| { | |
| "best_metric": 1.1204490661621094, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07942811755361398, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015885623510722795, | |
| "grad_norm": 0.8576938509941101, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5653, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015885623510722795, | |
| "eval_loss": 1.7700382471084595, | |
| "eval_runtime": 2.671, | |
| "eval_samples_per_second": 18.719, | |
| "eval_steps_per_second": 4.867, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003177124702144559, | |
| "grad_norm": 0.9243552088737488, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5262, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004765687053216839, | |
| "grad_norm": 0.9569259285926819, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.5643, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006354249404289118, | |
| "grad_norm": 0.8633149266242981, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.5359, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007942811755361398, | |
| "grad_norm": 0.8648080825805664, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.3851, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009531374106433678, | |
| "grad_norm": 0.6841714978218079, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3363, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011119936457505957, | |
| "grad_norm": 0.6894100308418274, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.3589, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012708498808578236, | |
| "grad_norm": 0.6219059824943542, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.2988, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014297061159650517, | |
| "grad_norm": 0.6542291641235352, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.2599, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015885623510722795, | |
| "grad_norm": 0.6986835598945618, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.3305, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017474185861795076, | |
| "grad_norm": 0.7146315574645996, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.3372, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.019062748212867357, | |
| "grad_norm": 0.9549993276596069, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.2227, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020651310563939634, | |
| "grad_norm": 0.8485234379768372, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.183, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.022239872915011914, | |
| "grad_norm": 0.8039460778236389, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.2449, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.023828435266084195, | |
| "grad_norm": 0.5031102895736694, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.1944, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025416997617156472, | |
| "grad_norm": 0.5859006643295288, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.1925, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.027005559968228753, | |
| "grad_norm": 0.6242632865905762, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.1986, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028594122319301033, | |
| "grad_norm": 0.5892954468727112, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2299, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.030182684670373314, | |
| "grad_norm": 0.5673774480819702, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.2748, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03177124702144559, | |
| "grad_norm": 0.42369166016578674, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.2004, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03335980937251787, | |
| "grad_norm": 0.4137592911720276, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.1957, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03494837172359015, | |
| "grad_norm": 0.4142400026321411, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.2044, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03653693407466243, | |
| "grad_norm": 0.5127531886100769, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.1488, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03812549642573471, | |
| "grad_norm": 0.5903114080429077, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.0466, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03971405877680699, | |
| "grad_norm": 0.6848862171173096, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.1485, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03971405877680699, | |
| "eval_loss": 1.1730780601501465, | |
| "eval_runtime": 2.0397, | |
| "eval_samples_per_second": 24.514, | |
| "eval_steps_per_second": 6.374, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04130262112787927, | |
| "grad_norm": 0.7173677086830139, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.1916, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04289118347895155, | |
| "grad_norm": 0.76693195104599, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.2504, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04447974583002383, | |
| "grad_norm": 0.6550216674804688, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.2569, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.046068308181096106, | |
| "grad_norm": 0.5112429857254028, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.2407, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04765687053216839, | |
| "grad_norm": 0.36219966411590576, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.1617, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04924543288324067, | |
| "grad_norm": 0.3246273100376129, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.1618, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.050833995234312944, | |
| "grad_norm": 0.3080134391784668, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.2093, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05242255758538523, | |
| "grad_norm": 0.36938804388046265, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.1696, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.054011119936457505, | |
| "grad_norm": 0.4594118893146515, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.1996, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05559968228752978, | |
| "grad_norm": 0.6706517934799194, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.154, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.057188244638602066, | |
| "grad_norm": 0.7852743864059448, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.1745, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05877680698967434, | |
| "grad_norm": 0.5067930817604065, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.9723, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06036536934074663, | |
| "grad_norm": 0.3320077955722809, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.1624, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.061953931691818905, | |
| "grad_norm": 0.23800799250602722, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.1551, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06354249404289118, | |
| "grad_norm": 0.2339501529932022, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.1591, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06513105639396347, | |
| "grad_norm": 0.24399659037590027, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.1155, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06671961874503574, | |
| "grad_norm": 0.24500925838947296, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.0994, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06830818109610802, | |
| "grad_norm": 0.27097079157829285, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.2019, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0698967434471803, | |
| "grad_norm": 0.26295530796051025, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.1541, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07148530579825259, | |
| "grad_norm": 0.2993250787258148, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.1529, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07307386814932486, | |
| "grad_norm": 0.32925310730934143, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.1371, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07466243050039714, | |
| "grad_norm": 0.32412636280059814, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.1342, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07625099285146943, | |
| "grad_norm": 0.45030054450035095, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.1043, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0778395552025417, | |
| "grad_norm": 0.43968403339385986, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.066, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07942811755361398, | |
| "grad_norm": 0.5369355082511902, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9676, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07942811755361398, | |
| "eval_loss": 1.1204490661621094, | |
| "eval_runtime": 2.0299, | |
| "eval_samples_per_second": 24.632, | |
| "eval_steps_per_second": 6.404, | |
| "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": 5.971813667564421e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |