初始化项目，由ModelHub XC社区提供模型

Model: shrinath-suresh/gpt2
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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

.gitignore

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

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: gpt2
+  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
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0655
+- Accuracy: 0.7402
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 30.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.27.0.dev0
+- Pytorch 1.13.1
+- Datasets 2.9.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.7402085369827305,
+    "eval_loss": 1.0654966831207275,
+    "eval_runtime": 1.3052,
+    "eval_samples": 30,
+    "eval_samples_per_second": 22.986,
+    "eval_steps_per_second": 11.493,
+    "perplexity": 2.9022801396881754,
+    "train_loss": 1.5244493435467037,
+    "train_runtime": 20965.488,
+    "train_samples": 3163,
+    "train_samples_per_second": 4.526,
+    "train_steps_per_second": 2.264
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "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": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 30.0,
+    "eval_accuracy": 0.7402085369827305,
+    "eval_loss": 1.0654966831207275,
+    "eval_runtime": 1.3052,
+    "eval_samples": 30,
+    "eval_samples_per_second": 22.986,
+    "eval_steps_per_second": 11.493,
+    "perplexity": 2.9022801396881754
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.27.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63c7812c6bf0fe5f55f9f426b178433145e555d956905e2dfdba9b04bbf851d
+size 510398013

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "train_loss": 1.5244493435467037,
+    "train_runtime": 20965.488,
+    "train_samples": 3163,
+    "train_samples_per_second": 4.526,
+    "train_steps_per_second": 2.264
+}

trainer_state.json

@@ -0,0 +1,589 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.0,
+  "global_step": 47460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.94732406236831e-05,
+      "loss": 2.451,
+      "step": 500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.8946481247366205e-05,
+      "loss": 2.2767,
+      "step": 1000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.8419721871049303e-05,
+      "loss": 2.2059,
+      "step": 1500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 4.789296249473241e-05,
+      "loss": 2.1348,
+      "step": 2000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 4.7366203118415506e-05,
+      "loss": 2.0683,
+      "step": 2500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 4.683944374209861e-05,
+      "loss": 2.0449,
+      "step": 3000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 4.631268436578171e-05,
+      "loss": 1.9823,
+      "step": 3500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 4.5785924989464814e-05,
+      "loss": 1.9737,
+      "step": 4000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 4.525916561314791e-05,
+      "loss": 1.9638,
+      "step": 4500
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 4.473240623683102e-05,
+      "loss": 1.8954,
+      "step": 5000
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 4.420564686051412e-05,
+      "loss": 1.8848,
+      "step": 5500
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 4.367888748419722e-05,
+      "loss": 1.8964,
+      "step": 6000
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 4.3152128107880325e-05,
+      "loss": 1.8572,
+      "step": 6500
+    },
+    {
+      "epoch": 4.42,
+      "learning_rate": 4.262536873156342e-05,
+      "loss": 1.8132,
+      "step": 7000
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 4.209860935524653e-05,
+      "loss": 1.8463,
+      "step": 7500
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 4.1571849978929626e-05,
+      "loss": 1.8012,
+      "step": 8000
+    },
+    {
+      "epoch": 5.37,
+      "learning_rate": 4.104509060261273e-05,
+      "loss": 1.7557,
+      "step": 8500
+    },
+    {
+      "epoch": 5.69,
+      "learning_rate": 4.051833122629583e-05,
+      "loss": 1.7647,
+      "step": 9000
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 3.9991571849978934e-05,
+      "loss": 1.7886,
+      "step": 9500
+    },
+    {
+      "epoch": 6.32,
+      "learning_rate": 3.946481247366203e-05,
+      "loss": 1.7078,
+      "step": 10000
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 3.893805309734514e-05,
+      "loss": 1.7211,
+      "step": 10500
+    },
+    {
+      "epoch": 6.95,
+      "learning_rate": 3.8411293721028235e-05,
+      "loss": 1.7393,
+      "step": 11000
+    },
+    {
+      "epoch": 7.27,
+      "learning_rate": 3.788453434471134e-05,
+      "loss": 1.6734,
+      "step": 11500
+    },
+    {
+      "epoch": 7.59,
+      "learning_rate": 3.735777496839444e-05,
+      "loss": 1.6889,
+      "step": 12000
+    },
+    {
+      "epoch": 7.9,
+      "learning_rate": 3.6831015592077536e-05,
+      "loss": 1.6733,
+      "step": 12500
+    },
+    {
+      "epoch": 8.22,
+      "learning_rate": 3.630425621576064e-05,
+      "loss": 1.6575,
+      "step": 13000
+    },
+    {
+      "epoch": 8.53,
+      "learning_rate": 3.577749683944374e-05,
+      "loss": 1.6172,
+      "step": 13500
+    },
+    {
+      "epoch": 8.85,
+      "learning_rate": 3.5250737463126844e-05,
+      "loss": 1.6498,
+      "step": 14000
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 3.472397808680995e-05,
+      "loss": 1.6185,
+      "step": 14500
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 3.419721871049305e-05,
+      "loss": 1.5877,
+      "step": 15000
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 3.367045933417615e-05,
+      "loss": 1.6174,
+      "step": 15500
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 3.3143699957859256e-05,
+      "loss": 1.6148,
+      "step": 16000
+    },
+    {
+      "epoch": 10.43,
+      "learning_rate": 3.2616940581542354e-05,
+      "loss": 1.5563,
+      "step": 16500
+    },
+    {
+      "epoch": 10.75,
+      "learning_rate": 3.209018120522546e-05,
+      "loss": 1.5754,
+      "step": 17000
+    },
+    {
+      "epoch": 11.06,
+      "learning_rate": 3.156342182890856e-05,
+      "loss": 1.5547,
+      "step": 17500
+    },
+    {
+      "epoch": 11.38,
+      "learning_rate": 3.1036662452591655e-05,
+      "loss": 1.5282,
+      "step": 18000
+    },
+    {
+      "epoch": 11.69,
+      "learning_rate": 3.050990307627476e-05,
+      "loss": 1.5312,
+      "step": 18500
+    },
+    {
+      "epoch": 12.01,
+      "learning_rate": 2.998314369995786e-05,
+      "loss": 1.5508,
+      "step": 19000
+    },
+    {
+      "epoch": 12.33,
+      "learning_rate": 2.9456384323640963e-05,
+      "loss": 1.4954,
+      "step": 19500
+    },
+    {
+      "epoch": 12.64,
+      "learning_rate": 2.8929624947324065e-05,
+      "loss": 1.5208,
+      "step": 20000
+    },
+    {
+      "epoch": 12.96,
+      "learning_rate": 2.8402865571007166e-05,
+      "loss": 1.5115,
+      "step": 20500
+    },
+    {
+      "epoch": 13.27,
+      "learning_rate": 2.7876106194690264e-05,
+      "loss": 1.4648,
+      "step": 21000
+    },
+    {
+      "epoch": 13.59,
+      "learning_rate": 2.7349346818373366e-05,
+      "loss": 1.4778,
+      "step": 21500
+    },
+    {
+      "epoch": 13.91,
+      "learning_rate": 2.6822587442056467e-05,
+      "loss": 1.4992,
+      "step": 22000
+    },
+    {
+      "epoch": 14.22,
+      "learning_rate": 2.629582806573957e-05,
+      "loss": 1.4505,
+      "step": 22500
+    },
+    {
+      "epoch": 14.54,
+      "learning_rate": 2.576906868942267e-05,
+      "loss": 1.4585,
+      "step": 23000
+    },
+    {
+      "epoch": 14.85,
+      "learning_rate": 2.524230931310577e-05,
+      "loss": 1.4571,
+      "step": 23500
+    },
+    {
+      "epoch": 15.17,
+      "learning_rate": 2.4715549936788876e-05,
+      "loss": 1.441,
+      "step": 24000
+    },
+    {
+      "epoch": 15.49,
+      "learning_rate": 2.4188790560471978e-05,
+      "loss": 1.4268,
+      "step": 24500
+    },
+    {
+      "epoch": 15.8,
+      "learning_rate": 2.366203118415508e-05,
+      "loss": 1.4248,
+      "step": 25000
+    },
+    {
+      "epoch": 16.12,
+      "learning_rate": 2.313527180783818e-05,
+      "loss": 1.4385,
+      "step": 25500
+    },
+    {
+      "epoch": 16.43,
+      "learning_rate": 2.2608512431521282e-05,
+      "loss": 1.3802,
+      "step": 26000
+    },
+    {
+      "epoch": 16.75,
+      "learning_rate": 2.2081753055204384e-05,
+      "loss": 1.4195,
+      "step": 26500
+    },
+    {
+      "epoch": 17.07,
+      "learning_rate": 2.1554993678887485e-05,
+      "loss": 1.4127,
+      "step": 27000
+    },
+    {
+      "epoch": 17.38,
+      "learning_rate": 2.1028234302570587e-05,
+      "loss": 1.3683,
+      "step": 27500
+    },
+    {
+      "epoch": 17.7,
+      "learning_rate": 2.0501474926253688e-05,
+      "loss": 1.3864,
+      "step": 28000
+    },
+    {
+      "epoch": 18.02,
+      "learning_rate": 1.997471554993679e-05,
+      "loss": 1.405,
+      "step": 28500
+    },
+    {
+      "epoch": 18.33,
+      "learning_rate": 1.944795617361989e-05,
+      "loss": 1.3668,
+      "step": 29000
+    },
+    {
+      "epoch": 18.65,
+      "learning_rate": 1.8921196797302992e-05,
+      "loss": 1.3738,
+      "step": 29500
+    },
+    {
+      "epoch": 18.96,
+      "learning_rate": 1.8394437420986094e-05,
+      "loss": 1.3662,
+      "step": 30000
+    },
+    {
+      "epoch": 19.28,
+      "learning_rate": 1.7867678044669195e-05,
+      "loss": 1.3227,
+      "step": 30500
+    },
+    {
+      "epoch": 19.6,
+      "learning_rate": 1.7340918668352297e-05,
+      "loss": 1.3413,
+      "step": 31000
+    },
+    {
+      "epoch": 19.91,
+      "learning_rate": 1.6814159292035402e-05,
+      "loss": 1.3815,
+      "step": 31500
+    },
+    {
+      "epoch": 20.23,
+      "learning_rate": 1.62873999157185e-05,
+      "loss": 1.3393,
+      "step": 32000
+    },
+    {
+      "epoch": 20.54,
+      "learning_rate": 1.57606405394016e-05,
+      "loss": 1.3243,
+      "step": 32500
+    },
+    {
+      "epoch": 20.86,
+      "learning_rate": 1.5233881163084704e-05,
+      "loss": 1.3235,
+      "step": 33000
+    },
+    {
+      "epoch": 21.18,
+      "learning_rate": 1.4707121786767806e-05,
+      "loss": 1.3202,
+      "step": 33500
+    },
+    {
+      "epoch": 21.49,
+      "learning_rate": 1.4180362410450906e-05,
+      "loss": 1.3038,
+      "step": 34000
+    },
+    {
+      "epoch": 21.81,
+      "learning_rate": 1.3653603034134007e-05,
+      "loss": 1.3142,
+      "step": 34500
+    },
+    {
+      "epoch": 22.12,
+      "learning_rate": 1.3126843657817109e-05,
+      "loss": 1.3412,
+      "step": 35000
+    },
+    {
+      "epoch": 22.44,
+      "learning_rate": 1.260008428150021e-05,
+      "loss": 1.293,
+      "step": 35500
+    },
+    {
+      "epoch": 22.76,
+      "learning_rate": 1.2073324905183313e-05,
+      "loss": 1.3082,
+      "step": 36000
+    },
+    {
+      "epoch": 23.07,
+      "learning_rate": 1.1546565528866415e-05,
+      "loss": 1.3009,
+      "step": 36500
+    },
+    {
+      "epoch": 23.39,
+      "learning_rate": 1.1019806152549515e-05,
+      "loss": 1.3034,
+      "step": 37000
+    },
+    {
+      "epoch": 23.7,
+      "learning_rate": 1.0493046776232618e-05,
+      "loss": 1.2953,
+      "step": 37500
+    },
+    {
+      "epoch": 24.02,
+      "learning_rate": 9.96628739991572e-06,
+      "loss": 1.2674,
+      "step": 38000
+    },
+    {
+      "epoch": 24.34,
+      "learning_rate": 9.43952802359882e-06,
+      "loss": 1.2845,
+      "step": 38500
+    },
+    {
+      "epoch": 24.65,
+      "learning_rate": 8.912768647281922e-06,
+      "loss": 1.2762,
+      "step": 39000
+    },
+    {
+      "epoch": 24.97,
+      "learning_rate": 8.386009270965024e-06,
+      "loss": 1.2756,
+      "step": 39500
+    },
+    {
+      "epoch": 25.28,
+      "learning_rate": 7.859249894648125e-06,
+      "loss": 1.2749,
+      "step": 40000
+    },
+    {
+      "epoch": 25.6,
+      "learning_rate": 7.3324905183312265e-06,
+      "loss": 1.2762,
+      "step": 40500
+    },
+    {
+      "epoch": 25.92,
+      "learning_rate": 6.805731142014328e-06,
+      "loss": 1.2609,
+      "step": 41000
+    },
+    {
+      "epoch": 26.23,
+      "learning_rate": 6.2789717656974295e-06,
+      "loss": 1.2401,
+      "step": 41500
+    },
+    {
+      "epoch": 26.55,
+      "learning_rate": 5.752212389380531e-06,
+      "loss": 1.2583,
+      "step": 42000
+    },
+    {
+      "epoch": 26.86,
+      "learning_rate": 5.225453013063633e-06,
+      "loss": 1.2767,
+      "step": 42500
+    },
+    {
+      "epoch": 27.18,
+      "learning_rate": 4.698693636746735e-06,
+      "loss": 1.2532,
+      "step": 43000
+    },
+    {
+      "epoch": 27.5,
+      "learning_rate": 4.171934260429835e-06,
+      "loss": 1.2522,
+      "step": 43500
+    },
+    {
+      "epoch": 27.81,
+      "learning_rate": 3.6451748841129377e-06,
+      "loss": 1.2567,
+      "step": 44000
+    },
+    {
+      "epoch": 28.13,
+      "learning_rate": 3.1184155077960387e-06,
+      "loss": 1.2599,
+      "step": 44500
+    },
+    {
+      "epoch": 28.45,
+      "learning_rate": 2.59165613147914e-06,
+      "loss": 1.2493,
+      "step": 45000
+    },
+    {
+      "epoch": 28.76,
+      "learning_rate": 2.064896755162242e-06,
+      "loss": 1.245,
+      "step": 45500
+    },
+    {
+      "epoch": 29.08,
+      "learning_rate": 1.5381373788453435e-06,
+      "loss": 1.2396,
+      "step": 46000
+    },
+    {
+      "epoch": 29.39,
+      "learning_rate": 1.0113780025284452e-06,
+      "loss": 1.2441,
+      "step": 46500
+    },
+    {
+      "epoch": 29.71,
+      "learning_rate": 4.846186262115466e-07,
+      "loss": 1.2251,
+      "step": 47000
+    },
+    {
+      "epoch": 30.0,
+      "step": 47460,
+      "total_flos": 4.958800183296e+16,
+      "train_loss": 1.5244493435467037,
+      "train_runtime": 20965.488,
+      "train_samples_per_second": 4.526,
+      "train_steps_per_second": 2.264
+    }
+  ],
+  "max_steps": 47460,
+  "num_train_epochs": 30,
+  "total_flos": 4.958800183296e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224fe1555ca1d9f041213aaea0a02e59f0b8a8b11fa9c34ec8becbf1ceeda8cd
+size 3515