add model

.gitignore

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

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- null
+model_index:
+- name: distilgpt2-finetuned-distilgpt2-med_articles
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+---
+
+<!-- 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-distilgpt2-med_articles
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5189
+
+## 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: 2e-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: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 260  | 3.6093          |
+| 3.7297        | 2.0   | 520  | 3.5603          |
+| 3.7297        | 3.0   | 780  | 3.5338          |
+| 3.5313        | 4.0   | 1040 | 3.5232          |
+| 3.5313        | 5.0   | 1300 | 3.5189          |
+
+
+### Framework versions
+
+- Transformers 4.9.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,45 @@
+{
+  "_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,
+  "gradient_checkpointing": false,
+  "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,
+  "resid_pdrop": 0.1,
+  "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": "4.9.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47bdd9cc0f58241e8c3723535e1d140733ebdbdacb62fa8bb46ce5635eb176e
+size 333972957

runs/Aug19_09-07-02_a08bd7a25748/1629364060.2303417/events.out.tfevents.1629364060.a08bd7a25748.75.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5976c3463eb4afef088c8ca08e92423eb3b9b1546c3b58194db40f7d0508124
+size 4205

runs/Aug19_09-07-02_a08bd7a25748/events.out.tfevents.1629364060.a08bd7a25748.75.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d26000a6883f76be30583af524de581731a2fd8f198be16e33cec31d48fa09ce
+size 5287

runs/Aug19_09-07-02_a08bd7a25748/events.out.tfevents.1629365091.a08bd7a25748.75.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e931fff94155c9cb07eb3b527c81cbf48f434985ee1f0133323d17e2963712e
+size 311

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "distilgpt2", "tokenizer_class": "GPT2Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0405174ec65f57997442cf28a7725916e28a12529b30095d35752bd25f6282c5
+size 2671