| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 8.361204013377927, |
| "eval_steps": 500, |
| "global_step": 7500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.56, |
| "learning_rate": 2.8327759197324414e-05, |
| "loss": 0.2283, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.711111111111111, |
| "eval_loss": 0.18087100982666016, |
| "eval_runtime": 8.0851, |
| "eval_samples_per_second": 27.829, |
| "eval_steps_per_second": 1.237, |
| "step": 897 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 2.665551839464883e-05, |
| "loss": 0.2091, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 2.4983277591973243e-05, |
| "loss": 0.2122, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.7644444444444445, |
| "eval_loss": 0.1918957531452179, |
| "eval_runtime": 8.2002, |
| "eval_samples_per_second": 27.438, |
| "eval_steps_per_second": 1.219, |
| "step": 1794 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 2.331103678929766e-05, |
| "loss": 0.2129, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.79, |
| "learning_rate": 2.1638795986622073e-05, |
| "loss": 0.1977, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.7733333333333334, |
| "eval_loss": 0.1987731158733368, |
| "eval_runtime": 8.2946, |
| "eval_samples_per_second": 27.126, |
| "eval_steps_per_second": 1.206, |
| "step": 2691 |
| }, |
| { |
| "epoch": 3.34, |
| "learning_rate": 1.996655518394649e-05, |
| "loss": 0.1975, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.9, |
| "learning_rate": 1.8294314381270902e-05, |
| "loss": 0.2049, |
| "step": 3500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.7377777777777779, |
| "eval_loss": 0.20192378759384155, |
| "eval_runtime": 8.5276, |
| "eval_samples_per_second": 26.385, |
| "eval_steps_per_second": 1.173, |
| "step": 3588 |
| }, |
| { |
| "epoch": 4.46, |
| "learning_rate": 1.662207357859532e-05, |
| "loss": 0.202, |
| "step": 4000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.7733333333333332, |
| "eval_loss": 0.2126660943031311, |
| "eval_runtime": 8.5344, |
| "eval_samples_per_second": 26.364, |
| "eval_steps_per_second": 1.172, |
| "step": 4485 |
| }, |
| { |
| "epoch": 5.02, |
| "learning_rate": 1.4949832775919733e-05, |
| "loss": 0.1849, |
| "step": 4500 |
| }, |
| { |
| "epoch": 5.57, |
| "learning_rate": 1.3277591973244148e-05, |
| "loss": 0.2007, |
| "step": 5000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.7955555555555556, |
| "eval_loss": 0.20662625133991241, |
| "eval_runtime": 8.6442, |
| "eval_samples_per_second": 26.029, |
| "eval_steps_per_second": 1.157, |
| "step": 5382 |
| }, |
| { |
| "epoch": 6.13, |
| "learning_rate": 1.1605351170568563e-05, |
| "loss": 0.1798, |
| "step": 5500 |
| }, |
| { |
| "epoch": 6.69, |
| "learning_rate": 9.933110367892978e-06, |
| "loss": 0.1888, |
| "step": 6000 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.7911111111111111, |
| "eval_loss": 0.20552584528923035, |
| "eval_runtime": 8.6299, |
| "eval_samples_per_second": 26.072, |
| "eval_steps_per_second": 1.159, |
| "step": 6279 |
| }, |
| { |
| "epoch": 7.25, |
| "learning_rate": 8.260869565217392e-06, |
| "loss": 0.1983, |
| "step": 6500 |
| }, |
| { |
| "epoch": 7.8, |
| "learning_rate": 6.588628762541806e-06, |
| "loss": 0.1844, |
| "step": 7000 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8, |
| "eval_loss": 0.21319705247879028, |
| "eval_runtime": 8.5588, |
| "eval_samples_per_second": 26.289, |
| "eval_steps_per_second": 1.168, |
| "step": 7176 |
| }, |
| { |
| "epoch": 8.36, |
| "learning_rate": 4.916387959866221e-06, |
| "loss": 0.176, |
| "step": 7500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 8970, |
| "num_train_epochs": 10, |
| "save_steps": 1500, |
| "total_flos": 1834764136380000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
