| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007022225343211264, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.4044450686422528e-05, | |
| "eval_loss": 0.7164075374603271, | |
| "eval_runtime": 961.2364, | |
| "eval_samples_per_second": 15.594, | |
| "eval_steps_per_second": 7.797, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014044450686422527, | |
| "grad_norm": 0.8396145105361938, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.6, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00018257785892349286, | |
| "eval_loss": 0.4354195296764374, | |
| "eval_runtime": 959.169, | |
| "eval_samples_per_second": 15.628, | |
| "eval_steps_per_second": 7.814, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00028088901372845055, | |
| "grad_norm": 0.7152711153030396, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.3656, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003651557178469857, | |
| "eval_loss": 0.3878459334373474, | |
| "eval_runtime": 958.831, | |
| "eval_samples_per_second": 15.634, | |
| "eval_steps_per_second": 7.817, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0004213335205926758, | |
| "grad_norm": 0.5551108717918396, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.3513, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005477335767704786, | |
| "eval_loss": 0.3726792335510254, | |
| "eval_runtime": 958.9138, | |
| "eval_samples_per_second": 15.632, | |
| "eval_steps_per_second": 7.816, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0005617780274569011, | |
| "grad_norm": 0.4752677083015442, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.3202, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0007022225343211264, | |
| "grad_norm": 0.4160292148590088, | |
| "learning_rate": 0.0, | |
| "loss": 0.3444, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8846302305583104.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |