Add model, config, tokenizer, and custom code

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+datasets:
+- iva_mt_wslot
+metrics:
+- bleu
+model-index:
+- name: seq2seq-imlla-test
+  results: []
+---
+
+<!-- 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. -->
+
+# seq2seq-imlla-test
+
+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: 6.0796
+- Bleu: 0.0023
+- Gen Len: 3.9927
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Bleu   | Gen Len |
+|:-------------:|:------:|:----:|:---------------:|:------:|:-------:|
+| 7.3774        | 0.9992 | 636  | 7.0402          | 0.0    | 4.1578  |
+| 6.528         | 2.0    | 1273 | 6.4745          | 0.0141 | 9.5716  |
+| 6.0907        | 2.9992 | 1909 | 6.2223          | 0.0024 | 5.0011  |
+| 5.903         | 4.0    | 2546 | 6.1164          | 0.0019 | 4.0774  |
+| 5.7639        | 4.9961 | 3180 | 6.0796          | 0.0023 | 3.9927  |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,21 @@
+{
+  "architectures": [
+    "CustomSeq2SeqModel"
+  ],
+  "bos_token_id": 0,
+  "dec_emb_dim": 256,
+  "decoder_start_token_id": 1,
+  "dropout": 0.1,
+  "enc_emb_dim": 256,
+  "eos_token_id": 2,
+  "hidden_dim": 256,
+  "max_position_embeddings": 256,
+  "model_type": "custom_seq2seq",
+  "n_layers": 3,
+  "num_attention_heads": 8,
+  "pad_token_id": 1,
+  "share_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "vocab_size": 28297
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51f2e6520ca5fb0355143b0d067108cd2da104149e34136005b0e75d4a773b8
+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

runs/Nov17_14-35-11_ef9497a56ea3/events.out.tfevents.1731854111.ef9497a56ea3.338.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c0cbc09a4036cf0798dcde41486cc6dfd0efb8423ed0f912d1577965bb1697
+size 5412

runs/Nov17_14-36-17_ef9497a56ea3/events.out.tfevents.1731854178.ef9497a56ea3.338.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb8a145083e99b88e693aebce280739ae87f7b8ee0fc225406774dff06cfdd5
+size 20276

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:058909e475a26ab742bc7d902942df98013eab57ce081dad9668c780a87beb0b
+size 5368