| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003902439024390244, | |
| "eval_steps": 5, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00026016260162601624, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 34.9906, | |
| "eval_samples_per_second": 46.27, | |
| "eval_steps_per_second": 23.149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007804878048780488, | |
| "grad_norm": 3.270714296377264e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0013008130081300813, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 35.5811, | |
| "eval_samples_per_second": 45.502, | |
| "eval_steps_per_second": 22.765, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015609756097560976, | |
| "grad_norm": 2.1516543711186387e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0023414634146341463, | |
| "grad_norm": 3.746010406757705e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026016260162601626, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 33.4884, | |
| "eval_samples_per_second": 48.345, | |
| "eval_steps_per_second": 24.187, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0031219512195121953, | |
| "grad_norm": 1.9942483049817383e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003902439024390244, | |
| "grad_norm": 3.0088403946137987e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003902439024390244, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 34.9316, | |
| "eval_samples_per_second": 46.348, | |
| "eval_steps_per_second": 23.188, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 608415350784.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |