| { | |
| "best_metric": 1.8320754766464233, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0432432432432432, | |
| "eval_steps": 25, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08648648648648649, | |
| "grad_norm": 12.519146919250488, | |
| "learning_rate": 5e-05, | |
| "loss": 32.0769, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08648648648648649, | |
| "eval_loss": 1.941705584526062, | |
| "eval_runtime": 4.7479, | |
| "eval_samples_per_second": 16.428, | |
| "eval_steps_per_second": 2.106, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17297297297297298, | |
| "grad_norm": 13.44698715209961, | |
| "learning_rate": 0.0001, | |
| "loss": 31.5154, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2594594594594595, | |
| "grad_norm": 8.150639533996582, | |
| "learning_rate": 9.977359612865423e-05, | |
| "loss": 32.4202, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.34594594594594597, | |
| "grad_norm": 14.541661262512207, | |
| "learning_rate": 9.909643486313533e-05, | |
| "loss": 31.2623, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 10.831154823303223, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 30.521, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.518918918918919, | |
| "grad_norm": 5.147383213043213, | |
| "learning_rate": 9.641839665080363e-05, | |
| "loss": 30.6469, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6054054054054054, | |
| "grad_norm": 4.451767921447754, | |
| "learning_rate": 9.444177243274618e-05, | |
| "loss": 30.4611, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6918918918918919, | |
| "grad_norm": 4.118326663970947, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 29.8147, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7783783783783784, | |
| "grad_norm": 3.2231149673461914, | |
| "learning_rate": 8.930265473713938e-05, | |
| "loss": 30.8363, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 3.3403027057647705, | |
| "learning_rate": 8.618670190525352e-05, | |
| "loss": 30.9248, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9513513513513514, | |
| "grad_norm": 4.539824962615967, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 30.8861, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0432432432432432, | |
| "grad_norm": 2.6900265216827393, | |
| "learning_rate": 7.900284547855991e-05, | |
| "loss": 29.4372, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1297297297297297, | |
| "grad_norm": 2.902007579803467, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 29.9205, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2162162162162162, | |
| "grad_norm": 3.2837560176849365, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 28.822, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3027027027027027, | |
| "grad_norm": 2.911205768585205, | |
| "learning_rate": 6.635339816587109e-05, | |
| "loss": 30.0186, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3891891891891892, | |
| "grad_norm": 2.4737565517425537, | |
| "learning_rate": 6.178794677547137e-05, | |
| "loss": 29.8052, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.4756756756756757, | |
| "grad_norm": 3.528310537338257, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 28.6351, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5621621621621622, | |
| "grad_norm": 2.513032913208008, | |
| "learning_rate": 5.2379095791187124e-05, | |
| "loss": 30.2261, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6486486486486487, | |
| "grad_norm": 2.8475759029388428, | |
| "learning_rate": 4.762090420881289e-05, | |
| "loss": 29.4439, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7351351351351352, | |
| "grad_norm": 3.580244779586792, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 29.1311, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8216216216216217, | |
| "grad_norm": 2.4849469661712646, | |
| "learning_rate": 3.821205322452863e-05, | |
| "loss": 30.246, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9081081081081082, | |
| "grad_norm": 2.6413068771362305, | |
| "learning_rate": 3.364660183412892e-05, | |
| "loss": 29.3512, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.9945945945945946, | |
| "grad_norm": 3.114119052886963, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 29.9625, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0864864864864865, | |
| "grad_norm": 2.31789493560791, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 29.9954, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.172972972972973, | |
| "grad_norm": 2.4415395259857178, | |
| "learning_rate": 2.09971545214401e-05, | |
| "loss": 29.3936, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.172972972972973, | |
| "eval_loss": 1.8320754766464233, | |
| "eval_runtime": 5.0327, | |
| "eval_samples_per_second": 15.499, | |
| "eval_steps_per_second": 1.987, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2594594594594595, | |
| "grad_norm": 3.1727261543273926, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 28.4688, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.345945945945946, | |
| "grad_norm": 2.3725779056549072, | |
| "learning_rate": 1.3813298094746491e-05, | |
| "loss": 29.8251, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.4324324324324325, | |
| "grad_norm": 2.7852530479431152, | |
| "learning_rate": 1.0697345262860636e-05, | |
| "loss": 28.014, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.518918918918919, | |
| "grad_norm": 3.078930377960205, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 29.2884, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.6054054054054054, | |
| "grad_norm": 2.356929063796997, | |
| "learning_rate": 5.558227567253832e-06, | |
| "loss": 29.585, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.691891891891892, | |
| "grad_norm": 2.9331376552581787, | |
| "learning_rate": 3.581603349196372e-06, | |
| "loss": 29.1139, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.7783783783783784, | |
| "grad_norm": 2.7119784355163574, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 28.906, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.864864864864865, | |
| "grad_norm": 2.287707567214966, | |
| "learning_rate": 9.035651368646648e-07, | |
| "loss": 28.6825, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.9513513513513514, | |
| "grad_norm": 3.3493847846984863, | |
| "learning_rate": 2.2640387134577058e-07, | |
| "loss": 28.1186, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.0432432432432432, | |
| "grad_norm": 2.538076162338257, | |
| "learning_rate": 0.0, | |
| "loss": 29.3932, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 35, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 5.774718047847711e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |