| { | |
| "best_metric": 0.11914384365081787, | |
| "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": 11.30103588104248, | |
| "learning_rate": 5e-05, | |
| "loss": 14.6893, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011363636363636364, | |
| "eval_loss": 16.7424259185791, | |
| "eval_runtime": 6.7678, | |
| "eval_samples_per_second": 87.621, | |
| "eval_steps_per_second": 11.082, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022727272727272728, | |
| "grad_norm": 11.835982322692871, | |
| "learning_rate": 0.0001, | |
| "loss": 15.1174, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03409090909090909, | |
| "grad_norm": 12.734379768371582, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 14.5118, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 19.658788681030273, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 13.0604, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.056818181818181816, | |
| "grad_norm": 31.426897048950195, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.671, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06818181818181818, | |
| "grad_norm": 36.82271957397461, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 9.2033, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07954545454545454, | |
| "grad_norm": 34.181549072265625, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.8811, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 37.13411331176758, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.2733, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10227272727272728, | |
| "grad_norm": 33.36564636230469, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.879, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11363636363636363, | |
| "grad_norm": 22.930240631103516, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.7821, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 11.455299377441406, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9542, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "grad_norm": 7.70440673828125, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6029, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14772727272727273, | |
| "grad_norm": 14.06171703338623, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.4586, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1590909090909091, | |
| "grad_norm": 18.02660369873047, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6814, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.17045454545454544, | |
| "grad_norm": 14.806828498840332, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9406, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 12.068374633789062, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7076, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19318181818181818, | |
| "grad_norm": 11.77354907989502, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6325, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20454545454545456, | |
| "grad_norm": 4.307706832885742, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4192, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2159090909090909, | |
| "grad_norm": 10.268922805786133, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4654, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 4.827605247497559, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2784, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23863636363636365, | |
| "grad_norm": 8.855995178222656, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.2529, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 6.721076488494873, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2368, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.26136363636363635, | |
| "grad_norm": 4.883802890777588, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2028, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 1.6547455787658691, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1722, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2840909090909091, | |
| "grad_norm": 4.705594539642334, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1273, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2840909090909091, | |
| "eval_loss": 0.2187383621931076, | |
| "eval_runtime": 6.7638, | |
| "eval_samples_per_second": 87.672, | |
| "eval_steps_per_second": 11.088, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29545454545454547, | |
| "grad_norm": 5.778199672698975, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3894, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3068181818181818, | |
| "grad_norm": 4.760310173034668, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2936, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3181818181818182, | |
| "grad_norm": 2.9043290615081787, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.224, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.32954545454545453, | |
| "grad_norm": 1.8596681356430054, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2239, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3409090909090909, | |
| "grad_norm": 2.2370481491088867, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1411, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3522727272727273, | |
| "grad_norm": 1.3053345680236816, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1207, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 5.874414443969727, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1589, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 3.6689720153808594, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1392, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.38636363636363635, | |
| "grad_norm": 1.4059278964996338, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0722, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3977272727272727, | |
| "grad_norm": 1.3172286748886108, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0914, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4090909090909091, | |
| "grad_norm": 4.161808490753174, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.133, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.42045454545454547, | |
| "grad_norm": 7.600207805633545, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.1262, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4318181818181818, | |
| "grad_norm": 7.597659587860107, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2628, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4431818181818182, | |
| "grad_norm": 3.380033016204834, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2251, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 2.1588728427886963, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2003, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4659090909090909, | |
| "grad_norm": 4.2201032638549805, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2124, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4772727272727273, | |
| "grad_norm": 4.442834854125977, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.1443, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48863636363636365, | |
| "grad_norm": 2.6062257289886475, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1259, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 1.960435390472412, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0906, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5113636363636364, | |
| "grad_norm": 1.2171847820281982, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0843, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5227272727272727, | |
| "grad_norm": 1.653974175453186, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0865, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5340909090909091, | |
| "grad_norm": 2.488990306854248, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0781, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.5377188324928284, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0432, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5568181818181818, | |
| "grad_norm": 1.272202491760254, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0986, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5681818181818182, | |
| "grad_norm": 1.9467240571975708, | |
| "learning_rate": 0.0, | |
| "loss": 0.1464, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5681818181818182, | |
| "eval_loss": 0.11914384365081787, | |
| "eval_runtime": 6.7655, | |
| "eval_samples_per_second": 87.65, | |
| "eval_steps_per_second": 11.086, | |
| "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 | |
| } | |