| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04678362573099415, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004678362573099415, | |
| "grad_norm": 0.7276586294174194, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0291, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "eval_loss": 2.0049281120300293, | |
| "eval_runtime": 2.5698, | |
| "eval_samples_per_second": 35.022, | |
| "eval_steps_per_second": 17.511, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "grad_norm": 0.8991158604621887, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0284, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 0.8298183679580688, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9763, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "eval_loss": 2.0029807090759277, | |
| "eval_runtime": 1.564, | |
| "eval_samples_per_second": 57.546, | |
| "eval_steps_per_second": 28.773, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "grad_norm": 1.060206651687622, | |
| "learning_rate": 8e-05, | |
| "loss": 2.3413, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 0.8521826863288879, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9854, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": 0.784907341003418, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8668, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "eval_loss": 1.9630398750305176, | |
| "eval_runtime": 1.5778, | |
| "eval_samples_per_second": 57.042, | |
| "eval_steps_per_second": 28.521, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03274853801169591, | |
| "grad_norm": 0.7844423055648804, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0469, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "grad_norm": 0.9878946542739868, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9194, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 1.2176491022109985, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8877, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "eval_loss": 1.8432834148406982, | |
| "eval_runtime": 1.5791, | |
| "eval_samples_per_second": 56.995, | |
| "eval_steps_per_second": 28.497, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 1.449363112449646, | |
| "learning_rate": 0.0002, | |
| "loss": 2.181, | |
| "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": 451022841446400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |