| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.33613445378151263, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03361344537815126, | |
| "grad_norm": 15.16921329498291, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8088, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03361344537815126, | |
| "eval_loss": 0.4763054847717285, | |
| "eval_runtime": 0.4799, | |
| "eval_samples_per_second": 27.087, | |
| "eval_steps_per_second": 14.585, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06722689075630252, | |
| "grad_norm": 17.20284080505371, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9939, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10084033613445378, | |
| "grad_norm": 14.288636207580566, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7288, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10084033613445378, | |
| "eval_loss": 0.32885998487472534, | |
| "eval_runtime": 0.4785, | |
| "eval_samples_per_second": 27.169, | |
| "eval_steps_per_second": 14.629, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13445378151260504, | |
| "grad_norm": 10.995784759521484, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2765, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16806722689075632, | |
| "grad_norm": 10.540312767028809, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6446, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20168067226890757, | |
| "grad_norm": 35.06471633911133, | |
| "learning_rate": 0.00012, | |
| "loss": 0.3919, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.20168067226890757, | |
| "eval_loss": 0.01614716462790966, | |
| "eval_runtime": 0.4792, | |
| "eval_samples_per_second": 27.126, | |
| "eval_steps_per_second": 14.606, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 3.6393842697143555, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0651, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2689075630252101, | |
| "grad_norm": 1.6398135423660278, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0085, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3025210084033613, | |
| "grad_norm": 0.22559121251106262, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0017, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3025210084033613, | |
| "eval_loss": 0.000281344837276265, | |
| "eval_runtime": 0.4789, | |
| "eval_samples_per_second": 27.147, | |
| "eval_steps_per_second": 14.617, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.33613445378151263, | |
| "grad_norm": 0.03774282708764076, | |
| "learning_rate": 0.0002, | |
| "loss": 0.001, | |
| "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": 1752669785948160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |