| { | |
| "best_metric": 1.809238076210022, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.18518518518518517, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003703703703703704, | |
| "grad_norm": 4.116030693054199, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0241, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003703703703703704, | |
| "eval_loss": 4.521655082702637, | |
| "eval_runtime": 1.4574, | |
| "eval_samples_per_second": 34.309, | |
| "eval_steps_per_second": 8.92, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007407407407407408, | |
| "grad_norm": 4.121915340423584, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2284, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011111111111111112, | |
| "grad_norm": 4.936906337738037, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.2735, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014814814814814815, | |
| "grad_norm": 2.855342388153076, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.5536, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018518518518518517, | |
| "grad_norm": 2.5260751247406006, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.3432, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022222222222222223, | |
| "grad_norm": 2.948049783706665, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.8829, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025925925925925925, | |
| "grad_norm": 3.049560546875, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.7401, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02962962962962963, | |
| "grad_norm": 2.5307116508483887, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.5649, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03333333333333333, | |
| "grad_norm": 3.314162492752075, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.5844, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.037037037037037035, | |
| "grad_norm": 2.8759920597076416, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.3834, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.040740740740740744, | |
| "grad_norm": 1.3312515020370483, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.2634, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.044444444444444446, | |
| "grad_norm": 2.3702969551086426, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.0426, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04814814814814815, | |
| "grad_norm": 2.423916816711426, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.2698, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05185185185185185, | |
| "grad_norm": 1.5132427215576172, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.3085, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 1.1343423128128052, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.2665, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05925925925925926, | |
| "grad_norm": 1.2370033264160156, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.0012, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06296296296296296, | |
| "grad_norm": 1.340045690536499, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.1011, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06666666666666667, | |
| "grad_norm": 1.0047345161437988, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.2134, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07037037037037037, | |
| "grad_norm": 0.9375550150871277, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.0775, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 1.221209168434143, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.0637, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07777777777777778, | |
| "grad_norm": 0.9997118711471558, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.0458, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08148148148148149, | |
| "grad_norm": 0.9523096084594727, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.0679, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08518518518518518, | |
| "grad_norm": 0.9293127655982971, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.9178, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 0.7721121907234192, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.0166, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "grad_norm": 1.129605770111084, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.8354, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "eval_loss": 1.8420437574386597, | |
| "eval_runtime": 0.7521, | |
| "eval_samples_per_second": 66.48, | |
| "eval_steps_per_second": 17.285, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0962962962962963, | |
| "grad_norm": 1.1217167377471924, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.1233, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.8602536916732788, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.1363, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1037037037037037, | |
| "grad_norm": 0.8962283134460449, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.174, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10740740740740741, | |
| "grad_norm": 0.8276489973068237, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.0971, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.8067771196365356, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.0047, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11481481481481481, | |
| "grad_norm": 0.7078531980514526, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.1274, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 1.049298644065857, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.9293, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.12222222222222222, | |
| "grad_norm": 0.8572384715080261, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.8519, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1259259259259259, | |
| "grad_norm": 0.7951518297195435, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.9323, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12962962962962962, | |
| "grad_norm": 0.7671780586242676, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.8821, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 0.7220433354377747, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.8686, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.13703703703703704, | |
| "grad_norm": 0.8542306423187256, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.8169, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.14074074074074075, | |
| "grad_norm": 0.8364683985710144, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.012, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.14444444444444443, | |
| "grad_norm": 0.7114874124526978, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.0428, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.740842878818512, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.0602, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15185185185185185, | |
| "grad_norm": 0.8619032502174377, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.2465, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.15555555555555556, | |
| "grad_norm": 0.7360240817070007, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.0157, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.15925925925925927, | |
| "grad_norm": 0.6555927991867065, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.8632, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.16296296296296298, | |
| "grad_norm": 0.7459237575531006, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.0581, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.845435619354248, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.1435, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.17037037037037037, | |
| "grad_norm": 0.7518559098243713, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.0249, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.17407407407407408, | |
| "grad_norm": 0.6932052373886108, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.9508, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.6623319387435913, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.8047, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1814814814814815, | |
| "grad_norm": 0.7716500759124756, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.9208, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "grad_norm": 0.8495790362358093, | |
| "learning_rate": 1e-05, | |
| "loss": 1.764, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "eval_loss": 1.809238076210022, | |
| "eval_runtime": 0.7465, | |
| "eval_samples_per_second": 66.983, | |
| "eval_steps_per_second": 17.416, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |