| { | |
| "best_metric": 6.899521350860596, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0237681417769657, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000475362835539314, | |
| "grad_norm": 0.2889825105667114, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9373, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000475362835539314, | |
| "eval_loss": 6.941147327423096, | |
| "eval_runtime": 0.7116, | |
| "eval_samples_per_second": 70.261, | |
| "eval_steps_per_second": 18.268, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000950725671078628, | |
| "grad_norm": 0.2633208632469177, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9376, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014260885066179419, | |
| "grad_norm": 0.2506893277168274, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 6.9348, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001901451342157256, | |
| "grad_norm": 0.24618133902549744, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.9347, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00237681417769657, | |
| "grad_norm": 0.2463768869638443, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.9328, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028521770132358838, | |
| "grad_norm": 0.24844573438167572, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 6.931, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003327539848775198, | |
| "grad_norm": 0.23925140500068665, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 6.9312, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003802902684314512, | |
| "grad_norm": 0.22544139623641968, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 6.9295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004278265519853826, | |
| "grad_norm": 0.21495969593524933, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.9319, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00475362835539314, | |
| "grad_norm": 0.21318794786930084, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 6.9289, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0052289911909324535, | |
| "grad_norm": 0.18213364481925964, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 6.9331, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0057043540264717675, | |
| "grad_norm": 0.1623869091272354, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 6.9348, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0061797168620110815, | |
| "grad_norm": 0.34758180379867554, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 6.9202, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006655079697550396, | |
| "grad_norm": 0.3087834119796753, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 6.9181, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00713044253308971, | |
| "grad_norm": 0.2853550612926483, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 6.9149, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007605805368629024, | |
| "grad_norm": 0.2866442799568176, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 6.9145, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008081168204168338, | |
| "grad_norm": 0.2917479872703552, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 6.9145, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008556531039707651, | |
| "grad_norm": 0.2843560576438904, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.9124, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009031893875246966, | |
| "grad_norm": 0.2888680398464203, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 6.9124, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00950725671078628, | |
| "grad_norm": 0.2755052149295807, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.9115, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009982619546325594, | |
| "grad_norm": 0.26480522751808167, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 6.9125, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010457982381864907, | |
| "grad_norm": 0.25958582758903503, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 6.9121, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010933345217404222, | |
| "grad_norm": 0.2043898105621338, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 6.919, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.011408708052943535, | |
| "grad_norm": 0.17020662128925323, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 6.9238, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01188407088848285, | |
| "grad_norm": 0.24424903094768524, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 6.9246, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01188407088848285, | |
| "eval_loss": 6.912273406982422, | |
| "eval_runtime": 0.1347, | |
| "eval_samples_per_second": 371.293, | |
| "eval_steps_per_second": 96.536, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012359433724022163, | |
| "grad_norm": 0.3867284655570984, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 6.898, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012834796559561478, | |
| "grad_norm": 0.3198029398918152, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 6.9001, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013310159395100793, | |
| "grad_norm": 0.3250506520271301, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 6.8974, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013785522230640106, | |
| "grad_norm": 0.31791263818740845, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 6.8979, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01426088506617942, | |
| "grad_norm": 0.30952978134155273, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 6.8985, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014736247901718734, | |
| "grad_norm": 0.327973335981369, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 6.8955, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.015211610737258048, | |
| "grad_norm": 0.30642637610435486, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 6.899, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01568697357279736, | |
| "grad_norm": 0.28234004974365234, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 6.9003, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016162336408336676, | |
| "grad_norm": 0.2788352072238922, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 6.8998, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01663769924387599, | |
| "grad_norm": 0.2545340657234192, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 6.9029, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.017113062079415303, | |
| "grad_norm": 0.19631724059581757, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 6.9147, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.017588424914954617, | |
| "grad_norm": 0.16539086401462555, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 6.9256, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.018063787750493932, | |
| "grad_norm": 0.4138210713863373, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 6.8862, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.018539150586033247, | |
| "grad_norm": 0.3455830514431, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 6.888, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01901451342157256, | |
| "grad_norm": 0.33522090315818787, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 6.8893, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019489876257111873, | |
| "grad_norm": 0.3389662802219391, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 6.8891, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.019965239092651188, | |
| "grad_norm": 0.31411075592041016, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 6.8911, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.020440601928190503, | |
| "grad_norm": 0.3265419602394104, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 6.8892, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.020915964763729814, | |
| "grad_norm": 0.3150964379310608, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 6.8915, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02139132759926913, | |
| "grad_norm": 0.3052806556224823, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 6.891, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021866690434808444, | |
| "grad_norm": 0.2852076590061188, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 6.894, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02234205327034776, | |
| "grad_norm": 0.26825907826423645, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 6.8974, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02281741610588707, | |
| "grad_norm": 0.2242056280374527, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 6.9082, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.023292778941426385, | |
| "grad_norm": 0.17848236858844757, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 6.9157, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0237681417769657, | |
| "grad_norm": 0.28793561458587646, | |
| "learning_rate": 1e-05, | |
| "loss": 6.9226, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0237681417769657, | |
| "eval_loss": 6.899521350860596, | |
| "eval_runtime": 0.1284, | |
| "eval_samples_per_second": 389.278, | |
| "eval_steps_per_second": 101.212, | |
| "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": 6231083778048.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |