| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001536688436419516, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001536688436419516, | |
| "grad_norm": 2.5537407398223877, | |
| "learning_rate": 2e-05, | |
| "loss": 3.6463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001536688436419516, | |
| "eval_loss": 3.188629388809204, | |
| "eval_runtime": 98.6555, | |
| "eval_samples_per_second": 27.773, | |
| "eval_steps_per_second": 13.887, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003073376872839032, | |
| "grad_norm": 1.6175376176834106, | |
| "learning_rate": 4e-05, | |
| "loss": 3.3646, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004610065309258548, | |
| "grad_norm": 1.179677963256836, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3409, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004610065309258548, | |
| "eval_loss": 3.179351806640625, | |
| "eval_runtime": 97.4705, | |
| "eval_samples_per_second": 28.111, | |
| "eval_steps_per_second": 14.056, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006146753745678064, | |
| "grad_norm": 1.4353758096694946, | |
| "learning_rate": 8e-05, | |
| "loss": 3.1662, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000768344218209758, | |
| "grad_norm": 3.241360664367676, | |
| "learning_rate": 0.0001, | |
| "loss": 3.9191, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009220130618517096, | |
| "grad_norm": 1.9459642171859741, | |
| "learning_rate": 0.00012, | |
| "loss": 2.5982, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009220130618517096, | |
| "eval_loss": 3.0730576515197754, | |
| "eval_runtime": 97.5286, | |
| "eval_samples_per_second": 28.094, | |
| "eval_steps_per_second": 14.047, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010756819054936612, | |
| "grad_norm": 1.4690053462982178, | |
| "learning_rate": 0.00014, | |
| "loss": 2.7402, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012293507491356128, | |
| "grad_norm": 1.8470284938812256, | |
| "learning_rate": 0.00016, | |
| "loss": 3.0458, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013830195927775643, | |
| "grad_norm": 1.7478736639022827, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6066, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013830195927775643, | |
| "eval_loss": 2.9789044857025146, | |
| "eval_runtime": 97.4701, | |
| "eval_samples_per_second": 28.111, | |
| "eval_steps_per_second": 14.056, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001536688436419516, | |
| "grad_norm": 2.394191026687622, | |
| "learning_rate": 0.0002, | |
| "loss": 3.0029, | |
| "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": 1895803354349568.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |