| { | |
| "best_metric": 6.911687850952148, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4125838060856111, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008251676121712223, | |
| "grad_norm": 0.19007240235805511, | |
| "learning_rate": 5e-05, | |
| "loss": 6.8772, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008251676121712223, | |
| "eval_loss": 6.937552452087402, | |
| "eval_runtime": 0.8717, | |
| "eval_samples_per_second": 937.293, | |
| "eval_steps_per_second": 118.165, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016503352243424446, | |
| "grad_norm": 0.18242356181144714, | |
| "learning_rate": 0.0001, | |
| "loss": 6.858, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02475502836513667, | |
| "grad_norm": 0.1995544582605362, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 6.8447, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03300670448684889, | |
| "grad_norm": 0.18593429028987885, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.8302, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.041258380608561115, | |
| "grad_norm": 0.18931446969509125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.8183, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04951005673027334, | |
| "grad_norm": 0.1950785368680954, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.8054, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05776173285198556, | |
| "grad_norm": 0.20064397156238556, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.7876, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06601340897369778, | |
| "grad_norm": 0.22192345559597015, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.769, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07426508509541001, | |
| "grad_norm": 0.22847650945186615, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 6.7498, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08251676121712223, | |
| "grad_norm": 0.2764003574848175, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.7123, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09076843733883445, | |
| "grad_norm": 0.25168463587760925, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 6.6124, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09902011346054668, | |
| "grad_norm": 0.31273701786994934, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 6.3779, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1072717895822589, | |
| "grad_norm": 0.18679746985435486, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 6.8239, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11552346570397112, | |
| "grad_norm": 0.19334200024604797, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.8569, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12377514182568335, | |
| "grad_norm": 0.21157041192054749, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 6.8419, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13202681794739557, | |
| "grad_norm": 0.20532171428203583, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 6.8266, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14027849406910778, | |
| "grad_norm": 0.1977279633283615, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 6.8141, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14853017019082002, | |
| "grad_norm": 0.19488519430160522, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 6.7972, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15678184631253222, | |
| "grad_norm": 0.21557967364788055, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 6.7828, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16503352243424446, | |
| "grad_norm": 0.22028861939907074, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.7694, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17328519855595667, | |
| "grad_norm": 0.23538333177566528, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 6.7487, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1815368746776689, | |
| "grad_norm": 0.2506059408187866, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 6.7218, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18978855079938112, | |
| "grad_norm": 0.25545573234558105, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 6.6615, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19804022692109335, | |
| "grad_norm": 0.28446659445762634, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 6.4915, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20629190304280556, | |
| "grad_norm": 0.3152291476726532, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 6.185, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20629190304280556, | |
| "eval_loss": 6.917301654815674, | |
| "eval_runtime": 0.8631, | |
| "eval_samples_per_second": 946.555, | |
| "eval_steps_per_second": 119.333, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2145435791645178, | |
| "grad_norm": 0.20274803042411804, | |
| "learning_rate": 5e-05, | |
| "loss": 6.8614, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.22279525528623, | |
| "grad_norm": 0.21126407384872437, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 6.8386, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.23104693140794225, | |
| "grad_norm": 0.2221248298883438, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 6.8223, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23929860752965446, | |
| "grad_norm": 0.2102772444486618, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 6.8099, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2475502836513667, | |
| "grad_norm": 0.20332932472229004, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 6.7978, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2558019597730789, | |
| "grad_norm": 0.22618810832500458, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 6.7843, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.26405363589479114, | |
| "grad_norm": 0.2285047322511673, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.7745, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2723053120165034, | |
| "grad_norm": 0.23838725686073303, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 6.7552, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.28055698813821556, | |
| "grad_norm": 0.22661758959293365, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.7389, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2888086642599278, | |
| "grad_norm": 0.2469901740550995, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 6.6998, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.29706034038164003, | |
| "grad_norm": 0.25235992670059204, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 6.6207, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.30531201650335227, | |
| "grad_norm": 0.3499048054218292, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 6.4126, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.31356369262506445, | |
| "grad_norm": 0.19594097137451172, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.8115, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3218153687467767, | |
| "grad_norm": 0.21886812150478363, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 6.842, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3300670448684889, | |
| "grad_norm": 0.2264992594718933, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 6.8276, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.33831872099020116, | |
| "grad_norm": 0.23042714595794678, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 6.8102, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.34657039711191334, | |
| "grad_norm": 0.21896089613437653, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 6.7979, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3548220732336256, | |
| "grad_norm": 0.21895575523376465, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 6.7872, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3630737493553378, | |
| "grad_norm": 0.21815863251686096, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 6.7742, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.37132542547705005, | |
| "grad_norm": 0.22837361693382263, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 6.7574, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.37957710159876223, | |
| "grad_norm": 0.2377353459596634, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 6.7389, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.38782877772047447, | |
| "grad_norm": 0.2529526650905609, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 6.7065, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3960804538421867, | |
| "grad_norm": 0.2696276307106018, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 6.658, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4043321299638989, | |
| "grad_norm": 0.2675720751285553, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 6.5319, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4125838060856111, | |
| "grad_norm": 0.28477150201797485, | |
| "learning_rate": 0.0, | |
| "loss": 6.2163, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4125838060856111, | |
| "eval_loss": 6.911687850952148, | |
| "eval_runtime": 0.78, | |
| "eval_samples_per_second": 1047.488, | |
| "eval_steps_per_second": 132.058, | |
| "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": 5705957376000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |