Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e88543caffb17042c4489aa47963a8388a8188b4f108028e5318e46ae3201eb
+oid sha256:f2b36db500f39f055e2df1755f95d37a99705ea67e05cc5185de69479fb1a53d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d97e28e6fe7124508f025ed977f93c4ac26d551de1f57dcfcd98b95871cc47b8
+oid sha256:07d2249d5307f0b64e5aa82b94bbf3904d13fa4ab0be666492d0de4a8cab9f5e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afb383c7427b2624c032eb9cec3a33da0380c9292fc9c147c59c840fa8dd709
+oid sha256:8232c99b3b9bd101763ab8cfa0b9f26a6a08232b451d165ce3fa8ae3b32d33cd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011938872970391596,
+  "epoch": 0.002387774594078319,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 1.6249,
       "step": 9
+    },
+    {
+      "epoch": 0.0014326647564469914,
+      "grad_norm": 5.267549514770508,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.0863,
+      "step": 12
+    },
+    {
+      "epoch": 0.0017908309455587394,
+      "grad_norm": 3.9862494468688965,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.9606,
+      "step": 15
+    },
+    {
+      "epoch": 0.0019102196752626551,
+      "eval_loss": 0.8825110197067261,
+      "eval_runtime": 204.4853,
+      "eval_samples_per_second": 17.248,
+      "eval_steps_per_second": 8.627,
+      "step": 16
+    },
+    {
+      "epoch": 0.002148997134670487,
+      "grad_norm": 2.57089900970459,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.8719,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7511608746049536.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null