| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 8.0, |
| "eval_steps": 100, |
| "global_step": 48, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.8333333333333334, |
| "grad_norm": 10.852923393249512, |
| "learning_rate": 4.867325323737765e-05, |
| "loss": 4.5302, |
| "num_input_tokens_seen": 71152, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.6666666666666665, |
| "grad_norm": 2.349968910217285, |
| "learning_rate": 4.4833833507280884e-05, |
| "loss": 0.4476, |
| "num_input_tokens_seen": 142488, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.9618425369262695, |
| "learning_rate": 3.888925582549006e-05, |
| "loss": 0.3925, |
| "num_input_tokens_seen": 214832, |
| "step": 15 |
| }, |
| { |
| "epoch": 3.3333333333333335, |
| "grad_norm": 2.0542993545532227, |
| "learning_rate": 3.147047612756302e-05, |
| "loss": 0.3049, |
| "num_input_tokens_seen": 285560, |
| "step": 20 |
| }, |
| { |
| "epoch": 4.166666666666667, |
| "grad_norm": 5.90749454498291, |
| "learning_rate": 2.3364921769246423e-05, |
| "loss": 0.283, |
| "num_input_tokens_seen": 356912, |
| "step": 25 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 2.0208399295806885, |
| "learning_rate": 1.5432914190872757e-05, |
| "loss": 0.2446, |
| "num_input_tokens_seen": 428520, |
| "step": 30 |
| }, |
| { |
| "epoch": 5.833333333333333, |
| "grad_norm": 1.1415902376174927, |
| "learning_rate": 8.51635462249828e-06, |
| "loss": 0.2004, |
| "num_input_tokens_seen": 500080, |
| "step": 35 |
| }, |
| { |
| "epoch": 6.666666666666667, |
| "grad_norm": 0.9424810409545898, |
| "learning_rate": 3.3493649053890326e-06, |
| "loss": 0.1442, |
| "num_input_tokens_seen": 572584, |
| "step": 40 |
| }, |
| { |
| "epoch": 7.5, |
| "grad_norm": 1.3394242525100708, |
| "learning_rate": 4.803679899192392e-07, |
| "loss": 0.1513, |
| "num_input_tokens_seen": 643064, |
| "step": 45 |
| }, |
| { |
| "epoch": 8.0, |
| "num_input_tokens_seen": 685632, |
| "step": 48, |
| "total_flos": 48431641919488.0, |
| "train_loss": 0.7059125807136297, |
| "train_runtime": 2114.6373, |
| "train_samples_per_second": 0.363, |
| "train_steps_per_second": 0.023 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 48, |
| "num_input_tokens_seen": 685632, |
| "num_train_epochs": 8, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 48431641919488.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
