| { | |
| "best_metric": 3.659489154815674, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08991794987074295, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001798358997414859, | |
| "grad_norm": 1.892904281616211, | |
| "learning_rate": 5e-05, | |
| "loss": 7.5914, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001798358997414859, | |
| "eval_loss": 7.87414026260376, | |
| "eval_runtime": 99.3294, | |
| "eval_samples_per_second": 37.723, | |
| "eval_steps_per_second": 4.722, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003596717994829718, | |
| "grad_norm": 1.8523627519607544, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2369, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005395076992244577, | |
| "grad_norm": 1.8711965084075928, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.1987, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007193435989659436, | |
| "grad_norm": 2.076180934906006, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.2361, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008991794987074295, | |
| "grad_norm": 2.2019765377044678, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.6906, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010790153984489154, | |
| "grad_norm": 2.547671318054199, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.5445, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012588512981904013, | |
| "grad_norm": 2.629695177078247, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.2388, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014386871979318872, | |
| "grad_norm": 2.921963691711426, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.8722, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01618523097673373, | |
| "grad_norm": 2.59285569190979, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.1905, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01798358997414859, | |
| "grad_norm": 2.041452407836914, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.264, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01978194897156345, | |
| "grad_norm": 2.5271718502044678, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.9013, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.021580307968978307, | |
| "grad_norm": 2.6541106700897217, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 5.3764, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.023378666966393166, | |
| "grad_norm": 2.242335796356201, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 5.0807, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.025177025963808025, | |
| "grad_norm": 2.364999532699585, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.1957, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.026975384961222884, | |
| "grad_norm": 2.047051191329956, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 4.0444, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.028773743958637743, | |
| "grad_norm": 1.811107873916626, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.0814, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.030572102956052602, | |
| "grad_norm": 1.699466347694397, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.9142, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03237046195346746, | |
| "grad_norm": 1.7499068975448608, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.0083, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03416882095088232, | |
| "grad_norm": 1.9480732679367065, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.0982, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03596717994829718, | |
| "grad_norm": 1.8687691688537598, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.1553, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03776553894571204, | |
| "grad_norm": 1.7071983814239502, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.8703, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0395638979431269, | |
| "grad_norm": 1.7296050786972046, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 4.2591, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.041362256940541756, | |
| "grad_norm": 1.612310528755188, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 4.3794, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.043160615937956615, | |
| "grad_norm": 1.6319174766540527, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 4.4063, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.044958974935371473, | |
| "grad_norm": 1.577831745147705, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.4786, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.044958974935371473, | |
| "eval_loss": 3.9233860969543457, | |
| "eval_runtime": 99.6308, | |
| "eval_samples_per_second": 37.609, | |
| "eval_steps_per_second": 4.707, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04675733393278633, | |
| "grad_norm": 1.887658953666687, | |
| "learning_rate": 5e-05, | |
| "loss": 3.5318, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04855569293020119, | |
| "grad_norm": 1.7948553562164307, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.3642, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05035405192761605, | |
| "grad_norm": 1.6475787162780762, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.3877, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05215241092503091, | |
| "grad_norm": 1.607811450958252, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.4879, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05395076992244577, | |
| "grad_norm": 1.7005120515823364, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.6429, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05574912891986063, | |
| "grad_norm": 1.7422455549240112, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.587, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.057547487917275486, | |
| "grad_norm": 1.6355663537979126, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.5677, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.059345846914690345, | |
| "grad_norm": 1.731115460395813, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.7815, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.061144205912105204, | |
| "grad_norm": 1.6795060634613037, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.7316, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06294256490952006, | |
| "grad_norm": 1.6759228706359863, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.8109, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06474092390693492, | |
| "grad_norm": 1.653753399848938, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 4.1712, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06653928290434978, | |
| "grad_norm": 1.7878714799880981, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 4.1051, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06833764190176464, | |
| "grad_norm": 1.6746171712875366, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.97, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0701360008991795, | |
| "grad_norm": 1.775249719619751, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.8569, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07193435989659436, | |
| "grad_norm": 1.6178361177444458, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.9099, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07373271889400922, | |
| "grad_norm": 1.8096075057983398, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.1256, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07553107789142408, | |
| "grad_norm": 1.727738857269287, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.3099, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07732943688883893, | |
| "grad_norm": 1.73582923412323, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.5413, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0791277958862538, | |
| "grad_norm": 1.7474498748779297, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.7499, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08092615488366865, | |
| "grad_norm": 1.7811682224273682, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.5255, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08272451388108351, | |
| "grad_norm": 1.751634955406189, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.8033, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08452287287849837, | |
| "grad_norm": 1.661466360092163, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 3.6937, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08632123187591323, | |
| "grad_norm": 1.6849561929702759, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.9422, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08811959087332809, | |
| "grad_norm": 1.6296294927597046, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.9785, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08991794987074295, | |
| "grad_norm": 1.6093735694885254, | |
| "learning_rate": 0.0, | |
| "loss": 4.2984, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08991794987074295, | |
| "eval_loss": 3.659489154815674, | |
| "eval_runtime": 99.7649, | |
| "eval_samples_per_second": 37.558, | |
| "eval_steps_per_second": 4.701, | |
| "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": 5.671510799768617e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |