| { | |
| "best_metric": 0.021049948409199715, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.97442143727162, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012992285830288266, | |
| "grad_norm": 36.630287170410156, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 8.1038, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012992285830288266, | |
| "eval_loss": 8.06094741821289, | |
| "eval_runtime": 1.481, | |
| "eval_samples_per_second": 33.762, | |
| "eval_steps_per_second": 8.778, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025984571660576532, | |
| "grad_norm": 36.71709060668945, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 7.9426, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0389768574908648, | |
| "grad_norm": 31.190719604492188, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2336, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.051969143321153065, | |
| "grad_norm": 27.901527404785156, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 5.3213, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06496142915144133, | |
| "grad_norm": 19.23626708984375, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 3.1653, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0779537149817296, | |
| "grad_norm": 25.957687377929688, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.0286, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09094600081201787, | |
| "grad_norm": 21.65407371520996, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 1.2344, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10393828664230613, | |
| "grad_norm": 6.849808692932129, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 0.6661, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11693057247259439, | |
| "grad_norm": 8.28010368347168, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.5171, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12992285830288267, | |
| "grad_norm": 6.745442867279053, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 0.4975, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14291514413317094, | |
| "grad_norm": 7.655923366546631, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 0.3611, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1559074299634592, | |
| "grad_norm": 7.9347124099731445, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.2793, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16889971579374746, | |
| "grad_norm": 4.294223785400391, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 0.1923, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.18189200162403574, | |
| "grad_norm": 1.2570604085922241, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 0.1265, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19488428745432398, | |
| "grad_norm": 2.589317798614502, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.1075, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20787657328461226, | |
| "grad_norm": 1.269200325012207, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 0.0922, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22086885911490053, | |
| "grad_norm": 11.871465682983398, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 0.1883, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23386114494518878, | |
| "grad_norm": 6.418728828430176, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.1336, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24685343077547706, | |
| "grad_norm": 3.559746026992798, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 0.091, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.25984571660576533, | |
| "grad_norm": 3.894230604171753, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 0.1084, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2728380024360536, | |
| "grad_norm": 2.0176477432250977, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.0966, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2858302882663419, | |
| "grad_norm": 3.4982409477233887, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 0.1054, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2988225740966301, | |
| "grad_norm": 0.9820318818092346, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 0.0746, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3118148599269184, | |
| "grad_norm": 3.725250482559204, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1343, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32480714575720665, | |
| "grad_norm": 4.605804920196533, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 0.1789, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.32480714575720665, | |
| "eval_loss": 0.1300944834947586, | |
| "eval_runtime": 1.4881, | |
| "eval_samples_per_second": 33.599, | |
| "eval_steps_per_second": 8.736, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3377994315874949, | |
| "grad_norm": 7.682220458984375, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 0.1106, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3507917174177832, | |
| "grad_norm": 8.865133285522461, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.1535, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3637840032480715, | |
| "grad_norm": 3.1668100357055664, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 0.0889, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.37677628907835975, | |
| "grad_norm": 2.320821523666382, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 0.0714, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.38976857490864797, | |
| "grad_norm": 3.224240303039551, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0948, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.40276086073893624, | |
| "grad_norm": 2.759305953979492, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 0.0817, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4157531465692245, | |
| "grad_norm": 1.3898932933807373, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 0.0546, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4287454323995128, | |
| "grad_norm": 2.0559136867523193, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0792, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.44173771822980107, | |
| "grad_norm": 1.2107505798339844, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 0.0658, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45473000406008934, | |
| "grad_norm": 0.8181975483894348, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 0.0573, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.46772228989037756, | |
| "grad_norm": 0.8736940622329712, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0906, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.48071457572066584, | |
| "grad_norm": 1.7226741313934326, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 0.0669, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4937068615509541, | |
| "grad_norm": 1.7814589738845825, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 0.0771, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5066991473812423, | |
| "grad_norm": 1.8109633922576904, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0613, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5196914332115307, | |
| "grad_norm": 2.7186203002929688, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 0.0735, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5326837190418189, | |
| "grad_norm": 2.1896440982818604, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 0.0928, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5456760048721072, | |
| "grad_norm": 1.4338561296463013, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0955, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5586682907023954, | |
| "grad_norm": 1.8646522760391235, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 0.0481, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5716605765326838, | |
| "grad_norm": 2.171997547149658, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 0.0493, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.584652862362972, | |
| "grad_norm": 1.8785721063613892, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.0529, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5976451481932602, | |
| "grad_norm": 0.8664989471435547, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 0.0541, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6106374340235485, | |
| "grad_norm": 2.1312761306762695, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 0.0664, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6236297198538368, | |
| "grad_norm": 2.3210947513580322, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.095, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6366220056841251, | |
| "grad_norm": 3.8043196201324463, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 0.0916, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6496142915144133, | |
| "grad_norm": 1.2356327772140503, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 0.0625, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6496142915144133, | |
| "eval_loss": 0.032049428671598434, | |
| "eval_runtime": 1.5457, | |
| "eval_samples_per_second": 32.348, | |
| "eval_steps_per_second": 8.411, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6626065773447016, | |
| "grad_norm": 3.8544723987579346, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.1116, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.6755988631749898, | |
| "grad_norm": 1.4536547660827637, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 0.0447, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.6885911490052781, | |
| "grad_norm": 1.1871592998504639, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 0.0683, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7015834348355664, | |
| "grad_norm": 0.5502886772155762, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0404, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7145757206658546, | |
| "grad_norm": 0.49863505363464355, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 0.0324, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.727568006496143, | |
| "grad_norm": 0.8850557208061218, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 0.0645, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7405602923264312, | |
| "grad_norm": 0.7965983748435974, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0548, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7535525781567195, | |
| "grad_norm": 0.6387767791748047, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 0.0658, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.7665448639870077, | |
| "grad_norm": 0.8699201345443726, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 0.0624, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.7795371498172959, | |
| "grad_norm": 1.0982764959335327, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0866, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7925294356475843, | |
| "grad_norm": 1.1414963006973267, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 0.075, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.8055217214778725, | |
| "grad_norm": 0.8054099082946777, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 0.0604, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8185140073081608, | |
| "grad_norm": 1.1966440677642822, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0677, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.831506293138449, | |
| "grad_norm": 0.9174244403839111, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 0.0516, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8444985789687373, | |
| "grad_norm": 0.6317915916442871, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 0.0512, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8574908647990256, | |
| "grad_norm": 1.381137490272522, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0516, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.8704831506293138, | |
| "grad_norm": 0.45590871572494507, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 0.0427, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.8834754364596021, | |
| "grad_norm": 1.784468650817871, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 0.059, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.8964677222898904, | |
| "grad_norm": 1.0624321699142456, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0443, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.9094600081201787, | |
| "grad_norm": 1.522290587425232, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 0.0563, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9224522939504669, | |
| "grad_norm": 0.38779476284980774, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 0.0314, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.9354445797807551, | |
| "grad_norm": 1.1681578159332275, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0623, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.9484368656110435, | |
| "grad_norm": 0.5920040011405945, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 0.0566, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.9614291514413317, | |
| "grad_norm": 0.5902805328369141, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 0.0524, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.97442143727162, | |
| "grad_norm": 0.6527218222618103, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0566, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.97442143727162, | |
| "eval_loss": 0.021049948409199715, | |
| "eval_runtime": 1.5036, | |
| "eval_samples_per_second": 33.255, | |
| "eval_steps_per_second": 8.646, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 4.42951368966144e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |