| { | |
| "best_metric": 0.32187753915786743, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.01704012950498424, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00034080259009968474, | |
| "grad_norm": 32.40592956542969, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7876, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00034080259009968474, | |
| "eval_loss": 4.506282806396484, | |
| "eval_runtime": 40.34, | |
| "eval_samples_per_second": 122.509, | |
| "eval_steps_per_second": 15.32, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006816051801993695, | |
| "grad_norm": 35.26675796508789, | |
| "learning_rate": 4e-05, | |
| "loss": 2.4626, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0010224077702990543, | |
| "grad_norm": 27.01038360595703, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1915, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001363210360398739, | |
| "grad_norm": 7.334166526794434, | |
| "learning_rate": 8e-05, | |
| "loss": 1.6678, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0017040129504984239, | |
| "grad_norm": 7.9066290855407715, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3352, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0020448155405981086, | |
| "grad_norm": 8.249860763549805, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.2722, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0023856181306977932, | |
| "grad_norm": 6.200305461883545, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.7406, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002726420720797478, | |
| "grad_norm": 4.214573383331299, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.479, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0030672233108971626, | |
| "grad_norm": 2.904484748840332, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.4033, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0034080259009968477, | |
| "grad_norm": 2.066265106201172, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.324, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0037488284910965324, | |
| "grad_norm": 1.7582463026046753, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.226, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004089631081196217, | |
| "grad_norm": 1.7222720384597778, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.2761, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004430433671295902, | |
| "grad_norm": 1.6275396347045898, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.219, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0047712362613955865, | |
| "grad_norm": 2.033787727355957, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.2957, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005112038851495271, | |
| "grad_norm": 1.971697211265564, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.2534, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005452841441594956, | |
| "grad_norm": 1.6060328483581543, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.2304, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0057936440316946405, | |
| "grad_norm": 2.0094447135925293, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.2735, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006134446621794325, | |
| "grad_norm": 1.913122534751892, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.3057, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006475249211894011, | |
| "grad_norm": 2.0093114376068115, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.2546, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0068160518019936955, | |
| "grad_norm": 2.41322922706604, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.253, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00715685439209338, | |
| "grad_norm": 1.3928881883621216, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.2105, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007497656982193065, | |
| "grad_norm": 1.8394007682800293, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.2806, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007838459572292749, | |
| "grad_norm": 1.9014151096343994, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.3008, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008179262162392434, | |
| "grad_norm": 1.8305542469024658, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.2682, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00852006475249212, | |
| "grad_norm": 1.6967408657073975, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.2992, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00852006475249212, | |
| "eval_loss": 0.3422561585903168, | |
| "eval_runtime": 40.098, | |
| "eval_samples_per_second": 123.248, | |
| "eval_steps_per_second": 15.412, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008860867342591804, | |
| "grad_norm": 1.9422880411148071, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.3305, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00920166993269149, | |
| "grad_norm": 1.764593482017517, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.2678, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009542472522791173, | |
| "grad_norm": 1.5991082191467285, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.2597, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009883275112890859, | |
| "grad_norm": 1.7475390434265137, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.2904, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.010224077702990542, | |
| "grad_norm": 2.1305644512176514, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.2603, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010564880293090228, | |
| "grad_norm": 2.0109963417053223, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.3122, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.010905682883189912, | |
| "grad_norm": 1.9568897485733032, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.2805, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.011246485473289597, | |
| "grad_norm": 2.2019479274749756, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.3558, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.011587288063389281, | |
| "grad_norm": 2.110915422439575, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.2975, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.011928090653488967, | |
| "grad_norm": 2.6419875621795654, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3606, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01226889324358865, | |
| "grad_norm": 2.0763304233551025, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.327, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.012609695833688336, | |
| "grad_norm": 2.4885149002075195, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.4387, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.012950498423788022, | |
| "grad_norm": 3.0897700786590576, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.471, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.013291301013887705, | |
| "grad_norm": 2.36295485496521, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.3544, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.013632103603987391, | |
| "grad_norm": 2.7423489093780518, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.4387, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013972906194087075, | |
| "grad_norm": 3.7384166717529297, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.5706, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01431370878418676, | |
| "grad_norm": 3.3828611373901367, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.4223, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.014654511374286444, | |
| "grad_norm": 4.098020553588867, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.5079, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01499531396438613, | |
| "grad_norm": 3.331911563873291, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.5553, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.015336116554485813, | |
| "grad_norm": 3.745422124862671, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.5396, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.015676919144585497, | |
| "grad_norm": 3.473151445388794, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.5857, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.016017721734685183, | |
| "grad_norm": 3.8388254642486572, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.5971, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01635852432478487, | |
| "grad_norm": 3.75164532661438, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.662, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.016699326914884554, | |
| "grad_norm": 4.220789909362793, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.8274, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.01704012950498424, | |
| "grad_norm": 5.04517936706543, | |
| "learning_rate": 0.0, | |
| "loss": 0.9047, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01704012950498424, | |
| "eval_loss": 0.32187753915786743, | |
| "eval_runtime": 40.1252, | |
| "eval_samples_per_second": 123.165, | |
| "eval_steps_per_second": 15.402, | |
| "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": 1664694091776000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |