Training in progress, epoch 0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "microsoft/phi-2",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,8 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "fc2",
+    "fc1",
     "v_proj",
-    "k_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9791595178e2c022ea24fe5360aa7af0060a60c77d5b2f35583ba9045871ca6
-size 31486304
+oid sha256:b3dc96a838978069f70bac32e97b1ef192924aca0ef3b8d35e67035a4223c6e9
+size 73433680

phi-2-custom.ipynb

@@ -547,7 +547,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 26,
    "id": "18d5599f-992d-4d8e-a90c-4d43774be473",
    "metadata": {},
    "outputs": [
@@ -555,7 +555,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "trainable params: 7,864,320 || all params: 2,787,548,160 || trainable%: 0.2821231974697076\n"
+      "trainable params: 18,350,080 || all params: 2,798,033,920 || trainable%: 0.6558204984162593\n"
      ]
     }
    ],
@@ -563,7 +563,7 @@
     "config = LoraConfig(\n",
     "    r=16,\n",
     "    lora_alpha=16,\n",
-    "    target_modules=[\"q_proj\",\"k_proj\",\"v_proj\"],\n",
+    "    #target_modules=[\"q_proj\",\"k_proj\",\"v_proj\"],\n",
     "    lora_dropout=0.05,\n",
     "    bias=\"none\",\n",
     "    task_type=\"CAUSAL_LM\"\n",
@@ -575,7 +575,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 27,
    "id": "baeee903-3dce-48b2-93c3-7a697d8c6daf",
    "metadata": {},
    "outputs": [],
@@ -587,10 +587,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 28,
    "id": "28a9b24a-a822-4fcb-96b3-d77b7ea30a5f",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
+      "To disable this warning, you can either:\n",
+      "\t- Avoid using `tokenizers` before the fork if possible\n",
+      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
+     ]
+    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -609,7 +619,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 29,
    "id": "1ee7fd2a-38e4-4f23-a978-0bdeeda64d8b",
    "metadata": {},
    "outputs": [],
@@ -624,7 +634,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 30,
    "id": "e84c29e2-843e-42c2-8c0f-324d392e671c",
    "metadata": {},
    "outputs": [
@@ -632,7 +642,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Tokenizing data: 100%|██████████| 16412/16412 [00:02<00:00, 6502.58 examples/s]\n"
+      "Tokenizing data: 100%|██████████| 16412/16412 [00:02<00:00, 7265.30 examples/s]\n"
      ]
     },
     {
@@ -644,7 +654,7 @@
        "})"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 30,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -659,7 +669,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 31,
    "id": "ac968254-5338-49df-950d-222b82647407",
    "metadata": {},
    "outputs": [],
@@ -680,7 +690,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 32,
    "id": "729df2d0-0890-4ac4-adf3-c167a6e9669d",
    "metadata": {},
    "outputs": [
@@ -719,7 +729,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 33,
    "id": "525f81a4-eb92-466e-bb9c-cd63122231ab",
    "metadata": {},
    "outputs": [
@@ -737,11 +747,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Requirement already satisfied: jupyterlab in /usr/local/lib/python3.11/site-packages (4.1.0)\n",
-      "Collecting jupyterlab\n",
-      "  Downloading jupyterlab-4.1.1-py3-none-any.whl.metadata (15 kB)\n",
-      "Collecting jupyterlab-git\n",
-      "  Downloading jupyterlab_git-0.50.0-py3-none-any.whl.metadata (31 kB)\n",
+      "Requirement already satisfied: jupyterlab in /usr/local/lib/python3.11/site-packages (4.1.1)\n",
+      "Requirement already satisfied: jupyterlab-git in /usr/local/lib/python3.11/site-packages (0.50.0)\n",
       "Requirement already satisfied: async-lru>=1.0.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (2.0.4)\n",
       "Requirement already satisfied: httpx>=0.25.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (0.26.0)\n",
       "Requirement already satisfied: ipykernel in /usr/local/lib/python3.11/site-packages (from jupyterlab) (6.29.1)\n",
@@ -754,8 +761,7 @@
       "Requirement already satisfied: packaging in /usr/local/lib/python3.11/site-packages (from jupyterlab) (23.2)\n",
       "Requirement already satisfied: tornado>=6.2.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab) (6.4)\n",
       "Requirement already satisfied: traitlets in /usr/local/lib/python3.11/site-packages (from jupyterlab) (5.14.1)\n",
-      "Collecting nbdime~=4.0.1 (from jupyterlab-git)\n",
-      "  Downloading nbdime-4.0.1-py3-none-any.whl.metadata (9.5 kB)\n",
+      "Requirement already satisfied: nbdime~=4.0.1 in /usr/local/lib/python3.11/site-packages (from jupyterlab-git) (4.0.1)\n",
       "Requirement already satisfied: nbformat in /usr/local/lib/python3.11/site-packages (from jupyterlab-git) (5.9.2)\n",
       "Requirement already satisfied: pexpect in /usr/local/lib/python3.11/site-packages (from jupyterlab-git) (4.9.0)\n",
       "Requirement already satisfied: anyio in /usr/local/lib/python3.11/site-packages (from httpx>=0.25.0->jupyterlab) (4.2.0)\n",
@@ -781,14 +787,10 @@
       "Requirement already satisfied: json5>=0.9.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab-server<3,>=2.19.0->jupyterlab) (0.9.14)\n",
       "Requirement already satisfied: jsonschema>=4.18.0 in /usr/local/lib/python3.11/site-packages (from jupyterlab-server<3,>=2.19.0->jupyterlab) (4.21.1)\n",
       "Requirement already satisfied: requests>=2.31 in /usr/local/lib/python3.11/site-packages (from jupyterlab-server<3,>=2.19.0->jupyterlab) (2.31.0)\n",
-      "Collecting colorama (from nbdime~=4.0.1->jupyterlab-git)\n",
-      "  Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n",
-      "Collecting gitpython!=2.1.4,!=2.1.5,!=2.1.6 (from nbdime~=4.0.1->jupyterlab-git)\n",
-      "  Downloading GitPython-3.1.41-py3-none-any.whl.metadata (14 kB)\n",
-      "Collecting jupyter-server-mathjax>=0.2.2 (from nbdime~=4.0.1->jupyterlab-git)\n",
-      "  Downloading jupyter_server_mathjax-0.2.6-py3-none-any.whl (3.1 MB)\n",
-      "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m265.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-      "\u001b[?25hRequirement already satisfied: pygments in /usr/local/lib/python3.11/site-packages (from nbdime~=4.0.1->jupyterlab-git) (2.17.2)\n",
+      "Requirement already satisfied: colorama in /usr/local/lib/python3.11/site-packages (from nbdime~=4.0.1->jupyterlab-git) (0.4.6)\n",
+      "Requirement already satisfied: gitpython!=2.1.4,!=2.1.5,!=2.1.6 in /usr/local/lib/python3.11/site-packages (from nbdime~=4.0.1->jupyterlab-git) (3.1.41)\n",
+      "Requirement already satisfied: jupyter-server-mathjax>=0.2.2 in /usr/local/lib/python3.11/site-packages (from nbdime~=4.0.1->jupyterlab-git) (0.2.6)\n",
+      "Requirement already satisfied: pygments in /usr/local/lib/python3.11/site-packages (from nbdime~=4.0.1->jupyterlab-git) (2.17.2)\n",
       "Requirement already satisfied: fastjsonschema in /usr/local/lib/python3.11/site-packages (from nbformat->jupyterlab-git) (2.19.1)\n",
       "Requirement already satisfied: comm>=0.1.1 in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (0.2.1)\n",
       "Requirement already satisfied: debugpy>=1.6.5 in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (1.8.0)\n",
@@ -797,8 +799,7 @@
       "Requirement already satisfied: nest-asyncio in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (1.6.0)\n",
       "Requirement already satisfied: psutil in /usr/local/lib/python3.11/site-packages (from ipykernel->jupyterlab) (5.9.8)\n",
       "Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.11/site-packages (from pexpect->jupyterlab-git) (0.7.0)\n",
-      "Collecting gitdb<5,>=4.0.1 (from gitpython!=2.1.4,!=2.1.5,!=2.1.6->nbdime~=4.0.1->jupyterlab-git)\n",
-      "  Downloading gitdb-4.0.11-py3-none-any.whl.metadata (1.2 kB)\n",
+      "Requirement already satisfied: gitdb<5,>=4.0.1 in /usr/local/lib/python3.11/site-packages (from gitpython!=2.1.4,!=2.1.5,!=2.1.6->nbdime~=4.0.1->jupyterlab-git) (4.0.11)\n",
       "Requirement already satisfied: decorator in /usr/local/lib/python3.11/site-packages (from ipython>=7.23.1->ipykernel->jupyterlab) (5.1.1)\n",
       "Requirement already satisfied: jedi>=0.16 in /usr/local/lib/python3.11/site-packages (from ipython>=7.23.1->ipykernel->jupyterlab) (0.19.1)\n",
       "Requirement already satisfied: prompt-toolkit<3.1.0,>=3.0.41 in /usr/local/lib/python3.11/site-packages (from ipython>=7.23.1->ipykernel->jupyterlab) (3.0.43)\n",
@@ -825,8 +826,7 @@
       "Requirement already satisfied: argon2-cffi-bindings in /usr/local/lib/python3.11/site-packages (from argon2-cffi->jupyter-server<3,>=2.4.0->jupyterlab) (21.2.0)\n",
       "Requirement already satisfied: six>=1.9.0 in /usr/local/lib/python3.11/site-packages (from bleach!=5.0.0->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (1.16.0)\n",
       "Requirement already satisfied: webencodings in /usr/local/lib/python3.11/site-packages (from bleach!=5.0.0->nbconvert>=6.4.4->jupyter-server<3,>=2.4.0->jupyterlab) (0.5.1)\n",
-      "Collecting smmap<6,>=3.0.1 (from gitdb<5,>=4.0.1->gitpython!=2.1.4,!=2.1.5,!=2.1.6->nbdime~=4.0.1->jupyterlab-git)\n",
-      "  Downloading smmap-5.0.1-py3-none-any.whl.metadata (4.3 kB)\n",
+      "Requirement already satisfied: smmap<6,>=3.0.1 in /usr/local/lib/python3.11/site-packages (from gitdb<5,>=4.0.1->gitpython!=2.1.4,!=2.1.5,!=2.1.6->nbdime~=4.0.1->jupyterlab-git) (5.0.1)\n",
       "Requirement already satisfied: parso<0.9.0,>=0.8.3 in /usr/local/lib/python3.11/site-packages (from jedi>=0.16->ipython>=7.23.1->ipykernel->jupyterlab) (0.8.3)\n",
       "Requirement already satisfied: fqdn in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (1.5.1)\n",
       "Requirement already satisfied: isoduration in /usr/local/lib/python3.11/site-packages (from jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (20.11.0)\n",
@@ -842,23 +842,6 @@
       "Requirement already satisfied: pycparser in /usr/local/lib/python3.11/site-packages (from cffi>=1.0.1->argon2-cffi-bindings->argon2-cffi->jupyter-server<3,>=2.4.0->jupyterlab) (2.21)\n",
       "Requirement already satisfied: arrow>=0.15.0 in /usr/local/lib/python3.11/site-packages (from isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (1.3.0)\n",
       "Requirement already satisfied: types-python-dateutil>=2.8.10 in /usr/local/lib/python3.11/site-packages (from arrow>=0.15.0->isoduration->jsonschema[format-nongpl]>=4.18.0->jupyter-events>=0.9.0->jupyter-server<3,>=2.4.0->jupyterlab) (2.8.19.20240106)\n",
-      "Downloading jupyterlab-4.1.1-py3-none-any.whl (11.4 MB)\n",
-      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.4/11.4 MB\u001b[0m \u001b[31m434.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-      "\u001b[?25hDownloading jupyterlab_git-0.50.0-py3-none-any.whl (1.2 MB)\n",
-      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m546.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-      "\u001b[?25hDownloading nbdime-4.0.1-py3-none-any.whl (5.9 MB)\n",
-      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.9/5.9 MB\u001b[0m \u001b[31m279.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-      "\u001b[?25hDownloading GitPython-3.1.41-py3-none-any.whl (196 kB)\n",
-      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.4/196.4 kB\u001b[0m \u001b[31m474.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-      "\u001b[?25hDownloading gitdb-4.0.11-py3-none-any.whl (62 kB)\n",
-      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m406.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
-      "\u001b[?25hDownloading smmap-5.0.1-py3-none-any.whl (24 kB)\n",
-      "Installing collected packages: smmap, colorama, gitdb, gitpython, jupyter-server-mathjax, nbdime, jupyterlab, jupyterlab-git\n",
-      "  Attempting uninstall: jupyterlab\n",
-      "    Found existing installation: jupyterlab 4.1.0\n",
-      "    Uninstalling jupyterlab-4.1.0:\n",
-      "      Successfully uninstalled jupyterlab-4.1.0\n",
-      "Successfully installed colorama-0.4.6 gitdb-4.0.11 gitpython-3.1.41 jupyter-server-mathjax-0.2.6 jupyterlab-4.1.1 jupyterlab-git-0.50.0 nbdime-4.0.1 smmap-5.0.1\n",
       "Note: you may need to restart the kernel to use updated packages.\n"
      ]
     }
@@ -914,7 +897,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "3bf553b6-b26c-49c3-9407-74c8d53a395e",
-   "metadata": {},
+   "metadata": {
+    "scrolled": true
+   },
    "outputs": [
     {
      "data": {
@@ -922,8 +907,8 @@
        "\n",
        "    <div>\n",
        "      \n",
-       "      <progress value='1044' max='1100' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [1044/1100 03:16 < 00:10, 5.31 it/s, Epoch 0.25/1]\n",
+       "      <progress value='1090' max='1100' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [1090/1100 12:44 < 00:07, 1.42 it/s, Epoch 0.27/1]\n",
        "    </div>\n",
        "    <table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
@@ -935,43 +920,43 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <td>100</td>\n",
-       "      <td>1.473100</td>\n",
+       "      <td>1.317300</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <td>200</td>\n",
-       "      <td>1.236100</td>\n",
+       "      <td>1.162700</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <td>300</td>\n",
-       "      <td>1.224800</td>\n",
+       "      <td>1.160700</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <td>400</td>\n",
-       "      <td>1.157900</td>\n",
+       "      <td>1.096200</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <td>500</td>\n",
-       "      <td>1.177800</td>\n",
+       "      <td>1.111000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <td>600</td>\n",
-       "      <td>1.150500</td>\n",
+       "      <td>1.088400</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <td>700</td>\n",
-       "      <td>1.178100</td>\n",
+       "      <td>1.122100</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <td>800</td>\n",
-       "      <td>1.166400</td>\n",
+       "      <td>1.102400</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <td>900</td>\n",
-       "      <td>1.138400</td>\n",
+       "      <td>1.067200</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <td>1000</td>\n",
-       "      <td>1.144000</td>\n",
+       "      <td>1.079000</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table><p>"
@@ -996,10 +981,55 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 24,
    "id": "263cc15e-8e9d-4bd8-9708-ec1638bc1165",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Loading checkpoint shards: 100%|██████████| 2/2 [00:02<00:00,  1.34s/it]\n",
+      "adapter_config.json: 100%|██████████| 592/592 [00:00<00:00, 3.99MB/s]\n",
+      "adapter_model.safetensors: 100%|██████████| 31.5M/31.5M [00:00<00:00, 117MB/s]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "PhiForCausalLM(\n",
+       "  (model): PhiModel(\n",
+       "    (embed_tokens): Embedding(51200, 2560)\n",
+       "    (embed_dropout): Dropout(p=0.0, inplace=False)\n",
+       "    (layers): ModuleList(\n",
+       "      (0-31): 32 x PhiDecoderLayer(\n",
+       "        (self_attn): PhiAttention(\n",
+       "          (q_proj): Linear(in_features=2560, out_features=2560, bias=True)\n",
+       "          (k_proj): Linear(in_features=2560, out_features=2560, bias=True)\n",
+       "          (v_proj): Linear(in_features=2560, out_features=2560, bias=True)\n",
+       "          (dense): Linear(in_features=2560, out_features=2560, bias=True)\n",
+       "          (rotary_emb): PhiRotaryEmbedding()\n",
+       "        )\n",
+       "        (mlp): PhiMLP(\n",
+       "          (activation_fn): NewGELUActivation()\n",
+       "          (fc1): Linear(in_features=2560, out_features=10240, bias=True)\n",
+       "          (fc2): Linear(in_features=10240, out_features=2560, bias=True)\n",
+       "        )\n",
+       "        (input_layernorm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True)\n",
+       "        (resid_dropout): Dropout(p=0.1, inplace=False)\n",
+       "      )\n",
+       "    )\n",
+       "    (final_layernorm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True)\n",
+       "  )\n",
+       "  (lm_head): Linear(in_features=2560, out_features=51200, bias=True)\n",
+       ")"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "from peft import PeftModel\n",
     "from transformers import AutoModelForCausalLM\n",
@@ -1012,13 +1042,526 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 25,
    "id": "8eef4f4f-52da-4ba9-8a22-2b7874420562",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "model-00001-of-00003.safetensors:   0%|          | 0.00/4.98G [00:00<?, ?B/s]\n",
+      "model-00002-of-00003.safetensors:   0%|          | 0.00/4.98G [00:00<?, ?B/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:   0%|          | 0.00/1.15G [00:00<?, ?B/s]\u001b[A\u001b[A\n",
+      "\n",
+      "\n",
+      "model-00001-of-00003.safetensors:   0%|          | 12.4M/4.98G [00:00<00:41, 121MB/s]\n",
+      "\n",
+      "model-00001-of-00003.safetensors:   0%|          | 24.5M/4.98G [00:00<01:02, 79.2MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:   0%|          | 16.0M/4.98G [00:00<01:34, 52.4MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:   1%|▏         | 16.0M/1.15G [00:00<00:26, 43.2MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:   1%|          | 33.2M/4.98G [00:00<01:30, 54.7MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:   3%|▎         | 32.0M/1.15G [00:00<00:18, 61.3MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:   1%|          | 48.0M/4.98G [00:00<01:25, 57.8MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:   4%|▍         | 48.0M/1.15G [00:00<00:18, 58.4MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:   1%|▏         | 64.0M/4.98G [00:01<01:32, 53.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:   2%|▏         | 80.0M/4.98G [00:01<01:14, 65.7MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:   2%|▏         | 80.0M/4.98G [00:01<01:44, 47.0MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:   2%|▏         | 96.0M/4.98G [00:01<01:31, 53.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:   2%|▏         | 112M/4.98G [00:02<01:27, 55.7MB/s] \u001b[A\n",
+      "model-00002-of-00003.safetensors:   3%|▎         | 128M/4.98G [00:02<01:21, 59.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:   3%|▎         | 128M/4.98G [00:02<01:39, 48.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:   3%|▎         | 160M/4.98G [00:02<01:19, 61.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:   4%|▎         | 176M/4.98G [00:02<01:23, 57.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:   4%|▍         | 192M/4.98G [00:03<01:16, 62.8MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:   4%|▍         | 208M/4.98G [00:03<01:16, 62.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:   4%|▍         | 224M/4.98G [00:03<01:19, 59.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:   5%|▍         | 240M/4.98G [00:04<01:17, 61.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:   5%|▌         | 256M/4.98G [00:04<01:17, 61.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:   5%|▌         | 272M/4.98G [00:04<01:24, 55.7MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:   7%|▋         | 80.0M/1.15G [00:04<01:41, 10.6MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:   6%|▌         | 288M/4.98G [00:05<01:22, 57.2MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:   8%|▊         | 96.0M/1.15G [00:05<01:13, 14.4MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:   6%|▌         | 304M/4.98G [00:05<01:28, 53.1MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:   6%|▋         | 313M/4.98G [00:05<01:24, 55.0MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:   6%|▋         | 320M/4.98G [00:05<01:20, 58.1MB/s] \u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:   6%|▋         | 320M/4.98G [00:05<01:39, 47.0MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:   7%|▋         | 336M/4.98G [00:05<01:18, 59.1MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:   7%|▋         | 352M/4.98G [00:06<01:17, 59.4MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  12%|█▏        | 144M/1.15G [00:06<00:38, 26.2MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:   8%|▊         | 384M/4.98G [00:06<01:07, 68.0MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  14%|█▍        | 160M/1.15G [00:06<00:32, 31.0MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:   8%|▊         | 400M/4.98G [00:06<01:11, 63.7MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:   8%|▊         | 384M/4.98G [00:06<01:25, 53.8MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:   8%|▊         | 416M/4.98G [00:07<01:11, 63.9MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  17%|█▋        | 192M/1.15G [00:07<00:22, 42.4MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:   9%|▊         | 432M/4.98G [00:07<01:10, 64.4MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  18%|█▊        | 208M/1.15G [00:07<00:21, 45.0MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:   9%|▉         | 448M/4.98G [00:07<01:09, 65.2MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  19%|█▉        | 224M/1.15G [00:07<00:18, 49.2MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:   9%|▉         | 464M/4.98G [00:07<01:20, 56.0MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:   9%|▊         | 432M/4.98G [00:08<01:51, 41.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  10%|▉         | 480M/4.98G [00:08<01:18, 57.1MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  22%|██▏       | 256M/1.15G [00:08<00:17, 52.1MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:   9%|▉         | 441M/4.98G [00:08<01:50, 41.0MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  10%|▉         | 496M/4.98G [00:08<01:20, 56.0MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:   9%|▉         | 448M/4.98G [00:08<02:36, 29.0MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  10%|█         | 512M/4.98G [00:08<01:20, 55.2MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:   9%|▉         | 464M/4.98G [00:08<01:58, 38.3MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  11%|█         | 528M/4.98G [00:09<01:26, 51.3MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  11%|█         | 544M/4.98G [00:09<01:22, 53.5MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  28%|██▊       | 320M/1.15G [00:09<00:17, 46.6MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  11%|█         | 560M/4.98G [00:09<01:16, 58.2MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  29%|█��▉       | 336M/1.15G [00:09<00:17, 47.1MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  12%|█▏        | 592M/4.98G [00:10<01:10, 62.1MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  31%|███       | 352M/1.15G [00:10<00:16, 48.3MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  11%|█         | 528M/4.98G [00:10<01:26, 51.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  11%|█         | 544M/4.98G [00:10<01:19, 55.8MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  12%|█▏        | 608M/4.98G [00:10<01:20, 54.3MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  13%|█▎        | 624M/4.98G [00:10<01:13, 59.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  12%|█▏        | 576M/4.98G [00:10<01:09, 63.7MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  13%|█▎        | 640M/4.98G [00:11<01:15, 57.7MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  12%|█▏        | 592M/4.98G [00:11<01:11, 61.1MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  13%|█▎        | 656M/4.98G [00:11<01:17, 56.0MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  12%|█▏        | 608M/4.98G [00:11<01:12, 60.3MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  36%|███▌      | 416M/1.15G [00:11<00:16, 45.4MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  13%|█▎        | 672M/4.98G [00:11<01:19, 54.3MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  37%|███▋      | 432M/1.15G [00:11<00:14, 48.6MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  13%|█▎        | 640M/4.98G [00:11<01:09, 62.3MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  14%|█▍        | 688M/4.98G [00:12<01:36, 44.6MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  13%|█▎        | 656M/4.98G [00:12<01:13, 59.0MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  14%|█▍        | 704M/4.98G [00:12<01:28, 48.3MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  15%|█▍        | 736M/4.98G [00:12<01:18, 53.9MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  14%|█▍        | 688M/4.98G [00:12<01:30, 47.4MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  15%|█▌        | 752M/4.98G [00:13<01:11, 58.9MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  14%|█▍        | 704M/4.98G [00:13<01:26, 49.2MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  43%|████▎     | 496M/1.15G [00:13<00:14, 44.5MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  44%|████▍     | 512M/1.15G [00:13<00:13, 47.9MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  15%|█▌        | 768M/4.98G [00:13<01:30, 46.6MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  46%|████▌     | 528M/1.15G [00:13<00:12, 48.7MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  16%|█▌        | 784M/4.98G [00:13<01:25, 49.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  15%|█▌        | 752M/4.98G [00:14<01:14, 56.8MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  16%|█▋        | 816M/4.98G [00:14<01:15, 55.1MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  49%|████▊     | 560M/1.15G [00:14<00:12, 49.4MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  15%|█▌        | 768M/4.98G [00:14<01:22, 51.2MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  50%|████▉     | 576M/1.15G [00:14<00:11, 51.9MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  17%|█▋        | 848M/4.98G [00:15<01:27, 47.4MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  17%|█▋        | 864M/4.98G [00:15<01:31, 45.0MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  18%|█▊        | 880M/4.98G [00:15<01:22, 49.6MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  18%|█▊        | 896M/4.98G [00:16<01:32, 44.3MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  18%|█▊        | 912M/4.98G [00:16<01:24, 48.1MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  19%|█▊        | 928M/4.98G [00:16<01:22, 49.4MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  19%|█▉        | 944M/4.98G [00:17<01:20, 49.9MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  20%|█▉        | 976M/4.98G [00:17<01:15, 53.2MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  20%|█▉        | 992M/4.98G [00:18<01:13, 54.3MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  20%|██        | 1.01G/4.98G [00:18<01:14, 53.6MB/s][A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  21%|██        | 1.02G/4.98G [00:18<01:13, 54.1MB/s][A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  21%|██        | 1.04G/4.98G [00:18<01:08, 57.6MB/s][A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  21%|██        | 1.06G/4.98G [00:19<01:07, 57.8MB/s][A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  22%|██▏       | 1.07G/4.98G [00:19<01:03, 61.4MB/s][A\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  71%|███████   | 816M/1.15G [00:19<00:05, 58.2MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  22%|██▏       | 1.09G/4.98G [00:19<01:03, 61.8MB/s][A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  72%|███████▏  | 832M/1.15G [00:19<00:05, 59.7MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  16%|█▌        | 800M/4.98G [00:19<05:43, 12.2MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  22%|██▏       | 1.10G/4.98G [00:19<01:05, 59.0MB/s][A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  16%|█▋        | 816M/4.98G [00:20<04:17, 16.2MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  22%|██▏       | 1.12G/4.98G [00:20<01:07, 57.0MB/s][A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  17%|█▋        | 832M/4.98G [00:20<03:19, 20.8MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  76%|███████▋  | 880M/1.15G [00:20<00:04, 66.3MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  23%|██▎       | 1.14G/4.98G [00:20<01:16, 50.4MB/s][A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  23%|██▎       | 1.15G/4.98G [00:20<01:09, 55.0MB/s][A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  23%|██▎       | 1.17G/4.98G [00:21<01:08, 55.6MB/s][A\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  80%|████████  | 928M/1.15G [00:21<00:03, 58.4MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  24%|██▍       | 1.18G/4.98G [00:21<01:09, 54.9MB/s][A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  24%|██▍       | 1.20G/4.98G [00:21<01:04, 59.0MB/s][A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  18%|█▊        | 880M/4.98G [00:21<02:24, 28.4MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  83%|████████▎ | 960M/1.15G [00:21<00:03, 57.5MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  24%|██▍       | 1.22G/4.98G [00:22<01:09, 53.9MB/s][A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  85%|████████▍ | 976M/1.15G [00:22<00:03, 56.4MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  25%|██▍       | 1.23G/4.98G [00:22<01:05, 57.2MB/s][A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  25%|██▌       | 1.25G/4.98G [00:22<00:59, 62.3MB/s][A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  19%|█▊        | 928M/4.98G [00:22<01:32, 43.7MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  25%|██▌       | 1.26G/4.98G [00:22<00:57, 64.8MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  19%|█▉        | 944M/4.98G [00:22<01:25, 47.4MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  19%|█▉        | 960M/4.98G [00:23<01:14, 53.7MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  26%|██▌       | 1.28G/4.98G [00:23<01:05, 56.6MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  20%|█▉        | 976M/4.98G [00:23<01:10, 56.7MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  26%|██▌       | 1.30G/4.98G [00:23<01:04, 56.8MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  92%|█████████▏| 1.06G/1.15G [00:23<00:01, 57.7MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  27%|██▋       | 1.33G/4.98G [00:23<01:00, 60.6MB/s][A\n",
+      "model-00002-of-00003.safetensors:  20%|██        | 1.01G/4.98G [00:23<01:16, 52.0MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  93%|█████████▎| 1.07G/1.15G [00:23<00:01, 49.7MB/s]\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  21%|██        | 1.02G/4.98G [00:24<01:11, 55.7MB/s]\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  27%|██▋       | 1.34G/4.98G [00:24<01:03, 56.9MB/s]\u001b[A\u001b[A\n",
+      "\n",
+      "model-00001-of-00003.safetensors:  27%|██▋       | 1.36G/4.98G [00:24<01:00, 59.9MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  28%|██▊       | 1.38G/4.98G [00:24<01:01, 59.0MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  97%|█████████▋| 1.12G/1.15G [00:24<00:00, 53.2MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  28%|██▊       | 1.39G/4.98G [00:25<01:04, 56.0MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors:  98%|█████████▊| 1.14G/1.15G [00:25<00:00, 55.6MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  28%|██▊       | 1.41G/4.98G [00:25<01:06, 54.1MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  22%|██▏       | 1.09G/4.98G [00:25<01:17, 50.4MB/s]\u001b[A\n",
+      "\n",
+      "model-00003-of-00003.safetensors: 100%|██████████| 1.15G/1.15G [00:25<00:00, 45.0MB/s]\u001b[A\u001b[A\n",
+      "model-00001-of-00003.safetensors:  29%|██▊       | 1.42G/4.98G [00:25<01:08, 52.1MB/s]\n",
+      "model-00001-of-00003.safetensors:  29%|██▉       | 1.44G/4.98G [00:25<01:03, 55.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  29%|██▉       | 1.46G/4.98G [00:26<01:01, 57.4MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  23%|██▎       | 1.14G/4.98G [00:26<01:18, 49.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  30%|██▉       | 1.47G/4.98G [00:26<01:09, 50.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  30%|██▉       | 1.49G/4.98G [00:26<01:00, 57.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  30%|███       | 1.50G/4.98G [00:27<01:00, 57.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  31%|███       | 1.54G/4.98G [00:27<01:01, 56.4MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  24%|██▍       | 1.18G/4.98G [00:27<02:03, 30.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  31%|███       | 1.55G/4.98G [00:27<00:59, 57.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  31%|███▏      | 1.57G/4.98G [00:28<00:56, 60.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  32%|███▏      | 1.58G/4.98G [00:28<00:53, 63.7MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  24%|██▍       | 1.22G/4.98G [00:28<01:49, 34.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  32%|███▏      | 1.62G/4.98G [00:28<00:52, 63.5MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  25%|██▍       | 1.23G/4.98G [00:28<01:37, 38.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  33%|███▎      | 1.63G/4.98G [00:29<00:54, 61.5MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  25%|██▌       | 1.25G/4.98G [00:29<01:39, 37.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  33%|███▎      | 1.65G/4.98G [00:29<00:53, 62.1MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  25%|██▌       | 1.26G/4.98G [00:29<01:28, 42.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  33%|███▎      | 1.66G/4.98G [00:29<00:58, 56.8MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  26%|██▌       | 1.29G/4.98G [00:29<01:21, 45.5MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  26%|██▌       | 1.30G/4.98G [00:30<01:10, 52.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  34%|███▎      | 1.68G/4.98G [00:30<01:20, 41.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  37%|███▋      | 1.82G/4.98G [00:32<00:52, 60.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  27%|██▋       | 1.33G/4.98G [00:32<04:56, 12.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  37%|███▋      | 1.84G/4.98G [00:33<00:52, 59.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  37%|███▋      | 1.86G/4.98G [00:33<00:55, 56.6MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  27%|██▋       | 1.36G/4.98G [00:33<02:33, 23.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  38%|███▊      | 1.87G/4.98G [00:33<01:00, 51.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  38%|███▊      | 1.89G/4.98G [00:34<01:05, 47.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  38%|███▊      | 1.90G/4.98G [00:34<01:02, 49.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  39%|███▊      | 1.92G/4.98G [00:34<00:57, 52.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  39%|███▉      | 1.95G/4.98G [00:35<00:56, 53.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  40%|███▉      | 1.98G/4.98G [00:35<00:49, 60.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  40%|████      | 2.00G/4.98G [00:36<00:52, 56.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  40%|████      | 2.02G/4.98G [00:36<00:52, 56.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  41%|████      | 2.03G/4.98G [00:36<00:55, 53.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  41%|████      | 2.05G/4.98G [00:37<00:54, 53.7MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  31%|███       | 1.54G/4.98G [00:37<01:23, 41.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  41%|████▏     | 2.06G/4.98G [00:37<01:11, 40.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  42%|████▏     | 2.08G/4.98G [00:38<01:03, 45.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  42%|████▏     | 2.10G/4.98G [00:38<00:57, 49.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  42%|████▏     | 2.11G/4.98G [00:38<00:58, 49.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  43%|████▎     | 2.13G/4.98G [00:38<00:53, 53.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  43%|████▎     | 2.14G/4.98G [00:39<00:55, 51.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  43%|████▎     | 2.16G/4.98G [00:39<00:54, 52.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  44%|████▎     | 2.18G/4.98G [00:39<00:49, 56.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  45%|████▍     | 2.22G/4.98G [00:40<00:51, 53.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  45%|████▌     | 2.26G/4.98G [00:41<00:46, 59.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  46%|████▌     | 2.27G/4.98G [00:41<00:43, 62.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  46%|████▌     | 2.29G/4.98G [00:41<00:44, 60.6MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  35%|███▌      | 1.74G/4.98G [00:41<01:10, 46.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  46%|████▌     | 2.30G/4.98G [00:41<00:45, 58.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  47%|████▋     | 2.34G/4.98G [00:42<00:44, 59.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  47%|████▋     | 2.35G/4.98G [00:42<00:45, 57.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  36%|███▋      | 1.81G/4.98G [00:42<01:07, 47.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  48%|████▊     | 2.37G/4.98G [00:43<00:56, 46.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  48%|████▊     | 2.38G/4.98G [00:43<00:51, 50.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  48%|████▊     | 2.40G/4.98G [00:43<00:48, 53.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  49%|████▉     | 2.43G/4.98G [00:44<00:49, 51.5MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  38%|███▊      | 1.89G/4.98G [00:44<01:03, 49.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  49%|████▉     | 2.45G/4.98G [00:44<00:54, 46.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  50%|████▉     | 2.48G/4.98G [00:45<00:45, 55.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  50%|█████     | 2.50G/4.98G [00:45<00:46, 53.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  50%|█████     | 2.51G/4.98G [00:45<00:47, 52.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  39%|███▉      | 1.97G/4.98G [00:45<00:59, 50.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  51%|█████     | 2.54G/4.98G [00:46<00:47, 51.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  52%|█████▏    | 2.58G/4.98G [00:47<00:48, 50.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  52%|█████▏    | 2.59G/4.98G [00:47<00:44, 53.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  53%|█████▎    | 2.62G/4.98G [00:47<00:41, 57.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  53%|█████▎    | 2.64G/4.98G [00:48<00:39, 59.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  41%|████▏     | 2.06G/4.98G [00:48<01:03, 46.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  54%|█████▍    | 2.69G/4.98G [00:49<00:39, 57.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  54%|█████▍    | 2.70G/4.98G [00:49<00:38, 58.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  55%|█████▍    | 2.74G/4.98G [00:49<00:34, 64.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  55%|█████▌    | 2.75G/4.98G [00:50<00:33, 66.7MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  43%|████▎     | 2.14G/4.98G [00:50<00:59, 47.9MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  43%|████▎     | 2.16G/4.98G [00:50<00:55, 51.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  44%|████▎     | 2.18G/4.98G [00:50<00:52, 53.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  56%|█████▌    | 2.77G/4.98G [00:51<01:17, 28.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  56%|█████▌    | 2.78G/4.98G [00:51<01:08, 31.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  57%|█████▋    | 2.82G/4.98G [00:52<00:50, 42.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  57%|█████▋    | 2.85G/4.98G [00:52<00:47, 44.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  57%|█████▋    | 2.86G/4.98G [00:53<00:43, 48.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  46%|████▌     | 2.27G/4.98G [00:53<01:18, 34.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  58%|█████▊    | 2.88G/4.98G [00:53<00:54, 38.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  58%|█████▊    | 2.90G/4.98G [00:53<00:45, 45.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  58%|█████▊    | 2.91G/4.98G [00:54<00:43, 47.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  47%|████▋     | 2.34G/4.98G [00:54<00:51, 51.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  59%|█████▉    | 2.93G/4.98G [00:54<00:45, 45.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  59%|█████▉    | 2.94G/4.98G [00:55<00:44, 46.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  59%|█████▉    | 2.96G/4.98G [00:55<00:40, 49.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  60%|██████    | 2.99G/4.98G [00:55<00:33, 59.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  60%|██████    | 3.01G/4.98G [00:55<00:32, 61.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  61%|██████    | 3.02G/4.98G [00:56<00:31, 61.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  61%|██████▏   | 3.06G/4.98G [00:56<00:31, 60.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  62%|██████▏   | 3.09G/4.98G [00:57<00:31, 59.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  62%|██████▏   | 3.10G/4.98G [00:57<00:30, 61.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  63%|██████▎   | 3.12G/4.98G [00:57<00:29, 62.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  63%|██████▎   | 3.14G/4.98G [00:58<00:28, 65.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  63%|██████▎   | 3.15G/4.98G [00:58<00:30, 60.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  64%|██████▎   | 3.17G/4.98G [00:58<00:30, 59.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  64%|██████▍   | 3.18G/4.98G [00:58<00:29, 60.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  65%|██████▍   | 3.22G/4.98G [00:59<00:33, 52.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  65%|██████▍   | 3.23G/4.98G [00:59<00:31, 55.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  65%|██████▌   | 3.25G/4.98G [01:00<00:30, 57.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  66%|██████▌   | 3.28G/4.98G [01:00<00:28, 60.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  66%|██████▌   | 3.30G/4.98G [01:00<00:27, 61.3MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  53%|█████▎    | 2.66G/4.98G [01:00<00:46, 49.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  66%|██████▋   | 3.31G/4.98G [01:01<00:28, 57.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  67%|██████▋   | 3.33G/4.98G [01:01<00:28, 57.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  68%|██████▊   | 3.38G/4.98G [01:02<00:27, 59.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  68%|██████▊   | 3.39G/4.98G [01:02<00:27, 58.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  68%|██████▊   | 3.41G/4.98G [01:02<00:28, 55.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  69%|██████▉   | 3.46G/4.98G [01:03<00:24, 63.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  70%|██████▉   | 3.47G/4.98G [01:03<00:23, 64.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  70%|███████   | 3.49G/4.98G [01:04<00:24, 62.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  70%|███████   | 3.50G/4.98G [01:04<00:27, 54.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  71%|███████   | 3.52G/4.98G [01:04<00:26, 56.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  57%|█████▋    | 2.83G/4.98G [01:04<00:48, 44.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  71%|███████▏  | 3.55G/4.98G [01:05<00:32, 43.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  72%|███████▏  | 3.57G/4.98G [01:05<00:29, 47.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  72%|███████▏  | 3.58G/4.98G [01:06<00:26, 52.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  72%|███████▏  | 3.60G/4.98G [01:06<00:25, 53.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  73%|███████▎  | 3.62G/4.98G [01:06<00:24, 56.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  59%|█████▉    | 2.93G/4.98G [01:06<00:35, 57.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  73%|███████▎  | 3.63G/4.98G [01:06<00:24, 56.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  73%|███████▎  | 3.65G/4.98G [01:07<00:23, 56.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  74%|███████▍  | 3.68G/4.98G [01:07<00:21, 61.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  74%|███████▍  | 3.70G/4.98G [01:07<00:21, 60.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  75%|███████▍  | 3.71G/4.98G [01:08<00:19, 64.1MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  61%|██████    | 3.02G/4.98G [01:08<00:33, 57.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  75%|███████▌  | 3.74G/4.98G [01:08<00:20, 60.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  75%|███████▌  | 3.76G/4.98G [01:09<00:20, 61.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  76%|███████▌  | 3.79G/4.98G [01:09<00:17, 68.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  76%|███████▋  | 3.81G/4.98G [01:09<00:16, 69.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  77%|███████▋  | 3.82G/4.98G [01:09<00:17, 67.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  77%|███████▋  | 3.86G/4.98G [01:10<00:16, 70.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  78%|███████▊  | 3.87G/4.98G [01:10<00:21, 50.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  78%|███████▊  | 3.89G/4.98G [01:11<00:19, 57.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  78%|███████▊  | 3.90G/4.98G [01:11<00:19, 54.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  79%|███████▊  | 3.92G/4.98G [01:11<00:19, 54.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  80%|███████▉  | 3.97G/4.98G [01:12<00:17, 58.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  80%|███████▉  | 3.98G/4.98G [01:12<00:18, 54.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  80%|████████  | 4.00G/4.98G [01:13<00:18, 54.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  81%|████████  | 4.02G/4.98G [01:13<00:17, 56.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  81%|████████  | 4.03G/4.98G [01:13<00:16, 57.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  81%|████████  | 4.05G/4.98G [01:13<00:16, 57.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  82%|████████▏ | 4.06G/4.98G [01:14<00:15, 60.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  82%|████████▏ | 4.08G/4.98G [01:14<00:13, 65.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  82%|████████▏ | 4.10G/4.98G [01:14<00:14, 61.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  83%|████████▎ | 4.11G/4.98G [01:14<00:13, 62.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  83%|████████▎ | 4.13G/4.98G [01:15<00:15, 56.3MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  68%|██████▊   | 3.38G/4.98G [01:15<00:25, 63.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  83%|████████▎ | 4.14G/4.98G [01:15<00:16, 50.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  83%|████████▎ | 4.16G/4.98G [01:15<00:14, 55.5MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  69%|██████▊   | 3.42G/4.98G [01:16<00:25, 61.3MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  84%|████████▍ | 4.18G/4.98G [01:16<00:17, 46.8MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  69%|██████▉   | 3.46G/4.98G [01:16<00:27, 55.4MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  70%|██████▉   | 3.47G/4.98G [01:16<00:26, 56.1MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  70%|███████   | 3.49G/4.98G [01:17<00:26, 57.1MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  70%|███████   | 3.50G/4.98G [01:17<00:26, 55.5MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  71%|███████   | 3.52G/4.98G [01:17<00:31, 46.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  84%|████████▍ | 4.21G/4.98G [01:18<00:32, 24.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  85%|████████▍ | 4.22G/4.98G [01:18<00:25, 30.3MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  72%|███████▏  | 3.57G/4.98G [01:18<00:27, 50.8MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  72%|███████▏  | 3.58G/4.98G [01:19<00:24, 56.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  85%|████████▌ | 4.24G/4.98G [01:19<00:26, 27.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  85%|████████▌ | 4.26G/4.98G [01:19<00:23, 31.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  86%|████████▌ | 4.27G/4.98G [01:20<00:19, 37.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  86%|████████▌ | 4.29G/4.98G [01:20<00:16, 41.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  86%|████████▋ | 4.30G/4.98G [01:20<00:15, 44.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  87%|████████▋ | 4.32G/4.98G [01:20<00:13, 50.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  87%|████████▋ | 4.34G/4.98G [01:21<00:12, 52.4MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  75%|███████▍  | 3.71G/4.98G [01:21<00:20, 62.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  88%|████████▊ | 4.37G/4.98G [01:21<00:10, 58.1MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  75%|███████▌  | 3.74G/4.98G [01:21<00:20, 61.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  88%|████████▊ | 4.40G/4.98G [01:22<00:10, 57.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  89%|████████▊ | 4.42G/4.98G [01:22<00:09, 61.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  89%|████████▉ | 4.43G/4.98G [01:22<00:08, 63.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  89%|████████▉ | 4.45G/4.98G [01:22<00:08, 64.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  90%|████████▉ | 4.46G/4.98G [01:23<00:08, 64.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  90%|█████████ | 4.50G/4.98G [01:23<00:07, 68.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  77%|███████▋  | 3.86G/4.98G [01:23<00:18, 61.7MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  78%|███████▊  | 3.87G/4.98G [01:23<00:17, 61.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  91%|█████████ | 4.51G/4.98G [01:24<00:11, 39.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  91%|█████████ | 4.53G/4.98G [01:24<00:09, 46.0MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  91%|█████████ | 4.54G/4.98G [01:24<00:08, 50.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  92%|█████████▏| 4.56G/4.98G [01:25<00:08, 52.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  92%|█████████▏| 4.59G/4.98G [01:25<00:06, 64.9MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  80%|███████▉  | 3.97G/4.98G [01:25<00:15, 64.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  92%|█████████▏| 4.61G/4.98G [01:25<00:06, 58.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  93%|█████████▎| 4.66G/4.98G [01:26<00:05, 60.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  94%|█████████▍| 4.67G/4.98G [01:27<00:05, 55.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  94%|█████████▍| 4.69G/4.98G [01:27<00:05, 57.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  94%|█████████▍| 4.70G/4.98G [01:27<00:04, 63.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  95%|█████████▍| 4.72G/4.98G [01:27<00:04, 63.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  95%|█████████▌| 4.74G/4.98G [01:28<00:04, 58.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  95%|█████████▌| 4.75G/4.98G [01:28<00:03, 59.5MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  96%|█████████▌| 4.77G/4.98G [01:28<00:03, 57.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  96%|█████████▌| 4.78G/4.98G [01:29<00:04, 48.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  96%|█████████▋| 4.80G/4.98G [01:29<00:03, 53.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  97%|█████████▋| 4.82G/4.98G [01:29<00:02, 57.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  97%|█████████▋| 4.83G/4.98G [01:29<00:02, 59.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  98%|█████████▊| 4.86G/4.98G [01:30<00:02, 41.8MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  98%|█████████▊| 4.88G/4.98G [01:31<00:02, 47.7MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  98%|█████████▊| 4.90G/4.98G [01:31<00:01, 46.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  99%|█████████▊| 4.91G/4.98G [01:31<00:01, 50.4MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  99%|█████████▉| 4.93G/4.98G [01:31<00:00, 58.1MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors:  99%|█████████▉| 4.94G/4.98G [01:32<00:00, 58.9MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors: 100%|█████████▉| 4.96G/4.98G [01:32<00:00, 42.6MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors: 100%|█████████▉| 4.98G/4.98G [01:33<00:00, 45.2MB/s]\u001b[A\n",
+      "model-00001-of-00003.safetensors: 100%|██████████| 4.98G/4.98G [01:33<00:00, 53.4MB/s]\u001b[A\n",
+      "\n",
+      "model-00002-of-00003.safetensors:  87%|████████▋ | 4.34G/4.98G [01:33<00:13, 48.2MB/s]\u001b[A\n",
+      "\n",
+      "\n",
+      "Upload 3 LFS files:  33%|███▎      | 1/3 [01:33<03:06, 93.49s/it]\u001b[A\u001b[A\u001b[A\n",
+      "model-00002-of-00003.safetensors:  87%|████████▋ | 4.35G/4.98G [01:33<00:12, 52.5MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  88%|████████▊ | 4.37G/4.98G [01:33<00:11, 54.7MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  88%|████████▊ | 4.38G/4.98G [01:34<00:11, 52.1MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  88%|████████▊ | 4.40G/4.98G [01:34<00:11, 49.8MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  89%|████████▊ | 4.42G/4.98G [01:35<00:13, 43.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  89%|████████▉ | 4.43G/4.98G [01:35<00:13, 41.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  89%|████████▉ | 4.45G/4.98G [01:35<00:11, 46.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  90%|████████▉ | 4.46G/4.98G [01:36<00:10, 49.6MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  90%|████████▉ | 4.48G/4.98G [01:36<00:08, 58.5MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  90%|█████████ | 4.50G/4.98G [01:36<00:08, 58.8MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  91%|█████████ | 4.51G/4.98G [01:36<00:07, 61.3MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  91%|█████████ | 4.53G/4.98G [01:37<00:07, 61.9MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  91%|█████████ | 4.54G/4.98G [01:37<00:06, 64.6MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  92%|█████████▏| 4.56G/4.98G [01:37<00:06, 61.9MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  92%|█████████▏| 4.58G/4.98G [01:37<00:07, 56.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  92%|█████████▏| 4.59G/4.98G [01:38<00:06, 58.9MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  92%|█████████▏| 4.61G/4.98G [01:38<00:06, 60.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  93%|█████████▎| 4.62G/4.98G [01:38<00:05, 62.7MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  93%|█████████▎| 4.64G/4.98G [01:38<00:05, 58.5MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  93%|█████████▎| 4.66G/4.98G [01:39<00:05, 59.8MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  94%|█████████▍| 4.67G/4.98G [01:39<00:05, 56.7MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  94%|█████████▍| 4.69G/4.98G [01:39<00:05, 53.8MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  94%|█████████▍| 4.70G/4.98G [01:40<00:05, 55.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  95%|█████████▍| 4.72G/4.98G [01:40<00:05, 51.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  95%|█████████▌| 4.74G/4.98G [01:40<00:05, 48.6MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  95%|█████████▌| 4.75G/4.98G [01:41<00:04, 50.4MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  96%|█████████▌| 4.77G/4.98G [01:41<00:03, 54.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  96%|█████████▌| 4.78G/4.98G [01:41<00:03, 58.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  96%|█████████▋| 4.80G/4.98G [01:41<00:03, 55.1MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  97%|█████████▋| 4.82G/4.98G [01:42<00:03, 52.0MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  97%|█████████▋| 4.83G/4.98G [01:42<00:02, 52.8MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  97%|█████████▋| 4.85G/4.98G [01:42<00:02, 55.3MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  98%|��████████▊| 4.86G/4.98G [01:43<00:02, 57.7MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  98%|█████████▊| 4.88G/4.98G [01:43<00:01, 57.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  98%|█████████▊| 4.90G/4.98G [01:43<00:01, 55.4MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  99%|█████████▊| 4.91G/4.98G [01:43<00:01, 54.2MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  99%|█████████▉| 4.93G/4.98G [01:44<00:01, 52.4MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors:  99%|█████████▉| 4.94G/4.98G [01:44<00:00, 56.1MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors: 100%|█████████▉| 4.96G/4.98G [01:44<00:00, 57.7MB/s]\u001b[A\n",
+      "model-00002-of-00003.safetensors: 100%|██████████| 4.98G/4.98G [01:45<00:00, 47.4MB/s]\u001b[A\n",
+      "\n",
+      "\n",
+      "\n",
+      "Upload 3 LFS files: 100%|██████████| 3/3 [01:45<00:00, 35.14s/it]\u001b[A\u001b[A\u001b[A\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "CommitInfo(commit_url='https://huggingface.co/aissatoubalde/lab/commit/a31ac628a1effc894512237599c8b851981d1e31', commit_message='Upload PhiForCausalLM', commit_description='', oid='a31ac628a1effc894512237599c8b851981d1e31', pr_url=None, pr_revision=None, pr_num=None)"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "model.push_to_hub('aissatoubalde/lab')"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fa43c8e1-945e-41ef-b2f6-e90db1f50140",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6018ee5dd9088c029dec6b7490a081b122e08b3ae81ee63f1cb6fda91dcb9fd4
+oid sha256:b97f3e3a61f154dd18e7d0d40e91564daa7cfb393ad45e0eb1adf8bad6659cc5
 size 4664