End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: gshields/translate_model_error_v0.4
+base_model: Helsinki-NLP/opus-mt-hi-en
 tags:
 - generated_from_trainer
 metrics:
@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # inverse_translate_model_v0.4
 
-This model is a fine-tuned version of [gshields/translate_model_error_v0.4](https://huggingface.co/gshields/translate_model_error_v0.4) on an unknown dataset.
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-hi-en](https://huggingface.co/Helsinki-NLP/opus-mt-hi-en) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 9.4895
-- Bleu: 0.0048
-- Gen Len: 283.3333
+- Loss: 3.1252
+- Bleu: 20.5627
+- Gen Len: 11.3333
 
 ## Model description
 
@@ -48,10 +48,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len  |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
-| No log        | 1.0   | 8    | 9.7714          | 0.0044 | 283.3333 |
-| No log        | 2.0   | 16   | 9.4895          | 0.0048 | 283.3333 |
+| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| No log        | 1.0   | 8    | 3.1641          | 21.0809 | 11.1    |
+| No log        | 2.0   | 16   | 3.1252          | 20.5627 | 11.3333 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "gshields/translate_model_error_v0.4",
+  "_name_or_path": "Helsinki-NLP/opus-mt-hi-en",
+  "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "swish",
   "add_bias_logits": false,
@@ -10,7 +11,7 @@
   "attention_dropout": 0.0,
   "bad_words_ids": [
     [
-      61949
+      61126
     ]
   ],
   "bos_token_id": 0,
@@ -21,15 +22,14 @@
   "decoder_ffn_dim": 2048,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
-  "decoder_start_token_id": 61949,
-  "decoder_vocab_size": 61950,
+  "decoder_start_token_id": 61126,
+  "decoder_vocab_size": 61127,
   "dropout": 0.1,
   "encoder_attention_heads": 8,
   "encoder_ffn_dim": 2048,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
   "eos_token_id": 0,
-  "extra_pos_embeddings": 61950,
   "forced_eos_token_id": 0,
   "id2label": {
     "0": "LABEL_0",
@@ -48,14 +48,14 @@
   "model_type": "marian",
   "normalize_before": false,
   "normalize_embedding": false,
-  "num_beams": 4,
+  "num_beams": 6,
   "num_hidden_layers": 6,
-  "pad_token_id": 61949,
+  "pad_token_id": 61126,
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.33.1",
   "use_cache": true,
-  "vocab_size": 61950
+  "vocab_size": 61127
 }

generation_config.json

@@ -1,16 +1,16 @@
 {
   "bad_words_ids": [
     [
-      61949
+      61126
     ]
   ],
   "bos_token_id": 0,
-  "decoder_start_token_id": 61949,
+  "decoder_start_token_id": 61126,
   "eos_token_id": 0,
   "forced_eos_token_id": 0,
   "max_length": 512,
-  "num_beams": 4,
-  "pad_token_id": 61949,
+  "num_beams": 6,
+  "pad_token_id": 61126,
   "renormalize_logits": true,
   "transformers_version": "4.33.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d2ef0ed95c54e640d44832eb35f199e174529c0149c8a235bf7c3bf9bc1273e
-size 303758277
+oid sha256:ec44cb5fe1963493ebaa6e5d9b2b8fb1ba9a928ece546996877e1029831811ab
+size 302069509

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a43cf21240f267b3cf5378779429571b11c7adb5e1e700f48f985da7bfe9fa9f
+oid sha256:c3387efea539a129f64edace18516817140b0bbe026605dcdc83ff40f7b1a317
 size 4155