| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022753128555176336, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022753128555176336, | |
| "grad_norm": 2.181785821914673, | |
| "learning_rate": 2e-05, | |
| "loss": 3.8738, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022753128555176336, | |
| "eval_loss": 4.178267002105713, | |
| "eval_runtime": 6.9722, | |
| "eval_samples_per_second": 26.534, | |
| "eval_steps_per_second": 13.339, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004550625711035267, | |
| "grad_norm": 2.2990353107452393, | |
| "learning_rate": 4e-05, | |
| "loss": 4.5938, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006825938566552901, | |
| "grad_norm": 1.950202226638794, | |
| "learning_rate": 6e-05, | |
| "loss": 3.7878, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006825938566552901, | |
| "eval_loss": 4.164106845855713, | |
| "eval_runtime": 5.8498, | |
| "eval_samples_per_second": 31.625, | |
| "eval_steps_per_second": 15.898, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009101251422070534, | |
| "grad_norm": 2.3290538787841797, | |
| "learning_rate": 8e-05, | |
| "loss": 3.5999, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011376564277588168, | |
| "grad_norm": 2.265613079071045, | |
| "learning_rate": 0.0001, | |
| "loss": 4.1407, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013651877133105802, | |
| "grad_norm": 2.3757424354553223, | |
| "learning_rate": 0.00012, | |
| "loss": 3.7781, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013651877133105802, | |
| "eval_loss": 3.848492383956909, | |
| "eval_runtime": 5.8772, | |
| "eval_samples_per_second": 31.477, | |
| "eval_steps_per_second": 15.824, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015927189988623434, | |
| "grad_norm": 3.146082639694214, | |
| "learning_rate": 0.00014, | |
| "loss": 3.6875, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01820250284414107, | |
| "grad_norm": 2.9855051040649414, | |
| "learning_rate": 0.00016, | |
| "loss": 3.7841, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020477815699658702, | |
| "grad_norm": 3.3753230571746826, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8995, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020477815699658702, | |
| "eval_loss": 3.114321231842041, | |
| "eval_runtime": 5.8846, | |
| "eval_samples_per_second": 31.438, | |
| "eval_steps_per_second": 15.804, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022753128555176336, | |
| "grad_norm": 3.318885326385498, | |
| "learning_rate": 0.0002, | |
| "loss": 2.9616, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |