| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9975429975429976, | |
| "eval_steps": 500, | |
| "global_step": 203, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00025, | |
| "loss": 0.5873, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0005, | |
| "loss": 0.18, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0004963251406715272, | |
| "loss": 0.1853, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0004854085994147815, | |
| "loss": 0.1675, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00046757131025753886, | |
| "loss": 0.1538, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00044333766942743246, | |
| "loss": 0.1566, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.0004134201186930015, | |
| "loss": 0.1319, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00037869820037745775, | |
| "loss": 0.1561, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0003401926998041959, | |
| "loss": 0.151, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00029903563535704927, | |
| "loss": 0.1364, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002564369784137472, | |
| "loss": 0.1346, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00021364908154907752, | |
| "loss": 0.1329, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00017192986077855136, | |
| "loss": 0.1321, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0001325058142431701, | |
| "loss": 0.142, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.653596454434699e-05, | |
| "loss": 0.1461, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.507778478375834e-05, | |
| "loss": 0.1352, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 3.905611004420359e-05, | |
| "loss": 0.1247, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.9235948278956e-05, | |
| "loss": 0.1318, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 6.199989938854372e-06, | |
| "loss": 0.1373, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.314775287923677e-07, | |
| "loss": 0.1067, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 203, | |
| "total_flos": 5.428363952337715e+16, | |
| "train_loss": 0.1659050089091503, | |
| "train_runtime": 878.3087, | |
| "train_samples_per_second": 3.704, | |
| "train_steps_per_second": 0.231 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 203, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 5.428363952337715e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |