| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004337610699439725, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001445870233146575, | |
| "eval_loss": 2.06308913230896, | |
| "eval_runtime": 173.4573, | |
| "eval_samples_per_second": 16.794, | |
| "eval_steps_per_second": 8.4, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00043376106994397255, | |
| "grad_norm": 0.4644452929496765, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9471, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008675221398879451, | |
| "grad_norm": 0.4791478216648102, | |
| "learning_rate": 0.00012, | |
| "loss": 2.0163, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00115669618651726, | |
| "eval_loss": 1.8069088459014893, | |
| "eval_runtime": 173.2693, | |
| "eval_samples_per_second": 16.812, | |
| "eval_steps_per_second": 8.409, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013012832098319176, | |
| "grad_norm": 0.7022720575332642, | |
| "learning_rate": 0.00018, | |
| "loss": 1.805, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017350442797758902, | |
| "grad_norm": 0.6181803941726685, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.485, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021688053497198627, | |
| "grad_norm": 0.6299495697021484, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.2606, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00231339237303452, | |
| "eval_loss": 1.2611411809921265, | |
| "eval_runtime": 173.4823, | |
| "eval_samples_per_second": 16.791, | |
| "eval_steps_per_second": 8.399, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002602566419663835, | |
| "grad_norm": 0.6869969964027405, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.2193, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0030363274896078075, | |
| "grad_norm": 0.6008644700050354, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.1037, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0034700885595517804, | |
| "grad_norm": 0.5576662421226501, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.0787, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0034700885595517804, | |
| "eval_loss": 1.1261745691299438, | |
| "eval_runtime": 173.3738, | |
| "eval_samples_per_second": 16.802, | |
| "eval_steps_per_second": 8.404, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003903849629495753, | |
| "grad_norm": 0.4697798490524292, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.0974, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004337610699439725, | |
| "grad_norm": 0.6208882331848145, | |
| "learning_rate": 0.0, | |
| "loss": 1.0671, | |
| "step": 30 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4939038012211200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |