Add Model Files

README.md

@@ -1,3 +1,56 @@
 ---
-license: mit
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: sanbooru\
+  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. -->
+
+# sanbooru\
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.6934
+- Accuracy: 0.4650
+
+## 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: 6
+- eval_batch_size: 6
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.27.0.dev0
+- Pytorch 1.13.1+cu116
+- Datasets 2.9.0
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6353ddc64072be10bc35861e3cc73e639debd29ddfd763ce379bd894004e84de
+size 333970169

runs/Feb20_17-51-22_cace4620fcc3/1676915547.6705458/events.out.tfevents.1676915547.cace4620fcc3.1077.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb365cc5c5658be09b6a9a21ca812a5d84c81b496f6c42287bd0d530fd3b64fc
+size 5799

runs/Feb20_17-51-22_cace4620fcc3/events.out.tfevents.1676915547.cace4620fcc3.1077.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d2328b591d6ad9a5467ac01c11d77c84227c0f857317484960ac80e6e4190b
+size 6687

runs/Feb20_17-51-22_cace4620fcc3/events.out.tfevents.1676924811.cace4620fcc3.1077.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cdd62374dad2f404361c221d3afbbe77095507c49fc42b83cc9306deb00ecb6
+size 363

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}