| { | |
| "best_metric": 2.10509991645813, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03518648838845883, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007037297677691766, | |
| "grad_norm": 1.0125492811203003, | |
| "learning_rate": 2e-05, | |
| "loss": 3.2816, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007037297677691766, | |
| "eval_loss": 3.9164936542510986, | |
| "eval_runtime": 37.2346, | |
| "eval_samples_per_second": 64.295, | |
| "eval_steps_per_second": 8.057, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014074595355383533, | |
| "grad_norm": 3.5766561031341553, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9462, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00211118930330753, | |
| "grad_norm": 2.5950045585632324, | |
| "learning_rate": 6e-05, | |
| "loss": 3.5797, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0028149190710767065, | |
| "grad_norm": 2.7977962493896484, | |
| "learning_rate": 8e-05, | |
| "loss": 3.6072, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003518648838845883, | |
| "grad_norm": 2.1631622314453125, | |
| "learning_rate": 0.0001, | |
| "loss": 3.2745, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00422237860661506, | |
| "grad_norm": 2.0710830688476562, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 3.3664, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0049261083743842365, | |
| "grad_norm": 1.2765297889709473, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 3.4573, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005629838142153413, | |
| "grad_norm": 1.2099251747131348, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 3.2101, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0063335679099225895, | |
| "grad_norm": 1.2356455326080322, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 3.0699, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007037297677691766, | |
| "grad_norm": 0.9908618927001953, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.9171, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007741027445460943, | |
| "grad_norm": 1.0424559116363525, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.9475, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00844475721323012, | |
| "grad_norm": 0.8514713644981384, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.6687, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009148486980999296, | |
| "grad_norm": 0.7458367943763733, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.7813, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009852216748768473, | |
| "grad_norm": 0.8679640889167786, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.2609, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01055594651653765, | |
| "grad_norm": 0.9870083928108215, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.5657, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011259676284306826, | |
| "grad_norm": 0.8825538158416748, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.5494, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011963406052076003, | |
| "grad_norm": 0.7419976592063904, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.6619, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.012667135819845179, | |
| "grad_norm": 0.9009146094322205, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.3459, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.013370865587614356, | |
| "grad_norm": 0.8520352244377136, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 2.3065, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.014074595355383532, | |
| "grad_norm": 0.7043901085853577, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3596, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014778325123152709, | |
| "grad_norm": 0.8790773749351501, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 2.3797, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015482054890921885, | |
| "grad_norm": 1.5859887599945068, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 2.2633, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01618578465869106, | |
| "grad_norm": 0.8419453501701355, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.1592, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01688951442646024, | |
| "grad_norm": 0.7322970032691956, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.197, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017593244194229415, | |
| "grad_norm": 0.7999675273895264, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.2641, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017593244194229415, | |
| "eval_loss": 2.1993303298950195, | |
| "eval_runtime": 37.7424, | |
| "eval_samples_per_second": 63.43, | |
| "eval_steps_per_second": 7.949, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018296973961998593, | |
| "grad_norm": 0.8108159899711609, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.185, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.019000703729767768, | |
| "grad_norm": 0.6874377727508545, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 2.1766, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.019704433497536946, | |
| "grad_norm": 0.7179682850837708, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.2221, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 1.216280221939087, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 2.4166, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0211118930330753, | |
| "grad_norm": 0.7951951622962952, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.0194, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021815622800844477, | |
| "grad_norm": 0.6431245803833008, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 2.0918, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.022519352568613652, | |
| "grad_norm": 0.7210680842399597, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.1332, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02322308233638283, | |
| "grad_norm": 0.7762433886528015, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 2.2283, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.023926812104152005, | |
| "grad_norm": 0.6160893440246582, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 2.0208, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.024630541871921183, | |
| "grad_norm": 0.9088425636291504, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.4412, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.025334271639690358, | |
| "grad_norm": 0.790292501449585, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 2.0857, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.026038001407459536, | |
| "grad_norm": 0.6113930940628052, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.9494, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02674173117522871, | |
| "grad_norm": 0.6941695809364319, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.8067, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02744546094299789, | |
| "grad_norm": 0.6881697177886963, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.8486, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.028149190710767064, | |
| "grad_norm": 0.9811816811561584, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.9745, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028852920478536243, | |
| "grad_norm": 0.8144062757492065, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.7651, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.029556650246305417, | |
| "grad_norm": 0.8490874171257019, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.7061, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.030260380014074596, | |
| "grad_norm": 1.0510660409927368, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.7503, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03096410978184377, | |
| "grad_norm": 0.9851308465003967, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.8392, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03166783954961295, | |
| "grad_norm": 1.0835424661636353, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.7826, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03237156931738212, | |
| "grad_norm": 1.0677682161331177, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.0415, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.033075299085151305, | |
| "grad_norm": 1.1599544286727905, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.0658, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03377902885292048, | |
| "grad_norm": 1.6693414449691772, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.2281, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": 2.1483304500579834, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.0819, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03518648838845883, | |
| "grad_norm": 3.549574375152588, | |
| "learning_rate": 0.0, | |
| "loss": 2.8289, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03518648838845883, | |
| "eval_loss": 2.10509991645813, | |
| "eval_runtime": 37.6616, | |
| "eval_samples_per_second": 63.566, | |
| "eval_steps_per_second": 7.966, | |
| "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": 8520778270113792.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |