| { | |
| "best_metric": 2.032545328140259, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5681818181818182, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011363636363636364, | |
| "grad_norm": 2.7021124362945557, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1193, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011363636363636364, | |
| "eval_loss": 4.739462375640869, | |
| "eval_runtime": 16.6811, | |
| "eval_samples_per_second": 35.549, | |
| "eval_steps_per_second": 4.496, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022727272727272728, | |
| "grad_norm": 3.2683639526367188, | |
| "learning_rate": 0.0001, | |
| "loss": 3.5775, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03409090909090909, | |
| "grad_norm": 3.1707563400268555, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.5869, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 3.4560506343841553, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.5091, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.056818181818181816, | |
| "grad_norm": 3.3004863262176514, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.3656, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06818181818181818, | |
| "grad_norm": 2.737147092819214, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.0477, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07954545454545454, | |
| "grad_norm": 3.0929532051086426, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.9262, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 2.786226987838745, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.0848, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10227272727272728, | |
| "grad_norm": 2.3751325607299805, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.8785, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11363636363636363, | |
| "grad_norm": 1.8524545431137085, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.5988, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 1.6459931135177612, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.5756, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "grad_norm": 1.4236981868743896, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.5151, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14772727272727273, | |
| "grad_norm": 0.9423320889472961, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9782, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1590909090909091, | |
| "grad_norm": 1.0780678987503052, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7815, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17045454545454544, | |
| "grad_norm": 1.0836559534072876, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.0837, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.9846199750900269, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.0718, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19318181818181818, | |
| "grad_norm": 1.0413646697998047, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8915, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20454545454545456, | |
| "grad_norm": 1.038799524307251, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.9604, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2159090909090909, | |
| "grad_norm": 1.0064616203308105, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.1818, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 0.9710341095924377, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.081, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23863636363636365, | |
| "grad_norm": 0.9461048245429993, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.0471, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.106583595275879, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.1361, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26136363636363635, | |
| "grad_norm": 1.0309126377105713, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.1852, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 1.174065113067627, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.3848, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2840909090909091, | |
| "grad_norm": 1.564176082611084, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.4425, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2840909090909091, | |
| "eval_loss": 2.0682475566864014, | |
| "eval_runtime": 16.7837, | |
| "eval_samples_per_second": 35.332, | |
| "eval_steps_per_second": 4.469, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29545454545454547, | |
| "grad_norm": 0.7505583167076111, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6557, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3068181818181818, | |
| "grad_norm": 0.8248937129974365, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.7955, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3181818181818182, | |
| "grad_norm": 0.7818592190742493, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.7143, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.32954545454545453, | |
| "grad_norm": 0.9162489771842957, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.8803, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3409090909090909, | |
| "grad_norm": 0.8971193432807922, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.8417, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3522727272727273, | |
| "grad_norm": 0.942955732345581, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.0823, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.8796543478965759, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8845, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 0.9612118601799011, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.0512, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38636363636363635, | |
| "grad_norm": 1.0305103063583374, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.1146, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3977272727272727, | |
| "grad_norm": 1.1519629955291748, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.1694, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4090909090909091, | |
| "grad_norm": 1.2092336416244507, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.2877, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.42045454545454547, | |
| "grad_norm": 1.228949785232544, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.4408, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4318181818181818, | |
| "grad_norm": 0.9068592190742493, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.8291, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4431818181818182, | |
| "grad_norm": 0.9036156535148621, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5543, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.8183141946792603, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.6965, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4659090909090909, | |
| "grad_norm": 0.7449139952659607, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.5929, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4772727272727273, | |
| "grad_norm": 0.9520010948181152, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.0831, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48863636363636365, | |
| "grad_norm": 0.9523089528083801, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.0609, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.8622874021530151, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.8157, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5113636363636364, | |
| "grad_norm": 0.9605145454406738, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.0216, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5227272727272727, | |
| "grad_norm": 0.9834564328193665, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.0998, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5340909090909091, | |
| "grad_norm": 0.9851539731025696, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.2128, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 1.0516159534454346, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.1404, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5568181818181818, | |
| "grad_norm": 1.004589319229126, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.2279, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5681818181818182, | |
| "grad_norm": 1.3169046640396118, | |
| "learning_rate": 0.0, | |
| "loss": 2.3239, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5681818181818182, | |
| "eval_loss": 2.032545328140259, | |
| "eval_runtime": 16.7126, | |
| "eval_samples_per_second": 35.482, | |
| "eval_steps_per_second": 4.488, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |