| { | |
| "best_metric": 4.331421375274658, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06760753824051381, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013521507648102764, | |
| "grad_norm": 1.8915984630584717, | |
| "learning_rate": 5e-05, | |
| "loss": 4.5786, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013521507648102764, | |
| "eval_loss": 5.687441825866699, | |
| "eval_runtime": 139.5212, | |
| "eval_samples_per_second": 35.715, | |
| "eval_steps_per_second": 4.465, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002704301529620553, | |
| "grad_norm": 1.756727933883667, | |
| "learning_rate": 0.0001, | |
| "loss": 4.9551, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004056452294430829, | |
| "grad_norm": 1.645915150642395, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.9015, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005408603059241106, | |
| "grad_norm": 1.7178233861923218, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.8088, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006760753824051381, | |
| "grad_norm": 1.3679091930389404, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.6121, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008112904588861658, | |
| "grad_norm": 0.87444007396698, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.6138, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009465055353671934, | |
| "grad_norm": 0.8649806380271912, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.6728, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010817206118482211, | |
| "grad_norm": 1.1052812337875366, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.6942, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012169356883292487, | |
| "grad_norm": 1.4397693872451782, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.9553, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013521507648102763, | |
| "grad_norm": 1.3489494323730469, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.9686, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01487365841291304, | |
| "grad_norm": 1.3816546201705933, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 5.1422, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016225809177723316, | |
| "grad_norm": 1.2895071506500244, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 5.7468, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017577959942533593, | |
| "grad_norm": 0.36154186725616455, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.7029, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018930110707343867, | |
| "grad_norm": 0.36087360978126526, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.0018, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020282261472154145, | |
| "grad_norm": 0.37742745876312256, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 4.0517, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021634412236964422, | |
| "grad_norm": 0.5160012245178223, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.0323, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022986563001774696, | |
| "grad_norm": 0.4996909201145172, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 4.1985, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.024338713766584974, | |
| "grad_norm": 0.5520260334014893, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.2072, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02569086453139525, | |
| "grad_norm": 0.6334313750267029, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.1884, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.027043015296205525, | |
| "grad_norm": 0.5337988138198853, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.3863, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028395166061015803, | |
| "grad_norm": 0.4783671200275421, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.4568, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02974731682582608, | |
| "grad_norm": 0.4848990738391876, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 4.5359, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.031099467590636354, | |
| "grad_norm": 0.5938157439231873, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 4.6106, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03245161835544663, | |
| "grad_norm": 0.8695794343948364, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 4.9047, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.033803769120256906, | |
| "grad_norm": 1.6180835962295532, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 5.4973, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.033803769120256906, | |
| "eval_loss": 4.454497337341309, | |
| "eval_runtime": 139.7567, | |
| "eval_samples_per_second": 35.655, | |
| "eval_steps_per_second": 4.458, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03515591988506719, | |
| "grad_norm": 0.5346957445144653, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7734, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03650807064987746, | |
| "grad_norm": 0.48548877239227295, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.7513, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.037860221414687735, | |
| "grad_norm": 0.5325626730918884, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.9249, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.039212372179498016, | |
| "grad_norm": 0.559912383556366, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.9959, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04056452294430829, | |
| "grad_norm": 0.5321981906890869, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 4.0154, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.041916673709118564, | |
| "grad_norm": 0.502756655216217, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 4.12, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.043268824473928845, | |
| "grad_norm": 0.4477120339870453, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.032, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04462097523873912, | |
| "grad_norm": 0.4660121202468872, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 4.2817, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04597312600354939, | |
| "grad_norm": 0.42898258566856384, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.3959, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.047325276768359674, | |
| "grad_norm": 0.4856753647327423, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 4.6094, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04867742753316995, | |
| "grad_norm": 0.5574827194213867, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 4.5035, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05002957829798022, | |
| "grad_norm": 0.9172268509864807, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 4.9945, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0513817290627905, | |
| "grad_norm": 0.2705156207084656, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.5267, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05273387982760078, | |
| "grad_norm": 0.25495946407318115, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.8079, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05408603059241105, | |
| "grad_norm": 0.258202463388443, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.8776, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05543818135722133, | |
| "grad_norm": 0.2978667616844177, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.9657, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.056790332122031606, | |
| "grad_norm": 0.3443995416164398, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 4.0358, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05814248288684188, | |
| "grad_norm": 0.325653612613678, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 4.0879, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05949463365165216, | |
| "grad_norm": 0.37084466218948364, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.1399, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.060846784416462435, | |
| "grad_norm": 0.3950638771057129, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 4.1623, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06219893518127271, | |
| "grad_norm": 0.4259364902973175, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 4.2288, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06355108594608298, | |
| "grad_norm": 0.5128974914550781, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 4.3181, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06490323671089326, | |
| "grad_norm": 0.5414010882377625, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 4.408, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06625538747570354, | |
| "grad_norm": 0.7349984049797058, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 4.7669, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06760753824051381, | |
| "grad_norm": 1.0795515775680542, | |
| "learning_rate": 0.0, | |
| "loss": 5.1084, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06760753824051381, | |
| "eval_loss": 4.331421375274658, | |
| "eval_runtime": 139.8916, | |
| "eval_samples_per_second": 35.62, | |
| "eval_steps_per_second": 4.453, | |
| "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": 5.6433905536650445e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |