Training in progress, step 14500

README.md

@@ -15,17 +15,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [NourFakih/image-captioning-Vit-GPT2-Flickr8k](https://huggingface.co/NourFakih/image-captioning-Vit-GPT2-Flickr8k) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.2346
-- eval_rouge1: 40.7779
-- eval_rouge2: 15.1884
-- eval_rougeL: 36.8863
-- eval_rougeLsum: 36.8581
-- eval_gen_len: 11.586
-- eval_runtime: 583.5999
-- eval_samples_per_second: 4.284
-- eval_steps_per_second: 1.071
-- epoch: 2.33
-- step: 14500
+- eval_loss: 0.2359
+- eval_rouge1: 40.7947
+- eval_rouge2: 15.3254
+- eval_rougeL: 36.9574
+- eval_rougeLsum: 36.9431
+- eval_gen_len: 11.504
+- eval_runtime: 588.289
+- eval_samples_per_second: 4.25
+- eval_steps_per_second: 1.062
+- epoch: 2.25
+- step: 14000
 
 ## Model description
 

runs/May14_18-03-36_bcca55e92abc/events.out.tfevents.1715709834.bcca55e92abc.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a4828d24bbf946b47d73efc1249352c961d7a92aae5eaa2a970154b73ee80e
+size 9239

runs/May14_18-05-01_bcca55e92abc/events.out.tfevents.1715709904.bcca55e92abc.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8052136f0a91322bace147404feed9f000009d9889f63efc956e24aaecc1743f
+size 9975

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf83a468c99f29afd397edd443b7797dba8cd8d10566c5abddc57f5f8ba36f6
-size 5176
+oid sha256:4e104d75eaa70fd22a3f9710ee8aff69fc7731a02b1a20a6e4611bf8589cfa4e
+size 5240