| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0030747943731262973, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00030747943731262973, | |
| "grad_norm": 4.839503765106201, | |
| "learning_rate": 2e-05, | |
| "loss": 7.5076, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00030747943731262973, | |
| "eval_loss": 8.116337776184082, | |
| "eval_runtime": 41.8717, | |
| "eval_samples_per_second": 32.719, | |
| "eval_steps_per_second": 16.359, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006149588746252595, | |
| "grad_norm": 5.878857612609863, | |
| "learning_rate": 4e-05, | |
| "loss": 7.9647, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009224383119378892, | |
| "grad_norm": 6.081296920776367, | |
| "learning_rate": 6e-05, | |
| "loss": 7.6554, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009224383119378892, | |
| "eval_loss": 8.096881866455078, | |
| "eval_runtime": 40.4417, | |
| "eval_samples_per_second": 33.876, | |
| "eval_steps_per_second": 16.938, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001229917749250519, | |
| "grad_norm": 4.793824195861816, | |
| "learning_rate": 8e-05, | |
| "loss": 5.5741, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015373971865631486, | |
| "grad_norm": 6.256138801574707, | |
| "learning_rate": 0.0001, | |
| "loss": 9.0043, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0018448766238757784, | |
| "grad_norm": 6.00553560256958, | |
| "learning_rate": 0.00012, | |
| "loss": 7.7881, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018448766238757784, | |
| "eval_loss": 7.770421028137207, | |
| "eval_runtime": 40.5882, | |
| "eval_samples_per_second": 33.754, | |
| "eval_steps_per_second": 16.877, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002152356061188408, | |
| "grad_norm": 5.929523944854736, | |
| "learning_rate": 0.00014, | |
| "loss": 8.65, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002459835498501038, | |
| "grad_norm": 6.152801513671875, | |
| "learning_rate": 0.00016, | |
| "loss": 7.4528, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0027673149358136673, | |
| "grad_norm": 4.511847019195557, | |
| "learning_rate": 0.00018, | |
| "loss": 5.0966, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027673149358136673, | |
| "eval_loss": 6.538444995880127, | |
| "eval_runtime": 40.6732, | |
| "eval_samples_per_second": 33.683, | |
| "eval_steps_per_second": 16.842, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0030747943731262973, | |
| "grad_norm": 7.016354084014893, | |
| "learning_rate": 0.0002, | |
| "loss": 6.6274, | |
| "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": 737027133800448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |