| { | |
| "best_metric": 1.3095707893371582, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.45610034207525657, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009122006841505131, | |
| "grad_norm": 8.655662536621094, | |
| "learning_rate": 5e-05, | |
| "loss": 1.871, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009122006841505131, | |
| "eval_loss": 3.7504098415374756, | |
| "eval_runtime": 1.5013, | |
| "eval_samples_per_second": 33.304, | |
| "eval_steps_per_second": 8.659, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018244013683010263, | |
| "grad_norm": 18.90291404724121, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5266, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.027366020524515394, | |
| "grad_norm": 11.101104736328125, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.2531, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.036488027366020526, | |
| "grad_norm": 3.917557954788208, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.1085, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04561003420752566, | |
| "grad_norm": 2.785952091217041, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.1402, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05473204104903079, | |
| "grad_norm": 2.5528736114501953, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.0671, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06385404789053592, | |
| "grad_norm": 3.1096019744873047, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.022, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07297605473204105, | |
| "grad_norm": 4.098336696624756, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.9843, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08209806157354618, | |
| "grad_norm": 4.202548027038574, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.0921, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09122006841505131, | |
| "grad_norm": 3.1605403423309326, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.0352, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10034207525655645, | |
| "grad_norm": 2.562784194946289, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.0455, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10946408209806158, | |
| "grad_norm": 2.120959520339966, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.0248, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11858608893956671, | |
| "grad_norm": 1.7797281742095947, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.3069, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12770809578107184, | |
| "grad_norm": 1.5691810846328735, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.4204, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13683010262257697, | |
| "grad_norm": 1.2062739133834839, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.5388, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1459521094640821, | |
| "grad_norm": 0.7961310744285583, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.4491, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.15507411630558723, | |
| "grad_norm": 0.7442319393157959, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.5383, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16419612314709237, | |
| "grad_norm": 0.6347817778587341, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.5935, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1733181299885975, | |
| "grad_norm": 0.6833974719047546, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.5712, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18244013683010263, | |
| "grad_norm": 0.9213839173316956, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.5696, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19156214367160776, | |
| "grad_norm": 1.3780533075332642, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.6993, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2006841505131129, | |
| "grad_norm": 1.2376089096069336, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.6858, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20980615735461802, | |
| "grad_norm": 1.1128700971603394, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.6236, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21892816419612315, | |
| "grad_norm": 1.1550122499465942, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.6805, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22805017103762829, | |
| "grad_norm": 1.4760537147521973, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.7456, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22805017103762829, | |
| "eval_loss": 1.4106637239456177, | |
| "eval_runtime": 1.0204, | |
| "eval_samples_per_second": 49.001, | |
| "eval_steps_per_second": 12.74, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23717217787913342, | |
| "grad_norm": 0.9181596040725708, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.1175, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24629418472063855, | |
| "grad_norm": 0.6287382245063782, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.3472, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2554161915621437, | |
| "grad_norm": 0.8954634666442871, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.382, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2645381984036488, | |
| "grad_norm": 0.5583573579788208, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.4087, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.27366020524515394, | |
| "grad_norm": 0.7373714447021484, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.4713, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28278221208665905, | |
| "grad_norm": 0.46830883622169495, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.4206, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2919042189281642, | |
| "grad_norm": 0.445218950510025, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.4428, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3010262257696693, | |
| "grad_norm": 0.5559998750686646, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.5217, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.31014823261117447, | |
| "grad_norm": 0.6704520583152771, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.4832, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.31927023945267957, | |
| "grad_norm": 0.9207093715667725, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.5879, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32839224629418473, | |
| "grad_norm": 0.606840193271637, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.5241, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.33751425313568983, | |
| "grad_norm": 1.1559696197509766, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.5729, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.346636259977195, | |
| "grad_norm": 0.6878672242164612, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.0944, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3557582668187001, | |
| "grad_norm": 0.4424948990345001, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.2331, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.36488027366020526, | |
| "grad_norm": 0.46379706263542175, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.4107, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.37400228050171036, | |
| "grad_norm": 0.5940743088722229, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.3661, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3831242873432155, | |
| "grad_norm": 0.5553629994392395, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.4202, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3922462941847206, | |
| "grad_norm": 0.40024417638778687, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.3746, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4013683010262258, | |
| "grad_norm": 0.4371756613254547, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.4586, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4104903078677309, | |
| "grad_norm": 0.49693790078163147, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.444, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.41961231470923605, | |
| "grad_norm": 0.463955819606781, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.5353, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.42873432155074115, | |
| "grad_norm": 0.496754914522171, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.4412, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4378563283922463, | |
| "grad_norm": 0.680721640586853, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.5626, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4469783352337514, | |
| "grad_norm": 0.5851555466651917, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.5285, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.45610034207525657, | |
| "grad_norm": 1.3343528509140015, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6886, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.45610034207525657, | |
| "eval_loss": 1.3095707893371582, | |
| "eval_runtime": 1.0162, | |
| "eval_samples_per_second": 49.203, | |
| "eval_steps_per_second": 12.793, | |
| "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": 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": 8.368021483552768e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |