初始化项目，由ModelHub XC社区提供模型

Model: fpadovani/urd-arab-100mb-10mb_seed3407
Source: Original Platform

.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

README.md

@@ -0,0 +1,58 @@
+---
+base_model: goldfish-models/urd_arab_100mb
+library_name: transformers
+model_name: urd-arab-100mb-10mb_seed3407
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for urd-arab-100mb-10mb_seed3407
+
+This model is a fine-tuned version of [goldfish-models/urd_arab_100mb](https://huggingface.co/goldfish-models/urd_arab_100mb).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="fpadovani/urd-arab-100mb-10mb_seed3407", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/f-padovani-university-of-groningen/new_tokenizers/runs/9b0g3wtp) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.23.0
+- Transformers: 4.56.2
+- Pytorch: 2.11.0
+- Datasets: 4.8.4
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

checkpoint-1000/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 47386,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 47387,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 47388,
+  "prefix": "[CLS]",
+  "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,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

checkpoint-1000/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 47386,
+  "eos_token_id": [
+    47387,
+    50001
+  ],
+  "pad_token_id": 47388,
+  "transformers_version": "4.56.2"
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8102512c0da2788f2190e5e2573a6f15fffcaecad995be9c3949a3b072d640d3
+size 246410944

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf2dc41bebd77e70beddf564df5eb87a8dcb1c43e6a6130c66e54467d3e0ee57
+size 14645

checkpoint-1000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c1246bf680a2a73ff33ccf7bbcde25b6d81c80c5cc610f4680cf9942f981b
+size 1138208

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1c135f6b8569a4ca131508cf9d8c7cebd96bc433f924eb7233c36a7d98147e
+size 6289

checkpoint-1500/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 47386,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 47387,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 47388,
+  "prefix": "[CLS]",
+  "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,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

checkpoint-1500/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 47386,
+  "eos_token_id": [
+    47387,
+    50001
+  ],
+  "pad_token_id": 47388,
+  "transformers_version": "4.56.2"
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135dfd095b5d3b7fce0dff5ac470a3c0f6c1f94e4e1469994e173e2c62bdd01d
+size 246410944

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35946c68c543618614b51fb86273bb877e6ce3fdf97d8590ae30f9ca10e6d669
+size 14645

checkpoint-1500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c1246bf680a2a73ff33ccf7bbcde25b6d81c80c5cc610f4680cf9942f981b
+size 1138208

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1c135f6b8569a4ca131508cf9d8c7cebd96bc433f924eb7233c36a7d98147e
+size 6289

checkpoint-2000/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 47386,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 47387,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 47388,
+  "prefix": "[CLS]",
+  "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,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 47386,
+  "eos_token_id": [
+    47387,
+    50001
+  ],
+  "pad_token_id": 47388,
+  "transformers_version": "4.56.2"
+}

checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39dc421a3385edd59daef8c967ddccefbe2ecbf7864d46d4336d4801af05a7da
+size 246410944

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8920f5b5788dbb71f54bae8932e965ac5e7bedc55140997566d358333cd64ad2
+size 14645

checkpoint-2000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c1246bf680a2a73ff33ccf7bbcde25b6d81c80c5cc610f4680cf9942f981b
+size 1138208

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1c135f6b8569a4ca131508cf9d8c7cebd96bc433f924eb7233c36a7d98147e
+size 6289

checkpoint-2500/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 47386,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 47387,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 47388,
+  "prefix": "[CLS]",
+  "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,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

checkpoint-2500/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 47386,
+  "eos_token_id": [
+    47387,
+    50001
+  ],
+  "pad_token_id": 47388,
+  "transformers_version": "4.56.2"
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6878cd3bc7bc17dcb1576bb59fe3afe5fef205b2ef44e599a2ce9a83544668e5
+size 246410944

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac2ed9da03b5d39f5a1c149cae285adb8a8a7e815304dce61aac185be2f9307
+size 14645

checkpoint-2500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c1246bf680a2a73ff33ccf7bbcde25b6d81c80c5cc610f4680cf9942f981b
+size 1138208

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1c135f6b8569a4ca131508cf9d8c7cebd96bc433f924eb7233c36a7d98147e
+size 6289

checkpoint-3000/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 47386,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 47387,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 47388,
+  "prefix": "[CLS]",
+  "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,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

checkpoint-3000/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 47386,
+  "eos_token_id": [
+    47387,
+    50001
+  ],
+  "pad_token_id": 47388,
+  "transformers_version": "4.56.2"
+}

checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7951a7a16f696afb45529946caaec0319795f2de0efa5b2de4967d1ea8f38be4
+size 246410944

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80c601e9cdbc389320d0068cd325a04242a53327f73e4679a932155bacee7fd0
+size 14645

checkpoint-3000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c1246bf680a2a73ff33ccf7bbcde25b6d81c80c5cc610f4680cf9942f981b
+size 1138208

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1c135f6b8569a4ca131508cf9d8c7cebd96bc433f924eb7233c36a7d98147e
+size 6289

checkpoint-3500/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 47386,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 47387,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 47388,
+  "prefix": "[CLS]",
+  "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,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

checkpoint-3500/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 47386,
+  "eos_token_id": [
+    47387,
+    50001
+  ],
+  "pad_token_id": 47388,
+  "transformers_version": "4.56.2"
+}

checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f79880f2303ed8909bf667fabeb206822f9286a6f49fdbe797887545f47ae6
+size 246410944

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf6b8eb5c1ee27c4add4001a0caa8b8a43e95632727924bcb4207820c61aaba
+size 14645

checkpoint-3500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c1246bf680a2a73ff33ccf7bbcde25b6d81c80c5cc610f4680cf9942f981b
+size 1138208

checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1c135f6b8569a4ca131508cf9d8c7cebd96bc433f924eb7233c36a7d98147e
+size 6289

checkpoint-4000/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 47386,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 47387,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 47388,
+  "prefix": "[CLS]",
+  "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,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

checkpoint-4000/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 47386,
+  "eos_token_id": [
+    47387,
+    50001
+  ],
+  "pad_token_id": 47388,
+  "transformers_version": "4.56.2"
+}

checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da045b6f162b8f24a71f2614c17fd48ebc5fed08c2a3ac26b5bf9d7358d1ab01
+size 246410944

checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe122c29393120b83e80b56d25df27f62c0ec7bb6765489e905efa63e449aa2
+size 14645

checkpoint-4000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c1246bf680a2a73ff33ccf7bbcde25b6d81c80c5cc610f4680cf9942f981b
+size 1138208

checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1c135f6b8569a4ca131508cf9d8c7cebd96bc433f924eb7233c36a7d98147e
+size 6289

checkpoint-4500/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 47386,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 47387,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 47388,
+  "prefix": "[CLS]",
+  "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,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

checkpoint-4500/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 47386,
+  "eos_token_id": [
+    47387,
+    50001
+  ],
+  "pad_token_id": 47388,
+  "transformers_version": "4.56.2"
+}

checkpoint-4500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601bda34192abba164714ebfe5587a993d9edd933877173749113decd6211b10
+size 246410944

checkpoint-4500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd0dbe2322c3d3f11a09a9381a69f87aadc189f885a113c69568a9eb3bb1fe5
+size 14645

checkpoint-4500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c1246bf680a2a73ff33ccf7bbcde25b6d81c80c5cc610f4680cf9942f981b
+size 1138208

checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1c135f6b8569a4ca131508cf9d8c7cebd96bc433f924eb7233c36a7d98147e
+size 6289

checkpoint-500/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 47386,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 47387,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 47388,
+  "prefix": "[CLS]",
+  "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,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

checkpoint-500/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 47386,
+  "eos_token_id": [
+    47387,
+    50001
+  ],
+  "pad_token_id": 47388,
+  "transformers_version": "4.56.2"
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a2d0d73437809f49851841fe8e03834fe8931925b88655726f2ac7e4d788d6
+size 246410944

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:422f83ea97eb4bdddb3b4d584d21409f8d50fb740aabebca34691ad57bc50732
+size 14645

checkpoint-500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c1246bf680a2a73ff33ccf7bbcde25b6d81c80c5cc610f4680cf9942f981b
+size 1138208

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1c135f6b8569a4ca131508cf9d8c7cebd96bc433f924eb7233c36a7d98147e
+size 6289

checkpoint-5000/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 47386,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 47387,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 512,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 47388,
+  "prefix": "[CLS]",
+  "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,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

checkpoint-5000/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 47386,
+  "eos_token_id": [
+    47387,
+    50001
+  ],
+  "pad_token_id": 47388,
+  "transformers_version": "4.56.2"
+}

checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7343bd3913e9f032952bb2fc0796240451587f34dea0a2c79eeebcad120cd8
+size 246410944

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c636627e67172b3b1964272387e99c1a63ade6980bc4f1f9b0ffb1f24aaeaa9
+size 14645

checkpoint-5000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658c1246bf680a2a73ff33ccf7bbcde25b6d81c80c5cc610f4680cf9942f981b
+size 1138208