| { | |
| "best_metric": 3.7166805267333984, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.7516198704103672, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03455723542116631, | |
| "grad_norm": 1.8546185493469238, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7889, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03455723542116631, | |
| "eval_loss": 5.762509822845459, | |
| "eval_runtime": 2.2799, | |
| "eval_samples_per_second": 85.53, | |
| "eval_steps_per_second": 10.965, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06911447084233262, | |
| "grad_norm": 2.838688373565674, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4169, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10367170626349892, | |
| "grad_norm": 3.2109413146972656, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.5528, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13822894168466524, | |
| "grad_norm": 3.303469657897949, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.9354, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.17278617710583152, | |
| "grad_norm": 4.00386381149292, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.2885, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20734341252699784, | |
| "grad_norm": 7.4307661056518555, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 5.8926, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.24190064794816415, | |
| "grad_norm": 10.542497634887695, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 7.3813, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.27645788336933047, | |
| "grad_norm": 1.3191660642623901, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.5787, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.31101511879049676, | |
| "grad_norm": 2.1402812004089355, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.9215, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.34557235421166305, | |
| "grad_norm": 2.7204787731170654, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.849, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3801295896328294, | |
| "grad_norm": 1.7316516637802124, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.0206, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4146868250539957, | |
| "grad_norm": 3.3468918800354004, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.2344, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.44924406047516197, | |
| "grad_norm": 3.2594194412231445, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 4.2046, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4838012958963283, | |
| "grad_norm": 4.910807132720947, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.0957, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5183585313174947, | |
| "grad_norm": 3.8754677772521973, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.4905, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5529157667386609, | |
| "grad_norm": 2.256284475326538, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.6448, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5874730021598272, | |
| "grad_norm": 1.49455726146698, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.7582, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6220302375809935, | |
| "grad_norm": 2.0562615394592285, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.8544, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6565874730021598, | |
| "grad_norm": 2.4462602138519287, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.958, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6911447084233261, | |
| "grad_norm": 3.01643443107605, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.2973, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7257019438444925, | |
| "grad_norm": 6.936033725738525, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.6049, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7602591792656588, | |
| "grad_norm": 0.8561592698097229, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.3791, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7948164146868251, | |
| "grad_norm": 1.1636525392532349, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.5051, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8293736501079914, | |
| "grad_norm": 1.9778391122817993, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.4923, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8639308855291576, | |
| "grad_norm": 1.1745647192001343, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.5901, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8639308855291576, | |
| "eval_loss": 3.814847469329834, | |
| "eval_runtime": 2.2789, | |
| "eval_samples_per_second": 85.567, | |
| "eval_steps_per_second": 10.97, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8984881209503239, | |
| "grad_norm": 2.3841733932495117, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7094, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.9330453563714903, | |
| "grad_norm": 2.165337324142456, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.9942, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9676025917926566, | |
| "grad_norm": 7.546828746795654, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 4.3582, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.0259179265658747, | |
| "grad_norm": 1.986472249031067, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 5.6933, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.060475161987041, | |
| "grad_norm": 1.5792019367218018, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.3252, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0950323974082075, | |
| "grad_norm": 1.5796281099319458, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.3205, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1295896328293737, | |
| "grad_norm": 1.7154875993728638, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.4918, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.16414686825054, | |
| "grad_norm": 2.2885804176330566, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.6606, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1987041036717063, | |
| "grad_norm": 3.100572347640991, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.7339, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2332613390928726, | |
| "grad_norm": 7.583836078643799, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 4.1832, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.267818574514039, | |
| "grad_norm": 1.4905058145523071, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.4948, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3023758099352052, | |
| "grad_norm": 1.3239670991897583, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.2022, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.3369330453563715, | |
| "grad_norm": 1.6314467191696167, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.3676, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.3714902807775378, | |
| "grad_norm": 2.0681777000427246, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.4819, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.406047516198704, | |
| "grad_norm": 2.430373430252075, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.6413, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4406047516198703, | |
| "grad_norm": 3.5118353366851807, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.7818, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.4751619870410368, | |
| "grad_norm": 4.599954605102539, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 4.1105, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.509719222462203, | |
| "grad_norm": 3.1489386558532715, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.3242, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.5442764578833694, | |
| "grad_norm": 1.399327039718628, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.1605, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.5788336933045355, | |
| "grad_norm": 2.1838557720184326, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.3349, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.613390928725702, | |
| "grad_norm": 1.7547966241836548, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.3238, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.6479481641468683, | |
| "grad_norm": 4.076164245605469, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 3.4109, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.6825053995680346, | |
| "grad_norm": 7.376658916473389, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.7638, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.7170626349892009, | |
| "grad_norm": 19.589956283569336, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 4.2819, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.7516198704103672, | |
| "grad_norm": 1.4673881530761719, | |
| "learning_rate": 0.0, | |
| "loss": 3.3217, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.7516198704103672, | |
| "eval_loss": 3.7166805267333984, | |
| "eval_runtime": 2.2813, | |
| "eval_samples_per_second": 85.477, | |
| "eval_steps_per_second": 10.959, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |