| { | |
| "best_metric": 3.4272310733795166, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05216484089723526, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010432968179447052, | |
| "grad_norm": 1.3536896705627441, | |
| "learning_rate": 1e-05, | |
| "loss": 3.9159, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010432968179447052, | |
| "eval_loss": 3.9926509857177734, | |
| "eval_runtime": 45.3778, | |
| "eval_samples_per_second": 35.568, | |
| "eval_steps_per_second": 8.903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020865936358894104, | |
| "grad_norm": 1.3918986320495605, | |
| "learning_rate": 2e-05, | |
| "loss": 3.9771, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003129890453834116, | |
| "grad_norm": 1.3853706121444702, | |
| "learning_rate": 3e-05, | |
| "loss": 4.0231, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004173187271778821, | |
| "grad_norm": 1.126749873161316, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9471, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005216484089723527, | |
| "grad_norm": 0.9558578133583069, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9798, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006259780907668232, | |
| "grad_norm": 1.1789942979812622, | |
| "learning_rate": 6e-05, | |
| "loss": 3.8752, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007303077725612937, | |
| "grad_norm": 1.2972698211669922, | |
| "learning_rate": 7e-05, | |
| "loss": 3.8675, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008346374543557642, | |
| "grad_norm": 0.9673587679862976, | |
| "learning_rate": 8e-05, | |
| "loss": 3.8187, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009389671361502348, | |
| "grad_norm": 0.8321828842163086, | |
| "learning_rate": 9e-05, | |
| "loss": 3.7787, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010432968179447054, | |
| "grad_norm": 0.8781248331069946, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7405, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011476264997391758, | |
| "grad_norm": 0.8188990950584412, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 3.7719, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012519561815336464, | |
| "grad_norm": 0.6031615138053894, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 3.6993, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013562858633281168, | |
| "grad_norm": 0.6562380790710449, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 3.6596, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.014606155451225874, | |
| "grad_norm": 0.6179069876670837, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 3.6793, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01564945226917058, | |
| "grad_norm": 0.5190150141716003, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 3.6748, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016692749087115284, | |
| "grad_norm": 0.5107501149177551, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 3.6221, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01773604590505999, | |
| "grad_norm": 0.4812328517436981, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 3.6798, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.018779342723004695, | |
| "grad_norm": 0.5446358919143677, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 3.5747, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0198226395409494, | |
| "grad_norm": 0.48601874709129333, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 3.5853, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.020865936358894107, | |
| "grad_norm": 0.47902897000312805, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 3.6475, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02190923317683881, | |
| "grad_norm": 0.46482163667678833, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 3.4818, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.022952529994783515, | |
| "grad_norm": 0.5013744235038757, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 3.5941, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.023995826812728223, | |
| "grad_norm": 0.47039228677749634, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 3.6272, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.025039123630672927, | |
| "grad_norm": 0.474264532327652, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 3.5004, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02608242044861763, | |
| "grad_norm": 0.457125186920166, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 3.4437, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027125717266562335, | |
| "grad_norm": 0.4855491518974304, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 3.5872, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.028169014084507043, | |
| "grad_norm": 0.5192623138427734, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 3.5309, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.029212310902451747, | |
| "grad_norm": 0.5076422691345215, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 3.535, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03025560772039645, | |
| "grad_norm": 0.484314501285553, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.5004, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03129890453834116, | |
| "grad_norm": 0.5465930104255676, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 3.5917, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03234220135628586, | |
| "grad_norm": 0.5205236077308655, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 3.4095, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03338549817423057, | |
| "grad_norm": 0.5593637228012085, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 3.5034, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03442879499217527, | |
| "grad_norm": 0.5713189244270325, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 3.4703, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03547209181011998, | |
| "grad_norm": 0.5576574802398682, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 3.4392, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.036515388628064686, | |
| "grad_norm": 0.5582655668258667, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 3.3823, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03755868544600939, | |
| "grad_norm": 0.5881125926971436, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 3.4655, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.038601982263954095, | |
| "grad_norm": 0.610686182975769, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 3.3674, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0396452790818988, | |
| "grad_norm": 0.5850858688354492, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 3.453, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0406885758998435, | |
| "grad_norm": 0.602027177810669, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 3.466, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.041731872717788214, | |
| "grad_norm": 0.6175333857536316, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 3.4765, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04277516953573292, | |
| "grad_norm": 0.6265369057655334, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 3.3938, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04381846635367762, | |
| "grad_norm": 0.6787665486335754, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 3.3514, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.044861763171622326, | |
| "grad_norm": 0.653775155544281, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 3.2032, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04590505998956703, | |
| "grad_norm": 0.6895964741706848, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 3.2933, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.046948356807511735, | |
| "grad_norm": 0.7148680090904236, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 3.2034, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.047991653625456446, | |
| "grad_norm": 0.8246645927429199, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 3.1824, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04903495044340115, | |
| "grad_norm": 0.8079376220703125, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 3.1431, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.050078247261345854, | |
| "grad_norm": 0.9385347962379456, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.1974, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05112154407929056, | |
| "grad_norm": 1.0700104236602783, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 2.9287, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05216484089723526, | |
| "grad_norm": 1.6941026449203491, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 2.9044, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05216484089723526, | |
| "eval_loss": 3.4272310733795166, | |
| "eval_runtime": 45.7283, | |
| "eval_samples_per_second": 35.295, | |
| "eval_steps_per_second": 8.835, | |
| "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": 1.356308410269696e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |