| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09216589861751152, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009216589861751152, | |
| "grad_norm": 14.310744285583496, | |
| "learning_rate": 2e-05, | |
| "loss": 5.6609, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009216589861751152, | |
| "eval_loss": 5.6318440437316895, | |
| "eval_runtime": 5.0294, | |
| "eval_samples_per_second": 36.386, | |
| "eval_steps_per_second": 4.573, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018433179723502304, | |
| "grad_norm": 16.09499740600586, | |
| "learning_rate": 4e-05, | |
| "loss": 6.1363, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.027649769585253458, | |
| "grad_norm": 12.103375434875488, | |
| "learning_rate": 6e-05, | |
| "loss": 5.1534, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027649769585253458, | |
| "eval_loss": 5.331299781799316, | |
| "eval_runtime": 4.9679, | |
| "eval_samples_per_second": 36.836, | |
| "eval_steps_per_second": 4.63, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03686635944700461, | |
| "grad_norm": 13.103915214538574, | |
| "learning_rate": 8e-05, | |
| "loss": 5.4683, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04608294930875576, | |
| "grad_norm": 11.824213981628418, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5965, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.055299539170506916, | |
| "grad_norm": 9.575993537902832, | |
| "learning_rate": 0.00012, | |
| "loss": 4.1653, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.055299539170506916, | |
| "eval_loss": 3.606476306915283, | |
| "eval_runtime": 4.945, | |
| "eval_samples_per_second": 37.007, | |
| "eval_steps_per_second": 4.651, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06451612903225806, | |
| "grad_norm": 10.15619945526123, | |
| "learning_rate": 0.00014, | |
| "loss": 3.9804, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07373271889400922, | |
| "grad_norm": 5.944631576538086, | |
| "learning_rate": 0.00016, | |
| "loss": 2.7903, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08294930875576037, | |
| "grad_norm": 5.762338638305664, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8695, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08294930875576037, | |
| "eval_loss": 2.5336620807647705, | |
| "eval_runtime": 4.8033, | |
| "eval_samples_per_second": 38.098, | |
| "eval_steps_per_second": 4.788, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09216589861751152, | |
| "grad_norm": 7.361027717590332, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2716, | |
| "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": 1.574040552603648e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |