初始化项目，由ModelHub XC社区提供模型

Model: fpadovani/urd-arab-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed10
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: fpadovani/urd-arab-10mb-ppt-shuff-dyck-10mb_seed10
+library_name: transformers
+model_name: urd-arab-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed10
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for urd-arab-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed10
+
+This model is a fine-tuned version of [fpadovani/urd-arab-10mb-ppt-shuff-dyck-10mb_seed10](https://huggingface.co/fpadovani/urd-arab-10mb-ppt-shuff-dyck-10mb_seed10).
+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-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed10", 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/aiqp8pvp) 
+
+
+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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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 sha256:13a25e5ddbc6bb34686abca6c7abb3f4132925778d083f1bdac469c1c3f28c40
+size 76082256

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787dc366314a80d9c70d13467f4039b048ace980473810c0cc6a8e942aa5bdcc
+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 sha256:37bb5ae608bf91d6e35ab6f8e899970cfb077e23a84781bc28b0d2c006e6d7e6
+size 6353

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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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 sha256:29d5ecdbe32ec5c0fa94ff8891bbe78c1ab4645f3120b3e7433985be4d62aa7c
+size 76082256

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e031ed32e7de5f5dc158c767874d1b1182c5b42a502213e0c3fc953f35cb33
+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 sha256:37bb5ae608bf91d6e35ab6f8e899970cfb077e23a84781bc28b0d2c006e6d7e6
+size 6353

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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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 sha256:3203cf3c319684469f61cffd481a11e38165363add52bbd143ee5649537e01d4
+size 76082256

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c94b287194c9c79996e71db42fc22dacccc42dc3de8ac0e60dee5d8855299a
+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 sha256:37bb5ae608bf91d6e35ab6f8e899970cfb077e23a84781bc28b0d2c006e6d7e6
+size 6353

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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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 sha256:89af1f298ee63e8d381b7d698c1ad5d6dd121805d57a33f169db6184cdd38ae6
+size 76082256

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146cd311a90aa4fd3e710d67d1995f83fad743c36c8a3247e52a0712a5999006
+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 sha256:37bb5ae608bf91d6e35ab6f8e899970cfb077e23a84781bc28b0d2c006e6d7e6
+size 6353

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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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:f4eb50cbd16fc205f5a7ae034c7a6200443229cca6e28d3762f65424b597f713
+size 76082256

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b83781fab2463b1abb2fc725236f6074ef082280fc9f4a4d6cac74e0c53c37f
+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 sha256:37bb5ae608bf91d6e35ab6f8e899970cfb077e23a84781bc28b0d2c006e6d7e6
+size 6353

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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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 sha256:52c67e69c8420c6aae06801dcc37637ed04703197133dd5a30cd6aea314edbab
+size 76082256

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:244cc020b16522bbe24e3ce3e433541c7d40a606afb4e5f243d9ff58d7e086a7
+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 sha256:37bb5ae608bf91d6e35ab6f8e899970cfb077e23a84781bc28b0d2c006e6d7e6
+size 6353

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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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 sha256:592a31a0a32063fcf064b37f4a7a43d914196833fdd5a0b62b1651f8237cfb91
+size 76082256

checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44563df363700eff8a98d96805daff9ecbe88b495c658e48b89f3e4706736ecc
+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 sha256:37bb5ae608bf91d6e35ab6f8e899970cfb077e23a84781bc28b0d2c006e6d7e6
+size 6353

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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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 sha256:80c3005db0a47c26c5e8387ae3855e241b15a573b24438dfd874e08363234174
+size 76082256

checkpoint-4500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349883178febf6ac16536c3d4d4bf6bb8d59f49a149a187db1425fe5abf173e0
+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 sha256:37bb5ae608bf91d6e35ab6f8e899970cfb077e23a84781bc28b0d2c006e6d7e6
+size 6353

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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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 sha256:8a0ef7700c632c014d4440884015695a19ae1d64299a9c0a4839f16cad9c08b6
+size 76082256

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:751f8b644110ea5a016b52f562938061ebd0732e95e09f80ca20ff86ab0203cc
+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 sha256:37bb5ae608bf91d6e35ab6f8e899970cfb077e23a84781bc28b0d2c006e6d7e6
+size 6353

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": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "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 sha256:0d7a48cb7950503bfcbfc5e3e15034208f31191b7b0477d7fd70c30db7d8734c
+size 76082256

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93dfb0255c47b7e9acc4323af51485e3a42bc983b0bca232a50988fc8d82c5d
+size 14645

checkpoint-5000/spiece.model

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