| { | |
| "best_metric": 10.354231834411621, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05461123626186088, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010922247252372176, | |
| "grad_norm": 2.2223293781280518, | |
| "learning_rate": 5e-05, | |
| "loss": 166.0541, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010922247252372176, | |
| "eval_loss": 10.377656936645508, | |
| "eval_runtime": 7.0096, | |
| "eval_samples_per_second": 879.936, | |
| "eval_steps_per_second": 109.992, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021844494504744353, | |
| "grad_norm": 2.143641948699951, | |
| "learning_rate": 0.0001, | |
| "loss": 166.0468, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0032766741757116525, | |
| "grad_norm": 2.7565910816192627, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 166.0687, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004368898900948871, | |
| "grad_norm": 3.15145206451416, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 166.0454, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005461123626186087, | |
| "grad_norm": 3.5360095500946045, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 166.019, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006553348351423305, | |
| "grad_norm": 3.5316290855407715, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 165.9768, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007645573076660523, | |
| "grad_norm": 3.707836627960205, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 166.0207, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008737797801897741, | |
| "grad_norm": 3.654756546020508, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 165.9468, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009830022527134958, | |
| "grad_norm": 3.74013614654541, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 165.9326, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010922247252372175, | |
| "grad_norm": 3.661339282989502, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 165.91, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012014471977609393, | |
| "grad_norm": 2.986882209777832, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 165.9262, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01310669670284661, | |
| "grad_norm": 3.208163022994995, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 165.883, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014198921428083829, | |
| "grad_norm": 3.428823232650757, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 165.859, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015291146153321045, | |
| "grad_norm": 2.624152421951294, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 165.9547, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016383370878558262, | |
| "grad_norm": 2.713590383529663, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 165.9609, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017475595603795482, | |
| "grad_norm": 3.764500856399536, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 165.888, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0185678203290327, | |
| "grad_norm": 3.648594617843628, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 165.8834, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.019660045054269916, | |
| "grad_norm": 4.561197757720947, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 165.8302, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.020752269779507133, | |
| "grad_norm": 4.624699115753174, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 165.8181, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02184449450474435, | |
| "grad_norm": 4.839552402496338, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 165.8065, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02293671922998157, | |
| "grad_norm": 4.766144752502441, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 165.7698, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.024028943955218787, | |
| "grad_norm": 4.585628509521484, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 165.7825, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025121168680456003, | |
| "grad_norm": 4.522224426269531, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 165.7515, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02621339340569322, | |
| "grad_norm": 3.736583709716797, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 165.7552, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02730561813093044, | |
| "grad_norm": 6.060925006866455, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 165.8265, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02730561813093044, | |
| "eval_loss": 10.360455513000488, | |
| "eval_runtime": 7.7588, | |
| "eval_samples_per_second": 794.969, | |
| "eval_steps_per_second": 99.371, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.028397842856167657, | |
| "grad_norm": 3.1417901515960693, | |
| "learning_rate": 5e-05, | |
| "loss": 165.8593, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.029490067581404874, | |
| "grad_norm": 3.3648159503936768, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 165.8664, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03058229230664209, | |
| "grad_norm": 4.148431301116943, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 165.8027, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03167451703187931, | |
| "grad_norm": 4.830881595611572, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 165.7497, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.032766741757116524, | |
| "grad_norm": 5.528181552886963, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 165.7045, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.033858966482353745, | |
| "grad_norm": 5.51494836807251, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 165.7317, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.034951191207590965, | |
| "grad_norm": 5.884454727172852, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 165.6762, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03604341593282818, | |
| "grad_norm": 5.676090717315674, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 165.681, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0371356406580654, | |
| "grad_norm": 5.77196741104126, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 165.6176, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03822786538330261, | |
| "grad_norm": 5.53093957901001, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 165.6452, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03932009010853983, | |
| "grad_norm": 4.67064094543457, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 165.7062, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04041231483377705, | |
| "grad_norm": 4.531012058258057, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 165.7318, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.041504539559014265, | |
| "grad_norm": 4.488137722015381, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 165.7726, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.042596764284251486, | |
| "grad_norm": 3.4259696006774902, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 165.8445, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0436889890094887, | |
| "grad_norm": 3.8617091178894043, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 165.7874, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04478121373472592, | |
| "grad_norm": 4.9109721183776855, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 165.721, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04587343845996314, | |
| "grad_norm": 5.6263017654418945, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 165.6487, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04696566318520035, | |
| "grad_norm": 5.893503189086914, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 165.6439, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04805788791043757, | |
| "grad_norm": 6.037866592407227, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 165.6367, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04915011263567479, | |
| "grad_norm": 6.400647163391113, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 165.6083, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05024233736091201, | |
| "grad_norm": 6.0521392822265625, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 165.5833, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05133456208614923, | |
| "grad_norm": 6.447074890136719, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 165.5869, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05242678681138644, | |
| "grad_norm": 5.763982772827148, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 165.591, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05351901153662366, | |
| "grad_norm": 4.520351886749268, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 165.7174, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05461123626186088, | |
| "grad_norm": 5.273721694946289, | |
| "learning_rate": 0.0, | |
| "loss": 165.7188, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05461123626186088, | |
| "eval_loss": 10.354231834411621, | |
| "eval_runtime": 7.1717, | |
| "eval_samples_per_second": 860.043, | |
| "eval_steps_per_second": 107.505, | |
| "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": 83859071827968.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |