初始化项目，由ModelHub XC社区提供模型

Model: arminmehrabian/distilgpt2-finetuned-wikitext2-agu
Source: Original Platform

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

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

README.md

@@ -0,0 +1,110 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: distilgpt2-finetuned-wikitext2-agu
+  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-wikitext2-agu
+
+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: 3.1869
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step    | Validation Loss |
+|:-------------:|:-----:|:-------:|:---------------:|
+| 3.7357        | 1.0   | 13655   | 3.6781          |
+| 3.5721        | 2.0   | 27310   | 3.5302          |
+| 3.4961        | 3.0   | 40965   | 3.4658          |
+| 3.4406        | 4.0   | 54620   | 3.4242          |
+| 3.4043        | 5.0   | 68275   | 3.3943          |
+| 3.3789        | 6.0   | 81930   | 3.3726          |
+| 3.3576        | 7.0   | 95585   | 3.3538          |
+| 3.3389        | 8.0   | 109240  | 3.3389          |
+| 3.3151        | 9.0   | 122895  | 3.3270          |
+| 3.314         | 5.0   | 136545  | 3.3226          |
+| 3.3044        | 6.0   | 163854  | 3.3124          |
+| 3.2931        | 7.0   | 191163  | 3.3078          |
+| 3.2874        | 8.0   | 218472  | 3.3094          |
+| 3.2817        | 9.0   | 245781  | 3.2943          |
+| 3.269         | 10.0  | 273090  | 3.2785          |
+| 3.2423        | 11.0  | 300399  | 3.2651          |
+| 3.2253        | 12.0  | 327708  | 3.2530          |
+| 3.2096        | 13.0  | 355017  | 3.2435          |
+| 3.1939        | 14.0  | 382326  | 3.2326          |
+| 3.1786        | 15.0  | 409635  | 3.2225          |
+| 3.1625        | 16.0  | 436944  | 3.2198          |
+| 3.1619        | 17.0  | 464253  | 3.2180          |
+| 3.1521        | 18.0  | 491562  | 3.2164          |
+| 3.1555        | 19.0  | 518871  | 3.2152          |
+| 3.1523        | 20.0  | 546180  | 3.2164          |
+| 3.1639        | 21.0  | 573489  | 3.2133          |
+| 3.1483        | 22.0  | 600798  | 3.2113          |
+| 3.1497        | 23.0  | 628107  | 3.2077          |
+| 3.1468        | 24.0  | 655416  | 3.2066          |
+| 3.1461        | 25.0  | 682725  | 3.2052          |
+| 3.1391        | 26.0  | 710034  | 3.2039          |
+| 3.1384        | 27.0  | 737343  | 3.2031          |
+| 3.135         | 28.0  | 764652  | 3.2020          |
+| 3.1262        | 29.0  | 791961  | 3.2015          |
+| 3.1357        | 30.0  | 819270  | 3.2019          |
+| 3.1372        | 31.0  | 846579  | 3.2003          |
+| 3.1346        | 32.0  | 873888  | 3.1988          |
+| 3.134         | 33.0  | 901197  | 3.1975          |
+| 3.1256        | 34.0  | 928506  | 3.1965          |
+| 3.1261        | 35.0  | 955815  | 3.1950          |
+| 3.1255        | 36.0  | 983124  | 3.1945          |
+| 3.1278        | 37.0  | 1010433 | 3.1940          |
+| 3.1186        | 38.0  | 1037742 | 3.1934          |
+| 3.1136        | 39.0  | 1065051 | 3.1932          |
+| 3.12          | 40.0  | 1092360 | 3.1931          |
+| 3.12          | 41.0  | 1119669 | 3.1930          |
+| 3.1165        | 42.0  | 1146978 | 3.1914          |
+| 3.1166        | 43.0  | 1174287 | 3.1900          |
+| 3.1139        | 44.0  | 1201596 | 3.1892          |
+| 3.1135        | 45.0  | 1228905 | 3.1885          |
+| 3.1077        | 46.0  | 1256214 | 3.1881          |
+| 3.1097        | 47.0  | 1283523 | 3.1873          |
+| 3.1076        | 48.0  | 1310832 | 3.1872          |
+| 3.102         | 49.0  | 1338141 | 3.1870          |
+| 3.1086        | 50.0  | 1365450 | 3.1869          |
+
+
+### Framework versions
+
+- Transformers 4.18.0
+- Pytorch 1.9.0+cu111
+- Datasets 2.4.0
+- Tokenizers 0.12.1

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": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89412489e86198c0ae67696da2f762dad5d9f533a69a86eea8811e64d09fb798
+size 333967901

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 sha256:31bb539e73bc6a0612788783e5b63c172966efe5801441875daa141c3a7e49cc
+size 3119