初始化项目，由ModelHub XC社区提供模型

Model: toloka/gpt2-large-supervised-prompt-writing
Source: Original Platform

.gitattributes

@@ -0,0 +1,52 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow 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
+ 
+*.msgpack 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
+*.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
+*.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
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: gpt2-sweep
+  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. -->
+
+# gpt2-sweep
+
+This model is a fine-tuned version of [gpt2-large](https://huggingface.co/gpt2-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0808
+- Accuracy: 0.8556
+
+## 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: 2.294477077303931e-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
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 2.4827        | 0.19  | 1000  | 2.4565          | 0.8520   |
+| 2.6468        | 0.37  | 2000  | 2.3303          | 0.8530   |
+| 2.5106        | 0.56  | 3000  | 2.2487          | 0.8537   |
+| 2.0732        | 0.74  | 4000  | 2.2020          | 0.8541   |
+| 2.159         | 0.93  | 5000  | 2.1594          | 0.8545   |
+| 1.856         | 1.12  | 6000  | 2.1518          | 0.8548   |
+| 1.9138        | 1.3   | 7000  | 2.1261          | 0.8551   |
+| 1.8055        | 1.49  | 8000  | 2.1126          | 0.8552   |
+| 2.0385        | 1.67  | 9000  | 2.1008          | 0.8554   |
+| 1.9648        | 1.86  | 10000 | 2.0858          | 0.8555   |
+
+
+### Framework versions
+
+- Transformers 4.26.0
+- Pytorch 2.0.0+cu117
+- Datasets 2.9.0
+- Tokenizers 0.13.2

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 50258,
+  "[PAD]": 50257
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.8555773331979283,
+    "eval_loss": 2.0807912349700928,
+    "eval_runtime": 125.0813,
+    "eval_samples": 10750,
+    "eval_samples_per_second": 85.944,
+    "eval_steps_per_second": 10.745,
+    "perplexity": 8.010804836289337,
+    "train_loss": 2.1236886782571673,
+    "train_runtime": 4504.4872,
+    "train_samples": 43003,
+    "train_samples_per_second": 19.093,
+    "train_steps_per_second": 2.387
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2-large",
+  "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": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "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": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 50259
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.8555773331979283,
+    "eval_loss": 2.0807912349700928,
+    "eval_runtime": 125.0813,
+    "eval_samples": 10750,
+    "eval_samples_per_second": 85.944,
+    "eval_steps_per_second": 10.745,
+    "perplexity": 8.010804836289337
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.26.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368a749450cb1a5803f7e73c1c57b26f4a12eb172800ba60f28f6d185b7bc539
+size 3133932520

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a854f911fcf67887abe92522ba2b32cb2eb42925c185792b4a089aaae7a38ae
+size 3134045245

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "sep_token": "</s>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a1f71fc93a6191eed67ec85ec92b97da343a6a20aad9f54ce7a10a5722dc25
+size 2107986

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2-large",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 2.1236886782571673,
+    "train_runtime": 4504.4872,
+    "train_samples": 43003,
+    "train_samples_per_second": 19.093,
+    "train_steps_per_second": 2.387
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4f0f455cfe353b38c6958e9dd682a9cb66e8e0afbc23961e3ce8be69bb0ab7
+size 3451