| { | |
| "best_metric": 1.7249575853347778, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.44543429844098, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008908685968819599, | |
| "grad_norm": 0.18826083838939667, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7415, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008908685968819599, | |
| "eval_loss": 3.07926607131958, | |
| "eval_runtime": 2.5246, | |
| "eval_samples_per_second": 19.805, | |
| "eval_steps_per_second": 5.149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017817371937639197, | |
| "grad_norm": 0.30603915452957153, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9616, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026726057906458798, | |
| "grad_norm": 0.3610508143901825, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.9984, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.035634743875278395, | |
| "grad_norm": 0.5573158860206604, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.163, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.044543429844097995, | |
| "grad_norm": 0.9881311058998108, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.1831, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.053452115812917596, | |
| "grad_norm": 0.839901864528656, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.1902, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.062360801781737196, | |
| "grad_norm": 0.8552520871162415, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.2376, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07126948775055679, | |
| "grad_norm": 1.0646421909332275, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.0431, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0801781737193764, | |
| "grad_norm": 1.5686012506484985, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.0651, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08908685968819599, | |
| "grad_norm": 1.91693115234375, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.0978, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09799554565701558, | |
| "grad_norm": 3.682119131088257, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.1288, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10690423162583519, | |
| "grad_norm": 5.470436096191406, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.476, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11581291759465479, | |
| "grad_norm": 1.755882740020752, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.8697, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12472160356347439, | |
| "grad_norm": 1.9602175951004028, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.8315, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.133630289532294, | |
| "grad_norm": 2.1201233863830566, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.9269, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14253897550111358, | |
| "grad_norm": 1.8778671026229858, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.9353, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1514476614699332, | |
| "grad_norm": 0.6909071803092957, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.0847, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1603563474387528, | |
| "grad_norm": 0.7083975672721863, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.9698, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16926503340757237, | |
| "grad_norm": 1.3670889139175415, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.0225, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17817371937639198, | |
| "grad_norm": 1.6945067644119263, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.9598, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1870824053452116, | |
| "grad_norm": 1.9324032068252563, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.8524, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19599109131403117, | |
| "grad_norm": 2.111894130706787, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.7163, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20489977728285078, | |
| "grad_norm": 3.049858570098877, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.8995, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21380846325167038, | |
| "grad_norm": 2.9982028007507324, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.5006, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22271714922049, | |
| "grad_norm": 12.080316543579102, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.64, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22271714922049, | |
| "eval_loss": 1.8580714464187622, | |
| "eval_runtime": 1.3464, | |
| "eval_samples_per_second": 37.135, | |
| "eval_steps_per_second": 9.655, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23162583518930957, | |
| "grad_norm": 0.41025131940841675, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.5984, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24053452115812918, | |
| "grad_norm": 0.8294768333435059, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.694, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24944320712694878, | |
| "grad_norm": 0.9431820511817932, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.9993, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2583518930957684, | |
| "grad_norm": 1.1680399179458618, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.8814, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.267260579064588, | |
| "grad_norm": 0.865944504737854, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 1.9858, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27616926503340755, | |
| "grad_norm": 0.6460347771644592, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.0091, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28507795100222716, | |
| "grad_norm": 0.4979117810726166, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.9771, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.29398663697104677, | |
| "grad_norm": 0.4473193883895874, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.7974, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3028953229398664, | |
| "grad_norm": 0.6420344114303589, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.8387, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.311804008908686, | |
| "grad_norm": 0.9772244095802307, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.7613, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3207126948775056, | |
| "grad_norm": 1.5189650058746338, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.6827, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.32962138084632514, | |
| "grad_norm": 3.2754437923431396, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.6556, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.33853006681514475, | |
| "grad_norm": 0.333280473947525, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.6686, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.34743875278396436, | |
| "grad_norm": 0.24920018017292023, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.4806, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.35634743875278396, | |
| "grad_norm": 0.320494681596756, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.7333, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36525612472160357, | |
| "grad_norm": 0.31181883811950684, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.7869, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3741648106904232, | |
| "grad_norm": 0.2530730068683624, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 1.9439, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3830734966592428, | |
| "grad_norm": 0.29116693139076233, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 1.8799, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.39198218262806234, | |
| "grad_norm": 0.3935719132423401, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.9294, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.40089086859688194, | |
| "grad_norm": 0.3431456983089447, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.8817, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40979955456570155, | |
| "grad_norm": 0.42623868584632874, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.8161, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.41870824053452116, | |
| "grad_norm": 0.48873162269592285, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.7659, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.42761692650334077, | |
| "grad_norm": 0.7280839085578918, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.8101, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4365256124721604, | |
| "grad_norm": 1.710809350013733, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.5907, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.44543429844098, | |
| "grad_norm": 4.463897228240967, | |
| "learning_rate": 1e-05, | |
| "loss": 2.065, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.44543429844098, | |
| "eval_loss": 1.7249575853347778, | |
| "eval_runtime": 1.3575, | |
| "eval_samples_per_second": 36.832, | |
| "eval_steps_per_second": 9.576, | |
| "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": 1.0621851957775565e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |