| { | |
| "best_metric": 1.349143624305725, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7299270072992701, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014598540145985401, | |
| "grad_norm": 0.3314630389213562, | |
| "learning_rate": 1e-05, | |
| "loss": 1.181, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014598540145985401, | |
| "eval_loss": 1.5133534669876099, | |
| "eval_runtime": 9.2058, | |
| "eval_samples_per_second": 12.601, | |
| "eval_steps_per_second": 3.15, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029197080291970802, | |
| "grad_norm": 0.22670935094356537, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4452, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.043795620437956206, | |
| "grad_norm": 0.3789464831352234, | |
| "learning_rate": 3e-05, | |
| "loss": 1.4232, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.058394160583941604, | |
| "grad_norm": 0.2621401250362396, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4073, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "grad_norm": 0.25601255893707275, | |
| "learning_rate": 5e-05, | |
| "loss": 1.344, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08759124087591241, | |
| "grad_norm": 0.2619723677635193, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3306, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10218978102189781, | |
| "grad_norm": 0.2971075177192688, | |
| "learning_rate": 7e-05, | |
| "loss": 1.4307, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11678832116788321, | |
| "grad_norm": 0.3079770803451538, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5267, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13138686131386862, | |
| "grad_norm": 0.3286444842815399, | |
| "learning_rate": 9e-05, | |
| "loss": 1.5575, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.145985401459854, | |
| "grad_norm": 0.31285712122917175, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5352, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16058394160583941, | |
| "grad_norm": 0.34175583720207214, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 1.3777, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.17518248175182483, | |
| "grad_norm": 0.3486191928386688, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 1.5109, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1897810218978102, | |
| "grad_norm": 0.3993035852909088, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 1.6024, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20437956204379562, | |
| "grad_norm": 0.4641835391521454, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 1.6562, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21897810218978103, | |
| "grad_norm": 0.5170352458953857, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 1.5123, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.23357664233576642, | |
| "grad_norm": 0.7671294212341309, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 1.5528, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24817518248175183, | |
| "grad_norm": 1.0964692831039429, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 1.5627, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.26277372262773724, | |
| "grad_norm": 0.22408375144004822, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 1.1167, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2773722627737226, | |
| "grad_norm": 0.27535220980644226, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 1.3162, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "grad_norm": 0.32067593932151794, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 1.4931, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.30656934306569344, | |
| "grad_norm": 0.2732066810131073, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 1.4165, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.32116788321167883, | |
| "grad_norm": 0.2587907314300537, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 1.3312, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3357664233576642, | |
| "grad_norm": 0.27388066053390503, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 1.2406, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.35036496350364965, | |
| "grad_norm": 0.2729540467262268, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 1.2964, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.36496350364963503, | |
| "grad_norm": 0.2680898904800415, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 1.3259, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3795620437956204, | |
| "grad_norm": 0.27648648619651794, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 1.5216, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.39416058394160586, | |
| "grad_norm": 0.2837010324001312, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 1.4691, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.40875912408759124, | |
| "grad_norm": 0.30292704701423645, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 1.4608, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4233576642335766, | |
| "grad_norm": 0.302458792924881, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.2839, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.43795620437956206, | |
| "grad_norm": 0.3292553424835205, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.5101, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.45255474452554745, | |
| "grad_norm": 0.4009181559085846, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 1.5497, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.46715328467153283, | |
| "grad_norm": 0.42407190799713135, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.3821, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.48175182481751827, | |
| "grad_norm": 0.595664918422699, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 1.2652, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.49635036496350365, | |
| "grad_norm": 1.1629176139831543, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.7652, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5109489051094891, | |
| "grad_norm": 0.23664163053035736, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 1.0537, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5255474452554745, | |
| "grad_norm": 0.29486626386642456, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.2419, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5401459854014599, | |
| "grad_norm": 0.3429765999317169, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 1.3914, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5547445255474452, | |
| "grad_norm": 0.31401655077934265, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.3065, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5693430656934306, | |
| "grad_norm": 0.2617841064929962, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 1.4523, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.583941605839416, | |
| "grad_norm": 0.30883294343948364, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.4265, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5985401459854015, | |
| "grad_norm": 0.24459517002105713, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 1.2564, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6131386861313869, | |
| "grad_norm": 0.2322646975517273, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.2948, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6277372262773723, | |
| "grad_norm": 0.2812507152557373, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 1.6696, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6423357664233577, | |
| "grad_norm": 0.24903182685375214, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.5108, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.656934306569343, | |
| "grad_norm": 0.2567322254180908, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 1.5481, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6715328467153284, | |
| "grad_norm": 0.2882676124572754, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 1.5023, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6861313868613139, | |
| "grad_norm": 0.307873010635376, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 1.6597, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7007299270072993, | |
| "grad_norm": 0.32634541392326355, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.3647, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7153284671532847, | |
| "grad_norm": 0.4027782678604126, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 1.4353, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7299270072992701, | |
| "grad_norm": 0.5115939378738403, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.544, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7299270072992701, | |
| "eval_loss": 1.349143624305725, | |
| "eval_runtime": 9.4009, | |
| "eval_samples_per_second": 12.339, | |
| "eval_steps_per_second": 3.085, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 7.749293335117824e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |