| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.997955010224949, | |
| "global_step": 610, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 39.944950103759766, | |
| "eval_runtime": 1.5442, | |
| "eval_samples_per_second": 79.651, | |
| "eval_steps_per_second": 10.361, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 39.573768615722656, | |
| "eval_runtime": 1.5441, | |
| "eval_samples_per_second": 79.656, | |
| "eval_steps_per_second": 10.362, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 40.006507873535156, | |
| "eval_runtime": 1.5451, | |
| "eval_samples_per_second": 79.606, | |
| "eval_steps_per_second": 10.355, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 39.271480560302734, | |
| "eval_runtime": 1.5464, | |
| "eval_samples_per_second": 79.54, | |
| "eval_steps_per_second": 10.347, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 38.749183654785156, | |
| "eval_runtime": 1.5468, | |
| "eval_samples_per_second": 79.518, | |
| "eval_steps_per_second": 10.344, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 38.856666564941406, | |
| "eval_runtime": 1.5467, | |
| "eval_samples_per_second": 79.525, | |
| "eval_steps_per_second": 10.345, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 38.75959396362305, | |
| "eval_runtime": 1.5455, | |
| "eval_samples_per_second": 79.588, | |
| "eval_steps_per_second": 10.353, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 38.665225982666016, | |
| "eval_runtime": 1.5457, | |
| "eval_samples_per_second": 79.578, | |
| "eval_steps_per_second": 10.352, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 9.01639344262295e-09, | |
| "loss": 42.1342, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 38.66032028198242, | |
| "eval_runtime": 1.551, | |
| "eval_samples_per_second": 79.304, | |
| "eval_steps_per_second": 10.316, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 38.66507339477539, | |
| "eval_runtime": 1.5562, | |
| "eval_samples_per_second": 79.038, | |
| "eval_steps_per_second": 10.281, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 610, | |
| "total_flos": 322666370343936.0, | |
| "train_loss": 41.80477074795082, | |
| "train_runtime": 454.8629, | |
| "train_samples_per_second": 10.75, | |
| "train_steps_per_second": 1.341 | |
| } | |
| ], | |
| "max_steps": 610, | |
| "num_train_epochs": 10, | |
| "total_flos": 322666370343936.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |