End of training

README.md

@@ -20,10 +20,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # smoke_test_glm4v_checkpoints
 
-This model is a fine-tuned version of [zai-org/GLM-OCR](https://huggingface.co/zai-org/GLM-OCR) on an unknown dataset.
+This model is a fine-tuned version of [zai-org/GLM-OCR](https://huggingface.co/zai-org/GLM-OCR) on the gujarati_ocr_stream dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5868
-- Accuracy: 0.5556
+- Loss: 2.5668
+- Accuracy: 0.5594
 
 ## Model description
 

all_results.json

@@ -2,12 +2,12 @@
     "epoch": 1.3076923076923077,
     "eval_accuracy": 0.5594251982846505,
     "eval_loss": 2.566760301589966,
-    "eval_runtime": 2.0028,
-    "eval_samples_per_second": 24.965,
-    "eval_steps_per_second": 3.495,
+    "eval_runtime": 2.0398,
+    "eval_samples_per_second": 24.512,
+    "eval_steps_per_second": 3.432,
     "total_flos": 197425390977024.0,
     "train_loss": 2.7674348831176756,
-    "train_runtime": 14.1312,
-    "train_samples_per_second": 5.661,
-    "train_steps_per_second": 0.354
+    "train_runtime": 14.3041,
+    "train_samples_per_second": 5.593,
+    "train_steps_per_second": 0.35
 }

eval_results.json

@@ -2,7 +2,7 @@
     "epoch": 1.3076923076923077,
     "eval_accuracy": 0.5594251982846505,
     "eval_loss": 2.566760301589966,
-    "eval_runtime": 2.0028,
-    "eval_samples_per_second": 24.965,
-    "eval_steps_per_second": 3.495
+    "eval_runtime": 2.0398,
+    "eval_samples_per_second": 24.512,
+    "eval_steps_per_second": 3.432
 }

runs/Apr09_05-18-42_cs-01knr8f8jy7kcvx4v0ce8jkn3q-1tpz/events.out.tfevents.1775711944.cs-01knr8f8jy7kcvx4v0ce8jkn3q-1tpz.131664.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4e73b6a031c0f4a80319852aa0106e65509edc06f2177c72ae89b158ea6685
+size 405

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 1.3076923076923077,
     "total_flos": 197425390977024.0,
     "train_loss": 2.7674348831176756,
-    "train_runtime": 14.1312,
-    "train_samples_per_second": 5.661,
-    "train_steps_per_second": 0.354
+    "train_runtime": 14.3041,
+    "train_samples_per_second": 5.593,
+    "train_steps_per_second": 0.35
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "epoch": 0.6153846153846154,
       "eval_accuracy": 0.5348454543007923,
       "eval_loss": 2.749584436416626,
-      "eval_runtime": 2.0771,
-      "eval_samples_per_second": 24.072,
-      "eval_steps_per_second": 3.37,
+      "eval_runtime": 2.0604,
+      "eval_samples_per_second": 24.267,
+      "eval_steps_per_second": 3.397,
       "step": 2
     },
     {
@@ -50,9 +50,9 @@
       "epoch": 1.0,
       "eval_accuracy": 0.5556479950956826,
       "eval_loss": 2.586768388748169,
-      "eval_runtime": 2.0364,
-      "eval_samples_per_second": 24.553,
-      "eval_steps_per_second": 3.437,
+      "eval_runtime": 2.0408,
+      "eval_samples_per_second": 24.5,
+      "eval_steps_per_second": 3.43,
       "step": 4
     },
     {
@@ -67,9 +67,9 @@
       "step": 5,
       "total_flos": 197425390977024.0,
       "train_loss": 2.7674348831176756,
-      "train_runtime": 14.1312,
-      "train_samples_per_second": 5.661,
-      "train_steps_per_second": 0.354
+      "train_runtime": 14.3041,
+      "train_samples_per_second": 5.593,
+      "train_steps_per_second": 0.35
     }
   ],
   "logging_steps": 1,