twi-gpt-chatbot

README.md

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilgpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+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: 0.4903
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 3.487         | 0.1216 | 500   | 2.7628          |
+| 2.4975        | 0.2433 | 1000  | 2.2091          |
+| 2.2501        | 0.3649 | 1500  | 1.8555          |
+| 2.0317        | 0.4866 | 2000  | 1.6036          |
+| 1.951         | 0.6082 | 2500  | 1.4196          |
+| 1.8645        | 0.7298 | 3000  | 1.2600          |
+| 1.7716        | 0.8515 | 3500  | 1.1290          |
+| 1.7462        | 0.9731 | 4000  | 1.0334          |
+| 1.6157        | 1.0946 | 4500  | 0.9300          |
+| 1.5509        | 1.2163 | 5000  | 0.8553          |
+| 1.5186        | 1.3379 | 5500  | 0.7855          |
+| 1.4767        | 1.4596 | 6000  | 0.7299          |
+| 1.4667        | 1.5812 | 6500  | 0.6972          |
+| 1.481         | 1.7028 | 7000  | 0.6611          |
+| 1.4245        | 1.8245 | 7500  | 0.6109          |
+| 1.4017        | 1.9461 | 8000  | 0.5911          |
+| 1.3376        | 2.0676 | 8500  | 0.5671          |
+| 1.3276        | 2.1893 | 9000  | 0.5600          |
+| 1.3228        | 2.3109 | 9500  | 0.5398          |
+| 1.3184        | 2.4326 | 10000 | 0.5246          |
+| 1.2939        | 2.5542 | 10500 | 0.5100          |
+| 1.3121        | 2.6758 | 11000 | 0.5025          |
+| 1.2904        | 2.7975 | 11500 | 0.4938          |
+| 1.2743        | 2.9191 | 12000 | 0.4903          |
+
+
+### Framework versions
+
+- Transformers 4.56.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.0

config.json

@@ -0,0 +1,46 @@
+{
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "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,
+  "pad_token_id": 50256,
+  "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
+    }
+  },
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "4.56.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f095846bfcc1139a58001e171f8f0e7cacd830c985a9ba59e8e1875b65fc20d9
+size 327657928

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "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": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb14bc404c8e1d7b6222aad56d7577bba08dddaa2f3b722c07a0a4b61a1bd68
+size 5713