| { | |
| "best_metric": 1.400192141532898, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.018281535648994516, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036563071297989033, | |
| "grad_norm": 0.263685405254364, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7146, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00036563071297989033, | |
| "eval_loss": 1.621423363685608, | |
| "eval_runtime": 68.7234, | |
| "eval_samples_per_second": 67.037, | |
| "eval_steps_per_second": 8.381, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007312614259597807, | |
| "grad_norm": 0.23099811375141144, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5916, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010968921389396709, | |
| "grad_norm": 0.2454378455877304, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5647, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014625228519195613, | |
| "grad_norm": 0.23810383677482605, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5945, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018281535648994515, | |
| "grad_norm": 0.23558178544044495, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5168, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0021937842778793418, | |
| "grad_norm": 0.22106045484542847, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.6018, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002559414990859232, | |
| "grad_norm": 0.1976412981748581, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.5256, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0029250457038391227, | |
| "grad_norm": 0.18290100991725922, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.5062, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0032906764168190127, | |
| "grad_norm": 0.18400928378105164, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.487, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003656307129798903, | |
| "grad_norm": 0.1838669329881668, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.4553, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0040219378427787935, | |
| "grad_norm": 0.19167158007621765, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.4515, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0043875685557586835, | |
| "grad_norm": 0.18224981427192688, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.4875, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004753199268738574, | |
| "grad_norm": 0.17719820141792297, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.4564, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.005118829981718464, | |
| "grad_norm": 0.17880447208881378, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.4321, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005484460694698354, | |
| "grad_norm": 0.16925093531608582, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.3777, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005850091407678245, | |
| "grad_norm": 0.16614092886447906, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 1.4482, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006215722120658135, | |
| "grad_norm": 0.1792985200881958, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.3997, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006581352833638025, | |
| "grad_norm": 0.16103695333003998, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.4049, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006946983546617916, | |
| "grad_norm": 0.15694041550159454, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.3884, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007312614259597806, | |
| "grad_norm": 0.1585288643836975, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3791, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007678244972577696, | |
| "grad_norm": 0.15279190242290497, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.414, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008043875685557587, | |
| "grad_norm": 0.1613546460866928, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 1.3907, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008409506398537478, | |
| "grad_norm": 0.1541416198015213, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.3546, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008775137111517367, | |
| "grad_norm": 0.16708770394325256, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 1.449, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009140767824497258, | |
| "grad_norm": 0.1675138622522354, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.5012, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009140767824497258, | |
| "eval_loss": 1.4338550567626953, | |
| "eval_runtime": 68.6236, | |
| "eval_samples_per_second": 67.134, | |
| "eval_steps_per_second": 8.394, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009506398537477149, | |
| "grad_norm": 0.15829448401927948, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 1.4437, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.009872029250457038, | |
| "grad_norm": 0.14465104043483734, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.4092, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010237659963436929, | |
| "grad_norm": 0.1586385816335678, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 1.4306, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01060329067641682, | |
| "grad_norm": 0.16052576899528503, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.4512, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.010968921389396709, | |
| "grad_norm": 0.15008322894573212, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.4282, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0113345521023766, | |
| "grad_norm": 0.1620539277791977, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.489, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01170018281535649, | |
| "grad_norm": 0.16483284533023834, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.4853, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01206581352833638, | |
| "grad_norm": 0.15536175668239594, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.4549, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01243144424131627, | |
| "grad_norm": 0.14910203218460083, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.3926, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.012797074954296161, | |
| "grad_norm": 0.14977602660655975, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3395, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01316270566727605, | |
| "grad_norm": 0.15815122425556183, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.4415, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.013528336380255941, | |
| "grad_norm": 0.15232770144939423, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.431, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.013893967093235832, | |
| "grad_norm": 0.16287685930728912, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.4705, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.014259597806215722, | |
| "grad_norm": 0.16413241624832153, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.4865, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.014625228519195612, | |
| "grad_norm": 0.146493062376976, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.4395, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014990859232175503, | |
| "grad_norm": 0.1493939459323883, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.4134, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.015356489945155392, | |
| "grad_norm": 0.16362649202346802, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.4669, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.015722120658135285, | |
| "grad_norm": 0.17766478657722473, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.4814, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.016087751371115174, | |
| "grad_norm": 0.14952148497104645, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.4376, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.016453382084095063, | |
| "grad_norm": 0.16464552283287048, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.5386, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.016819012797074956, | |
| "grad_norm": 0.1606977880001068, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.4878, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.017184643510054845, | |
| "grad_norm": 0.16758908331394196, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.4678, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.017550274223034734, | |
| "grad_norm": 0.16065165400505066, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.4645, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.017915904936014627, | |
| "grad_norm": 0.17361202836036682, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.5199, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.018281535648994516, | |
| "grad_norm": 0.19459863007068634, | |
| "learning_rate": 0.0, | |
| "loss": 1.4341, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018281535648994516, | |
| "eval_loss": 1.400192141532898, | |
| "eval_runtime": 68.6675, | |
| "eval_samples_per_second": 67.091, | |
| "eval_steps_per_second": 8.388, | |
| "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": 5, | |
| "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": 3434439770112000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |