| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.036596523330283626, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036596523330283625, | |
| "grad_norm": 16.431114196777344, | |
| "learning_rate": 2e-05, | |
| "loss": 6.7731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007319304666056725, | |
| "grad_norm": 13.973880767822266, | |
| "learning_rate": 4e-05, | |
| "loss": 6.7965, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010978956999085087, | |
| "grad_norm": 16.485984802246094, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9483, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010978956999085087, | |
| "eval_loss": 6.581966876983643, | |
| "eval_runtime": 6.0089, | |
| "eval_samples_per_second": 19.138, | |
| "eval_steps_per_second": 9.652, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01463860933211345, | |
| "grad_norm": 16.0874080657959, | |
| "learning_rate": 8e-05, | |
| "loss": 6.7443, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018298261665141813, | |
| "grad_norm": 20.540544509887695, | |
| "learning_rate": 0.0001, | |
| "loss": 6.0838, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.021957913998170174, | |
| "grad_norm": 22.555376052856445, | |
| "learning_rate": 0.00012, | |
| "loss": 4.8242, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.021957913998170174, | |
| "eval_loss": 3.0552265644073486, | |
| "eval_runtime": 5.3044, | |
| "eval_samples_per_second": 21.68, | |
| "eval_steps_per_second": 10.934, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025617566331198535, | |
| "grad_norm": 12.365771293640137, | |
| "learning_rate": 0.00014, | |
| "loss": 3.0256, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0292772186642269, | |
| "grad_norm": 7.180561065673828, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7685, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03293687099725526, | |
| "grad_norm": 4.194366931915283, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0649, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03293687099725526, | |
| "eval_loss": 0.7600207924842834, | |
| "eval_runtime": 8.1062, | |
| "eval_samples_per_second": 14.187, | |
| "eval_steps_per_second": 7.155, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.036596523330283626, | |
| "grad_norm": 2.806422472000122, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6251, | |
| "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": 1647822923366400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |