| { | |
| "best_metric": 2.2613911628723145, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6745362563237775, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013490725126475547, | |
| "grad_norm": 85.44503784179688, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6571, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013490725126475547, | |
| "eval_loss": 3.286269187927246, | |
| "eval_runtime": 33.0276, | |
| "eval_samples_per_second": 15.139, | |
| "eval_steps_per_second": 1.907, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026981450252951095, | |
| "grad_norm": 95.18113708496094, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9702, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04047217537942664, | |
| "grad_norm": 77.65520477294922, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.7021, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05396290050590219, | |
| "grad_norm": 135.69296264648438, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.7404, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06745362563237774, | |
| "grad_norm": 84.60151672363281, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.6488, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08094435075885328, | |
| "grad_norm": 80.55194091796875, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.6615, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09443507588532883, | |
| "grad_norm": 108.89022827148438, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.6358, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10792580101180438, | |
| "grad_norm": 79.09467315673828, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5546, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12141652613827993, | |
| "grad_norm": 87.56582641601562, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.7197, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13490725126475547, | |
| "grad_norm": 93.86714172363281, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.4651, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14839797639123103, | |
| "grad_norm": 41.895912170410156, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.5984, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16188870151770657, | |
| "grad_norm": 86.19235229492188, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.5576, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17537942664418213, | |
| "grad_norm": 76.61930847167969, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.6488, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18887015177065766, | |
| "grad_norm": 58.94124984741211, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.3962, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20236087689713322, | |
| "grad_norm": 61.75034713745117, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.4865, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.21585160202360876, | |
| "grad_norm": 69.10595703125, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.3925, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22934232715008432, | |
| "grad_norm": 58.51557159423828, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.5001, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24283305227655985, | |
| "grad_norm": 40.6702880859375, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.4163, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2563237774030354, | |
| "grad_norm": 50.67131042480469, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.2799, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.26981450252951095, | |
| "grad_norm": 54.50019836425781, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3563, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28330522765598654, | |
| "grad_norm": 35.64760208129883, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.2526, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.29679595278246207, | |
| "grad_norm": 54.67503356933594, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.4552, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3102866779089376, | |
| "grad_norm": 79.10367584228516, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.4652, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32377740303541314, | |
| "grad_norm": 67.79601287841797, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.2297, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3372681281618887, | |
| "grad_norm": 49.42949295043945, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.3913, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3372681281618887, | |
| "eval_loss": 2.9423482418060303, | |
| "eval_runtime": 32.9894, | |
| "eval_samples_per_second": 15.156, | |
| "eval_steps_per_second": 1.91, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35075885328836426, | |
| "grad_norm": 327.58599853515625, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0293, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3642495784148398, | |
| "grad_norm": 362.6495056152344, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.3553, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3777403035413153, | |
| "grad_norm": 316.2618103027344, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.9598, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3912310286677909, | |
| "grad_norm": 237.7189178466797, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.7075, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.40472175379426645, | |
| "grad_norm": 114.92796325683594, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.4807, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.418212478920742, | |
| "grad_norm": 48.19389724731445, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.4164, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4317032040472175, | |
| "grad_norm": 71.13121032714844, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.3391, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4451939291736931, | |
| "grad_norm": 78.83213806152344, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.2943, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.45868465430016864, | |
| "grad_norm": 71.80233001708984, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3639, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.47217537942664417, | |
| "grad_norm": 74.17680358886719, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.4181, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4856661045531197, | |
| "grad_norm": 69.19786071777344, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.2874, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4991568296795953, | |
| "grad_norm": 66.0870132446289, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.34, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5126475548060708, | |
| "grad_norm": 43.74034881591797, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3367, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5261382799325464, | |
| "grad_norm": 63.72829055786133, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.2909, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5396290050590219, | |
| "grad_norm": 79.226318359375, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.2279, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5531197301854974, | |
| "grad_norm": 74.6691665649414, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.232, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5666104553119731, | |
| "grad_norm": 71.57418823242188, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.1768, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5801011804384486, | |
| "grad_norm": 63.76176452636719, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.3299, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5935919055649241, | |
| "grad_norm": 51.7007942199707, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.2503, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6070826306913997, | |
| "grad_norm": 39.83833694458008, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.3118, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6205733558178752, | |
| "grad_norm": 38.03684616088867, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.3047, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6340640809443507, | |
| "grad_norm": 34.288970947265625, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.2329, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6475548060708263, | |
| "grad_norm": 31.958253860473633, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.2962, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6610455311973018, | |
| "grad_norm": 39.0740966796875, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.3091, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6745362563237775, | |
| "grad_norm": 87.91134643554688, | |
| "learning_rate": 0.0, | |
| "loss": 2.4479, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6745362563237775, | |
| "eval_loss": 2.2613911628723145, | |
| "eval_runtime": 33.0075, | |
| "eval_samples_per_second": 15.148, | |
| "eval_steps_per_second": 1.909, | |
| "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": 5.658027780734976e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |