Training Step 3150

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a03d639092e06311eac92b0d6dcc0cbe1d4ca3c7e4205dd9f5f3122ea45b546
+oid sha256:682820912a0be395bc6ca06d0e7a4aa799531f51111dc0587455961aa3a5cf03
 size 175188712

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca388b29527b0775ba858dfdd1a22af407396fc57d7589c987af64a13623f99
+oid sha256:e47c51f6e873dff7c40af1e053cfefb38c9d92ace623800de897595899edbcaa
 size 349892271

training_config.json

@@ -61,7 +61,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x153041159340>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x152fe6bcdf10>",
   "wandb_table": null,
-  "optimizer": "AdamW (\nParameter Group 0\n    amsgrad: False\n    betas: (0.9, 0.999)\n    capturable: False\n    decoupled_weight_decay: True\n    differentiable: False\n    eps: 1e-08\n    foreach: None\n    fused: None\n    initial_lr: 0.0003\n    lr: 0.0002739638623053539\n    maximize: False\n    weight_decay: 0.10977513538342132\n)",
+  "optimizer": "AdamW (\nParameter Group 0\n    amsgrad: False\n    betas: (0.9, 0.999)\n    capturable: False\n    decoupled_weight_decay: True\n    differentiable: False\n    eps: 1e-08\n    foreach: None\n    fused: None\n    initial_lr: 0.0003\n    lr: 0.0002647836668194221\n    maximize: False\n    weight_decay: 0.12473733846918944\n)",
   "lr_scheduler": "<torch.optim.lr_scheduler.SequentialLR object at 0x152fef701f40>",
   "wd_scheduler": "<trainers.schedulers.weight_decay.WeightDecayScheduler object at 0x152fe6c44110>",
   "momentum_scheduler": "<trainers.schedulers.momentum.MomentumScheduler object at 0x152fe5892240>",