| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.132013201320132, | |
| "eval_steps": 40, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016501650165016502, | |
| "eval_loss": 4.0092339515686035, | |
| "eval_runtime": 222.6347, | |
| "eval_samples_per_second": 44.827, | |
| "eval_steps_per_second": 3.737, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0165016501650165, | |
| "grad_norm": 4.71875, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 6.5728, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.033003300330033, | |
| "grad_norm": 1.703125, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 5.9863, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04950495049504951, | |
| "grad_norm": 1.9609375, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 5.595, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.066006600660066, | |
| "grad_norm": 14.625, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 5.0188, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.066006600660066, | |
| "eval_loss": 3.641935348510742, | |
| "eval_runtime": 214.321, | |
| "eval_samples_per_second": 46.566, | |
| "eval_steps_per_second": 3.882, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08250825082508251, | |
| "grad_norm": 16.5, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 4.6939, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09900990099009901, | |
| "grad_norm": 16.0, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 4.3269, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11551155115511551, | |
| "grad_norm": 11.75, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0728, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.132013201320132, | |
| "grad_norm": 5.5625, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 3.9329, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.132013201320132, | |
| "eval_loss": 3.323232412338257, | |
| "eval_runtime": 215.3024, | |
| "eval_samples_per_second": 46.353, | |
| "eval_steps_per_second": 3.864, | |
| "step": 80 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 40, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.894391884198707e+16, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |