| { | |
| "best_metric": 1.1372556686401367, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4672897196261682, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009345794392523364, | |
| "grad_norm": 0.3978344798088074, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9398, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009345794392523364, | |
| "eval_loss": 1.7340189218521118, | |
| "eval_runtime": 8.5936, | |
| "eval_samples_per_second": 83.9, | |
| "eval_steps_per_second": 10.589, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018691588785046728, | |
| "grad_norm": 0.5709060430526733, | |
| "learning_rate": 0.0001, | |
| "loss": 1.757, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "grad_norm": 0.787490963935852, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.7692, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 0.7441607117652893, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.8385, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04672897196261682, | |
| "grad_norm": 0.9779700040817261, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.6621, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 0.96686851978302, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7432, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06542056074766354, | |
| "grad_norm": 1.0333670377731323, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.6088, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "grad_norm": 0.9446337223052979, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5466, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08411214953271028, | |
| "grad_norm": 0.6854303479194641, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.2227, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.09345794392523364, | |
| "grad_norm": 0.47890907526016235, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1518, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.102803738317757, | |
| "grad_norm": 0.7436364889144897, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.8991, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 0.7621960639953613, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6585, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.12149532710280374, | |
| "grad_norm": 0.35844719409942627, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.2974, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1308411214953271, | |
| "grad_norm": 0.3635321259498596, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.644, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.14018691588785046, | |
| "grad_norm": 0.5268105268478394, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5573, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14953271028037382, | |
| "grad_norm": 0.34928566217422485, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.5635, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1588785046728972, | |
| "grad_norm": 0.31971651315689087, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.6137, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16822429906542055, | |
| "grad_norm": 0.31752440333366394, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.6834, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.17757009345794392, | |
| "grad_norm": 0.27759334444999695, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.5909, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.18691588785046728, | |
| "grad_norm": 0.2512029707431793, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4532, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19626168224299065, | |
| "grad_norm": 0.27232271432876587, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1634, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.205607476635514, | |
| "grad_norm": 0.3015228509902954, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.1902, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.21495327102803738, | |
| "grad_norm": 0.42352810502052307, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.058, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.22429906542056074, | |
| "grad_norm": 0.5410281419754028, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.705, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2336448598130841, | |
| "grad_norm": 0.9533042311668396, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5321, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2336448598130841, | |
| "eval_loss": 1.1425410509109497, | |
| "eval_runtime": 8.6098, | |
| "eval_samples_per_second": 83.742, | |
| "eval_steps_per_second": 10.569, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.24299065420560748, | |
| "grad_norm": 0.14727185666561127, | |
| "learning_rate": 5e-05, | |
| "loss": 1.469, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2523364485981308, | |
| "grad_norm": 0.19489595293998718, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5368, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2616822429906542, | |
| "grad_norm": 0.199602410197258, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.4505, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.27102803738317754, | |
| "grad_norm": 0.20316776633262634, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.5289, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2803738317757009, | |
| "grad_norm": 0.2126455456018448, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.5463, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2897196261682243, | |
| "grad_norm": 0.24680300056934357, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.641, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.29906542056074764, | |
| "grad_norm": 0.2757948637008667, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.551, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.308411214953271, | |
| "grad_norm": 0.2962428331375122, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.3126, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3177570093457944, | |
| "grad_norm": 0.3176026940345764, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.186, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.32710280373831774, | |
| "grad_norm": 0.3386916518211365, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.074, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3364485981308411, | |
| "grad_norm": 0.5389696955680847, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8624, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.34579439252336447, | |
| "grad_norm": 0.4262228012084961, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5714, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.35514018691588783, | |
| "grad_norm": 0.18187835812568665, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4737, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3644859813084112, | |
| "grad_norm": 0.16893325746059418, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.3986, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.37383177570093457, | |
| "grad_norm": 0.16854919493198395, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5729, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.38317757009345793, | |
| "grad_norm": 0.19124285876750946, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.5008, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3925233644859813, | |
| "grad_norm": 0.19107972085475922, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.5696, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.40186915887850466, | |
| "grad_norm": 0.20743322372436523, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.5389, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.411214953271028, | |
| "grad_norm": 0.2289905697107315, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5983, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4205607476635514, | |
| "grad_norm": 0.21572710573673248, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.5261, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.42990654205607476, | |
| "grad_norm": 0.23301757872104645, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2894, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4392523364485981, | |
| "grad_norm": 0.2420756071805954, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.0929, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4485981308411215, | |
| "grad_norm": 0.2989835739135742, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.1027, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.45794392523364486, | |
| "grad_norm": 0.3651668429374695, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.724, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4672897196261682, | |
| "grad_norm": 0.43937990069389343, | |
| "learning_rate": 0.0, | |
| "loss": 0.5712, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4672897196261682, | |
| "eval_loss": 1.1372556686401367, | |
| "eval_runtime": 8.6063, | |
| "eval_samples_per_second": 83.775, | |
| "eval_steps_per_second": 10.574, | |
| "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": 1.0635096147099648e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |