| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 6070, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.8352553542009887e-05, | |
| "loss": 0.2073, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.9750730374140043, | |
| "eval_loss": 0.08468761295080185, | |
| "eval_runtime": 237.9595, | |
| "eval_samples_per_second": 326.173, | |
| "eval_steps_per_second": 2.551, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1.6705107084019773e-05, | |
| "loss": 0.1121, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.986432880313593, | |
| "eval_loss": 0.04612227529287338, | |
| "eval_runtime": 237.9341, | |
| "eval_samples_per_second": 326.208, | |
| "eval_steps_per_second": 2.551, | |
| "step": 1214 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 1.5057660626029655e-05, | |
| "loss": 0.0823, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.9916420153073202, | |
| "eval_loss": 0.02950172871351242, | |
| "eval_runtime": 237.7454, | |
| "eval_samples_per_second": 326.467, | |
| "eval_steps_per_second": 2.553, | |
| "step": 1821 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 1.341021416803954e-05, | |
| "loss": 0.0593, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.9947999625222524, | |
| "eval_loss": 0.01778862066566944, | |
| "eval_runtime": 237.6987, | |
| "eval_samples_per_second": 326.531, | |
| "eval_steps_per_second": 2.554, | |
| "step": 2428 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 1.1762767710049425e-05, | |
| "loss": 0.0422, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 1.011532125205931e-05, | |
| "loss": 0.03, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_f1": 0.9961641778789194, | |
| "eval_loss": 0.012077880091965199, | |
| "eval_runtime": 237.5463, | |
| "eval_samples_per_second": 326.741, | |
| "eval_steps_per_second": 2.555, | |
| "step": 3035 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 8.467874794069193e-06, | |
| "loss": 0.0215, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_f1": 0.9972702243570969, | |
| "eval_loss": 0.008092650212347507, | |
| "eval_runtime": 237.646, | |
| "eval_samples_per_second": 326.603, | |
| "eval_steps_per_second": 2.554, | |
| "step": 3642 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 6.8204283360790776e-06, | |
| "loss": 0.0159, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_f1": 0.997763649349585, | |
| "eval_loss": 0.006471516564488411, | |
| "eval_runtime": 237.5957, | |
| "eval_samples_per_second": 326.673, | |
| "eval_steps_per_second": 2.555, | |
| "step": 4249 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 5.172981878088963e-06, | |
| "loss": 0.0141, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_f1": 0.9986060513769636, | |
| "eval_loss": 0.0039009908214211464, | |
| "eval_runtime": 237.631, | |
| "eval_samples_per_second": 326.624, | |
| "eval_steps_per_second": 2.554, | |
| "step": 4856 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 3.525535420098847e-06, | |
| "loss": 0.0089, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_f1": 0.9990627269958058, | |
| "eval_loss": 0.0030426010489463806, | |
| "eval_runtime": 237.6288, | |
| "eval_samples_per_second": 326.627, | |
| "eval_steps_per_second": 2.554, | |
| "step": 5463 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 1.8780889621087318e-06, | |
| "loss": 0.0079, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 2.3064250411861617e-07, | |
| "loss": 0.0057, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_f1": 0.9991682773970597, | |
| "eval_loss": 0.002530897269025445, | |
| "eval_runtime": 237.7374, | |
| "eval_samples_per_second": 326.478, | |
| "eval_steps_per_second": 2.553, | |
| "step": 6070 | |
| } | |
| ], | |
| "max_steps": 6070, | |
| "num_train_epochs": 10, | |
| "total_flos": 1.8083196174016512e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |