HUGGINGFACE_ACCT_NAME/Transformers-Workshop-GPT-Generation

README.md

@@ -0,0 +1,86 @@
+---
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: lyric-gpt
+  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. -->
+
+# lyric-gpt
+
+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: 5.4529
+
+## 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: 0.0001
+- 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: 30
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.406         | 1.0   | 92   | 3.1840          |
+| 2.8788        | 2.0   | 184  | 3.2090          |
+| 2.92          | 3.0   | 276  | 3.2549          |
+| 2.8856        | 4.0   | 368  | 3.2943          |
+| 2.5725        | 5.0   | 460  | 3.3856          |
+| 2.3395        | 6.0   | 552  | 3.5080          |
+| 2.167         | 7.0   | 644  | 3.6203          |
+| 1.9773        | 8.0   | 736  | 3.7681          |
+| 1.9391        | 9.0   | 828  | 3.8787          |
+| 1.6115        | 10.0  | 920  | 4.0798          |
+| 1.6445        | 11.0  | 1012 | 4.1552          |
+| 1.528         | 12.0  | 1104 | 4.3184          |
+| 1.3714        | 13.0  | 1196 | 4.4737          |
+| 1.269         | 14.0  | 1288 | 4.5747          |
+| 1.0994        | 15.0  | 1380 | 4.6625          |
+| 1.0443        | 16.0  | 1472 | 4.8032          |
+| 0.9456        | 17.0  | 1564 | 4.9048          |
+| 0.8008        | 18.0  | 1656 | 4.9934          |
+| 0.8819        | 19.0  | 1748 | 5.0594          |
+| 0.8631        | 20.0  | 1840 | 5.1399          |
+| 0.7939        | 21.0  | 1932 | 5.1844          |
+| 0.717         | 22.0  | 2024 | 5.2256          |
+| 0.8029        | 23.0  | 2116 | 5.2945          |
+| 0.7064        | 24.0  | 2208 | 5.3211          |
+| 0.6867        | 25.0  | 2300 | 5.3637          |
+| 0.6398        | 26.0  | 2392 | 5.3977          |
+| 0.5992        | 27.0  | 2484 | 5.4118          |
+| 0.5986        | 28.0  | 2576 | 5.4357          |
+| 0.5909        | 29.0  | 2668 | 5.4557          |
+| 0.512         | 30.0  | 2760 | 5.4529          |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_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,
+  "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,
+  "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": 200,
+      "min_length": 100,
+      "temperature": 1.0,
+      "top_p": 0.95
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.41.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318a36bb6d957f2affe63cc25e5544278638cc335e1f0aa907de93518c22855c
+size 497774208

runs/May26_22-49-23_01c46465b667/events.out.tfevents.1716763774.01c46465b667.229.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fe250819d4d507456bcd00decbc365cdf79e1e1641e68891a3f27626d4e95fa
+size 129961

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,28 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf7acb78d32465dc84fd3e9149f6faf517fa365c8d7180b61d29229afcb2c0e
+size 5112