| { | |
| "best_metric": 0.9352908730506897, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4550625711035267, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009101251422070534, | |
| "grad_norm": 4.816208839416504, | |
| "learning_rate": 5e-05, | |
| "loss": 6.3161, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009101251422070534, | |
| "eval_loss": 8.30978775024414, | |
| "eval_runtime": 45.8486, | |
| "eval_samples_per_second": 16.14, | |
| "eval_steps_per_second": 2.028, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01820250284414107, | |
| "grad_norm": 4.660228252410889, | |
| "learning_rate": 0.0001, | |
| "loss": 6.8743, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.027303754266211604, | |
| "grad_norm": 4.933719635009766, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.1543, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03640500568828214, | |
| "grad_norm": 5.35949182510376, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.2262, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04550625711035267, | |
| "grad_norm": 5.189940452575684, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.1873, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05460750853242321, | |
| "grad_norm": 5.019341468811035, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.4138, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06370875995449374, | |
| "grad_norm": 4.33259916305542, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.6671, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07281001137656427, | |
| "grad_norm": 3.7665863037109375, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.1342, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08191126279863481, | |
| "grad_norm": 3.4121315479278564, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.8445, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09101251422070535, | |
| "grad_norm": 3.057300090789795, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.409, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10011376564277588, | |
| "grad_norm": 3.3132073879241943, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.3277, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10921501706484642, | |
| "grad_norm": 3.2704758644104004, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.4697, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11831626848691695, | |
| "grad_norm": 4.299544334411621, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.941, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12741751990898748, | |
| "grad_norm": 3.567735433578491, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5576, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13651877133105803, | |
| "grad_norm": 2.713759422302246, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5628, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14562002275312855, | |
| "grad_norm": 2.3682448863983154, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.3022, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1547212741751991, | |
| "grad_norm": 2.226658821105957, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.281, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16382252559726962, | |
| "grad_norm": 2.2093777656555176, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.2902, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17292377701934017, | |
| "grad_norm": 2.205993890762329, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.174, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1820250284414107, | |
| "grad_norm": 2.5380332469940186, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2994, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19112627986348124, | |
| "grad_norm": 2.6909568309783936, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3494, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.20022753128555176, | |
| "grad_norm": 2.351163625717163, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.1553, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20932878270762229, | |
| "grad_norm": 2.3341007232666016, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.2526, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21843003412969283, | |
| "grad_norm": 3.1375274658203125, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.2524, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22753128555176336, | |
| "grad_norm": 3.1662492752075195, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.2828, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22753128555176336, | |
| "eval_loss": 1.06704580783844, | |
| "eval_runtime": 45.8087, | |
| "eval_samples_per_second": 16.154, | |
| "eval_steps_per_second": 2.03, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2366325369738339, | |
| "grad_norm": 4.486268997192383, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8433, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24573378839590443, | |
| "grad_norm": 3.177172899246216, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.94, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.25483503981797495, | |
| "grad_norm": 2.8514692783355713, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9403, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.26393629124004553, | |
| "grad_norm": 2.081775188446045, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9287, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.27303754266211605, | |
| "grad_norm": 1.5277687311172485, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8997, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2821387940841866, | |
| "grad_norm": 1.7213866710662842, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.958, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2912400455062571, | |
| "grad_norm": 1.9582645893096924, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0021, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3003412969283277, | |
| "grad_norm": 1.9742724895477295, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0717, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3094425483503982, | |
| "grad_norm": 1.8114529848098755, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.0286, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3185437997724687, | |
| "grad_norm": 2.001466989517212, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0724, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32764505119453924, | |
| "grad_norm": 2.1843643188476562, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1028, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.33674630261660976, | |
| "grad_norm": 2.835616111755371, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1713, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.34584755403868034, | |
| "grad_norm": 2.740234375, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8349, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.35494880546075086, | |
| "grad_norm": 2.345097780227661, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.73, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3640500568828214, | |
| "grad_norm": 2.214395761489868, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7998, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3731513083048919, | |
| "grad_norm": 1.7848715782165527, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8458, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3822525597269625, | |
| "grad_norm": 1.850387692451477, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9189, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.391353811149033, | |
| "grad_norm": 1.9545140266418457, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8823, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4004550625711035, | |
| "grad_norm": 1.9864474534988403, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9604, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.40955631399317405, | |
| "grad_norm": 1.8967782258987427, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9466, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.41865756541524457, | |
| "grad_norm": 1.9333577156066895, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9746, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.42775881683731515, | |
| "grad_norm": 1.8357700109481812, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.027, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.43686006825938567, | |
| "grad_norm": 2.4668965339660645, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0493, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4459613196814562, | |
| "grad_norm": 2.4607532024383545, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0706, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4550625711035267, | |
| "grad_norm": 2.967007875442505, | |
| "learning_rate": 0.0, | |
| "loss": 1.1603, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4550625711035267, | |
| "eval_loss": 0.9352908730506897, | |
| "eval_runtime": 45.835, | |
| "eval_samples_per_second": 16.145, | |
| "eval_steps_per_second": 2.029, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |