| { | |
| "best_metric": 0.3443070352077484, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.017562346329469618, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00035124692658939234, | |
| "grad_norm": 32.192405700683594, | |
| "learning_rate": 5e-05, | |
| "loss": 7.295, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00035124692658939234, | |
| "eval_loss": 6.720856666564941, | |
| "eval_runtime": 342.6114, | |
| "eval_samples_per_second": 55.982, | |
| "eval_steps_per_second": 6.999, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007024938531787847, | |
| "grad_norm": 20.206274032592773, | |
| "learning_rate": 0.0001, | |
| "loss": 5.6671, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001053740779768177, | |
| "grad_norm": 17.400434494018555, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.0339, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014049877063575693, | |
| "grad_norm": 12.235267639160156, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.71, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0017562346329469617, | |
| "grad_norm": 7.465464115142822, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.4487, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002107481559536354, | |
| "grad_norm": 6.217895030975342, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0162, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0024587284861257463, | |
| "grad_norm": 4.9625020027160645, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.9202, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0028099754127151387, | |
| "grad_norm": 3.371049404144287, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.6555, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003161222339304531, | |
| "grad_norm": 3.4292800426483154, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.6458, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0035124692658939235, | |
| "grad_norm": 2.848095178604126, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4674, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003863716192483316, | |
| "grad_norm": 2.848973512649536, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4835, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004214963119072708, | |
| "grad_norm": 3.2421960830688477, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4446, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0045662100456621, | |
| "grad_norm": 9.692215919494629, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.3768, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004917456972251493, | |
| "grad_norm": 9.407149314880371, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2451, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005268703898840885, | |
| "grad_norm": 3.8585033416748047, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2473, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005619950825430277, | |
| "grad_norm": 2.9171791076660156, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.2217, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00597119775201967, | |
| "grad_norm": 2.5240423679351807, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0613, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006322444678609062, | |
| "grad_norm": 2.544886350631714, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0402, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0066736916051984545, | |
| "grad_norm": 2.4813730716705322, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.8948, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007024938531787847, | |
| "grad_norm": 2.7242941856384277, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8626, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007376185458377239, | |
| "grad_norm": 2.9735679626464844, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.908, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007727432384966632, | |
| "grad_norm": 4.013394355773926, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.9104, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.008078679311556024, | |
| "grad_norm": 3.7732810974121094, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7861, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.008429926238145416, | |
| "grad_norm": 4.526644229888916, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.7839, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008781173164734809, | |
| "grad_norm": 4.796482563018799, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7826, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008781173164734809, | |
| "eval_loss": 0.7938250303268433, | |
| "eval_runtime": 225.7508, | |
| "eval_samples_per_second": 84.961, | |
| "eval_steps_per_second": 10.622, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0091324200913242, | |
| "grad_norm": 9.767693519592285, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4242, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.009483667017913594, | |
| "grad_norm": 3.4661805629730225, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.7501, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009834913944502985, | |
| "grad_norm": 3.630671977996826, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6906, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.010186160871092378, | |
| "grad_norm": 4.088723182678223, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.7193, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01053740779768177, | |
| "grad_norm": 2.984363079071045, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.534, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010888654724271163, | |
| "grad_norm": 2.782954454421997, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4701, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.011239901650860555, | |
| "grad_norm": 3.33673357963562, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4251, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.011591148577449948, | |
| "grad_norm": 2.900033950805664, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3944, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01194239550403934, | |
| "grad_norm": 3.8180954456329346, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4438, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.012293642430628733, | |
| "grad_norm": 5.123332977294922, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.3738, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.012644889357218124, | |
| "grad_norm": 4.384796142578125, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.3805, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.012996136283807516, | |
| "grad_norm": 5.82057523727417, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3628, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.013347383210396909, | |
| "grad_norm": 6.459886074066162, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5976, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0136986301369863, | |
| "grad_norm": 8.909965515136719, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.7892, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.014049877063575694, | |
| "grad_norm": 2.968870162963867, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.374, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014401123990165085, | |
| "grad_norm": 2.7978880405426025, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2767, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.014752370916754479, | |
| "grad_norm": 3.1695451736450195, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2828, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01510361784334387, | |
| "grad_norm": 2.9912350177764893, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2397, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.015454864769933263, | |
| "grad_norm": 2.6705098152160645, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1982, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.015806111696522657, | |
| "grad_norm": 3.1095471382141113, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2159, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.016157358623112048, | |
| "grad_norm": 3.1432695388793945, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.204, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.01650860554970144, | |
| "grad_norm": 3.4346730709075928, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.2457, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01685985247629083, | |
| "grad_norm": 4.1334547996521, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2389, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.017211099402880226, | |
| "grad_norm": 3.5191686153411865, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.23, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.017562346329469618, | |
| "grad_norm": 6.209085941314697, | |
| "learning_rate": 0.0, | |
| "loss": 0.3094, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.017562346329469618, | |
| "eval_loss": 0.3443070352077484, | |
| "eval_runtime": 161.0645, | |
| "eval_samples_per_second": 119.083, | |
| "eval_steps_per_second": 14.888, | |
| "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": 3.216011515920384e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |