checkpoint 171895

README.md

@@ -1,74 +1,61 @@
 ---
 license: apache-2.0
-datasets:
-- opus100
-language:
-- bn
-- en
+base_model: Helsinki-NLP/opus-mt-en-inc
+tags:
+- generated_from_trainer
 metrics:
-- sacrebleu
-pipeline_tag: translation
-widget:
-- text: "Will you come home tonight?"
-  example_title: "Example 1"
-- text: "I am so sorry this is a day late, guys. Unfortunately, my internet was down so it was out of my control."
-  example_title: "Example 2"
+- bleu
 model-index:
-- name: shhossain/opus-mt-en-to-bn
-  results:
-  - task:
-      type: translation
-      name: Translation
-    dataset:
-      type: opus100
-      name: opus100
-      split: validation       
-    metrics:
-      - type: Bleu
-        value: 12.537400
-      - type: Validation Loss
-        value: 2.120669
-      - type: Training Loss
-        value: 1.771200
+- name: opus-mt-en-inc-finetuned-en-to-bn-fp16
+  results: []
 ---
 
-# English-Bengali Translation Model
-This model is finetuned on `Helsinki-NLP/opus-mt-en-inc` for English to Bangla Translation.
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-- **Developed by:** [shhossain](https://github.com/shhossain)
-- **Model type:** [transformer-align]
-- **Language(s) (NLP):** [English, Bengali]
-- **License:** [apache-2.0]
-- **Finetuned from model [Helsinki-NLP/opus-mt-en-inc]:** [Helsinki-NLP/opus-mt-en-inc](Helsinki-NLP/opus-mt-en-inc)
+# opus-mt-en-inc-finetuned-en-to-bn-fp16
 
-## Use with transformers
-```python
-from transformers import pipeline
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-inc](https://huggingface.co/Helsinki-NLP/opus-mt-en-inc) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8782
+- Bleu: 21.613
+- Gen Len: 21.9459
 
-pipe = pipeline("translation", model="shhossain/opus-mt-en-to-bn")
-```
+## Model description
 
-## Use with BanglaTranslationKit
+More information needed
 
-BanglaTranslationKit is an open-source translation package for offline conversion between both Bengali and English languages (English to Bangla and Bangla to English)
+## Intended uses & limitations
 
-### Installation
+More information needed
 
-```bash
-pip install bntrans
-```
+## Training and evaluation data
 
-### Usage
+More information needed
 
-You can use this package to translate any Bangla to English or English to Bangla.
+## Training procedure
 
-```python
-from bntrans import Translator
+### Training hyperparameters
 
-translator = Translator(src="en", dest="bn")
-translation = translator.translate("Hello world!")  #  ্যালো বিশ্ব!
-print(translation)
-```
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
 
-More info on [BanglaTranslationKit](https://github.com/shhossain/BanglaTranslationKit)
+### Training results
 
+| Training Loss | Epoch | Step   | Validation Loss | Bleu   | Gen Len |
+|:-------------:|:-----:|:------:|:---------------:|:------:|:-------:|
+| 1.9652        | 1.0   | 171895 | 1.8782          | 21.613 | 21.9459 |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/opus-mt-en-inc-finetuned-en-to-bn/checkpoint-22000",
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-inc",
   "activation_dropout": 0.0,
   "activation_function": "swish",
   "add_bias_logits": false,
@@ -55,7 +55,7 @@
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.32.0",
+  "transformers_version": "4.32.1",
   "use_cache": true,
   "vocab_size": 61760
 }

generation_config.json

@@ -12,5 +12,5 @@
   "num_beams": 4,
   "pad_token_id": 61759,
   "renormalize_logits": true,
-  "transformers_version": "4.32.0"
+  "transformers_version": "4.32.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9285076ac677c350c66999179ede16ae2008fc73c1520aeb4d67f36b118c32a9
-size 303368453
+oid sha256:62094b0cd201aa52496ab6db2ff2aa4eb331375c2637f4f82967388f43dde033
+size 303372037

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f234669df19c9814c570a9349ec1ca21462043991de4ea20e86e01b8f5fb67c
+size 4219