| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0021369804466289132, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021369804466289135, | |
| "grad_norm": 5.769245147705078, | |
| "learning_rate": 2e-05, | |
| "loss": 4.2239, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021369804466289135, | |
| "eval_loss": 4.499746322631836, | |
| "eval_runtime": 47.5315, | |
| "eval_samples_per_second": 41.467, | |
| "eval_steps_per_second": 20.744, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004273960893257827, | |
| "grad_norm": 6.243180274963379, | |
| "learning_rate": 4e-05, | |
| "loss": 4.544, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000641094133988674, | |
| "grad_norm": 5.095125675201416, | |
| "learning_rate": 6e-05, | |
| "loss": 4.0301, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000641094133988674, | |
| "eval_loss": 4.448275089263916, | |
| "eval_runtime": 40.7286, | |
| "eval_samples_per_second": 48.394, | |
| "eval_steps_per_second": 24.209, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008547921786515654, | |
| "grad_norm": 6.316955089569092, | |
| "learning_rate": 8e-05, | |
| "loss": 4.6077, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010684902233144566, | |
| "grad_norm": 7.403411388397217, | |
| "learning_rate": 0.0001, | |
| "loss": 4.6353, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001282188267977348, | |
| "grad_norm": 6.7435688972473145, | |
| "learning_rate": 0.00012, | |
| "loss": 4.498, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001282188267977348, | |
| "eval_loss": 3.760186195373535, | |
| "eval_runtime": 38.4186, | |
| "eval_samples_per_second": 51.303, | |
| "eval_steps_per_second": 25.665, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014958863126402393, | |
| "grad_norm": 4.81810188293457, | |
| "learning_rate": 0.00014, | |
| "loss": 3.5625, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0017095843573031308, | |
| "grad_norm": 5.296993255615234, | |
| "learning_rate": 0.00016, | |
| "loss": 3.2156, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001923282401966022, | |
| "grad_norm": 4.5458083152771, | |
| "learning_rate": 0.00018, | |
| "loss": 2.9665, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001923282401966022, | |
| "eval_loss": 2.9628167152404785, | |
| "eval_runtime": 39.5428, | |
| "eval_samples_per_second": 49.845, | |
| "eval_steps_per_second": 24.935, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0021369804466289132, | |
| "grad_norm": 5.89293098449707, | |
| "learning_rate": 0.0002, | |
| "loss": 2.9729, | |
| "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": 89038163804160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |