add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,63 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- null
+model-index:
+- name: gpt2-finetuned-nft-shakes-seuss
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+---
+
+<!-- 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-finetuned-nft-shakes-seuss
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.8505
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 4.2178        | 1.0   | 1095 | 4.0073          |
+| 3.9522        | 2.0   | 2190 | 3.8824          |
+| 3.8393        | 3.0   | 3285 | 3.8505          |
+
+
+### Framework versions
+
+- Transformers 4.10.0
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d07fd6db2133ed5e905df2c1b4e9c43bc574b24e3740332ad66e57032720f21
+size 510403817

runs/Sep06_19-00-20_8ab5c6b2034d/1630954843.179381/events.out.tfevents.1630954843.8ab5c6b2034d.77.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dfc1038e4af96ad79733f0e2ca330e94946dd5205f6e0305edc2636186bc4c4
+size 4216

runs/Sep06_19-00-20_8ab5c6b2034d/events.out.tfevents.1630954843.8ab5c6b2034d.77.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac28a0570f031eca11f259e3360dd14eb8594be007e48a1d76cf7c6737a3b643
+size 5284

runs/Sep06_19-00-20_8ab5c6b2034d/events.out.tfevents.1630956933.8ab5c6b2034d.77.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030d75dacc99704cf0357ba90cc2787c7878737462267384efcd0c2b1a35ab0b
+size 311

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4016b6114f5d94e6f8bb0a6f4de55d97bd04c765bc6822e6c785213b52daf62d
+size 2671