End of training

all_results.json

@@ -4,8 +4,8 @@
     "eval_f1": 92.97352589089498,
     "eval_samples": 10788,
     "train_loss": 1.088201597354519,
-    "train_runtime": 823.8622,
+    "train_runtime": 725.1829,
     "train_samples": 88550,
-    "train_samples_per_second": 214.963,
-    "train_steps_per_second": 1.677
+    "train_samples_per_second": 244.214,
+    "train_steps_per_second": 1.906
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26181949daf0a3b96f33978b8a607d3a4f8bf5308e8fb64db8072291df9a61bd
+oid sha256:5c53de7a6f355194542f010b25d2591fb9ca83acda557a8734b3b17ed060f8d9
 size 277274547

runs/May25_20-50-55_gbnwp-pod015-2.ipu.graphcore.ai/events.out.tfevents.1653508449.gbnwp-pod015-2.ipu.graphcore.ai

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e361a1b62fee7a6b7cdf4106c18b0e541b0b79bb61c7c09e7980f840be675b90
-size 18514
+oid sha256:186aad98915e464332e767a86604d0d7dae601b07dc91cf95efcd7d4faf5bf41
+size 24991

runs/May25_20-50-55_gbnwp-pod015-2.ipu.graphcore.ai/events.out.tfevents.1653509467.gbnwp-pod015-2.ipu.graphcore.ai

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e06cd98d5592af878ca35bfbf167a3ba0e9e9368cc5d36c7efcda7ffd880c22e
+size 40

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 1.088201597354519,
-    "train_runtime": 823.8622,
+    "train_runtime": 725.1829,
     "train_samples": 88550,
-    "train_samples_per_second": 214.963,
-    "train_steps_per_second": 1.677
+    "train_samples_per_second": 244.214,
+    "train_steps_per_second": 1.906
 }

trainer_state.json

@@ -840,9 +840,9 @@
       "step": 1382,
       "total_flos": 5.175834887457866e+18,
       "train_loss": 1.088201597354519,
-      "train_runtime": 823.8622,
-      "train_samples_per_second": 214.963,
-      "train_steps_per_second": 1.677
+      "train_runtime": 725.1829,
+      "train_samples_per_second": 244.214,
+      "train_steps_per_second": 1.906
     }
   ],
   "max_steps": 1382,