| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009311492709877166, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.103830903292389e-05, | |
| "eval_loss": 7.834071636199951, | |
| "eval_runtime": 286.5273, | |
| "eval_samples_per_second": 47.346, | |
| "eval_steps_per_second": 23.673, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.311492709877166e-05, | |
| "grad_norm": 8.889198303222656, | |
| "learning_rate": 6e-05, | |
| "loss": 7.7908, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00018622985419754331, | |
| "grad_norm": 6.911953449249268, | |
| "learning_rate": 0.00012, | |
| "loss": 7.7203, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002483064722633911, | |
| "eval_loss": 7.593387603759766, | |
| "eval_runtime": 285.3413, | |
| "eval_samples_per_second": 47.543, | |
| "eval_steps_per_second": 23.772, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00027934478129631497, | |
| "grad_norm": 8.1396484375, | |
| "learning_rate": 0.00018, | |
| "loss": 7.6247, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00037245970839508663, | |
| "grad_norm": 5.066481590270996, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 7.4849, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004655746354938583, | |
| "grad_norm": 6.424334526062012, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 7.3485, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004966129445267822, | |
| "eval_loss": 6.95123815536499, | |
| "eval_runtime": 286.048, | |
| "eval_samples_per_second": 47.426, | |
| "eval_steps_per_second": 23.713, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005586895625926299, | |
| "grad_norm": 7.5147705078125, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 6.8683, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006518044896914017, | |
| "grad_norm": 5.200011730194092, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 6.9236, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007449194167901733, | |
| "grad_norm": 7.063309192657471, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 6.7891, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0007449194167901733, | |
| "eval_loss": 6.664403438568115, | |
| "eval_runtime": 286.6637, | |
| "eval_samples_per_second": 47.324, | |
| "eval_steps_per_second": 23.662, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000838034343888945, | |
| "grad_norm": 5.639961242675781, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 6.7768, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0009311492709877166, | |
| "grad_norm": 5.1643171310424805, | |
| "learning_rate": 0.0, | |
| "loss": 6.6312, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5670814089216.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |