Training Step 1575

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32d67c0e94a4b16f5bbf7b91ee1441b54d6ac09164664e11e1aeecfb7377402b
+oid sha256:0072844ad0ca96ac4ecf9050728b0b1a0708847d40d96bbe1dc0a84d6f1e7112
 size 374952416

trainer_state.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8232469eadd6851202575e7e978c23c153ee1877d71e8cba0f50f1b995a34d
+oid sha256:98ce6dae0ec9ba7576e75379b6bc81484c36105b7df91270a5ebba7495f48ddb
 size 733099875

training_config.json

@@ -61,7 +61,7 @@
   "hf_api": "<huggingface_hub.hf_api.HfApi object at 0x1549f71da0f0>",
   "wandb_writer": "<wandb.sdk.wandb_run.Run object at 0x1549ff67a750>",
   "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: 8.387096774193496e-06\n    maximize: False\n    weight_decay: 0.04000922838120785\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: 9.983870967741894e-06\n    maximize: False\n    weight_decay: 0.04001442385781745\n)",
   "lr_scheduler": "<torch.optim.lr_scheduler.SequentialLR object at 0x1549f703bbf0>",
   "wd_scheduler": "<trainers.schedulers.weight_decay.WeightDecayScheduler object at 0x1549ffc515e0>",
   "momentum_scheduler": "<trainers.schedulers.momentum.MomentumScheduler object at 0x1549ffc51ee0>",