yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-09-26 00:24:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

use training set len

Browse Source
This commit is contained in:
rasbt 2024-04-29 21:50:07 -05:00
parent 97ed38116a
commit 0ac19a1e50
4 changed files with 35 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
ch06/02_bonus_additional-experiments/README.md
View File

@ -9,16 +9,16 @@ For example,
 
| | Model | Weights | Trainable token | Trainable layers | Context length | CPU/GPU | Training time | Training acc | Validation acc | Test acc |
|---|--------------------|------------|-----------------|------------------|-------------------------|---------|---------------|--------------|----------------|----------|
| 1 | gpt2-small (124M) | pretrained | last | last_block | longest train ex. (120) | V100 | 0.39 min | 96.63% | 97.99% | 94.33% |
| 2 | gpt2-small (124M) | pretrained | first | last_block | longest train ex. (120) | V100 | 0.37 min | 78.46% | 80.54% | 75.00% |
| 3 | gpt2-small (124M) | pretrained | last | last_layer | longest train ex. (120) | V100 | 0.33 min | 78.65% | 87.25% | 78.33% |
| 4 | gpt2-small (124M) | pretrained | last | all | longest train ex. (120) | V100 | 0.94 min | 99.62% | 96.64% | 96.33% |
| 5 | gpt2-medium (355M) | pretrained | last | last_block | longest train ex. (120) | V100 | 0.91 min | 87.50% | 51.01% | 56.67% |
| 6 | gpt2-large (774M) | pretrained | last | last_block | longest train ex. (120) | V100 | 1.91 min | 99.52% | 98.66% | 96.67% |
| 7 | gpt2-small (124M) | random | last | all | longest train ex. (120) | V100 | 0.93 min | 100% | 97.32% | 93.00% |
| 8 | gpt2-small (124M) | pretrained | last | last_block | context length (1024) | V100 | 3.24 min | 83.08% | 87.92% | 78.33% |
| | Model | Weights | Trainable token | Trainable layers | Context length | CPU/GPU | Training time | Training acc | Validation acc | Test acc |
| ---- | ------------------ | ---------- | --------------- | ---------------- | ----------------------- | ------- | ------------- | ------------ | -------------- | -------- |
| 1 | gpt2-small (124M) | pretrained | last | last_block | longest train ex. (120) | V100 | 0.39 min | 96.63% | 99.33% | 95.00% |
| 2 | gpt2-small (124M) | pretrained | first | last_block | longest train ex. (120) | V100 | 0.37 min | 78.46% | 80.54% | 75.00% |
| 3 | gpt2-small (124M) | pretrained | last | last_layer | longest train ex. (120) | V100 | 0.33 min | 78.65% | 79.87% | 72.00% |
| 4 | gpt2-small (124M) | pretrained | last | all | longest train ex. (120) | V100 | 0.94 min | 99.62% | 96.64% | 96.67% |
| 5 | gpt2-medium (355M) | pretrained | last | last_block | longest train ex. (120) | V100 | 0.91 min | 87.50% | 91.28% | 84.67% |
| 6 | gpt2-large (774M) | pretrained | last | last_block | longest train ex. (120) | V100 | 1.91 min | 99.52% | 98.66% | 96.67% |
| 7 | gpt2-small (124M) | random | last | all | longest train ex. (120) | V100 | 0.93 min | 100% | 96.64% | 93.67% |
| 8 | gpt2-small (124M) | pretrained | last | last_block | context length (1024) | V100 | 3.24 min | 83.08% | 87.92% | 78.33% |
 
@ -30,24 +30,24 @@ You can use the following code to reproduce the experiments:
- Row 2: `python additional-experiments.py --trainable_token first`
- Row 3: `python additional-experiments.py --trainable_layers last_layer`
- Row 4: `python additional-experiments.py --trainable_layers all`
- Row 5: `python additional-experiments.py --model_size gpt2-medium (355M)`
- Row 6: `python additional-experiments.py --model_size gpt2-large (774M)`
- Row 5: `python additional-experiments.py --model_size "gpt2-medium (355M)"`
- Row 6: `python additional-experiments.py --model_size "gpt2-large (774M)"`
- Row 7: `python additional-experiments.py --weights random --trainable_layers all`
- Row 8: `python additional-experiments.py --context_length "model_context_length"`
I've kept the LLM and dataset small on purpose, so you can run the training on a regular laptop like a MacBook Air M3 in about 15 minutes in case you don't have access to a GPU.
 
### Interpretation
1. **Training the Last vs. First Output Token (Row 1 vs. 2)**: Training the last output token results in significantly better performance compared to the first. This improvement is expected due to the causal self-attention mask.
1. **Training the Last vs. First Output Token (Row 1 vs. 2)**: Training the last output token results in substantially better performance compared to the first. This improvement is expected due to the causal self-attention mask.
2. **Training the Last Transformer Block vs. Last Layer (Row 1 vs. 3)**: Training the entire last transformer block is much more effective than training only the last layer.
2. **Training the Last Transformer Block vs. Last Layer (Row 1 vs. 3)**: Training the entire last transformer block is also results in substantially better results than training only the last layer.
3. **Training All Layers vs. Last Transformer Block (Row 1 vs. 4)**: Training all layers shows a modest improvement of 2% over just training the last transformer block, but it requires almost three times longer in terms of training duration.
3. **Training All Layers vs. Last Transformer Block (Row 1 vs. 4)**: Training all layers shows a modest improvement of ~2% over just training the last transformer block, but it requires almost three times longer in terms of training duration.
4. **Using Larger Pretrained Models (Row 1 vs 5, and Row 1 vs. 6)**: Employing a 3x larger pretrained model leads to worse results. However, using a 5x larger model improves performance compared to the initial model, as was anticipated.
4. **Using Larger Pretrained Models (Row 1 vs 5, and Row 1 vs. 6)**: Employing a 3x larger pretrained model leads to worse results. However, using a 5x larger model improves performance compared to the initial model, as was anticipated. (The medium model was perhaps not well pretrained or the particular finetuning configuration works not as well for this model.)
5. **Using a Model with Random Weights vs. Pretrained Weights (Row 1 vs. 7)**: Utilizing a model with random weights yields results that are only slightly worse by 1.3% compared to using pretrained weights.

10
ch06/02_bonus_additional-experiments/additional-experiments.py
View File

@ -123,6 +123,9 @@ def instantiate_model(choose_model, load_weights):
}
BASE_CONFIG.update(model_configs[choose_model])
if not load_weights:
torch.manual_seed(123)
model = GPTModel(BASE_CONFIG)
if load_weights:
@ -354,17 +357,20 @@ if __name__ == "__main__":
tokenizer = tiktoken.get_encoding("gpt2")
train_dataset = None
if args.context_length == "model_context_length":
max_length = model.pos_emb.weight.shape[0]
elif args.context_length == "longest_training_example":
max_length = None
train_dataset = SpamDataset(base_path / "train.csv", max_length=None, tokenizer=tokenizer)
max_length = train_dataset.max_length
else:
try:
max_length = int(args.context_length)
except ValueError:
raise ValueError("Invalid --context_length argument")
train_dataset = SpamDataset(base_path / "train.csv", max_length=max_length, tokenizer=tokenizer)
if train_dataset is None:
train_dataset = SpamDataset(base_path / "train.csv", max_length=max_length, tokenizer=tokenizer)
val_dataset = SpamDataset(base_path / "validation.csv", max_length=max_length, tokenizer=tokenizer)
test_dataset = SpamDataset(base_path / "test.csv", max_length=max_length, tokenizer=tokenizer)

2
ch06/03_bonus_imdb-classification/download-prepare-dataset.py
View File

@ -68,7 +68,7 @@ def partition_and_save(df, sizes=(35000, 5000, 10000)):
# Save to CSV files
train.to_csv("train.csv", index=False)
val.to_csv("val.csv", index=False)
val.to_csv("validation.csv", index=False)
test.to_csv("test.csv", index=False)

12
ch06/03_bonus_imdb-classification/train-gpt.py
View File

@ -67,6 +67,9 @@ def instantiate_model(choose_model, load_weights):
}
BASE_CONFIG.update(model_configs[choose_model])
if not load_weights:
torch.manual_seed(123)
model = GPTModel(BASE_CONFIG)
if load_weights:
@ -294,18 +297,21 @@ if __name__ == "__main__":
tokenizer = tiktoken.get_encoding("gpt2")
train_dataset = None
if args.context_length == "model_context_length":
max_length = model.pos_emb.weight.shape[0]
elif args.context_length == "longest_training_example":
max_length = None
train_dataset = IMDBDataset(base_path / "train.csv", max_length=None, tokenizer=tokenizer)
max_length = train_dataset.max_length
else:
try:
max_length = int(args.context_length)
except ValueError:
raise ValueError("Invalid --context_length argument")
train_dataset = IMDBDataset(base_path / "train.csv", max_length=max_length, tokenizer=tokenizer)
val_dataset = IMDBDataset(base_path / "val.csv", max_length=max_length, tokenizer=tokenizer)
if train_dataset is None:
train_dataset = IMDBDataset(base_path / "train.csv", max_length=max_length, tokenizer=tokenizer)
val_dataset = IMDBDataset(base_path / "validation.csv", max_length=max_length, tokenizer=tokenizer)
test_dataset = IMDBDataset(base_path / "test.csv", max_length=max_length, tokenizer=tokenizer)
num_workers = 0