| { | |
| "best_metric": 0.05764225125312805, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4214963119072708, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008429926238145416, | |
| "grad_norm": 1.3341302871704102, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7493, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008429926238145416, | |
| "eval_loss": 0.21355804800987244, | |
| "eval_runtime": 128.7109, | |
| "eval_samples_per_second": 6.215, | |
| "eval_steps_per_second": 0.777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01685985247629083, | |
| "grad_norm": 1.6189820766448975, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5138, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02528977871443625, | |
| "grad_norm": 1.9272456169128418, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.3181, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03371970495258166, | |
| "grad_norm": 1.0431249141693115, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.8563, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04214963119072708, | |
| "grad_norm": 1.2577431201934814, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.3348, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0505795574288725, | |
| "grad_norm": 0.8566964864730835, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3272, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.059009483667017915, | |
| "grad_norm": 0.9277756214141846, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4395, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06743940990516333, | |
| "grad_norm": 1.50494384765625, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9858, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07586933614330875, | |
| "grad_norm": 6.605533599853516, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.6619, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08429926238145416, | |
| "grad_norm": 3.0556588172912598, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9706, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09272918861959958, | |
| "grad_norm": 4.112440586090088, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9054, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.101159114857745, | |
| "grad_norm": 2.5288426876068115, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.44, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1095890410958904, | |
| "grad_norm": 2.0018320083618164, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.9965, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.11801896733403583, | |
| "grad_norm": 1.453355073928833, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6349, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12644889357218125, | |
| "grad_norm": 1.1725133657455444, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9425, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13487881981032665, | |
| "grad_norm": 0.9537891745567322, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.9102, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14330874604847207, | |
| "grad_norm": 1.0789560079574585, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0972, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1517386722866175, | |
| "grad_norm": 2.126995801925659, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.0853, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1601685985247629, | |
| "grad_norm": 1.467456340789795, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.6946, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16859852476290832, | |
| "grad_norm": 1.6159006357192993, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0233, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17702845100105374, | |
| "grad_norm": 3.9295225143432617, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.2685, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18545837723919917, | |
| "grad_norm": 5.1888909339904785, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.9563, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19388830347734456, | |
| "grad_norm": 0.7670079469680786, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.096, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20231822971549, | |
| "grad_norm": 0.6988094449043274, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0889, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2107481559536354, | |
| "grad_norm": 0.9281933307647705, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.1051, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2107481559536354, | |
| "eval_loss": 0.06404294073581696, | |
| "eval_runtime": 121.7973, | |
| "eval_samples_per_second": 6.568, | |
| "eval_steps_per_second": 0.821, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 0.8070772290229797, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0797, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.22760800842992623, | |
| "grad_norm": 0.5251370668411255, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.0025, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.23603793466807166, | |
| "grad_norm": 0.4461825489997864, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7255, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24446786090621708, | |
| "grad_norm": 0.42862668633461, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3988, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2528977871443625, | |
| "grad_norm": 0.4532180428504944, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.8711, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2613277133825079, | |
| "grad_norm": 0.5346589684486389, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.9462, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2697576396206533, | |
| "grad_norm": 0.8099014163017273, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8339, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2781875658587987, | |
| "grad_norm": 1.1245605945587158, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.4904, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.28661749209694415, | |
| "grad_norm": 2.838240385055542, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.2306, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2950474183350896, | |
| "grad_norm": 0.8263105750083923, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.2503, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.303477344573235, | |
| "grad_norm": 0.22436164319515228, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0252, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3119072708113804, | |
| "grad_norm": 1.1818960905075073, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.053, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3203371970495258, | |
| "grad_norm": 0.6988030672073364, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6634, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3287671232876712, | |
| "grad_norm": 0.29791903495788574, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4388, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.33719704952581664, | |
| "grad_norm": 0.4577045440673828, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6004, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.34562697576396206, | |
| "grad_norm": 0.4514332115650177, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5685, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3540569020021075, | |
| "grad_norm": 0.603263795375824, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5244, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3624868282402529, | |
| "grad_norm": 0.4666103422641754, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.9812, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.37091675447839834, | |
| "grad_norm": 0.768443763256073, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6074, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3793466807165437, | |
| "grad_norm": 0.6417664885520935, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.651, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.38777660695468913, | |
| "grad_norm": 1.7357624769210815, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.9473, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.39620653319283455, | |
| "grad_norm": 2.6136465072631836, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.4396, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.40463645943098, | |
| "grad_norm": 0.3199690282344818, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0324, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.4130663856691254, | |
| "grad_norm": 0.24052637815475464, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0266, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4214963119072708, | |
| "grad_norm": 1.7562198638916016, | |
| "learning_rate": 0.0, | |
| "loss": 0.051, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4214963119072708, | |
| "eval_loss": 0.05764225125312805, | |
| "eval_runtime": 121.1566, | |
| "eval_samples_per_second": 6.603, | |
| "eval_steps_per_second": 0.825, | |
| "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": 5.086786570116137e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |