| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.15710919088766692, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03927729772191673, | |
| "grad_norm": 0.3003779351711273, | |
| "learning_rate": 6.544502617801048e-05, | |
| "loss": 4.2186, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03927729772191673, | |
| "eval_loss": 3.861752510070801, | |
| "eval_runtime": 29.4492, | |
| "eval_samples_per_second": 3.396, | |
| "eval_steps_per_second": 0.441, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07855459544383346, | |
| "grad_norm": 0.19962768256664276, | |
| "learning_rate": 0.00013089005235602096, | |
| "loss": 3.1772, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07855459544383346, | |
| "eval_loss": 2.59340238571167, | |
| "eval_runtime": 29.4336, | |
| "eval_samples_per_second": 3.397, | |
| "eval_steps_per_second": 0.442, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1178318931657502, | |
| "grad_norm": 0.17451965808868408, | |
| "learning_rate": 0.00019633507853403142, | |
| "loss": 2.401, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1178318931657502, | |
| "eval_loss": 2.2559566497802734, | |
| "eval_runtime": 29.4433, | |
| "eval_samples_per_second": 3.396, | |
| "eval_steps_per_second": 0.442, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 3819, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1866163847086080.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |