{ "best_metric": 0.9084668755531311, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.6717044500419815, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01343408900083963, "grad_norm": 0.8177830576896667, "learning_rate": 5e-05, "loss": 1.1135, "step": 1 }, { "epoch": 0.01343408900083963, "eval_loss": 1.183107852935791, "eval_runtime": 1.2488, "eval_samples_per_second": 40.037, "eval_steps_per_second": 10.41, "step": 1 }, { "epoch": 0.02686817800167926, "grad_norm": 0.9810848236083984, "learning_rate": 0.0001, "loss": 1.1578, "step": 2 }, { "epoch": 0.04030226700251889, "grad_norm": 0.8007834553718567, "learning_rate": 9.990365154573717e-05, "loss": 1.1187, "step": 3 }, { "epoch": 0.05373635600335852, "grad_norm": 0.7766106724739075, "learning_rate": 9.961501876182148e-05, "loss": 1.0517, "step": 4 }, { "epoch": 0.06717044500419815, "grad_norm": 0.7464326620101929, "learning_rate": 9.913533761814537e-05, "loss": 1.0337, "step": 5 }, { "epoch": 0.08060453400503778, "grad_norm": 0.7660011649131775, "learning_rate": 9.846666218300807e-05, "loss": 1.0099, "step": 6 }, { "epoch": 0.09403862300587741, "grad_norm": 0.5880798101425171, "learning_rate": 9.761185582727977e-05, "loss": 0.995, "step": 7 }, { "epoch": 0.10747271200671704, "grad_norm": 0.5018829107284546, "learning_rate": 9.657457896300791e-05, "loss": 0.9742, "step": 8 }, { "epoch": 0.12090680100755667, "grad_norm": 0.40732744336128235, "learning_rate": 9.535927336897098e-05, "loss": 0.9342, "step": 9 }, { "epoch": 0.1343408900083963, "grad_norm": 0.3656207323074341, "learning_rate": 9.397114317029975e-05, "loss": 0.9605, "step": 10 }, { "epoch": 0.14777497900923595, "grad_norm": 0.3609546422958374, "learning_rate": 9.241613255361455e-05, "loss": 0.9203, "step": 11 }, { "epoch": 0.16120906801007556, "grad_norm": 0.3753810524940491, "learning_rate": 9.070090031310558e-05, "loss": 0.9331, "step": 12 }, { "epoch": 0.1746431570109152, "grad_norm": 0.32539620995521545, "learning_rate": 8.883279133655399e-05, "loss": 0.9353, "step": 13 }, { "epoch": 0.18807724601175482, "grad_norm": 0.3410118520259857, "learning_rate": 8.681980515339464e-05, "loss": 0.9557, "step": 14 }, { "epoch": 0.20151133501259447, "grad_norm": 0.2768735885620117, "learning_rate": 8.467056167950311e-05, "loss": 0.9446, "step": 15 }, { "epoch": 0.21494542401343408, "grad_norm": 0.24224700033664703, "learning_rate": 8.239426430539243e-05, "loss": 0.9245, "step": 16 }, { "epoch": 0.22837951301427373, "grad_norm": 0.26210564374923706, "learning_rate": 8.000066048588211e-05, "loss": 0.9539, "step": 17 }, { "epoch": 0.24181360201511334, "grad_norm": 0.27018633484840393, "learning_rate": 7.75e-05, "loss": 0.9509, "step": 18 }, { "epoch": 0.25524769101595296, "grad_norm": 0.2700554430484772, "learning_rate": 7.490299105985507e-05, "loss": 0.9021, "step": 19 }, { "epoch": 0.2686817800167926, "grad_norm": 0.2731901705265045, "learning_rate": 7.222075445642904e-05, "loss": 0.9273, "step": 20 }, { "epoch": 0.28211586901763225, "grad_norm": 0.25166821479797363, "learning_rate": 6.946477593864228e-05, "loss": 0.9204, "step": 21 }, { "epoch": 0.2955499580184719, "grad_norm": 0.26470544934272766, "learning_rate": 6.664685702961344e-05, "loss": 0.9469, "step": 22 }, { "epoch": 0.3089840470193115, "grad_norm": 0.2386406660079956, "learning_rate": 6.377906449072578e-05, "loss": 0.924, "step": 23 }, { "epoch": 0.3224181360201511, "grad_norm": 0.24416282773017883, "learning_rate": 6.087367864990233e-05, "loss": 0.9205, "step": 24 }, { "epoch": 0.33585222502099077, "grad_norm": 0.2733912169933319, "learning_rate": 5.794314081535644e-05, "loss": 0.9519, "step": 25 }, { "epoch": 0.33585222502099077, "eval_loss": 0.9214932918548584, "eval_runtime": 0.7466, "eval_samples_per_second": 66.968, "eval_steps_per_second": 17.412, "step": 25 }, { "epoch": 0.3492863140218304, "grad_norm": 0.2771437466144562, "learning_rate": 5.500000000000001e-05, "loss": 0.9501, "step": 26 }, { "epoch": 0.36272040302267, "grad_norm": 0.2764880955219269, "learning_rate": 5.205685918464356e-05, "loss": 0.9396, "step": 27 }, { "epoch": 0.37615449202350965, "grad_norm": 0.24223656952381134, "learning_rate": 4.912632135009769e-05, "loss": 0.9147, "step": 28 }, { "epoch": 0.3895885810243493, "grad_norm": 0.24211497604846954, "learning_rate": 4.6220935509274235e-05, "loss": 0.9259, "step": 29 }, { "epoch": 0.40302267002518893, "grad_norm": 0.22469313442707062, "learning_rate": 4.3353142970386564e-05, "loss": 0.8902, "step": 30 }, { "epoch": 0.4164567590260285, "grad_norm": 0.2251465618610382, "learning_rate": 4.053522406135775e-05, "loss": 0.9032, "step": 31 }, { "epoch": 0.42989084802686817, "grad_norm": 0.2130904495716095, "learning_rate": 3.777924554357096e-05, "loss": 0.9317, "step": 32 }, { "epoch": 0.4433249370277078, "grad_norm": 0.2265763282775879, "learning_rate": 3.509700894014496e-05, "loss": 0.8936, "step": 33 }, { "epoch": 0.45675902602854745, "grad_norm": 0.24248380959033966, "learning_rate": 3.250000000000001e-05, "loss": 0.8983, "step": 34 }, { "epoch": 0.47019311502938704, "grad_norm": 0.24923619627952576, "learning_rate": 2.9999339514117912e-05, "loss": 0.9229, "step": 35 }, { "epoch": 0.4836272040302267, "grad_norm": 0.23115158081054688, "learning_rate": 2.760573569460757e-05, "loss": 0.8954, "step": 36 }, { "epoch": 0.49706129303106633, "grad_norm": 0.255435585975647, "learning_rate": 2.53294383204969e-05, "loss": 0.8836, "step": 37 }, { "epoch": 0.5104953820319059, "grad_norm": 0.22626522183418274, "learning_rate": 2.3180194846605367e-05, "loss": 0.9098, "step": 38 }, { "epoch": 0.5239294710327456, "grad_norm": 0.20505741238594055, "learning_rate": 2.1167208663446025e-05, "loss": 0.9165, "step": 39 }, { "epoch": 0.5373635600335852, "grad_norm": 0.2080068439245224, "learning_rate": 1.9299099686894423e-05, "loss": 0.9177, "step": 40 }, { "epoch": 0.5507976490344249, "grad_norm": 0.2057790458202362, "learning_rate": 1.758386744638546e-05, "loss": 0.9319, "step": 41 }, { "epoch": 0.5642317380352645, "grad_norm": 0.20780308544635773, "learning_rate": 1.602885682970026e-05, "loss": 0.8765, "step": 42 }, { "epoch": 0.5776658270361041, "grad_norm": 0.20456816256046295, "learning_rate": 1.464072663102903e-05, "loss": 0.8815, "step": 43 }, { "epoch": 0.5910999160369438, "grad_norm": 0.20141682028770447, "learning_rate": 1.3425421036992098e-05, "loss": 0.9079, "step": 44 }, { "epoch": 0.6045340050377834, "grad_norm": 0.2008521854877472, "learning_rate": 1.2388144172720251e-05, "loss": 0.8941, "step": 45 }, { "epoch": 0.617968094038623, "grad_norm": 0.212819442152977, "learning_rate": 1.1533337816991932e-05, "loss": 0.8951, "step": 46 }, { "epoch": 0.6314021830394626, "grad_norm": 0.20845483243465424, "learning_rate": 1.0864662381854632e-05, "loss": 0.8793, "step": 47 }, { "epoch": 0.6448362720403022, "grad_norm": 0.21866247057914734, "learning_rate": 1.0384981238178534e-05, "loss": 0.9227, "step": 48 }, { "epoch": 0.6582703610411419, "grad_norm": 0.22729778289794922, "learning_rate": 1.0096348454262845e-05, "loss": 0.8741, "step": 49 }, { "epoch": 0.6717044500419815, "grad_norm": 0.2767520248889923, "learning_rate": 1e-05, "loss": 0.9384, "step": 50 }, { "epoch": 0.6717044500419815, "eval_loss": 0.9084668755531311, "eval_runtime": 0.7392, "eval_samples_per_second": 67.644, "eval_steps_per_second": 17.588, "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": 2.95300912644096e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }