| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003649035742305096, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.649035742305096e-05, | |
| "grad_norm": 1.1290621757507324, | |
| "learning_rate": 2e-05, | |
| "loss": 1.9881, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.649035742305096e-05, | |
| "eval_loss": 2.0853261947631836, | |
| "eval_runtime": 571.0847, | |
| "eval_samples_per_second": 20.205, | |
| "eval_steps_per_second": 10.104, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.298071484610192e-05, | |
| "grad_norm": 1.6017961502075195, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2776, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010947107226915287, | |
| "grad_norm": 1.2497326135635376, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3003, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010947107226915287, | |
| "eval_loss": 2.072291612625122, | |
| "eval_runtime": 570.5902, | |
| "eval_samples_per_second": 20.223, | |
| "eval_steps_per_second": 10.112, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014596142969220384, | |
| "grad_norm": 1.0052485466003418, | |
| "learning_rate": 8e-05, | |
| "loss": 1.8931, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001824517871152548, | |
| "grad_norm": 1.2682143449783325, | |
| "learning_rate": 0.0001, | |
| "loss": 1.957, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00021894214453830574, | |
| "grad_norm": 0.9915633797645569, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8722, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00021894214453830574, | |
| "eval_loss": 1.916281819343567, | |
| "eval_runtime": 570.8714, | |
| "eval_samples_per_second": 20.213, | |
| "eval_steps_per_second": 10.107, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002554325019613567, | |
| "grad_norm": 1.8786778450012207, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0582, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00029192285938440767, | |
| "grad_norm": 2.1627986431121826, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7706, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00032841321680745865, | |
| "grad_norm": 1.709800362586975, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0935, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00032841321680745865, | |
| "eval_loss": 1.8575516939163208, | |
| "eval_runtime": 570.5043, | |
| "eval_samples_per_second": 20.226, | |
| "eval_steps_per_second": 10.114, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003649035742305096, | |
| "grad_norm": 1.6819078922271729, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9501, | |
| "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": 2052393617326080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |