Fine-tuned Hausa-En educational model complete.

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-ha-en
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: hausaenglishchatbotmodel
+  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. -->
+
+# hausaenglishchatbotmodel
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ha-en](https://huggingface.co/Helsinki-NLP/opus-mt-ha-en) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1336
+- Bleu: 8.9109
+
+## 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: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu    |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| No log        | 1.0   | 33   | 0.1666          | 5.4192  |
+| No log        | 2.0   | 66   | 0.1532          | 15.0023 |
+| No log        | 3.0   | 99   | 0.1466          | 14.3780 |
+| No log        | 4.0   | 132  | 0.1448          | 15.1544 |
+| No log        | 5.0   | 165  | 0.1433          | 15.4036 |
+| No log        | 6.0   | 198  | 0.1425          | 14.6474 |
+| No log        | 7.0   | 231  | 0.1418          | 14.1405 |
+| No log        | 8.0   | 264  | 0.1417          | 20.3918 |
+| No log        | 9.0   | 297  | 0.1420          | 14.2228 |
+| No log        | 10.0  | 330  | 0.1415          | 20.6111 |
+| No log        | 11.0  | 363  | 0.1418          | 19.4349 |
+| No log        | 12.0  | 396  | 0.1417          | 19.0929 |
+| No log        | 13.0  | 429  | 0.1419          | 19.9174 |
+| No log        | 14.0  | 462  | 0.1419          | 19.9016 |
+| No log        | 15.0  | 495  | 0.1418          | 19.8220 |
+
+
+### Framework versions
+
+- Transformers 5.2.0
+- Pytorch 2.9.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,54 @@
+{
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 58088,
+  "decoder_vocab_size": 58089,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_decoder": false,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_hidden_layers": 6,
+  "pad_token_id": 58088,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "vocab_size": 58089
+}

generation_config.json

@@ -0,0 +1,43 @@
+{
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "bad_words_ids": [
+    [
+      58088
+    ]
+  ],
+  "decoder_start_token_id": 58088,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": [
+    0
+  ],
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "forced_eos_token_id": 0,
+  "length_penalty": 1.0,
+  "max_length": 512,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 4,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "pad_token_id": 58088,
+  "remove_invalid_values": false,
+  "renormalize_logits": true,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "target_lookbehind": 10,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.2.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fecf9d997392c86f91b647f6646ee1605ce94c5d5e153064fcc5d02dcf51ab2
+size 533714764

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff009c3f913456abb6fd297ec49eacad54fb6027c3994b0d936cbe371fcbba7
+size 782683

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142ff4b7d573fd3e868afe4d31c94625ae57e7351bc37b0197279797773e6dc9
+size 812660

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58088": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "custom",
+  "eos_token": "</s>",
+  "is_local": false,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "ha",
+  "sp_model_kwargs": {},
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e7ff47dc232c306989d415695c3482a175631b2ce29911f19bd996216ce0f3
+size 5393