Training Step 2205

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7850ea4511281d90084291442eebc7bb9e8e4aea15c14c70042f1d41ac36a623
+oid sha256:b6310bd7162db4cf924dcb0ffb33a78234cf55f248782e5be86fa7b861acc59a
 size 97225416

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c6d5ae73b82bdbbdb815faf0a21be896a7efd92cc3e46a400f6e1d8194b855
+oid sha256:84e4b76ef9c53a220d195c28f6f4b2b446db9336ec2d14054d5417f1c65effb1
 size 186100579

training_config.json

@@ -66,7 +66,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x14d8adf96f00>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x14d8ae47d280>",
   "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: 6.25e-05\n    lr: 1.373440000000002e-06\n    maximize: False\n    weight_decay: 0.04000129827171861\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: 6.25e-05\n    lr: 1.4981800000000044e-06\n    maximize: False\n    weight_decay: 0.04000176735857941\n)",
   "lr_scheduler": "<torch.optim.lr_scheduler.SequentialLR object at 0x14d8ad275340>",
   "wd_scheduler": "<trainers.schedulers.weight_decay.WeightDecayScheduler object at 0x14d8ae8119a0>",
   "momentum_scheduler": "<trainers.schedulers.momentum.MomentumScheduler object at 0x14d8ae811940>",