| { | |
| "best_metric": 0.16976743936538696, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4429678848283499, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008859357696566999, | |
| "grad_norm": 0.26701509952545166, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4372, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008859357696566999, | |
| "eval_loss": 0.7574589848518372, | |
| "eval_runtime": 8.6807, | |
| "eval_samples_per_second": 87.665, | |
| "eval_steps_per_second": 11.059, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017718715393133997, | |
| "grad_norm": 0.33556580543518066, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5025, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026578073089700997, | |
| "grad_norm": 0.34542733430862427, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.5014, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.035437430786267994, | |
| "grad_norm": 0.3709663450717926, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.4774, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.044296788482835, | |
| "grad_norm": 0.4700615704059601, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.4953, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 0.4017373025417328, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.4265, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06201550387596899, | |
| "grad_norm": 0.36468979716300964, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.4036, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07087486157253599, | |
| "grad_norm": 0.3217746913433075, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3646, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07973421926910298, | |
| "grad_norm": 0.442488431930542, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.4004, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08859357696567, | |
| "grad_norm": 0.5189948678016663, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.3696, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09745293466223699, | |
| "grad_norm": 0.6615598201751709, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.3726, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10631229235880399, | |
| "grad_norm": 0.5893646478652954, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.3483, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11517165005537099, | |
| "grad_norm": 0.2828221023082733, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.2823, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12403100775193798, | |
| "grad_norm": 0.2135816216468811, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2338, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.132890365448505, | |
| "grad_norm": 0.23487742245197296, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.2048, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14174972314507198, | |
| "grad_norm": 0.25205743312835693, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2285, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.150609080841639, | |
| "grad_norm": 0.2694821059703827, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2289, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15946843853820597, | |
| "grad_norm": 0.24723684787750244, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.2372, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16832779623477298, | |
| "grad_norm": 0.2388889044523239, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.1972, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17718715393134, | |
| "grad_norm": 0.2475564330816269, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1926, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18604651162790697, | |
| "grad_norm": 0.2660873830318451, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.1988, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19490586932447398, | |
| "grad_norm": 0.23354309797286987, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.1854, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20376522702104097, | |
| "grad_norm": 0.29445981979370117, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1813, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21262458471760798, | |
| "grad_norm": 0.26251375675201416, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1612, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22148394241417496, | |
| "grad_norm": 0.8390752077102661, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3283, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22148394241417496, | |
| "eval_loss": 0.2014174461364746, | |
| "eval_runtime": 8.6745, | |
| "eval_samples_per_second": 87.728, | |
| "eval_steps_per_second": 11.067, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23034330011074197, | |
| "grad_norm": 0.22343534231185913, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1952, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23920265780730898, | |
| "grad_norm": 0.19105540215969086, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.173, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24806201550387597, | |
| "grad_norm": 0.17523346841335297, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.1682, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.25692137320044295, | |
| "grad_norm": 0.20423345267772675, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1695, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.26578073089701, | |
| "grad_norm": 0.18141619861125946, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1611, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27464008859357697, | |
| "grad_norm": 0.20421284437179565, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.155, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28349944629014395, | |
| "grad_norm": 0.21378573775291443, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.17, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.292358803986711, | |
| "grad_norm": 0.2366197109222412, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1752, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.301218161683278, | |
| "grad_norm": 0.22274832427501678, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.1512, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 0.23347826302051544, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1566, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.31893687707641194, | |
| "grad_norm": 0.272474080324173, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1339, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.327796234772979, | |
| "grad_norm": 0.3316216766834259, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1746, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.33665559246954596, | |
| "grad_norm": 0.1879485845565796, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1864, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.34551495016611294, | |
| "grad_norm": 0.1565822809934616, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.1537, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.35437430786268, | |
| "grad_norm": 0.16383326053619385, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1537, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36323366555924697, | |
| "grad_norm": 0.15877383947372437, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1608, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 0.17451423406600952, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.17, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 0.17804326117038727, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1566, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.38981173864894797, | |
| "grad_norm": 0.1988825649023056, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1517, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.39867109634551495, | |
| "grad_norm": 0.1755303293466568, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1322, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40753045404208194, | |
| "grad_norm": 0.20757441222667694, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1638, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.416389811738649, | |
| "grad_norm": 0.2278241515159607, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1578, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.42524916943521596, | |
| "grad_norm": 0.23360906541347504, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.151, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.43410852713178294, | |
| "grad_norm": 0.2692311406135559, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.17, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4429678848283499, | |
| "grad_norm": 0.5288310050964355, | |
| "learning_rate": 0.0, | |
| "loss": 0.2595, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4429678848283499, | |
| "eval_loss": 0.16976743936538696, | |
| "eval_runtime": 8.6765, | |
| "eval_samples_per_second": 87.709, | |
| "eval_steps_per_second": 11.064, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |