| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00019502586530538614, | |
| "eval_steps": 8, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.9502586530538612e-05, | |
| "eval_loss": 3.453108072280884, | |
| "eval_runtime": 1466.7785, | |
| "eval_samples_per_second": 14.719, | |
| "eval_steps_per_second": 7.36, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.850775959161584e-05, | |
| "grad_norm": 29.78322982788086, | |
| "learning_rate": 6e-05, | |
| "loss": 15.4558, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00011701551918323167, | |
| "grad_norm": 16.993513107299805, | |
| "learning_rate": 0.00012, | |
| "loss": 12.5761, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001560206922443089, | |
| "eval_loss": 2.9539127349853516, | |
| "eval_runtime": 1467.4803, | |
| "eval_samples_per_second": 14.712, | |
| "eval_steps_per_second": 7.356, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00017552327877484752, | |
| "grad_norm": 12.85067081451416, | |
| "learning_rate": 0.00018, | |
| "loss": 11.6503, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3515647493406720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |