Training in progress, step 28

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 3.431561927399424e+16,
-    "train_loss": 0.5415381789207458,
-    "train_runtime": 23.1548,
-    "train_samples_per_second": 19.089,
-    "train_steps_per_second": 1.209
+    "train_loss": 0.37262931891850065,
+    "train_runtime": 25.36,
+    "train_samples_per_second": 17.429,
+    "train_steps_per_second": 1.104
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c04d97f1960e5ae8ceec0c675206575abf86be9ef3b694338739b889175cf3e9
+oid sha256:f768932a537601c5c8400a48b0cf6198083fd5a4748127cc4268a3b85f30d866
 size 343866868

runs/Jan15_18-44-55_a99b99d67614/events.out.tfevents.1736966698.a99b99d67614.505.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf3167010faa89626cf4e6c4323492acdb74e666c7178b3fbaa6ddb47019a12
+size 17504

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 3.431561927399424e+16,
-    "train_loss": 0.5415381789207458,
-    "train_runtime": 23.1548,
-    "train_samples_per_second": 19.089,
-    "train_steps_per_second": 1.209
+    "train_loss": 0.37262931891850065,
+    "train_runtime": 25.36,
+    "train_samples_per_second": 17.429,
+    "train_steps_per_second": 1.104
 }

trainer_state.json

@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 0.35714285714285715,
-      "grad_norm": 0.18035346269607544,
+      "grad_norm": 0.1482367217540741,
       "learning_rate": 0.00012857142857142858,
-      "loss": 0.6226,
+      "loss": 0.4295,
       "step": 10
     },
     {
       "epoch": 0.7142857142857143,
-      "grad_norm": 0.16660097241401672,
+      "grad_norm": 0.13569863140583038,
       "learning_rate": 5.714285714285714e-05,
-      "loss": 0.5136,
+      "loss": 0.3544,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 28,
       "total_flos": 3.431561927399424e+16,
-      "train_loss": 0.5415381789207458,
-      "train_runtime": 23.1548,
-      "train_samples_per_second": 19.089,
-      "train_steps_per_second": 1.209
+      "train_loss": 0.37262931891850065,
+      "train_runtime": 25.36,
+      "train_samples_per_second": 17.429,
+      "train_steps_per_second": 1.104
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2777ca7067d0f22175b2b1c135794ab1428bb365b0bac16e5b69bf007c2dace8
+oid sha256:07f4e1e85db05c79f514d40e2fb5102fd42d1d377b76b06b3142464edb633aba
 size 5304