| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020537395173712135, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006845798391237378, | |
| "eval_loss": 2.7142088413238525, | |
| "eval_runtime": 9.1893, | |
| "eval_samples_per_second": 66.926, | |
| "eval_steps_per_second": 33.517, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020537395173712133, | |
| "grad_norm": 8.022150993347168, | |
| "learning_rate": 6e-05, | |
| "loss": 11.7639, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004107479034742427, | |
| "grad_norm": 8.038663864135742, | |
| "learning_rate": 0.00012, | |
| "loss": 10.9252, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005476638712989902, | |
| "eval_loss": 2.5979135036468506, | |
| "eval_runtime": 7.5921, | |
| "eval_samples_per_second": 81.005, | |
| "eval_steps_per_second": 40.568, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00616121855211364, | |
| "grad_norm": 4.232173442840576, | |
| "learning_rate": 0.00018, | |
| "loss": 9.9597, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008214958069484853, | |
| "grad_norm": 5.966957092285156, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 11.2484, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010268697586856067, | |
| "grad_norm": 5.1489033699035645, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 9.7961, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010953277425979804, | |
| "eval_loss": 2.451749563217163, | |
| "eval_runtime": 7.6713, | |
| "eval_samples_per_second": 80.169, | |
| "eval_steps_per_second": 40.15, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01232243710422728, | |
| "grad_norm": 4.852463722229004, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.2773, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014376176621598494, | |
| "grad_norm": 5.321272373199463, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.2782, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016429916138969707, | |
| "grad_norm": 5.256471633911133, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 9.7387, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016429916138969707, | |
| "eval_loss": 2.3914122581481934, | |
| "eval_runtime": 7.7382, | |
| "eval_samples_per_second": 79.476, | |
| "eval_steps_per_second": 39.803, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01848365565634092, | |
| "grad_norm": 5.111404895782471, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 9.2745, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.020537395173712135, | |
| "grad_norm": 5.149004936218262, | |
| "learning_rate": 0.0, | |
| "loss": 10.1422, | |
| "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": 133645096452096.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |