648124971, "percentage": 53.21, "elapsed_time": "22:33:51", "remaining_time": "19:50:24"} +{"current_steps": 5760, "total_steps": 10787, "loss": 0.06374808549880981, "lr": 4.694678215574023e-05, "epoch": 0.5340008343763037, "percentage": 53.4, "elapsed_time": "22:38:32", "remaining_time": "19:45:39"} +{"current_steps": 5780, "total_steps": 10787, "loss": 0.06397829055786133, "lr": 4.664714199003867e-05, "epoch": 0.5358550039401103, "percentage": 53.58, "elapsed_time": "22:43:13", "remaining_time": "19:40:54"} +{"current_steps": 5800, "total_steps": 10787, "loss": 0.06379647254943847, "lr": 4.634762273403692e-05, "epoch": 0.5377091735039169, "percentage": 53.77, "elapsed_time": "22:47:54", "remaining_time": "19:36:10"} +{"current_steps": 5820, "total_steps": 10787, "loss": 0.06524479389190674, "lr": 4.604823518890315e-05, "epoch": 0.5395633430677236, "percentage": 53.95, "elapsed_time": "22:52:35", "remaining_time": "19:31:25"} +{"current_steps": 5840, "total_steps": 10787, "loss": 0.063930743932724, "lr": 4.5748990151055876e-05, "epoch": 0.5414175126315302, "percentage": 54.14, "elapsed_time": "22:57:16", "remaining_time": "19:26:40"} +{"current_steps": 5860, "total_steps": 10787, "loss": 0.06565963625907897, "lr": 4.5449898411774504e-05, "epoch": 0.5432716821953367, "percentage": 54.32, "elapsed_time": "23:01:58", "remaining_time": "19:21:56"} +{"current_steps": 5880, "total_steps": 10787, "loss": 0.06600631475448608, "lr": 4.515097075681029e-05, "epoch": 0.5451258517591434, "percentage": 54.51, "elapsed_time": "23:06:39", "remaining_time": "19:17:11"} +{"current_steps": 5900, "total_steps": 10787, "loss": 0.06486299037933349, "lr": 4.485221796599729e-05, "epoch": 0.54698002132295, "percentage": 54.7, "elapsed_time": "23:11:20", "remaining_time": "19:12:27"} +{"current_steps": 5920, "total_steps": 10787, "loss": 0.06194999217987061, "lr": 4.455365081286371e-05, "epoch": 0.5488341908867566, "percentage": 54.88, "elapsed_time": "23:16:01", "remaining_time": "19:07:42"} +{"current_steps": 5940, "total_steps": 10787, "loss": 0.06475620269775391, "lr": 4.425528006424329e-05, "epoch": 0.5506883604505632, "percentage": 55.07, "elapsed_time": "23:20:42", "remaining_time": "19:02:57"} +{"current_steps": 5960, "total_steps": 10787, "loss": 0.06375322341918946, "lr": 4.395711647988714e-05, "epoch": 0.5525425300143698, "percentage": 55.25, "elapsed_time": "23:25:23", "remaining_time": "18:58:13"} +{"current_steps": 5980, "total_steps": 10787, "loss": 0.0641134262084961, "lr": 4.365917081207566e-05, "epoch": 0.5543966995781764, "percentage": 55.44, "elapsed_time": "23:30:04", "remaining_time": "18:53:28"} +{"current_steps": 6000, "total_steps": 10787, "loss": 0.06496943831443787, "lr": 4.3361453805230814e-05, "epoch": 0.5562508691419831, "percentage": 55.62, "elapsed_time": "23:34:45", "remaining_time": "18:48:44"} +{"current_steps": 6020, "total_steps": 10787, "loss": 0.06265571117401122, "lr": 4.3063976195528666e-05, "epoch": 0.5581050387057896, "percentage": 55.81, "elapsed_time": "23:41:10", "remaining_time": "18:45:22"} +{"current_steps": 6040, "total_steps": 10787, "loss": 0.06494598984718322, "lr": 4.2766748710512225e-05, "epoch": 0.5599592082695962, "percentage": 55.99, "elapsed_time": "23:45:51", "remaining_time": "18:40:37"} +{"current_steps": 6060, "total_steps": 10787, "loss": 0.06517527103424073, "lr": 4.2469782068704566e-05, "epoch": 0.5618133778334029, "percentage": 56.18, "elapsed_time": "23:50:32", "remaining_time": "18:35:52"} +{"current_steps": 6080, "total_steps": 10787, "loss": 0.06466827392578126, "lr": 4.217308697922236e-05, "epoch": 0.5636675473972095, "percentage": 56.36, "elapsed_time": "23:55:13", "remaining_time": "18:31:07"} +{"current_steps": 6100, "total_steps": 10787, "loss": 0.06504812240600585, "lr": 4.187667414138958e-05, "epoch": 0.565521716961016, "percentage": 56.55, "elapsed_time": "23:59:54", "remaining_time": "18:26:22"} +{"current_steps": 6120, "total_steps": 10787, "loss": 0.06338067054748535, "lr": 4.158055424435177e-05, "epoch": 0.5673758865248227, "percentage": 56.73, "elapsed_time": "1 day, 0:04:35", "remaining_time": "18:21:37"} +{"current_steps": 6140, "total_steps": 10787, "loss": 0.06424614191055297, "lr": 4.128473796669054e-05, "epoch": 0.5692300560886293, "percentage": 56.92, "elapsed_time": "1 day, 0:09:16", "remaining_time": "18:16:52"} +{"current_steps": 6160, "total_steps": 10787, "loss": 0.06370105147361756, "lr": 4.0989235976038463e-05, "epoch": 0.5710842256524359, "percentage": 57.11, "elapsed_time": "1 day, 0:13:57", "remaining_time": "18:12:07"} +{"current_steps": 6180, "total_steps": 10787, "loss": 0.06322758197784424, "lr": 4.069405892869439e-05, "epoch": 0.5729383952162426, "percentage": 57.29, "elapsed_time": "1 day, 0:18:38", "remaining_time": "18:07:22"} +{"current_steps": 6200, "total_steps": 10787, "loss": 0.06390318274497986, "lr": 4.0399217469239174e-05, "epoch": 0.5747925647800491, "percentage": 57.48, "elapsed_time": "1 day, 0:23:19", "remaining_time": "18:02:37"} +{"current_steps": 6220, "total_steps": 10787, "loss": 0.06472771167755127, "lr": 4.010472223015182e-05, "epoch": 0.5766467343438557, "percentage": 57.66, "elapsed_time": "1 day, 0:28:00", "remaining_time": "17:57:52"} +{"current_steps": 6240, "total_steps": 10787, "loss": 0.061773234605789186, "lr": 3.981058383142602e-05, "epoch": 0.5785009039076624, "percentage": 57.85, "elapsed_time": "1 day, 0:32:41", "remaining_time": "17:53:07"} +{"current_steps": 6260, "total_steps": 10787, "loss": 0.06225782036781311, "lr": 3.9516812880187227e-05, "epoch": 0.580355073471469, "percentage": 58.03, "elapsed_time": "1 day, 0:37:22", "remaining_time": "17:48:23"} +{"current_steps": 6280, "total_steps": 10787, "loss": 0.06542969346046448, "lr": 3.922341997031007e-05, "epoch": 0.5822092430352755, "percentage": 58.22, "elapsed_time": "1 day, 0:42:03", "remaining_time": "17:43:38"} +{"current_steps": 6300, "total_steps": 10787, "loss": 0.06415734887123108, "lr": 3.8930415682036435e-05, "epoch": 0.5840634125990822, "percentage": 58.4, "elapsed_time": "1 day, 0:46:44", "remaining_time": "17:38:53"} +{"current_steps": 6320, "total_steps": 10787, "loss": 0.06317670941352845, "lr": 3.863781058159381e-05, "epoch": 0.5859175821628888, "percentage": 58.59, "elapsed_time": "1 day, 0:51:25", "remaining_time": "17:34:08"} +{"current_steps": 6340, "total_steps": 10787, "loss": 0.06259400844573974, "lr": 3.834561522081434e-05, "epoch": 0.5877717517266954, "percentage": 58.77, "elapsed_time": "1 day, 0:56:07", "remaining_time": "17:29:24"} +{"current_steps": 6360, "total_steps": 10787, "loss": 0.06343435049057007, "lr": 3.805384013675423e-05, "epoch": 0.5896259212905021, "percentage": 58.96, "elapsed_time": "1 day, 1:00:48", "remaining_time": "17:24:40"} +{"current_steps": 6380, "total_steps": 10787, "loss": 0.0633241891860962, "lr": 3.776249585131382e-05, "epoch": 0.5914800908543086, "percentage": 59.15, "elapsed_time": "1 day, 1:05:29", "remaining_time": "17:19:55"} +{"current_steps": 6400, "total_steps": 10787, "loss": 0.0616495668888092, "lr": 3.747159287085812e-05, "epoch": 0.5933342604181152, "percentage": 59.33, "elapsed_time": "1 day, 1:10:10", "remaining_time": "17:15:10"} +{"current_steps": 6420, "total_steps": 10787, "loss": 0.06143069267272949, "lr": 3.7181141685837943e-05, "epoch": 0.5951884299819219, "percentage": 59.52, "elapsed_time": "1 day, 1:14:51", "remaining_time": "17:10:26"} +{"current_steps": 6440, "total_steps": 10787, "loss": 0.0653111219406128, "lr": 3.68911527704116e-05, "epoch": 0.5970425995457285, "percentage": 59.7, "elapsed_time": "1 day, 1:19:33", "remaining_time": "17:05:42"} +{"current_steps": 6460, "total_steps": 10787, "loss": 0.0612871527671814, "lr": 3.660163658206718e-05, "epoch": 0.598896769109535, "percentage": 59.89, "elapsed_time": "1 day, 1:24:15", "remaining_time": "17:00:57"} +{"current_steps": 6480, "total_steps": 10787, "loss": 0.06316884756088256, "lr": 3.631260356124545e-05, "epoch": 0.6007509386733417, "percentage": 60.07, "elapsed_time": "1 day, 1:28:56", "remaining_time": "16:56:13"} +{"current_steps": 6500, "total_steps": 10787, "loss": 0.06191706657409668, "lr": 3.6024064130963316e-05, "epoch": 0.6026051082371483, "percentage": 60.26, "elapsed_time": "1 day, 1:33:38", "remaining_time": "16:51:29"} +{"current_steps": 6520, "total_steps": 10787, "loss": 0.06327232122421264, "lr": 3.573602869643801e-05, "epoch": 0.6044592778009549, "percentage": 60.44, "elapsed_time": "1 day, 1:38:19", "remaining_time": "16:46:45"} +{"current_steps": 6540, "total_steps": 10787, "loss": 0.060802686214447024, "lr": 3.5448507644711806e-05, "epoch": 0.6063134473647616, "percentage": 60.63, "elapsed_time": "1 day, 1:43:01", "remaining_time": "16:42:01"} +{"current_steps": 6560, "total_steps": 10787, "loss": 0.06530459523200989, "lr": 3.516151134427745e-05, "epoch": 0.6081676169285681, "percentage": 60.81, "elapsed_time": "1 day, 1:47:42", "remaining_time": "16:37:17"} +{"current_steps": 6580, "total_steps": 10787, "loss": 0.06244962215423584, "lr": 3.487505014470437e-05, "epoch": 0.6100217864923747, "percentage": 61.0, "elapsed_time": "1 day, 1:52:24", "remaining_time": "16:32:32"} +{"current_steps": 6600, "total_steps": 10787, "loss": 0.06283918023109436, "lr": 3.458913437626524e-05, "epoch": 0.6118759560561814, "percentage": 61.18, "elapsed_time": "1 day, 1:57:05", "remaining_time": "16:27:48"} +{"current_steps": 6620, "total_steps": 10787, "loss": 0.06382766962051392, "lr": 3.4303774349563623e-05, "epoch": 0.613730125619988, "percentage": 61.37, "elapsed_time": "1 day, 2:01:47", "remaining_time": "16:23:04"} +{"current_steps": 6640, "total_steps": 10787, "loss": 0.06351471543312073, "lr": 3.4018980355162114e-05, "epoch": 0.6155842951837945, "percentage": 61.56, "elapsed_time": "1 day, 2:06:28", "remaining_time": "16:18:20"} +{"current_steps": 6660, "total_steps": 10787, "loss": 0.06272737979888916, "lr": 3.373476266321118e-05, "epoch": 0.6174384647476012, "percentage": 61.74, "elapsed_time": "1 day, 2:11:10", "remaining_time": "16:13:36"} +{"current_steps": 6680, "total_steps": 10787, "loss": 0.062467378377914426, "lr": 3.3451131523078915e-05, "epoch": 0.6192926343114078, "percentage": 61.93, "elapsed_time": "1 day, 2:15:51", "remaining_time": "16:08:52"} +{"current_steps": 6700, "total_steps": 10787, "loss": 0.06361099481582641, "lr": 3.316809716298134e-05, "epoch": 0.6211468038752144, "percentage": 62.11, "elapsed_time": "1 day, 2:20:32", "remaining_time": "16:04:08"} +{"current_steps": 6720, "total_steps": 10787, "loss": 0.06314346790313721, "lr": 3.288566978961356e-05, "epoch": 0.6230009734390209, "percentage": 62.3, "elapsed_time": "1 day, 2:25:14", "remaining_time": "15:59:23"} +{"current_steps": 6740, "total_steps": 10787, "loss": 0.06231023669242859, "lr": 3.260385958778174e-05, "epoch": 0.6248551430028276, "percentage": 62.48, "elapsed_time": "1 day, 2:29:55", "remaining_time": "15:54:39"} +{"current_steps": 6760, "total_steps": 10787, "loss": 0.06305838823318481, "lr": 3.23226767200358e-05, "epoch": 0.6267093125666342, "percentage": 62.67, "elapsed_time": "1 day, 2:34:36", "remaining_time": "15:49:55"} +{"current_steps": 6780, "total_steps": 10787, "loss": 0.06089724898338318, "lr": 3.204213132630296e-05, "epoch": 0.6285634821304408, "percentage": 62.85, "elapsed_time": "1 day, 2:39:17", "remaining_time": "15:45:11"} +{"current_steps": 6800, "total_steps": 10787, "loss": 0.062238240242004396, "lr": 3.176223352352201e-05, "epoch": 0.6304176516942475, "percentage": 63.04, "elapsed_time": "1 day, 2:43:59", "remaining_time": "15:40:27"} +{"current_steps": 6820, "total_steps": 10787, "loss": 0.060497474670410153, "lr": 3.148299340527857e-05, "epoch": 0.632271821258054, "percentage": 63.22, "elapsed_time": "1 day, 2:48:40", "remaining_time": "15:35:43"} +{"current_steps": 6840, "total_steps": 10787, "loss": 0.060766249895095825, "lr": 3.120442104144099e-05, "epoch": 0.6341259908218606, "percentage": 63.41, "elapsed_time": "1 day, 2:53:21", "remaining_time": "15:30:58"} +{"current_steps": 6860, "total_steps": 10787, "loss": 0.062382560968399045, "lr": 3.092652647779733e-05, "epoch": 0.6359801603856673, "percentage": 63.6, "elapsed_time": "1 day, 2:58:02", "remaining_time": "15:26:14"} +{"current_steps": 6880, "total_steps": 10787, "loss": 0.06159923672676086, "lr": 3.0649319735692984e-05, "epoch": 0.6378343299494739, "percentage": 63.78, "elapsed_time": "1 day, 3:02:43", "remaining_time": "15:21:30"} +{"current_steps": 6900, "total_steps": 10787, "loss": 0.06012410521507263, "lr": 3.037281081166938e-05, "epoch": 0.6396884995132804, "percentage": 63.97, "elapsed_time": "1 day, 3:07:24", "remaining_time": "15:16:46"} +{"current_steps": 6920, "total_steps": 10787, "loss": 0.062421870231628415, "lr": 3.0097009677103472e-05, "epoch": 0.6415426690770871, "percentage": 64.15, "elapsed_time": "1 day, 3:12:06", "remaining_time": "15:12:02"} +{"current_steps": 6940, "total_steps": 10787, "loss": 0.062098950147628784, "lr": 2.9821926277848082e-05, "epoch": 0.6433968386408937, "percentage": 64.34, "elapsed_time": "1 day, 3:16:47", "remaining_time": "15:07:18"} +{"current_steps": 6960, "total_steps": 10787, "loss": 0.06206930875778198, "lr": 2.9547570533873316e-05, "epoch": 0.6452510082047003, "percentage": 64.52, "elapsed_time": "1 day, 3:21:28", "remaining_time": "15:02:34"} +{"current_steps": 6980, "total_steps": 10787, "loss": 0.06005668640136719, "lr": 2.9273952338908805e-05, "epoch": 0.647105177768507, "percentage": 64.71, "elapsed_time": "1 day, 3:26:10", "remaining_time": "14:57:50"} +{"current_steps": 7000, "total_steps": 10787, "loss": 0.06390679478645325, "lr": 2.900108156008693e-05, "epoch": 0.6489593473323135, "percentage": 64.89, "elapsed_time": "1 day, 3:30:51", "remaining_time": "14:53:06"} +{"current_steps": 7020, "total_steps": 10787, "loss": 0.061896789073944095, "lr": 2.8728968037586966e-05, "epoch": 0.6508135168961201, "percentage": 65.08, "elapsed_time": "1 day, 3:37:05", "remaining_time": "14:49:12"} +{"current_steps": 7040, "total_steps": 10787, "loss": 0.06296419501304626, "lr": 2.8457621584280282e-05, "epoch": 0.6526676864599268, "percentage": 65.26, "elapsed_time": "1 day, 3:41:46", "remaining_time": "14:44:28"} +{"current_steps": 7060, "total_steps": 10787, "loss": 0.06295238733291626, "lr": 2.8187051985376412e-05, "epoch": 0.6545218560237334, "percentage": 65.45, "elapsed_time": "1 day, 3:46:28", "remaining_time": "14:39:44"} +{"current_steps": 7080, "total_steps": 10787, "loss": 0.06277818083763123, "lr": 2.7917268998070245e-05, "epoch": 0.6563760255875399, "percentage": 65.63, "elapsed_time": "1 day, 3:51:09", "remaining_time": "14:34:59"} +{"current_steps": 7100, "total_steps": 10787, "loss": 0.06296697854995728, "lr": 2.764828235119008e-05, "epoch": 0.6582301951513466, "percentage": 65.82, "elapsed_time": "1 day, 3:55:51", "remaining_time": "14:30:15"} +{"current_steps": 7120, "total_steps": 10787, "loss": 0.06177424788475037, "lr": 2.7380101744846898e-05, "epoch": 0.6600843647151532, "percentage": 66.01, "elapsed_time": "1 day, 4:00:32", "remaining_time": "14:25:31"} +{"current_steps": 7140, "total_steps": 10787, "loss": 0.06221094131469727, "lr": 2.7112736850084476e-05, "epoch": 0.6619385342789598, "percentage": 66.19, "elapsed_time": "1 day, 4:05:13", "remaining_time": "14:20:47"} +{"current_steps": 7160, "total_steps": 10787, "loss": 0.06288429498672485, "lr": 2.6846197308530662e-05, "epoch": 0.6637927038427665, "percentage": 66.38, "elapsed_time": "1 day, 4:09:55", "remaining_time": "14:16:03"} +{"current_steps": 7180, "total_steps": 10787, "loss": 0.061210185289382935, "lr": 2.6580492732049677e-05, "epoch": 0.665646873406573, "percentage": 66.56, "elapsed_time": "1 day, 4:14:36", "remaining_time": "14:11:18"} +{"current_steps": 7200, "total_steps": 10787, "loss": 0.060793828964233396, "lr": 2.631563270239551e-05, "epoch": 0.6675010429703796, "percentage": 66.75, "elapsed_time": "1 day, 4:19:17", "remaining_time": "14:06:34"} +{"current_steps": 7220, "total_steps": 10787, "loss": 0.06118553876876831, "lr": 2.6051626770866343e-05, "epoch": 0.6693552125341863, "percentage": 66.93, "elapsed_time": "1 day, 4:23:59", "remaining_time": "14:01:50"} +{"current_steps": 7240, "total_steps": 10787, "loss": 0.06138489246368408, "lr": 2.5788484457960155e-05, "epoch": 0.6712093820979929, "percentage": 67.12, "elapsed_time": "1 day, 4:28:40", "remaining_time": "13:57:06"} +{"current_steps": 7260, "total_steps": 10787, "loss": 0.06212824583053589, "lr": 2.552621525303144e-05, "epoch": 0.6730635516617994, "percentage": 67.3, "elapsed_time": "1 day, 4:33:21", "remaining_time": "13:52:22"} +{"current_steps": 7280, "total_steps": 10787, "loss": 0.059517890214920044, "lr": 2.5264828613948842e-05, "epoch": 0.6749177212256061, "percentage": 67.49, "elapsed_time": "1 day, 4:38:02", "remaining_time": "13:47:37"} +{"current_steps": 7300, "total_steps": 10787, "loss": 0.05914331078529358, "lr": 2.500433396675428e-05, "epoch": 0.6767718907894127, "percentage": 67.67, "elapsed_time": "1 day, 4:42:43", "remaining_time": "13:42:53"} +{"current_steps": 7320, "total_steps": 10787, "loss": 0.06060423851013184, "lr": 2.4744740705322912e-05, "epoch": 0.6786260603532193, "percentage": 67.86, "elapsed_time": "1 day, 4:47:24", "remaining_time": "13:38:09"} +{"current_steps": 7340, "total_steps": 10787, "loss": 0.059140574932098386, "lr": 2.448605819102442e-05, "epoch": 0.680480229917026, "percentage": 68.04, "elapsed_time": "1 day, 4:52:05", "remaining_time": "13:33:25"} +{"current_steps": 7360, "total_steps": 10787, "loss": 0.060806494951248166, "lr": 2.42282957523854e-05, "epoch": 0.6823343994808325, "percentage": 68.23, "elapsed_time": "1 day, 4:56:46", "remaining_time": "13:28:41"} +{"current_steps": 7380, "total_steps": 10787, "loss": 0.06241018772125244, "lr": 2.3971462684752983e-05, "epoch": 0.6841885690446391, "percentage": 68.42, "elapsed_time": "1 day, 5:01:27", "remaining_time": "13:23:57"} +{"current_steps": 7400, "total_steps": 10787, "loss": 0.06107102632522583, "lr": 2.371556824995962e-05, "epoch": 0.6860427386084458, "percentage": 68.6, "elapsed_time": "1 day, 5:06:09", "remaining_time": "13:19:13"} +{"current_steps": 7420, "total_steps": 10787, "loss": 0.061403405666351316, "lr": 2.3460621675989075e-05, "epoch": 0.6878969081722524, "percentage": 68.79, "elapsed_time": "1 day, 5:10:50", "remaining_time": "13:14:29"} +{"current_steps": 7440, "total_steps": 10787, "loss": 0.059847354888916016, "lr": 2.320663215664366e-05, "epoch": 0.6897510777360589, "percentage": 68.97, "elapsed_time": "1 day, 5:15:31", "remaining_time": "13:09:44"} +{"current_steps": 7460, "total_steps": 10787, "loss": 0.06029091477394104, "lr": 2.2953608851212687e-05, "epoch": 0.6916052472998656, "percentage": 69.16, "elapsed_time": "1 day, 5:20:12", "remaining_time": "13:05:00"} +{"current_steps": 7480, "total_steps": 10787, "loss": 0.06045289039611816, "lr": 2.270156088414217e-05, "epoch": 0.6934594168636722, "percentage": 69.34, "elapsed_time": "1 day, 5:24:53", "remaining_time": "13:00:16"} +{"current_steps": 7500, "total_steps": 10787, "loss": 0.06151350736618042, "lr": 2.2450497344705794e-05, "epoch": 0.6953135864274788, "percentage": 69.53, "elapsed_time": "1 day, 5:29:34", "remaining_time": "12:55:32"} +{"current_steps": 7520, "total_steps": 10787, "loss": 0.05916010141372681, "lr": 2.2200427286677077e-05, "epoch": 0.6971677559912854, "percentage": 69.71, "elapsed_time": "1 day, 5:34:16", "remaining_time": "12:50:48"} +{"current_steps": 7540, "total_steps": 10787, "loss": 0.06019682884216308, "lr": 2.195135972800299e-05, "epoch": 0.699021925555092, "percentage": 69.9, "elapsed_time": "1 day, 5:38:57", "remaining_time": "12:46:04"} +{"current_steps": 7560, "total_steps": 10787, "loss": 0.060142922401428225, "lr": 2.170330365047865e-05, "epoch": 0.7008760951188986, "percentage": 70.08, "elapsed_time": "1 day, 5:43:38", "remaining_time": "12:41:21"} +{"current_steps": 7580, "total_steps": 10787, "loss": 0.06119601726531983, "lr": 2.1456267999423468e-05, "epoch": 0.7027302646827053, "percentage": 70.27, "elapsed_time": "1 day, 5:48:19", "remaining_time": "12:36:37"} +{"current_steps": 7600, "total_steps": 10787, "loss": 0.05998234748840332, "lr": 2.1210261683358595e-05, "epoch": 0.7045844342465118, "percentage": 70.46, "elapsed_time": "1 day, 5:53:00", "remaining_time": "12:31:53"} +{"current_steps": 7620, "total_steps": 10787, "loss": 0.059972834587097165, "lr": 2.0965293573685595e-05, "epoch": 0.7064386038103184, "percentage": 70.64, "elapsed_time": "1 day, 5:57:41", "remaining_time": "12:27:09"} +{"current_steps": 7640, "total_steps": 10787, "loss": 0.061202061176300046, "lr": 2.072137250436657e-05, "epoch": 0.7082927733741251, "percentage": 70.83, "elapsed_time": "1 day, 6:02:22", "remaining_time": "12:22:25"} +{"current_steps": 7660, "total_steps": 10787, "loss": 0.05759580135345459, "lr": 2.0478507271605583e-05, "epoch": 0.7101469429379317, "percentage": 71.01, "elapsed_time": "1 day, 6:07:03", "remaining_time": "12:17:41"} +{"current_steps": 7680, "total_steps": 10787, "loss": 0.05981243848800659, "lr": 2.023670663353146e-05, "epoch": 0.7120011125017383, "percentage": 71.2, "elapsed_time": "1 day, 6:11:44", "remaining_time": "12:12:57"} +{"current_steps": 7700, "total_steps": 10787, "loss": 0.05943760871887207, "lr": 1.9995979309881975e-05, "epoch": 0.7138552820655449, "percentage": 71.38, "elapsed_time": "1 day, 6:16:26", "remaining_time": "12:08:13"} +{"current_steps": 7720, "total_steps": 10787, "loss": 0.05771678686141968, "lr": 1.9756333981689308e-05, "epoch": 0.7157094516293515, "percentage": 71.57, "elapsed_time": "1 day, 6:21:07", "remaining_time": "12:03:29"} +{"current_steps": 7740, "total_steps": 10787, "loss": 0.060441124439239505, "lr": 1.951777929096713e-05, "epoch": 0.7175636211931581, "percentage": 71.75, "elapsed_time": "1 day, 6:25:48", "remaining_time": "11:58:46"} +{"current_steps": 7760, "total_steps": 10787, "loss": 0.060588645935058597, "lr": 1.9280323840398872e-05, "epoch": 0.7194177907569648, "percentage": 71.94, "elapsed_time": "1 day, 6:30:30", "remaining_time": "11:54:02"} +{"current_steps": 7780, "total_steps": 10787, "loss": 0.059179884195327756, "lr": 1.904397619302752e-05, "epoch": 0.7212719603207713, "percentage": 72.12, "elapsed_time": "1 day, 6:35:11", "remaining_time": "11:49:18"} +{"current_steps": 7800, "total_steps": 10787, "loss": 0.060727423429489134, "lr": 1.8808744871946794e-05, "epoch": 0.7231261298845779, "percentage": 72.31, "elapsed_time": "1 day, 6:39:52", "remaining_time": "11:44:34"} +{"current_steps": 7820, "total_steps": 10787, "loss": 0.05868118405342102, "lr": 1.8574638359993825e-05, "epoch": 0.7249802994483846, "percentage": 72.49, "elapsed_time": "1 day, 6:44:33", "remaining_time": "11:39:50"} +{"current_steps": 7840, "total_steps": 10787, "loss": 0.061199039220809937, "lr": 1.8341665099443235e-05, "epoch": 0.7268344690121912, "percentage": 72.68, "elapsed_time": "1 day, 6:49:14", "remaining_time": "11:35:07"} +{"current_steps": 7860, "total_steps": 10787, "loss": 0.06120600700378418, "lr": 1.8109833491702695e-05, "epoch": 0.7286886385759977, "percentage": 72.87, "elapsed_time": "1 day, 6:53:56", "remaining_time": "11:30:23"} +{"current_steps": 7880, "total_steps": 10787, "loss": 0.05963542461395264, "lr": 1.7879151897009943e-05, "epoch": 0.7305428081398044, "percentage": 73.05, "elapsed_time": "1 day, 6:58:37", "remaining_time": "11:25:39"} +{"current_steps": 7900, "total_steps": 10787, "loss": 0.05993167161941528, "lr": 1.7649628634131326e-05, "epoch": 0.732396977703611, "percentage": 73.24, "elapsed_time": "1 day, 7:03:18", "remaining_time": "11:20:56"} +{"current_steps": 7920, "total_steps": 10787, "loss": 0.05901572108268738, "lr": 1.74212719800618e-05, "epoch": 0.7342511472674176, "percentage": 73.42, "elapsed_time": "1 day, 7:07:59", "remaining_time": "11:16:12"} +{"current_steps": 7940, "total_steps": 10787, "loss": 0.06098179817199707, "lr": 1.7194090169726417e-05, "epoch": 0.7361053168312243, "percentage": 73.61, "elapsed_time": "1 day, 7:12:41", "remaining_time": "11:11:28"} +{"current_steps": 7960, "total_steps": 10787, "loss": 0.058015406131744385, "lr": 1.6968091395683428e-05, "epoch": 0.7379594863950308, "percentage": 73.79, "elapsed_time": "1 day, 7:17:22", "remaining_time": "11:06:45"} +{"current_steps": 7980, "total_steps": 10787, "loss": 0.059897661209106445, "lr": 1.6743283807828776e-05, "epoch": 0.7398136559588374, "percentage": 73.98, "elapsed_time": "1 day, 7:22:04", "remaining_time": "11:02:01"} +{"current_steps": 8000, "total_steps": 10787, "loss": 0.06034721732139588, "lr": 1.6519675513102228e-05, "epoch": 0.7416678255226441, "percentage": 74.16, "elapsed_time": "1 day, 7:26:46", "remaining_time": "10:57:18"} +{"current_steps": 8020, "total_steps": 10787, "loss": 0.05882605314254761, "lr": 1.629727457519505e-05, "epoch": 0.7435219950864507, "percentage": 74.35, "elapsed_time": "1 day, 7:33:01", "remaining_time": "10:53:07"} +{"current_steps": 8040, "total_steps": 10787, "loss": 0.05778524875640869, "lr": 1.607608901425915e-05, "epoch": 0.7453761646502572, "percentage": 74.53, "elapsed_time": "1 day, 7:37:43", "remaining_time": "10:48:23"} +{"current_steps": 8060, "total_steps": 10787, "loss": 0.05960347652435303, "lr": 1.5856126806617932e-05, "epoch": 0.7472303342140639, "percentage": 74.72, "elapsed_time": "1 day, 7:42:24", "remaining_time": "10:43:39"} +{"current_steps": 8080, "total_steps": 10787, "loss": 0.05910018682479858, "lr": 1.5637395884478607e-05, "epoch": 0.7490845037778705, "percentage": 74.9, "elapsed_time": "1 day, 7:47:06", "remaining_time": "10:38:55"} +{"current_steps": 8100, "total_steps": 10787, "loss": 0.05863996744155884, "lr": 1.5419904135646156e-05, "epoch": 0.7509386733416771, "percentage": 75.09, "elapsed_time": "1 day, 7:51:47", "remaining_time": "10:34:11"} +{"current_steps": 8120, "total_steps": 10787, "loss": 0.06005077362060547, "lr": 1.5203659403238918e-05, "epoch": 0.7527928429054838, "percentage": 75.28, "elapsed_time": "1 day, 7:56:29", "remaining_time": "10:29:27"} +{"current_steps": 8140, "total_steps": 10787, "loss": 0.06016584038734436, "lr": 1.4988669485405654e-05, "epoch": 0.7546470124692903, "percentage": 75.46, "elapsed_time": "1 day, 8:01:10", "remaining_time": "10:24:44"} +{"current_steps": 8160, "total_steps": 10787, "loss": 0.06094483137130737, "lr": 1.4774942135044467e-05, "epoch": 0.7565011820330969, "percentage": 75.65, "elapsed_time": "1 day, 8:05:51", "remaining_time": "10:20:00"} +{"current_steps": 8180, "total_steps": 10787, "loss": 0.05919557809829712, "lr": 1.4562485059523123e-05, "epoch": 0.7583553515969035, "percentage": 75.83, "elapsed_time": "1 day, 8:10:32", "remaining_time": "10:15:16"} +{"current_steps": 8200, "total_steps": 10787, "loss": 0.05924775004386902, "lr": 1.4351305920401148e-05, "epoch": 0.7602095211607102, "percentage": 76.02, "elapsed_time": "1 day, 8:15:14", "remaining_time": "10:10:32"} +{"current_steps": 8220, "total_steps": 10787, "loss": 0.05741736888885498, "lr": 1.4141412333153531e-05, "epoch": 0.7620636907245167, "percentage": 76.2, "elapsed_time": "1 day, 8:19:55", "remaining_time": "10:05:48"} +{"current_steps": 8240, "total_steps": 10787, "loss": 0.06202120184898376, "lr": 1.39328118668961e-05, "epoch": 0.7639178602883233, "percentage": 76.39, "elapsed_time": "1 day, 8:24:36", "remaining_time": "10:01:05"} +{"current_steps": 8260, "total_steps": 10787, "loss": 0.05924309492111206, "lr": 1.3725512044112555e-05, "epoch": 0.76577202985213, "percentage": 76.57, "elapsed_time": "1 day, 8:29:18", "remaining_time": "9:56:21"} +{"current_steps": 8280, "total_steps": 10787, "loss": 0.05931833982467651, "lr": 1.3519520340383202e-05, "epoch": 0.7676261994159366, "percentage": 76.76, "elapsed_time": "1 day, 8:33:59", "remaining_time": "9:51:37"} +{"current_steps": 8300, "total_steps": 10787, "loss": 0.05921122431755066, "lr": 1.3314844184115405e-05, "epoch": 0.7694803689797431, "percentage": 76.94, "elapsed_time": "1 day, 8:38:40", "remaining_time": "9:46:53"} +{"current_steps": 8320, "total_steps": 10787, "loss": 0.05935220122337341, "lr": 1.3111490956275663e-05, "epoch": 0.7713345385435498, "percentage": 77.13, "elapsed_time": "1 day, 8:43:21", "remaining_time": "9:42:09"} +{"current_steps": 8340, "total_steps": 10787, "loss": 0.0584735095500946, "lr": 1.2909467990123402e-05, "epoch": 0.7731887081073564, "percentage": 77.32, "elapsed_time": "1 day, 8:48:02", "remaining_time": "9:37:26"} +{"current_steps": 8360, "total_steps": 10787, "loss": 0.05790427327156067, "lr": 1.270878257094663e-05, "epoch": 0.775042877671163, "percentage": 77.5, "elapsed_time": "1 day, 8:52:43", "remaining_time": "9:32:42"} +{"current_steps": 8380, "total_steps": 10787, "loss": 0.05840156078338623, "lr": 1.2509441935799139e-05, "epoch": 0.7768970472349697, "percentage": 77.69, "elapsed_time": "1 day, 8:57:24", "remaining_time": "9:27:58"} +{"current_steps": 8400, "total_steps": 10787, "loss": 0.0588322639465332, "lr": 1.2311453273239548e-05, "epoch": 0.7787512167987762, "percentage": 77.87, "elapsed_time": "1 day, 9:02:05", "remaining_time": "9:23:14"} +{"current_steps": 8420, "total_steps": 10787, "loss": 0.05915929079055786, "lr": 1.2114823723072077e-05, "epoch": 0.7806053863625828, "percentage": 78.06, "elapsed_time": "1 day, 9:06:47", "remaining_time": "9:18:31"} +{"current_steps": 8440, "total_steps": 10787, "loss": 0.05861332416534424, "lr": 1.1919560376089062e-05, "epoch": 0.7824595559263895, "percentage": 78.24, "elapsed_time": "1 day, 9:11:28", "remaining_time": "9:13:47"} +{"current_steps": 8460, "total_steps": 10787, "loss": 0.05743967890739441, "lr": 1.1725670273815248e-05, "epoch": 0.7843137254901961, "percentage": 78.43, "elapsed_time": "1 day, 9:16:09", "remaining_time": "9:09:03"} +{"current_steps": 8480, "total_steps": 10787, "loss": 0.056289541721344, "lr": 1.1533160408253879e-05, "epoch": 0.7861678950540026, "percentage": 78.61, "elapsed_time": "1 day, 9:20:50", "remaining_time": "9:04:20"} +{"current_steps": 8500, "total_steps": 10787, "loss": 0.05721364617347717, "lr": 1.134203772163453e-05, "epoch": 0.7880220646178093, "percentage": 78.8, "elapsed_time": "1 day, 9:25:31", "remaining_time": "8:59:36"} +{"current_steps": 8520, "total_steps": 10787, "loss": 0.058383059501647946, "lr": 1.1152309106162777e-05, "epoch": 0.7898762341816159, "percentage": 78.98, "elapsed_time": "1 day, 9:30:12", "remaining_time": "8:54:52"} +{"current_steps": 8540, "total_steps": 10787, "loss": 0.059176528453826906, "lr": 1.096398140377164e-05, "epoch": 0.7917304037454225, "percentage": 79.17, "elapsed_time": "1 day, 9:34:54", "remaining_time": "8:50:09"} +{"current_steps": 8560, "total_steps": 10787, "loss": 0.05802996158599853, "lr": 1.0777061405874872e-05, "epoch": 0.7935845733092292, "percentage": 79.35, "elapsed_time": "1 day, 9:39:35", "remaining_time": "8:45:25"} +{"current_steps": 8580, "total_steps": 10787, "loss": 0.05956486463546753, "lr": 1.0591555853121998e-05, "epoch": 0.7954387428730357, "percentage": 79.54, "elapsed_time": "1 day, 9:44:17", "remaining_time": "8:40:41"} +{"current_steps": 8600, "total_steps": 10787, "loss": 0.05859973430633545, "lr": 1.0407471435155313e-05, "epoch": 0.7972929124368423, "percentage": 79.73, "elapsed_time": "1 day, 9:48:58", "remaining_time": "8:35:58"} +{"current_steps": 8620, "total_steps": 10787, "loss": 0.05868813991546631, "lr": 1.0224814790368558e-05, "epoch": 0.799147082000649, "percentage": 79.91, "elapsed_time": "1 day, 9:53:40", "remaining_time": "8:31:14"} +{"current_steps": 8640, "total_steps": 10787, "loss": 0.057529407739639285, "lr": 1.0043592505667632e-05, "epoch": 0.8010012515644556, "percentage": 80.1, "elapsed_time": "1 day, 9:58:21", "remaining_time": "8:26:31"} +{"current_steps": 8660, "total_steps": 10787, "loss": 0.057827317714691163, "lr": 9.863811116232946e-06, "epoch": 0.8028554211282621, "percentage": 80.28, "elapsed_time": "1 day, 10:03:03", "remaining_time": "8:21:47"} +{"current_steps": 8680, "total_steps": 10787, "loss": 0.05748317241668701, "lr": 9.685477105283825e-06, "epoch": 0.8047095906920688, "percentage": 80.47, "elapsed_time": "1 day, 10:07:44", "remaining_time": "8:17:04"} +{"current_steps": 8700, "total_steps": 10787, "loss": 0.05913045406341553, "lr": 9.508596903844668e-06, "epoch": 0.8065637602558754, "percentage": 80.65, "elapsed_time": "1 day, 10:12:25", "remaining_time": "8:12:20"} +{"current_steps": 8720, "total_steps": 10787, "loss": 0.05958133339881897, "lr": 9.333176890513095e-06, "epoch": 0.808417929819682, "percentage": 80.84, "elapsed_time": "1 day, 10:17:06", "remaining_time": "8:07:37"} +{"current_steps": 8740, "total_steps": 10787, "loss": 0.05868912935256958, "lr": 9.15922339122986e-06, "epoch": 0.8102720993834887, "percentage": 81.02, "elapsed_time": "1 day, 10:21:48", "remaining_time": "8:02:53"} +{"current_steps": 8760, "total_steps": 10787, "loss": 0.05822650790214538, "lr": 8.986742679050764e-06, "epoch": 0.8121262689472952, "percentage": 81.21, "elapsed_time": "1 day, 10:26:29", "remaining_time": "7:58:10"} +{"current_steps": 8780, "total_steps": 10787, "loss": 0.05828083753585815, "lr": 8.815740973920411e-06, "epoch": 0.8139804385111018, "percentage": 81.39, "elapsed_time": "1 day, 10:31:10", "remaining_time": "7:53:26"} +{"current_steps": 8800, "total_steps": 10787, "loss": 0.05864385366439819, "lr": 8.646224442447937e-06, "epoch": 0.8158346080749085, "percentage": 81.58, "elapsed_time": "1 day, 10:35:52", "remaining_time": "7:48:43"} +{"current_steps": 8820, "total_steps": 10787, "loss": 0.060294324159622194, "lr": 8.478199197684627e-06, "epoch": 0.8176887776387151, "percentage": 81.77, "elapsed_time": "1 day, 10:40:33", "remaining_time": "7:43:59"} +{"current_steps": 8840, "total_steps": 10787, "loss": 0.058967453241348264, "lr": 8.311671298903439e-06, "epoch": 0.8195429472025216, "percentage": 81.95, "elapsed_time": "1 day, 10:45:15", "remaining_time": "7:39:16"} +{"current_steps": 8860, "total_steps": 10787, "loss": 0.057421672344207766, "lr": 8.146646751380532e-06, "epoch": 0.8213971167663283, "percentage": 82.14, "elapsed_time": "1 day, 10:49:56", "remaining_time": "7:34:32"} +{"current_steps": 8880, "total_steps": 10787, "loss": 0.05738742351531982, "lr": 7.983131506178676e-06, "epoch": 0.8232512863301349, "percentage": 82.32, "elapsed_time": "1 day, 10:54:37", "remaining_time": "7:29:49"} +{"current_steps": 8900, "total_steps": 10787, "loss": 0.05822542905807495, "lr": 7.821131459932673e-06, "epoch": 0.8251054558939415, "percentage": 82.51, "elapsed_time": "1 day, 10:59:18", "remaining_time": "7:25:05"} +{"current_steps": 8920, "total_steps": 10787, "loss": 0.055188226699829104, "lr": 7.660652454636696e-06, "epoch": 0.8269596254577481, "percentage": 82.69, "elapsed_time": "1 day, 11:03:59", "remaining_time": "7:20:22"} +{"current_steps": 8940, "total_steps": 10787, "loss": 0.059385663270950316, "lr": 7.501700277433621e-06, "epoch": 0.8288137950215547, "percentage": 82.88, "elapsed_time": "1 day, 11:08:41", "remaining_time": "7:15:39"} +{"current_steps": 8960, "total_steps": 10787, "loss": 0.058476173877716066, "lr": 7.344280660406333e-06, "epoch": 0.8306679645853613, "percentage": 83.06, "elapsed_time": "1 day, 11:13:22", "remaining_time": "7:10:55"} +{"current_steps": 8980, "total_steps": 10787, "loss": 0.05890741944313049, "lr": 7.188399280371033e-06, "epoch": 0.832522134149168, "percentage": 83.25, "elapsed_time": "1 day, 11:18:03", "remaining_time": "7:06:12"} +{"current_steps": 9000, "total_steps": 10787, "loss": 0.057273268699645996, "lr": 7.034061758672489e-06, "epoch": 0.8343763037129746, "percentage": 83.43, "elapsed_time": "1 day, 11:22:45", "remaining_time": "7:01:29"} +{"current_steps": 9020, "total_steps": 10787, "loss": 0.06076174974441528, "lr": 6.881273660981352e-06, "epoch": 0.8362304732767811, "percentage": 83.62, "elapsed_time": "1 day, 11:28:57", "remaining_time": "6:57:03"} +{"current_steps": 9040, "total_steps": 10787, "loss": 0.05773304700851441, "lr": 6.730040497093437e-06, "epoch": 0.8380846428405878, "percentage": 83.8, "elapsed_time": "1 day, 11:33:38", "remaining_time": "6:52:19"} +{"current_steps": 9060, "total_steps": 10787, "loss": 0.057690989971160886, "lr": 6.580367720731029e-06, "epoch": 0.8399388124043944, "percentage": 83.99, "elapsed_time": "1 day, 11:38:19", "remaining_time": "6:47:36"} +{"current_steps": 9080, "total_steps": 10787, "loss": 0.05713052749633789, "lr": 6.4322607293462065e-06, "epoch": 0.841792981968201, "percentage": 84.18, "elapsed_time": "1 day, 11:43:00", "remaining_time": "6:42:52"} +{"current_steps": 9100, "total_steps": 10787, "loss": 0.05859750509262085, "lr": 6.285724863926224e-06, "epoch": 0.8436471515320076, "percentage": 84.36, "elapsed_time": "1 day, 11:47:41", "remaining_time": "6:38:09"} +{"current_steps": 9120, "total_steps": 10787, "loss": 0.05815015435218811, "lr": 6.140765408800869e-06, "epoch": 0.8455013210958142, "percentage": 84.55, "elapsed_time": "1 day, 11:52:23", "remaining_time": "6:33:25"} +{"current_steps": 9140, "total_steps": 10787, "loss": 0.05699597597122193, "lr": 5.997387591451947e-06, "epoch": 0.8473554906596208, "percentage": 84.73, "elapsed_time": "1 day, 11:57:04", "remaining_time": "6:28:41"} +{"current_steps": 9160, "total_steps": 10787, "loss": 0.05847395658493042, "lr": 5.855596582324724e-06, "epoch": 0.8492096602234275, "percentage": 84.92, "elapsed_time": "1 day, 12:01:45", "remaining_time": "6:23:58"} +{"current_steps": 9180, "total_steps": 10787, "loss": 0.05857234001159668, "lr": 5.7153974946415165e-06, "epoch": 0.851063829787234, "percentage": 85.1, "elapsed_time": "1 day, 12:06:26", "remaining_time": "6:19:14"} +{"current_steps": 9200, "total_steps": 10787, "loss": 0.057513868808746337, "lr": 5.576795384217232e-06, "epoch": 0.8529179993510406, "percentage": 85.29, "elapsed_time": "1 day, 12:11:07", "remaining_time": "6:14:31"} +{"current_steps": 9220, "total_steps": 10787, "loss": 0.05662814378738403, "lr": 5.439795249277141e-06, "epoch": 0.8547721689148473, "percentage": 85.47, "elapsed_time": "1 day, 12:15:48", "remaining_time": "6:09:47"} +{"current_steps": 9240, "total_steps": 10787, "loss": 0.05687806010246277, "lr": 5.304402030276551e-06, "epoch": 0.8566263384786539, "percentage": 85.66, "elapsed_time": "1 day, 12:20:29", "remaining_time": "6:05:04"} +{"current_steps": 9260, "total_steps": 10787, "loss": 0.05730761289596557, "lr": 5.1706206097226925e-06, "epoch": 0.8584805080424605, "percentage": 85.84, "elapsed_time": "1 day, 12:25:10", "remaining_time": "6:00:20"} +{"current_steps": 9280, "total_steps": 10787, "loss": 0.05795542001724243, "lr": 5.038455811998627e-06, "epoch": 0.8603346776062671, "percentage": 86.03, "elapsed_time": "1 day, 12:29:51", "remaining_time": "5:55:36"} +{"current_steps": 9300, "total_steps": 10787, "loss": 0.05497853755950928, "lr": 4.907912403189285e-06, "epoch": 0.8621888471700737, "percentage": 86.21, "elapsed_time": "1 day, 12:34:32", "remaining_time": "5:50:53"} +{"current_steps": 9320, "total_steps": 10787, "loss": 0.05861245393753052, "lr": 4.77899509090956e-06, "epoch": 0.8640430167338803, "percentage": 86.4, "elapsed_time": "1 day, 12:39:13", "remaining_time": "5:46:09"} +{"current_steps": 9340, "total_steps": 10787, "loss": 0.05678141713142395, "lr": 4.651708524134624e-06, "epoch": 0.865897186297687, "percentage": 86.59, "elapsed_time": "1 day, 12:43:54", "remaining_time": "5:41:26"} +{"current_steps": 9360, "total_steps": 10787, "loss": 0.0577523946762085, "lr": 4.52605729303216e-06, "epoch": 0.8677513558614935, "percentage": 86.77, "elapsed_time": "1 day, 12:48:34", "remaining_time": "5:36:42"} +{"current_steps": 9380, "total_steps": 10787, "loss": 0.058051574230194095, "lr": 4.402045928796944e-06, "epoch": 0.8696055254253001, "percentage": 86.96, "elapsed_time": "1 day, 12:53:15", "remaining_time": "5:31:59"} +{"current_steps": 9400, "total_steps": 10787, "loss": 0.056524813175201416, "lr": 4.279678903487355e-06, "epoch": 0.8714596949891068, "percentage": 87.14, "elapsed_time": "1 day, 12:57:56", "remaining_time": "5:27:15"} +{"current_steps": 9420, "total_steps": 10787, "loss": 0.05766661167144775, "lr": 4.158960629864167e-06, "epoch": 0.8733138645529134, "percentage": 87.33, "elapsed_time": "1 day, 13:02:36", "remaining_time": "5:22:32"} +{"current_steps": 9440, "total_steps": 10787, "loss": 0.05792294144630432, "lr": 4.039895461231396e-06, "epoch": 0.87516803411672, "percentage": 87.51, "elapsed_time": "1 day, 13:07:17", "remaining_time": "5:17:48"} +{"current_steps": 9460, "total_steps": 10787, "loss": 0.05697953701019287, "lr": 3.922487691279309e-06, "epoch": 0.8770222036805266, "percentage": 87.7, "elapsed_time": "1 day, 13:11:58", "remaining_time": "5:13:05"} +{"current_steps": 9480, "total_steps": 10787, "loss": 0.05770295858383179, "lr": 3.806741553929577e-06, "epoch": 0.8788763732443332, "percentage": 87.88, "elapsed_time": "1 day, 13:16:39", "remaining_time": "5:08:21"} +{"current_steps": 9500, "total_steps": 10787, "loss": 0.056513524055480956, "lr": 3.6926612231826197e-06, "epoch": 0.8807305428081398, "percentage": 88.07, "elapsed_time": "1 day, 13:21:20", "remaining_time": "5:03:38"} +{"current_steps": 9520, "total_steps": 10787, "loss": 0.05862005949020386, "lr": 3.5802508129670564e-06, "epoch": 0.8825847123719465, "percentage": 88.25, "elapsed_time": "1 day, 13:26:01", "remaining_time": "4:58:55"} +{"current_steps": 9540, "total_steps": 10787, "loss": 0.05859295129776001, "lr": 3.4695143769913784e-06, "epoch": 0.884438881935753, "percentage": 88.44, "elapsed_time": "1 day, 13:30:42", "remaining_time": "4:54:11"} +{"current_steps": 9560, "total_steps": 10787, "loss": 0.057581615447998044, "lr": 3.3604559085977317e-06, "epoch": 0.8862930514995596, "percentage": 88.63, "elapsed_time": "1 day, 13:35:22", "remaining_time": "4:49:28"} +{"current_steps": 9580, "total_steps": 10787, "loss": 0.0586451530456543, "lr": 3.253079340617937e-06, "epoch": 0.8881472210633663, "percentage": 88.81, "elapsed_time": "1 day, 13:40:03", "remaining_time": "4:44:44"} +{"current_steps": 9600, "total_steps": 10787, "loss": 0.05632882118225098, "lr": 3.1473885452316665e-06, "epoch": 0.8900013906271729, "percentage": 89.0, "elapsed_time": "1 day, 13:44:44", "remaining_time": "4:40:01"} +{"current_steps": 9620, "total_steps": 10787, "loss": 0.058455199003219604, "lr": 3.0433873338267915e-06, "epoch": 0.8918555601909794, "percentage": 89.18, "elapsed_time": "1 day, 13:49:25", "remaining_time": "4:35:18"} +{"current_steps": 9640, "total_steps": 10787, "loss": 0.05593242645263672, "lr": 2.941079456861917e-06, "epoch": 0.893709729754786, "percentage": 89.37, "elapsed_time": "1 day, 13:54:07", "remaining_time": "4:30:34"} +{"current_steps": 9660, "total_steps": 10787, "loss": 0.05731314420700073, "lr": 2.840468603731189e-06, "epoch": 0.8955638993185927, "percentage": 89.55, "elapsed_time": "1 day, 13:58:48", "remaining_time": "4:25:51"} +{"current_steps": 9680, "total_steps": 10787, "loss": 0.058256596326828, "lr": 2.7415584026312223e-06, "epoch": 0.8974180688823993, "percentage": 89.74, "elapsed_time": "1 day, 14:03:29", "remaining_time": "4:21:08"} +{"current_steps": 9700, "total_steps": 10787, "loss": 0.05611896514892578, "lr": 2.644352420430246e-06, "epoch": 0.8992722384462059, "percentage": 89.92, "elapsed_time": "1 day, 14:08:10", "remaining_time": "4:16:25"} +{"current_steps": 9720, "total_steps": 10787, "loss": 0.05943126082420349, "lr": 2.5488541625394933e-06, "epoch": 0.9011264080100125, "percentage": 90.11, "elapsed_time": "1 day, 14:12:51", "remaining_time": "4:11:41"} +{"current_steps": 9740, "total_steps": 10787, "loss": 0.05685185194015503, "lr": 2.4550670727867763e-06, "epoch": 0.9029805775738191, "percentage": 90.29, "elapsed_time": "1 day, 14:17:32", "remaining_time": "4:06:58"} +{"current_steps": 9760, "total_steps": 10787, "loss": 0.05601794123649597, "lr": 2.362994533292323e-06, "epoch": 0.9048347471376257, "percentage": 90.48, "elapsed_time": "1 day, 14:22:13", "remaining_time": "4:02:15"} +{"current_steps": 9780, "total_steps": 10787, "loss": 0.05724194049835205, "lr": 2.272639864346776e-06, "epoch": 0.9066889167014324, "percentage": 90.66, "elapsed_time": "1 day, 14:26:54", "remaining_time": "3:57:31"} +{"current_steps": 9800, "total_steps": 10787, "loss": 0.056692618131637576, "lr": 2.1840063242915045e-06, "epoch": 0.9085430862652389, "percentage": 90.85, "elapsed_time": "1 day, 14:31:35", "remaining_time": "3:52:48"} +{"current_steps": 9820, "total_steps": 10787, "loss": 0.05840623378753662, "lr": 2.0970971094010305e-06, "epoch": 0.9103972558290455, "percentage": 91.04, "elapsed_time": "1 day, 14:36:16", "remaining_time": "3:48:05"} +{"current_steps": 9840, "total_steps": 10787, "loss": 0.05786421298980713, "lr": 2.0119153537678513e-06, "epoch": 0.9122514253928522, "percentage": 91.22, "elapsed_time": "1 day, 14:40:57", "remaining_time": "3:43:22"} +{"current_steps": 9860, "total_steps": 10787, "loss": 0.057442504167556765, "lr": 1.9284641291893615e-06, "epoch": 0.9141055949566588, "percentage": 91.41, "elapsed_time": "1 day, 14:45:38", "remaining_time": "3:38:38"} +{"current_steps": 9880, "total_steps": 10787, "loss": 0.05783541202545166, "lr": 1.8467464450570903e-06, "epoch": 0.9159597645204653, "percentage": 91.59, "elapsed_time": "1 day, 14:50:20", "remaining_time": "3:33:55"} +{"current_steps": 9900, "total_steps": 10787, "loss": 0.058336269855499265, "lr": 1.7667652482481922e-06, "epoch": 0.917813934084272, "percentage": 91.78, "elapsed_time": "1 day, 14:55:01", "remaining_time": "3:29:12"} +{"current_steps": 9920, "total_steps": 10787, "loss": 0.05814253091812134, "lr": 1.6885234230191615e-06, "epoch": 0.9196681036480786, "percentage": 91.96, "elapsed_time": "1 day, 14:59:42", "remaining_time": "3:24:29"} +{"current_steps": 9940, "total_steps": 10787, "loss": 0.055842363834381105, "lr": 1.6120237909018287e-06, "epoch": 0.9215222732118852, "percentage": 92.15, "elapsed_time": "1 day, 15:04:23", "remaining_time": "3:19:46"} +{"current_steps": 9960, "total_steps": 10787, "loss": 0.05697543621063232, "lr": 1.5372691106016135e-06, "epoch": 0.9233764427756919, "percentage": 92.33, "elapsed_time": "1 day, 15:09:04", "remaining_time": "3:15:02"} +{"current_steps": 9980, "total_steps": 10787, "loss": 0.05675085783004761, "lr": 1.464262077898032e-06, "epoch": 0.9252306123394984, "percentage": 92.52, "elapsed_time": "1 day, 15:13:45", "remaining_time": "3:10:19"} +{"current_steps": 10000, "total_steps": 10787, "loss": 0.05656332969665527, "lr": 1.3930053255474863e-06, "epoch": 0.927084781903305, "percentage": 92.7, "elapsed_time": "1 day, 15:18:26", "remaining_time": "3:05:36"} +{"current_steps": 10020, "total_steps": 10787, "loss": 0.05754779577255249, "lr": 1.3235014231883391e-06, "epoch": 0.9289389514671117, "percentage": 92.89, "elapsed_time": "1 day, 15:24:41", "remaining_time": "3:01:00"} +{"current_steps": 10040, "total_steps": 10787, "loss": 0.05811010599136353, "lr": 1.2557528772482175e-06, "epoch": 0.9307931210309183, "percentage": 93.07, "elapsed_time": "1 day, 15:29:22", "remaining_time": "2:56:17"} +{"current_steps": 10060, "total_steps": 10787, "loss": 0.057920646667480466, "lr": 1.1897621308536556e-06, "epoch": 0.9326472905947248, "percentage": 93.26, "elapsed_time": "1 day, 15:34:03", "remaining_time": "2:51:33"} +{"current_steps": 10080, "total_steps": 10787, "loss": 0.05935220718383789, "lr": 1.125531563741966e-06, "epoch": 0.9345014601585315, "percentage": 93.45, "elapsed_time": "1 day, 15:38:45", "remaining_time": "2:46:50"} +{"current_steps": 10100, "total_steps": 10787, "loss": 0.05946972370147705, "lr": 1.0630634921754478e-06, "epoch": 0.9363556297223381, "percentage": 93.63, "elapsed_time": "1 day, 15:43:26", "remaining_time": "2:42:07"} +{"current_steps": 10120, "total_steps": 10787, "loss": 0.05542746782302856, "lr": 1.0023601688578467e-06, "epoch": 0.9382097992861447, "percentage": 93.82, "elapsed_time": "1 day, 15:48:07", "remaining_time": "2:37:23"} +{"current_steps": 10140, "total_steps": 10787, "loss": 0.058707261085510255, "lr": 9.434237828531034e-07, "epoch": 0.9400639688499514, "percentage": 94.0, "elapsed_time": "1 day, 15:52:49", "remaining_time": "2:32:40"} +{"current_steps": 10160, "total_steps": 10787, "loss": 0.05690791606903076, "lr": 8.862564595064349e-07, "epoch": 0.9419181384137579, "percentage": 94.19, "elapsed_time": "1 day, 15:57:31", "remaining_time": "2:27:57"} +{"current_steps": 10180, "total_steps": 10787, "loss": 0.054658901691436765, "lr": 8.30860260367694e-07, "epoch": 0.9437723079775645, "percentage": 94.37, "elapsed_time": "1 day, 16:02:12", "remaining_time": "2:23:14"} +{"current_steps": 10200, "total_steps": 10787, "loss": 0.05803183317184448, "lr": 7.772371831170022e-07, "epoch": 0.9456264775413712, "percentage": 94.56, "elapsed_time": "1 day, 16:06:54", "remaining_time": "2:18:30"} +{"current_steps": 10220, "total_steps": 10787, "loss": 0.05667737126350403, "lr": 7.253891614927177e-07, "epoch": 0.9474806471051778, "percentage": 94.74, "elapsed_time": "1 day, 16:11:35", "remaining_time": "2:13:47"} +{"current_steps": 10240, "total_steps": 10787, "loss": 0.05827021598815918, "lr": 6.753180652217306e-07, "epoch": 0.9493348166689843, "percentage": 94.93, "elapsed_time": "1 day, 16:16:17", "remaining_time": "2:09:04"} +{"current_steps": 10260, "total_steps": 10787, "loss": 0.05811399817466736, "lr": 6.270256999519885e-07, "epoch": 0.951188986232791, "percentage": 95.11, "elapsed_time": "1 day, 16:20:58", "remaining_time": "2:04:21"} +{"current_steps": 10280, "total_steps": 10787, "loss": 0.05737486481666565, "lr": 5.805138071874161e-07, "epoch": 0.9530431557965976, "percentage": 95.3, "elapsed_time": "1 day, 16:25:40", "remaining_time": "1:59:37"} +{"current_steps": 10300, "total_steps": 10787, "loss": 0.05651825666427612, "lr": 5.357840642251089e-07, "epoch": 0.9548973253604042, "percentage": 95.49, "elapsed_time": "1 day, 16:30:21", "remaining_time": "1:54:54"} +{"current_steps": 10320, "total_steps": 10787, "loss": 0.05737701654434204, "lr": 4.928380840948377e-07, "epoch": 0.9567514949242109, "percentage": 95.67, "elapsed_time": "1 day, 16:35:02", "remaining_time": "1:50:11"} +{"current_steps": 10340, "total_steps": 10787, "loss": 0.05547755360603333, "lr": 4.5167741550088406e-07, "epoch": 0.9586056644880174, "percentage": 95.86, "elapsed_time": "1 day, 16:39:44", "remaining_time": "1:45:28"} +{"current_steps": 10360, "total_steps": 10787, "loss": 0.056265252828598025, "lr": 4.12303542766207e-07, "epoch": 0.960459834051824, "percentage": 96.04, "elapsed_time": "1 day, 16:44:25", "remaining_time": "1:40:45"} +{"current_steps": 10380, "total_steps": 10787, "loss": 0.05831778049468994, "lr": 3.747178857788802e-07, "epoch": 0.9623140036156307, "percentage": 96.23, "elapsed_time": "1 day, 16:49:07", "remaining_time": "1:36:01"} +{"current_steps": 10400, "total_steps": 10787, "loss": 0.05711444616317749, "lr": 3.389217999409222e-07, "epoch": 0.9641681731794373, "percentage": 96.41, "elapsed_time": "1 day, 16:53:48", "remaining_time": "1:31:18"} +{"current_steps": 10420, "total_steps": 10787, "loss": 0.05954468250274658, "lr": 3.0491657611939615e-07, "epoch": 0.9660223427432438, "percentage": 96.6, "elapsed_time": "1 day, 16:58:29", "remaining_time": "1:26:35"} +{"current_steps": 10440, "total_steps": 10787, "loss": 0.058045947551727296, "lr": 2.7270344059988074e-07, "epoch": 0.9678765123070505, "percentage": 96.78, "elapsed_time": "1 day, 17:03:10", "remaining_time": "1:21:52"} +{"current_steps": 10460, "total_steps": 10787, "loss": 0.05838167667388916, "lr": 2.4228355504222756e-07, "epoch": 0.9697306818708571, "percentage": 96.97, "elapsed_time": "1 day, 17:07:52", "remaining_time": "1:17:09"} +{"current_steps": 10480, "total_steps": 10787, "loss": 0.05804737210273743, "lr": 2.1365801643868366e-07, "epoch": 0.9715848514346637, "percentage": 97.15, "elapsed_time": "1 day, 17:12:33", "remaining_time": "1:12:25"} +{"current_steps": 10500, "total_steps": 10787, "loss": 0.05664463639259339, "lr": 1.8682785707431205e-07, "epoch": 0.9734390209984704, "percentage": 97.34, "elapsed_time": "1 day, 17:17:14", "remaining_time": "1:07:42"} +{"current_steps": 10520, "total_steps": 10787, "loss": 0.056443202495574954, "lr": 1.6179404448980474e-07, "epoch": 0.9752931905622769, "percentage": 97.52, "elapsed_time": "1 day, 17:21:55", "remaining_time": "1:02:59"} +{"current_steps": 10540, "total_steps": 10787, "loss": 0.0574646532535553, "lr": 1.38557481446544e-07, "epoch": 0.9771473601260835, "percentage": 97.71, "elapsed_time": "1 day, 17:26:36", "remaining_time": "0:58:16"} +{"current_steps": 10560, "total_steps": 10787, "loss": 0.05568208694458008, "lr": 1.1711900589408409e-07, "epoch": 0.9790015296898902, "percentage": 97.9, "elapsed_time": "1 day, 17:31:18", "remaining_time": "0:53:33"} +{"current_steps": 10580, "total_steps": 10787, "loss": 0.05898926854133606, "lr": 9.74793909399141e-08, "epoch": 0.9808556992536968, "percentage": 98.08, "elapsed_time": "1 day, 17:35:59", "remaining_time": "0:48:50"} +{"current_steps": 10600, "total_steps": 10787, "loss": 0.05666929483413696, "lr": 7.963934482158597e-08, "epoch": 0.9827098688175033, "percentage": 98.27, "elapsed_time": "1 day, 17:40:40", "remaining_time": "0:44:06"} +{"current_steps": 10620, "total_steps": 10787, "loss": 0.05665904879570007, "lr": 6.359951088117933e-08, "epoch": 0.98456403838131, "percentage": 98.45, "elapsed_time": "1 day, 17:45:21", "remaining_time": "0:39:23"} +{"current_steps": 10640, "total_steps": 10787, "loss": 0.05817822813987732, "lr": 4.936046754207557e-08, "epoch": 0.9864182079451166, "percentage": 98.64, "elapsed_time": "1 day, 17:50:02", "remaining_time": "0:34:40"} +{"current_steps": 10660, "total_steps": 10787, "loss": 0.057973289489746095, "lr": 3.69227282881357e-08, "epoch": 0.9882723775089232, "percentage": 98.82, "elapsed_time": "1 day, 17:54:43", "remaining_time": "0:29:57"} +{"current_steps": 10680, "total_steps": 10787, "loss": 0.057922327518463136, "lr": 2.628674164515954e-08, "epoch": 0.9901265470727298, "percentage": 99.01, "elapsed_time": "1 day, 17:59:24", "remaining_time": "0:25:14"} +{"current_steps": 10700, "total_steps": 10787, "loss": 0.05686279535293579, "lr": 1.745289116471538e-08, "epoch": 0.9919807166365364, "percentage": 99.19, "elapsed_time": "1 day, 18:04:06", "remaining_time": "0:20:31"} +{"current_steps": 10720, "total_steps": 10787, "loss": 0.05729717016220093, "lr": 1.042149541031212e-08, "epoch": 0.993834886200343, "percentage": 99.38, "elapsed_time": "1 day, 18:08:47", "remaining_time": "0:15:48"} +{"current_steps": 10740, "total_steps": 10787, "loss": 0.05722014904022217, "lr": 5.192807945902934e-09, "epoch": 0.9956890557641497, "percentage": 99.56, "elapsed_time": "1 day, 18:13:28", "remaining_time": "0:11:05"} +{"current_steps": 10760, "total_steps": 10787, "loss": 0.059349268674850464, "lr": 1.767017326764764e-09, "epoch": 0.9975432253279563, "percentage": 99.75, "elapsed_time": "1 day, 18:18:10", "remaining_time": "0:06:22"} +{"current_steps": 10780, "total_steps": 10787, "loss": 0.056857752799987796, "lr": 1.4424709265936642e-10, "epoch": 0.9993973948917628, "percentage": 99.94, "elapsed_time": "1 day, 18:22:51", "remaining_time": "0:01:39"} +{"current_steps": 10787, "total_steps": 10787, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1 day, 18:25:54", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..1bfaa05 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3816 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 10787, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00185416956380661, + "grad_norm": 3.820171696571671, + "learning_rate": 5.864197530864198e-06, + "loss": 2.011005401611328, + "step": 20 + }, + { + "epoch": 0.00370833912761322, + "grad_norm": 1.096620777853325, + "learning_rate": 1.2037037037037037e-05, + "loss": 0.5124849319458008, + "step": 40 + }, + { + "epoch": 0.00556250869141983, + "grad_norm": 0.3680814920079142, + "learning_rate": 1.8209876543209877e-05, + "loss": 0.22042126655578614, + "step": 60 + }, + { + "epoch": 0.00741667825522644, + "grad_norm": 0.2707298056373599, + "learning_rate": 2.438271604938272e-05, + "loss": 0.14981963634490966, + "step": 80 + }, + { + "epoch": 0.00927084781903305, + "grad_norm": 0.2659431724016679, + "learning_rate": 3.055555555555556e-05, + "loss": 0.12978166341781616, + "step": 100 + }, + { + "epoch": 0.01112501738283966, + "grad_norm": 0.22306664143926566, + "learning_rate": 3.67283950617284e-05, + "loss": 0.11404435634613037, + "step": 120 + }, + { + "epoch": 0.01297918694664627, + "grad_norm": 0.30576307991303725, + "learning_rate": 4.290123456790124e-05, + "loss": 0.1076289176940918, + "step": 140 + }, + { + "epoch": 0.01483335651045288, + "grad_norm": 0.19329367022139832, + "learning_rate": 4.9074074074074075e-05, + "loss": 0.10596754550933837, + "step": 160 + }, + { + "epoch": 0.016687526074259492, + "grad_norm": 0.18942231256837483, + "learning_rate": 5.524691358024692e-05, + "loss": 0.100307297706604, + "step": 180 + }, + { + "epoch": 0.0185416956380661, + "grad_norm": 0.15043901400684026, + "learning_rate": 6.141975308641975e-05, + "loss": 0.0976285457611084, + "step": 200 + }, + { + "epoch": 0.020395865201872712, + "grad_norm": 0.22845759117348927, + "learning_rate": 6.759259259259259e-05, + "loss": 0.09554426670074463, + "step": 220 + }, + { + "epoch": 0.02225003476567932, + "grad_norm": 0.19139025279674057, + "learning_rate": 7.376543209876543e-05, + "loss": 0.09421352148056031, + "step": 240 + }, + { + "epoch": 0.024104204329485932, + "grad_norm": 0.1811447164471412, + "learning_rate": 7.993827160493828e-05, + "loss": 0.0942450761795044, + "step": 260 + }, + { + "epoch": 0.02595837389329254, + "grad_norm": 0.1650628838740293, + "learning_rate": 8.611111111111112e-05, + "loss": 0.09581634402275085, + "step": 280 + }, + { + "epoch": 0.027812543457099152, + "grad_norm": 0.15454810302337588, + "learning_rate": 9.228395061728396e-05, + "loss": 0.09313751459121704, + "step": 300 + }, + { + "epoch": 0.02966671302090576, + "grad_norm": 0.13705135560279838, + "learning_rate": 9.84567901234568e-05, + "loss": 0.09234297275543213, + "step": 320 + }, + { + "epoch": 0.03152088258471237, + "grad_norm": 0.15487945666116068, + "learning_rate": 9.999949288192827e-05, + "loss": 0.08958485126495361, + "step": 340 + }, + { + "epoch": 0.033375052148518984, + "grad_norm": 0.12737126215222822, + "learning_rate": 9.99972390445745e-05, + "loss": 0.0907970130443573, + "step": 360 + }, + { + "epoch": 0.03522922171232559, + "grad_norm": 0.2133019246480929, + "learning_rate": 9.999318222267878e-05, + "loss": 0.08801476955413819, + "step": 380 + }, + { + "epoch": 0.0370833912761322, + "grad_norm": 0.17216898375465342, + "learning_rate": 9.99873225625369e-05, + "loss": 0.09476873278617859, + "step": 400 + }, + { + "epoch": 0.03893756083993881, + "grad_norm": 0.1980181417116414, + "learning_rate": 9.997966027545811e-05, + "loss": 0.09878499507904052, + "step": 420 + }, + { + "epoch": 0.040791730403745424, + "grad_norm": 0.12021105467998261, + "learning_rate": 9.997019563775733e-05, + "loss": 0.0894039511680603, + "step": 440 + }, + { + "epoch": 0.04264589996755203, + "grad_norm": 0.1506140007132925, + "learning_rate": 9.995892899074535e-05, + "loss": 0.0881020188331604, + "step": 460 + }, + { + "epoch": 0.04450006953135864, + "grad_norm": 0.09779255157559406, + "learning_rate": 9.994586074071638e-05, + "loss": 0.0859219789505005, + "step": 480 + }, + { + "epoch": 0.046354239095165256, + "grad_norm": 0.09470959480876269, + "learning_rate": 9.993099135893353e-05, + "loss": 0.08542002439498901, + "step": 500 + }, + { + "epoch": 0.048208408658971864, + "grad_norm": 0.09917038420264507, + "learning_rate": 9.991432138161169e-05, + "loss": 0.08334171175956726, + "step": 520 + }, + { + "epoch": 0.05006257822277847, + "grad_norm": 0.10889320362609117, + "learning_rate": 9.989585140989832e-05, + "loss": 0.08618338704109192, + "step": 540 + }, + { + "epoch": 0.05191674778658508, + "grad_norm": 0.09906113890359036, + "learning_rate": 9.987558210985163e-05, + "loss": 0.08432861566543579, + "step": 560 + }, + { + "epoch": 0.053770917350391696, + "grad_norm": 0.10940459744489729, + "learning_rate": 9.98535142124167e-05, + "loss": 0.08541926145553588, + "step": 580 + }, + { + "epoch": 0.055625086914198305, + "grad_norm": 0.09296178818963359, + "learning_rate": 9.982964851339902e-05, + "loss": 0.08227111101150512, + "step": 600 + }, + { + "epoch": 0.05747925647800491, + "grad_norm": 0.07844261933645442, + "learning_rate": 9.980398587343585e-05, + "loss": 0.08189270496368409, + "step": 620 + }, + { + "epoch": 0.05933342604181152, + "grad_norm": 0.10575423206665098, + "learning_rate": 9.977652721796516e-05, + "loss": 0.08317902684211731, + "step": 640 + }, + { + "epoch": 0.061187595605618136, + "grad_norm": 0.09709604090363623, + "learning_rate": 9.974727353719224e-05, + "loss": 0.08244485855102539, + "step": 660 + }, + { + "epoch": 0.06304176516942474, + "grad_norm": 0.09179391965642997, + "learning_rate": 9.971622588605402e-05, + "loss": 0.08294405937194824, + "step": 680 + }, + { + "epoch": 0.06489593473323135, + "grad_norm": 0.09556116581662638, + "learning_rate": 9.968338538418107e-05, + "loss": 0.08182405829429626, + "step": 700 + }, + { + "epoch": 0.06675010429703797, + "grad_norm": 0.08650063066723065, + "learning_rate": 9.96487532158571e-05, + "loss": 0.0813271701335907, + "step": 720 + }, + { + "epoch": 0.06860427386084457, + "grad_norm": 0.09090183837909592, + "learning_rate": 9.961233062997633e-05, + "loss": 0.08164938688278198, + "step": 740 + }, + { + "epoch": 0.07045844342465118, + "grad_norm": 0.1015857342614738, + "learning_rate": 9.957411893999851e-05, + "loss": 0.08256611824035645, + "step": 760 + }, + { + "epoch": 0.0723126129884578, + "grad_norm": 0.09745727469768291, + "learning_rate": 9.953411952390146e-05, + "loss": 0.08092707395553589, + "step": 780 + }, + { + "epoch": 0.0741667825522644, + "grad_norm": 0.08097614595740198, + "learning_rate": 9.949233382413139e-05, + "loss": 0.0815312385559082, + "step": 800 + }, + { + "epoch": 0.07602095211607102, + "grad_norm": 0.08685249110755532, + "learning_rate": 9.944876334755093e-05, + "loss": 0.07997688055038452, + "step": 820 + }, + { + "epoch": 0.07787512167987762, + "grad_norm": 0.07968029411937462, + "learning_rate": 9.940340966538476e-05, + "loss": 0.07891923189163208, + "step": 840 + }, + { + "epoch": 0.07972929124368423, + "grad_norm": 0.08963184148096366, + "learning_rate": 9.935627441316296e-05, + "loss": 0.08197757005691528, + "step": 860 + }, + { + "epoch": 0.08158346080749085, + "grad_norm": 0.10326821002778926, + "learning_rate": 9.930735929066198e-05, + "loss": 0.0796918511390686, + "step": 880 + }, + { + "epoch": 0.08343763037129745, + "grad_norm": 0.07608638835599486, + "learning_rate": 9.925666606184343e-05, + "loss": 0.08107801675796508, + "step": 900 + }, + { + "epoch": 0.08529179993510407, + "grad_norm": 0.07881338421551327, + "learning_rate": 9.920419655479045e-05, + "loss": 0.08010420799255372, + "step": 920 + }, + { + "epoch": 0.08714596949891068, + "grad_norm": 0.0888223955745175, + "learning_rate": 9.91499526616417e-05, + "loss": 0.07916066646575928, + "step": 940 + }, + { + "epoch": 0.08900013906271728, + "grad_norm": 0.08736576160887341, + "learning_rate": 9.909393633852318e-05, + "loss": 0.0791887640953064, + "step": 960 + }, + { + "epoch": 0.0908543086265239, + "grad_norm": 0.0872645623571638, + "learning_rate": 9.903614960547778e-05, + "loss": 0.07827670574188232, + "step": 980 + }, + { + "epoch": 0.09270847819033051, + "grad_norm": 0.09683278584901765, + "learning_rate": 9.897659454639227e-05, + "loss": 0.07974874973297119, + "step": 1000 + }, + { + "epoch": 0.09456264775413711, + "grad_norm": 0.09670970512572408, + "learning_rate": 9.891527330892226e-05, + "loss": 0.07780462503433228, + "step": 1020 + }, + { + "epoch": 0.09641681731794373, + "grad_norm": 0.07922410697673214, + "learning_rate": 9.885218810441474e-05, + "loss": 0.07922825217247009, + "step": 1040 + }, + { + "epoch": 0.09827098688175033, + "grad_norm": 0.08764111011974576, + "learning_rate": 9.878734120782831e-05, + "loss": 0.07735201120376586, + "step": 1060 + }, + { + "epoch": 0.10012515644555695, + "grad_norm": 0.09389190550005704, + "learning_rate": 9.872073495765111e-05, + "loss": 0.07676548957824707, + "step": 1080 + }, + { + "epoch": 0.10197932600936356, + "grad_norm": 0.08348731011483394, + "learning_rate": 9.865237175581656e-05, + "loss": 0.0770105242729187, + "step": 1100 + }, + { + "epoch": 0.10383349557317016, + "grad_norm": 0.08265777585705475, + "learning_rate": 9.858225406761677e-05, + "loss": 0.07735653519630432, + "step": 1120 + }, + { + "epoch": 0.10568766513697678, + "grad_norm": 0.08441811101976025, + "learning_rate": 9.851038442161347e-05, + "loss": 0.07819046974182128, + "step": 1140 + }, + { + "epoch": 0.10754183470078339, + "grad_norm": 0.07866301603118257, + "learning_rate": 9.843676540954699e-05, + "loss": 0.07668208479881286, + "step": 1160 + }, + { + "epoch": 0.10939600426459, + "grad_norm": 0.07928327546519687, + "learning_rate": 9.836139968624276e-05, + "loss": 0.07516925930976867, + "step": 1180 + }, + { + "epoch": 0.11125017382839661, + "grad_norm": 0.08036947844849412, + "learning_rate": 9.828428996951556e-05, + "loss": 0.07837026715278625, + "step": 1200 + }, + { + "epoch": 0.11310434339220321, + "grad_norm": 0.09143072603694366, + "learning_rate": 9.820543904007143e-05, + "loss": 0.07502893805503845, + "step": 1220 + }, + { + "epoch": 0.11495851295600983, + "grad_norm": 0.07104320586794924, + "learning_rate": 9.812484974140757e-05, + "loss": 0.07647337913513183, + "step": 1240 + }, + { + "epoch": 0.11681268251981644, + "grad_norm": 0.07471332199388478, + "learning_rate": 9.804252497970961e-05, + "loss": 0.07538799047470093, + "step": 1260 + }, + { + "epoch": 0.11866685208362304, + "grad_norm": 0.08695452168038581, + "learning_rate": 9.795846772374698e-05, + "loss": 0.0785320520401001, + "step": 1280 + }, + { + "epoch": 0.12052102164742966, + "grad_norm": 0.38095845451037036, + "learning_rate": 9.787268100476571e-05, + "loss": 0.14148486852645875, + "step": 1300 + }, + { + "epoch": 0.12237519121123627, + "grad_norm": 0.23453784446382794, + "learning_rate": 9.778516791637918e-05, + "loss": 0.09106227159500122, + "step": 1320 + }, + { + "epoch": 0.12422936077504287, + "grad_norm": 0.3078447269608703, + "learning_rate": 9.769593161445658e-05, + "loss": 0.10610485076904297, + "step": 1340 + }, + { + "epoch": 0.12608353033884948, + "grad_norm": 0.10392810136594262, + "learning_rate": 9.760497531700905e-05, + "loss": 0.09194117784500122, + "step": 1360 + }, + { + "epoch": 0.1279376999026561, + "grad_norm": 0.08295602822436413, + "learning_rate": 9.751230230407368e-05, + "loss": 0.08373166918754578, + "step": 1380 + }, + { + "epoch": 0.1297918694664627, + "grad_norm": 0.08248000439562024, + "learning_rate": 9.741791591759523e-05, + "loss": 0.07780111432075501, + "step": 1400 + }, + { + "epoch": 0.1316460390302693, + "grad_norm": 0.07283731134539405, + "learning_rate": 9.732181956130555e-05, + "loss": 0.08092001676559449, + "step": 1420 + }, + { + "epoch": 0.13350020859407594, + "grad_norm": 0.07447210866239493, + "learning_rate": 9.722401670060088e-05, + "loss": 0.07920002937316895, + "step": 1440 + }, + { + "epoch": 0.13535437815788254, + "grad_norm": 0.09523382561674014, + "learning_rate": 9.712451086241689e-05, + "loss": 0.07667785882949829, + "step": 1460 + }, + { + "epoch": 0.13720854772168914, + "grad_norm": 0.08215211048712649, + "learning_rate": 9.702330563510153e-05, + "loss": 0.07909265160560608, + "step": 1480 + }, + { + "epoch": 0.13906271728549577, + "grad_norm": 0.06602271525153754, + "learning_rate": 9.69204046682855e-05, + "loss": 0.07624268531799316, + "step": 1500 + }, + { + "epoch": 0.14091688684930237, + "grad_norm": 0.06950526744671304, + "learning_rate": 9.681581167275077e-05, + "loss": 0.07816213369369507, + "step": 1520 + }, + { + "epoch": 0.14277105641310897, + "grad_norm": 0.08286355489711139, + "learning_rate": 9.670953042029669e-05, + "loss": 0.07695078253746032, + "step": 1540 + }, + { + "epoch": 0.1446252259769156, + "grad_norm": 0.07783014967631326, + "learning_rate": 9.6601564743604e-05, + "loss": 0.07489546537399291, + "step": 1560 + }, + { + "epoch": 0.1464793955407222, + "grad_norm": 0.7215238075868866, + "learning_rate": 9.649191853609665e-05, + "loss": 0.0800896406173706, + "step": 1580 + }, + { + "epoch": 0.1483335651045288, + "grad_norm": 0.13862601143690534, + "learning_rate": 9.638059575180127e-05, + "loss": 0.11360986232757568, + "step": 1600 + }, + { + "epoch": 0.15018773466833543, + "grad_norm": 0.08115822256628541, + "learning_rate": 9.626760040520475e-05, + "loss": 0.08856036067008972, + "step": 1620 + }, + { + "epoch": 0.15204190423214203, + "grad_norm": 0.07756202053063599, + "learning_rate": 9.615293657110937e-05, + "loss": 0.08102580308914184, + "step": 1640 + }, + { + "epoch": 0.15389607379594863, + "grad_norm": 0.08278086676458717, + "learning_rate": 9.603660838448584e-05, + "loss": 0.08062328100204467, + "step": 1660 + }, + { + "epoch": 0.15575024335975524, + "grad_norm": 0.07970365542115601, + "learning_rate": 9.591862004032429e-05, + "loss": 0.08349821567535401, + "step": 1680 + }, + { + "epoch": 0.15760441292356187, + "grad_norm": 0.06570684068013177, + "learning_rate": 9.579897579348282e-05, + "loss": 0.0809329867362976, + "step": 1700 + }, + { + "epoch": 0.15945858248736847, + "grad_norm": 0.07584058985918503, + "learning_rate": 9.567767995853429e-05, + "loss": 0.07894476652145385, + "step": 1720 + }, + { + "epoch": 0.16131275205117507, + "grad_norm": 0.09071650635538053, + "learning_rate": 9.555473690961051e-05, + "loss": 0.07519868612289429, + "step": 1740 + }, + { + "epoch": 0.1631669216149817, + "grad_norm": 0.06348361705719396, + "learning_rate": 9.543015108024463e-05, + "loss": 0.0785559892654419, + "step": 1760 + }, + { + "epoch": 0.1650210911787883, + "grad_norm": 0.0647389173291084, + "learning_rate": 9.530392696321126e-05, + "loss": 0.07550161480903625, + "step": 1780 + }, + { + "epoch": 0.1668752607425949, + "grad_norm": 0.07269711770311187, + "learning_rate": 9.517606911036433e-05, + "loss": 0.07608571052551269, + "step": 1800 + }, + { + "epoch": 0.16872943030640153, + "grad_norm": 0.07223723741746069, + "learning_rate": 9.504658213247316e-05, + "loss": 0.07413275241851806, + "step": 1820 + }, + { + "epoch": 0.17058359987020813, + "grad_norm": 0.06738973545359006, + "learning_rate": 9.491547069905593e-05, + "loss": 0.07561180591583253, + "step": 1840 + }, + { + "epoch": 0.17243776943401473, + "grad_norm": 0.07323238258643082, + "learning_rate": 9.478273953821149e-05, + "loss": 0.07366191148757935, + "step": 1860 + }, + { + "epoch": 0.17429193899782136, + "grad_norm": 0.07257321862760945, + "learning_rate": 9.464839343644878e-05, + "loss": 0.07775602340698243, + "step": 1880 + }, + { + "epoch": 0.17614610856162796, + "grad_norm": 0.06847894564081444, + "learning_rate": 9.451243723851421e-05, + "loss": 0.07233434915542603, + "step": 1900 + }, + { + "epoch": 0.17800027812543456, + "grad_norm": 0.06335817185237871, + "learning_rate": 9.437487584721698e-05, + "loss": 0.07621219754219055, + "step": 1920 + }, + { + "epoch": 0.1798544476892412, + "grad_norm": 0.0640719189203514, + "learning_rate": 9.423571422325223e-05, + "loss": 0.07463518381118775, + "step": 1940 + }, + { + "epoch": 0.1817086172530478, + "grad_norm": 0.06515539813387905, + "learning_rate": 9.409495738502226e-05, + "loss": 0.07639362812042236, + "step": 1960 + }, + { + "epoch": 0.1835627868168544, + "grad_norm": 0.06569879839529959, + "learning_rate": 9.39526104084554e-05, + "loss": 0.07541184425354004, + "step": 1980 + }, + { + "epoch": 0.18541695638066102, + "grad_norm": 0.0578643398896708, + "learning_rate": 9.380867842682305e-05, + "loss": 0.07277128696441651, + "step": 2000 + }, + { + "epoch": 0.18727112594446763, + "grad_norm": 0.07226395006206054, + "learning_rate": 9.366316663055462e-05, + "loss": 0.07344133853912353, + "step": 2020 + }, + { + "epoch": 0.18912529550827423, + "grad_norm": 0.06647566469815315, + "learning_rate": 9.351608026705023e-05, + "loss": 0.0730777382850647, + "step": 2040 + }, + { + "epoch": 0.19097946507208083, + "grad_norm": 0.06745200883731671, + "learning_rate": 9.336742464049157e-05, + "loss": 0.07285230755805969, + "step": 2060 + }, + { + "epoch": 0.19283363463588746, + "grad_norm": 0.06455764222430915, + "learning_rate": 9.32172051116506e-05, + "loss": 0.07300975322723388, + "step": 2080 + }, + { + "epoch": 0.19468780419969406, + "grad_norm": 0.06680772726708664, + "learning_rate": 9.306542709769622e-05, + "loss": 0.07422054409980774, + "step": 2100 + }, + { + "epoch": 0.19654197376350066, + "grad_norm": 0.08413515246100994, + "learning_rate": 9.291209607199892e-05, + "loss": 0.07437876462936402, + "step": 2120 + }, + { + "epoch": 0.1983961433273073, + "grad_norm": 0.06339429581775848, + "learning_rate": 9.275721756393339e-05, + "loss": 0.0755193829536438, + "step": 2140 + }, + { + "epoch": 0.2002503128911139, + "grad_norm": 0.19889530430082372, + "learning_rate": 9.260079715867917e-05, + "loss": 0.07785636186599731, + "step": 2160 + }, + { + "epoch": 0.2021044824549205, + "grad_norm": 0.07340354751257809, + "learning_rate": 9.244284049701923e-05, + "loss": 0.07767927646636963, + "step": 2180 + }, + { + "epoch": 0.20395865201872712, + "grad_norm": 0.06404995523476703, + "learning_rate": 9.228335327513644e-05, + "loss": 0.07524172067642212, + "step": 2200 + }, + { + "epoch": 0.20581282158253372, + "grad_norm": 0.0618291038067499, + "learning_rate": 9.212234124440831e-05, + "loss": 0.07576064467430114, + "step": 2220 + }, + { + "epoch": 0.20766699114634032, + "grad_norm": 0.07109039366191955, + "learning_rate": 9.195981021119955e-05, + "loss": 0.07323854565620422, + "step": 2240 + }, + { + "epoch": 0.20952116071014695, + "grad_norm": 0.07029203315945454, + "learning_rate": 9.179576603665258e-05, + "loss": 0.07339696884155274, + "step": 2260 + }, + { + "epoch": 0.21137533027395355, + "grad_norm": 0.05424922342213343, + "learning_rate": 9.163021463647628e-05, + "loss": 0.07229110598564148, + "step": 2280 + }, + { + "epoch": 0.21322949983776016, + "grad_norm": 0.06673481099949503, + "learning_rate": 9.146316198073263e-05, + "loss": 0.07312118411064147, + "step": 2300 + }, + { + "epoch": 0.21508366940156678, + "grad_norm": 0.06063445092674018, + "learning_rate": 9.129461409362141e-05, + "loss": 0.07265024781227111, + "step": 2320 + }, + { + "epoch": 0.2169378389653734, + "grad_norm": 0.0597139015702256, + "learning_rate": 9.112457705326292e-05, + "loss": 0.07265085577964783, + "step": 2340 + }, + { + "epoch": 0.21879200852918, + "grad_norm": 0.06807060961713832, + "learning_rate": 9.095305699147889e-05, + "loss": 0.07184367179870606, + "step": 2360 + }, + { + "epoch": 0.22064617809298662, + "grad_norm": 0.07140570456141754, + "learning_rate": 9.078006009357125e-05, + "loss": 0.07540631890296937, + "step": 2380 + }, + { + "epoch": 0.22250034765679322, + "grad_norm": 0.06703730660153011, + "learning_rate": 9.060559259809915e-05, + "loss": 0.07418131828308105, + "step": 2400 + }, + { + "epoch": 0.22435451722059982, + "grad_norm": 0.06548741413963394, + "learning_rate": 9.042966079665397e-05, + "loss": 0.0729554533958435, + "step": 2420 + }, + { + "epoch": 0.22620868678440642, + "grad_norm": 0.06888642053259762, + "learning_rate": 9.025227103363238e-05, + "loss": 0.07194913625717163, + "step": 2440 + }, + { + "epoch": 0.22806285634821305, + "grad_norm": 0.06526620320003416, + "learning_rate": 9.007342970600762e-05, + "loss": 0.07399054765701293, + "step": 2460 + }, + { + "epoch": 0.22991702591201965, + "grad_norm": 0.06599047053204352, + "learning_rate": 8.989314326309885e-05, + "loss": 0.07210756540298462, + "step": 2480 + }, + { + "epoch": 0.23177119547582625, + "grad_norm": 0.057272141367375115, + "learning_rate": 8.971141820633842e-05, + "loss": 0.07364898920059204, + "step": 2500 + }, + { + "epoch": 0.23362536503963288, + "grad_norm": 0.07141711922984666, + "learning_rate": 8.95282610890376e-05, + "loss": 0.07184793949127197, + "step": 2520 + }, + { + "epoch": 0.23547953460343948, + "grad_norm": 0.05980379022872412, + "learning_rate": 8.934367851615009e-05, + "loss": 0.07045998573303222, + "step": 2540 + }, + { + "epoch": 0.23733370416724608, + "grad_norm": 0.05868034732418876, + "learning_rate": 8.9157677144034e-05, + "loss": 0.07100774049758911, + "step": 2560 + }, + { + "epoch": 0.2391878737310527, + "grad_norm": 0.057496908915986564, + "learning_rate": 8.897026368021167e-05, + "loss": 0.07279749512672425, + "step": 2580 + }, + { + "epoch": 0.24104204329485932, + "grad_norm": 0.067832866197957, + "learning_rate": 8.878144488312786e-05, + "loss": 0.07153629064559937, + "step": 2600 + }, + { + "epoch": 0.24289621285866592, + "grad_norm": 0.056524705132541014, + "learning_rate": 8.859122756190601e-05, + "loss": 0.07133421301841736, + "step": 2620 + }, + { + "epoch": 0.24475038242247255, + "grad_norm": 0.05764463896204705, + "learning_rate": 8.83996185761027e-05, + "loss": 0.07275062203407287, + "step": 2640 + }, + { + "epoch": 0.24660455198627915, + "grad_norm": 0.06490036766892582, + "learning_rate": 8.820662483546027e-05, + "loss": 0.07059406042098999, + "step": 2660 + }, + { + "epoch": 0.24845872155008575, + "grad_norm": 0.0585184759576509, + "learning_rate": 8.801225329965764e-05, + "loss": 0.07081823348999024, + "step": 2680 + }, + { + "epoch": 0.2503128911138924, + "grad_norm": 0.06661292390742107, + "learning_rate": 8.781651097805936e-05, + "loss": 0.07319986224174499, + "step": 2700 + }, + { + "epoch": 0.25216706067769895, + "grad_norm": 0.058350353721374024, + "learning_rate": 8.76194049294628e-05, + "loss": 0.07124414443969726, + "step": 2720 + }, + { + "epoch": 0.2540212302415056, + "grad_norm": 0.08957973296693779, + "learning_rate": 8.742094226184365e-05, + "loss": 0.07674325704574585, + "step": 2740 + }, + { + "epoch": 0.2558753998053122, + "grad_norm": 0.071281796664039, + "learning_rate": 8.722113013209954e-05, + "loss": 0.07280395030975342, + "step": 2760 + }, + { + "epoch": 0.2577295693691188, + "grad_norm": 0.07898835447697226, + "learning_rate": 8.701997574579196e-05, + "loss": 0.07572759985923767, + "step": 2780 + }, + { + "epoch": 0.2595837389329254, + "grad_norm": 0.06414597933057603, + "learning_rate": 8.681748635688645e-05, + "loss": 0.07128249406814575, + "step": 2800 + }, + { + "epoch": 0.26143790849673204, + "grad_norm": 0.06678113600827112, + "learning_rate": 8.661366926749101e-05, + "loss": 0.07258655428886414, + "step": 2820 + }, + { + "epoch": 0.2632920780605386, + "grad_norm": 0.06377380307680854, + "learning_rate": 8.640853182759274e-05, + "loss": 0.07168116569519042, + "step": 2840 + }, + { + "epoch": 0.26514624762434524, + "grad_norm": 0.06714205421571565, + "learning_rate": 8.620208143479276e-05, + "loss": 0.07134959697723389, + "step": 2860 + }, + { + "epoch": 0.2670004171881519, + "grad_norm": 0.0586694563117733, + "learning_rate": 8.59943255340395e-05, + "loss": 0.07181867361068725, + "step": 2880 + }, + { + "epoch": 0.26885458675195845, + "grad_norm": 0.06080732058251141, + "learning_rate": 8.578527161736027e-05, + "loss": 0.07058979272842407, + "step": 2900 + }, + { + "epoch": 0.2707087563157651, + "grad_norm": 0.054343947451525515, + "learning_rate": 8.557492722359091e-05, + "loss": 0.06852529644966125, + "step": 2920 + }, + { + "epoch": 0.2725629258795717, + "grad_norm": 0.06408410445364573, + "learning_rate": 8.53632999381041e-05, + "loss": 0.07001596689224243, + "step": 2940 + }, + { + "epoch": 0.2744170954433783, + "grad_norm": 0.06594523188673412, + "learning_rate": 8.515039739253576e-05, + "loss": 0.07448661923408509, + "step": 2960 + }, + { + "epoch": 0.2762712650071849, + "grad_norm": 0.0661265872233322, + "learning_rate": 8.493622726450981e-05, + "loss": 0.07278544902801513, + "step": 2980 + }, + { + "epoch": 0.27812543457099154, + "grad_norm": 0.05787193677356709, + "learning_rate": 8.472079727736128e-05, + "loss": 0.06984232664108277, + "step": 3000 + }, + { + "epoch": 0.2799796041347981, + "grad_norm": 0.05692169605401866, + "learning_rate": 8.450411519985794e-05, + "loss": 0.07119113206863403, + "step": 3020 + }, + { + "epoch": 0.28183377369860474, + "grad_norm": 0.05714621162711715, + "learning_rate": 8.428618884592001e-05, + "loss": 0.0721335768699646, + "step": 3040 + }, + { + "epoch": 0.28368794326241137, + "grad_norm": 0.056044521516826984, + "learning_rate": 8.406702607433833e-05, + "loss": 0.07185147404670715, + "step": 3060 + }, + { + "epoch": 0.28554211282621794, + "grad_norm": 0.05866908411820298, + "learning_rate": 8.384663478849116e-05, + "loss": 0.06987054347991943, + "step": 3080 + }, + { + "epoch": 0.28739628239002457, + "grad_norm": 0.05304897286452575, + "learning_rate": 8.362502293605898e-05, + "loss": 0.07024177312850952, + "step": 3100 + }, + { + "epoch": 0.2892504519538312, + "grad_norm": 0.0665427531160301, + "learning_rate": 8.340219850873794e-05, + "loss": 0.07095595598220825, + "step": 3120 + }, + { + "epoch": 0.2911046215176378, + "grad_norm": 0.06428509102988876, + "learning_rate": 8.317816954195175e-05, + "loss": 0.07078310251235961, + "step": 3140 + }, + { + "epoch": 0.2929587910814444, + "grad_norm": 0.05450559848407936, + "learning_rate": 8.295294411456176e-05, + "loss": 0.07231824398040772, + "step": 3160 + }, + { + "epoch": 0.29481296064525103, + "grad_norm": 0.05831466107721256, + "learning_rate": 8.272653034857577e-05, + "loss": 0.07037442922592163, + "step": 3180 + }, + { + "epoch": 0.2966671302090576, + "grad_norm": 0.10743868781185825, + "learning_rate": 8.249893640885505e-05, + "loss": 0.07160881757736207, + "step": 3200 + }, + { + "epoch": 0.29852129977286423, + "grad_norm": 0.06273025352399365, + "learning_rate": 8.227017050281987e-05, + "loss": 0.07143862247467041, + "step": 3220 + }, + { + "epoch": 0.30037546933667086, + "grad_norm": 0.057489325657076214, + "learning_rate": 8.204024088015363e-05, + "loss": 0.07265503406524658, + "step": 3240 + }, + { + "epoch": 0.30222963890047744, + "grad_norm": 0.06875218626973734, + "learning_rate": 8.180915583250532e-05, + "loss": 0.07018079757690429, + "step": 3260 + }, + { + "epoch": 0.30408380846428407, + "grad_norm": 0.05917589418608448, + "learning_rate": 8.157692369319045e-05, + "loss": 0.07140896916389465, + "step": 3280 + }, + { + "epoch": 0.3059379780280907, + "grad_norm": 0.06423179153616093, + "learning_rate": 8.134355283689063e-05, + "loss": 0.07040358781814575, + "step": 3300 + }, + { + "epoch": 0.30779214759189727, + "grad_norm": 0.058824570513165975, + "learning_rate": 8.110905167935147e-05, + "loss": 0.07193192243576049, + "step": 3320 + }, + { + "epoch": 0.3096463171557039, + "grad_norm": 0.06801954697849306, + "learning_rate": 8.087342867707918e-05, + "loss": 0.07015389204025269, + "step": 3340 + }, + { + "epoch": 0.31150048671951047, + "grad_norm": 0.05871440603852085, + "learning_rate": 8.063669232703559e-05, + "loss": 0.06960692405700683, + "step": 3360 + }, + { + "epoch": 0.3133546562833171, + "grad_norm": 0.05730341489672219, + "learning_rate": 8.03988511663317e-05, + "loss": 0.06944797039031983, + "step": 3380 + }, + { + "epoch": 0.31520882584712373, + "grad_norm": 0.0568291514334782, + "learning_rate": 8.015991377191984e-05, + "loss": 0.06993094086647034, + "step": 3400 + }, + { + "epoch": 0.3170629954109303, + "grad_norm": 0.0549687290382305, + "learning_rate": 7.991988876028437e-05, + "loss": 0.06836211681365967, + "step": 3420 + }, + { + "epoch": 0.31891716497473693, + "grad_norm": 0.06274212662593626, + "learning_rate": 7.967878478713097e-05, + "loss": 0.0685504674911499, + "step": 3440 + }, + { + "epoch": 0.32077133453854356, + "grad_norm": 0.05313533630838134, + "learning_rate": 7.943661054707448e-05, + "loss": 0.06650092601776122, + "step": 3460 + }, + { + "epoch": 0.32262550410235014, + "grad_norm": 0.052743862770069115, + "learning_rate": 7.919337477332536e-05, + "loss": 0.0690037727355957, + "step": 3480 + }, + { + "epoch": 0.32447967366615676, + "grad_norm": 0.05567356208095886, + "learning_rate": 7.894908623737478e-05, + "loss": 0.06971213817596436, + "step": 3500 + }, + { + "epoch": 0.3263338432299634, + "grad_norm": 0.06645957761141873, + "learning_rate": 7.870375374867827e-05, + "loss": 0.06895116567611695, + "step": 3520 + }, + { + "epoch": 0.32818801279376997, + "grad_norm": 0.05552776725124249, + "learning_rate": 7.845738615433804e-05, + "loss": 0.07218914031982422, + "step": 3540 + }, + { + "epoch": 0.3300421823575766, + "grad_norm": 0.05876603194289993, + "learning_rate": 7.820999233878398e-05, + "loss": 0.06853553056716918, + "step": 3560 + }, + { + "epoch": 0.3318963519213832, + "grad_norm": 0.05786796219083153, + "learning_rate": 7.796158122345322e-05, + "loss": 0.06862747669219971, + "step": 3580 + }, + { + "epoch": 0.3337505214851898, + "grad_norm": 0.05626094635104044, + "learning_rate": 7.771216176646844e-05, + "loss": 0.07211055755615234, + "step": 3600 + }, + { + "epoch": 0.33560469104899643, + "grad_norm": 0.05358929639409373, + "learning_rate": 7.746174296231482e-05, + "loss": 0.0689316987991333, + "step": 3620 + }, + { + "epoch": 0.33745886061280306, + "grad_norm": 0.06834932968026425, + "learning_rate": 7.721033384151568e-05, + "loss": 0.06952942609786987, + "step": 3640 + }, + { + "epoch": 0.33931303017660963, + "grad_norm": 0.053843769856845705, + "learning_rate": 7.69579434703068e-05, + "loss": 0.0695588767528534, + "step": 3660 + }, + { + "epoch": 0.34116719974041626, + "grad_norm": 0.0537965169492173, + "learning_rate": 7.670458095030955e-05, + "loss": 0.07019612789154053, + "step": 3680 + }, + { + "epoch": 0.3430213693042229, + "grad_norm": 0.053970780996903334, + "learning_rate": 7.645025541820254e-05, + "loss": 0.07074885964393615, + "step": 3700 + }, + { + "epoch": 0.34487553886802946, + "grad_norm": 0.05500723418032885, + "learning_rate": 7.619497604539232e-05, + "loss": 0.06914512515068054, + "step": 3720 + }, + { + "epoch": 0.3467297084318361, + "grad_norm": 0.05286890609596364, + "learning_rate": 7.593875203768247e-05, + "loss": 0.06664897799491883, + "step": 3740 + }, + { + "epoch": 0.3485838779956427, + "grad_norm": 0.05218547592002417, + "learning_rate": 7.568159263494171e-05, + "loss": 0.06811505556106567, + "step": 3760 + }, + { + "epoch": 0.3504380475594493, + "grad_norm": 0.053639225720427654, + "learning_rate": 7.542350711077068e-05, + "loss": 0.06916459798812866, + "step": 3780 + }, + { + "epoch": 0.3522922171232559, + "grad_norm": 0.05160367111654179, + "learning_rate": 7.516450477216749e-05, + "loss": 0.06800092458724975, + "step": 3800 + }, + { + "epoch": 0.35414638668706255, + "grad_norm": 0.05341978285742432, + "learning_rate": 7.49045949591922e-05, + "loss": 0.06905245780944824, + "step": 3820 + }, + { + "epoch": 0.3560005562508691, + "grad_norm": 0.05616921682628937, + "learning_rate": 7.464378704462984e-05, + "loss": 0.0688902497291565, + "step": 3840 + }, + { + "epoch": 0.35785472581467576, + "grad_norm": 0.05279023341750433, + "learning_rate": 7.438209043365249e-05, + "loss": 0.06842745542526245, + "step": 3860 + }, + { + "epoch": 0.3597088953784824, + "grad_norm": 0.04750647210947389, + "learning_rate": 7.41195145634802e-05, + "loss": 0.06902355551719666, + "step": 3880 + }, + { + "epoch": 0.36156306494228896, + "grad_norm": 0.051454390959194005, + "learning_rate": 7.385606890304052e-05, + "loss": 0.0672761082649231, + "step": 3900 + }, + { + "epoch": 0.3634172345060956, + "grad_norm": 0.05547366674280859, + "learning_rate": 7.359176295262711e-05, + "loss": 0.06806289553642272, + "step": 3920 + }, + { + "epoch": 0.3652714040699022, + "grad_norm": 0.05543290058096399, + "learning_rate": 7.332660624355715e-05, + "loss": 0.06858486533164979, + "step": 3940 + }, + { + "epoch": 0.3671255736337088, + "grad_norm": 0.05355034043300937, + "learning_rate": 7.306060833782759e-05, + "loss": 0.06711235046386718, + "step": 3960 + }, + { + "epoch": 0.3689797431975154, + "grad_norm": 0.05307257946024117, + "learning_rate": 7.279377882777036e-05, + "loss": 0.07175731658935547, + "step": 3980 + }, + { + "epoch": 0.37083391276132205, + "grad_norm": 0.052004343105162644, + "learning_rate": 7.252612733570642e-05, + "loss": 0.06841775178909301, + "step": 4000 + }, + { + "epoch": 0.3726880823251286, + "grad_norm": 0.052420044317239005, + "learning_rate": 7.225766351359881e-05, + "loss": 0.06980134844779969, + "step": 4020 + }, + { + "epoch": 0.37454225188893525, + "grad_norm": 0.05076973367976567, + "learning_rate": 7.198839704270454e-05, + "loss": 0.06585143804550171, + "step": 4040 + }, + { + "epoch": 0.3763964214527419, + "grad_norm": 0.04933338155179922, + "learning_rate": 7.171833763322553e-05, + "loss": 0.06848374009132385, + "step": 4060 + }, + { + "epoch": 0.37825059101654845, + "grad_norm": 0.056698449655288474, + "learning_rate": 7.144749502395832e-05, + "loss": 0.06790245175361634, + "step": 4080 + }, + { + "epoch": 0.3801047605803551, + "grad_norm": 0.05659410847003245, + "learning_rate": 7.1175878981943e-05, + "loss": 0.06954320073127747, + "step": 4100 + }, + { + "epoch": 0.38195893014416166, + "grad_norm": 0.055205533803030456, + "learning_rate": 7.090349930211094e-05, + "loss": 0.06869494915008545, + "step": 4120 + }, + { + "epoch": 0.3838130997079683, + "grad_norm": 0.04801055885664534, + "learning_rate": 7.063036580693159e-05, + "loss": 0.06774266958236694, + "step": 4140 + }, + { + "epoch": 0.3856672692717749, + "grad_norm": 0.05817794340467535, + "learning_rate": 7.035648834605821e-05, + "loss": 0.06900098323822021, + "step": 4160 + }, + { + "epoch": 0.3875214388355815, + "grad_norm": 0.055261341198151466, + "learning_rate": 7.008187679597276e-05, + "loss": 0.06982098817825318, + "step": 4180 + }, + { + "epoch": 0.3893756083993881, + "grad_norm": 0.046136016119472184, + "learning_rate": 6.980654105962965e-05, + "loss": 0.06795721054077149, + "step": 4200 + }, + { + "epoch": 0.39122977796319475, + "grad_norm": 0.04428693135314919, + "learning_rate": 6.95304910660987e-05, + "loss": 0.07044395208358764, + "step": 4220 + }, + { + "epoch": 0.3930839475270013, + "grad_norm": 0.05867699879205952, + "learning_rate": 6.9253736770207e-05, + "loss": 0.06826889514923096, + "step": 4240 + }, + { + "epoch": 0.39493811709080795, + "grad_norm": 0.05524625679458913, + "learning_rate": 6.897628815218004e-05, + "loss": 0.06704115867614746, + "step": 4260 + }, + { + "epoch": 0.3967922866546146, + "grad_norm": 0.04784807226686665, + "learning_rate": 6.869815521728167e-05, + "loss": 0.06963608860969543, + "step": 4280 + }, + { + "epoch": 0.39864645621842115, + "grad_norm": 0.05626967952229251, + "learning_rate": 6.841934799545337e-05, + "loss": 0.07049011588096618, + "step": 4300 + }, + { + "epoch": 0.4005006257822278, + "grad_norm": 0.049080750288660435, + "learning_rate": 6.813987654095258e-05, + "loss": 0.06666951179504395, + "step": 4320 + }, + { + "epoch": 0.4023547953460344, + "grad_norm": 0.05428166421605746, + "learning_rate": 6.785975093199001e-05, + "loss": 0.06822763085365295, + "step": 4340 + }, + { + "epoch": 0.404208964909841, + "grad_norm": 0.05187808062037162, + "learning_rate": 6.757898127036638e-05, + "loss": 0.06750587821006775, + "step": 4360 + }, + { + "epoch": 0.4060631344736476, + "grad_norm": 0.04994621419507147, + "learning_rate": 6.729757768110792e-05, + "loss": 0.06976407766342163, + "step": 4380 + }, + { + "epoch": 0.40791730403745424, + "grad_norm": 0.0530031470064577, + "learning_rate": 6.701555031210148e-05, + "loss": 0.06885499358177186, + "step": 4400 + }, + { + "epoch": 0.4097714736012608, + "grad_norm": 0.04836802069144157, + "learning_rate": 6.673290933372835e-05, + "loss": 0.06657370328903198, + "step": 4420 + }, + { + "epoch": 0.41162564316506745, + "grad_norm": 0.052208575398455824, + "learning_rate": 6.644966493849768e-05, + "loss": 0.06978561878204345, + "step": 4440 + }, + { + "epoch": 0.4134798127288741, + "grad_norm": 0.04896375874971665, + "learning_rate": 6.61658273406788e-05, + "loss": 0.06789119243621826, + "step": 4460 + }, + { + "epoch": 0.41533398229268065, + "grad_norm": 0.05207583875443149, + "learning_rate": 6.588140677593293e-05, + "loss": 0.06801660060882568, + "step": 4480 + }, + { + "epoch": 0.4171881518564873, + "grad_norm": 0.052321701855526835, + "learning_rate": 6.55964135009441e-05, + "loss": 0.0674366295337677, + "step": 4500 + }, + { + "epoch": 0.4190423214202939, + "grad_norm": 0.052460056969454404, + "learning_rate": 6.531085779304918e-05, + "loss": 0.06703794598579407, + "step": 4520 + }, + { + "epoch": 0.4208964909841005, + "grad_norm": 0.05984149730805949, + "learning_rate": 6.502474994986734e-05, + "loss": 0.06836413145065308, + "step": 4540 + }, + { + "epoch": 0.4227506605479071, + "grad_norm": 0.051043482645265106, + "learning_rate": 6.473810028892865e-05, + "loss": 0.06563597917556763, + "step": 4560 + }, + { + "epoch": 0.42460483011171374, + "grad_norm": 0.05440966274797062, + "learning_rate": 6.445091914730213e-05, + "loss": 0.06778264045715332, + "step": 4580 + }, + { + "epoch": 0.4264589996755203, + "grad_norm": 0.05744240077417072, + "learning_rate": 6.416321688122278e-05, + "loss": 0.06670353412628174, + "step": 4600 + }, + { + "epoch": 0.42831316923932694, + "grad_norm": 0.0563410864459583, + "learning_rate": 6.387500386571827e-05, + "loss": 0.06842938661575318, + "step": 4620 + }, + { + "epoch": 0.43016733880313357, + "grad_norm": 0.05677881581473309, + "learning_rate": 6.358629049423477e-05, + "loss": 0.06564785242080688, + "step": 4640 + }, + { + "epoch": 0.43202150836694014, + "grad_norm": 0.051386096259373924, + "learning_rate": 6.329708717826209e-05, + "loss": 0.06799172163009644, + "step": 4660 + }, + { + "epoch": 0.4338756779307468, + "grad_norm": 0.054688365900863255, + "learning_rate": 6.30074043469583e-05, + "loss": 0.06615757346153259, + "step": 4680 + }, + { + "epoch": 0.4357298474945534, + "grad_norm": 0.05221690983924291, + "learning_rate": 6.271725244677357e-05, + "loss": 0.06634211540222168, + "step": 4700 + }, + { + "epoch": 0.43758401705836, + "grad_norm": 0.05447789674208455, + "learning_rate": 6.24266419410735e-05, + "loss": 0.06808164119720458, + "step": 4720 + }, + { + "epoch": 0.4394381866221666, + "grad_norm": 0.045986624762272, + "learning_rate": 6.213558330976177e-05, + "loss": 0.06660630106925965, + "step": 4740 + }, + { + "epoch": 0.44129235618597323, + "grad_norm": 0.06057721119805469, + "learning_rate": 6.184408704890221e-05, + "loss": 0.06852835416793823, + "step": 4760 + }, + { + "epoch": 0.4431465257497798, + "grad_norm": 0.046200947505290135, + "learning_rate": 6.155216367034035e-05, + "loss": 0.0657484233379364, + "step": 4780 + }, + { + "epoch": 0.44500069531358644, + "grad_norm": 0.051188517402448765, + "learning_rate": 6.125982370132428e-05, + "loss": 0.06651111841201782, + "step": 4800 + }, + { + "epoch": 0.446854864877393, + "grad_norm": 0.04434185112458488, + "learning_rate": 6.0967077684124996e-05, + "loss": 0.06592975258827209, + "step": 4820 + }, + { + "epoch": 0.44870903444119964, + "grad_norm": 0.052132687845858554, + "learning_rate": 6.067393617565633e-05, + "loss": 0.06635326147079468, + "step": 4840 + }, + { + "epoch": 0.45056320400500627, + "grad_norm": 0.045119727419172674, + "learning_rate": 6.03804097470942e-05, + "loss": 0.06596879959106446, + "step": 4860 + }, + { + "epoch": 0.45241737356881284, + "grad_norm": 0.05246974817161853, + "learning_rate": 6.008650898349536e-05, + "loss": 0.06706082224845886, + "step": 4880 + }, + { + "epoch": 0.45427154313261947, + "grad_norm": 0.04974037668743926, + "learning_rate": 5.9792244483415717e-05, + "loss": 0.06731083393096923, + "step": 4900 + }, + { + "epoch": 0.4561257126964261, + "grad_norm": 0.049176896941555956, + "learning_rate": 5.9497626858528156e-05, + "loss": 0.06804193258285522, + "step": 4920 + }, + { + "epoch": 0.4579798822602327, + "grad_norm": 0.04754516758165675, + "learning_rate": 5.92026667332398e-05, + "loss": 0.06767497062683106, + "step": 4940 + }, + { + "epoch": 0.4598340518240393, + "grad_norm": 0.050756677328236376, + "learning_rate": 5.890737474430892e-05, + "loss": 0.06706864833831787, + "step": 4960 + }, + { + "epoch": 0.46168822138784593, + "grad_norm": 0.05135634722815149, + "learning_rate": 5.8611761540461386e-05, + "loss": 0.06532019376754761, + "step": 4980 + }, + { + "epoch": 0.4635423909516525, + "grad_norm": 0.04709592553591549, + "learning_rate": 5.831583778200656e-05, + "loss": 0.0650861382484436, + "step": 5000 + }, + { + "epoch": 0.46539656051545913, + "grad_norm": 0.05007547630131113, + "learning_rate": 5.801961414045299e-05, + "loss": 0.06561164855957032, + "step": 5020 + }, + { + "epoch": 0.46725073007926576, + "grad_norm": 0.05050759770015865, + "learning_rate": 5.772310129812345e-05, + "loss": 0.06795594096183777, + "step": 5040 + }, + { + "epoch": 0.46910489964307234, + "grad_norm": 0.05062220466713996, + "learning_rate": 5.742630994776982e-05, + "loss": 0.06659960150718688, + "step": 5060 + }, + { + "epoch": 0.47095906920687897, + "grad_norm": 0.04765243391149529, + "learning_rate": 5.712925079218741e-05, + "loss": 0.06613020896911621, + "step": 5080 + }, + { + "epoch": 0.4728132387706856, + "grad_norm": 0.04663876275325524, + "learning_rate": 5.683193454382909e-05, + "loss": 0.06645833253860474, + "step": 5100 + }, + { + "epoch": 0.47466740833449217, + "grad_norm": 0.05430827572057466, + "learning_rate": 5.6534371924418913e-05, + "loss": 0.06557634472846985, + "step": 5120 + }, + { + "epoch": 0.4765215778982988, + "grad_norm": 0.05355476380062587, + "learning_rate": 5.623657366456545e-05, + "loss": 0.06667708158493042, + "step": 5140 + }, + { + "epoch": 0.4783757474621054, + "grad_norm": 0.0539010131124388, + "learning_rate": 5.59385505033749e-05, + "loss": 0.06924290657043457, + "step": 5160 + }, + { + "epoch": 0.480229917025912, + "grad_norm": 0.053887588219191936, + "learning_rate": 5.564031318806376e-05, + "loss": 0.06771377325057984, + "step": 5180 + }, + { + "epoch": 0.48208408658971863, + "grad_norm": 0.05200039551143676, + "learning_rate": 5.534187247357131e-05, + "loss": 0.06644275188446044, + "step": 5200 + }, + { + "epoch": 0.48393825615352526, + "grad_norm": 0.04411301193034954, + "learning_rate": 5.504323912217171e-05, + "loss": 0.06886463165283203, + "step": 5220 + }, + { + "epoch": 0.48579242571733183, + "grad_norm": 0.04945757926239084, + "learning_rate": 5.474442390308598e-05, + "loss": 0.06803133487701415, + "step": 5240 + }, + { + "epoch": 0.48764659528113846, + "grad_norm": 0.049760885213020335, + "learning_rate": 5.444543759209354e-05, + "loss": 0.06640726327896118, + "step": 5260 + }, + { + "epoch": 0.4895007648449451, + "grad_norm": 0.05729644020155762, + "learning_rate": 5.414629097114371e-05, + "loss": 0.06845622062683106, + "step": 5280 + }, + { + "epoch": 0.49135493440875166, + "grad_norm": 0.04458570133378101, + "learning_rate": 5.384699482796686e-05, + "loss": 0.06699745655059815, + "step": 5300 + }, + { + "epoch": 0.4932091039725583, + "grad_norm": 0.06376727879348462, + "learning_rate": 5.354755995568534e-05, + "loss": 0.06719425320625305, + "step": 5320 + }, + { + "epoch": 0.4950632735363649, + "grad_norm": 0.05295423655645316, + "learning_rate": 5.3247997152424366e-05, + "loss": 0.06554273366928101, + "step": 5340 + }, + { + "epoch": 0.4969174431001715, + "grad_norm": 0.0491963165583997, + "learning_rate": 5.2948317220922506e-05, + "loss": 0.0648796796798706, + "step": 5360 + }, + { + "epoch": 0.4987716126639781, + "grad_norm": 0.047344994455222826, + "learning_rate": 5.26485309681422e-05, + "loss": 0.06562695503234864, + "step": 5380 + }, + { + "epoch": 0.5006257822277848, + "grad_norm": 0.0488658569397386, + "learning_rate": 5.2348649204879993e-05, + "loss": 0.06633292436599732, + "step": 5400 + }, + { + "epoch": 0.5024799517915913, + "grad_norm": 0.047741841923988455, + "learning_rate": 5.204868274537673e-05, + "loss": 0.06479262113571167, + "step": 5420 + }, + { + "epoch": 0.5043341213553979, + "grad_norm": 0.05667018797109963, + "learning_rate": 5.1748642406927506e-05, + "loss": 0.0654104232788086, + "step": 5440 + }, + { + "epoch": 0.5061882909192046, + "grad_norm": 0.04754587562985411, + "learning_rate": 5.1448539009491635e-05, + "loss": 0.06632285118103028, + "step": 5460 + }, + { + "epoch": 0.5080424604830112, + "grad_norm": 0.05609620041404095, + "learning_rate": 5.114838337530244e-05, + "loss": 0.06753811836242676, + "step": 5480 + }, + { + "epoch": 0.5098966300468177, + "grad_norm": 0.04656503893277827, + "learning_rate": 5.084818632847701e-05, + "loss": 0.06613025069236755, + "step": 5500 + }, + { + "epoch": 0.5117507996106244, + "grad_norm": 0.04736067371428652, + "learning_rate": 5.054795869462581e-05, + "loss": 0.06611216068267822, + "step": 5520 + }, + { + "epoch": 0.513604969174431, + "grad_norm": 0.049346478479543515, + "learning_rate": 5.024771130046234e-05, + "loss": 0.06571578383445739, + "step": 5540 + }, + { + "epoch": 0.5154591387382376, + "grad_norm": 0.04626565533371505, + "learning_rate": 4.994745497341269e-05, + "loss": 0.06566253900527955, + "step": 5560 + }, + { + "epoch": 0.5173133083020443, + "grad_norm": 0.04565379716480066, + "learning_rate": 4.964720054122509e-05, + "loss": 0.06430123448371887, + "step": 5580 + }, + { + "epoch": 0.5191674778658508, + "grad_norm": 0.04594537471780315, + "learning_rate": 4.934695883157943e-05, + "loss": 0.06554259061813354, + "step": 5600 + }, + { + "epoch": 0.5210216474296574, + "grad_norm": 0.052013576795831996, + "learning_rate": 4.9046740671696804e-05, + "loss": 0.06661000251770019, + "step": 5620 + }, + { + "epoch": 0.5228758169934641, + "grad_norm": 0.051090964226342454, + "learning_rate": 4.874655688794908e-05, + "loss": 0.0648884654045105, + "step": 5640 + }, + { + "epoch": 0.5247299865572707, + "grad_norm": 0.04724305963653279, + "learning_rate": 4.844641830546842e-05, + "loss": 0.06492191553115845, + "step": 5660 + }, + { + "epoch": 0.5265841561210772, + "grad_norm": 0.04902816710436297, + "learning_rate": 4.8146335747757e-05, + "loss": 0.06522760391235352, + "step": 5680 + }, + { + "epoch": 0.5284383256848839, + "grad_norm": 0.04941475339442223, + "learning_rate": 4.784632003629662e-05, + "loss": 0.06443318128585815, + "step": 5700 + }, + { + "epoch": 0.5302924952486905, + "grad_norm": 0.04733271095021244, + "learning_rate": 4.754638199015851e-05, + "loss": 0.06498017311096191, + "step": 5720 + }, + { + "epoch": 0.5321466648124971, + "grad_norm": 0.04798333935806849, + "learning_rate": 4.724653242561314e-05, + "loss": 0.0655935525894165, + "step": 5740 + }, + { + "epoch": 0.5340008343763037, + "grad_norm": 0.04822235889333689, + "learning_rate": 4.694678215574023e-05, + "loss": 0.06374808549880981, + "step": 5760 + }, + { + "epoch": 0.5358550039401103, + "grad_norm": 0.05227364492353613, + "learning_rate": 4.664714199003867e-05, + "loss": 0.06397829055786133, + "step": 5780 + }, + { + "epoch": 0.5377091735039169, + "grad_norm": 0.04952429568599143, + "learning_rate": 4.634762273403692e-05, + "loss": 0.06379647254943847, + "step": 5800 + }, + { + "epoch": 0.5395633430677236, + "grad_norm": 0.04485795030378189, + "learning_rate": 4.604823518890315e-05, + "loss": 0.06524479389190674, + "step": 5820 + }, + { + "epoch": 0.5414175126315302, + "grad_norm": 0.04725077082162728, + "learning_rate": 4.5748990151055876e-05, + "loss": 0.063930743932724, + "step": 5840 + }, + { + "epoch": 0.5432716821953367, + "grad_norm": 0.045571947917625574, + "learning_rate": 4.5449898411774504e-05, + "loss": 0.06565963625907897, + "step": 5860 + }, + { + "epoch": 0.5451258517591434, + "grad_norm": 0.04512121708064776, + "learning_rate": 4.515097075681029e-05, + "loss": 0.06600631475448608, + "step": 5880 + }, + { + "epoch": 0.54698002132295, + "grad_norm": 0.04796594600522924, + "learning_rate": 4.485221796599729e-05, + "loss": 0.06486299037933349, + "step": 5900 + }, + { + "epoch": 0.5488341908867566, + "grad_norm": 0.05035116256547558, + "learning_rate": 4.455365081286371e-05, + "loss": 0.06194999217987061, + "step": 5920 + }, + { + "epoch": 0.5506883604505632, + "grad_norm": 0.047597307893845496, + "learning_rate": 4.425528006424329e-05, + "loss": 0.06475620269775391, + "step": 5940 + }, + { + "epoch": 0.5525425300143698, + "grad_norm": 0.04960910114042581, + "learning_rate": 4.395711647988714e-05, + "loss": 0.06375322341918946, + "step": 5960 + }, + { + "epoch": 0.5543966995781764, + "grad_norm": 0.049130127096257234, + "learning_rate": 4.365917081207566e-05, + "loss": 0.0641134262084961, + "step": 5980 + }, + { + "epoch": 0.5562508691419831, + "grad_norm": 0.049172771141996544, + "learning_rate": 4.3361453805230814e-05, + "loss": 0.06496943831443787, + "step": 6000 + }, + { + "epoch": 0.5581050387057896, + "grad_norm": 0.04697420126877478, + "learning_rate": 4.3063976195528666e-05, + "loss": 0.06265571117401122, + "step": 6020 + }, + { + "epoch": 0.5599592082695962, + "grad_norm": 0.051790011897020614, + "learning_rate": 4.2766748710512225e-05, + "loss": 0.06494598984718322, + "step": 6040 + }, + { + "epoch": 0.5618133778334029, + "grad_norm": 0.046873609269863045, + "learning_rate": 4.2469782068704566e-05, + "loss": 0.06517527103424073, + "step": 6060 + }, + { + "epoch": 0.5636675473972095, + "grad_norm": 0.052474352319326345, + "learning_rate": 4.217308697922236e-05, + "loss": 0.06466827392578126, + "step": 6080 + }, + { + "epoch": 0.565521716961016, + "grad_norm": 0.049136762781101115, + "learning_rate": 4.187667414138958e-05, + "loss": 0.06504812240600585, + "step": 6100 + }, + { + "epoch": 0.5673758865248227, + "grad_norm": 0.04877058356279773, + "learning_rate": 4.158055424435177e-05, + "loss": 0.06338067054748535, + "step": 6120 + }, + { + "epoch": 0.5692300560886293, + "grad_norm": 0.05077888378135565, + "learning_rate": 4.128473796669054e-05, + "loss": 0.06424614191055297, + "step": 6140 + }, + { + "epoch": 0.5710842256524359, + "grad_norm": 0.04686343405918838, + "learning_rate": 4.0989235976038463e-05, + "loss": 0.06370105147361756, + "step": 6160 + }, + { + "epoch": 0.5729383952162426, + "grad_norm": 0.04552201782807027, + "learning_rate": 4.069405892869439e-05, + "loss": 0.06322758197784424, + "step": 6180 + }, + { + "epoch": 0.5747925647800491, + "grad_norm": 0.05142990846690097, + "learning_rate": 4.0399217469239174e-05, + "loss": 0.06390318274497986, + "step": 6200 + }, + { + "epoch": 0.5766467343438557, + "grad_norm": 0.05355258710451629, + "learning_rate": 4.010472223015182e-05, + "loss": 0.06472771167755127, + "step": 6220 + }, + { + "epoch": 0.5785009039076624, + "grad_norm": 0.048165961612589056, + "learning_rate": 3.981058383142602e-05, + "loss": 0.061773234605789186, + "step": 6240 + }, + { + "epoch": 0.580355073471469, + "grad_norm": 0.05429088591442539, + "learning_rate": 3.9516812880187227e-05, + "loss": 0.06225782036781311, + "step": 6260 + }, + { + "epoch": 0.5822092430352755, + "grad_norm": 0.0604603829071715, + "learning_rate": 3.922341997031007e-05, + "loss": 0.06542969346046448, + "step": 6280 + }, + { + "epoch": 0.5840634125990822, + "grad_norm": 0.04602032275751061, + "learning_rate": 3.8930415682036435e-05, + "loss": 0.06415734887123108, + "step": 6300 + }, + { + "epoch": 0.5859175821628888, + "grad_norm": 0.047392659065524145, + "learning_rate": 3.863781058159381e-05, + "loss": 0.06317670941352845, + "step": 6320 + }, + { + "epoch": 0.5877717517266954, + "grad_norm": 0.046575981405470104, + "learning_rate": 3.834561522081434e-05, + "loss": 0.06259400844573974, + "step": 6340 + }, + { + "epoch": 0.5896259212905021, + "grad_norm": 0.04333812916706854, + "learning_rate": 3.805384013675423e-05, + "loss": 0.06343435049057007, + "step": 6360 + }, + { + "epoch": 0.5914800908543086, + "grad_norm": 0.04556101087924968, + "learning_rate": 3.776249585131382e-05, + "loss": 0.0633241891860962, + "step": 6380 + }, + { + "epoch": 0.5933342604181152, + "grad_norm": 0.04884870911304169, + "learning_rate": 3.747159287085812e-05, + "loss": 0.0616495668888092, + "step": 6400 + }, + { + "epoch": 0.5951884299819219, + "grad_norm": 0.04401211899298281, + "learning_rate": 3.7181141685837943e-05, + "loss": 0.06143069267272949, + "step": 6420 + }, + { + "epoch": 0.5970425995457285, + "grad_norm": 0.05094195053050948, + "learning_rate": 3.68911527704116e-05, + "loss": 0.0653111219406128, + "step": 6440 + }, + { + "epoch": 0.598896769109535, + "grad_norm": 0.04487752972178212, + "learning_rate": 3.660163658206718e-05, + "loss": 0.0612871527671814, + "step": 6460 + }, + { + "epoch": 0.6007509386733417, + "grad_norm": 0.04708924884783961, + "learning_rate": 3.631260356124545e-05, + "loss": 0.06316884756088256, + "step": 6480 + }, + { + "epoch": 0.6026051082371483, + "grad_norm": 0.049087841455752984, + "learning_rate": 3.6024064130963316e-05, + "loss": 0.06191706657409668, + "step": 6500 + }, + { + "epoch": 0.6044592778009549, + "grad_norm": 0.05066544046233841, + "learning_rate": 3.573602869643801e-05, + "loss": 0.06327232122421264, + "step": 6520 + }, + { + "epoch": 0.6063134473647616, + "grad_norm": 0.044158995584808736, + "learning_rate": 3.5448507644711806e-05, + "loss": 0.060802686214447024, + "step": 6540 + }, + { + "epoch": 0.6081676169285681, + "grad_norm": 0.043851940149196716, + "learning_rate": 3.516151134427745e-05, + "loss": 0.06530459523200989, + "step": 6560 + }, + { + "epoch": 0.6100217864923747, + "grad_norm": 0.04152111869549671, + "learning_rate": 3.487505014470437e-05, + "loss": 0.06244962215423584, + "step": 6580 + }, + { + "epoch": 0.6118759560561814, + "grad_norm": 0.048155508768233726, + "learning_rate": 3.458913437626524e-05, + "loss": 0.06283918023109436, + "step": 6600 + }, + { + "epoch": 0.613730125619988, + "grad_norm": 0.04499639289333585, + "learning_rate": 3.4303774349563623e-05, + "loss": 0.06382766962051392, + "step": 6620 + }, + { + "epoch": 0.6155842951837945, + "grad_norm": 0.04317627130891494, + "learning_rate": 3.4018980355162114e-05, + "loss": 0.06351471543312073, + "step": 6640 + }, + { + "epoch": 0.6174384647476012, + "grad_norm": 0.05614677644073403, + "learning_rate": 3.373476266321118e-05, + "loss": 0.06272737979888916, + "step": 6660 + }, + { + "epoch": 0.6192926343114078, + "grad_norm": 0.042284697745079196, + "learning_rate": 3.3451131523078915e-05, + "loss": 0.062467378377914426, + "step": 6680 + }, + { + "epoch": 0.6211468038752144, + "grad_norm": 0.044517009371772165, + "learning_rate": 3.316809716298134e-05, + "loss": 0.06361099481582641, + "step": 6700 + }, + { + "epoch": 0.6230009734390209, + "grad_norm": 0.04892616862217898, + "learning_rate": 3.288566978961356e-05, + "loss": 0.06314346790313721, + "step": 6720 + }, + { + "epoch": 0.6248551430028276, + "grad_norm": 0.047445153141174416, + "learning_rate": 3.260385958778174e-05, + "loss": 0.06231023669242859, + "step": 6740 + }, + { + "epoch": 0.6267093125666342, + "grad_norm": 0.049105883450664495, + "learning_rate": 3.23226767200358e-05, + "loss": 0.06305838823318481, + "step": 6760 + }, + { + "epoch": 0.6285634821304408, + "grad_norm": 0.050572022069277335, + "learning_rate": 3.204213132630296e-05, + "loss": 0.06089724898338318, + "step": 6780 + }, + { + "epoch": 0.6304176516942475, + "grad_norm": 0.04206886641894423, + "learning_rate": 3.176223352352201e-05, + "loss": 0.062238240242004396, + "step": 6800 + }, + { + "epoch": 0.632271821258054, + "grad_norm": 0.0418493494393944, + "learning_rate": 3.148299340527857e-05, + "loss": 0.060497474670410153, + "step": 6820 + }, + { + "epoch": 0.6341259908218606, + "grad_norm": 0.0490312711310362, + "learning_rate": 3.120442104144099e-05, + "loss": 0.060766249895095825, + "step": 6840 + }, + { + "epoch": 0.6359801603856673, + "grad_norm": 0.04354326975358762, + "learning_rate": 3.092652647779733e-05, + "loss": 0.062382560968399045, + "step": 6860 + }, + { + "epoch": 0.6378343299494739, + "grad_norm": 0.04925031587484033, + "learning_rate": 3.0649319735692984e-05, + "loss": 0.06159923672676086, + "step": 6880 + }, + { + "epoch": 0.6396884995132804, + "grad_norm": 0.04435824396894195, + "learning_rate": 3.037281081166938e-05, + "loss": 0.06012410521507263, + "step": 6900 + }, + { + "epoch": 0.6415426690770871, + "grad_norm": 0.04636097546402966, + "learning_rate": 3.0097009677103472e-05, + "loss": 0.062421870231628415, + "step": 6920 + }, + { + "epoch": 0.6433968386408937, + "grad_norm": 0.04510143941986499, + "learning_rate": 2.9821926277848082e-05, + "loss": 0.062098950147628784, + "step": 6940 + }, + { + "epoch": 0.6452510082047003, + "grad_norm": 0.051468922824027076, + "learning_rate": 2.9547570533873316e-05, + "loss": 0.06206930875778198, + "step": 6960 + }, + { + "epoch": 0.647105177768507, + "grad_norm": 0.04447352421134208, + "learning_rate": 2.9273952338908805e-05, + "loss": 0.06005668640136719, + "step": 6980 + }, + { + "epoch": 0.6489593473323135, + "grad_norm": 0.04544630265467154, + "learning_rate": 2.900108156008693e-05, + "loss": 0.06390679478645325, + "step": 7000 + }, + { + "epoch": 0.6508135168961201, + "grad_norm": 0.0440316629640448, + "learning_rate": 2.8728968037586966e-05, + "loss": 0.061896789073944095, + "step": 7020 + }, + { + "epoch": 0.6526676864599268, + "grad_norm": 0.06308094532142822, + "learning_rate": 2.8457621584280282e-05, + "loss": 0.06296419501304626, + "step": 7040 + }, + { + "epoch": 0.6545218560237334, + "grad_norm": 0.04910828003002323, + "learning_rate": 2.8187051985376412e-05, + "loss": 0.06295238733291626, + "step": 7060 + }, + { + "epoch": 0.6563760255875399, + "grad_norm": 0.04902831553853863, + "learning_rate": 2.7917268998070245e-05, + "loss": 0.06277818083763123, + "step": 7080 + }, + { + "epoch": 0.6582301951513466, + "grad_norm": 0.04474910712199461, + "learning_rate": 2.764828235119008e-05, + "loss": 0.06296697854995728, + "step": 7100 + }, + { + "epoch": 0.6600843647151532, + "grad_norm": 0.045427696600719006, + "learning_rate": 2.7380101744846898e-05, + "loss": 0.06177424788475037, + "step": 7120 + }, + { + "epoch": 0.6619385342789598, + "grad_norm": 0.043537695583022555, + "learning_rate": 2.7112736850084476e-05, + "loss": 0.06221094131469727, + "step": 7140 + }, + { + "epoch": 0.6637927038427665, + "grad_norm": 0.047252055160959865, + "learning_rate": 2.6846197308530662e-05, + "loss": 0.06288429498672485, + "step": 7160 + }, + { + "epoch": 0.665646873406573, + "grad_norm": 0.04093048002300296, + "learning_rate": 2.6580492732049677e-05, + "loss": 0.061210185289382935, + "step": 7180 + }, + { + "epoch": 0.6675010429703796, + "grad_norm": 0.044138439067128124, + "learning_rate": 2.631563270239551e-05, + "loss": 0.060793828964233396, + "step": 7200 + }, + { + "epoch": 0.6693552125341863, + "grad_norm": 0.048270908164784763, + "learning_rate": 2.6051626770866343e-05, + "loss": 0.06118553876876831, + "step": 7220 + }, + { + "epoch": 0.6712093820979929, + "grad_norm": 0.04192358707110994, + "learning_rate": 2.5788484457960155e-05, + "loss": 0.06138489246368408, + "step": 7240 + }, + { + "epoch": 0.6730635516617994, + "grad_norm": 0.047264151685931725, + "learning_rate": 2.552621525303144e-05, + "loss": 0.06212824583053589, + "step": 7260 + }, + { + "epoch": 0.6749177212256061, + "grad_norm": 0.043126828895902566, + "learning_rate": 2.5264828613948842e-05, + "loss": 0.059517890214920044, + "step": 7280 + }, + { + "epoch": 0.6767718907894127, + "grad_norm": 0.04502796682666258, + "learning_rate": 2.500433396675428e-05, + "loss": 0.05914331078529358, + "step": 7300 + }, + { + "epoch": 0.6786260603532193, + "grad_norm": 0.046555462215773086, + "learning_rate": 2.4744740705322912e-05, + "loss": 0.06060423851013184, + "step": 7320 + }, + { + "epoch": 0.680480229917026, + "grad_norm": 0.047731159871982634, + "learning_rate": 2.448605819102442e-05, + "loss": 0.059140574932098386, + "step": 7340 + }, + { + "epoch": 0.6823343994808325, + "grad_norm": 0.04434178582787534, + "learning_rate": 2.42282957523854e-05, + "loss": 0.060806494951248166, + "step": 7360 + }, + { + "epoch": 0.6841885690446391, + "grad_norm": 0.05200993355357385, + "learning_rate": 2.3971462684752983e-05, + "loss": 0.06241018772125244, + "step": 7380 + }, + { + "epoch": 0.6860427386084458, + "grad_norm": 0.04451607128480399, + "learning_rate": 2.371556824995962e-05, + "loss": 0.06107102632522583, + "step": 7400 + }, + { + "epoch": 0.6878969081722524, + "grad_norm": 0.04672584936907622, + "learning_rate": 2.3460621675989075e-05, + "loss": 0.061403405666351316, + "step": 7420 + }, + { + "epoch": 0.6897510777360589, + "grad_norm": 0.043451300395321676, + "learning_rate": 2.320663215664366e-05, + "loss": 0.059847354888916016, + "step": 7440 + }, + { + "epoch": 0.6916052472998656, + "grad_norm": 0.042078989419009484, + "learning_rate": 2.2953608851212687e-05, + "loss": 0.06029091477394104, + "step": 7460 + }, + { + "epoch": 0.6934594168636722, + "grad_norm": 0.05215931582044261, + "learning_rate": 2.270156088414217e-05, + "loss": 0.06045289039611816, + "step": 7480 + }, + { + "epoch": 0.6953135864274788, + "grad_norm": 0.04304544077869624, + "learning_rate": 2.2450497344705794e-05, + "loss": 0.06151350736618042, + "step": 7500 + }, + { + "epoch": 0.6971677559912854, + "grad_norm": 0.042418084422899426, + "learning_rate": 2.2200427286677077e-05, + "loss": 0.05916010141372681, + "step": 7520 + }, + { + "epoch": 0.699021925555092, + "grad_norm": 0.044102051228497634, + "learning_rate": 2.195135972800299e-05, + "loss": 0.06019682884216308, + "step": 7540 + }, + { + "epoch": 0.7008760951188986, + "grad_norm": 0.03989097633004308, + "learning_rate": 2.170330365047865e-05, + "loss": 0.060142922401428225, + "step": 7560 + }, + { + "epoch": 0.7027302646827053, + "grad_norm": 0.04396154557734182, + "learning_rate": 2.1456267999423468e-05, + "loss": 0.06119601726531983, + "step": 7580 + }, + { + "epoch": 0.7045844342465118, + "grad_norm": 0.046452591818073735, + "learning_rate": 2.1210261683358595e-05, + "loss": 0.05998234748840332, + "step": 7600 + }, + { + "epoch": 0.7064386038103184, + "grad_norm": 0.041849405904192685, + "learning_rate": 2.0965293573685595e-05, + "loss": 0.059972834587097165, + "step": 7620 + }, + { + "epoch": 0.7082927733741251, + "grad_norm": 0.04648194004262054, + "learning_rate": 2.072137250436657e-05, + "loss": 0.061202061176300046, + "step": 7640 + }, + { + "epoch": 0.7101469429379317, + "grad_norm": 0.04203816172547841, + "learning_rate": 2.0478507271605583e-05, + "loss": 0.05759580135345459, + "step": 7660 + }, + { + "epoch": 0.7120011125017383, + "grad_norm": 0.04159246437703577, + "learning_rate": 2.023670663353146e-05, + "loss": 0.05981243848800659, + "step": 7680 + }, + { + "epoch": 0.7138552820655449, + "grad_norm": 0.04558860752127258, + "learning_rate": 1.9995979309881975e-05, + "loss": 0.05943760871887207, + "step": 7700 + }, + { + "epoch": 0.7157094516293515, + "grad_norm": 0.04168710404499, + "learning_rate": 1.9756333981689308e-05, + "loss": 0.05771678686141968, + "step": 7720 + }, + { + "epoch": 0.7175636211931581, + "grad_norm": 0.04112165344234754, + "learning_rate": 1.951777929096713e-05, + "loss": 0.060441124439239505, + "step": 7740 + }, + { + "epoch": 0.7194177907569648, + "grad_norm": 0.04588808450921567, + "learning_rate": 1.9280323840398872e-05, + "loss": 0.060588645935058597, + "step": 7760 + }, + { + "epoch": 0.7212719603207713, + "grad_norm": 0.0423833586200973, + "learning_rate": 1.904397619302752e-05, + "loss": 0.059179884195327756, + "step": 7780 + }, + { + "epoch": 0.7231261298845779, + "grad_norm": 0.04360990379593918, + "learning_rate": 1.8808744871946794e-05, + "loss": 0.060727423429489134, + "step": 7800 + }, + { + "epoch": 0.7249802994483846, + "grad_norm": 0.044329689258979815, + "learning_rate": 1.8574638359993825e-05, + "loss": 0.05868118405342102, + "step": 7820 + }, + { + "epoch": 0.7268344690121912, + "grad_norm": 0.05481220787679917, + "learning_rate": 1.8341665099443235e-05, + "loss": 0.061199039220809937, + "step": 7840 + }, + { + "epoch": 0.7286886385759977, + "grad_norm": 0.04355173821302689, + "learning_rate": 1.8109833491702695e-05, + "loss": 0.06120600700378418, + "step": 7860 + }, + { + "epoch": 0.7305428081398044, + "grad_norm": 0.047542762018884, + "learning_rate": 1.7879151897009943e-05, + "loss": 0.05963542461395264, + "step": 7880 + }, + { + "epoch": 0.732396977703611, + "grad_norm": 0.04859362398408984, + "learning_rate": 1.7649628634131326e-05, + "loss": 0.05993167161941528, + "step": 7900 + }, + { + "epoch": 0.7342511472674176, + "grad_norm": 0.07696156343679936, + "learning_rate": 1.74212719800618e-05, + "loss": 0.05901572108268738, + "step": 7920 + }, + { + "epoch": 0.7361053168312243, + "grad_norm": 0.04571216891813866, + "learning_rate": 1.7194090169726417e-05, + "loss": 0.06098179817199707, + "step": 7940 + }, + { + "epoch": 0.7379594863950308, + "grad_norm": 0.042788171803501564, + "learning_rate": 1.6968091395683428e-05, + "loss": 0.058015406131744385, + "step": 7960 + }, + { + "epoch": 0.7398136559588374, + "grad_norm": 0.060228689880550704, + "learning_rate": 1.6743283807828776e-05, + "loss": 0.059897661209106445, + "step": 7980 + }, + { + "epoch": 0.7416678255226441, + "grad_norm": 0.045260107901039764, + "learning_rate": 1.6519675513102228e-05, + "loss": 0.06034721732139588, + "step": 8000 + }, + { + "epoch": 0.7435219950864507, + "grad_norm": 0.042569996313028956, + "learning_rate": 1.629727457519505e-05, + "loss": 0.05882605314254761, + "step": 8020 + }, + { + "epoch": 0.7453761646502572, + "grad_norm": 0.04035259949630576, + "learning_rate": 1.607608901425915e-05, + "loss": 0.05778524875640869, + "step": 8040 + }, + { + "epoch": 0.7472303342140639, + "grad_norm": 0.04381818680813006, + "learning_rate": 1.5856126806617932e-05, + "loss": 0.05960347652435303, + "step": 8060 + }, + { + "epoch": 0.7490845037778705, + "grad_norm": 0.041521924269364706, + "learning_rate": 1.5637395884478607e-05, + "loss": 0.05910018682479858, + "step": 8080 + }, + { + "epoch": 0.7509386733416771, + "grad_norm": 0.04483661643227132, + "learning_rate": 1.5419904135646156e-05, + "loss": 0.05863996744155884, + "step": 8100 + }, + { + "epoch": 0.7527928429054838, + "grad_norm": 0.04170345267394013, + "learning_rate": 1.5203659403238918e-05, + "loss": 0.06005077362060547, + "step": 8120 + }, + { + "epoch": 0.7546470124692903, + "grad_norm": 0.04314173300757244, + "learning_rate": 1.4988669485405654e-05, + "loss": 0.06016584038734436, + "step": 8140 + }, + { + "epoch": 0.7565011820330969, + "grad_norm": 0.042521117092671874, + "learning_rate": 1.4774942135044467e-05, + "loss": 0.06094483137130737, + "step": 8160 + }, + { + "epoch": 0.7583553515969035, + "grad_norm": 0.03935765032771935, + "learning_rate": 1.4562485059523123e-05, + "loss": 0.05919557809829712, + "step": 8180 + }, + { + "epoch": 0.7602095211607102, + "grad_norm": 0.0465010858441232, + "learning_rate": 1.4351305920401148e-05, + "loss": 0.05924775004386902, + "step": 8200 + }, + { + "epoch": 0.7620636907245167, + "grad_norm": 0.041847767906551384, + "learning_rate": 1.4141412333153531e-05, + "loss": 0.05741736888885498, + "step": 8220 + }, + { + "epoch": 0.7639178602883233, + "grad_norm": 0.04556519610235416, + "learning_rate": 1.39328118668961e-05, + "loss": 0.06202120184898376, + "step": 8240 + }, + { + "epoch": 0.76577202985213, + "grad_norm": 0.03944873638533435, + "learning_rate": 1.3725512044112555e-05, + "loss": 0.05924309492111206, + "step": 8260 + }, + { + "epoch": 0.7676261994159366, + "grad_norm": 0.043579723817803145, + "learning_rate": 1.3519520340383202e-05, + "loss": 0.05931833982467651, + "step": 8280 + }, + { + "epoch": 0.7694803689797431, + "grad_norm": 0.04250241195591931, + "learning_rate": 1.3314844184115405e-05, + "loss": 0.05921122431755066, + "step": 8300 + }, + { + "epoch": 0.7713345385435498, + "grad_norm": 0.040768383521444185, + "learning_rate": 1.3111490956275663e-05, + "loss": 0.05935220122337341, + "step": 8320 + }, + { + "epoch": 0.7731887081073564, + "grad_norm": 0.040466842442575784, + "learning_rate": 1.2909467990123402e-05, + "loss": 0.0584735095500946, + "step": 8340 + }, + { + "epoch": 0.775042877671163, + "grad_norm": 0.04578923242449133, + "learning_rate": 1.270878257094663e-05, + "loss": 0.05790427327156067, + "step": 8360 + }, + { + "epoch": 0.7768970472349697, + "grad_norm": 0.04015645828975025, + "learning_rate": 1.2509441935799139e-05, + "loss": 0.05840156078338623, + "step": 8380 + }, + { + "epoch": 0.7787512167987762, + "grad_norm": 0.04505252691393977, + "learning_rate": 1.2311453273239548e-05, + "loss": 0.0588322639465332, + "step": 8400 + }, + { + "epoch": 0.7806053863625828, + "grad_norm": 0.04616645906001549, + "learning_rate": 1.2114823723072077e-05, + "loss": 0.05915929079055786, + "step": 8420 + }, + { + "epoch": 0.7824595559263895, + "grad_norm": 0.038235671796898386, + "learning_rate": 1.1919560376089062e-05, + "loss": 0.05861332416534424, + "step": 8440 + }, + { + "epoch": 0.7843137254901961, + "grad_norm": 0.04185333629619464, + "learning_rate": 1.1725670273815248e-05, + "loss": 0.05743967890739441, + "step": 8460 + }, + { + "epoch": 0.7861678950540026, + "grad_norm": 0.0452666487111135, + "learning_rate": 1.1533160408253879e-05, + "loss": 0.056289541721344, + "step": 8480 + }, + { + "epoch": 0.7880220646178093, + "grad_norm": 0.041946528912211886, + "learning_rate": 1.134203772163453e-05, + "loss": 0.05721364617347717, + "step": 8500 + }, + { + "epoch": 0.7898762341816159, + "grad_norm": 0.04391208195397317, + "learning_rate": 1.1152309106162777e-05, + "loss": 0.058383059501647946, + "step": 8520 + }, + { + "epoch": 0.7917304037454225, + "grad_norm": 0.04316038206952691, + "learning_rate": 1.096398140377164e-05, + "loss": 0.059176528453826906, + "step": 8540 + }, + { + "epoch": 0.7935845733092292, + "grad_norm": 0.047489102105126565, + "learning_rate": 1.0777061405874872e-05, + "loss": 0.05802996158599853, + "step": 8560 + }, + { + "epoch": 0.7954387428730357, + "grad_norm": 0.04540449359760401, + "learning_rate": 1.0591555853121998e-05, + "loss": 0.05956486463546753, + "step": 8580 + }, + { + "epoch": 0.7972929124368423, + "grad_norm": 0.03887464619210056, + "learning_rate": 1.0407471435155313e-05, + "loss": 0.05859973430633545, + "step": 8600 + }, + { + "epoch": 0.799147082000649, + "grad_norm": 0.0423623187098013, + "learning_rate": 1.0224814790368558e-05, + "loss": 0.05868813991546631, + "step": 8620 + }, + { + "epoch": 0.8010012515644556, + "grad_norm": 0.04291959975527767, + "learning_rate": 1.0043592505667632e-05, + "loss": 0.057529407739639285, + "step": 8640 + }, + { + "epoch": 0.8028554211282621, + "grad_norm": 0.04161053163954707, + "learning_rate": 9.863811116232946e-06, + "loss": 0.057827317714691163, + "step": 8660 + }, + { + "epoch": 0.8047095906920688, + "grad_norm": 0.039652467368728676, + "learning_rate": 9.685477105283825e-06, + "loss": 0.05748317241668701, + "step": 8680 + }, + { + "epoch": 0.8065637602558754, + "grad_norm": 0.0463013238541496, + "learning_rate": 9.508596903844668e-06, + "loss": 0.05913045406341553, + "step": 8700 + }, + { + "epoch": 0.808417929819682, + "grad_norm": 0.039819163372741787, + "learning_rate": 9.333176890513095e-06, + "loss": 0.05958133339881897, + "step": 8720 + }, + { + "epoch": 0.8102720993834887, + "grad_norm": 0.041806269641331766, + "learning_rate": 9.15922339122986e-06, + "loss": 0.05868912935256958, + "step": 8740 + }, + { + "epoch": 0.8121262689472952, + "grad_norm": 0.03828066923207382, + "learning_rate": 8.986742679050764e-06, + "loss": 0.05822650790214538, + "step": 8760 + }, + { + "epoch": 0.8139804385111018, + "grad_norm": 0.04169883461469084, + "learning_rate": 8.815740973920411e-06, + "loss": 0.05828083753585815, + "step": 8780 + }, + { + "epoch": 0.8158346080749085, + "grad_norm": 0.040155940979838246, + "learning_rate": 8.646224442447937e-06, + "loss": 0.05864385366439819, + "step": 8800 + }, + { + "epoch": 0.8176887776387151, + "grad_norm": 0.04793987505855137, + "learning_rate": 8.478199197684627e-06, + "loss": 0.060294324159622194, + "step": 8820 + }, + { + "epoch": 0.8195429472025216, + "grad_norm": 0.043479469746193086, + "learning_rate": 8.311671298903439e-06, + "loss": 0.058967453241348264, + "step": 8840 + }, + { + "epoch": 0.8213971167663283, + "grad_norm": 0.0453819372959514, + "learning_rate": 8.146646751380532e-06, + "loss": 0.057421672344207766, + "step": 8860 + }, + { + "epoch": 0.8232512863301349, + "grad_norm": 0.04145958828741325, + "learning_rate": 7.983131506178676e-06, + "loss": 0.05738742351531982, + "step": 8880 + }, + { + "epoch": 0.8251054558939415, + "grad_norm": 0.04270621605428974, + "learning_rate": 7.821131459932673e-06, + "loss": 0.05822542905807495, + "step": 8900 + }, + { + "epoch": 0.8269596254577481, + "grad_norm": 0.03988428126639982, + "learning_rate": 7.660652454636696e-06, + "loss": 0.055188226699829104, + "step": 8920 + }, + { + "epoch": 0.8288137950215547, + "grad_norm": 0.0444594845643032, + "learning_rate": 7.501700277433621e-06, + "loss": 0.059385663270950316, + "step": 8940 + }, + { + "epoch": 0.8306679645853613, + "grad_norm": 0.04895959613153919, + "learning_rate": 7.344280660406333e-06, + "loss": 0.058476173877716066, + "step": 8960 + }, + { + "epoch": 0.832522134149168, + "grad_norm": 0.046447821589595005, + "learning_rate": 7.188399280371033e-06, + "loss": 0.05890741944313049, + "step": 8980 + }, + { + "epoch": 0.8343763037129746, + "grad_norm": 0.040919231212288, + "learning_rate": 7.034061758672489e-06, + "loss": 0.057273268699645996, + "step": 9000 + }, + { + "epoch": 0.8362304732767811, + "grad_norm": 0.04341624851269591, + "learning_rate": 6.881273660981352e-06, + "loss": 0.06076174974441528, + "step": 9020 + }, + { + "epoch": 0.8380846428405878, + "grad_norm": 0.04407832512819701, + "learning_rate": 6.730040497093437e-06, + "loss": 0.05773304700851441, + "step": 9040 + }, + { + "epoch": 0.8399388124043944, + "grad_norm": 0.045206674958552885, + "learning_rate": 6.580367720731029e-06, + "loss": 0.057690989971160886, + "step": 9060 + }, + { + "epoch": 0.841792981968201, + "grad_norm": 0.04184821375620571, + "learning_rate": 6.4322607293462065e-06, + "loss": 0.05713052749633789, + "step": 9080 + }, + { + "epoch": 0.8436471515320076, + "grad_norm": 0.04260664949525322, + "learning_rate": 6.285724863926224e-06, + "loss": 0.05859750509262085, + "step": 9100 + }, + { + "epoch": 0.8455013210958142, + "grad_norm": 0.040353521145304376, + "learning_rate": 6.140765408800869e-06, + "loss": 0.05815015435218811, + "step": 9120 + }, + { + "epoch": 0.8473554906596208, + "grad_norm": 0.04308098450102359, + "learning_rate": 5.997387591451947e-06, + "loss": 0.05699597597122193, + "step": 9140 + }, + { + "epoch": 0.8492096602234275, + "grad_norm": 0.04208165862880175, + "learning_rate": 5.855596582324724e-06, + "loss": 0.05847395658493042, + "step": 9160 + }, + { + "epoch": 0.851063829787234, + "grad_norm": 0.04278651313519997, + "learning_rate": 5.7153974946415165e-06, + "loss": 0.05857234001159668, + "step": 9180 + }, + { + "epoch": 0.8529179993510406, + "grad_norm": 0.04300820482667514, + "learning_rate": 5.576795384217232e-06, + "loss": 0.057513868808746337, + "step": 9200 + }, + { + "epoch": 0.8547721689148473, + "grad_norm": 0.04184979151941222, + "learning_rate": 5.439795249277141e-06, + "loss": 0.05662814378738403, + "step": 9220 + }, + { + "epoch": 0.8566263384786539, + "grad_norm": 0.04238638559267024, + "learning_rate": 5.304402030276551e-06, + "loss": 0.05687806010246277, + "step": 9240 + }, + { + "epoch": 0.8584805080424605, + "grad_norm": 0.04160902207940939, + "learning_rate": 5.1706206097226925e-06, + "loss": 0.05730761289596557, + "step": 9260 + }, + { + "epoch": 0.8603346776062671, + "grad_norm": 0.05031467787868118, + "learning_rate": 5.038455811998627e-06, + "loss": 0.05795542001724243, + "step": 9280 + }, + { + "epoch": 0.8621888471700737, + "grad_norm": 0.041455506138344166, + "learning_rate": 4.907912403189285e-06, + "loss": 0.05497853755950928, + "step": 9300 + }, + { + "epoch": 0.8640430167338803, + "grad_norm": 0.04730451151432445, + "learning_rate": 4.77899509090956e-06, + "loss": 0.05861245393753052, + "step": 9320 + }, + { + "epoch": 0.865897186297687, + "grad_norm": 0.042890295818311636, + "learning_rate": 4.651708524134624e-06, + "loss": 0.05678141713142395, + "step": 9340 + }, + { + "epoch": 0.8677513558614935, + "grad_norm": 0.04472612219626013, + "learning_rate": 4.52605729303216e-06, + "loss": 0.0577523946762085, + "step": 9360 + }, + { + "epoch": 0.8696055254253001, + "grad_norm": 0.04405663125228961, + "learning_rate": 4.402045928796944e-06, + "loss": 0.058051574230194095, + "step": 9380 + }, + { + "epoch": 0.8714596949891068, + "grad_norm": 0.03734709383772662, + "learning_rate": 4.279678903487355e-06, + "loss": 0.056524813175201416, + "step": 9400 + }, + { + "epoch": 0.8733138645529134, + "grad_norm": 0.04367894462048559, + "learning_rate": 4.158960629864167e-06, + "loss": 0.05766661167144775, + "step": 9420 + }, + { + "epoch": 0.87516803411672, + "grad_norm": 0.043940010716802015, + "learning_rate": 4.039895461231396e-06, + "loss": 0.05792294144630432, + "step": 9440 + }, + { + "epoch": 0.8770222036805266, + "grad_norm": 0.04157334593197274, + "learning_rate": 3.922487691279309e-06, + "loss": 0.05697953701019287, + "step": 9460 + }, + { + "epoch": 0.8788763732443332, + "grad_norm": 0.04280963353466024, + "learning_rate": 3.806741553929577e-06, + "loss": 0.05770295858383179, + "step": 9480 + }, + { + "epoch": 0.8807305428081398, + "grad_norm": 0.04360315147910498, + "learning_rate": 3.6926612231826197e-06, + "loss": 0.056513524055480956, + "step": 9500 + }, + { + "epoch": 0.8825847123719465, + "grad_norm": 0.0433451861162174, + "learning_rate": 3.5802508129670564e-06, + "loss": 0.05862005949020386, + "step": 9520 + }, + { + "epoch": 0.884438881935753, + "grad_norm": 0.04073468808567981, + "learning_rate": 3.4695143769913784e-06, + "loss": 0.05859295129776001, + "step": 9540 + }, + { + "epoch": 0.8862930514995596, + "grad_norm": 0.04239051801792883, + "learning_rate": 3.3604559085977317e-06, + "loss": 0.057581615447998044, + "step": 9560 + }, + { + "epoch": 0.8881472210633663, + "grad_norm": 0.041622529510343655, + "learning_rate": 3.253079340617937e-06, + "loss": 0.0586451530456543, + "step": 9580 + }, + { + "epoch": 0.8900013906271729, + "grad_norm": 0.04111746214218652, + "learning_rate": 3.1473885452316665e-06, + "loss": 0.05632882118225098, + "step": 9600 + }, + { + "epoch": 0.8918555601909794, + "grad_norm": 0.04096285048135897, + "learning_rate": 3.0433873338267915e-06, + "loss": 0.058455199003219604, + "step": 9620 + }, + { + "epoch": 0.893709729754786, + "grad_norm": 0.042381302291485984, + "learning_rate": 2.941079456861917e-06, + "loss": 0.05593242645263672, + "step": 9640 + }, + { + "epoch": 0.8955638993185927, + "grad_norm": 0.044748109156357865, + "learning_rate": 2.840468603731189e-06, + "loss": 0.05731314420700073, + "step": 9660 + }, + { + "epoch": 0.8974180688823993, + "grad_norm": 0.04319157638334523, + "learning_rate": 2.7415584026312223e-06, + "loss": 0.058256596326828, + "step": 9680 + }, + { + "epoch": 0.8992722384462059, + "grad_norm": 0.04388308005862721, + "learning_rate": 2.644352420430246e-06, + "loss": 0.05611896514892578, + "step": 9700 + }, + { + "epoch": 0.9011264080100125, + "grad_norm": 0.04519528134021101, + "learning_rate": 2.5488541625394933e-06, + "loss": 0.05943126082420349, + "step": 9720 + }, + { + "epoch": 0.9029805775738191, + "grad_norm": 0.04251086029166456, + "learning_rate": 2.4550670727867763e-06, + "loss": 0.05685185194015503, + "step": 9740 + }, + { + "epoch": 0.9048347471376257, + "grad_norm": 0.03944944934977318, + "learning_rate": 2.362994533292323e-06, + "loss": 0.05601794123649597, + "step": 9760 + }, + { + "epoch": 0.9066889167014324, + "grad_norm": 0.044177980988593026, + "learning_rate": 2.272639864346776e-06, + "loss": 0.05724194049835205, + "step": 9780 + }, + { + "epoch": 0.9085430862652389, + "grad_norm": 0.04189831748981764, + "learning_rate": 2.1840063242915045e-06, + "loss": 0.056692618131637576, + "step": 9800 + }, + { + "epoch": 0.9103972558290455, + "grad_norm": 0.043673059482412624, + "learning_rate": 2.0970971094010305e-06, + "loss": 0.05840623378753662, + "step": 9820 + }, + { + "epoch": 0.9122514253928522, + "grad_norm": 0.045504438871193945, + "learning_rate": 2.0119153537678513e-06, + "loss": 0.05786421298980713, + "step": 9840 + }, + { + "epoch": 0.9141055949566588, + "grad_norm": 0.04557063826056399, + "learning_rate": 1.9284641291893615e-06, + "loss": 0.057442504167556765, + "step": 9860 + }, + { + "epoch": 0.9159597645204653, + "grad_norm": 0.04545043254971616, + "learning_rate": 1.8467464450570903e-06, + "loss": 0.05783541202545166, + "step": 9880 + }, + { + "epoch": 0.917813934084272, + "grad_norm": 0.04107832026051421, + "learning_rate": 1.7667652482481922e-06, + "loss": 0.058336269855499265, + "step": 9900 + }, + { + "epoch": 0.9196681036480786, + "grad_norm": 0.041143537773437405, + "learning_rate": 1.6885234230191615e-06, + "loss": 0.05814253091812134, + "step": 9920 + }, + { + "epoch": 0.9215222732118852, + "grad_norm": 0.04132684264242279, + "learning_rate": 1.6120237909018287e-06, + "loss": 0.055842363834381105, + "step": 9940 + }, + { + "epoch": 0.9233764427756919, + "grad_norm": 0.043378747724282775, + "learning_rate": 1.5372691106016135e-06, + "loss": 0.05697543621063232, + "step": 9960 + }, + { + "epoch": 0.9252306123394984, + "grad_norm": 0.043723662998569265, + "learning_rate": 1.464262077898032e-06, + "loss": 0.05675085783004761, + "step": 9980 + }, + { + "epoch": 0.927084781903305, + "grad_norm": 0.0413347860452099, + "learning_rate": 1.3930053255474863e-06, + "loss": 0.05656332969665527, + "step": 10000 + }, + { + "epoch": 0.9289389514671117, + "grad_norm": 0.042641886326804886, + "learning_rate": 1.3235014231883391e-06, + "loss": 0.05754779577255249, + "step": 10020 + }, + { + "epoch": 0.9307931210309183, + "grad_norm": 0.04240135883945068, + "learning_rate": 1.2557528772482175e-06, + "loss": 0.05811010599136353, + "step": 10040 + }, + { + "epoch": 0.9326472905947248, + "grad_norm": 0.04366464083419553, + "learning_rate": 1.1897621308536556e-06, + "loss": 0.057920646667480466, + "step": 10060 + }, + { + "epoch": 0.9345014601585315, + "grad_norm": 0.04251203177049702, + "learning_rate": 1.125531563741966e-06, + "loss": 0.05935220718383789, + "step": 10080 + }, + { + "epoch": 0.9363556297223381, + "grad_norm": 0.043375762175896594, + "learning_rate": 1.0630634921754478e-06, + "loss": 0.05946972370147705, + "step": 10100 + }, + { + "epoch": 0.9382097992861447, + "grad_norm": 0.038546399018732955, + "learning_rate": 1.0023601688578467e-06, + "loss": 0.05542746782302856, + "step": 10120 + }, + { + "epoch": 0.9400639688499514, + "grad_norm": 0.046981608590331715, + "learning_rate": 9.434237828531034e-07, + "loss": 0.058707261085510255, + "step": 10140 + }, + { + "epoch": 0.9419181384137579, + "grad_norm": 0.04263830532013562, + "learning_rate": 8.862564595064349e-07, + "loss": 0.05690791606903076, + "step": 10160 + }, + { + "epoch": 0.9437723079775645, + "grad_norm": 0.04582874833814285, + "learning_rate": 8.30860260367694e-07, + "loss": 0.054658901691436765, + "step": 10180 + }, + { + "epoch": 0.9456264775413712, + "grad_norm": 0.048305071305060066, + "learning_rate": 7.772371831170022e-07, + "loss": 0.05803183317184448, + "step": 10200 + }, + { + "epoch": 0.9474806471051778, + "grad_norm": 0.0424560803178508, + "learning_rate": 7.253891614927177e-07, + "loss": 0.05667737126350403, + "step": 10220 + }, + { + "epoch": 0.9493348166689843, + "grad_norm": 0.04137248823550589, + "learning_rate": 6.753180652217306e-07, + "loss": 0.05827021598815918, + "step": 10240 + }, + { + "epoch": 0.951188986232791, + "grad_norm": 0.04384442951859904, + "learning_rate": 6.270256999519885e-07, + "loss": 0.05811399817466736, + "step": 10260 + }, + { + "epoch": 0.9530431557965976, + "grad_norm": 0.04076128530415887, + "learning_rate": 5.805138071874161e-07, + "loss": 0.05737486481666565, + "step": 10280 + }, + { + "epoch": 0.9548973253604042, + "grad_norm": 0.04109366675767673, + "learning_rate": 5.357840642251089e-07, + "loss": 0.05651825666427612, + "step": 10300 + }, + { + "epoch": 0.9567514949242109, + "grad_norm": 0.042700389903543114, + "learning_rate": 4.928380840948377e-07, + "loss": 0.05737701654434204, + "step": 10320 + }, + { + "epoch": 0.9586056644880174, + "grad_norm": 0.038933652888396515, + "learning_rate": 4.5167741550088406e-07, + "loss": 0.05547755360603333, + "step": 10340 + }, + { + "epoch": 0.960459834051824, + "grad_norm": 0.04499435022161428, + "learning_rate": 4.12303542766207e-07, + "loss": 0.056265252828598025, + "step": 10360 + }, + { + "epoch": 0.9623140036156307, + "grad_norm": 0.052695850731408304, + "learning_rate": 3.747178857788802e-07, + "loss": 0.05831778049468994, + "step": 10380 + }, + { + "epoch": 0.9641681731794373, + "grad_norm": 0.041355706582808766, + "learning_rate": 3.389217999409222e-07, + "loss": 0.05711444616317749, + "step": 10400 + }, + { + "epoch": 0.9660223427432438, + "grad_norm": 0.04541694220798916, + "learning_rate": 3.0491657611939615e-07, + "loss": 0.05954468250274658, + "step": 10420 + }, + { + "epoch": 0.9678765123070505, + "grad_norm": 0.037048819417347126, + "learning_rate": 2.7270344059988074e-07, + "loss": 0.058045947551727296, + "step": 10440 + }, + { + "epoch": 0.9697306818708571, + "grad_norm": 0.04118746781043515, + "learning_rate": 2.4228355504222756e-07, + "loss": 0.05838167667388916, + "step": 10460 + }, + { + "epoch": 0.9715848514346637, + "grad_norm": 0.04512917614986576, + "learning_rate": 2.1365801643868366e-07, + "loss": 0.05804737210273743, + "step": 10480 + }, + { + "epoch": 0.9734390209984704, + "grad_norm": 0.04157722297753857, + "learning_rate": 1.8682785707431205e-07, + "loss": 0.05664463639259339, + "step": 10500 + }, + { + "epoch": 0.9752931905622769, + "grad_norm": 0.042394494386684016, + "learning_rate": 1.6179404448980474e-07, + "loss": 0.056443202495574954, + "step": 10520 + }, + { + "epoch": 0.9771473601260835, + "grad_norm": 0.04209941914717253, + "learning_rate": 1.38557481446544e-07, + "loss": 0.0574646532535553, + "step": 10540 + }, + { + "epoch": 0.9790015296898902, + "grad_norm": 0.0368439030248634, + "learning_rate": 1.1711900589408409e-07, + "loss": 0.05568208694458008, + "step": 10560 + }, + { + "epoch": 0.9808556992536968, + "grad_norm": 0.043675112327923045, + "learning_rate": 9.74793909399141e-08, + "loss": 0.05898926854133606, + "step": 10580 + }, + { + "epoch": 0.9827098688175033, + "grad_norm": 0.043385754999838926, + "learning_rate": 7.963934482158597e-08, + "loss": 0.05666929483413696, + "step": 10600 + }, + { + "epoch": 0.98456403838131, + "grad_norm": 0.042106162195492784, + "learning_rate": 6.359951088117933e-08, + "loss": 0.05665904879570007, + "step": 10620 + }, + { + "epoch": 0.9864182079451166, + "grad_norm": 0.04469787281700635, + "learning_rate": 4.936046754207557e-08, + "loss": 0.05817822813987732, + "step": 10640 + }, + { + "epoch": 0.9882723775089232, + "grad_norm": 0.04979760711070391, + "learning_rate": 3.69227282881357e-08, + "loss": 0.057973289489746095, + "step": 10660 + }, + { + "epoch": 0.9901265470727298, + "grad_norm": 0.043219446213679145, + "learning_rate": 2.628674164515954e-08, + "loss": 0.057922327518463136, + "step": 10680 + }, + { + "epoch": 0.9919807166365364, + "grad_norm": 0.03814284539819102, + "learning_rate": 1.745289116471538e-08, + "loss": 0.05686279535293579, + "step": 10700 + }, + { + "epoch": 0.993834886200343, + "grad_norm": 0.04435709286094493, + "learning_rate": 1.042149541031212e-08, + "loss": 0.05729717016220093, + "step": 10720 + }, + { + "epoch": 0.9956890557641497, + "grad_norm": 0.043708263904856166, + "learning_rate": 5.192807945902934e-09, + "loss": 0.05722014904022217, + "step": 10740 + }, + { + "epoch": 0.9975432253279563, + "grad_norm": 0.04332449630622139, + "learning_rate": 1.767017326764764e-09, + "loss": 0.059349268674850464, + "step": 10760 + }, + { + "epoch": 0.9993973948917628, + "grad_norm": 0.0389811994209693, + "learning_rate": 1.4424709265936642e-10, + "loss": 0.056857752799987796, + "step": 10780 + }, + { + "epoch": 1.0, + "step": 10787, + "total_flos": 5228992760119296.0, + "train_loss": 0.07239722475082117, + "train_runtime": 152754.4145, + "train_samples_per_second": 1.13, + "train_steps_per_second": 0.071 + } + ], + "logging_steps": 20, + "max_steps": 10787, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 5228992760119296.0, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..e3cf5bd --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6744cccb22c55327336ea599e38c0192fb1e8501751c8600f1c939cb9ebcd158 +size 6968