| { | |
| "best_metric": 0.953262984752655, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.010930753675465924, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021861507350931847, | |
| "grad_norm": 16.407384872436523, | |
| "learning_rate": 2e-05, | |
| "loss": 7.5287, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021861507350931847, | |
| "eval_loss": 2.686614751815796, | |
| "eval_runtime": 563.7197, | |
| "eval_samples_per_second": 13.666, | |
| "eval_steps_per_second": 1.708, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00043723014701863694, | |
| "grad_norm": 17.86746597290039, | |
| "learning_rate": 4e-05, | |
| "loss": 7.593, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006558452205279554, | |
| "grad_norm": 12.385472297668457, | |
| "learning_rate": 6e-05, | |
| "loss": 7.2987, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008744602940372739, | |
| "grad_norm": 12.885078430175781, | |
| "learning_rate": 8e-05, | |
| "loss": 6.6756, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010930753675465923, | |
| "grad_norm": 10.959245681762695, | |
| "learning_rate": 0.0001, | |
| "loss": 6.5323, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013116904410559109, | |
| "grad_norm": 9.190923690795898, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 5.9949, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015303055145652292, | |
| "grad_norm": 8.72174072265625, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 5.8229, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0017489205880745478, | |
| "grad_norm": 7.519791603088379, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 5.6152, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001967535661583866, | |
| "grad_norm": 8.365340232849121, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 5.6945, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0021861507350931847, | |
| "grad_norm": 6.8350090980529785, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 5.6613, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002404765808602503, | |
| "grad_norm": 5.859904766082764, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 5.3751, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0026233808821118218, | |
| "grad_norm": 6.787869930267334, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 5.6417, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00284199595562114, | |
| "grad_norm": 6.37191915512085, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 5.3381, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0030606110291304584, | |
| "grad_norm": 6.0006103515625, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 5.3387, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003279226102639777, | |
| "grad_norm": 6.7284088134765625, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 5.2278, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0034978411761490955, | |
| "grad_norm": 6.43040657043457, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 4.9573, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003716456249658414, | |
| "grad_norm": 6.7755560874938965, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 4.8515, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003935071323167732, | |
| "grad_norm": 6.345210552215576, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 4.945, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004153686396677051, | |
| "grad_norm": 6.206517219543457, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 4.8408, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004372301470186369, | |
| "grad_norm": 6.259011745452881, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.9371, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004590916543695688, | |
| "grad_norm": 6.050141334533691, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 4.8264, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004809531617205006, | |
| "grad_norm": 5.958347797393799, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 4.9043, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005028146690714325, | |
| "grad_norm": 6.363147735595703, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 4.774, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0052467617642236435, | |
| "grad_norm": 5.6820759773254395, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 4.8601, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005465376837732962, | |
| "grad_norm": 5.9423112869262695, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 4.646, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005465376837732962, | |
| "eval_loss": 0.953262984752655, | |
| "eval_runtime": 569.4761, | |
| "eval_samples_per_second": 13.528, | |
| "eval_steps_per_second": 1.691, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00568399191124228, | |
| "grad_norm": 5.9507737159729, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 4.9033, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005902606984751598, | |
| "grad_norm": 5.530628204345703, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 4.7583, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006121222058260917, | |
| "grad_norm": 5.337352275848389, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 4.3889, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006339837131770235, | |
| "grad_norm": 5.4964799880981445, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 4.9386, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006558452205279554, | |
| "grad_norm": 5.906266689300537, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 4.5782, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0067770672787888725, | |
| "grad_norm": 5.448102951049805, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 4.063, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006995682352298191, | |
| "grad_norm": 6.286194801330566, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 4.3136, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00721429742580751, | |
| "grad_norm": 6.302289009094238, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 4.3495, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.007432912499316828, | |
| "grad_norm": 6.26800012588501, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 4.1651, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007651527572826147, | |
| "grad_norm": 8.510433197021484, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.4399, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007870142646335464, | |
| "grad_norm": 12.65410327911377, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.1253, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.008088757719844783, | |
| "grad_norm": 10.533549308776855, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.0505, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.008307372793354102, | |
| "grad_norm": 9.48660945892334, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.9796, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00852598786686342, | |
| "grad_norm": 8.460052490234375, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.0586, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.008744602940372739, | |
| "grad_norm": 9.045680046081543, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.9932, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008963218013882057, | |
| "grad_norm": 8.324438095092773, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.0128, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.009181833087391376, | |
| "grad_norm": 6.455205917358398, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.9578, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.009400448160900694, | |
| "grad_norm": 8.26326847076416, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.076, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009619063234410013, | |
| "grad_norm": 9.695878982543945, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.0531, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009837678307919331, | |
| "grad_norm": 10.864912986755371, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.9696, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01005629338142865, | |
| "grad_norm": 8.258566856384277, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.0418, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.010274908454937969, | |
| "grad_norm": 6.829498291015625, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.8508, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.010493523528447287, | |
| "grad_norm": 6.845117092132568, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.8732, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.010712138601956606, | |
| "grad_norm": 10.317815780639648, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.8618, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.010930753675465924, | |
| "grad_norm": 8.375981330871582, | |
| "learning_rate": 0.0, | |
| "loss": 0.8755, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010930753675465924, | |
| "eval_loss": 0.9876481294631958, | |
| "eval_runtime": 568.1922, | |
| "eval_samples_per_second": 13.559, | |
| "eval_steps_per_second": 1.695, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.11922310751191e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |