add model

.gitignore

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

README.md

@@ -0,0 +1,65 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- null
+model-index:
+- name: gpt2-nft-poetry
+  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-nft-poetry
+
+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: 4.0243
+
+## 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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 282  | 4.3092          |
+| 4.5403        | 2.0   | 564  | 4.1283          |
+| 4.5403        | 3.0   | 846  | 4.0605          |
+| 4.039         | 4.0   | 1128 | 4.0321          |
+| 4.039         | 5.0   | 1410 | 4.0243          |
+
+
+### 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:d1121c85a0a13732b5c4b1c6897af90f2b78763fc4eda4372f26918a96818f5a
+size 510403817

runs/Sep08_05-28-07_fbd567ce2372/1631078894.917259/events.out.tfevents.1631078894.fbd567ce2372.77.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff989ecb0c77d57632e829191e60b1d6e089117921060618964f1eb7ae38225d
+size 4188

runs/Sep08_05-28-07_fbd567ce2372/events.out.tfevents.1631078894.fbd567ce2372.77.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70577c048ec8aa9aacfeac951930042a7f809b8e6fbf4e0540e2c325b9c32ca
+size 5168

runs/Sep08_05-28-07_fbd567ce2372/events.out.tfevents.1631082229.fbd567ce2372.77.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1899d956234b010e706fa71d71e9355f154768c86a380f1c4d73106a58c2fef1
+size 311

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9750920060c8be2e8ea4077f3cecb4563674a09e17a56881050cf92ea6ea7a9b
+size 2671