| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9950948634891255, | |
| "eval_steps": 100, | |
| "global_step": 168, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02961591855622397, | |
| "grad_norm": 2.3442330740780277, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 1.0993, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05923183711244794, | |
| "grad_norm": 1.641034492875168, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 1.0402, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08884775566867191, | |
| "grad_norm": 0.8960224147096862, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.9534, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11846367422489588, | |
| "grad_norm": 0.6112485269393575, | |
| "learning_rate": 1.9980527694749952e-05, | |
| "loss": 0.8922, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14807959278111985, | |
| "grad_norm": 0.5441559417985111, | |
| "learning_rate": 1.986180478852149e-05, | |
| "loss": 0.8552, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17769551133734382, | |
| "grad_norm": 0.4332021689446225, | |
| "learning_rate": 1.963645895935632e-05, | |
| "loss": 0.8282, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2073114298935678, | |
| "grad_norm": 0.38382303949408464, | |
| "learning_rate": 1.930692657985482e-05, | |
| "loss": 0.8229, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23692734844979177, | |
| "grad_norm": 0.4088289227254056, | |
| "learning_rate": 1.887677045685188e-05, | |
| "loss": 0.8224, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2665432670060157, | |
| "grad_norm": 0.35283270050172044, | |
| "learning_rate": 1.8350641311400813e-05, | |
| "loss": 0.8073, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2961591855622397, | |
| "grad_norm": 0.34333417676546135, | |
| "learning_rate": 1.773422749654988e-05, | |
| "loss": 0.7977, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32577510411846367, | |
| "grad_norm": 0.37999964258525404, | |
| "learning_rate": 1.7034193496547903e-05, | |
| "loss": 0.7877, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.35539102267468764, | |
| "grad_norm": 0.38222978618089914, | |
| "learning_rate": 1.6258107872407376e-05, | |
| "loss": 0.7982, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3850069412309116, | |
| "grad_norm": 0.35207288860321423, | |
| "learning_rate": 1.5414361432856475e-05, | |
| "loss": 0.7722, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4146228597871356, | |
| "grad_norm": 0.35345620477306205, | |
| "learning_rate": 1.4512076515391375e-05, | |
| "loss": 0.7741, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.44423877834335956, | |
| "grad_norm": 0.34380353959645715, | |
| "learning_rate": 1.356100835825547e-05, | |
| "loss": 0.7852, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.47385469689958354, | |
| "grad_norm": 0.3590313717420253, | |
| "learning_rate": 1.257143962968246e-05, | |
| "loss": 0.7667, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5034706154558075, | |
| "grad_norm": 0.3745326526316502, | |
| "learning_rate": 1.155406925472205e-05, | |
| "loss": 0.7706, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5330865340120314, | |
| "grad_norm": 0.36610230798525156, | |
| "learning_rate": 1.0519896741619803e-05, | |
| "loss": 0.77, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5627024525682555, | |
| "grad_norm": 0.36979148543489454, | |
| "learning_rate": 9.480103258380198e-06, | |
| "loss": 0.7772, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5923183711244794, | |
| "grad_norm": 0.3425948386153071, | |
| "learning_rate": 8.445930745277953e-06, | |
| "loss": 0.7531, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5923183711244794, | |
| "eval_loss": 0.7880966663360596, | |
| "eval_runtime": 15.4807, | |
| "eval_samples_per_second": 8.268, | |
| "eval_steps_per_second": 4.134, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6219342896807034, | |
| "grad_norm": 0.3393558650030019, | |
| "learning_rate": 7.428560370317542e-06, | |
| "loss": 0.757, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6515502082369273, | |
| "grad_norm": 0.35020627160992307, | |
| "learning_rate": 6.438991641744531e-06, | |
| "loss": 0.7682, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6811661267931514, | |
| "grad_norm": 0.31392880355113534, | |
| "learning_rate": 5.487923484608629e-06, | |
| "loss": 0.7624, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7107820453493753, | |
| "grad_norm": 0.30053120714503473, | |
| "learning_rate": 4.5856385671435285e-06, | |
| "loss": 0.7515, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7403979639055993, | |
| "grad_norm": 0.3521300494936363, | |
| "learning_rate": 3.7418921275926245e-06, | |
| "loss": 0.7539, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7700138824618232, | |
| "grad_norm": 0.3165591064584497, | |
| "learning_rate": 2.965806503452098e-06, | |
| "loss": 0.7556, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7996298010180471, | |
| "grad_norm": 0.32826601854304405, | |
| "learning_rate": 2.265772503450122e-06, | |
| "loss": 0.7586, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8292457195742712, | |
| "grad_norm": 0.3032411643319663, | |
| "learning_rate": 1.6493586885991908e-06, | |
| "loss": 0.75, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8588616381304951, | |
| "grad_norm": 0.31678218955007104, | |
| "learning_rate": 1.1232295431481222e-06, | |
| "loss": 0.7568, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8884775566867191, | |
| "grad_norm": 0.3005522639748892, | |
| "learning_rate": 6.930734201451817e-07, | |
| "loss": 0.7668, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.918093475242943, | |
| "grad_norm": 0.30229315868039475, | |
| "learning_rate": 3.635410406436857e-07, | |
| "loss": 0.7616, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9477093937991671, | |
| "grad_norm": 0.2885290642352494, | |
| "learning_rate": 1.3819521147851122e-07, | |
| "loss": 0.7609, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.977325312355391, | |
| "grad_norm": 0.28006098540662894, | |
| "learning_rate": 1.947230525005006e-08, | |
| "loss": 0.7448, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9950948634891255, | |
| "step": 168, | |
| "total_flos": 76567849992192.0, | |
| "train_loss": 0.8028926622299921, | |
| "train_runtime": 10782.6732, | |
| "train_samples_per_second": 2.004, | |
| "train_steps_per_second": 0.016 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 168, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 76567849992192.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |