初始化项目，由ModelHub XC社区提供模型

Model: akahana/gpt2-indonesia
Source: Original Platform

.gitattributes

@@ -0,0 +1,28 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin 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
+*.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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,30 @@
+---
+language: "id"
+widget:
+- text: "dahulu kala ada sebuah"
+---
+
+## how to use
+
+```python
+from transformers import pipeline, set_seed
+
+path = "akahana/gpt2-indonesia"
+generator = pipeline('text-generation', 
+                     model=path)
+set_seed(42)
+
+kalimat = "dahulu kala ada sebuah"
+preds = generator(kalimat, 
+                  max_length=64,
+                  num_return_sequences=3)
+for data in preds:
+  print(data)
+  
+
+{'generated_text': 'dahulu kala ada sebuah perkampungan yang bernama pomere. namun kini kawasan ini sudah tidak dikembangkan lagi sebagai kawasan industri seperti perusahaan pupuk. sumber-sumber lain sudah sulit ditemukan karena belum adanya kilang pupuk milik indonesia yang sering di kembangkan sehingga belum ada satupun yang masih tersisa yang tersisa. kawasan ini juga memproduksi gula aren milik pt graha bina sarana'}
+{'generated_text': 'dahulu kala ada sebuah desa kecil bernama desa. desa yang terkenal seperti halnya kota terdekat lainnya adalah desa tetangga yang bernama sama."\n"sebuah masjid merupakan suatu tempat suci yang digunakan umat islam untuk beribadah. beberapa masjid yang didaftarkan berikut memiliki suatu kehormatan tersendiri bagi masing-masing denominasi islam di dunia. sebuah masjid selain memiliki fungsi sebagai tempat'}
+{'generated_text': 'dahulu kala ada sebuah peradaban yang dibangun di sebelah barat sungai mississippi di sekitar desa kecil desa yang bernama sama. penduduk asli di desa ini berasal dari etnis teweh yang berpindah agama menjadi kristen, namun kemudian pindah agama menjadi kristen. desa arawak mempunyai beberapa desa lain seperti adibei, deti, riuhut dan sa'}
+
+
+```

added_tokens.json

@@ -0,0 +1 @@
+{"<|endoftext|>": 50257}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 35.0,
+    "eval_loss": 2.2617902755737305,
+    "eval_runtime": 115.5265,
+    "eval_samples": 5290,
+    "eval_samples_per_second": 45.79,
+    "eval_steps_per_second": 5.73,
+    "perplexity": 9.60026090370471,
+    "train_loss": 2.6988527534168076,
+    "train_runtime": 23608.904,
+    "train_samples": 99940,
+    "train_samples_per_second": 148.16,
+    "train_steps_per_second": 1.158
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "./gpt2/output",
+  "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": "4.13.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50258
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 35.0,
+    "eval_loss": 2.2617902755737305,
+    "eval_runtime": 115.5265,
+    "eval_samples": 5290,
+    "eval_samples_per_second": 45.79,
+    "eval_steps_per_second": 5.73,
+    "perplexity": 9.60026090370471
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f03bea0fdc6d310a5451e78b0bb0002b29ed37af4514c5bab04fe125b77daa3
+size 664755464

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4034228eb3a7f76d5e7c3c1f43ca1c0c0d992d27130cf91196325779be70ac8
+size 664794436

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a4a16f81c7a4d236ac109c3e244de8f3dae5cd1329e546533e25f7351aacfd
+size 497938536

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 35.0,
+    "train_loss": 2.6988527534168076,
+    "train_runtime": 23608.904,
+    "train_samples": 99940,
+    "train_samples_per_second": 148.16,
+    "train_steps_per_second": 1.158
+}

trainer_state.json

@@ -0,0 +1,349 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 35.0,
+  "global_step": 27335,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.908542162063289e-05,
+      "loss": 6.7425,
+      "step": 500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.8170843241265775e-05,
+      "loss": 5.4902,
+      "step": 1000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 4.725626486189867e-05,
+      "loss": 4.9535,
+      "step": 1500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 4.6341686482531555e-05,
+      "loss": 4.5816,
+      "step": 2000
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 4.5427108103164445e-05,
+      "loss": 4.3055,
+      "step": 2500
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 4.451252972379733e-05,
+      "loss": 4.0758,
+      "step": 3000
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 4.359795134443022e-05,
+      "loss": 3.8768,
+      "step": 3500
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 4.268337296506311e-05,
+      "loss": 3.7165,
+      "step": 4000
+    },
+    {
+      "epoch": 5.76,
+      "learning_rate": 4.1768794585696e-05,
+      "loss": 3.5584,
+      "step": 4500
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 4.085421620632888e-05,
+      "loss": 3.431,
+      "step": 5000
+    },
+    {
+      "epoch": 7.04,
+      "learning_rate": 3.993963782696177e-05,
+      "loss": 3.3197,
+      "step": 5500
+    },
+    {
+      "epoch": 7.68,
+      "learning_rate": 3.902505944759466e-05,
+      "loss": 3.2002,
+      "step": 6000
+    },
+    {
+      "epoch": 8.32,
+      "learning_rate": 3.811048106822755e-05,
+      "loss": 3.1084,
+      "step": 6500
+    },
+    {
+      "epoch": 8.96,
+      "learning_rate": 3.719590268886043e-05,
+      "loss": 3.0326,
+      "step": 7000
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 3.628132430949332e-05,
+      "loss": 2.9372,
+      "step": 7500
+    },
+    {
+      "epoch": 10.24,
+      "learning_rate": 3.536674593012621e-05,
+      "loss": 2.8657,
+      "step": 8000
+    },
+    {
+      "epoch": 10.88,
+      "learning_rate": 3.44521675507591e-05,
+      "loss": 2.8072,
+      "step": 8500
+    },
+    {
+      "epoch": 11.52,
+      "learning_rate": 3.353758917139199e-05,
+      "loss": 2.7354,
+      "step": 9000
+    },
+    {
+      "epoch": 12.16,
+      "learning_rate": 3.2623010792024876e-05,
+      "loss": 2.6862,
+      "step": 9500
+    },
+    {
+      "epoch": 12.8,
+      "learning_rate": 3.1708432412657766e-05,
+      "loss": 2.6269,
+      "step": 10000
+    },
+    {
+      "epoch": 13.44,
+      "learning_rate": 3.0793854033290656e-05,
+      "loss": 2.5687,
+      "step": 10500
+    },
+    {
+      "epoch": 14.08,
+      "learning_rate": 2.9879275653923545e-05,
+      "loss": 2.5422,
+      "step": 11000
+    },
+    {
+      "epoch": 14.72,
+      "learning_rate": 2.896469727455643e-05,
+      "loss": 2.4796,
+      "step": 11500
+    },
+    {
+      "epoch": 15.36,
+      "learning_rate": 2.8050118895189322e-05,
+      "loss": 2.4468,
+      "step": 12000
+    },
+    {
+      "epoch": 16.01,
+      "learning_rate": 2.7135540515822205e-05,
+      "loss": 2.4179,
+      "step": 12500
+    },
+    {
+      "epoch": 16.65,
+      "learning_rate": 2.6220962136455095e-05,
+      "loss": 2.3558,
+      "step": 13000
+    },
+    {
+      "epoch": 17.29,
+      "learning_rate": 2.530638375708798e-05,
+      "loss": 2.3408,
+      "step": 13500
+    },
+    {
+      "epoch": 17.93,
+      "learning_rate": 2.439180537772087e-05,
+      "loss": 2.3129,
+      "step": 14000
+    },
+    {
+      "epoch": 18.57,
+      "learning_rate": 2.347722699835376e-05,
+      "loss": 2.2645,
+      "step": 14500
+    },
+    {
+      "epoch": 19.21,
+      "learning_rate": 2.2562648618986647e-05,
+      "loss": 2.2492,
+      "step": 15000
+    },
+    {
+      "epoch": 19.85,
+      "learning_rate": 2.1648070239619537e-05,
+      "loss": 2.2222,
+      "step": 15500
+    },
+    {
+      "epoch": 20.49,
+      "learning_rate": 2.0733491860252424e-05,
+      "loss": 2.1802,
+      "step": 16000
+    },
+    {
+      "epoch": 21.13,
+      "learning_rate": 1.9818913480885314e-05,
+      "loss": 2.173,
+      "step": 16500
+    },
+    {
+      "epoch": 21.77,
+      "learning_rate": 1.89043351015182e-05,
+      "loss": 2.1459,
+      "step": 17000
+    },
+    {
+      "epoch": 22.41,
+      "learning_rate": 1.7989756722151087e-05,
+      "loss": 2.118,
+      "step": 17500
+    },
+    {
+      "epoch": 23.05,
+      "learning_rate": 1.7075178342783976e-05,
+      "loss": 2.1077,
+      "step": 18000
+    },
+    {
+      "epoch": 23.69,
+      "learning_rate": 1.6160599963416863e-05,
+      "loss": 2.0791,
+      "step": 18500
+    },
+    {
+      "epoch": 24.33,
+      "learning_rate": 1.5246021584049754e-05,
+      "loss": 2.0544,
+      "step": 19000
+    },
+    {
+      "epoch": 24.97,
+      "learning_rate": 1.4331443204682643e-05,
+      "loss": 2.0541,
+      "step": 19500
+    },
+    {
+      "epoch": 25.61,
+      "learning_rate": 1.341686482531553e-05,
+      "loss": 2.0238,
+      "step": 20000
+    },
+    {
+      "epoch": 26.25,
+      "learning_rate": 1.2502286445948419e-05,
+      "loss": 2.0115,
+      "step": 20500
+    },
+    {
+      "epoch": 26.89,
+      "learning_rate": 1.1587708066581307e-05,
+      "loss": 1.9977,
+      "step": 21000
+    },
+    {
+      "epoch": 27.53,
+      "learning_rate": 1.0673129687214195e-05,
+      "loss": 1.979,
+      "step": 21500
+    },
+    {
+      "epoch": 28.17,
+      "learning_rate": 9.758551307847083e-06,
+      "loss": 1.9705,
+      "step": 22000
+    },
+    {
+      "epoch": 28.81,
+      "learning_rate": 8.843972928479972e-06,
+      "loss": 1.9635,
+      "step": 22500
+    },
+    {
+      "epoch": 29.45,
+      "learning_rate": 7.92939454911286e-06,
+      "loss": 1.9388,
+      "step": 23000
+    },
+    {
+      "epoch": 30.09,
+      "learning_rate": 7.014816169745747e-06,
+      "loss": 1.9347,
+      "step": 23500
+    },
+    {
+      "epoch": 30.73,
+      "learning_rate": 6.100237790378636e-06,
+      "loss": 1.9227,
+      "step": 24000
+    },
+    {
+      "epoch": 31.37,
+      "learning_rate": 5.1856594110115235e-06,
+      "loss": 1.9157,
+      "step": 24500
+    },
+    {
+      "epoch": 32.01,
+      "learning_rate": 4.271081031644412e-06,
+      "loss": 1.9104,
+      "step": 25000
+    },
+    {
+      "epoch": 32.65,
+      "learning_rate": 3.3565026522773006e-06,
+      "loss": 1.895,
+      "step": 25500
+    },
+    {
+      "epoch": 33.29,
+      "learning_rate": 2.4419242729101884e-06,
+      "loss": 1.8957,
+      "step": 26000
+    },
+    {
+      "epoch": 33.93,
+      "learning_rate": 1.5273458935430768e-06,
+      "loss": 1.8829,
+      "step": 26500
+    },
+    {
+      "epoch": 34.57,
+      "learning_rate": 6.127675141759649e-07,
+      "loss": 1.8824,
+      "step": 27000
+    },
+    {
+      "epoch": 35.0,
+      "step": 27335,
+      "total_flos": 5.713934155776e+16,
+      "train_loss": 2.6988527534168076,
+      "train_runtime": 23608.904,
+      "train_samples_per_second": 148.16,
+      "train_steps_per_second": 1.158
+    }
+  ],
+  "max_steps": 27335,
+  "num_train_epochs": 35,
+  "total_flos": 5.713934155776e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479fcaaa17cbced1ba01f7b545b882d75d139a89da1fbb57266758f9216ddec5
+size 2799