| { | |
| "best_metric": 11.935591697692871, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.45454545454545453, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00909090909090909, | |
| "grad_norm": 0.014407745562493801, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9324, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00909090909090909, | |
| "eval_loss": 11.940053939819336, | |
| "eval_runtime": 1.5718, | |
| "eval_samples_per_second": 471.441, | |
| "eval_steps_per_second": 59.169, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01818181818181818, | |
| "grad_norm": 0.020456792786717415, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9359, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02727272727272727, | |
| "grad_norm": 0.02752542309463024, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9359, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03636363636363636, | |
| "grad_norm": 0.030046707019209862, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9355, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 0.03253328800201416, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9362, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05454545454545454, | |
| "grad_norm": 0.03853551298379898, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.9368, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06363636363636363, | |
| "grad_norm": 0.047178175300359726, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9367, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 0.05311514064669609, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9372, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08181818181818182, | |
| "grad_norm": 0.05621656775474548, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9387, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 0.08180534094572067, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9402, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.10444722324609756, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9424, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10909090909090909, | |
| "grad_norm": 0.1504172831773758, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9463, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11818181818181818, | |
| "grad_norm": 0.027267219498753548, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9336, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12727272727272726, | |
| "grad_norm": 0.021916711702942848, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9336, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "grad_norm": 0.025460882112383842, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9342, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 0.03715614974498749, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9351, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15454545454545454, | |
| "grad_norm": 0.04742095246911049, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9355, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16363636363636364, | |
| "grad_norm": 0.04686274006962776, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9349, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17272727272727273, | |
| "grad_norm": 0.05396494269371033, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.936, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.06768876314163208, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9369, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19090909090909092, | |
| "grad_norm": 0.07629425823688507, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9363, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.09198444336652756, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9379, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20909090909090908, | |
| "grad_norm": 0.12001596391201019, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9388, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21818181818181817, | |
| "grad_norm": 0.16391249001026154, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9413, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 0.23358383774757385, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9449, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "eval_loss": 11.936851501464844, | |
| "eval_runtime": 1.576, | |
| "eval_samples_per_second": 470.181, | |
| "eval_steps_per_second": 59.011, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23636363636363636, | |
| "grad_norm": 0.02547423541545868, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9328, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24545454545454545, | |
| "grad_norm": 0.032784029841423035, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.9333, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2545454545454545, | |
| "grad_norm": 0.03990747034549713, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9346, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2636363636363636, | |
| "grad_norm": 0.04943360760807991, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9343, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 0.06197665259242058, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9335, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2818181818181818, | |
| "grad_norm": 0.07167532294988632, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9344, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 0.07756704837083817, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9335, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.09547356516122818, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.9343, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3090909090909091, | |
| "grad_norm": 0.1049596518278122, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9362, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3181818181818182, | |
| "grad_norm": 0.12272288650274277, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.9367, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32727272727272727, | |
| "grad_norm": 0.1635354906320572, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.9389, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.33636363636363636, | |
| "grad_norm": 0.2163349837064743, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.9403, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.34545454545454546, | |
| "grad_norm": 0.04375721141695976, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9328, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.35454545454545455, | |
| "grad_norm": 0.03665831312537193, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.9324, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.050286322832107544, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.9341, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.37272727272727274, | |
| "grad_norm": 0.04947338625788689, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.9333, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.38181818181818183, | |
| "grad_norm": 0.06359462440013885, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9332, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.39090909090909093, | |
| "grad_norm": 0.07127209007740021, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9336, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.07325005531311035, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9339, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4090909090909091, | |
| "grad_norm": 0.09760692715644836, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9347, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.41818181818181815, | |
| "grad_norm": 0.10781180113554001, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.9351, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.42727272727272725, | |
| "grad_norm": 0.1281491219997406, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.9344, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 0.14875389635562897, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.9376, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.44545454545454544, | |
| "grad_norm": 0.20203977823257446, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.9389, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.2914524972438812, | |
| "learning_rate": 0.0, | |
| "loss": 11.9421, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "eval_loss": 11.935591697692871, | |
| "eval_runtime": 1.5904, | |
| "eval_samples_per_second": 465.919, | |
| "eval_steps_per_second": 58.476, | |
| "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": 1046077833216.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |