| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12965964343598055, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02593192868719611, | |
| "grad_norm": 8.377267837524414, | |
| "learning_rate": 1e-05, | |
| "loss": 9.5606, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02593192868719611, | |
| "eval_loss": 9.4830961227417, | |
| "eval_runtime": 34.6886, | |
| "eval_samples_per_second": 1.874, | |
| "eval_steps_per_second": 0.951, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05186385737439222, | |
| "grad_norm": 9.141130447387695, | |
| "learning_rate": 2e-05, | |
| "loss": 9.7395, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05186385737439222, | |
| "eval_loss": 9.462117195129395, | |
| "eval_runtime": 0.2303, | |
| "eval_samples_per_second": 282.296, | |
| "eval_steps_per_second": 143.319, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07779578606158834, | |
| "grad_norm": 8.418513298034668, | |
| "learning_rate": 3e-05, | |
| "loss": 9.3496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10372771474878444, | |
| "grad_norm": 8.357897758483887, | |
| "learning_rate": 4e-05, | |
| "loss": 9.5666, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10372771474878444, | |
| "eval_loss": 9.41639232635498, | |
| "eval_runtime": 0.2451, | |
| "eval_samples_per_second": 265.15, | |
| "eval_steps_per_second": 134.614, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12965964343598055, | |
| "grad_norm": 8.449214935302734, | |
| "learning_rate": 5e-05, | |
| "loss": 9.4912, | |
| "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": 1311170887680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |