"
],
"text/html": [
"\n",
" \n",
" \n",
"
\n",
" [251/251 00:21, Epoch 1/1]\n",
"
\n",
" \n",
" \n",
" | Epoch | \n",
" Training Loss | \n",
" Validation Loss | \n",
"
\n",
" \n",
" \n",
" \n",
" | 1 | \n",
" No log | \n",
" 1.876339 | \n",
"
\n",
" \n",
"
"
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.11/dist-packages/transformers/modeling_utils.py:2758: UserWarning: Moving the following attributes in the config to the generation config: {'max_length': 512, 'num_beams': 4, 'bad_words_ids': [[61949]]}. You are seeing this warning because you've set generation parameters in the model config, as opposed to in the generation config.\n",
" warnings.warn(\n",
"There were missing keys in the checkpoint model loaded: ['model.encoder.embed_tokens.weight', 'model.encoder.embed_positions.weight', 'model.decoder.embed_tokens.weight', 'model.decoder.embed_positions.weight', 'lm_head.weight'].\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"TrainOutput(global_step=251, training_loss=2.212838830225971, metrics={'train_runtime': 45.16, 'train_samples_per_second': 44.376, 'train_steps_per_second': 5.558, 'total_flos': 67932323315712.0, 'train_loss': 2.212838830225971, 'epoch': 1.0})"
]
},
"metadata": {},
"execution_count": 29
}
]
},
{
"cell_type": "code",
"source": [
"def translate(text, src_lang=\"en\", tgt_lang=\"hi\"):\n",
" inputs = tokenizer(text, return_tensors=\"pt\")\n",
" # Move inputs to the same device as the model\n",
" # Assuming model is on cuda:0 or default cuda device\n",
" for k in inputs:\n",
" inputs[k] = inputs[k].to(model.device)\n",
" translated_tokens = model.generate(**inputs, max_length=50)\n",
" return tokenizer.decode(translated_tokens[0], skip_special_tokens=True)\n",
"\n",
"print(translate(\"good man\"))"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "OqV0Fiud09tt",
"outputId": "fcd79a5e-7dbe-4138-b7c8-226318c4ac7c"
},
"execution_count": 30,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"अच्छा आदमी\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"save_directory = \"translate_model\"\n",
"\n",
"model.save_pretrained(save_directory)\n",
"\n",
"tokenizer.save_pretrained(save_directory)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "5pDS9v4lBynb",
"outputId": "652888cf-660d-40cd-fe5a-a53d27880b0a"
},
"execution_count": 33,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"('translate_model/tokenizer_config.json',\n",
" 'translate_model/special_tokens_map.json',\n",
" 'translate_model/vocab.json',\n",
" 'translate_model/source.spm',\n",
" 'translate_model/target.spm',\n",
" 'translate_model/added_tokens.json')"
]
},
"metadata": {},
"execution_count": 33
}
]
},
{
"cell_type": "code",
"source": [
"import shutil\n",
"\n",
"\n",
"folder_path = \"/content/translate_model\"\n",
"zip_name = \"translate_model_finetune.zip\"\n",
"\n",
"\n",
"shutil.make_archive(zip_name.replace('.zip', ''), 'zip', folder_path)\n",
"\n",
"print(f\"Folder '{folder_path}' has been zipped as '{zip_name}'.\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "9SuQLZ8KMnLl",
"outputId": "27e6b557-ee86-425a-a47c-7d0f8ca812ab"
},
"execution_count": 35,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Folder '/content/translate_model' has been zipped as 'translate_model_finetune.zip'.\n"
]
}
]
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "qP6EM7VnWXaM"
},
"execution_count": null,
"outputs": []
}
]
}