Michaelj1/distilgpt2-finetuned-private

README.md

@@ -0,0 +1,82 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilgpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: distilgpt2-finetuned
+  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. -->
+
+# distilgpt2-finetuned
+
+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: 3.6391
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 4.0748        | 0.0436 | 50   | 3.8923          |
+| 3.8414        | 0.0871 | 100  | 3.8125          |
+| 3.8957        | 0.1307 | 150  | 3.7769          |
+| 3.8723        | 0.1743 | 200  | 3.7545          |
+| 4.0205        | 0.2179 | 250  | 3.7336          |
+| 3.7175        | 0.2614 | 300  | 3.7282          |
+| 3.7778        | 0.3050 | 350  | 3.7111          |
+| 3.7763        | 0.3486 | 400  | 3.6994          |
+| 3.8142        | 0.3922 | 450  | 3.6945          |
+| 3.7654        | 0.4357 | 500  | 3.6831          |
+| 3.9636        | 0.4793 | 550  | 3.6773          |
+| 3.703         | 0.5229 | 600  | 3.6692          |
+| 3.6114        | 0.5664 | 650  | 3.6647          |
+| 3.6269        | 0.6100 | 700  | 3.6591          |
+| 3.693         | 0.6536 | 750  | 3.6564          |
+| 3.7969        | 0.6972 | 800  | 3.6529          |
+| 3.6011        | 0.7407 | 850  | 3.6491          |
+| 3.4943        | 0.7843 | 900  | 3.6466          |
+| 3.7543        | 0.8279 | 950  | 3.6440          |
+| 3.861         | 0.8715 | 1000 | 3.6406          |
+| 3.5354        | 0.9150 | 1050 | 3.6401          |
+| 3.6661        | 0.9586 | 1100 | 3.6396          |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.0
+- Datasets 3.0.1
+- Tokenizers 0.20.0

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": "4.45.1",
+  "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": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7211ddd9a672647cb9490d9e032ebb9440497bd5a14f0518793cc28e9ec80667
+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 +1,20 @@
+{
+  "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|>",
+  "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:d08c8c41382c00e87f32acfdea2ed86146d1ade3d09cad5de275d42760df5076
+size 5240