Training Step 630

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09bed1e0d89889aae2f289010b766c1cadb8fccf4ab76f69bbc98e8ddec971bc
+oid sha256:c6618102062dfe863132dd67575016e91cf9dc4ae027eb29be9de7b0dc134b52
 size 124660456

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa1061a97cc424d0b35921ca39679bf6a74dd5c88045643ef8da14f835cdb0d
+oid sha256:2d13f50349f2b3a94e4f98b0644602d3da7feafffc62128ee728b93c72bc3c80
 size 215673699

training_config.json

@@ -61,7 +61,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x14e641e1e600>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x14e642ade690>",
   "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: 0.0002\n    lr: 5.1935483870967665e-06\n    maximize: False\n    weight_decay: 0.040002296128245685\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: 0.0002\n    lr: 8.387096774193515e-06\n    maximize: False\n    weight_decay: 0.04000921372729599\n)",
   "lr_scheduler": "<torch.optim.lr_scheduler.SequentialLR object at 0x14e642129e50>",
   "wd_scheduler": "<trainers.schedulers.weight_decay.WeightDecayScheduler object at 0x14e642129f40>",
   "momentum_scheduler": "<trainers.schedulers.momentum.MomentumScheduler object at 0x14e642129e80>",