| { | |
| "best_metric": 2.8744540214538574, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03696345238645289, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007392690477290579, | |
| "grad_norm": 0.5833294987678528, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1577, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007392690477290579, | |
| "eval_loss": 4.195895195007324, | |
| "eval_runtime": 969.195, | |
| "eval_samples_per_second": 9.403, | |
| "eval_steps_per_second": 1.176, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014785380954581157, | |
| "grad_norm": 0.892480731010437, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4383, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022178071431871735, | |
| "grad_norm": 0.5106385946273804, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.5461, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029570761909162315, | |
| "grad_norm": 0.7261525988578796, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.5415, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0036963452386452895, | |
| "grad_norm": 0.9784935116767883, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.6274, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004435614286374347, | |
| "grad_norm": 1.1571110486984253, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.609, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0051748833341034054, | |
| "grad_norm": 1.2241264581680298, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.6862, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005914152381832463, | |
| "grad_norm": 1.4280940294265747, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.6754, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006653421429561521, | |
| "grad_norm": 1.5976660251617432, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.6256, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007392690477290579, | |
| "grad_norm": 1.4110456705093384, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.6138, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008131959525019637, | |
| "grad_norm": 1.5504977703094482, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.8511, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008871228572748694, | |
| "grad_norm": 2.184483766555786, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.878, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009610497620477753, | |
| "grad_norm": 0.938169002532959, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.7686, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010349766668206811, | |
| "grad_norm": 0.9936007261276245, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.8706, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011089035715935868, | |
| "grad_norm": 0.892974853515625, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.814, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011828304763664926, | |
| "grad_norm": 0.5331243276596069, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.8764, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012567573811393984, | |
| "grad_norm": 0.44186845421791077, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.9785, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013306842859123043, | |
| "grad_norm": 0.5591869950294495, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.9373, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0140461119068521, | |
| "grad_norm": 2.1058056354522705, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.925, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.014785380954581158, | |
| "grad_norm": 1.9208186864852905, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.053, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015524650002310215, | |
| "grad_norm": 3.2802469730377197, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.1154, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016263919050039273, | |
| "grad_norm": 2.129404306411743, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.1378, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01700318809776833, | |
| "grad_norm": 2.14886212348938, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.2828, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.017742457145497388, | |
| "grad_norm": 3.9402661323547363, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.3309, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.018481726193226446, | |
| "grad_norm": 4.390961170196533, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.4106, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018481726193226446, | |
| "eval_loss": 2.9548091888427734, | |
| "eval_runtime": 968.7842, | |
| "eval_samples_per_second": 9.407, | |
| "eval_steps_per_second": 1.177, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.019220995240955507, | |
| "grad_norm": 1.4390382766723633, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6398, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.019960264288684564, | |
| "grad_norm": 1.285017490386963, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.6834, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.020699533336413622, | |
| "grad_norm": 0.7559266686439514, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.7456, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02143880238414268, | |
| "grad_norm": 0.438568651676178, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.7858, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.022178071431871737, | |
| "grad_norm": 0.36864879727363586, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.8327, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.022917340479600794, | |
| "grad_norm": 1.0010043382644653, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.8275, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.023656609527329852, | |
| "grad_norm": 1.105016827583313, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8782, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02439587857505891, | |
| "grad_norm": 0.4782523512840271, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.9056, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.025135147622787967, | |
| "grad_norm": 0.6142726540565491, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.0591, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.025874416670517025, | |
| "grad_norm": 0.6701408624649048, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.0697, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.026613685718246086, | |
| "grad_norm": 0.6728911399841309, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.0663, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.027352954765975143, | |
| "grad_norm": 1.5853469371795654, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.1271, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0280922238137042, | |
| "grad_norm": 0.5142918825149536, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.5163, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02883149286143326, | |
| "grad_norm": 0.5276281237602234, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.6449, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.029570761909162316, | |
| "grad_norm": 0.5071715712547302, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.6503, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.030310030956891373, | |
| "grad_norm": 0.4902350604534149, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.7115, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03104930000462043, | |
| "grad_norm": 0.5433118939399719, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.7676, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03178856905234949, | |
| "grad_norm": 0.44246047735214233, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.8322, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.032527838100078546, | |
| "grad_norm": 0.5774577856063843, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8249, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.033267107147807604, | |
| "grad_norm": 0.3766028583049774, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.9393, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03400637619553666, | |
| "grad_norm": 0.5460787415504456, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.0283, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03474564524326572, | |
| "grad_norm": 0.6633034944534302, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.9091, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.035484914290994776, | |
| "grad_norm": 0.7276972532272339, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.0902, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.036224183338723834, | |
| "grad_norm": 0.775564432144165, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.1153, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03696345238645289, | |
| "grad_norm": 2.0693697929382324, | |
| "learning_rate": 0.0, | |
| "loss": 3.2925, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03696345238645289, | |
| "eval_loss": 2.8744540214538574, | |
| "eval_runtime": 968.9207, | |
| "eval_samples_per_second": 9.405, | |
| "eval_steps_per_second": 1.177, | |
| "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": 1.0228361536208896e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |