| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017383746197305518, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001738374619730552, | |
| "grad_norm": 0.051137156784534454, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3746, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001738374619730552, | |
| "eval_loss": 10.373723983764648, | |
| "eval_runtime": 1.984, | |
| "eval_samples_per_second": 122.481, | |
| "eval_steps_per_second": 61.492, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003476749239461104, | |
| "grad_norm": 0.03803086280822754, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3774, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005215123859191656, | |
| "grad_norm": 0.03892258554697037, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3743, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005215123859191656, | |
| "eval_loss": 10.373678207397461, | |
| "eval_runtime": 2.017, | |
| "eval_samples_per_second": 120.478, | |
| "eval_steps_per_second": 60.487, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006953498478922208, | |
| "grad_norm": 0.05050083249807358, | |
| "learning_rate": 8e-05, | |
| "loss": 10.376, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008691873098652759, | |
| "grad_norm": 0.042805321514606476, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3728, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010430247718383311, | |
| "grad_norm": 0.041813645511865616, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3757, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010430247718383311, | |
| "eval_loss": 10.373467445373535, | |
| "eval_runtime": 2.0449, | |
| "eval_samples_per_second": 118.833, | |
| "eval_steps_per_second": 59.661, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012168622338113864, | |
| "grad_norm": 0.055100347846746445, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3785, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013906996957844416, | |
| "grad_norm": 0.05738470330834389, | |
| "learning_rate": 0.00016, | |
| "loss": 10.375, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01564537157757497, | |
| "grad_norm": 0.04711873456835747, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3732, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01564537157757497, | |
| "eval_loss": 10.373083114624023, | |
| "eval_runtime": 2.0617, | |
| "eval_samples_per_second": 117.867, | |
| "eval_steps_per_second": 59.176, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.017383746197305518, | |
| "grad_norm": 0.04928680136799812, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3716, | |
| "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": 258618163200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |