| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006644463085854769, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00013288926171709536, | |
| "grad_norm": 2.108687400817871, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6251, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013288926171709536, | |
| "eval_loss": 3.0204312801361084, | |
| "eval_runtime": 339.3491, | |
| "eval_samples_per_second": 37.348, | |
| "eval_steps_per_second": 18.674, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00026577852343419073, | |
| "grad_norm": 2.5102126598358154, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9052, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00026577852343419073, | |
| "eval_loss": 2.9318974018096924, | |
| "eval_runtime": 441.2381, | |
| "eval_samples_per_second": 28.724, | |
| "eval_steps_per_second": 14.362, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003986677851512861, | |
| "grad_norm": 2.559051513671875, | |
| "learning_rate": 3e-05, | |
| "loss": 2.7985, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005315570468683815, | |
| "grad_norm": 2.5379083156585693, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6094, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005315570468683815, | |
| "eval_loss": 2.7825121879577637, | |
| "eval_runtime": 574.2258, | |
| "eval_samples_per_second": 22.071, | |
| "eval_steps_per_second": 11.036, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0006644463085854769, | |
| "grad_norm": 3.019728899002075, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5341, | |
| "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": 3699128496291840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |