books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Correct batch_idx in appendix A logging (#942)

Browse Source 
* Correct batch_idx in appendix A logging

* update batch idx

---------

Co-authored-by: Sebastian Raschka <sebastian@Sebastians-MacBook-Air.local>
This commit is contained in:
Henry
2026-01-08 09:14:17 +08:00
committed by GitHub
parent 491fd58463
commit 9df9e69cd2
2 changed files with 29 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
appendix-A/01_main-chapter-code/code-part1.ipynb
View File

@@ -46,7 +46,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"2.4.0\n" "2.9.1\n"
] ]
} }
], ],
@@ -658,13 +658,13 @@
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Parameter containing:\n", "Parameter containing:\n",
"tensor([[ 0.1182, 0.0606, -0.1292, ..., -0.1126, 0.0735, -0.0597],\n", "tensor([[ 0.0979, 0.0412, 0.1005, ..., -0.0544, -0.0804, 0.0842],\n",
" [-0.0249, 0.0154, -0.0476, ..., -0.1001, -0.1288, 0.1295],\n", " [-0.0115, 0.0382, -0.0261, ..., 0.0573, 0.1094, 0.1364],\n",
" [ 0.0641, 0.0018, -0.0367, ..., -0.0990, -0.0424, -0.0043],\n", " [ 0.0162, -0.0050, 0.0752, ..., 0.1298, 0.1250, -0.0117],\n",
" ...,\n", " ...,\n",
" [ 0.0618, 0.0867, 0.1361, ..., -0.0254, 0.0399, 0.1006],\n", " [-0.0312, 0.1319, -0.0954, ..., -0.1066, -0.0970, -0.0373],\n",
" [ 0.0842, -0.0512, -0.0960, ..., -0.1091, 0.1242, -0.0428],\n", " [ 0.0563, -0.1373, -0.1226, ..., 0.0154, -0.0969, 0.0113],\n",
" [ 0.0518, -0.1390, -0.0923, ..., -0.0954, -0.0668, -0.0037]],\n", " [-0.0872, -0.0098, 0.0322, ..., -0.0108, 0.1091, -0.1043]],\n",
" requires_grad=True)\n" " requires_grad=True)\n"
] ]
} }
@@ -1002,12 +1002,12 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Epoch: 001/003 | Batch 000/002 | Train/Val Loss: 0.75\n", "Epoch: 001/003 | Batch 001/002 | Train/Val Loss: 0.75\n",
"Epoch: 001/003 | Batch 001/002 | Train/Val Loss: 0.65\n", "Epoch: 001/003 | Batch 002/002 | Train/Val Loss: 0.65\n",
"Epoch: 002/003 | Batch 000/002 | Train/Val Loss: 0.44\n", "Epoch: 002/003 | Batch 001/002 | Train/Val Loss: 0.44\n",
"Epoch: 002/003 | Batch 001/002 | Train/Val Loss: 0.13\n", "Epoch: 002/003 | Batch 002/002 | Train/Val Loss: 0.13\n",
"Epoch: 003/003 | Batch 000/002 | Train/Val Loss: 0.03\n", "Epoch: 003/003 | Batch 001/002 | Train/Val Loss: 0.03\n",
"Epoch: 003/003 | Batch 001/002 | Train/Val Loss: 0.00\n" "Epoch: 003/003 | Batch 002/002 | Train/Val Loss: 0.00\n"
] ]
} }
], ],
@@ -1036,7 +1036,7 @@
" \n", " \n",
" ### LOGGING\n", " ### LOGGING\n",
" print(f\"Epoch: {epoch+1:03d}/{num_epochs:03d}\"\n", " print(f\"Epoch: {epoch+1:03d}/{num_epochs:03d}\"\n",
" f\" | Batch {batch_idx:03d}/{len(train_loader):03d}\"\n", " f\" | Batch {batch_idx+1:03d}/{len(train_loader):03d}\"\n",
" f\" | Train/Val Loss: {loss:.2f}\")\n", " f\" | Train/Val Loss: {loss:.2f}\")\n",
"\n", "\n",
" model.eval()\n", " model.eval()\n",
@@ -1080,11 +1080,11 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"tensor([[ 0.9991, 0.0009],\n", "tensor([[0.9991, 0.0009],\n",
" [ 0.9982, 0.0018],\n", " [0.9982, 0.0018],\n",
" [ 0.9949, 0.0051],\n", " [0.9949, 0.0051],\n",
" [ 0.0491, 0.9509],\n", " [0.0491, 0.9509],\n",
" [ 0.0307, 0.9693]])\n", " [0.0307, 0.9693]])\n",
"tensor([0, 0, 0, 1, 1])\n" "tensor([0, 0, 0, 1, 1])\n"
] ]
} }
@@ -1340,7 +1340,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.4" "version": "3.11.11"
} }
}, },
"nbformat": 4, "nbformat": 4,

18
appendix-A/01_main-chapter-code/code-part2.ipynb
View File

@@ -301,7 +301,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": null,
"metadata": { "metadata": {
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
@@ -314,12 +314,12 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Epoch: 001/003 | Batch 000/002 | Train/Val Loss: 0.75\n", "Epoch: 001/003 | Batch 001/002 | Train/Val Loss: 0.75\n",
"Epoch: 001/003 | Batch 001/002 | Train/Val Loss: 0.65\n", "Epoch: 001/003 | Batch 002/002 | Train/Val Loss: 0.65\n",
"Epoch: 002/003 | Batch 000/002 | Train/Val Loss: 0.44\n", "Epoch: 002/003 | Batch 001/002 | Train/Val Loss: 0.44\n",
"Epoch: 002/003 | Batch 001/002 | Train/Val Loss: 0.13\n", "Epoch: 002/003 | Batch 002/002 | Train/Val Loss: 0.13\n",
"Epoch: 003/003 | Batch 000/002 | Train/Val Loss: 0.03\n", "Epoch: 003/003 | Batch 001/002 | Train/Val Loss: 0.03\n",
"Epoch: 003/003 | Batch 001/002 | Train/Val Loss: 0.00\n" "Epoch: 003/003 | Batch 002/002 | Train/Val Loss: 0.00\n"
] ]
} }
], ],
@@ -355,7 +355,7 @@
"\n", "\n",
" ### LOGGING\n", " ### LOGGING\n",
" print(f\"Epoch: {epoch+1:03d}/{num_epochs:03d}\"\n", " print(f\"Epoch: {epoch+1:03d}/{num_epochs:03d}\"\n",
" f\" | Batch {batch_idx:03d}/{len(train_loader):03d}\"\n", " f\" | Batch {batch_idx+1:03d}/{len(train_loader):03d}\"\n",
" f\" | Train/Val Loss: {loss:.2f}\")\n", " f\" | Train/Val Loss: {loss:.2f}\")\n",
"\n", "\n",
" model.eval()\n", " model.eval()\n",
@@ -493,7 +493,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.10.16" "version": "3.11.11"
} }
}, },
"nbformat": 4, "nbformat": 4,