| { | |
| "best_metric": 0.9063095450401306, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7168458781362007, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014336917562724014, | |
| "grad_norm": 0.6213638782501221, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0649, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014336917562724014, | |
| "eval_loss": 1.3422572612762451, | |
| "eval_runtime": 5.6069, | |
| "eval_samples_per_second": 83.826, | |
| "eval_steps_per_second": 10.523, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02867383512544803, | |
| "grad_norm": 0.649164080619812, | |
| "learning_rate": 0.0001, | |
| "loss": 1.095, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.043010752688172046, | |
| "grad_norm": 0.5671748518943787, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.9873, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05734767025089606, | |
| "grad_norm": 0.4552786946296692, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.0297, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07168458781362007, | |
| "grad_norm": 0.4016531705856323, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9408, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08602150537634409, | |
| "grad_norm": 0.4510401487350464, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9504, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1003584229390681, | |
| "grad_norm": 0.4686371088027954, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.9787, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11469534050179211, | |
| "grad_norm": 0.5549091696739197, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9985, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 0.5296815633773804, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.0088, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14336917562724014, | |
| "grad_norm": 0.5552384853363037, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1156, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15770609318996415, | |
| "grad_norm": 0.5902155637741089, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.2264, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17204301075268819, | |
| "grad_norm": 0.8949041366577148, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3434, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1863799283154122, | |
| "grad_norm": 0.6701123714447021, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0776, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2007168458781362, | |
| "grad_norm": 0.5380650758743286, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.918, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21505376344086022, | |
| "grad_norm": 0.44414275884628296, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.8055, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22939068100358423, | |
| "grad_norm": 0.32161274552345276, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8237, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24372759856630824, | |
| "grad_norm": 0.2952149212360382, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.8208, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 0.2965078353881836, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8949, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2724014336917563, | |
| "grad_norm": 0.3145495057106018, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8765, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2867383512544803, | |
| "grad_norm": 0.30555495619773865, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3010752688172043, | |
| "grad_norm": 0.3113645017147064, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9633, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3154121863799283, | |
| "grad_norm": 0.3889707326889038, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.9765, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.32974910394265233, | |
| "grad_norm": 0.4638270437717438, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.0945, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.34408602150537637, | |
| "grad_norm": 0.49984094500541687, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0843, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.35842293906810035, | |
| "grad_norm": 0.8894054889678955, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1579, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35842293906810035, | |
| "eval_loss": 0.9273486137390137, | |
| "eval_runtime": 5.6191, | |
| "eval_samples_per_second": 83.643, | |
| "eval_steps_per_second": 10.5, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3727598566308244, | |
| "grad_norm": 0.30773016810417175, | |
| "learning_rate": 5e-05, | |
| "loss": 0.956, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 0.32094433903694153, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.8451, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4014336917562724, | |
| "grad_norm": 0.31829121708869934, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.8853, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4157706093189964, | |
| "grad_norm": 0.2644154131412506, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.8618, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 0.25124552845954895, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.859, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.2580159902572632, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.8108, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.45878136200716846, | |
| "grad_norm": 0.2689642608165741, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8594, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4731182795698925, | |
| "grad_norm": 0.30206048488616943, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8952, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4874551971326165, | |
| "grad_norm": 0.339311420917511, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9332, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5017921146953405, | |
| "grad_norm": 0.4023721218109131, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0003, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 0.5078405737876892, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0957, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5304659498207885, | |
| "grad_norm": 0.5228250622749329, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0414, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5448028673835126, | |
| "grad_norm": 0.29582732915878296, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9022, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5591397849462365, | |
| "grad_norm": 0.22622767090797424, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8707, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5734767025089605, | |
| "grad_norm": 0.21357566118240356, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.8208, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5878136200716846, | |
| "grad_norm": 0.21832652390003204, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8524, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6021505376344086, | |
| "grad_norm": 0.21806098520755768, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.8115, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6164874551971327, | |
| "grad_norm": 0.22838038206100464, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8503, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6308243727598566, | |
| "grad_norm": 0.24952520430088043, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8594, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 0.2428099364042282, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.8317, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6594982078853047, | |
| "grad_norm": 0.2742410898208618, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9024, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6738351254480287, | |
| "grad_norm": 0.29396843910217285, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.9405, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6881720430107527, | |
| "grad_norm": 0.34846463799476624, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0345, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7025089605734767, | |
| "grad_norm": 0.4186893701553345, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0665, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7168458781362007, | |
| "grad_norm": 0.6892691850662231, | |
| "learning_rate": 0.0, | |
| "loss": 1.2407, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7168458781362007, | |
| "eval_loss": 0.9063095450401306, | |
| "eval_runtime": 5.6162, | |
| "eval_samples_per_second": 83.686, | |
| "eval_steps_per_second": 10.505, | |
| "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": 1.067482872849367e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |