| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0823045267489712, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027434842249657062, | |
| "eval_loss": 0.9235183000564575, | |
| "eval_runtime": 19.8583, | |
| "eval_samples_per_second": 7.755, | |
| "eval_steps_per_second": 3.877, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00823045267489712, | |
| "grad_norm": 1.4497631788253784, | |
| "learning_rate": 6e-05, | |
| "loss": 0.8756, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01646090534979424, | |
| "grad_norm": 1.4429152011871338, | |
| "learning_rate": 0.00012, | |
| "loss": 0.7314, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02194787379972565, | |
| "eval_loss": 0.3222784101963043, | |
| "eval_runtime": 19.8038, | |
| "eval_samples_per_second": 7.776, | |
| "eval_steps_per_second": 3.888, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024691358024691357, | |
| "grad_norm": 1.7610608339309692, | |
| "learning_rate": 0.00018, | |
| "loss": 0.3779, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03292181069958848, | |
| "grad_norm": 1.0906153917312622, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.1599, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0411522633744856, | |
| "grad_norm": 1.4689967632293701, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.1314, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0438957475994513, | |
| "eval_loss": 0.175197035074234, | |
| "eval_runtime": 19.8746, | |
| "eval_samples_per_second": 7.749, | |
| "eval_steps_per_second": 3.874, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04938271604938271, | |
| "grad_norm": 1.8150358200073242, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.1141, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05761316872427984, | |
| "grad_norm": 1.2124422788619995, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.1481, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06584362139917696, | |
| "grad_norm": 0.7941676378250122, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.1215, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06584362139917696, | |
| "eval_loss": 0.14350953698158264, | |
| "eval_runtime": 19.9308, | |
| "eval_samples_per_second": 7.727, | |
| "eval_steps_per_second": 3.863, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.6792399287223816, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.1419, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0823045267489712, | |
| "grad_norm": 0.7815915942192078, | |
| "learning_rate": 0.0, | |
| "loss": 0.1259, | |
| "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": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |