| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.056794786238623295, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00567947862386233, | |
| "eval_accuracy": 0.577217863529113, | |
| "eval_loss": 2.233586072921753, | |
| "eval_runtime": 1986.1249, | |
| "eval_samples_per_second": 14.911, | |
| "eval_steps_per_second": 7.456, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01135895724772466, | |
| "eval_accuracy": 0.6331085624965921, | |
| "eval_loss": 1.865549921989441, | |
| "eval_runtime": 1990.8563, | |
| "eval_samples_per_second": 14.876, | |
| "eval_steps_per_second": 7.438, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.017038435871586988, | |
| "eval_accuracy": 0.6620234759230288, | |
| "eval_loss": 1.6861233711242676, | |
| "eval_runtime": 1994.7346, | |
| "eval_samples_per_second": 14.847, | |
| "eval_steps_per_second": 7.424, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.02271791449544932, | |
| "eval_accuracy": 0.6771864912263876, | |
| "eval_loss": 1.5935094356536865, | |
| "eval_runtime": 1993.4218, | |
| "eval_samples_per_second": 14.857, | |
| "eval_steps_per_second": 7.428, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.028397393119311647, | |
| "grad_norm": 4.40625, | |
| "learning_rate": 4.8580110183449765e-05, | |
| "loss": 2.0591, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.028397393119311647, | |
| "eval_accuracy": 0.6888090836794671, | |
| "eval_loss": 1.5249096155166626, | |
| "eval_runtime": 1993.694, | |
| "eval_samples_per_second": 14.855, | |
| "eval_steps_per_second": 7.427, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.034076871743173975, | |
| "eval_accuracy": 0.6971747896369712, | |
| "eval_loss": 1.477766752243042, | |
| "eval_runtime": 1994.0632, | |
| "eval_samples_per_second": 14.852, | |
| "eval_steps_per_second": 7.426, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.03975635036703631, | |
| "eval_accuracy": 0.7031079032429749, | |
| "eval_loss": 1.4431705474853516, | |
| "eval_runtime": 1994.0576, | |
| "eval_samples_per_second": 14.852, | |
| "eval_steps_per_second": 7.426, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.04543582899089864, | |
| "eval_accuracy": 0.7086350429994105, | |
| "eval_loss": 1.4113129377365112, | |
| "eval_runtime": 1995.6333, | |
| "eval_samples_per_second": 14.84, | |
| "eval_steps_per_second": 7.42, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.05111530761476096, | |
| "eval_accuracy": 0.7133429387568253, | |
| "eval_loss": 1.3802016973495483, | |
| "eval_runtime": 1996.6407, | |
| "eval_samples_per_second": 14.833, | |
| "eval_steps_per_second": 7.416, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.056794786238623295, | |
| "grad_norm": 2.640625, | |
| "learning_rate": 4.7160220366899535e-05, | |
| "loss": 1.4351, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.056794786238623295, | |
| "eval_accuracy": 0.716021928609194, | |
| "eval_loss": 1.3633891344070435, | |
| "eval_runtime": 1991.0825, | |
| "eval_samples_per_second": 14.874, | |
| "eval_steps_per_second": 7.437, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 17607, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.41887283560448e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |