Rsr2425/Transformers-Workshop-GPT-Generation

README.md

@@ -0,0 +1,87 @@
+---
+library_name: transformers
+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: 5.4268
+
+## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.4133        | 1.0   | 92   | 3.1858          |
+| 2.8751        | 2.0   | 184  | 3.2040          |
+| 2.9241        | 3.0   | 276  | 3.2442          |
+| 2.8796        | 4.0   | 368  | 3.2893          |
+| 2.5508        | 5.0   | 460  | 3.3988          |
+| 2.3505        | 6.0   | 552  | 3.4852          |
+| 2.1709        | 7.0   | 644  | 3.5973          |
+| 1.9833        | 8.0   | 736  | 3.7801          |
+| 1.9428        | 9.0   | 828  | 3.8925          |
+| 1.6357        | 10.0  | 920  | 4.0321          |
+| 1.6304        | 11.0  | 1012 | 4.1989          |
+| 1.5399        | 12.0  | 1104 | 4.3302          |
+| 1.3642        | 13.0  | 1196 | 4.4324          |
+| 1.2646        | 14.0  | 1288 | 4.5765          |
+| 1.0898        | 15.0  | 1380 | 4.7299          |
+| 1.0398        | 16.0  | 1472 | 4.7749          |
+| 0.945         | 17.0  | 1564 | 4.8901          |
+| 0.8175        | 18.0  | 1656 | 4.9615          |
+| 0.8893        | 19.0  | 1748 | 5.0045          |
+| 0.8573        | 20.0  | 1840 | 5.1104          |
+| 0.7946        | 21.0  | 1932 | 5.1732          |
+| 0.713         | 22.0  | 2024 | 5.2327          |
+| 0.7842        | 23.0  | 2116 | 5.2922          |
+| 0.6976        | 24.0  | 2208 | 5.2967          |
+| 0.6625        | 25.0  | 2300 | 5.3163          |
+| 0.6503        | 26.0  | 2392 | 5.3695          |
+| 0.5927        | 27.0  | 2484 | 5.3891          |
+| 0.6025        | 28.0  | 2576 | 5.4029          |
+| 0.6163        | 29.0  | 2668 | 5.4203          |
+| 0.5178        | 30.0  | 2760 | 5.4268          |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

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": "4.47.1",
+  "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": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40739bd9bcb6ae8410b0c66dd4343a399ea95d887d61704c9a092b4073fca8f9
+size 497774208

runs/Dec30_15-22-21_acb197b2c9fb/events.out.tfevents.1735572155.acb197b2c9fb.539.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b335d07770b0d9ce1e7c27f26eff8615eeee738a7b656130bf8ddf6785fddbec
+size 130209

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 +1,29 @@
+{
+  "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": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "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 sha256:18215b5094e7a88a4d5924ceb71c5a4c14b5bfba010661c8229643e97f090b00
+size 5368