| { | |
| "best_metric": 0.9392607808113098, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1943410275502606, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023827252419955324, | |
| "grad_norm": 0.5301724076271057, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8503, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023827252419955324, | |
| "eval_loss": 1.869744062423706, | |
| "eval_runtime": 3.9299, | |
| "eval_samples_per_second": 12.723, | |
| "eval_steps_per_second": 3.308, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04765450483991065, | |
| "grad_norm": 0.6033576130867004, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8216, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07148175725986597, | |
| "grad_norm": 0.6661578416824341, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.7577, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0953090096798213, | |
| "grad_norm": 1.927734375, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.583, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11913626209977662, | |
| "grad_norm": 0.8361942768096924, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.3356, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14296351451973194, | |
| "grad_norm": 0.8832393288612366, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.1745, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.16679076693968728, | |
| "grad_norm": 0.6611458659172058, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.1152, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1906180193596426, | |
| "grad_norm": 0.4512140154838562, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0633, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2144452717795979, | |
| "grad_norm": 0.43131425976753235, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.8673, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.23827252419955325, | |
| "grad_norm": 0.6786872148513794, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.9355, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26209977661950856, | |
| "grad_norm": 1.4149280786514282, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.6414, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2859270290394639, | |
| "grad_norm": 1.0948524475097656, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.4557, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3097542814594192, | |
| "grad_norm": 0.6199193596839905, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.2544, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.33358153387937456, | |
| "grad_norm": 0.4825551509857178, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.1293, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3574087862993299, | |
| "grad_norm": 0.48133859038352966, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.0348, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3812360387192852, | |
| "grad_norm": 0.4450385272502899, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.8606, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4050632911392405, | |
| "grad_norm": 0.4208439290523529, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.9032, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4288905435591958, | |
| "grad_norm": 0.3791106939315796, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.8922, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4527177959791511, | |
| "grad_norm": 0.39627334475517273, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.9247, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4765450483991065, | |
| "grad_norm": 0.37859562039375305, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.708, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5003723008190618, | |
| "grad_norm": 0.5165320038795471, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.382, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5241995532390171, | |
| "grad_norm": 0.6610217690467834, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.4692, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5480268056589724, | |
| "grad_norm": 0.5120995044708252, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.3404, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5718540580789278, | |
| "grad_norm": 0.3750569820404053, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.1033, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5956813104988831, | |
| "grad_norm": 0.3585754632949829, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.9403, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5956813104988831, | |
| "eval_loss": 1.0111019611358643, | |
| "eval_runtime": 3.9918, | |
| "eval_samples_per_second": 12.526, | |
| "eval_steps_per_second": 3.257, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6195085629188384, | |
| "grad_norm": 0.4272650480270386, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.8835, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6433358153387937, | |
| "grad_norm": 0.4884018003940582, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.8979, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6671630677587491, | |
| "grad_norm": 0.4665274918079376, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.8445, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6909903201787044, | |
| "grad_norm": 0.47663161158561707, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.822, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7148175725986597, | |
| "grad_norm": 0.4935821294784546, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.7297, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7386448250186151, | |
| "grad_norm": 0.3330288231372833, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.1636, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7624720774385704, | |
| "grad_norm": 0.39705488085746765, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.4158, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7862993298585257, | |
| "grad_norm": 0.41890138387680054, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.2318, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.810126582278481, | |
| "grad_norm": 0.4597773551940918, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.0762, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8339538346984363, | |
| "grad_norm": 0.4643116891384125, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.9961, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8577810871183916, | |
| "grad_norm": 0.38791903853416443, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.8689, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8816083395383469, | |
| "grad_norm": 0.39262112975120544, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.8219, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9054355919583023, | |
| "grad_norm": 0.35502174496650696, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.8349, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9292628443782577, | |
| "grad_norm": 0.3888930678367615, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.9012, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.953090096798213, | |
| "grad_norm": 0.3541257381439209, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.7204, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9769173492181683, | |
| "grad_norm": 0.6055673360824585, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.6248, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.003723008190618, | |
| "grad_norm": 0.3594631552696228, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.4831, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0275502606105733, | |
| "grad_norm": 0.31771546602249146, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.3284, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.0513775130305287, | |
| "grad_norm": 0.3231451213359833, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.1876, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.075204765450484, | |
| "grad_norm": 0.29634058475494385, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.1231, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0990320178704394, | |
| "grad_norm": 0.27380484342575073, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.8992, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1228592702903946, | |
| "grad_norm": 0.32522863149642944, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.7892, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.14668652271035, | |
| "grad_norm": 0.3326983153820038, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.8262, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.1705137751303052, | |
| "grad_norm": 0.32248544692993164, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.8126, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1943410275502606, | |
| "grad_norm": 0.3252665102481842, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7998, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1943410275502606, | |
| "eval_loss": 0.9392607808113098, | |
| "eval_runtime": 3.9593, | |
| "eval_samples_per_second": 12.628, | |
| "eval_steps_per_second": 3.283, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |