Best model at Step 76565

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1330dd934c2a48b262e0d774377999df3a43bf20d111a4b138c642014648085
+oid sha256:85cba135c8a7eda44d3f1282537349f7d663e236cd881fd675922a63220edf23
 size 13101212

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3099f52c5e0ddf810ad5ebe3e1d2eacc11622d0082089f0305defd080e3c49e6
+oid sha256:9bc0c51b0bc26187d29b62b7399990898cdb17bf0bbf31db21ca92a0551b0344
 size 26209926

training_config.json

@@ -47,7 +47,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x153dd3661040>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x153dd36ad940>",
   "wandb_table": "<wandb.sdk.data_types.table.Table object at 0x153dd36ae900>",
-  "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: 1.5289315058583208e-05\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: 7.350326937918619e-06\n    maximize: False\n    weight_decay: 0.05\n)",
   "scheduler": "<torch.optim.lr_scheduler.SequentialLR object at 0x153e820e67b0>",
   "optimizer_class": "adamw",
   "scheduler_class": "cosine",