| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01002004008016032, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001002004008016032, | |
| "grad_norm": 0.14840464293956757, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9341, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001002004008016032, | |
| "eval_loss": 11.937933921813965, | |
| "eval_runtime": 20.781, | |
| "eval_samples_per_second": 20.259, | |
| "eval_steps_per_second": 10.154, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002004008016032064, | |
| "grad_norm": 0.16377779841423035, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9423, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003006012024048096, | |
| "grad_norm": 0.1717039793729782, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9353, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003006012024048096, | |
| "eval_loss": 11.93774700164795, | |
| "eval_runtime": 19.8189, | |
| "eval_samples_per_second": 21.242, | |
| "eval_steps_per_second": 10.646, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004008016032064128, | |
| "grad_norm": 0.1474914401769638, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9373, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00501002004008016, | |
| "grad_norm": 0.14932551980018616, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9362, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006012024048096192, | |
| "grad_norm": 0.1468937247991562, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9331, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006012024048096192, | |
| "eval_loss": 11.93669319152832, | |
| "eval_runtime": 19.8017, | |
| "eval_samples_per_second": 21.261, | |
| "eval_steps_per_second": 10.656, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0070140280561122245, | |
| "grad_norm": 0.17056019604206085, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9374, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008016032064128256, | |
| "grad_norm": 0.1461707204580307, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9358, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009018036072144289, | |
| "grad_norm": 0.1584092676639557, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9383, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009018036072144289, | |
| "eval_loss": 11.93490219116211, | |
| "eval_runtime": 19.8691, | |
| "eval_samples_per_second": 21.189, | |
| "eval_steps_per_second": 10.619, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01002004008016032, | |
| "grad_norm": 0.1568196415901184, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9349, | |
| "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": 2503118684160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |