| { | |
| "best_metric": 1.7739577293395996, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.27586206896551724, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005517241379310344, | |
| "grad_norm": 1.807527780532837, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3986, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005517241379310344, | |
| "eval_loss": 3.0793025493621826, | |
| "eval_runtime": 36.6991, | |
| "eval_samples_per_second": 33.271, | |
| "eval_steps_per_second": 4.169, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011034482758620689, | |
| "grad_norm": 3.114354133605957, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6026, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016551724137931035, | |
| "grad_norm": 2.534005880355835, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.5059, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022068965517241378, | |
| "grad_norm": 3.5857439041137695, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.2618, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.027586206896551724, | |
| "grad_norm": 1.6016645431518555, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.1228, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03310344827586207, | |
| "grad_norm": 1.3642950057983398, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0125, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.038620689655172416, | |
| "grad_norm": 0.8602076172828674, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0021, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.044137931034482755, | |
| "grad_norm": 0.9072312712669373, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.024, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0496551724137931, | |
| "grad_norm": 0.5932643413543701, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.8993, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05517241379310345, | |
| "grad_norm": 0.6446831822395325, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.8462, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.060689655172413794, | |
| "grad_norm": 0.6931407451629639, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.7446, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06620689655172414, | |
| "grad_norm": 0.888304591178894, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.6002, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07172413793103448, | |
| "grad_norm": 1.3450971841812134, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.0469, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07724137931034483, | |
| "grad_norm": 1.306834101676941, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1241, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08275862068965517, | |
| "grad_norm": 0.9052755832672119, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.9154, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08827586206896551, | |
| "grad_norm": 0.5119055509567261, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.9414, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09379310344827586, | |
| "grad_norm": 0.4537582993507385, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.9063, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0993103448275862, | |
| "grad_norm": 0.4957878887653351, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.914, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10482758620689656, | |
| "grad_norm": 0.5619772672653198, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.9696, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1103448275862069, | |
| "grad_norm": 0.6423885226249695, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8864, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11586206896551725, | |
| "grad_norm": 0.7338322401046753, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.882, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12137931034482759, | |
| "grad_norm": 0.6952574253082275, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8506, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12689655172413794, | |
| "grad_norm": 0.7422984838485718, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.6765, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13241379310344828, | |
| "grad_norm": 0.9016779065132141, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.6063, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": 1.0913209915161133, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.4827, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "eval_loss": 1.8006632328033447, | |
| "eval_runtime": 36.6828, | |
| "eval_samples_per_second": 33.285, | |
| "eval_steps_per_second": 4.171, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14344827586206896, | |
| "grad_norm": 0.42979636788368225, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9951, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1489655172413793, | |
| "grad_norm": 0.6208154559135437, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.9629, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.15448275862068966, | |
| "grad_norm": 0.7410222291946411, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.9223, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.710483968257904, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.8629, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.16551724137931034, | |
| "grad_norm": 0.6926829218864441, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.9071, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17103448275862068, | |
| "grad_norm": 0.5659056901931763, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.8826, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.17655172413793102, | |
| "grad_norm": 0.5118544101715088, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9053, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1820689655172414, | |
| "grad_norm": 0.4353203773498535, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.8, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.18758620689655173, | |
| "grad_norm": 0.46631351113319397, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.8122, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.19310344827586207, | |
| "grad_norm": 0.4434465765953064, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.7479, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1986206896551724, | |
| "grad_norm": 0.5267812609672546, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.7205, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.20413793103448277, | |
| "grad_norm": 0.7954340577125549, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.4462, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2096551724137931, | |
| "grad_norm": 0.2572181522846222, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7751, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.21517241379310345, | |
| "grad_norm": 0.21893517673015594, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.9198, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2206896551724138, | |
| "grad_norm": 0.2396923303604126, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.8549, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22620689655172413, | |
| "grad_norm": 0.2584957480430603, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.8653, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2317241379310345, | |
| "grad_norm": 0.2715318202972412, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.853, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.23724137931034484, | |
| "grad_norm": 0.28509530425071716, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.8154, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.24275862068965517, | |
| "grad_norm": 0.3081589639186859, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.8422, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2482758620689655, | |
| "grad_norm": 0.3403320610523224, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.8003, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2537931034482759, | |
| "grad_norm": 0.3637648820877075, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.8166, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2593103448275862, | |
| "grad_norm": 0.41386306285858154, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.8, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.26482758620689656, | |
| "grad_norm": 0.5368902683258057, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.6797, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.27034482758620687, | |
| "grad_norm": 0.6475918292999268, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.5817, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 0.9710679650306702, | |
| "learning_rate": 0.0, | |
| "loss": 1.2874, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "eval_loss": 1.7739577293395996, | |
| "eval_runtime": 36.6968, | |
| "eval_samples_per_second": 33.273, | |
| "eval_steps_per_second": 4.169, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |