| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01638001638001638, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001638001638001638, | |
| "grad_norm": 5.249002933502197, | |
| "learning_rate": 2e-05, | |
| "loss": 3.1443, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001638001638001638, | |
| "eval_loss": 3.0673675537109375, | |
| "eval_runtime": 6.5322, | |
| "eval_samples_per_second": 39.497, | |
| "eval_steps_per_second": 19.748, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003276003276003276, | |
| "grad_norm": 3.6380615234375, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9126, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004914004914004914, | |
| "grad_norm": 5.660929203033447, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9545, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004914004914004914, | |
| "eval_loss": 3.0659334659576416, | |
| "eval_runtime": 5.8628, | |
| "eval_samples_per_second": 44.006, | |
| "eval_steps_per_second": 22.003, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006552006552006552, | |
| "grad_norm": 7.41387414932251, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1492, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00819000819000819, | |
| "grad_norm": 3.9331319332122803, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8614, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009828009828009828, | |
| "grad_norm": 3.552950143814087, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9855, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009828009828009828, | |
| "eval_loss": 3.0527846813201904, | |
| "eval_runtime": 5.9655, | |
| "eval_samples_per_second": 43.249, | |
| "eval_steps_per_second": 21.625, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011466011466011465, | |
| "grad_norm": 5.114128112792969, | |
| "learning_rate": 0.00014, | |
| "loss": 2.658, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013104013104013105, | |
| "grad_norm": 5.544708728790283, | |
| "learning_rate": 0.00016, | |
| "loss": 2.9712, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014742014742014743, | |
| "grad_norm": 3.2389752864837646, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8572, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014742014742014743, | |
| "eval_loss": 3.007380485534668, | |
| "eval_runtime": 5.9348, | |
| "eval_samples_per_second": 43.473, | |
| "eval_steps_per_second": 21.736, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01638001638001638, | |
| "grad_norm": 5.132890701293945, | |
| "learning_rate": 0.0002, | |
| "loss": 2.5909, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 653821948723200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |