Model save

README.md

@@ -0,0 +1,91 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: gpt2_cfg_add_8
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# gpt2_cfg_add_8
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+- Accuracy: 1.0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.001
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| No log        | 0      | 0    | 2.7379          | 0.0      |
+| 1.9725        | 0.0320 | 100  | 1.9286          | 0.0      |
+| 1.0948        | 0.0641 | 200  | 0.9757          | 0.02     |
+| 0.6137        | 0.0961 | 300  | 0.6562          | 0.09     |
+| 0.3684        | 0.1281 | 400  | 0.3644          | 0.35     |
+| 0.2853        | 0.1602 | 500  | 0.2482          | 0.61     |
+| 0.0578        | 0.1922 | 600  | 0.0728          | 0.84     |
+| 0.0081        | 0.2242 | 700  | 0.0669          | 0.88     |
+| 0.0033        | 0.2562 | 800  | 0.0264          | 0.93     |
+| 2.4737        | 0.2883 | 900  | 1.5848          | 0.005    |
+| 0.0482        | 0.3203 | 1000 | 0.0470          | 0.89     |
+| 0.0009        | 0.3523 | 1100 | 0.0078          | 0.985    |
+| 0.0125        | 0.3844 | 1200 | 0.0068          | 0.98     |
+| 0.005         | 0.4164 | 1300 | 0.0116          | 0.975    |
+| 0.0256        | 0.4484 | 1400 | 0.0035          | 0.995    |
+| 0.0003        | 0.4805 | 1500 | 0.0005          | 1.0      |
+| 0.0001        | 0.5125 | 1600 | 0.0001          | 1.0      |
+| 0.0           | 0.5445 | 1700 | 0.0000          | 1.0      |
+| 0.0           | 0.5766 | 1800 | 0.0000          | 1.0      |
+| 0.0001        | 0.6086 | 1900 | 0.0002          | 1.0      |
+| 0.0           | 0.6406 | 2000 | 0.0000          | 1.0      |
+| 0.0           | 0.6726 | 2100 | 0.0000          | 1.0      |
+| 0.0           | 0.7047 | 2200 | 0.0000          | 1.0      |
+| 0.0           | 0.7367 | 2300 | 0.0000          | 1.0      |
+| 0.0           | 0.7687 | 2400 | 0.0000          | 1.0      |
+| 0.0           | 0.8008 | 2500 | 0.0000          | 1.0      |
+| 0.0           | 0.8328 | 2600 | 0.0000          | 1.0      |
+| 0.0           | 0.8648 | 2700 | 0.0000          | 1.0      |
+| 0.0           | 0.8969 | 2800 | 0.0000          | 1.0      |
+| 0.0           | 0.9289 | 2900 | 0.0000          | 1.0      |
+| 0.0           | 0.9609 | 3000 | 0.0000          | 1.0      |
+| 0.0           | 0.9930 | 3100 | 0.0000          | 1.0      |
+
+
+### Framework versions
+
+- Transformers 4.46.0
+- Pytorch 2.5.1
+- Datasets 3.1.0
+- Tokenizers 0.20.1

config.json

@@ -0,0 +1,18 @@
+{
+  "architectures": [
+    "NanoGPT"
+  ],
+  "bias": true,
+  "block_size": 256,
+  "dropout": 0.0,
+  "model_type": "nanogpt",
+  "n_embd": 384,
+  "n_head": 6,
+  "n_layer": 6,
+  "nonlinearity": "RELU",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "use_NoPE": true,
+  "use_layernorm": true,
+  "vocab_size": 14
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.46.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f90ea81987635cfe3db95050c2810dc318722b05b429be12d7439c8f0b974018
+size 42640744

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf2427c9da03e58124d55de2bd74f3b1e6618a0e32595560014fe30aad05a1f
+size 5176