| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017543859649122806, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017543859649122807, | |
| "grad_norm": 2.082876926579047e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017543859649122807, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.2716, | |
| "eval_samples_per_second": 188.744, | |
| "eval_steps_per_second": 94.372, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035087719298245615, | |
| "grad_norm": 3.644842217909172e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005263157894736842, | |
| "grad_norm": 5.134688035468571e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005263157894736842, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.2481, | |
| "eval_samples_per_second": 192.296, | |
| "eval_steps_per_second": 96.148, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007017543859649123, | |
| "grad_norm": 2.7331225282978266e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008771929824561403, | |
| "grad_norm": 1.5740233720862307e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "grad_norm": 2.3159351258073002e-05, | |
| "learning_rate": 0.00012, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.3373, | |
| "eval_samples_per_second": 179.47, | |
| "eval_steps_per_second": 89.735, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012280701754385965, | |
| "grad_norm": 3.5230528737884015e-05, | |
| "learning_rate": 0.00014, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 5.756669634138234e-05, | |
| "learning_rate": 0.00016, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015789473684210527, | |
| "grad_norm": 5.9218640672042966e-05, | |
| "learning_rate": 0.00018, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015789473684210527, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 1.2659, | |
| "eval_samples_per_second": 189.59, | |
| "eval_steps_per_second": 94.795, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": 5.540232450584881e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 46.0, | |
| "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": 199228784640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |