| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0028456923332305724, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.485641110768574e-05, | |
| "eval_loss": 4.818389415740967, | |
| "eval_runtime": 517.8108, | |
| "eval_samples_per_second": 8.573, | |
| "eval_steps_per_second": 4.287, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002845692333230572, | |
| "grad_norm": 10.10597038269043, | |
| "learning_rate": 6e-05, | |
| "loss": 19.8011, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005691384666461144, | |
| "grad_norm": 8.171477317810059, | |
| "learning_rate": 0.00012, | |
| "loss": 20.1722, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007588512888614859, | |
| "eval_loss": 4.06050443649292, | |
| "eval_runtime": 517.6006, | |
| "eval_samples_per_second": 8.576, | |
| "eval_steps_per_second": 4.289, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008537076999691717, | |
| "grad_norm": 11.392943382263184, | |
| "learning_rate": 0.00018, | |
| "loss": 19.0904, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011382769332922288, | |
| "grad_norm": 7.457381725311279, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 13.1863, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0014228461666152862, | |
| "grad_norm": 10.310413360595703, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.9676, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015177025777229718, | |
| "eval_loss": 2.6157023906707764, | |
| "eval_runtime": 517.9585, | |
| "eval_samples_per_second": 8.57, | |
| "eval_steps_per_second": 4.286, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0017074153999383434, | |
| "grad_norm": 9.0299654006958, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 9.6165, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0019919846332614004, | |
| "grad_norm": 8.466657638549805, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.5539, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0022765538665844576, | |
| "grad_norm": 11.605523109436035, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.7119, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0022765538665844576, | |
| "eval_loss": 2.4811155796051025, | |
| "eval_runtime": 517.5568, | |
| "eval_samples_per_second": 8.577, | |
| "eval_steps_per_second": 4.289, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002561123099907515, | |
| "grad_norm": 8.81380844116211, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.0272, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0028456923332305724, | |
| "grad_norm": 8.043525695800781, | |
| "learning_rate": 0.0, | |
| "loss": 8.7699, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.042527481856e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |