| { | |
| "best_metric": 4.039027214050293, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.9197080291970803, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.058394160583941604, | |
| "grad_norm": 1.2822612524032593, | |
| "learning_rate": 5e-05, | |
| "loss": 4.1834, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.058394160583941604, | |
| "eval_loss": 5.098187446594238, | |
| "eval_runtime": 0.3396, | |
| "eval_samples_per_second": 341.606, | |
| "eval_steps_per_second": 44.173, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11678832116788321, | |
| "grad_norm": 2.569211006164551, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8724, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.17518248175182483, | |
| "grad_norm": 2.091531276702881, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.2191, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.23357664233576642, | |
| "grad_norm": 1.7123160362243652, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.3955, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "grad_norm": 0.8882278203964233, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.055, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.35036496350364965, | |
| "grad_norm": 0.8794437646865845, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.5183, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.40875912408759124, | |
| "grad_norm": 1.4536943435668945, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.8049, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.46715328467153283, | |
| "grad_norm": 2.662942886352539, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.0266, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5255474452554745, | |
| "grad_norm": 0.9087815880775452, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.9506, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.583941605839416, | |
| "grad_norm": 0.7557864189147949, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.2279, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6423357664233577, | |
| "grad_norm": 1.1979687213897705, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.4896, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7007299270072993, | |
| "grad_norm": 1.4247801303863525, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.7441, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7591240875912408, | |
| "grad_norm": 0.7902650833129883, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 4.0107, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8175182481751825, | |
| "grad_norm": 0.7168551087379456, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.0785, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8759124087591241, | |
| "grad_norm": 0.7550625801086426, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 4.272, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9343065693430657, | |
| "grad_norm": 1.0377146005630493, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.5471, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9927007299270073, | |
| "grad_norm": 1.4056518077850342, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 4.8509, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.051094890510949, | |
| "grad_norm": 1.4291749000549316, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 7.0564, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1094890510948905, | |
| "grad_norm": 0.7004761099815369, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.0164, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.167883211678832, | |
| "grad_norm": 0.9470470547676086, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.2587, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2262773722627738, | |
| "grad_norm": 1.1709222793579102, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.557, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2846715328467153, | |
| "grad_norm": 0.6594967246055603, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.7556, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.343065693430657, | |
| "grad_norm": 0.6004905700683594, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.9757, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.4014598540145986, | |
| "grad_norm": 0.865336537361145, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 4.224, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4598540145985401, | |
| "grad_norm": 1.046862006187439, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 4.2923, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4598540145985401, | |
| "eval_loss": 4.168821811676025, | |
| "eval_runtime": 0.3358, | |
| "eval_samples_per_second": 345.484, | |
| "eval_steps_per_second": 44.675, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5182481751824817, | |
| "grad_norm": 0.8879239559173584, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6184, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5766423357664232, | |
| "grad_norm": 0.7602900862693787, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 4.2293, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.635036496350365, | |
| "grad_norm": 0.7398382425308228, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 4.083, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6934306569343067, | |
| "grad_norm": 0.7375873327255249, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 4.1524, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7518248175182483, | |
| "grad_norm": 0.5078723430633545, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.9595, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.8102189781021898, | |
| "grad_norm": 0.9409177303314209, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 4.5501, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8686131386861313, | |
| "grad_norm": 0.6193199157714844, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.9367, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.9270072992700729, | |
| "grad_norm": 0.6904658079147339, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 4.1563, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9854014598540146, | |
| "grad_norm": 1.267682433128357, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 4.6498, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0437956204379564, | |
| "grad_norm": 1.2440922260284424, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 6.9059, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.102189781021898, | |
| "grad_norm": 0.7068952322006226, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.7204, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1605839416058394, | |
| "grad_norm": 0.7181689143180847, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 4.1171, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.218978102189781, | |
| "grad_norm": 1.070713758468628, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.3304, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2773722627737225, | |
| "grad_norm": 0.5744719505310059, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.6591, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.335766423357664, | |
| "grad_norm": 0.6503571271896362, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.8797, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.394160583941606, | |
| "grad_norm": 0.7630330920219421, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.9595, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4525547445255476, | |
| "grad_norm": 0.753737211227417, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 4.1945, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.510948905109489, | |
| "grad_norm": 0.6379414796829224, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.2557, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5693430656934306, | |
| "grad_norm": 0.7391951084136963, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.2283, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.627737226277372, | |
| "grad_norm": 0.5288726687431335, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.8803, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.686131386861314, | |
| "grad_norm": 0.7749550938606262, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 4.0824, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.7445255474452557, | |
| "grad_norm": 0.4466674029827118, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.6886, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.802919708029197, | |
| "grad_norm": 1.1186093091964722, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 5.789, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8613138686131387, | |
| "grad_norm": 0.5663947463035583, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.8237, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.9197080291970803, | |
| "grad_norm": 0.6125584244728088, | |
| "learning_rate": 0.0, | |
| "loss": 4.0685, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.9197080291970803, | |
| "eval_loss": 4.039027214050293, | |
| "eval_runtime": 0.3355, | |
| "eval_samples_per_second": 345.792, | |
| "eval_steps_per_second": 44.715, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1.13737243557888e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |