| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001510745175057597, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015107451750575972, | |
| "grad_norm": 0.3094334006309509, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1896, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015107451750575972, | |
| "eval_loss": 1.3592280149459839, | |
| "eval_runtime": 87.6726, | |
| "eval_samples_per_second": 31.789, | |
| "eval_steps_per_second": 15.9, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00030214903501151944, | |
| "grad_norm": 0.42551469802856445, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5883, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00045322355251727916, | |
| "grad_norm": 0.4838829040527344, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5357, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00045322355251727916, | |
| "eval_loss": 1.3581395149230957, | |
| "eval_runtime": 85.608, | |
| "eval_samples_per_second": 32.555, | |
| "eval_steps_per_second": 16.284, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006042980700230389, | |
| "grad_norm": 0.3123856782913208, | |
| "learning_rate": 8e-05, | |
| "loss": 1.238, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007553725875287985, | |
| "grad_norm": 0.3366721272468567, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3196, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009064471050345583, | |
| "grad_norm": 0.4621126651763916, | |
| "learning_rate": 0.00012, | |
| "loss": 1.53, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009064471050345583, | |
| "eval_loss": 1.3454577922821045, | |
| "eval_runtime": 85.7135, | |
| "eval_samples_per_second": 32.515, | |
| "eval_steps_per_second": 16.263, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001057521622540318, | |
| "grad_norm": 0.4359261989593506, | |
| "learning_rate": 0.00014, | |
| "loss": 1.1655, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012085961400460777, | |
| "grad_norm": 0.6732693910598755, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7161, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013596706575518375, | |
| "grad_norm": 0.4551469385623932, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2531, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013596706575518375, | |
| "eval_loss": 1.2973469495773315, | |
| "eval_runtime": 86.04, | |
| "eval_samples_per_second": 32.392, | |
| "eval_steps_per_second": 16.202, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001510745175057597, | |
| "grad_norm": 0.39229777455329895, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1691, | |
| "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": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |