| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006983240223463687, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006983240223463687, | |
| "grad_norm": 1.9424208402633667, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6599, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006983240223463687, | |
| "eval_loss": 2.5736658573150635, | |
| "eval_runtime": 15.3353, | |
| "eval_samples_per_second": 39.321, | |
| "eval_steps_per_second": 19.693, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013966480446927375, | |
| "grad_norm": 2.5907845497131348, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7064, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002094972067039106, | |
| "grad_norm": 2.302950859069824, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5257, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002094972067039106, | |
| "eval_loss": 2.549306631088257, | |
| "eval_runtime": 15.317, | |
| "eval_samples_per_second": 39.368, | |
| "eval_steps_per_second": 19.717, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002793296089385475, | |
| "grad_norm": 2.260442018508911, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5051, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0034916201117318434, | |
| "grad_norm": 1.644205927848816, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7689, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004189944134078212, | |
| "grad_norm": 1.1809669733047485, | |
| "learning_rate": 0.00012, | |
| "loss": 2.8851, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004189944134078212, | |
| "eval_loss": 2.377427577972412, | |
| "eval_runtime": 15.3604, | |
| "eval_samples_per_second": 39.257, | |
| "eval_steps_per_second": 19.661, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004888268156424581, | |
| "grad_norm": 0.7674152851104736, | |
| "learning_rate": 0.00014, | |
| "loss": 2.3201, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00558659217877095, | |
| "grad_norm": 0.8000145554542542, | |
| "learning_rate": 0.00016, | |
| "loss": 2.2271, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006284916201117319, | |
| "grad_norm": 0.9004802703857422, | |
| "learning_rate": 0.00018, | |
| "loss": 2.0464, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006284916201117319, | |
| "eval_loss": 2.3105177879333496, | |
| "eval_runtime": 15.381, | |
| "eval_samples_per_second": 39.204, | |
| "eval_steps_per_second": 19.635, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006983240223463687, | |
| "grad_norm": 0.9847251176834106, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1128, | |
| "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": 942244752261120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |