| { | |
| "best_metric": 0.03684283792972565, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.9093078758949882, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03818615751789976, | |
| "grad_norm": 18.204166412353516, | |
| "learning_rate": 5e-05, | |
| "loss": 10.1005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03818615751789976, | |
| "eval_loss": 10.637901306152344, | |
| "eval_runtime": 1.5969, | |
| "eval_samples_per_second": 110.84, | |
| "eval_steps_per_second": 14.403, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07637231503579953, | |
| "grad_norm": 17.951631546020508, | |
| "learning_rate": 0.0001, | |
| "loss": 10.2512, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11455847255369929, | |
| "grad_norm": 17.36567497253418, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.8106, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15274463007159905, | |
| "grad_norm": 19.454853057861328, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.1351, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1909307875894988, | |
| "grad_norm": 15.515449523925781, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.8323, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.22911694510739858, | |
| "grad_norm": 14.878862380981445, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9643, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.26730310262529833, | |
| "grad_norm": 15.07313060760498, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0562, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3054892601431981, | |
| "grad_norm": 10.510856628417969, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9481, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3436754176610978, | |
| "grad_norm": 7.305045127868652, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7004, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3818615751789976, | |
| "grad_norm": 4.291569232940674, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.3932, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4200477326968974, | |
| "grad_norm": 17.4228572845459, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5181, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.45823389021479716, | |
| "grad_norm": 11.316972732543945, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.3498, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4964200477326969, | |
| "grad_norm": 3.6023671627044678, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.1702, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5346062052505967, | |
| "grad_norm": 7.567449569702148, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2549, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5727923627684964, | |
| "grad_norm": 2.988668441772461, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.2299, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6109785202863962, | |
| "grad_norm": 2.0232656002044678, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.1651, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.649164677804296, | |
| "grad_norm": 4.046605110168457, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1712, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6873508353221957, | |
| "grad_norm": 2.3642256259918213, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0926, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7255369928400954, | |
| "grad_norm": 1.0628883838653564, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0866, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7637231503579952, | |
| "grad_norm": 4.586023330688477, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1302, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.801909307875895, | |
| "grad_norm": 5.113855361938477, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1574, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8400954653937948, | |
| "grad_norm": 4.510216236114502, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0988, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8782816229116945, | |
| "grad_norm": 1.9437726736068726, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0773, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9164677804295943, | |
| "grad_norm": 2.351114511489868, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0832, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.954653937947494, | |
| "grad_norm": 0.7252147197723389, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0438, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.954653937947494, | |
| "eval_loss": 0.07827573269605637, | |
| "eval_runtime": 1.636, | |
| "eval_samples_per_second": 108.188, | |
| "eval_steps_per_second": 14.058, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9928400954653938, | |
| "grad_norm": 1.0364090204238892, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0835, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0310262529832936, | |
| "grad_norm": 17.326866149902344, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2532, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0692124105011933, | |
| "grad_norm": 6.2615647315979, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1134, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.107398568019093, | |
| "grad_norm": 3.5731632709503174, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0594, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1455847255369929, | |
| "grad_norm": 1.441209316253662, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0227, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1837708830548925, | |
| "grad_norm": 2.8011887073516846, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0682, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2219570405727924, | |
| "grad_norm": 1.7012304067611694, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0513, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.260143198090692, | |
| "grad_norm": 6.563292980194092, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1411, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2983293556085918, | |
| "grad_norm": 1.9492319822311401, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1558, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3365155131264916, | |
| "grad_norm": 3.193370819091797, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1007, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3747016706443915, | |
| "grad_norm": 6.734858989715576, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0638, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4128878281622912, | |
| "grad_norm": 6.953091621398926, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0497, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4510739856801909, | |
| "grad_norm": 3.499946117401123, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0416, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.4892601431980907, | |
| "grad_norm": 3.893627405166626, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0265, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5274463007159904, | |
| "grad_norm": 1.17046058177948, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0381, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5656324582338903, | |
| "grad_norm": 1.5724403858184814, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.064, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.60381861575179, | |
| "grad_norm": 1.290392518043518, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0385, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6420047732696896, | |
| "grad_norm": 0.47391846776008606, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.018, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6801909307875895, | |
| "grad_norm": 0.229345440864563, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0192, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7183770883054894, | |
| "grad_norm": 0.7760948538780212, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0231, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.756563245823389, | |
| "grad_norm": 2.864842414855957, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0292, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7947494033412887, | |
| "grad_norm": 3.478466033935547, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0627, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8329355608591884, | |
| "grad_norm": 1.9896175861358643, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0599, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8711217183770883, | |
| "grad_norm": 1.9609580039978027, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0331, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9093078758949882, | |
| "grad_norm": 0.23864984512329102, | |
| "learning_rate": 0.0, | |
| "loss": 0.0127, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9093078758949882, | |
| "eval_loss": 0.03684283792972565, | |
| "eval_runtime": 3.5326, | |
| "eval_samples_per_second": 50.105, | |
| "eval_steps_per_second": 6.511, | |
| "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": 7.83042868150272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |