| { | |
| "best_metric": 0.6226815581321716, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.29455081001472755, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005891016200294551, | |
| "grad_norm": 5.842298984527588, | |
| "learning_rate": 5e-05, | |
| "loss": 9.5356, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005891016200294551, | |
| "eval_loss": 9.313302040100098, | |
| "eval_runtime": 29.0711, | |
| "eval_samples_per_second": 39.352, | |
| "eval_steps_per_second": 4.919, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011782032400589101, | |
| "grad_norm": 5.442224025726318, | |
| "learning_rate": 0.0001, | |
| "loss": 9.6149, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.017673048600883652, | |
| "grad_norm": 5.885929584503174, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 9.0404, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.023564064801178203, | |
| "grad_norm": 5.703976631164551, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.5045, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.029455081001472753, | |
| "grad_norm": 5.090454578399658, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 8.0282, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.035346097201767304, | |
| "grad_norm": 5.094424724578857, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.7382, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": 5.329985618591309, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.2681, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.047128129602356406, | |
| "grad_norm": 5.399036407470703, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.4843, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.053019145802650956, | |
| "grad_norm": 6.035473346710205, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.8206, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05891016200294551, | |
| "grad_norm": 4.776269435882568, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.2461, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06480117820324006, | |
| "grad_norm": 4.449507713317871, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.6786, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07069219440353461, | |
| "grad_norm": 3.3939056396484375, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.3633, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07658321060382917, | |
| "grad_norm": 2.991218090057373, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.5821, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 3.1551268100738525, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.58, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08836524300441827, | |
| "grad_norm": 2.813246488571167, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.3115, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09425625920471281, | |
| "grad_norm": 2.7603561878204346, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.2722, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10014727540500737, | |
| "grad_norm": 2.7277021408081055, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.0294, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10603829160530191, | |
| "grad_norm": 3.1602253913879395, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.859, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11192930780559647, | |
| "grad_norm": 2.9966933727264404, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.4994, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11782032400589101, | |
| "grad_norm": 3.4069058895111084, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.37, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "grad_norm": 3.8147764205932617, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.1856, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12960235640648013, | |
| "grad_norm": 3.6965410709381104, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8319, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13549337260677466, | |
| "grad_norm": 3.231584072113037, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4828, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14138438880706922, | |
| "grad_norm": 2.6291158199310303, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.4255, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14727540500736377, | |
| "grad_norm": 3.0126707553863525, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.5902, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14727540500736377, | |
| "eval_loss": 1.3429416418075562, | |
| "eval_runtime": 28.9981, | |
| "eval_samples_per_second": 39.451, | |
| "eval_steps_per_second": 4.931, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15316642120765833, | |
| "grad_norm": 3.405451774597168, | |
| "learning_rate": 5e-05, | |
| "loss": 1.216, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.15905743740795286, | |
| "grad_norm": 3.620307445526123, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.3363, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16494845360824742, | |
| "grad_norm": 3.1116671562194824, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.1192, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.17083946980854198, | |
| "grad_norm": 2.9447152614593506, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.0844, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.17673048600883653, | |
| "grad_norm": 3.7199738025665283, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.1033, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18262150220913106, | |
| "grad_norm": 2.903928756713867, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.9522, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.18851251840942562, | |
| "grad_norm": 3.3113131523132324, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8444, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.19440353460972018, | |
| "grad_norm": 2.6979331970214844, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7607, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.20029455081001474, | |
| "grad_norm": 3.231203556060791, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7709, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.20618556701030927, | |
| "grad_norm": 3.6387054920196533, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.7232, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.21207658321060383, | |
| "grad_norm": 2.7801897525787354, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5396, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.21796759941089838, | |
| "grad_norm": 2.580199718475342, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7473, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.22385861561119294, | |
| "grad_norm": 1.9330986738204956, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6726, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.22974963181148747, | |
| "grad_norm": 2.1914916038513184, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5355, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.23564064801178203, | |
| "grad_norm": 2.175992488861084, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6397, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24153166421207659, | |
| "grad_norm": 3.0352063179016113, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6349, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.24742268041237114, | |
| "grad_norm": 3.7624361515045166, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5524, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2533136966126657, | |
| "grad_norm": 2.5523576736450195, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4813, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.25920471281296026, | |
| "grad_norm": 2.155388593673706, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4657, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2650957290132548, | |
| "grad_norm": 1.2593159675598145, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.491, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2709867452135493, | |
| "grad_norm": 1.8870849609375, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4691, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2768777614138439, | |
| "grad_norm": 1.8218656778335571, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4868, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.28276877761413843, | |
| "grad_norm": 1.4828749895095825, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5507, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.28865979381443296, | |
| "grad_norm": 1.5562994480133057, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4537, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.29455081001472755, | |
| "grad_norm": 2.369784116744995, | |
| "learning_rate": 0.0, | |
| "loss": 0.6343, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.29455081001472755, | |
| "eval_loss": 0.6226815581321716, | |
| "eval_runtime": 29.0409, | |
| "eval_samples_per_second": 39.393, | |
| "eval_steps_per_second": 4.924, | |
| "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 | |
| } | |