| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013304506901712955, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002660901380342591, | |
| "grad_norm": 1.981186866760254, | |
| "learning_rate": 1e-05, | |
| "loss": 1.326, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002660901380342591, | |
| "eval_loss": 1.593505620956421, | |
| "eval_runtime": 183.2982, | |
| "eval_samples_per_second": 3.453, | |
| "eval_steps_per_second": 1.729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005321802760685182, | |
| "grad_norm": 1.3898383378982544, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4333, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005321802760685182, | |
| "eval_loss": 1.565208077430725, | |
| "eval_runtime": 21.1948, | |
| "eval_samples_per_second": 29.866, | |
| "eval_steps_per_second": 14.957, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007982704141027773, | |
| "grad_norm": 1.312504529953003, | |
| "learning_rate": 3e-05, | |
| "loss": 1.4293, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010643605521370364, | |
| "grad_norm": 1.230638861656189, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4553, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010643605521370364, | |
| "eval_loss": 1.5374736785888672, | |
| "eval_runtime": 21.1938, | |
| "eval_samples_per_second": 29.867, | |
| "eval_steps_per_second": 14.957, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013304506901712955, | |
| "grad_norm": 0.6640193462371826, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2064, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5317497213419520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |