| { | |
| "best_metric": 2.4689817428588867, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.11363636363636363, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0022727272727272726, | |
| "grad_norm": 1.606259822845459, | |
| "learning_rate": 2e-05, | |
| "loss": 2.6575, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022727272727272726, | |
| "eval_loss": 2.972724676132202, | |
| "eval_runtime": 6.8425, | |
| "eval_samples_per_second": 108.294, | |
| "eval_steps_per_second": 13.592, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004545454545454545, | |
| "grad_norm": 1.7978665828704834, | |
| "learning_rate": 4e-05, | |
| "loss": 2.566, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006818181818181818, | |
| "grad_norm": 1.5056153535842896, | |
| "learning_rate": 6e-05, | |
| "loss": 2.6681, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00909090909090909, | |
| "grad_norm": 1.284254550933838, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5945, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011363636363636364, | |
| "grad_norm": 1.6918977499008179, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6936, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013636363636363636, | |
| "grad_norm": 2.2507495880126953, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.7084, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015909090909090907, | |
| "grad_norm": 1.648572325706482, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.5595, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01818181818181818, | |
| "grad_norm": 1.4604798555374146, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.3795, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020454545454545454, | |
| "grad_norm": 1.4552377462387085, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.532, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022727272727272728, | |
| "grad_norm": 1.552384376525879, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.4922, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 1.5556209087371826, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.4043, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02727272727272727, | |
| "grad_norm": 1.5756804943084717, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.4997, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029545454545454545, | |
| "grad_norm": 1.541499376296997, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.4007, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.031818181818181815, | |
| "grad_norm": 1.5218021869659424, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.5088, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03409090909090909, | |
| "grad_norm": 1.52951180934906, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.402, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03636363636363636, | |
| "grad_norm": 1.5703572034835815, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.4933, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.038636363636363635, | |
| "grad_norm": 1.676938772201538, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.3683, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04090909090909091, | |
| "grad_norm": 1.6145377159118652, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.5634, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04318181818181818, | |
| "grad_norm": 1.7284026145935059, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 2.5014, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 1.7103477716445923, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.4047, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04772727272727273, | |
| "grad_norm": 1.8176960945129395, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 2.4621, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1.9118075370788574, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 2.3042, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05227272727272727, | |
| "grad_norm": 1.9427374601364136, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.3648, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05454545454545454, | |
| "grad_norm": 1.935987949371338, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.3904, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.056818181818181816, | |
| "grad_norm": 2.205674409866333, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.4429, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.056818181818181816, | |
| "eval_loss": 2.5051064491271973, | |
| "eval_runtime": 6.7932, | |
| "eval_samples_per_second": 109.08, | |
| "eval_steps_per_second": 13.69, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05909090909090909, | |
| "grad_norm": 2.0927062034606934, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.2257, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06136363636363636, | |
| "grad_norm": 2.312185049057007, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 2.1917, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06363636363636363, | |
| "grad_norm": 2.3717732429504395, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.2485, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0659090909090909, | |
| "grad_norm": 2.3789658546447754, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 2.3248, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06818181818181818, | |
| "grad_norm": 2.333639621734619, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.2749, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07045454545454545, | |
| "grad_norm": 2.7359251976013184, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 2.4323, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 2.6724472045898438, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.6001, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 2.704455614089966, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 2.3212, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07727272727272727, | |
| "grad_norm": 2.7967569828033447, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 2.245, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07954545454545454, | |
| "grad_norm": 2.7874977588653564, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.0644, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08181818181818182, | |
| "grad_norm": 3.0134224891662598, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 2.2045, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08409090909090909, | |
| "grad_norm": 3.377096652984619, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 2.0878, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08636363636363636, | |
| "grad_norm": 3.990339517593384, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 2.3226, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08863636363636364, | |
| "grad_norm": 3.2142210006713867, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.0823, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 3.8085083961486816, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.4723, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09318181818181819, | |
| "grad_norm": 3.704538106918335, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.1217, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09545454545454546, | |
| "grad_norm": 3.812995195388794, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.9568, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09772727272727273, | |
| "grad_norm": 4.169566631317139, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 2.2289, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 4.201821327209473, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 2.184, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10227272727272728, | |
| "grad_norm": 4.2996907234191895, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 2.4758, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10454545454545454, | |
| "grad_norm": 4.644790172576904, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.1504, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10681818181818181, | |
| "grad_norm": 5.309967041015625, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.0347, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10909090909090909, | |
| "grad_norm": 7.990983009338379, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.2895, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11136363636363636, | |
| "grad_norm": 10.469155311584473, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 2.84, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11363636363636363, | |
| "grad_norm": 20.095691680908203, | |
| "learning_rate": 0.0, | |
| "loss": 3.1589, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11363636363636363, | |
| "eval_loss": 2.4689817428588867, | |
| "eval_runtime": 6.7551, | |
| "eval_samples_per_second": 109.694, | |
| "eval_steps_per_second": 13.767, | |
| "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": 1990084226187264.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |