| { | |
| "best_metric": 2.2637264728546143, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.6454918032786885, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03278688524590164, | |
| "grad_norm": 0.10683845728635788, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3058, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03278688524590164, | |
| "eval_loss": 2.365455150604248, | |
| "eval_runtime": 5.7073, | |
| "eval_samples_per_second": 72.012, | |
| "eval_steps_per_second": 4.556, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06557377049180328, | |
| "grad_norm": 0.15207913517951965, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3936, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09836065573770492, | |
| "grad_norm": 0.15899555385112762, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.3863, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13114754098360656, | |
| "grad_norm": 0.15452754497528076, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.4017, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16393442622950818, | |
| "grad_norm": 0.18732032179832458, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.3827, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.19672131147540983, | |
| "grad_norm": 0.22198736667633057, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.2848, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22950819672131148, | |
| "grad_norm": 0.2722856402397156, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.2445, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 0.18571333587169647, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3194, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.29508196721311475, | |
| "grad_norm": 0.17011678218841553, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.3642, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.32786885245901637, | |
| "grad_norm": 0.14831551909446716, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.3724, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.36065573770491804, | |
| "grad_norm": 0.1516992300748825, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.3302, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.39344262295081966, | |
| "grad_norm": 0.14887568354606628, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.3302, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4262295081967213, | |
| "grad_norm": 0.1539280265569687, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.3542, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.45901639344262296, | |
| "grad_norm": 0.17510248720645905, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.3209, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4918032786885246, | |
| "grad_norm": 0.38928839564323425, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.3094, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 0.07632654905319214, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.3377, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5573770491803278, | |
| "grad_norm": 0.08971171826124191, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.3444, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5901639344262295, | |
| "grad_norm": 0.09893781691789627, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3751, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6229508196721312, | |
| "grad_norm": 0.11338970810174942, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.3477, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6557377049180327, | |
| "grad_norm": 0.1321367770433426, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3616, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6885245901639344, | |
| "grad_norm": 0.14731402695178986, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.2856, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7213114754098361, | |
| "grad_norm": 0.1837431788444519, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.1892, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7540983606557377, | |
| "grad_norm": 0.07160807400941849, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.3181, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 0.07446505129337311, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.3274, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "grad_norm": 0.08624447137117386, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.3193, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.819672131147541, | |
| "eval_loss": 2.268705129623413, | |
| "eval_runtime": 5.5244, | |
| "eval_samples_per_second": 74.397, | |
| "eval_steps_per_second": 4.706, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8524590163934426, | |
| "grad_norm": 0.0991344079375267, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3498, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8852459016393442, | |
| "grad_norm": 0.12045133858919144, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.338, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9180327868852459, | |
| "grad_norm": 0.13006040453910828, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.3029, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9508196721311475, | |
| "grad_norm": 0.16934581100940704, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.2783, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9836065573770492, | |
| "grad_norm": 0.3354940712451935, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.2464, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0225409836065573, | |
| "grad_norm": 0.15646272897720337, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 3.9901, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.055327868852459, | |
| "grad_norm": 0.11801426857709885, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.1995, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0881147540983607, | |
| "grad_norm": 0.14715805649757385, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.2941, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1209016393442623, | |
| "grad_norm": 0.1737724095582962, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3553, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.153688524590164, | |
| "grad_norm": 0.19558919966220856, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.2409, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1864754098360657, | |
| "grad_norm": 0.23931904137134552, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.3564, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.2192622950819672, | |
| "grad_norm": 0.3004460334777832, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.2929, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2520491803278688, | |
| "grad_norm": 0.11587761342525482, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.5015, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2848360655737705, | |
| "grad_norm": 0.11674284189939499, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.0545, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3176229508196722, | |
| "grad_norm": 0.13231879472732544, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.2792, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3504098360655736, | |
| "grad_norm": 0.155413419008255, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.2946, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3831967213114753, | |
| "grad_norm": 0.18727189302444458, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.2622, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.415983606557377, | |
| "grad_norm": 0.2269286960363388, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.3557, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.4487704918032787, | |
| "grad_norm": 0.26384779810905457, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1776, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4815573770491803, | |
| "grad_norm": 0.4085754454135895, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.4615, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.514344262295082, | |
| "grad_norm": 0.15077833831310272, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.1837, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5471311475409837, | |
| "grad_norm": 0.11710967868566513, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.2568, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5799180327868854, | |
| "grad_norm": 0.1437835991382599, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.3031, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.612704918032787, | |
| "grad_norm": 0.1696387678384781, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.272, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.6454918032786885, | |
| "grad_norm": 0.1985762119293213, | |
| "learning_rate": 0.0, | |
| "loss": 2.4134, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6454918032786885, | |
| "eval_loss": 2.2637264728546143, | |
| "eval_runtime": 5.5227, | |
| "eval_samples_per_second": 74.42, | |
| "eval_steps_per_second": 4.708, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2.210457704034468e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |