| { | |
| "best_metric": 3.218653678894043, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1983635011157947, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003967270022315894, | |
| "grad_norm": 0.8384901881217957, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4866, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003967270022315894, | |
| "eval_loss": 3.7426881790161133, | |
| "eval_runtime": 11.5378, | |
| "eval_samples_per_second": 147.255, | |
| "eval_steps_per_second": 18.461, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007934540044631788, | |
| "grad_norm": 0.8666318655014038, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4657, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011901810066947682, | |
| "grad_norm": 0.9170944690704346, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.54, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015869080089263576, | |
| "grad_norm": 0.7768110632896423, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.4557, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01983635011157947, | |
| "grad_norm": 0.8774210810661316, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.5275, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.023803620133895365, | |
| "grad_norm": 0.9877316951751709, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.5123, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02777089015621126, | |
| "grad_norm": 0.9963244199752808, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.5656, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03173816017852715, | |
| "grad_norm": 1.0385092496871948, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.4515, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03570543020084305, | |
| "grad_norm": 1.0765231847763062, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.479, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03967270022315894, | |
| "grad_norm": 1.140158772468567, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.5338, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.043639970245474835, | |
| "grad_norm": 1.110844612121582, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.5084, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04760724026779073, | |
| "grad_norm": 1.2204970121383667, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.4684, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05157451029010662, | |
| "grad_norm": 1.1391159296035767, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.4127, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05554178031242252, | |
| "grad_norm": 1.0791676044464111, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.3018, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05950905033473841, | |
| "grad_norm": 1.1504735946655273, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.3335, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0634763203570543, | |
| "grad_norm": 0.8548083901405334, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.2564, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0674435903793702, | |
| "grad_norm": 0.7931250333786011, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.3037, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0714108604016861, | |
| "grad_norm": 0.9208283424377441, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.3395, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07537813042400199, | |
| "grad_norm": 0.918303906917572, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.2767, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07934540044631788, | |
| "grad_norm": 1.0649625062942505, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.2903, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08331267046863378, | |
| "grad_norm": 1.2601035833358765, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.4656, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08727994049094967, | |
| "grad_norm": 1.17075777053833, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.344, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09124721051326556, | |
| "grad_norm": 1.0512211322784424, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.3148, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09521448053558146, | |
| "grad_norm": 1.053127408027649, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.22, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09918175055789735, | |
| "grad_norm": 1.2787140607833862, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.2812, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09918175055789735, | |
| "eval_loss": 3.267822504043579, | |
| "eval_runtime": 11.5347, | |
| "eval_samples_per_second": 147.295, | |
| "eval_steps_per_second": 18.466, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10314902058021325, | |
| "grad_norm": 1.0147478580474854, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2645, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.10711629060252914, | |
| "grad_norm": 1.2164422273635864, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.1775, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11108356062484503, | |
| "grad_norm": 1.3750309944152832, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 3.2619, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11505083064716093, | |
| "grad_norm": 1.3229867219924927, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.2809, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.11901810066947682, | |
| "grad_norm": 1.0716197490692139, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.2646, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12298537069179272, | |
| "grad_norm": 0.9642243385314941, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.2412, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1269526407141086, | |
| "grad_norm": 0.8288385272026062, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.2419, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1309199107364245, | |
| "grad_norm": 0.8620959520339966, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.3797, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1348871807587404, | |
| "grad_norm": 0.8693250417709351, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.218, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1388544507810563, | |
| "grad_norm": 0.9725481271743774, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.2733, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1428217208033722, | |
| "grad_norm": 0.9870604276657104, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.2407, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14678899082568808, | |
| "grad_norm": 1.25055992603302, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.301, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15075626084800398, | |
| "grad_norm": 0.8020516633987427, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.2486, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15472353087031987, | |
| "grad_norm": 0.6509931087493896, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.2495, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.15869080089263576, | |
| "grad_norm": 0.6136582493782043, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 3.2264, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16265807091495166, | |
| "grad_norm": 0.575463056564331, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 3.1638, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.16662534093726755, | |
| "grad_norm": 0.5796473026275635, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.2206, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.17059261095958345, | |
| "grad_norm": 0.6185922622680664, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 3.2557, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17455988098189934, | |
| "grad_norm": 0.648368239402771, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.2409, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.17852715100421523, | |
| "grad_norm": 0.7235672473907471, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.2006, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18249442102653113, | |
| "grad_norm": 0.8252574801445007, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.2917, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.18646169104884702, | |
| "grad_norm": 0.9163631796836853, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 3.2976, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.19042896107116292, | |
| "grad_norm": 0.9612374901771545, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.1845, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1943962310934788, | |
| "grad_norm": 1.0789424180984497, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.1664, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1983635011157947, | |
| "grad_norm": 1.5217560529708862, | |
| "learning_rate": 0.0, | |
| "loss": 3.2755, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1983635011157947, | |
| "eval_loss": 3.218653678894043, | |
| "eval_runtime": 11.5312, | |
| "eval_samples_per_second": 147.339, | |
| "eval_steps_per_second": 18.472, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |