Training in progress, step 20, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e5eb4a883937e96c950093ab4d6b86746b8c7e18ce6915bc47da02a55ffd429
+oid sha256:fca60095f86e48a89c115bed3de4d6e6d51ec2903783fab00ce19205817f38c5
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5317de9449b47a23fdbfcc31bffea58037950a2d4a4c2f2a29c8e87618fd6a5
+oid sha256:67a4bb936e346a4b958bd78c0646fdd71067c03febe3739e01fb6f283bec2fc9
 size 350603

last-checkpoint/trainer_state.json

@@ -11,38 +11,38 @@
   "log_history": [
     {
       "epoch": 0.025,
-      "grad_norm": 0.12107392400503159,
+      "grad_norm": 0.11081302911043167,
       "learning_rate": 1.6e-06,
-      "loss": 10.970177459716798,
+      "loss": 11.017050170898438,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 0.11410612612962723,
+      "grad_norm": 0.1046549528837204,
       "learning_rate": 3.6e-06,
-      "loss": 10.963343811035156,
+      "loss": 11.006002807617188,
       "step": 10
     },
     {
       "epoch": 0.075,
-      "grad_norm": 0.10789366811513901,
+      "grad_norm": 0.1001407653093338,
       "learning_rate": 3.995627254437549e-06,
-      "loss": 10.965518951416016,
+      "loss": 10.999064636230468,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 0.10765355825424194,
+      "grad_norm": 0.10080653429031372,
       "learning_rate": 3.9778957412029366e-06,
-      "loss": 10.960431671142578,
+      "loss": 10.995188903808593,
       "step": 20
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 9.4993894993895e-05,
-      "eval_loss": 10.96417236328125,
-      "eval_runtime": 91.763,
-      "eval_samples_per_second": 10.898,
+      "eval_accuracy": 1.7094017094017095e-05,
+      "eval_loss": 10.983185768127441,
+      "eval_runtime": 91.7452,
+      "eval_samples_per_second": 10.9,
       "eval_steps_per_second": 1.82,
       "step": 20
     }