{ "best_metric": 0.2157745063304901, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.042886244237160934, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0008577248847432186, "grad_norm": 11.464567184448242, "learning_rate": 5e-05, "loss": 13.7551, "step": 1 }, { "epoch": 0.0008577248847432186, "eval_loss": 13.996685981750488, "eval_runtime": 110.3419, "eval_samples_per_second": 71.188, "eval_steps_per_second": 8.9, "step": 1 }, { "epoch": 0.0017154497694864372, "grad_norm": 11.63041877746582, "learning_rate": 0.0001, "loss": 13.8213, "step": 2 }, { "epoch": 0.002573174654229656, "grad_norm": 11.084935188293457, "learning_rate": 9.989294616193017e-05, "loss": 13.2895, "step": 3 }, { "epoch": 0.0034308995389728744, "grad_norm": 12.581958770751953, "learning_rate": 9.957224306869053e-05, "loss": 12.625, "step": 4 }, { "epoch": 0.004288624423716093, "grad_norm": 13.262085914611816, "learning_rate": 9.903926402016153e-05, "loss": 11.7361, "step": 5 }, { "epoch": 0.005146349308459312, "grad_norm": 15.954154014587402, "learning_rate": 9.829629131445342e-05, "loss": 10.0106, "step": 6 }, { "epoch": 0.00600407419320253, "grad_norm": 14.970663070678711, "learning_rate": 9.73465064747553e-05, "loss": 8.6617, "step": 7 }, { "epoch": 0.006861799077945749, "grad_norm": 9.681559562683105, "learning_rate": 9.619397662556435e-05, "loss": 7.4063, "step": 8 }, { "epoch": 0.0077195239626889674, "grad_norm": 7.998727321624756, "learning_rate": 9.484363707663442e-05, "loss": 6.5682, "step": 9 }, { "epoch": 0.008577248847432186, "grad_norm": 8.295345306396484, "learning_rate": 9.330127018922194e-05, "loss": 6.2947, "step": 10 }, { "epoch": 0.009434973732175405, "grad_norm": 9.30639362335205, "learning_rate": 9.157348061512727e-05, "loss": 5.7786, "step": 11 }, { "epoch": 0.010292698616918623, "grad_norm": 8.417024612426758, "learning_rate": 8.966766701456177e-05, "loss": 5.0726, "step": 12 }, { "epoch": 0.011150423501661842, "grad_norm": 9.081653594970703, "learning_rate": 8.759199037394887e-05, "loss": 4.5328, "step": 13 }, { "epoch": 0.01200814838640506, "grad_norm": 10.386723518371582, "learning_rate": 8.535533905932738e-05, "loss": 4.1116, "step": 14 }, { "epoch": 0.012865873271148279, "grad_norm": 10.071829795837402, "learning_rate": 8.296729075500344e-05, "loss": 3.2801, "step": 15 }, { "epoch": 0.013723598155891498, "grad_norm": 9.80232048034668, "learning_rate": 8.043807145043604e-05, "loss": 2.298, "step": 16 }, { "epoch": 0.014581323040634716, "grad_norm": 9.103277206420898, "learning_rate": 7.777851165098012e-05, "loss": 1.6048, "step": 17 }, { "epoch": 0.015439047925377935, "grad_norm": 11.06741714477539, "learning_rate": 7.500000000000001e-05, "loss": 1.4564, "step": 18 }, { "epoch": 0.016296772810121155, "grad_norm": 18.316673278808594, "learning_rate": 7.211443451095007e-05, "loss": 1.6177, "step": 19 }, { "epoch": 0.017154497694864372, "grad_norm": 22.55585289001465, "learning_rate": 6.91341716182545e-05, "loss": 2.0887, "step": 20 }, { "epoch": 0.018012222579607592, "grad_norm": 20.116098403930664, "learning_rate": 6.607197326515808e-05, "loss": 1.5927, "step": 21 }, { "epoch": 0.01886994746435081, "grad_norm": 15.487234115600586, "learning_rate": 6.294095225512603e-05, "loss": 1.2727, "step": 22 }, { "epoch": 0.01972767234909403, "grad_norm": 8.50413990020752, "learning_rate": 5.9754516100806423e-05, "loss": 0.8617, "step": 23 }, { "epoch": 0.020585397233837247, "grad_norm": 3.4919447898864746, "learning_rate": 5.6526309611002594e-05, "loss": 0.512, "step": 24 }, { "epoch": 0.021443122118580467, "grad_norm": 2.9044764041900635, "learning_rate": 5.327015646150716e-05, "loss": 0.4989, "step": 25 }, { "epoch": 0.021443122118580467, "eval_loss": 0.3860068619251251, "eval_runtime": 110.7856, "eval_samples_per_second": 70.903, "eval_steps_per_second": 8.864, "step": 25 }, { "epoch": 0.022300847003323684, "grad_norm": 2.8950188159942627, "learning_rate": 5e-05, "loss": 0.73, "step": 26 }, { "epoch": 0.023158571888066904, "grad_norm": 3.2829320430755615, "learning_rate": 4.6729843538492847e-05, "loss": 0.5514, "step": 27 }, { "epoch": 0.02401629677281012, "grad_norm": 2.5224287509918213, "learning_rate": 4.347369038899744e-05, "loss": 0.3176, "step": 28 }, { "epoch": 0.02487402165755334, "grad_norm": 4.160872936248779, "learning_rate": 4.0245483899193595e-05, "loss": 0.2866, "step": 29 }, { "epoch": 0.025731746542296558, "grad_norm": 2.872546672821045, "learning_rate": 3.705904774487396e-05, "loss": 0.3233, "step": 30 }, { "epoch": 0.02658947142703978, "grad_norm": 2.607795476913452, "learning_rate": 3.392802673484193e-05, "loss": 0.2424, "step": 31 }, { "epoch": 0.027447196311782995, "grad_norm": 1.1529837846755981, "learning_rate": 3.086582838174551e-05, "loss": 0.2562, "step": 32 }, { "epoch": 0.028304921196526216, "grad_norm": 1.0159945487976074, "learning_rate": 2.7885565489049946e-05, "loss": 0.1601, "step": 33 }, { "epoch": 0.029162646081269433, "grad_norm": 1.7587469816207886, "learning_rate": 2.500000000000001e-05, "loss": 0.2515, "step": 34 }, { "epoch": 0.030020370966012653, "grad_norm": 3.4404122829437256, "learning_rate": 2.2221488349019903e-05, "loss": 0.3353, "step": 35 }, { "epoch": 0.03087809585075587, "grad_norm": 2.699526786804199, "learning_rate": 1.9561928549563968e-05, "loss": 0.306, "step": 36 }, { "epoch": 0.03173582073549909, "grad_norm": 2.4039580821990967, "learning_rate": 1.703270924499656e-05, "loss": 0.3528, "step": 37 }, { "epoch": 0.03259354562024231, "grad_norm": 1.31723153591156, "learning_rate": 1.4644660940672627e-05, "loss": 0.2554, "step": 38 }, { "epoch": 0.033451270504985524, "grad_norm": 2.59911847114563, "learning_rate": 1.2408009626051137e-05, "loss": 0.3681, "step": 39 }, { "epoch": 0.034308995389728744, "grad_norm": 1.1396697759628296, "learning_rate": 1.0332332985438248e-05, "loss": 0.1878, "step": 40 }, { "epoch": 0.035166720274471965, "grad_norm": 1.5017955303192139, "learning_rate": 8.426519384872733e-06, "loss": 0.231, "step": 41 }, { "epoch": 0.036024445159215185, "grad_norm": 1.122409462928772, "learning_rate": 6.698729810778065e-06, "loss": 0.2008, "step": 42 }, { "epoch": 0.0368821700439584, "grad_norm": 1.102306604385376, "learning_rate": 5.156362923365588e-06, "loss": 0.1537, "step": 43 }, { "epoch": 0.03773989492870162, "grad_norm": 0.766008734703064, "learning_rate": 3.8060233744356633e-06, "loss": 0.1989, "step": 44 }, { "epoch": 0.03859761981344484, "grad_norm": 0.9516524076461792, "learning_rate": 2.653493525244721e-06, "loss": 0.1724, "step": 45 }, { "epoch": 0.03945534469818806, "grad_norm": 1.9921557903289795, "learning_rate": 1.70370868554659e-06, "loss": 0.1597, "step": 46 }, { "epoch": 0.04031306958293127, "grad_norm": 1.784018635749817, "learning_rate": 9.607359798384785e-07, "loss": 0.2322, "step": 47 }, { "epoch": 0.04117079446767449, "grad_norm": 3.5011606216430664, "learning_rate": 4.277569313094809e-07, "loss": 0.256, "step": 48 }, { "epoch": 0.04202851935241771, "grad_norm": 1.876481533050537, "learning_rate": 1.0705383806982606e-07, "loss": 0.224, "step": 49 }, { "epoch": 0.042886244237160934, "grad_norm": 2.9017508029937744, "learning_rate": 0.0, "loss": 0.2913, "step": 50 }, { "epoch": 0.042886244237160934, "eval_loss": 0.2157745063304901, "eval_runtime": 111.122, "eval_samples_per_second": 70.688, "eval_steps_per_second": 8.837, "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": 1.2634971083846451e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }