| { | |
| "best_metric": 1.5225000381469727, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.3399915002124947, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006799830004249894, | |
| "grad_norm": 0.6069297790527344, | |
| "learning_rate": 5e-05, | |
| "loss": 1.832, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006799830004249894, | |
| "eval_loss": 2.2264111042022705, | |
| "eval_runtime": 4.6563, | |
| "eval_samples_per_second": 10.738, | |
| "eval_steps_per_second": 2.792, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013599660008499787, | |
| "grad_norm": 0.5864896178245544, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8994, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.020399490012749683, | |
| "grad_norm": 0.5557830333709717, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.8712, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027199320016999574, | |
| "grad_norm": 0.5305060148239136, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.7959, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.033999150021249466, | |
| "grad_norm": 0.7138293385505676, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.6871, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.040798980025499365, | |
| "grad_norm": 0.515021562576294, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.5862, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04759881002974926, | |
| "grad_norm": 0.4679142236709595, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.6153, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05439864003399915, | |
| "grad_norm": 0.5950599908828735, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.6585, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06119847003824904, | |
| "grad_norm": 0.6498391628265381, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.6453, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06799830004249893, | |
| "grad_norm": 0.6871522665023804, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.75, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07479813004674883, | |
| "grad_norm": 0.729438304901123, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.7807, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08159796005099873, | |
| "grad_norm": 0.9872363805770874, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.7717, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08839779005524862, | |
| "grad_norm": 0.6045026779174805, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.6279, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09519762005949851, | |
| "grad_norm": 0.4743182361125946, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6571, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10199745006374841, | |
| "grad_norm": 0.4291192591190338, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.6561, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1087972800679983, | |
| "grad_norm": 0.44301918148994446, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.4419, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1155971100722482, | |
| "grad_norm": 0.3981197476387024, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.4868, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12239694007649808, | |
| "grad_norm": 0.3518918752670288, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.4214, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12919677008074798, | |
| "grad_norm": 0.33067092299461365, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.4134, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13599660008499787, | |
| "grad_norm": 0.35203248262405396, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.3739, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14279643008924778, | |
| "grad_norm": 0.36580803990364075, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.4184, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14959626009349766, | |
| "grad_norm": 0.42581117153167725, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.4493, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15639609009774755, | |
| "grad_norm": 0.45482969284057617, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.5233, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16319592010199746, | |
| "grad_norm": 0.6383174061775208, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.6185, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16999575010624735, | |
| "grad_norm": 1.0003234148025513, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.8125, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16999575010624735, | |
| "eval_loss": 1.6187020540237427, | |
| "eval_runtime": 4.909, | |
| "eval_samples_per_second": 10.185, | |
| "eval_steps_per_second": 2.648, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17679558011049723, | |
| "grad_norm": 0.41425418853759766, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.5504, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.18359541011474714, | |
| "grad_norm": 0.39358168840408325, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.5128, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19039524011899703, | |
| "grad_norm": 0.3743652105331421, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.5086, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1971950701232469, | |
| "grad_norm": 0.29533228278160095, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.4098, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20399490012749683, | |
| "grad_norm": 0.3027362525463104, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.3184, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2107947301317467, | |
| "grad_norm": 0.3000122606754303, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.234, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2175945601359966, | |
| "grad_norm": 0.29423949122428894, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.3064, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22439439014024648, | |
| "grad_norm": 0.3147090673446655, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.3182, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2311942201444964, | |
| "grad_norm": 0.3395575284957886, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.4098, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23799405014874628, | |
| "grad_norm": 0.41077926754951477, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.3439, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.24479388015299616, | |
| "grad_norm": 0.46304410696029663, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.5453, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2515937101572461, | |
| "grad_norm": 0.6503234505653381, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.5968, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.25839354016149596, | |
| "grad_norm": 0.3714839816093445, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.523, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.26519337016574585, | |
| "grad_norm": 0.2543235719203949, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.5445, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.27199320016999573, | |
| "grad_norm": 0.2596566081047058, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.5307, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27879303017424567, | |
| "grad_norm": 0.2656037509441376, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.4163, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.28559286017849556, | |
| "grad_norm": 0.24982349574565887, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3385, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.29239269018274544, | |
| "grad_norm": 0.24610008299350739, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.2552, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2991925201869953, | |
| "grad_norm": 0.2621634602546692, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2534, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3059923501912452, | |
| "grad_norm": 0.2883884012699127, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.2217, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3127921801954951, | |
| "grad_norm": 0.31969720125198364, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.2927, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.319592010199745, | |
| "grad_norm": 0.3438730239868164, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.4063, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3263918402039949, | |
| "grad_norm": 0.420473575592041, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.4759, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3331916702082448, | |
| "grad_norm": 0.5387545824050903, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.5752, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3399915002124947, | |
| "grad_norm": 0.875813901424408, | |
| "learning_rate": 1e-05, | |
| "loss": 1.7165, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3399915002124947, | |
| "eval_loss": 1.5225000381469727, | |
| "eval_runtime": 4.9, | |
| "eval_samples_per_second": 10.204, | |
| "eval_steps_per_second": 2.653, | |
| "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": 5.513049055124521e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |