Duplicate from ECE1786-AG/lyrics-generator

Co-authored-by: Yiqian Qin <qiny17@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

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

README.md

@@ -0,0 +1,83 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: lyrics-generator-v2
+  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. -->
+
+# lyrics-generator-v2
+
+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: 2.1114
+
+## 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: 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.4325        | 0.36  | 200  | 2.3267          |
+| 2.4121        | 0.71  | 400  | 2.2693          |
+| 2.3582        | 1.07  | 600  | 2.2401          |
+| 2.2903        | 1.42  | 800  | 2.2182          |
+| 2.2738        | 1.78  | 1000 | 2.2046          |
+| 2.2322        | 2.14  | 1200 | 2.1922          |
+| 2.1933        | 2.49  | 1400 | 2.1832          |
+| 2.1944        | 2.85  | 1600 | 2.1736          |
+| 2.1632        | 3.2   | 1800 | 2.1648          |
+| 2.1366        | 3.56  | 2000 | 2.1554          |
+| 2.1492        | 3.91  | 2200 | 2.1491          |
+| 2.1108        | 4.27  | 2400 | 2.1472          |
+| 2.0882        | 4.63  | 2600 | 2.1422          |
+| 2.0971        | 4.98  | 2800 | 2.1343          |
+| 2.0829        | 5.34  | 3000 | 2.1318          |
+| 2.042         | 5.69  | 3200 | 2.1280          |
+| 2.0375        | 6.05  | 3400 | 2.1261          |
+| 2.0146        | 6.41  | 3600 | 2.1245          |
+| 2.0551        | 6.76  | 3800 | 2.1217          |
+| 1.992         | 7.12  | 4000 | 2.1182          |
+| 1.9994        | 7.47  | 4200 | 2.1170          |
+| 2.0189        | 7.83  | 4400 | 2.1156          |
+| 1.9795        | 8.19  | 4600 | 2.1133          |
+| 2.0101        | 8.54  | 4800 | 2.1143          |
+| 1.9864        | 8.9   | 5000 | 2.1111          |
+| 1.9602        | 9.25  | 5200 | 2.1120          |
+| 1.9899        | 9.61  | 5400 | 2.1117          |
+| 1.9928        | 9.96  | 5600 | 2.1114          |
+
+
+### Framework versions
+
+- Transformers 4.25.1
+- Pytorch 1.12.1+cu113
+- Datasets 2.7.1
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,12 @@
+{
+  "<BOS>": 50257,
+  "<EOS>": 50258,
+  "<PAD>": 50260,
+  "<UNK>": 50259,
+  "<country>": 50263,
+  "<generic>": 50266,
+  "<pop>": 50261,
+  "<r&b>": 50265,
+  "<rap>": 50262,
+  "<rock>": 50264
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50257,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50258,
+  "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,
+  "pad_token_id": 50260,
+  "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": "4.25.1",
+  "unk_token_id": 50259,
+  "use_cache": true,
+  "vocab_size": 50267
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad41da6864a100200d58dd01927753e62c2ca896cf983573c3bda12081ef5838
+size 510427241

runs/Dec05_02-10-54_c6ed9cf582c8/1670224274.1706448/events.out.tfevents.1670224274.c6ed9cf582c8.116.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aae94c858bc3bd780168715d6e877636c48c82f479b940345e70a33df93ae89
+size 5600

runs/Dec05_02-10-54_c6ed9cf582c8/events.out.tfevents.1670224274.c6ed9cf582c8.116.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43143c6fa886a3330bf2e55cb0d3b2d37659bc2423c462c81443b5cdf0b24fe4
+size 16442

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<pop>",
+    "<rap>",
+    "<country>",
+    "<rock>",
+    "<r&b>",
+    "<generic>"
+  ],
+  "bos_token": "<BOS>",
+  "eos_token": "<EOS>",
+  "pad_token": "<PAD>",
+  "unk_token": "<UNK>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee597ed88a2711f849d8301c55edea6741fe02ef0a6a5dfaf18ec376ef01df2
+size 3439