Training Step 50625

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d3e3364699fe7944a74b912b34e13d19f897e43c31a4ed2454a5ebba67177e4
+oid sha256:cbdd393f7804d9cfdf4f0a7b635cf72a3b904cc97e2451831277271b5a01d131
 size 445494204

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81df843a14f4aae1d60497dc9ca8d8e8ecc1fee885ecfc78e67d913753caacda
+oid sha256:3932f74bb53ab0298d69ac5fa777f778387bc504ce520d9eba604315f1f95fee
 size 890995910

training_config.json

@@ -47,7 +47,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x1483a37b1150>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x1483a26ed940>",
   "wandb_table": "<wandb.sdk.data_types.table.Table object at 0x1484249297f0>",
-  "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: 0.0001500019227245448\n    maximize: False\n    weight_decay: 0.05\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: 0.00012133912722722001\n    maximize: False\n    weight_decay: 0.05\n)",
   "scheduler": "<torch.optim.lr_scheduler.SequentialLR object at 0x1483a46ae7b0>",
   "optimizer_class": "adamw",
   "scheduler_class": "cosine",