| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001180307031149513, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0264282849987515e-05, | |
| "eval_loss": 5.79030179977417, | |
| "eval_runtime": 951.2774, | |
| "eval_samples_per_second": 14.626, | |
| "eval_steps_per_second": 7.313, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015132141424993757, | |
| "grad_norm": 11.172880172729492, | |
| "learning_rate": 5e-05, | |
| "loss": 5.9734, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00030264282849987514, | |
| "grad_norm": 8.808457374572754, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8053, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00030264282849987514, | |
| "eval_loss": 2.8650171756744385, | |
| "eval_runtime": 955.0464, | |
| "eval_samples_per_second": 14.568, | |
| "eval_steps_per_second": 7.284, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004539642427498127, | |
| "grad_norm": 6.514718055725098, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0989, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006052856569997503, | |
| "grad_norm": 4.128428936004639, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.04, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006052856569997503, | |
| "eval_loss": 0.8372714519500732, | |
| "eval_runtime": 953.3817, | |
| "eval_samples_per_second": 14.593, | |
| "eval_steps_per_second": 7.297, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007566070712496879, | |
| "grad_norm": 3.0278117656707764, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4554, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0009079284854996254, | |
| "grad_norm": 5.293846130371094, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6779, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009079284854996254, | |
| "eval_loss": 0.7594659328460693, | |
| "eval_runtime": 954.1608, | |
| "eval_samples_per_second": 14.581, | |
| "eval_steps_per_second": 7.291, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001059249899749563, | |
| "grad_norm": 3.4036614894866943, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6567, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7213300567769088.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |