Training in progress, step 10

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32bcd55b69273467370848543d59b267b0c7d994c802a5f375b642af3f90a290
+oid sha256:714c773a2d791e54be8f6815ab4233ba57e668409fcebca02c34a07d4535460b
 size 40422208

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.0091324200913242,
     "total_flos": 6.970544231337165e+16,
-    "train_loss": 4.537882995605469,
-    "train_runtime": 129.105,
-    "train_samples_per_second": 6.197,
-    "train_steps_per_second": 0.077
+    "train_loss": 4.542318725585938,
+    "train_runtime": 133.2368,
+    "train_samples_per_second": 6.004,
+    "train_steps_per_second": 0.075
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.0091324200913242,
     "total_flos": 6.970544231337165e+16,
-    "train_loss": 4.537882995605469,
-    "train_runtime": 129.105,
-    "train_samples_per_second": 6.197,
-    "train_steps_per_second": 0.077
+    "train_loss": 4.542318725585938,
+    "train_runtime": 133.2368,
+    "train_samples_per_second": 6.004,
+    "train_steps_per_second": 0.075
 }

trainer_state.json

@@ -11,19 +11,19 @@
   "log_history": [
     {
       "epoch": 0.0091324200913242,
-      "grad_norm": 0.6447323560714722,
+      "grad_norm": 0.7353410720825195,
       "learning_rate": 0.0001,
-      "loss": 4.5379,
+      "loss": 4.5423,
       "step": 10
     },
     {
       "epoch": 0.0091324200913242,
       "step": 10,
       "total_flos": 6.970544231337165e+16,
-      "train_loss": 4.537882995605469,
-      "train_runtime": 129.105,
-      "train_samples_per_second": 6.197,
-      "train_steps_per_second": 0.077
+      "train_loss": 4.542318725585938,
+      "train_runtime": 133.2368,
+      "train_samples_per_second": 6.004,
+      "train_steps_per_second": 0.075
     }
   ],
   "logging_steps": 10,