| { | |
| "best_metric": 0.0012385094305500388, | |
| "best_model_checkpoint": "./model/checkpoint-500", | |
| "epoch": 30.0, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.482758620689655e-07, | |
| "loss": 0.1587, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_Acc": 1.0, | |
| "eval_loss": 0.006247001700103283, | |
| "eval_macro_F1": 1.0, | |
| "eval_runtime": 0.3079, | |
| "eval_samples_per_second": 324.744, | |
| "eval_steps_per_second": 12.99, | |
| "eval_weighted_F1": 1.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.620689655172412e-07, | |
| "loss": 0.1631, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_Acc": 0.99, | |
| "eval_loss": 0.0467730276286602, | |
| "eval_macro_F1": 0.988936829295276, | |
| "eval_runtime": 0.3093, | |
| "eval_samples_per_second": 323.311, | |
| "eval_steps_per_second": 12.932, | |
| "eval_weighted_F1": 0.9899657041708153, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 7.758620689655172e-07, | |
| "loss": 0.1274, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "eval_Acc": 1.0, | |
| "eval_loss": 0.003920665942132473, | |
| "eval_macro_F1": 1.0, | |
| "eval_runtime": 0.2879, | |
| "eval_samples_per_second": 347.397, | |
| "eval_steps_per_second": 13.896, | |
| "eval_weighted_F1": 1.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 6.896551724137931e-07, | |
| "loss": 0.108, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_Acc": 1.0, | |
| "eval_loss": 0.008137707598507404, | |
| "eval_macro_F1": 1.0, | |
| "eval_runtime": 0.2882, | |
| "eval_samples_per_second": 346.98, | |
| "eval_steps_per_second": 13.879, | |
| "eval_weighted_F1": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 6.03448275862069e-07, | |
| "loss": 0.1032, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "eval_Acc": 0.97, | |
| "eval_loss": 0.11218936741352081, | |
| "eval_macro_F1": 0.9676410311724732, | |
| "eval_runtime": 0.2888, | |
| "eval_samples_per_second": 346.313, | |
| "eval_steps_per_second": 13.853, | |
| "eval_weighted_F1": 0.9702621076475029, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 5.172413793103448e-07, | |
| "loss": 0.1117, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_Acc": 1.0, | |
| "eval_loss": 0.008067261427640915, | |
| "eval_macro_F1": 1.0, | |
| "eval_runtime": 0.2984, | |
| "eval_samples_per_second": 335.167, | |
| "eval_steps_per_second": 13.407, | |
| "eval_weighted_F1": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 4.310344827586206e-07, | |
| "loss": 0.0855, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "eval_Acc": 1.0, | |
| "eval_loss": 0.0037926011718809605, | |
| "eval_macro_F1": 1.0, | |
| "eval_runtime": 0.2856, | |
| "eval_samples_per_second": 350.082, | |
| "eval_steps_per_second": 14.003, | |
| "eval_weighted_F1": 1.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.4482758620689656e-07, | |
| "loss": 0.0871, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_Acc": 1.0, | |
| "eval_loss": 0.00232470384798944, | |
| "eval_macro_F1": 1.0, | |
| "eval_runtime": 0.2916, | |
| "eval_samples_per_second": 342.994, | |
| "eval_steps_per_second": 13.72, | |
| "eval_weighted_F1": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "learning_rate": 2.586206896551724e-07, | |
| "loss": 0.0746, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "eval_Acc": 1.0, | |
| "eval_loss": 0.0018292993772774935, | |
| "eval_macro_F1": 1.0, | |
| "eval_runtime": 0.3231, | |
| "eval_samples_per_second": 309.536, | |
| "eval_steps_per_second": 12.381, | |
| "eval_weighted_F1": 1.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 1.7241379310344828e-07, | |
| "loss": 0.0726, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_Acc": 1.0, | |
| "eval_loss": 0.0012385094305500388, | |
| "eval_macro_F1": 1.0, | |
| "eval_runtime": 0.2944, | |
| "eval_samples_per_second": 339.647, | |
| "eval_steps_per_second": 13.586, | |
| "eval_weighted_F1": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "learning_rate": 8.620689655172414e-08, | |
| "loss": 0.077, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "eval_Acc": 1.0, | |
| "eval_loss": 0.001301100361160934, | |
| "eval_macro_F1": 1.0, | |
| "eval_runtime": 0.2913, | |
| "eval_samples_per_second": 343.306, | |
| "eval_steps_per_second": 13.732, | |
| "eval_weighted_F1": 1.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0686, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_Acc": 1.0, | |
| "eval_loss": 0.0012519867159426212, | |
| "eval_macro_F1": 1.0, | |
| "eval_runtime": 0.2884, | |
| "eval_samples_per_second": 346.698, | |
| "eval_steps_per_second": 13.868, | |
| "eval_weighted_F1": 1.0, | |
| "step": 600 | |
| } | |
| ], | |
| "max_steps": 600, | |
| "num_train_epochs": 30, | |
| "total_flos": 2458772812339200.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |