| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016909744240118367, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "grad_norm": 7.885344505310059, | |
| "learning_rate": 2e-05, | |
| "loss": 6.6256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 6.817934036254883, | |
| "eval_runtime": 86.6291, | |
| "eval_samples_per_second": 28.743, | |
| "eval_steps_per_second": 14.372, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003381948848023674, | |
| "grad_norm": 8.441402435302734, | |
| "learning_rate": 4e-05, | |
| "loss": 6.6485, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "grad_norm": 8.27196216583252, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9607, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "eval_loss": 6.720228672027588, | |
| "eval_runtime": 85.2233, | |
| "eval_samples_per_second": 29.217, | |
| "eval_steps_per_second": 14.609, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006763897696047348, | |
| "grad_norm": 8.289449691772461, | |
| "learning_rate": 8e-05, | |
| "loss": 6.312, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "grad_norm": 8.284539222717285, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4338, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "grad_norm": 7.369958877563477, | |
| "learning_rate": 0.00012, | |
| "loss": 5.6306, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "eval_loss": 5.395904541015625, | |
| "eval_runtime": 85.4588, | |
| "eval_samples_per_second": 29.137, | |
| "eval_steps_per_second": 14.568, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011836820968082857, | |
| "grad_norm": 6.458924293518066, | |
| "learning_rate": 0.00014, | |
| "loss": 5.675, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013527795392094695, | |
| "grad_norm": 5.89903450012207, | |
| "learning_rate": 0.00016, | |
| "loss": 4.7366, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "grad_norm": 5.359555244445801, | |
| "learning_rate": 0.00018, | |
| "loss": 4.34, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "eval_loss": 3.663693904876709, | |
| "eval_runtime": 85.4769, | |
| "eval_samples_per_second": 29.131, | |
| "eval_steps_per_second": 14.565, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "grad_norm": 5.384970188140869, | |
| "learning_rate": 0.0002, | |
| "loss": 3.5552, | |
| "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": 1199811613163520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |