| { | |
| "best_metric": 0.3203987777233124, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1958863858961802, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0039177277179236044, | |
| "grad_norm": 35.1519660949707, | |
| "learning_rate": 1e-05, | |
| "loss": 3.3377, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0039177277179236044, | |
| "eval_loss": 1.376975655555725, | |
| "eval_runtime": 30.7914, | |
| "eval_samples_per_second": 13.965, | |
| "eval_steps_per_second": 3.507, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007835455435847209, | |
| "grad_norm": 37.591468811035156, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5823, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011753183153770812, | |
| "grad_norm": 27.038301467895508, | |
| "learning_rate": 3e-05, | |
| "loss": 3.1019, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015670910871694418, | |
| "grad_norm": 17.632797241210938, | |
| "learning_rate": 4e-05, | |
| "loss": 2.424, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.019588638589618023, | |
| "grad_norm": 13.900057792663574, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7934, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023506366307541625, | |
| "grad_norm": 6.731367111206055, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5624, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02742409402546523, | |
| "grad_norm": 4.34248161315918, | |
| "learning_rate": 7e-05, | |
| "loss": 1.2948, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.031341821743388835, | |
| "grad_norm": 3.769124746322632, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3975, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03525954946131244, | |
| "grad_norm": 3.391641855239868, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2989, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.039177277179236046, | |
| "grad_norm": 3.0701184272766113, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0842, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.043095004897159644, | |
| "grad_norm": 3.9934017658233643, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.0914, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04701273261508325, | |
| "grad_norm": 3.2494006156921387, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.1219, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.050930460333006855, | |
| "grad_norm": 3.7557196617126465, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.1797, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05484818805093046, | |
| "grad_norm": 3.097635507583618, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.215, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.058765915768854066, | |
| "grad_norm": 3.3909478187561035, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.0895, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06268364348677767, | |
| "grad_norm": 3.7466847896575928, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.3652, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06660137120470128, | |
| "grad_norm": 3.1385905742645264, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.1725, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07051909892262488, | |
| "grad_norm": 3.1092734336853027, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.3138, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07443682664054849, | |
| "grad_norm": 2.706139326095581, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.0156, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07835455435847209, | |
| "grad_norm": 3.3206448554992676, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.3558, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08227228207639568, | |
| "grad_norm": 2.7940611839294434, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.2443, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08619000979431929, | |
| "grad_norm": 2.728489875793457, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.1225, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0901077375122429, | |
| "grad_norm": 2.7424354553222656, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.118, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0940254652301665, | |
| "grad_norm": 2.959437847137451, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.1265, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0979431929480901, | |
| "grad_norm": 3.068791151046753, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.111, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10186092066601371, | |
| "grad_norm": 3.436812400817871, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.2612, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10577864838393732, | |
| "grad_norm": 2.8119099140167236, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.9175, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10969637610186092, | |
| "grad_norm": 2.9515905380249023, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.1611, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11361410381978453, | |
| "grad_norm": 3.0629842281341553, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.0789, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11753183153770813, | |
| "grad_norm": 3.72255277633667, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.1929, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12144955925563174, | |
| "grad_norm": 2.680954694747925, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.9458, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12536728697355534, | |
| "grad_norm": 2.4375383853912354, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.949, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12928501469147893, | |
| "grad_norm": 2.8537662029266357, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.1638, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13320274240940255, | |
| "grad_norm": 2.751599073410034, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.1644, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.13712047012732614, | |
| "grad_norm": 2.9511516094207764, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.052, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14103819784524976, | |
| "grad_norm": 2.903895616531372, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.0966, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14495592556317335, | |
| "grad_norm": 2.5975160598754883, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.033, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14887365328109697, | |
| "grad_norm": 2.664412021636963, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.1325, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15279138099902057, | |
| "grad_norm": 2.3869800567626953, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.8831, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15670910871694418, | |
| "grad_norm": 3.5770905017852783, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.0356, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16062683643486778, | |
| "grad_norm": 3.232245922088623, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.1462, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.16454456415279137, | |
| "grad_norm": 2.72615647315979, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.0273, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.168462291870715, | |
| "grad_norm": 2.8978590965270996, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.021, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17238001958863858, | |
| "grad_norm": 3.248000144958496, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.093, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1762977473065622, | |
| "grad_norm": 2.8521573543548584, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.0163, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1802154750244858, | |
| "grad_norm": 3.390756845474243, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.8542, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1841332027424094, | |
| "grad_norm": 2.9699442386627197, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.9035, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.188050930460333, | |
| "grad_norm": 2.9843027591705322, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.0058, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.19196865817825662, | |
| "grad_norm": 4.668224334716797, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.7376, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1958863858961802, | |
| "grad_norm": 2.9681031703948975, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.7555, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1958863858961802, | |
| "eval_loss": 0.3203987777233124, | |
| "eval_runtime": 31.553, | |
| "eval_samples_per_second": 13.628, | |
| "eval_steps_per_second": 3.423, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.15808242139136e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |