Training in progress, step 28

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 3.431561927399424e+16,
-    "train_loss": 0.5450659223965236,
-    "train_runtime": 39.5158,
-    "train_samples_per_second": 11.185,
-    "train_steps_per_second": 0.709
+    "train_loss": 0.5415381789207458,
+    "train_runtime": 23.1548,
+    "train_samples_per_second": 19.089,
+    "train_steps_per_second": 1.209
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:193b1c439fb1acd0626d17b8be3ec85d17730c962d3d83cd32823a9cb2cd5689
+oid sha256:c04d97f1960e5ae8ceec0c675206575abf86be9ef3b694338739b889175cf3e9
 size 343866868

runs/Jan15_18-39-57_a99b99d67614/events.out.tfevents.1736966444.a99b99d67614.505.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00e324264169655a190a031e2c72747fbe1b4a84671201f55302e867065868a9
-size 16472
+oid sha256:5488f9a5a02f0b85039b7b3f46d66ce3eccd642d6793b8c4c81ae0fd9ffc732b
+size 16741

runs/Jan15_18-41-54_a99b99d67614/events.out.tfevents.1736966626.a99b99d67614.505.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459fbe1d0e01013da554bbb2b896a7680437c2a42a6832e4e6244fc2a3e8f4a5
+size 17557

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 3.431561927399424e+16,
-    "train_loss": 0.5450659223965236,
-    "train_runtime": 39.5158,
-    "train_samples_per_second": 11.185,
-    "train_steps_per_second": 0.709
+    "train_loss": 0.5415381789207458,
+    "train_runtime": 23.1548,
+    "train_samples_per_second": 19.089,
+    "train_steps_per_second": 1.209
 }

trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 0.35714285714285715,
-      "grad_norm": 0.17901776731014252,
+      "grad_norm": 0.18035346269607544,
       "learning_rate": 0.00012857142857142858,
-      "loss": 0.6271,
+      "loss": 0.6226,
       "step": 10
     },
     {
       "epoch": 0.7142857142857143,
-      "grad_norm": 0.16683264076709747,
+      "grad_norm": 0.16660097241401672,
       "learning_rate": 5.714285714285714e-05,
-      "loss": 0.517,
+      "loss": 0.5136,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 28,
       "total_flos": 3.431561927399424e+16,
-      "train_loss": 0.5450659223965236,
-      "train_runtime": 39.5158,
-      "train_samples_per_second": 11.185,
-      "train_steps_per_second": 0.709
+      "train_loss": 0.5415381789207458,
+      "train_runtime": 23.1548,
+      "train_samples_per_second": 19.089,
+      "train_steps_per_second": 1.209
     }
   ],
   "logging_steps": 10,