| { | |
| "best_metric": 11.930959701538086, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.7777777777777777, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.010871877893805504, | |
| "learning_rate": 5e-05, | |
| "loss": 11.932, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "eval_loss": 11.932236671447754, | |
| "eval_runtime": 0.2798, | |
| "eval_samples_per_second": 432.457, | |
| "eval_steps_per_second": 57.184, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.014063762500882149, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9328, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.009596806019544601, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.929, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.011132453568279743, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9334, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 0.009860910475254059, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9332, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.013270008377730846, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.929, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 0.011237203143537045, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9311, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.010505507700145245, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9329, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.012720140628516674, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9311, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.012777755036950111, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9318, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6111111111111112, | |
| "grad_norm": 0.013362806290388107, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9327, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.012490603141486645, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9322, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7222222222222222, | |
| "grad_norm": 0.014601469971239567, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9329, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.012229213491082191, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9321, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.0167827308177948, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9307, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.015168695710599422, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9302, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9444444444444444, | |
| "grad_norm": 0.01865260861814022, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9315, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.014603833667933941, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9326, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0555555555555556, | |
| "grad_norm": 0.014844034798443317, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9309, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.01844005472958088, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9305, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1666666666666667, | |
| "grad_norm": 0.014500699937343597, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9287, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2222222222222223, | |
| "grad_norm": 0.019635509699583054, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9331, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2777777777777777, | |
| "grad_norm": 0.015835417434573174, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9323, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.020890524610877037, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.931, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3888888888888888, | |
| "grad_norm": 0.022467510774731636, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.93, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3888888888888888, | |
| "eval_loss": 11.931645393371582, | |
| "eval_runtime": 0.2777, | |
| "eval_samples_per_second": 435.707, | |
| "eval_steps_per_second": 57.614, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4444444444444444, | |
| "grad_norm": 0.017678676173090935, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9328, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.021845893934369087, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.9308, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": 0.022769257426261902, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9299, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6111111111111112, | |
| "grad_norm": 0.026064997538924217, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9315, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 0.017668651416897774, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9318, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7222222222222223, | |
| "grad_norm": 0.02388639561831951, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9326, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.0233757346868515, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9302, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8333333333333335, | |
| "grad_norm": 0.02187464013695717, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.9291, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.8888888888888888, | |
| "grad_norm": 0.023511428385972977, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9305, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.9444444444444444, | |
| "grad_norm": 0.025736413896083832, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.9306, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.02582811564207077, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.9313, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.0555555555555554, | |
| "grad_norm": 0.02202489972114563, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.9324, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.111111111111111, | |
| "grad_norm": 0.024345090612769127, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9282, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.1666666666666665, | |
| "grad_norm": 0.02134646661579609, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.9291, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.026549415662884712, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.9334, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.2777777777777777, | |
| "grad_norm": 0.02680145390331745, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.932, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.3333333333333335, | |
| "grad_norm": 0.02874022163450718, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9292, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.388888888888889, | |
| "grad_norm": 0.02543819695711136, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9291, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.4444444444444446, | |
| "grad_norm": 0.02165454439818859, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9291, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.02238444611430168, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9317, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.5555555555555554, | |
| "grad_norm": 0.03011086955666542, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.929, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.611111111111111, | |
| "grad_norm": 0.024565398693084717, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.9307, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.028965452685952187, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.9326, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.7222222222222223, | |
| "grad_norm": 0.028163012117147446, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.9299, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.7777777777777777, | |
| "grad_norm": 0.02760309912264347, | |
| "learning_rate": 0.0, | |
| "loss": 11.9299, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.7777777777777777, | |
| "eval_loss": 11.930959701538086, | |
| "eval_runtime": 0.2723, | |
| "eval_samples_per_second": 444.413, | |
| "eval_steps_per_second": 58.765, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1042494259200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |