Training Step 2520

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e55baba15d4df3b3780ab2bbd1bb527b651446e4f5475d375ff9ba21067075a9
+oid sha256:fda6fe810233aef75d80373722fe9e1a8954f3dc14685f6b97692620dca36680
 size 116239064

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5e304b7dcb6610c7db45684b08d19f7e75f39426d6af7241bb3728d3aca6bc0
+oid sha256:806753056829c1925fc652a5c538ea937c6970b3e08fb6f12ac4be8232ca8f26
 size 232451759

training_config.json

@@ -61,7 +61,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x154ce2c4f3e0>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x154ce36bd940>",
   "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: 0.0002884271473318095\n    maximize: False\n    weight_decay: 0.08338582430187574\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: 0.0002818720721208917\n    maximize: False\n    weight_decay: 0.0959439885666929\n)",
   "lr_scheduler": "<torch.optim.lr_scheduler.SequentialLR object at 0x154ce392dcd0>",
   "wd_scheduler": "<trainers.schedulers.weight_decay.WeightDecayScheduler object at 0x154ce392ddf0>",
   "momentum_scheduler": "<trainers.schedulers.momentum.MomentumScheduler object at 0x154ce392de20>",