| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.7735849056603774, | |
| "eval_steps": 100, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4716981132075472, | |
| "grad_norm": 3.3795788288116455, | |
| "learning_rate": 2.20959595959596e-05, | |
| "loss": 1.2797, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9433962264150944, | |
| "grad_norm": 2.9120898246765137, | |
| "learning_rate": 1.893939393939394e-05, | |
| "loss": 1.1962, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.4150943396226414, | |
| "grad_norm": 3.0452721118927, | |
| "learning_rate": 1.5782828282828283e-05, | |
| "loss": 1.0634, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.8867924528301887, | |
| "grad_norm": 3.187485933303833, | |
| "learning_rate": 1.2626262626262628e-05, | |
| "loss": 1.0311, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.8867924528301887, | |
| "eval_loss": 0.9837524890899658, | |
| "eval_runtime": 20.3264, | |
| "eval_samples_per_second": 5.166, | |
| "eval_steps_per_second": 0.689, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.358490566037736, | |
| "grad_norm": 3.267012119293213, | |
| "learning_rate": 9.46969696969697e-06, | |
| "loss": 0.9671, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.830188679245283, | |
| "grad_norm": 3.161576509475708, | |
| "learning_rate": 6.313131313131314e-06, | |
| "loss": 0.9191, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.30188679245283, | |
| "grad_norm": 3.007451295852661, | |
| "learning_rate": 3.156565656565657e-06, | |
| "loss": 0.9242, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 3.7735849056603774, | |
| "grad_norm": 3.3202719688415527, | |
| "learning_rate": 0.0, | |
| "loss": 0.8966, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.7735849056603774, | |
| "eval_loss": 0.9046460390090942, | |
| "eval_runtime": 20.5876, | |
| "eval_samples_per_second": 5.1, | |
| "eval_steps_per_second": 0.68, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 463911645216768.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |