| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016909744240118367, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "grad_norm": 9.851485252380371, | |
| "learning_rate": 2e-05, | |
| "loss": 4.6538, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001690974424011837, | |
| "eval_loss": 4.714530944824219, | |
| "eval_runtime": 48.9153, | |
| "eval_samples_per_second": 50.904, | |
| "eval_steps_per_second": 25.452, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003381948848023674, | |
| "grad_norm": 9.353590965270996, | |
| "learning_rate": 4e-05, | |
| "loss": 4.5746, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "grad_norm": 10.873821258544922, | |
| "learning_rate": 6e-05, | |
| "loss": 4.5166, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000507292327203551, | |
| "eval_loss": 4.6112165451049805, | |
| "eval_runtime": 48.5075, | |
| "eval_samples_per_second": 51.332, | |
| "eval_steps_per_second": 25.666, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006763897696047348, | |
| "grad_norm": 8.955278396606445, | |
| "learning_rate": 8e-05, | |
| "loss": 4.5239, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008454872120059184, | |
| "grad_norm": 11.914831161499023, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0488, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "grad_norm": 9.92457103729248, | |
| "learning_rate": 0.00012, | |
| "loss": 3.8753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001014584654407102, | |
| "eval_loss": 3.2814440727233887, | |
| "eval_runtime": 48.4631, | |
| "eval_samples_per_second": 51.379, | |
| "eval_steps_per_second": 25.69, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011836820968082857, | |
| "grad_norm": 12.483610153198242, | |
| "learning_rate": 0.00014, | |
| "loss": 3.1536, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013527795392094695, | |
| "grad_norm": 15.145976066589355, | |
| "learning_rate": 0.00016, | |
| "loss": 2.8401, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "grad_norm": 14.290426254272461, | |
| "learning_rate": 0.00018, | |
| "loss": 1.9698, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015218769816106531, | |
| "eval_loss": 1.4378986358642578, | |
| "eval_runtime": 48.46, | |
| "eval_samples_per_second": 51.383, | |
| "eval_steps_per_second": 25.691, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016909744240118367, | |
| "grad_norm": 11.172967910766602, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3211, | |
| "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": 104619842469888.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |