| { | |
| "best_metric": 0.2833782136440277, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6808510638297872, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013617021276595745, | |
| "grad_norm": 36.09283447265625, | |
| "learning_rate": 5e-05, | |
| "loss": 10.0622, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013617021276595745, | |
| "eval_loss": 11.450489044189453, | |
| "eval_runtime": 1.2393, | |
| "eval_samples_per_second": 40.346, | |
| "eval_steps_per_second": 10.49, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02723404255319149, | |
| "grad_norm": 34.0181884765625, | |
| "learning_rate": 0.0001, | |
| "loss": 9.8471, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04085106382978723, | |
| "grad_norm": 26.330429077148438, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.4379, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05446808510638298, | |
| "grad_norm": 16.99547576904297, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.0363, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06808510638297872, | |
| "grad_norm": 13.660845756530762, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.5316, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08170212765957446, | |
| "grad_norm": 11.409526824951172, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.6212, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09531914893617022, | |
| "grad_norm": 8.352482795715332, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.5698, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10893617021276596, | |
| "grad_norm": 6.6505022048950195, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.1538, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1225531914893617, | |
| "grad_norm": 4.057483196258545, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.7903, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13617021276595745, | |
| "grad_norm": 4.380706787109375, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.7029, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1497872340425532, | |
| "grad_norm": 5.304778099060059, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.6185, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16340425531914893, | |
| "grad_norm": 5.661269187927246, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.5185, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.17702127659574468, | |
| "grad_norm": 8.71065616607666, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.5735, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19063829787234043, | |
| "grad_norm": 3.896979570388794, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.3239, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20425531914893616, | |
| "grad_norm": 8.72924518585205, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.531, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2178723404255319, | |
| "grad_norm": 7.908350467681885, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.5867, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23148936170212767, | |
| "grad_norm": 2.7389485836029053, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.4325, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2451063829787234, | |
| "grad_norm": 1.7867705821990967, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.4213, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.25872340425531914, | |
| "grad_norm": 2.428112030029297, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.4061, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2723404255319149, | |
| "grad_norm": 2.647061824798584, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.3546, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.28595744680851065, | |
| "grad_norm": 1.9521253108978271, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.314, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2995744680851064, | |
| "grad_norm": 2.206204414367676, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.2852, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3131914893617021, | |
| "grad_norm": 2.3123114109039307, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.2978, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.32680851063829786, | |
| "grad_norm": 2.398576259613037, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.2755, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 2.2486066818237305, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.2441, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "eval_loss": 0.5611550807952881, | |
| "eval_runtime": 1.2652, | |
| "eval_samples_per_second": 39.52, | |
| "eval_steps_per_second": 10.275, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35404255319148936, | |
| "grad_norm": 2.8560750484466553, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.2116, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3676595744680851, | |
| "grad_norm": 3.257420301437378, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.3268, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.38127659574468087, | |
| "grad_norm": 3.010044574737549, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.3178, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3948936170212766, | |
| "grad_norm": 2.024600028991699, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.1889, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4085106382978723, | |
| "grad_norm": 1.2341009378433228, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.1911, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4221276595744681, | |
| "grad_norm": 1.252215027809143, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.2421, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4357446808510638, | |
| "grad_norm": 1.4999184608459473, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.194, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4493617021276596, | |
| "grad_norm": 1.5111395120620728, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.2403, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.46297872340425533, | |
| "grad_norm": 1.3706086874008179, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.225, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4765957446808511, | |
| "grad_norm": 1.4278351068496704, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.2078, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4902127659574468, | |
| "grad_norm": 1.333633303642273, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.1474, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5038297872340426, | |
| "grad_norm": 1.118594765663147, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.1509, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5174468085106383, | |
| "grad_norm": 0.9480551481246948, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.1769, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.531063829787234, | |
| "grad_norm": 1.409814476966858, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.1691, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5446808510638298, | |
| "grad_norm": 2.1385762691497803, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.2022, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5582978723404255, | |
| "grad_norm": 1.9792088270187378, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.2006, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5719148936170213, | |
| "grad_norm": 1.943965196609497, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.193, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.585531914893617, | |
| "grad_norm": 2.0789599418640137, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.2098, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5991489361702128, | |
| "grad_norm": 1.5010707378387451, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.1491, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6127659574468085, | |
| "grad_norm": 2.0292575359344482, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.1774, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6263829787234042, | |
| "grad_norm": 1.5886896848678589, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.1914, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 2.02972674369812, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.1959, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6536170212765957, | |
| "grad_norm": 2.147615432739258, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.2052, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6672340425531915, | |
| "grad_norm": 1.4841364622116089, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.1658, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 1.6794753074645996, | |
| "learning_rate": 1e-05, | |
| "loss": 0.098, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "eval_loss": 0.2833782136440277, | |
| "eval_runtime": 1.2463, | |
| "eval_samples_per_second": 40.117, | |
| "eval_steps_per_second": 10.43, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |