| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007801833430856252, | |
| "eval_steps": 3, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001300305571809375, | |
| "grad_norm": 0.031008053570985794, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3786, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001300305571809375, | |
| "eval_loss": 10.3822660446167, | |
| "eval_runtime": 9.6789, | |
| "eval_samples_per_second": 334.644, | |
| "eval_steps_per_second": 167.374, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000260061114361875, | |
| "grad_norm": 0.03545593470335007, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3779, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003900916715428126, | |
| "grad_norm": 0.03853485360741615, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003900916715428126, | |
| "eval_loss": 10.38223648071289, | |
| "eval_runtime": 9.7152, | |
| "eval_samples_per_second": 333.396, | |
| "eval_steps_per_second": 166.75, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00052012222872375, | |
| "grad_norm": 0.037035856395959854, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3809, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006501527859046876, | |
| "grad_norm": 0.03260985389351845, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3817, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007801833430856252, | |
| "grad_norm": 0.033107344061136246, | |
| "learning_rate": 0.00012, | |
| "loss": 10.377, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007801833430856252, | |
| "eval_loss": 10.382102966308594, | |
| "eval_runtime": 9.7751, | |
| "eval_samples_per_second": 331.351, | |
| "eval_steps_per_second": 165.727, | |
| "step": 6 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 161636352000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |