| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2505175983436853, | |
| "eval_steps": 500, | |
| "global_step": 121, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020703933747412008, | |
| "grad_norm": 2.7109034061431885, | |
| "learning_rate": 0.000199658449300667, | |
| "loss": 0.5702, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.041407867494824016, | |
| "grad_norm": 2.019132375717163, | |
| "learning_rate": 0.0001936511241197055, | |
| "loss": 0.2695, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.062111801242236024, | |
| "grad_norm": 2.7597837448120117, | |
| "learning_rate": 0.00018057651056609784, | |
| "loss": 0.2096, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08281573498964803, | |
| "grad_norm": 1.2507442235946655, | |
| "learning_rate": 0.0001614212712689668, | |
| "loss": 0.1855, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10351966873706005, | |
| "grad_norm": 1.8468929529190063, | |
| "learning_rate": 0.00013763093719478358, | |
| "loss": 0.1573, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12422360248447205, | |
| "grad_norm": 0.8407199382781982, | |
| "learning_rate": 0.00011100082209940795, | |
| "loss": 0.1637, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14492753623188406, | |
| "grad_norm": 0.9125467538833618, | |
| "learning_rate": 8.35405409719266e-05, | |
| "loss": 0.1278, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16563146997929606, | |
| "grad_norm": 0.8212506175041199, | |
| "learning_rate": 5.732235645035964e-05, | |
| "loss": 0.1175, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18633540372670807, | |
| "grad_norm": 0.6263362169265747, | |
| "learning_rate": 3.4324797595226565e-05, | |
| "loss": 0.1032, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2070393374741201, | |
| "grad_norm": 0.6752850413322449, | |
| "learning_rate": 1.6283352173747145e-05, | |
| "loss": 0.1003, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2277432712215321, | |
| "grad_norm": 0.7334072589874268, | |
| "learning_rate": 4.559499812049251e-06, | |
| "loss": 0.0935, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2484472049689441, | |
| "grad_norm": 0.4544273614883423, | |
| "learning_rate": 3.796929750485845e-08, | |
| "loss": 0.1022, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2505175983436853, | |
| "step": 121, | |
| "total_flos": 4388878621315584.0, | |
| "train_loss": 0.18267044973028593, | |
| "train_runtime": 70.2121, | |
| "train_samples_per_second": 27.574, | |
| "train_steps_per_second": 1.723 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 121, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4388878621315584.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |