Add model, config, tokenizer, and custom code

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on the iva_mt_wslot dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.0849
-- Bleu: 0.0032
-- Gen Len: 5.1554
+- Loss: 6.0821
+- Bleu: 0.009
+- Gen Len: 5.5922
 
 ## Model description
 
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 32
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 5
@@ -55,16 +55,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Bleu   | Gen Len |
 |:-------------:|:------:|:----:|:---------------:|:------:|:-------:|
-| 7.3868        | 0.9992 | 636  | 7.0446          | 0.0    | 2.7952  |
-| 6.5132        | 2.0    | 1273 | 6.4775          | 0.0504 | 7.3246  |
-| 6.0691        | 2.9992 | 1909 | 6.2289          | 0.0007 | 3.6667  |
-| 5.8713        | 4.0    | 2546 | 6.1236          | 0.0096 | 6.216   |
-| 5.7608        | 4.9961 | 3180 | 6.0849          | 0.0032 | 5.1554  |
+| 7.4016        | 0.9992 | 636  | 7.0495          | 0.0009 | 3.7101  |
+| 6.5244        | 2.0    | 1273 | 6.4803          | 0.0268 | 7.1527  |
+| 6.101         | 2.9992 | 1909 | 6.2219          | 0.0068 | 5.5162  |
+| 5.919         | 4.0    | 2546 | 6.1188          | 0.0106 | 5.9943  |
+| 5.7827        | 4.9961 | 3180 | 6.0821          | 0.009  | 5.5922  |
 
 
 ### Framework versions
 
-- Transformers 4.46.2
-- Pytorch 2.5.0+cu121
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
 - Datasets 3.1.0
-- Tokenizers 0.20.3
+- Tokenizers 0.19.1

config.json

@@ -16,6 +16,6 @@
   "pad_token_id": 1,
   "share_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.2",
+  "transformers_version": "4.44.2",
   "vocab_size": 28297
 }

generation_config.json

@@ -4,5 +4,5 @@
   "decoder_start_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.46.2"
+  "transformers_version": "4.44.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038d0644a5d3cbc88516779d64980ba234fd511a458251ce718926f5a1d983ed
+oid sha256:f5ae73bafcbaf410d89666c8d86969ae195b9c753ded9e33d0d5daa2a0cc5b5c
 size 109582088

runs/Nov17_14-07-59_ef9497a56ea3/events.out.tfevents.1731852481.ef9497a56ea3.338.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd29a20d2af069b51dcd7d203fca8f2d866f8fe4942ad32feff6a106b0591848
+size 20281

tokenizer_config.json

@@ -34,7 +34,7 @@
     }
   },
   "bos_token": "<bos>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "eos_token": "<eos>",
   "model_max_length": 256,
   "pad_token": "<pad>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:409f5332a77fd169428b007f8b529523e7bd1e1f55ec793941d2cf55bb9cc620
-size 5496
+oid sha256:cd890c205aa8a72772cb1a5e32a1df9b10bc8f47140268d35196a933c7b159cc
+size 5368