add model

.gitignore

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

README.md

@@ -0,0 +1,60 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: tolkien-mythopoeic-gen
+  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. -->
+
+# tolkien-mythopoeic-gen
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5110
+
+## 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: 16
+- eval_batch_size: 16
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.5732        | 1.0   | 145  | 3.5110          |
+| 3.5713        | 2.0   | 290  | 3.5110          |
+| 3.5718        | 3.0   | 435  | 3.5110          |
+
+
+### Framework versions
+
+- Transformers 4.10.2
+- Pytorch 1.9.0+cu102
+- 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": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2169b18f89c16392db042c084938a3aa345a71f65287b59ae513433837b78a86
+size 510403817

runs/Sep17_20-58-12_809f1a19f9e4/1631912379.7387805/events.out.tfevents.1631912379.809f1a19f9e4.75.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a94c320bd98345251aab768df353934219e2ae40711f6878b1993a37f8ac706
+size 4201

runs/Sep17_20-58-12_809f1a19f9e4/1631912910.4550812/events.out.tfevents.1631912910.809f1a19f9e4.75.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f92b6f510dc35ce2872317d4fae88a63edc938b3e6703e966931dde1a0ea2f
+size 4201

runs/Sep17_20-58-12_809f1a19f9e4/events.out.tfevents.1631912379.809f1a19f9e4.75.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3bf1a53b62a018beada61d2cb77ab46724ca8e6ce0f5ff37375e50d8bf0210
+size 4798

runs/Sep17_20-58-12_809f1a19f9e4/events.out.tfevents.1631912910.809f1a19f9e4.75.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14bc528b9c6d0ec088248c7f3625901854aafcb70a701de159029abcf232c4d
+size 4798

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a0129ffff269672b0c20ccad0119362f29a869a42ba838a9a8ddc16c7ab28a
+size 2671