| { | |
| "best_metric": 0.5923976302146912, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06441742491343909, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012883484982687816, | |
| "grad_norm": 47.613548278808594, | |
| "learning_rate": 5e-05, | |
| "loss": 60.1193, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012883484982687816, | |
| "eval_loss": 2.737609624862671, | |
| "eval_runtime": 4.1599, | |
| "eval_samples_per_second": 12.02, | |
| "eval_steps_per_second": 3.125, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025766969965375633, | |
| "grad_norm": 52.00191116333008, | |
| "learning_rate": 0.0001, | |
| "loss": 65.2752, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0038650454948063453, | |
| "grad_norm": 53.02202224731445, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 71.0087, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0051533939930751265, | |
| "grad_norm": 49.392635345458984, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 64.6277, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006441742491343909, | |
| "grad_norm": 53.78055953979492, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 63.4741, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007730090989612691, | |
| "grad_norm": 57.29056167602539, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 58.9412, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009018439487881473, | |
| "grad_norm": 53.10818862915039, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 55.5142, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010306787986150253, | |
| "grad_norm": 60.22203826904297, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 53.7236, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011595136484419035, | |
| "grad_norm": 43.83124923706055, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 49.4407, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012883484982687817, | |
| "grad_norm": 55.66758346557617, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 47.6461, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0141718334809566, | |
| "grad_norm": 93.18301391601562, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 48.988, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015460181979225381, | |
| "grad_norm": 64.65294647216797, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 47.249, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016748530477494163, | |
| "grad_norm": 64.37872314453125, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 40.3842, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018036878975762945, | |
| "grad_norm": 62.399436950683594, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 31.3045, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019325227474031724, | |
| "grad_norm": 30.31430435180664, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 32.2455, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020613575972300506, | |
| "grad_norm": 27.626392364501953, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 30.5162, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021901924470569288, | |
| "grad_norm": 26.39891242980957, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 31.7303, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02319027296883807, | |
| "grad_norm": 24.801267623901367, | |
| "learning_rate": 7.75e-05, | |
| "loss": 31.2513, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024478621467106852, | |
| "grad_norm": 24.73192596435547, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 31.0303, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025766969965375634, | |
| "grad_norm": 25.891586303710938, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 30.0861, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027055318463644416, | |
| "grad_norm": 24.747957229614258, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 29.9776, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0283436669619132, | |
| "grad_norm": 26.517791748046875, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 30.5861, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.02963201546018198, | |
| "grad_norm": 25.020784378051758, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 27.3878, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.030920363958450763, | |
| "grad_norm": 26.573110580444336, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 27.9549, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.032208712456719545, | |
| "grad_norm": 32.546878814697266, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 25.2439, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.032208712456719545, | |
| "eval_loss": 0.8477029204368591, | |
| "eval_runtime": 4.042, | |
| "eval_samples_per_second": 12.37, | |
| "eval_steps_per_second": 3.216, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03349706095498833, | |
| "grad_norm": 36.677696228027344, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 24.531, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03478540945325711, | |
| "grad_norm": 29.125059127807617, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 20.848, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03607375795152589, | |
| "grad_norm": 25.221555709838867, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 20.9429, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03736210644979467, | |
| "grad_norm": 24.186708450317383, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 21.7346, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03865045494806345, | |
| "grad_norm": 24.044862747192383, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 21.4339, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03993880344633223, | |
| "grad_norm": 24.531862258911133, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 20.8275, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04122715194460101, | |
| "grad_norm": 24.415983200073242, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 20.4433, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.042515500442869794, | |
| "grad_norm": 20.245210647583008, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 20.7097, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.043803848941138576, | |
| "grad_norm": 20.419910430908203, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 20.0465, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04509219743940736, | |
| "grad_norm": 21.229557037353516, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 19.755, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04638054593767614, | |
| "grad_norm": 24.20121955871582, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 20.3669, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04766889443594492, | |
| "grad_norm": 27.731250762939453, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 20.5599, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.048957242934213704, | |
| "grad_norm": 22.39792251586914, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 19.2265, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.050245591432482486, | |
| "grad_norm": 23.370872497558594, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 16.5371, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05153393993075127, | |
| "grad_norm": 30.893217086791992, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 17.1265, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05282228842902005, | |
| "grad_norm": 23.17006492614746, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 16.948, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05411063692728883, | |
| "grad_norm": 19.363140106201172, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 18.092, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.055398985425557615, | |
| "grad_norm": 21.08965301513672, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 18.0266, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0566873339238264, | |
| "grad_norm": 20.33384895324707, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 17.16, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05797568242209518, | |
| "grad_norm": 22.02051544189453, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 17.0887, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05926403092036396, | |
| "grad_norm": 24.07645606994629, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 16.9783, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06055237941863274, | |
| "grad_norm": 25.257797241210938, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 17.5447, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.061840727916901525, | |
| "grad_norm": 32.02328872680664, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 18.0569, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06312907641517031, | |
| "grad_norm": 27.761093139648438, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 17.8059, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06441742491343909, | |
| "grad_norm": 36.194374084472656, | |
| "learning_rate": 1e-05, | |
| "loss": 17.8447, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06441742491343909, | |
| "eval_loss": 0.5923976302146912, | |
| "eval_runtime": 4.1863, | |
| "eval_samples_per_second": 11.944, | |
| "eval_steps_per_second": 3.105, | |
| "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": 5.268143856628531e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |