| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009086159507530155, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001817231901506031, | |
| "grad_norm": 10.410955429077148, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3114, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001817231901506031, | |
| "eval_loss": 10.349905014038086, | |
| "eval_runtime": 92.5754, | |
| "eval_samples_per_second": 100.113, | |
| "eval_steps_per_second": 50.056, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003634463803012062, | |
| "grad_norm": 11.770838737487793, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3272, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003634463803012062, | |
| "eval_loss": 10.196455955505371, | |
| "eval_runtime": 65.1625, | |
| "eval_samples_per_second": 142.229, | |
| "eval_steps_per_second": 71.114, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005451695704518092, | |
| "grad_norm": 10.492831230163574, | |
| "learning_rate": 3e-05, | |
| "loss": 10.619, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007268927606024124, | |
| "grad_norm": 10.384638786315918, | |
| "learning_rate": 4e-05, | |
| "loss": 9.842, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007268927606024124, | |
| "eval_loss": 9.903849601745605, | |
| "eval_runtime": 73.3528, | |
| "eval_samples_per_second": 126.348, | |
| "eval_steps_per_second": 63.174, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0009086159507530155, | |
| "grad_norm": 10.335015296936035, | |
| "learning_rate": 5e-05, | |
| "loss": 9.591, | |
| "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": 481091030876160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |