| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2801, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03570153516601214, | |
| "grad_norm": 0.2294982522726059, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.4571, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07140307033202428, | |
| "grad_norm": 0.17154090106487274, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.4541, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.10710460549803641, | |
| "grad_norm": 0.19298459589481354, | |
| "learning_rate": 6e-06, | |
| "loss": 2.4134, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.14280614066404856, | |
| "grad_norm": 0.32980746030807495, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 2.3925, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1785076758300607, | |
| "grad_norm": 0.4573824107646942, | |
| "learning_rate": 1e-05, | |
| "loss": 2.309, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.21420921099607282, | |
| "grad_norm": 0.438753604888916, | |
| "learning_rate": 1.2e-05, | |
| "loss": 2.3336, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.24991074616208497, | |
| "grad_norm": 0.5054428577423096, | |
| "learning_rate": 1.4e-05, | |
| "loss": 2.2911, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.28561228132809713, | |
| "grad_norm": 0.5664726495742798, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 2.234, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.32131381649410923, | |
| "grad_norm": 0.6149884462356567, | |
| "learning_rate": 1.8e-05, | |
| "loss": 2.2339, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3570153516601214, | |
| "grad_norm": 0.7202581763267517, | |
| "learning_rate": 2e-05, | |
| "loss": 2.198, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.39271688682613354, | |
| "grad_norm": 0.6320284008979797, | |
| "learning_rate": 1.98482457644138e-05, | |
| "loss": 2.1665, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.42841842199214564, | |
| "grad_norm": 0.6476149559020996, | |
| "learning_rate": 1.9397588927258876e-05, | |
| "loss": 2.2035, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.4641199571581578, | |
| "grad_norm": 0.6560292840003967, | |
| "learning_rate": 1.8661707305302052e-05, | |
| "loss": 2.1686, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.49982149232416995, | |
| "grad_norm": 0.6389040350914001, | |
| "learning_rate": 1.7662935529147725e-05, | |
| "loss": 2.1021, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5355230274901821, | |
| "grad_norm": 0.8602333068847656, | |
| "learning_rate": 1.643158716827897e-05, | |
| "loss": 2.1302, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5712245626561943, | |
| "grad_norm": 0.764371395111084, | |
| "learning_rate": 1.500503468854458e-05, | |
| "loss": 2.147, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6069260978222063, | |
| "grad_norm": 0.809414267539978, | |
| "learning_rate": 1.342657516616169e-05, | |
| "loss": 2.1208, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.6426276329882185, | |
| "grad_norm": 0.8461398482322693, | |
| "learning_rate": 1.1744116184774898e-05, | |
| "loss": 2.067, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.6783291681542306, | |
| "grad_norm": 0.7336994409561157, | |
| "learning_rate": 1.00087217997093e-05, | |
| "loss": 2.1056, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.7140307033202428, | |
| "grad_norm": 0.8887193202972412, | |
| "learning_rate": 8.273062700634137e-06, | |
| "loss": 2.0957, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7497322384862549, | |
| "grad_norm": 0.7335702776908875, | |
| "learning_rate": 6.589817611513086e-06, | |
| "loss": 2.0847, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.7854337736522671, | |
| "grad_norm": 0.7930261492729187, | |
| "learning_rate": 5.010074446706905e-06, | |
| "loss": 2.1111, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.8211353088182792, | |
| "grad_norm": 0.754761278629303, | |
| "learning_rate": 3.5817797494951313e-06, | |
| "loss": 2.1029, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.8568368439842913, | |
| "grad_norm": 0.7991265058517456, | |
| "learning_rate": 2.3482834738712023e-06, | |
| "loss": 2.0618, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.8925383791503034, | |
| "grad_norm": 1.1803473234176636, | |
| "learning_rate": 1.347023276716265e-06, | |
| "loss": 2.0831, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.9282399143163156, | |
| "grad_norm": 0.8793602585792542, | |
| "learning_rate": 6.083882531987495e-07, | |
| "loss": 2.1029, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.9639414494823277, | |
| "grad_norm": 1.1215691566467285, | |
| "learning_rate": 1.5479660199286927e-07, | |
| "loss": 2.0779, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.9996429846483399, | |
| "grad_norm": 0.8478527665138245, | |
| "learning_rate": 1.5213958033388766e-11, | |
| "loss": 2.0917, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 2801, | |
| "total_flos": 5.10776634114048e+16, | |
| "train_loss": 2.1906768205718286, | |
| "train_runtime": 755.3629, | |
| "train_samples_per_second": 7.416, | |
| "train_steps_per_second": 3.708 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2801, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.10776634114048e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |