| { | |
| "best_metric": 0.12280955910682678, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05829204313611192, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011658408627222385, | |
| "grad_norm": 16.436328887939453, | |
| "learning_rate": 5e-05, | |
| "loss": 12.1759, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011658408627222385, | |
| "eval_loss": 12.8995943069458, | |
| "eval_runtime": 174.9955, | |
| "eval_samples_per_second": 33.024, | |
| "eval_steps_per_second": 4.132, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002331681725444477, | |
| "grad_norm": 16.717208862304688, | |
| "learning_rate": 0.0001, | |
| "loss": 12.3466, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0034975225881667153, | |
| "grad_norm": 17.714265823364258, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.6317, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004663363450888954, | |
| "grad_norm": 15.972993850708008, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.5037, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005829204313611192, | |
| "grad_norm": 17.83697509765625, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.7562, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006995045176333431, | |
| "grad_norm": 15.482553482055664, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.0961, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00816088603905567, | |
| "grad_norm": 9.93425464630127, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4779, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009326726901777908, | |
| "grad_norm": 6.917999267578125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8561, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010492567764500145, | |
| "grad_norm": 6.441965579986572, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5291, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011658408627222384, | |
| "grad_norm": 10.570073127746582, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7219, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012824249489944622, | |
| "grad_norm": 7.498240947723389, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5289, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013990090352666861, | |
| "grad_norm": 4.377902507781982, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.308, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0151559312153891, | |
| "grad_norm": 4.175413131713867, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3511, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01632177207811134, | |
| "grad_norm": 4.24492883682251, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.262, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017487612940833577, | |
| "grad_norm": 1.2066303491592407, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.1986, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018653453803555816, | |
| "grad_norm": 1.8215632438659668, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2076, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019819294666278055, | |
| "grad_norm": 3.175055503845215, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2152, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02098513552900029, | |
| "grad_norm": 0.8772231936454773, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1795, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02215097639172253, | |
| "grad_norm": 3.0992307662963867, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1667, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023316817254444767, | |
| "grad_norm": 2.158484697341919, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1375, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024482658117167006, | |
| "grad_norm": 2.368549108505249, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1403, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025648498979889245, | |
| "grad_norm": 1.2931737899780273, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1402, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.026814339842611484, | |
| "grad_norm": 1.9940847158432007, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1262, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.027980180705333722, | |
| "grad_norm": 1.068817377090454, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0905, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02914602156805596, | |
| "grad_norm": 1.0869516134262085, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1269, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02914602156805596, | |
| "eval_loss": 0.1435670405626297, | |
| "eval_runtime": 174.9516, | |
| "eval_samples_per_second": 33.032, | |
| "eval_steps_per_second": 4.133, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0303118624307782, | |
| "grad_norm": 2.517028331756592, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1762, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.031477703293500435, | |
| "grad_norm": 1.4719444513320923, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.1734, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03264354415622268, | |
| "grad_norm": 4.189019680023193, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1852, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03380938501894491, | |
| "grad_norm": 2.236452102661133, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1602, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.034975225881667155, | |
| "grad_norm": 1.3396327495574951, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1157, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03614106674438939, | |
| "grad_norm": 1.026810646057129, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1083, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03730690760711163, | |
| "grad_norm": 0.5179802775382996, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1017, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03847274846983387, | |
| "grad_norm": 1.053564429283142, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.12, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03963858933255611, | |
| "grad_norm": 0.9238091111183167, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1108, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.040804430195278345, | |
| "grad_norm": 0.655486524105072, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1086, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04197027105800058, | |
| "grad_norm": 1.3844945430755615, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1304, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04313611192072282, | |
| "grad_norm": 2.077029228210449, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1312, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04430195278344506, | |
| "grad_norm": 0.49116334319114685, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.114, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0454677936461673, | |
| "grad_norm": 1.8224717378616333, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1352, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.046633634508889535, | |
| "grad_norm": 0.638178288936615, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1262, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04779947537161178, | |
| "grad_norm": 0.6785788536071777, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1205, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04896531623433401, | |
| "grad_norm": 0.6223834753036499, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1145, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.050131157097056255, | |
| "grad_norm": 1.2081153392791748, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1274, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05129699795977849, | |
| "grad_norm": 1.6178852319717407, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1332, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05246283882250073, | |
| "grad_norm": 0.6872188448905945, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1384, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05362867968522297, | |
| "grad_norm": 0.9840008020401001, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1038, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0547945205479452, | |
| "grad_norm": 1.2670667171478271, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1206, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.055960361410667445, | |
| "grad_norm": 0.6150506734848022, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1007, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05712620227338968, | |
| "grad_norm": 0.7032421827316284, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1494, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05829204313611192, | |
| "grad_norm": 0.9980733394622803, | |
| "learning_rate": 0.0, | |
| "loss": 0.127, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05829204313611192, | |
| "eval_loss": 0.12280955910682678, | |
| "eval_runtime": 175.0073, | |
| "eval_samples_per_second": 33.021, | |
| "eval_steps_per_second": 4.131, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |