| { | |
| "best_metric": 2.114685535430908, | |
| "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": 0.1201447919011116, | |
| "learning_rate": 5e-05, | |
| "loss": 2.293, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08648648648648649, | |
| "eval_loss": 2.171900749206543, | |
| "eval_runtime": 4.6949, | |
| "eval_samples_per_second": 16.614, | |
| "eval_steps_per_second": 2.13, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17297297297297298, | |
| "grad_norm": 0.17884157598018646, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1798, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2594594594594595, | |
| "grad_norm": 0.13708369433879852, | |
| "learning_rate": 9.977359612865423e-05, | |
| "loss": 2.2398, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.34594594594594597, | |
| "grad_norm": 0.1070648804306984, | |
| "learning_rate": 9.909643486313533e-05, | |
| "loss": 2.2443, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 0.13643398880958557, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 2.1152, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.518918918918919, | |
| "grad_norm": 0.12095701694488525, | |
| "learning_rate": 9.641839665080363e-05, | |
| "loss": 2.228, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6054054054054054, | |
| "grad_norm": 0.10209406912326813, | |
| "learning_rate": 9.444177243274618e-05, | |
| "loss": 2.208, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6918918918918919, | |
| "grad_norm": 0.12675008177757263, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 2.0981, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7783783783783784, | |
| "grad_norm": 0.08076164871454239, | |
| "learning_rate": 8.930265473713938e-05, | |
| "loss": 2.2462, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 0.07629045844078064, | |
| "learning_rate": 8.618670190525352e-05, | |
| "loss": 2.2099, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9513513513513514, | |
| "grad_norm": 0.13773678243160248, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 2.1853, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0432432432432432, | |
| "grad_norm": 0.1455334573984146, | |
| "learning_rate": 7.900284547855991e-05, | |
| "loss": 3.3208, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1297297297297297, | |
| "grad_norm": 0.12233733385801315, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.357, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2162162162162162, | |
| "grad_norm": 0.111093670129776, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 1.6117, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3027027027027027, | |
| "grad_norm": 0.1097041666507721, | |
| "learning_rate": 6.635339816587109e-05, | |
| "loss": 2.5142, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.3891891891891892, | |
| "grad_norm": 0.12267576903104782, | |
| "learning_rate": 6.178794677547137e-05, | |
| "loss": 2.3654, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.4756756756756757, | |
| "grad_norm": 0.08579951524734497, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 1.317, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.5621621621621622, | |
| "grad_norm": 0.11934143304824829, | |
| "learning_rate": 5.2379095791187124e-05, | |
| "loss": 2.938, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.6486486486486487, | |
| "grad_norm": 0.13156631588935852, | |
| "learning_rate": 4.762090420881289e-05, | |
| "loss": 2.2236, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7351351351351352, | |
| "grad_norm": 0.09800512343645096, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 1.6747, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.8216216216216217, | |
| "grad_norm": 0.11417602002620697, | |
| "learning_rate": 3.821205322452863e-05, | |
| "loss": 2.6849, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9081081081081082, | |
| "grad_norm": 0.1482521891593933, | |
| "learning_rate": 3.364660183412892e-05, | |
| "loss": 2.1636, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.9945945945945946, | |
| "grad_norm": 0.11442886292934418, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 3.0638, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.0864864864864865, | |
| "grad_norm": 0.06609407812356949, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.2353, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.172972972972973, | |
| "grad_norm": 0.07348883897066116, | |
| "learning_rate": 2.09971545214401e-05, | |
| "loss": 2.1368, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.172972972972973, | |
| "eval_loss": 2.114685535430908, | |
| "eval_runtime": 4.4306, | |
| "eval_samples_per_second": 17.605, | |
| "eval_steps_per_second": 2.257, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2594594594594595, | |
| "grad_norm": 0.0808861255645752, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 2.1414, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.345945945945946, | |
| "grad_norm": 0.06256955862045288, | |
| "learning_rate": 1.3813298094746491e-05, | |
| "loss": 2.2125, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.4324324324324325, | |
| "grad_norm": 0.08788362145423889, | |
| "learning_rate": 1.0697345262860636e-05, | |
| "loss": 2.0403, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.518918918918919, | |
| "grad_norm": 0.07894165813922882, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 2.1777, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.6054054054054054, | |
| "grad_norm": 0.06610658764839172, | |
| "learning_rate": 5.558227567253832e-06, | |
| "loss": 2.2242, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.691891891891892, | |
| "grad_norm": 0.087137870490551, | |
| "learning_rate": 3.581603349196372e-06, | |
| "loss": 2.1225, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.7783783783783784, | |
| "grad_norm": 0.06447353959083557, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 2.1822, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.864864864864865, | |
| "grad_norm": 0.06715308874845505, | |
| "learning_rate": 9.035651368646648e-07, | |
| "loss": 2.1205, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.9513513513513514, | |
| "grad_norm": 0.1029222309589386, | |
| "learning_rate": 2.2640387134577058e-07, | |
| "loss": 2.0541, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.0432432432432432, | |
| "grad_norm": 0.13228559494018555, | |
| "learning_rate": 0.0, | |
| "loss": 3.2883, | |
| "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": 5.841261823000576e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |