Training in progress, step 10800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b157da58de763723afba58a487dce4affd5aa4ea8842fbd4da7c7f50fe12697
+oid sha256:7ef4eecea3629afcace64b5a917ddd966970bb97958ca98caf3b5b8b8f4cb9f9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b66793c07b1b0a84c67dfb67dabbc667be148932241d1875f1cf4cef5d93cb
+oid sha256:faa46c7ed1d599bf3e19190dd49f7e1e57d3c190ced1afb5d39e58b75b5b6e9d
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a19a56fa0d8bb9b191b59d03bf40b790346150a7f3d469cfde615d3a433c9a
+oid sha256:d3933564f2de09fa9ed32bd0876590ad1ced5b512ea947850a85c5527075c34c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a2e63dae0ad86e6af927f787db5624af1572bceb0832f3c088d78644536e527
+oid sha256:4b9b6db394b3d452474e4549621859e2d2c7908c6ab758c808d3d275e4c68c06
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007882828448086741,
+  "epoch": 0.008031561060314793,
   "eval_steps": 2000,
-  "global_step": 10600,
+  "global_step": 10800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -378,6 +378,13 @@
       "learning_rate": 1.9999877597068942e-05,
       "loss": 1.572,
       "step": 10600
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.2719645500183105,
+      "learning_rate": 1.9999872929636188e-05,
+      "loss": 1.5997,
+      "step": 10800
     }
   ],
   "logging_steps": 200,
@@ -385,7 +392,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 1.3848555079593984e+17,
+  "total_flos": 1.4106137221472256e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null