End of training

README.md

@@ -2,7 +2,7 @@
 tags:
 - generated_from_trainer
 datasets:
-- coco_dataset_script
+- ydshieh/coco_dataset_script
 model-index:
 - name: clip-roberta-finetuned
   results: []
@@ -13,7 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # clip-roberta-finetuned
 
-This model was trained from scratch on the coco_dataset_script dataset.
+This model was trained from scratch on the ydshieh/coco_dataset_script 2017 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5789
 
 ## Model description
 

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 3.0,
-    "eval_loss": 1.5879405736923218,
-    "eval_runtime": 43.7011,
-    "eval_samples_per_second": 572.389,
-    "eval_steps_per_second": 2.243,
-    "train_loss": 0.3107225017701603,
-    "train_runtime": 5244.1454,
-    "train_samples_per_second": 338.522,
-    "train_steps_per_second": 1.323
+    "eval_loss": 1.5789210796356201,
+    "eval_runtime": 43.7782,
+    "eval_samples_per_second": 571.381,
+    "eval_steps_per_second": 2.239,
+    "train_loss": 0.32176698312902396,
+    "train_runtime": 5235.8231,
+    "train_samples_per_second": 339.06,
+    "train_steps_per_second": 1.325
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "eval_loss": 1.5879405736923218,
-    "eval_runtime": 43.7011,
-    "eval_samples_per_second": 572.389,
-    "eval_steps_per_second": 2.243
+    "eval_loss": 1.5789210796356201,
+    "eval_runtime": 43.7782,
+    "eval_samples_per_second": 571.381,
+    "eval_steps_per_second": 2.239
 }

runs/Feb08_07-51-31_c6de909f9f29/events.out.tfevents.1707384112.c6de909f9f29.2229.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75619e7ded02b8aa52bf4189949caa0dd52972f557de07959164747334bbf987
+size 359

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.3107225017701603,
-    "train_runtime": 5244.1454,
-    "train_samples_per_second": 338.522,
-    "train_steps_per_second": 1.323
+    "train_loss": 0.32176698312902396,
+    "train_runtime": 5235.8231,
+    "train_samples_per_second": 339.06,
+    "train_steps_per_second": 1.325
 }

trainer_state.json

@@ -11,43 +11,43 @@
     {
       "epoch": 0.22,
       "learning_rate": 4.639561707035756e-05,
-      "loss": 0.8543,
+      "loss": 1.0025,
       "step": 500
     },
     {
       "epoch": 0.43,
       "learning_rate": 4.2791234140715114e-05,
-      "loss": 0.512,
+      "loss": 0.518,
       "step": 1000
     },
     {
       "epoch": 0.65,
       "learning_rate": 3.9186851211072664e-05,
-      "loss": 0.4291,
+      "loss": 0.4347,
       "step": 1500
     },
     {
       "epoch": 0.87,
       "learning_rate": 3.558246828143022e-05,
-      "loss": 0.3857,
+      "loss": 0.3828,
       "step": 2000
     },
     {
       "epoch": 1.08,
       "learning_rate": 3.1978085351787776e-05,
-      "loss": 0.3264,
+      "loss": 0.3254,
       "step": 2500
     },
     {
       "epoch": 1.3,
       "learning_rate": 2.8373702422145332e-05,
-      "loss": 0.2763,
+      "loss": 0.2748,
       "step": 3000
     },
     {
       "epoch": 1.51,
       "learning_rate": 2.4769319492502884e-05,
-      "loss": 0.2598,
+      "loss": 0.2603,
       "step": 3500
     },
     {
@@ -65,35 +65,35 @@
     {
       "epoch": 2.16,
       "learning_rate": 1.395617070357555e-05,
-      "loss": 0.185,
+      "loss": 0.1851,
       "step": 5000
     },
     {
       "epoch": 2.38,
       "learning_rate": 1.0351787773933102e-05,
-      "loss": 0.1686,
+      "loss": 0.1683,
       "step": 5500
     },
     {
       "epoch": 2.6,
       "learning_rate": 6.747404844290659e-06,
-      "loss": 0.1595,
+      "loss": 0.159,
       "step": 6000
     },
     {
       "epoch": 2.81,
       "learning_rate": 3.143021914648212e-06,
-      "loss": 0.1537,
+      "loss": 0.1536,
       "step": 6500
     },
     {
       "epoch": 3.0,
       "step": 6936,
       "total_flos": 2.370754172808069e+17,
-      "train_loss": 0.3107225017701603,
-      "train_runtime": 5244.1454,
-      "train_samples_per_second": 338.522,
-      "train_steps_per_second": 1.323
+      "train_loss": 0.32176698312902396,
+      "train_runtime": 5235.8231,
+      "train_samples_per_second": 339.06,
+      "train_steps_per_second": 1.325
     }
   ],
   "logging_steps": 500,