| { | |
| "best_metric": 0.11900235712528229, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06642311524410495, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001328462304882099, | |
| "grad_norm": 1.3991806507110596, | |
| "learning_rate": 1e-05, | |
| "loss": 1.2451, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001328462304882099, | |
| "eval_loss": 0.9099801778793335, | |
| "eval_runtime": 42.0554, | |
| "eval_samples_per_second": 30.151, | |
| "eval_steps_per_second": 7.538, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002656924609764198, | |
| "grad_norm": 1.197432041168213, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5518, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003985386914646297, | |
| "grad_norm": 1.144295334815979, | |
| "learning_rate": 3e-05, | |
| "loss": 0.8168, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005313849219528396, | |
| "grad_norm": 1.1892198324203491, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9958, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006642311524410495, | |
| "grad_norm": 1.2396732568740845, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6305, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007970773829292593, | |
| "grad_norm": 1.2879739999771118, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5989, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009299236134174693, | |
| "grad_norm": 1.630868673324585, | |
| "learning_rate": 7e-05, | |
| "loss": 0.6053, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010627698439056792, | |
| "grad_norm": 1.6003340482711792, | |
| "learning_rate": 8e-05, | |
| "loss": 0.4353, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01195616074393889, | |
| "grad_norm": 2.563776969909668, | |
| "learning_rate": 9e-05, | |
| "loss": 0.2927, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01328462304882099, | |
| "grad_norm": 1.628896951675415, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3386, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014613085353703089, | |
| "grad_norm": 1.5699366331100464, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 0.3045, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015941547658585187, | |
| "grad_norm": 1.328123688697815, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 0.2609, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017270009963467288, | |
| "grad_norm": 1.599324107170105, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 0.1865, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018598472268349386, | |
| "grad_norm": 1.4006145000457764, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 0.1577, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019926934573231483, | |
| "grad_norm": 1.027660608291626, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.1287, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021255396878113585, | |
| "grad_norm": 1.1444554328918457, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 0.1756, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022583859182995682, | |
| "grad_norm": 0.8250659108161926, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 0.1705, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02391232148787778, | |
| "grad_norm": 1.2994184494018555, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 0.1767, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02524078379275988, | |
| "grad_norm": 0.9651134014129639, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 0.1161, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02656924609764198, | |
| "grad_norm": 1.0957099199295044, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.1397, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.027897708402524077, | |
| "grad_norm": 0.8373222351074219, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 0.108, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029226170707406178, | |
| "grad_norm": 1.938508152961731, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 0.16, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.030554633012288276, | |
| "grad_norm": 1.1585845947265625, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 0.1239, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.031883095317170373, | |
| "grad_norm": 0.9152848124504089, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 0.0872, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.033211557622052475, | |
| "grad_norm": 0.716942548751831, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.0809, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.034540019926934576, | |
| "grad_norm": 0.9917988777160645, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 0.1373, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03586848223181667, | |
| "grad_norm": 0.9087157845497131, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 0.1231, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03719694453669877, | |
| "grad_norm": 0.4621882140636444, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 0.0762, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03852540684158087, | |
| "grad_norm": 1.1974875926971436, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.099, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03985386914646297, | |
| "grad_norm": 0.6985036730766296, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.0772, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04118233145134507, | |
| "grad_norm": 0.6680667400360107, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 0.082, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04251079375622717, | |
| "grad_norm": 0.6564874649047852, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 0.0691, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.043839256061109264, | |
| "grad_norm": 0.5068350434303284, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 0.0566, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.045167718365991365, | |
| "grad_norm": 0.5241013765335083, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 0.051, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.046496180670873466, | |
| "grad_norm": 1.0206941366195679, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.1009, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04782464297575556, | |
| "grad_norm": 0.936644434928894, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 0.0895, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04915310528063766, | |
| "grad_norm": 1.2153074741363525, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 0.0833, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05048156758551976, | |
| "grad_norm": 1.9132487773895264, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 0.1536, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05181002989040186, | |
| "grad_norm": 1.4385014772415161, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 0.1551, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05313849219528396, | |
| "grad_norm": 1.128587245941162, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.1262, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05446695450016606, | |
| "grad_norm": 0.6382101774215698, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 0.0608, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.055795416805048154, | |
| "grad_norm": 0.5120552182197571, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 0.0495, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.057123879109930255, | |
| "grad_norm": 0.6968569755554199, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 0.0713, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.058452341414812356, | |
| "grad_norm": 0.5472718477249146, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 0.0618, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05978080371969445, | |
| "grad_norm": 1.030089020729065, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.1089, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06110926602457655, | |
| "grad_norm": 1.0972938537597656, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 0.1525, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06243772832945865, | |
| "grad_norm": 0.699333906173706, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 0.0547, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06376619063434075, | |
| "grad_norm": 1.0085898637771606, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0849, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06509465293922286, | |
| "grad_norm": 1.6594712734222412, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 0.1065, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06642311524410495, | |
| "grad_norm": 2.0280661582946777, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.1971, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06642311524410495, | |
| "eval_loss": 0.11900235712528229, | |
| "eval_runtime": 42.6792, | |
| "eval_samples_per_second": 29.71, | |
| "eval_steps_per_second": 7.428, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7971770657079296e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |