| { | |
| "best_metric": 0.7740952372550964, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3104384943733023, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006208769887466045, | |
| "grad_norm": 19.560606002807617, | |
| "learning_rate": 5e-05, | |
| "loss": 10.9171, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006208769887466045, | |
| "eval_loss": 1.11298406124115, | |
| "eval_runtime": 28.9605, | |
| "eval_samples_per_second": 37.465, | |
| "eval_steps_per_second": 4.696, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01241753977493209, | |
| "grad_norm": 23.52311897277832, | |
| "learning_rate": 0.0001, | |
| "loss": 13.1041, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018626309662398137, | |
| "grad_norm": 12.965242385864258, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 13.7213, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02483507954986418, | |
| "grad_norm": 18.21459197998047, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 14.4377, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03104384943733023, | |
| "grad_norm": 15.356135368347168, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 14.4143, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.037252619324796274, | |
| "grad_norm": 11.831315994262695, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 13.9598, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04346138921226232, | |
| "grad_norm": 11.837441444396973, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 14.6875, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04967015909972836, | |
| "grad_norm": 13.21572494506836, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 14.6386, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05587892898719441, | |
| "grad_norm": 14.249505043029785, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 14.6072, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06208769887466046, | |
| "grad_norm": 13.186634063720703, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 14.1525, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0682964687621265, | |
| "grad_norm": 13.565954208374023, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 14.272, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07450523864959255, | |
| "grad_norm": 14.474984169006348, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 15.3644, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0807140085370586, | |
| "grad_norm": 17.69236946105957, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 13.4338, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08692277842452464, | |
| "grad_norm": 7.923816680908203, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.0057, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09313154831199069, | |
| "grad_norm": 7.850938320159912, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.5823, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09934031819945673, | |
| "grad_norm": 7.282667636871338, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 12.5114, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10554908808692277, | |
| "grad_norm": 7.891377925872803, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 12.7295, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11175785797438882, | |
| "grad_norm": 7.253997325897217, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 12.8208, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11796662786185487, | |
| "grad_norm": 7.745668411254883, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 13.2546, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12417539774932092, | |
| "grad_norm": 8.683799743652344, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 13.5887, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13038416763678695, | |
| "grad_norm": 10.244661331176758, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 13.8284, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.136592937524253, | |
| "grad_norm": 10.36053466796875, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 13.2502, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14280170741171905, | |
| "grad_norm": 11.601000785827637, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 13.6668, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1490104772991851, | |
| "grad_norm": 11.934355735778809, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 14.1468, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15521924718665114, | |
| "grad_norm": 16.675373077392578, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 14.9058, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15521924718665114, | |
| "eval_loss": 0.7947022318840027, | |
| "eval_runtime": 29.5165, | |
| "eval_samples_per_second": 36.759, | |
| "eval_steps_per_second": 4.608, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1614280170741172, | |
| "grad_norm": 5.082066535949707, | |
| "learning_rate": 5e-05, | |
| "loss": 9.8421, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.16763678696158324, | |
| "grad_norm": 5.646501064300537, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.8886, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1738455568490493, | |
| "grad_norm": 5.460198402404785, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.0623, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18005432673651534, | |
| "grad_norm": 6.139311790466309, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 12.0344, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.18626309662398138, | |
| "grad_norm": 6.533102035522461, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 12.672, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19247186651144743, | |
| "grad_norm": 7.447323322296143, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 13.082, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.19868063639891345, | |
| "grad_norm": 8.437141418457031, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 13.3574, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2048894062863795, | |
| "grad_norm": 9.51140308380127, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 13.1222, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.21109817617384555, | |
| "grad_norm": 10.1847562789917, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 13.8075, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2173069460613116, | |
| "grad_norm": 9.696736335754395, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 12.9002, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22351571594877764, | |
| "grad_norm": 10.21894645690918, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 13.2216, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2297244858362437, | |
| "grad_norm": 11.558626174926758, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 13.9245, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.23593325572370974, | |
| "grad_norm": 11.94530963897705, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 12.3904, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2421420256111758, | |
| "grad_norm": 4.622230052947998, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.1714, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.24835079549864184, | |
| "grad_norm": 5.022961139678955, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.678, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25455956538610786, | |
| "grad_norm": 5.296011924743652, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.71, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2607683352735739, | |
| "grad_norm": 5.8643412590026855, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 12.5232, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.26697710516103995, | |
| "grad_norm": 6.14801025390625, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 13.006, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.273185875048506, | |
| "grad_norm": 6.819303035736084, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 12.6432, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.27939464493597205, | |
| "grad_norm": 7.7182722091674805, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 12.9021, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2856034148234381, | |
| "grad_norm": 8.286754608154297, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 13.2977, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.29181218471090414, | |
| "grad_norm": 8.834489822387695, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 12.9507, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2980209545983702, | |
| "grad_norm": 10.305696487426758, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 12.9905, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.30422972448583624, | |
| "grad_norm": 11.25792121887207, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 14.2701, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3104384943733023, | |
| "grad_norm": 16.177717208862305, | |
| "learning_rate": 0.0, | |
| "loss": 15.1178, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3104384943733023, | |
| "eval_loss": 0.7740952372550964, | |
| "eval_runtime": 29.1943, | |
| "eval_samples_per_second": 37.165, | |
| "eval_steps_per_second": 4.658, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 5.6880795595309056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |