| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05847953216374269, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005847953216374269, | |
| "grad_norm": 4.507676124572754, | |
| "learning_rate": 2e-05, | |
| "loss": 5.2745, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005847953216374269, | |
| "eval_loss": 4.5855512619018555, | |
| "eval_runtime": 2.1794, | |
| "eval_samples_per_second": 33.036, | |
| "eval_steps_per_second": 16.518, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011695906432748537, | |
| "grad_norm": 2.5267856121063232, | |
| "learning_rate": 4e-05, | |
| "loss": 4.7194, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": 2.4641594886779785, | |
| "learning_rate": 6e-05, | |
| "loss": 3.8961, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.017543859649122806, | |
| "eval_loss": 4.5594916343688965, | |
| "eval_runtime": 2.1744, | |
| "eval_samples_per_second": 33.112, | |
| "eval_steps_per_second": 16.556, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 3.718451738357544, | |
| "learning_rate": 8e-05, | |
| "loss": 4.4404, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.029239766081871343, | |
| "grad_norm": 3.099238634109497, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5315, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 3.4281084537506104, | |
| "learning_rate": 0.00012, | |
| "loss": 4.5732, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "eval_loss": 4.279503345489502, | |
| "eval_runtime": 2.2462, | |
| "eval_samples_per_second": 32.055, | |
| "eval_steps_per_second": 16.027, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04093567251461988, | |
| "grad_norm": 2.3720695972442627, | |
| "learning_rate": 0.00014, | |
| "loss": 3.9692, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 4.447011947631836, | |
| "learning_rate": 0.00016, | |
| "loss": 3.8493, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 3.8399388790130615, | |
| "learning_rate": 0.00018, | |
| "loss": 4.404, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "eval_loss": 3.8104772567749023, | |
| "eval_runtime": 2.2218, | |
| "eval_samples_per_second": 32.406, | |
| "eval_steps_per_second": 16.203, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "grad_norm": 3.0827927589416504, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3768, | |
| "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": 500097330708480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |