add model

.gitignore

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

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+model_index:
+- name: ZORK-AI-TEST
+  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. -->
+
+# ZORK-AI-TEST
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unkown dataset.
+
+## 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.8.2
+- Pytorch 1.9.0+cu102
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,37 @@
+{
+  "_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
+    }
+  },
+  "transformers_version": "4.8.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df8d813c3beca7e470c02619dbca94b3f51e5d714db828142178784de53ddeaf
+size 510403817

runs/Jul16_17-07-38_b5043029bd2f/1626455272.445084/events.out.tfevents.1626455272.b5043029bd2f.66.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186de7640ffccb47d1f1e46356d855477d29e6cb66f6e7d619dc3d98d0055bed
+size 4182

runs/Jul16_17-07-38_b5043029bd2f/events.out.tfevents.1626455272.b5043029bd2f.66.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f65b652bd9ed776d36aa022a5a5173653f113db80b6da828beac599ce99d6e
+size 3488

runs/Jul16_17-09-41_b5043029bd2f/1626455383.0266037/events.out.tfevents.1626455383.b5043029bd2f.66.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1fadb8540cd2c50bf6991af3ebeaf501f2f11aa9bc346be0a96feef4cccb29e
+size 4182

runs/Jul16_17-09-41_b5043029bd2f/events.out.tfevents.1626455383.b5043029bd2f.66.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac82a046da3cca774758dee57ab0fc7d1dff9015c8c867040c0ebb974bb92d7b
+size 3488

runs/Jul16_17-11-14_b5043029bd2f/1626455475.1321268/events.out.tfevents.1626455475.b5043029bd2f.66.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95afc6f864c58c6f4ec7d9a5eb2c7a1d7c5c5a0cb66826ae32eb9dacb0aa5fd
+size 4182

runs/Jul16_17-11-14_b5043029bd2f/events.out.tfevents.1626455475.b5043029bd2f.66.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abbeb8e0bc9c6e81389d99b365f19c4e4bbea365b0fece2a6c66a9214b347299
+size 3488

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e529847181eae6481f2814f4c77f4452bddad0e8a1c157ad67cf91c03201e52a
+size 2607