初始化项目，由ModelHub XC社区提供模型

Model: yasutoshi-lab/gpt2-verification Source: Original Platform
2026-06-13 17:40:49 +08:00
commit 0ef5f77815
12 changed files with 250813 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.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
+*.ckpt 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
+*.mlmodel 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,92 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+datasets:
+- wikitext
+metrics:
+- accuracy
+model-index:
+- name: gpt2-verification
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: wikitext wikitext-2-raw-v1
+      type: wikitext
+      args: wikitext-2-raw-v1
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.18546350602802217
+---
+
+<!-- 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-verification
+
+This model utilizes the GPT2 architecture and GPT2 tokenizer, and was trained from scratch using wikitext-2-raw-v1.
+
+It achieves the following results on the evaluation set:
+- Loss: 6.0571
+- Accuracy: 0.1855
+
+## Model Train Command
+
+```
+CUDA_VISIBLE_DEVICES=0 uv run python examples/pytorch/language-modeling/run_clm.py \
+  --model_type gpt2 \
+  --tokenizer_name gpt2 \
+  --dataset_name wikitext \
+  --dataset_config_name wikitext-2-raw-v1 \
+  --per_device_train_batch_size 2 \
+  --per_device_eval_batch_size 2 \
+  --num_train_epochs 3 \
+  --do_train \
+  --do_eval \
+  --output_dir ./output/gpt2-test \
+  --save_steps 500 \
+  --logging_steps 100 \
+  --push_to_hub \
+  --hub_model_id "yasutoshi-lab/gpt2-verification"
+  --hub_private_repo true \
+  --hub_strategy "end"
+```
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- 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
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.6.0.dev0
+- Pytorch 2.11.0+cu128
+- Datasets 4.8.4
+- Tokenizers 0.22.2
--- a/all_results.json
+++ b/all_results.json
@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.18546350602802217,
+    "eval_loss": 6.057050704956055,
+    "eval_runtime": 2.6888,
+    "eval_samples": 240,
+    "eval_samples_per_second": 89.26,
+    "eval_steps_per_second": 44.63,
+    "perplexity": 427.1138925540386,
+    "total_flos": 3634049581056000.0,
+    "train_loss": 6.285199090465582,
+    "train_runtime": 228.5387,
+    "train_samples": 2318,
+    "train_samples_per_second": 30.428,
+    "train_steps_per_second": 15.214
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": null,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.0.dev0",
+  "use_cache": false,
+  "vocab_size": 50257
+}
--- a/eval_results.json
+++ b/eval_results.json
@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.18546350602802217,
+    "eval_loss": 6.057050704956055,
+    "eval_runtime": 2.6888,
+    "eval_samples": 240,
+    "eval_samples_per_second": 89.26,
+    "eval_steps_per_second": 44.63,
+    "perplexity": 427.1138925540386
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.6.0.dev0",
+  "use_cache": true
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b5fadb2fa41ffba6fa57a2b2b65216107834a697a7d4c2e0c7f5660b866de6
+size 497774208
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3634049581056000.0,
+    "train_loss": 6.285199090465582,
+    "train_runtime": 228.5387,
+    "train_samples": 2318,
+    "train_samples_per_second": 30.428,
+    "train_steps_per_second": 15.214
+}
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,281 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3477,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08628127696289906,
+      "grad_norm": 1.6037696599960327,
+      "learning_rate": 4.857635893011217e-05,
+      "loss": 8.298780517578125,
+      "step": 100
+    },
+    {
+      "epoch": 0.1725625539257981,
+      "grad_norm": 1.7524189949035645,
+      "learning_rate": 4.7138337647397185e-05,
+      "loss": 7.087490844726562,
+      "step": 200
+    },
+    {
+      "epoch": 0.25884383088869717,
+      "grad_norm": 1.324486494064331,
+      "learning_rate": 4.57003163646822e-05,
+      "loss": 6.956798095703125,
+      "step": 300
+    },
+    {
+      "epoch": 0.3451251078515962,
+      "grad_norm": 1.4535937309265137,
+      "learning_rate": 4.426229508196721e-05,
+      "loss": 6.822440795898437,
+      "step": 400
+    },
+    {
+      "epoch": 0.4314063848144953,
+      "grad_norm": 1.327022910118103,
+      "learning_rate": 4.282427379925223e-05,
+      "loss": 6.734780883789062,
+      "step": 500
+    },
+    {
+      "epoch": 0.5176876617773943,
+      "grad_norm": 1.1214697360992432,
+      "learning_rate": 4.138625251653725e-05,
+      "loss": 6.682239379882812,
+      "step": 600
+    },
+    {
+      "epoch": 0.6039689387402933,
+      "grad_norm": 1.5475066900253296,
+      "learning_rate": 3.994823123382226e-05,
+      "loss": 6.600054321289062,
+      "step": 700
+    },
+    {
+      "epoch": 0.6902502157031924,
+      "grad_norm": 1.3128082752227783,
+      "learning_rate": 3.8510209951107276e-05,
+      "loss": 6.516415405273437,
+      "step": 800
+    },
+    {
+      "epoch": 0.7765314926660914,
+      "grad_norm": 1.6903055906295776,
+      "learning_rate": 3.707218866839229e-05,
+      "loss": 6.505012817382813,
+      "step": 900
+    },
+    {
+      "epoch": 0.8628127696289906,
+      "grad_norm": 1.616003394126892,
+      "learning_rate": 3.563416738567731e-05,
+      "loss": 6.397700805664062,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9490940465918896,
+      "grad_norm": 1.7408578395843506,
+      "learning_rate": 3.4196146102962325e-05,
+      "loss": 6.376287841796875,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0353753235547887,
+      "grad_norm": 1.6899269819259644,
+      "learning_rate": 3.2758124820247346e-05,
+      "loss": 6.3477630615234375,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1216566005176876,
+      "grad_norm": 1.5354853868484497,
+      "learning_rate": 3.132010353753236e-05,
+      "loss": 6.22337158203125,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2079378774805867,
+      "grad_norm": 1.530237078666687,
+      "learning_rate": 2.9882082254817374e-05,
+      "loss": 6.231620483398437,
+      "step": 1400
+    },
+    {
+      "epoch": 1.2942191544434858,
+      "grad_norm": 1.71237313747406,
+      "learning_rate": 2.8444060972102388e-05,
+      "loss": 6.191749877929688,
+      "step": 1500
+    },
+    {
+      "epoch": 1.380500431406385,
+      "grad_norm": 1.532090425491333,
+      "learning_rate": 2.7006039689387402e-05,
+      "loss": 6.148622436523437,
+      "step": 1600
+    },
+    {
+      "epoch": 1.4667817083692838,
+      "grad_norm": 1.5732359886169434,
+      "learning_rate": 2.5568018406672423e-05,
+      "loss": 6.130806274414063,
+      "step": 1700
+    },
+    {
+      "epoch": 1.553062985332183,
+      "grad_norm": 1.74668288230896,
+      "learning_rate": 2.4129997123957434e-05,
+      "loss": 6.11656005859375,
+      "step": 1800
+    },
+    {
+      "epoch": 1.639344262295082,
+      "grad_norm": 1.6298942565917969,
+      "learning_rate": 2.269197584124245e-05,
+      "loss": 6.120827026367188,
+      "step": 1900
+    },
+    {
+      "epoch": 1.725625539257981,
+      "grad_norm": 1.5918290615081787,
+      "learning_rate": 2.125395455852747e-05,
+      "loss": 6.088132934570313,
+      "step": 2000
+    },
+    {
+      "epoch": 1.8119068162208802,
+      "grad_norm": 1.4154537916183472,
+      "learning_rate": 1.9815933275812482e-05,
+      "loss": 6.068784790039063,
+      "step": 2100
+    },
+    {
+      "epoch": 1.8981880931837791,
+      "grad_norm": 1.5682926177978516,
+      "learning_rate": 1.83779119930975e-05,
+      "loss": 6.038920288085937,
+      "step": 2200
+    },
+    {
+      "epoch": 1.984469370146678,
+      "grad_norm": 1.5493305921554565,
+      "learning_rate": 1.6939890710382514e-05,
+      "loss": 6.069011840820313,
+      "step": 2300
+    },
+    {
+      "epoch": 2.0707506471095773,
+      "grad_norm": 1.7473928928375244,
+      "learning_rate": 1.550186942766753e-05,
+      "loss": 6.010381469726562,
+      "step": 2400
+    },
+    {
+      "epoch": 2.1570319240724762,
+      "grad_norm": 1.7771306037902832,
+      "learning_rate": 1.4063848144952545e-05,
+      "loss": 5.94528076171875,
+      "step": 2500
+    },
+    {
+      "epoch": 2.243313201035375,
+      "grad_norm": 1.8056012392044067,
+      "learning_rate": 1.2625826862237561e-05,
+      "loss": 5.949163208007812,
+      "step": 2600
+    },
+    {
+      "epoch": 2.3295944779982745,
+      "grad_norm": 1.547564148902893,
+      "learning_rate": 1.1187805579522577e-05,
+      "loss": 5.962681884765625,
+      "step": 2700
+    },
+    {
+      "epoch": 2.4158757549611733,
+      "grad_norm": 1.4664490222930908,
+      "learning_rate": 9.749784296807593e-06,
+      "loss": 5.9176702880859375,
+      "step": 2800
+    },
+    {
+      "epoch": 2.5021570319240727,
+      "grad_norm": 1.5322167873382568,
+      "learning_rate": 8.31176301409261e-06,
+      "loss": 5.913838500976563,
+      "step": 2900
+    },
+    {
+      "epoch": 2.5884383088869716,
+      "grad_norm": 1.51213538646698,
+      "learning_rate": 6.873741731377626e-06,
+      "loss": 5.912578735351563,
+      "step": 3000
+    },
+    {
+      "epoch": 2.6747195858498705,
+      "grad_norm": 1.7505192756652832,
+      "learning_rate": 5.435720448662641e-06,
+      "loss": 5.9252081298828125,
+      "step": 3100
+    },
+    {
+      "epoch": 2.76100086281277,
+      "grad_norm": 1.5077073574066162,
+      "learning_rate": 3.997699165947656e-06,
+      "loss": 5.895281982421875,
+      "step": 3200
+    },
+    {
+      "epoch": 2.8472821397756687,
+      "grad_norm": 1.7371774911880493,
+      "learning_rate": 2.559677883232672e-06,
+      "loss": 5.896738891601562,
+      "step": 3300
+    },
+    {
+      "epoch": 2.9335634167385676,
+      "grad_norm": 1.5654444694519043,
+      "learning_rate": 1.1216566005176878e-06,
+      "loss": 5.89673583984375,
+      "step": 3400
+    },
+    {
+      "epoch": 3.0,
+      "step": 3477,
+      "total_flos": 3634049581056000.0,
+      "train_loss": 6.285199090465582,
+      "train_runtime": 228.5387,
+      "train_samples_per_second": 30.428,
+      "train_steps_per_second": 15.214
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3477,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3634049581056000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19550298655b69d02d9936c4e57218adedfa90d1bf0bbb6c754d24ceddbdb5b1
+size 5265