| { | |
| "best_metric": 2.7797110080718994, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.9096077316657192, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018192154633314382, | |
| "grad_norm": 1.3784114122390747, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018192154633314382, | |
| "eval_loss": 3.853982448577881, | |
| "eval_runtime": 24.4677, | |
| "eval_samples_per_second": 2.044, | |
| "eval_steps_per_second": 2.044, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.036384309266628764, | |
| "grad_norm": 1.8491235971450806, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7979, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.054576463899943146, | |
| "grad_norm": 1.8634520769119263, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.6402, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07276861853325753, | |
| "grad_norm": 1.8880945444107056, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.5581, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09096077316657192, | |
| "grad_norm": 1.8060595989227295, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.4714, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10915292779988629, | |
| "grad_norm": 1.7226263284683228, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.3249, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1273450824332007, | |
| "grad_norm": 1.5638408660888672, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.2999, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14553723706651506, | |
| "grad_norm": 1.3382917642593384, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.3125, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.16372939169982945, | |
| "grad_norm": 1.4067829847335815, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 3.321, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18192154633314384, | |
| "grad_norm": 1.416619896888733, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.2242, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.20011370096645822, | |
| "grad_norm": 1.5895527601242065, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.3318, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.21830585559977259, | |
| "grad_norm": 1.6364977359771729, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.282, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.23649801023308697, | |
| "grad_norm": 1.7518558502197266, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.4948, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2546901648664014, | |
| "grad_norm": 0.9145893454551697, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.9504, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.27288231949971575, | |
| "grad_norm": 0.8769288063049316, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.9157, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2910744741330301, | |
| "grad_norm": 0.9550091028213501, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 2.8564, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.30926662876634453, | |
| "grad_norm": 0.9505354762077332, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.0263, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3274587833996589, | |
| "grad_norm": 0.9421805739402771, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.9063, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.34565093803297325, | |
| "grad_norm": 1.0061366558074951, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.0103, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.36384309266628767, | |
| "grad_norm": 1.1248557567596436, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.0336, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.38203524729960203, | |
| "grad_norm": 0.9607459306716919, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.8884, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.40022740193291645, | |
| "grad_norm": 1.0829633474349976, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.0463, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.4184195565662308, | |
| "grad_norm": 1.0684621334075928, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.9154, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.43661171119954517, | |
| "grad_norm": 1.1708316802978516, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 2.8696, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4548038658328596, | |
| "grad_norm": 1.249573826789856, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.0593, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4548038658328596, | |
| "eval_loss": 2.8358163833618164, | |
| "eval_runtime": 24.5293, | |
| "eval_samples_per_second": 2.038, | |
| "eval_steps_per_second": 2.038, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.47299602046617395, | |
| "grad_norm": 1.5048713684082031, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.0791, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.49118817509948837, | |
| "grad_norm": 0.7179594039916992, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.7134, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5093803297328028, | |
| "grad_norm": 0.829193651676178, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.7442, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5275724843661171, | |
| "grad_norm": 0.8534348011016846, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.7626, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5457646389994315, | |
| "grad_norm": 0.9056811928749084, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.7227, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5639567936327459, | |
| "grad_norm": 1.0109838247299194, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.8242, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5821489482660602, | |
| "grad_norm": 1.0501476526260376, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.9651, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6003411028993746, | |
| "grad_norm": 1.0235837697982788, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 2.9603, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6185332575326891, | |
| "grad_norm": 0.9916844964027405, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.7348, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6367254121660034, | |
| "grad_norm": 1.1904057264328003, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.952, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6549175667993178, | |
| "grad_norm": 1.140678882598877, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.7728, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6731097214326321, | |
| "grad_norm": 1.5060383081436157, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 3.0226, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6913018760659465, | |
| "grad_norm": 1.3354346752166748, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.0054, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.709494030699261, | |
| "grad_norm": 1.5781848430633545, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.2393, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7276861853325753, | |
| "grad_norm": 0.771239161491394, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.7187, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7458783399658897, | |
| "grad_norm": 0.7969554662704468, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.6002, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7640704945992041, | |
| "grad_norm": 0.8249459266662598, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.6314, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7822626492325184, | |
| "grad_norm": 0.8862389326095581, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.6552, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8004548038658329, | |
| "grad_norm": 1.0187329053878784, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.8716, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8186469584991473, | |
| "grad_norm": 0.936937689781189, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.7814, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8368391131324616, | |
| "grad_norm": 0.990962564945221, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.6903, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.855031267765776, | |
| "grad_norm": 0.9852021336555481, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.6722, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8732234223990903, | |
| "grad_norm": 1.0664312839508057, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.7077, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8914155770324048, | |
| "grad_norm": 1.079053521156311, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 3.0082, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9096077316657192, | |
| "grad_norm": 1.2218210697174072, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0138, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9096077316657192, | |
| "eval_loss": 2.7797110080718994, | |
| "eval_runtime": 24.607, | |
| "eval_samples_per_second": 2.032, | |
| "eval_steps_per_second": 2.032, | |
| "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": 2.65684361674752e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |