| { | |
| "best_metric": 2.2648308277130127, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0167115790353241, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000334231580706482, | |
| "grad_norm": 5.496165752410889, | |
| "learning_rate": 5e-05, | |
| "loss": 31.0236, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000334231580706482, | |
| "eval_loss": 2.416963577270508, | |
| "eval_runtime": 4.6942, | |
| "eval_samples_per_second": 10.651, | |
| "eval_steps_per_second": 2.769, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000668463161412964, | |
| "grad_norm": 8.403727531433105, | |
| "learning_rate": 0.0001, | |
| "loss": 32.6935, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001002694742119446, | |
| "grad_norm": 6.8086442947387695, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 33.4726, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001336926322825928, | |
| "grad_norm": 6.322213649749756, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 34.4679, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00167115790353241, | |
| "grad_norm": 9.177667617797852, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 33.4588, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002005389484238892, | |
| "grad_norm": 9.946578979492188, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 33.4397, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0023396210649453742, | |
| "grad_norm": 9.198806762695312, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 34.1534, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002673852645651856, | |
| "grad_norm": 19.019378662109375, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 34.8272, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003008084226358338, | |
| "grad_norm": 14.353171348571777, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 35.0351, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00334231580706482, | |
| "grad_norm": 15.570418357849121, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 38.1495, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003676547387771302, | |
| "grad_norm": 16.995012283325195, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 37.8086, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004010778968477784, | |
| "grad_norm": 20.282392501831055, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 40.2625, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004345010549184266, | |
| "grad_norm": 18.340831756591797, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 39.0408, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0046792421298907485, | |
| "grad_norm": 9.529115676879883, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 34.0686, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00501347371059723, | |
| "grad_norm": 10.36082649230957, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 34.1487, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005347705291303712, | |
| "grad_norm": 11.908557891845703, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 33.2204, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005681936872010194, | |
| "grad_norm": 8.402276039123535, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 33.5902, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006016168452716676, | |
| "grad_norm": 8.26902961730957, | |
| "learning_rate": 7.75e-05, | |
| "loss": 33.4582, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006350400033423158, | |
| "grad_norm": 9.017067909240723, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 34.3777, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00668463161412964, | |
| "grad_norm": 8.824953079223633, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 32.7606, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007018863194836122, | |
| "grad_norm": 9.761025428771973, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 35.2556, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007353094775542604, | |
| "grad_norm": 11.351914405822754, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 36.7428, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007687326356249086, | |
| "grad_norm": 17.06279182434082, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 36.5333, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008021557936955567, | |
| "grad_norm": 18.976041793823242, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 40.7233, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00835578951766205, | |
| "grad_norm": 22.932994842529297, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 44.8268, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00835578951766205, | |
| "eval_loss": 2.2737886905670166, | |
| "eval_runtime": 4.7443, | |
| "eval_samples_per_second": 10.539, | |
| "eval_steps_per_second": 2.74, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008690021098368531, | |
| "grad_norm": 4.368255615234375, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 32.8048, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.009024252679075015, | |
| "grad_norm": 5.049758434295654, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 33.632, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009358484259781497, | |
| "grad_norm": 5.552004337310791, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 33.4633, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009692715840487979, | |
| "grad_norm": 6.246798038482666, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 31.611, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01002694742119446, | |
| "grad_norm": 5.866751670837402, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 32.8603, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010361179001900943, | |
| "grad_norm": 7.1694865226745605, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 33.6185, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.010695410582607425, | |
| "grad_norm": 7.402153491973877, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 33.4369, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.011029642163313907, | |
| "grad_norm": 7.939614772796631, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 34.4956, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.011363873744020389, | |
| "grad_norm": 9.427316665649414, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 35.5888, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01169810532472687, | |
| "grad_norm": 11.526426315307617, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 34.8295, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.012032336905433353, | |
| "grad_norm": 15.830511093139648, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 38.0113, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.012366568486139835, | |
| "grad_norm": 16.048410415649414, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 41.1285, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.012700800066846317, | |
| "grad_norm": 17.221982955932617, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 40.34, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.013035031647552799, | |
| "grad_norm": 3.4482598304748535, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 32.6562, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01336926322825928, | |
| "grad_norm": 4.213986873626709, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 33.9774, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013703494808965763, | |
| "grad_norm": 4.579893589019775, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 32.5801, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.014037726389672244, | |
| "grad_norm": 5.420438289642334, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 31.9658, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.014371957970378726, | |
| "grad_norm": 6.065475940704346, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 34.2332, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.014706189551085208, | |
| "grad_norm": 6.8349080085754395, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 32.6066, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.01504042113179169, | |
| "grad_norm": 7.83049201965332, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 33.1971, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.015374652712498172, | |
| "grad_norm": 9.868491172790527, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 33.5423, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.015708884293204654, | |
| "grad_norm": 10.248172760009766, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 35.64, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.016043115873911135, | |
| "grad_norm": 12.959470748901367, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 36.4588, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01637734745461762, | |
| "grad_norm": 14.926746368408203, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 38.2075, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0167115790353241, | |
| "grad_norm": 21.086666107177734, | |
| "learning_rate": 1e-05, | |
| "loss": 45.6951, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0167115790353241, | |
| "eval_loss": 2.2648308277130127, | |
| "eval_runtime": 4.7822, | |
| "eval_samples_per_second": 10.455, | |
| "eval_steps_per_second": 2.718, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |