update ckpt, bleuu

README.md

@@ -71,21 +71,22 @@ optimizer used is Adam with a learning rate of 3e-4, β1 = 0.9, β2 = 0.98 and
 ε = 1e-8, a weight decay of 0.01, learning rate warmup for 1,000 steps and linear decay of the learning
 rate after.
 
-We tracked experiments using Tensorboard which can be found in `Training Metrics` tab.
+We tracked experiments using Tensorboard which can be found in `Training Metrics` tab. BLEU scores for languages other than English might be wrongly tracked but the model gives good performance in other languages too as evident from the evaluation scores.
 
 #### **Pretraining Results 📊**
 
-Our model reached **eval loss of ~2.6** around ~70K steps. Here are the BLEU^ scores for different languages:
+Our model reached **eval loss of ~2.6** around ~60k steps. Here are the BLEU scores (out of 1) for different languages:
 
 |Language                  |BLEU-1|BLEU-2|BLEU-3|BLEU-4|
 |--------------------------|------|------|------|------|
-|English                   | 0.163| 0.127| 0.10 | 0.081|
-|Spanish                   | 0.171| 0.133| 0.114| 0.082|
-|German                    | 0.165| 0.129| 0.103| 0.077|
-|French                    | 0.162| 0.124| 0.104| 0.073|
+|English                   | 0.13083| 0.08887| 0.06681 | 0.04899|
+|Spanish                   | 0.15981| 0.09858| 0.06918| 0.04776|
+|German                    | 0.14234| 0.09817| 0.07405| 0.0515|
+|French                    | 0.13021| 0.08862| 0.06598| 0.04647|
 
-^BLEU scores are out of 1
+Model used: ckpt-51999/
 
+In order to reproduce the results, one can use the [evaluation script](https://github.com/gchhablani/multilingual-image-captioning/blob/main/evaluation.py) available in this project's repository.
 
 ## **App Demo**
 

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e476868cd065e62e2bb97c737b2b0f008b2a87b9ebf0ed0ee85b536313c250
+oid sha256:e19869c5129cb6338a9213928b4f0f4bf9dd6dfb418db64eaf1a1cd74af8e438
 size 2188672582

logs/{events.out.tfevents.1626777663.t1v-n-e32efd45-w-0.1846718.3.v2 → events.out.tfevents.1626901021.t1v-n-e32efd45-w-0.2243015.3.v2}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e6c4ab6e9bb14ec893541f156b36d17bea7c9b8d8ba677bf80d7a0bb6c5853d
-size 13753034
+oid sha256:08b67ae69db766025a6e695b192868ab8e00f02bc3ebe79b139f9066d8bdc677
+size 9032126