Update space

FinGPT.ipynb

@@ -23,7 +23,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -54,9 +54,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Dataset({\n",
+       "    features: ['input', 'output', 'instruction'],\n",
+       "    num_rows: 9543\n",
+       "})"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "from datasets import load_dataset\n",
     "import datasets\n",
@@ -86,9 +100,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "19086\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "(19086, 3)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "tmp_dataset = datasets.concatenate_datasets([tfns]*2)\n",
     "train_dataset = tmp_dataset\n",
@@ -114,9 +146,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "8204ff4d7ae048508ff011ff341df7b3",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "formatting..:   0%|          | 0/19086 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "import json\n",
     "from tqdm.notebook import tqdm\n",
@@ -155,7 +202,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -207,9 +254,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ee7846a30c5d4d59be6bd5e2cf6c1870",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Saving the dataset (0/1 shards):   0%|          | 0/19086 [00:00<?, ? examples/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# The script then creates a Hugging Face Dataset object from the generator and saves it to disk.\n",
     "save_path = './data/dataset_new'\n",
@@ -236,14 +298,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "W0801 20:19:58.973000 23260 site-packages\\torch\\distributed\\elastic\\multiprocessing\\redirects.py:29] NOTE: Redirects are currently not supported in Windows or MacOs.\n"
+      "W0804 14:22:55.473000 584 site-packages\\torch\\distributed\\elastic\\multiprocessing\\redirects.py:29] NOTE: Redirects are currently not supported in Windows or MacOs.\n"
      ]
     }
    ],
@@ -300,7 +362,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -321,7 +383,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -335,7 +397,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4bc8b4c85e974cfe806fda92d57ad1c3",
+       "model_id": "85d1520006a04d289fe3431da7df7e42",
        "version_major": 2,
        "version_minor": 0
       },
@@ -456,7 +518,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -478,7 +540,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -664,7 +726,7 @@
     "trainer.train()\n",
     "writer.close()\n",
     "# save model\n",
-    "model.save_pretrained(training_args.output_dir)"
+    "# model.save_pretrained(training_args.output_dir)"
    ]
   },
   {
@@ -683,7 +745,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -696,7 +758,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "014c4259e386457ca0892de97c5a8ec3",
+       "model_id": "f632e66d18914e13a9febb54f4e9ee42",
        "version_major": 2,
        "version_minor": 0
       },
@@ -783,7 +845,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -805,21 +867,155 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 299/299 [00:48<00:00,  6.23it/s]"
+      "  0%|          | 0/299 [00:01<?, ?it/s]\n"
      ]
     },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Acc: 0.8756281407035176. F1 macro: 0.8401912464851741. F1 micro: 0.8756281407035176. F1 weighted (BloombergGPT): 0.8753926635410131. \n"
+      "Unexpected exception formatting exception. Falling back to standard exception\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "\n"
+      "Traceback (most recent call last):\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 3667, in run_code\n",
+      "    exec(code_obj, self.user_global_ns, self.user_ns)\n",
+      "  File \"C:\\Users\\23524\\AppData\\Local\\Temp\\ipykernel_584\\2487751523.py\", line 5, in <module>\n",
+      "    res = test_tfns(model, tokenizer, batch_size = batch_size)\n",
+      "          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\fingpt\\tfns.py\", line 62, in test_tfns\n",
+      "    res = model.generate(**tokens, max_length=512)\n",
+      "          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\peft\\peft_model.py\", line 1148, in generate\n",
+      "    outputs = self.base_model.generate(*args, **kwargs)\n",
+      "              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\torch\\utils\\_contextlib.py\", line 120, in decorate_context\n",
+      "    return func(*args, **kwargs)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\transformers\\generation\\utils.py\", line 1522, in generate\n",
+      "    return self.greedy_search(\n",
+      "           ^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\transformers\\generation\\utils.py\", line 2339, in greedy_search\n",
+      "    outputs = self(\n",
+      "              ^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1773, in _wrapped_call_impl\n",
+      "    return self._call_impl(*args, **kwargs)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1784, in _call_impl\n",
+      "    return forward_call(*args, **kwargs)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\accelerate\\hooks.py\", line 165, in new_forward\n",
+      "    output = module._old_forward(*args, **kwargs)\n",
+      "             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"C:\\Users\\23524/.cache\\huggingface\\modules\\transformers_modules\\THUDM\\chatglm2-6b\\d2e2d91789248536a747d9ce60642a336444186c\\modeling_chatglm.py\", line 937, in forward\n",
+      "    transformer_outputs = self.transformer(\n",
+      "                          ^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1773, in _wrapped_call_impl\n",
+      "    return self._call_impl(*args, **kwargs)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1784, in _call_impl\n",
+      "    return forward_call(*args, **kwargs)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\accelerate\\hooks.py\", line 165, in new_forward\n",
+      "    output = module._old_forward(*args, **kwargs)\n",
+      "             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"C:\\Users\\23524/.cache\\huggingface\\modules\\transformers_modules\\THUDM\\chatglm2-6b\\d2e2d91789248536a747d9ce60642a336444186c\\modeling_chatglm.py\", line 807, in forward\n",
+      "    inputs_embeds = self.embedding(input_ids)\n",
+      "                    ^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1773, in _wrapped_call_impl\n",
+      "    return self._call_impl(*args, **kwargs)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1784, in _call_impl\n",
+      "    return forward_call(*args, **kwargs)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\accelerate\\hooks.py\", line 165, in new_forward\n",
+      "    output = module._old_forward(*args, **kwargs)\n",
+      "             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"C:\\Users\\23524/.cache\\huggingface\\modules\\transformers_modules\\THUDM\\chatglm2-6b\\d2e2d91789248536a747d9ce60642a336444186c\\modeling_chatglm.py\", line 723, in forward\n",
+      "    words_embeddings = self.word_embeddings(input_ids)\n",
+      "                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1773, in _wrapped_call_impl\n",
+      "    return self._call_impl(*args, **kwargs)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1784, in _call_impl\n",
+      "    return forward_call(*args, **kwargs)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\accelerate\\hooks.py\", line 165, in new_forward\n",
+      "    output = module._old_forward(*args, **kwargs)\n",
+      "             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\torch\\nn\\modules\\sparse.py\", line 192, in forward\n",
+      "    return F.embedding(\n",
+      "           ^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\torch\\nn\\functional.py\", line 2546, in embedding\n",
+      "    return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "torch.AcceleratorError: CUDA error: out of memory\n",
+      "Search for `cudaErrorMemoryAllocation' in https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html for more information.\n",
+      "CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.\n",
+      "For debugging consider passing CUDA_LAUNCH_BLOCKING=1\n",
+      "Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.\n",
+      "\n",
+      "\n",
+      "During handling of the above exception, another exception occurred:\n",
+      "\n",
+      "Traceback (most recent call last):\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 2176, in showtraceback\n",
+      "    stb = self.InteractiveTB.structured_traceback(\n",
+      "          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\IPython\\core\\ultratb.py\", line 1182, in structured_traceback\n",
+      "    return FormattedTB.structured_traceback(\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\IPython\\core\\ultratb.py\", line 1053, in structured_traceback\n",
+      "    return VerboseTB.structured_traceback(\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\IPython\\core\\ultratb.py\", line 861, in structured_traceback\n",
+      "    formatted_exceptions: list[list[str]] = self.format_exception_as_a_whole(\n",
+      "                                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\IPython\\core\\ultratb.py\", line 773, in format_exception_as_a_whole\n",
+      "    frames.append(self.format_record(record))\n",
+      "                  ^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\IPython\\core\\ultratb.py\", line 651, in format_record\n",
+      "    _format_traceback_lines(\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\IPython\\core\\tbtools.py\", line 99, in _format_traceback_lines\n",
+      "    line = stack_line.render(pygmented=has_colors).rstrip(\"\\n\") + \"\\n\"\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\stack_data\\core.py\", line 360, in render\n",
+      "    start_line, lines = self.frame_info._pygmented_scope_lines\n",
+      "                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\stack_data\\utils.py\", line 145, in cached_property_wrapper\n",
+      "    value = obj.__dict__[self.func.__name__] = self.func(obj)\n",
+      "                                               ^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\stack_data\\core.py\", line 780, in _pygmented_scope_lines\n",
+      "    lines = _pygmented_with_ranges(formatter, code, ranges)\n",
+      "            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\stack_data\\utils.py\", line 165, in _pygmented_with_ranges\n",
+      "    return pygments.highlight(code, lexer, formatter).splitlines()\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\pygments\\__init__.py\", line 82, in highlight\n",
+      "    return format(lex(code, lexer), formatter, outfile)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\pygments\\__init__.py\", line 64, in format\n",
+      "    formatter.format(tokens, realoutfile)\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\pygments\\formatters\\terminal256.py\", line 250, in format\n",
+      "    return Formatter.format(self, tokensource, outfile)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\pygments\\formatter.py\", line 124, in format\n",
+      "    return self.format_unencoded(tokensource, outfile)\n",
+      "           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\pygments\\formatters\\terminal256.py\", line 256, in format_unencoded\n",
+      "    for ttype, value in tokensource:\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\stack_data\\utils.py\", line 158, in get_tokens\n",
+      "    for ttype, value in super().get_tokens(text):\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\pygments\\lexer.py\", line 270, in streamer\n",
+      "    for _, t, v in self.get_tokens_unprocessed(text):\n",
+      "  File \"d:\\anaconda\\envs\\fingpt-env\\Lib\\site-packages\\pygments\\lexer.py\", line 712, in get_tokens_unprocessed\n",
+      "    m = rexmatch(text, pos)\n",
+      "        ^^^^^^^^^^^^^^^^^^^\n",
+      "MemoryError\n"
      ]
     }
    ],

data/dataset_new/cache-73a60c7a93c40e4d.arrow

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7b6320f4c6a40b0bca5fd1336162679cc0774a05571c48f611cb5eb448d8e544
-size 124752

data/dataset_new/cache-fba1c6867270024b.arrow

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4c4dcf79222ef1e06ebad7422e5ec4ba475314461029ad502303af90ad7ecf25
-size 31424

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+transformers
+torch