| { | |
| "best_metric": 1.5259586572647095, | |
| "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": 0.6067718267440796, | |
| "learning_rate": 5e-05, | |
| "loss": 1.832, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006799830004249894, | |
| "eval_loss": 2.2264111042022705, | |
| "eval_runtime": 4.6611, | |
| "eval_samples_per_second": 10.727, | |
| "eval_steps_per_second": 2.789, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013599660008499787, | |
| "grad_norm": 0.5895602107048035, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8994, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.020399490012749683, | |
| "grad_norm": 0.558321475982666, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.8711, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027199320016999574, | |
| "grad_norm": 0.5225681662559509, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.7962, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.033999150021249466, | |
| "grad_norm": 0.7051050066947937, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.6881, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.040798980025499365, | |
| "grad_norm": 0.5118870139122009, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.5875, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04759881002974926, | |
| "grad_norm": 0.472113698720932, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.6164, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05439864003399915, | |
| "grad_norm": 0.6019394397735596, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.6597, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06119847003824904, | |
| "grad_norm": 0.6556828022003174, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.6461, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06799830004249893, | |
| "grad_norm": 0.6972203850746155, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.7525, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07479813004674883, | |
| "grad_norm": 0.7438275218009949, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.7829, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08159796005099873, | |
| "grad_norm": 0.9848412871360779, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.7746, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08839779005524862, | |
| "grad_norm": 0.6186333298683167, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.6287, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09519762005949851, | |
| "grad_norm": 0.48741579055786133, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6574, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10199745006374841, | |
| "grad_norm": 0.429099977016449, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.6563, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1087972800679983, | |
| "grad_norm": 0.4337676465511322, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.4421, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1155971100722482, | |
| "grad_norm": 0.3974376618862152, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.4875, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12239694007649808, | |
| "grad_norm": 0.3560201823711395, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.4224, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12919677008074798, | |
| "grad_norm": 0.33195987343788147, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.4148, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.13599660008499787, | |
| "grad_norm": 0.3476126492023468, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.375, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14279643008924778, | |
| "grad_norm": 0.3612964451313019, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.4194, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.14959626009349766, | |
| "grad_norm": 0.4287199079990387, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.45, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15639609009774755, | |
| "grad_norm": 0.45417842268943787, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.5254, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16319592010199746, | |
| "grad_norm": 0.6283352971076965, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.6192, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.16999575010624735, | |
| "grad_norm": 1.0015681982040405, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.8127, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16999575010624735, | |
| "eval_loss": 1.6209921836853027, | |
| "eval_runtime": 4.9609, | |
| "eval_samples_per_second": 10.079, | |
| "eval_steps_per_second": 2.62, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17679558011049723, | |
| "grad_norm": 0.4103982448577881, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.5513, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.18359541011474714, | |
| "grad_norm": 0.3940969407558441, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.5133, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19039524011899703, | |
| "grad_norm": 0.3779045343399048, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.5095, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1971950701232469, | |
| "grad_norm": 0.2973446249961853, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.4108, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20399490012749683, | |
| "grad_norm": 0.3024841248989105, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.3195, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2107947301317467, | |
| "grad_norm": 0.30010512471199036, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.2344, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2175945601359966, | |
| "grad_norm": 0.30236589908599854, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.3064, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22439439014024648, | |
| "grad_norm": 0.3136184513568878, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.3178, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2311942201444964, | |
| "grad_norm": 0.33479824662208557, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.4102, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.23799405014874628, | |
| "grad_norm": 0.4079354703426361, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.3445, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.24479388015299616, | |
| "grad_norm": 0.45617911219596863, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.5454, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2515937101572461, | |
| "grad_norm": 0.677880048751831, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.5967, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.25839354016149596, | |
| "grad_norm": 0.3763822317123413, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.5233, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.26519337016574585, | |
| "grad_norm": 0.25510433316230774, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.5443, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.27199320016999573, | |
| "grad_norm": 0.2586897611618042, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.5314, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27879303017424567, | |
| "grad_norm": 0.2617841958999634, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.4165, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.28559286017849556, | |
| "grad_norm": 0.24825793504714966, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.3391, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.29239269018274544, | |
| "grad_norm": 0.24704131484031677, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.2556, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2991925201869953, | |
| "grad_norm": 0.2630559206008911, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.2538, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3059923501912452, | |
| "grad_norm": 0.28859418630599976, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.2219, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3127921801954951, | |
| "grad_norm": 0.32302361726760864, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.2928, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.319592010199745, | |
| "grad_norm": 0.34231433272361755, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.4075, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3263918402039949, | |
| "grad_norm": 0.4183900058269501, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.476, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3331916702082448, | |
| "grad_norm": 0.5364781022071838, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.5752, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3399915002124947, | |
| "grad_norm": 0.8765597343444824, | |
| "learning_rate": 1e-05, | |
| "loss": 1.7162, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3399915002124947, | |
| "eval_loss": 1.5259586572647095, | |
| "eval_runtime": 5.0112, | |
| "eval_samples_per_second": 9.978, | |
| "eval_steps_per_second": 2.594, | |
| "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 | |
| } | |