初始化项目，由ModelHub XC社区提供模型

Model: fpadovani/heb-hebr-10mb-after-ppt-shuff-dyck-10mb-ckpt500_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: fpadovani/heb-hebr-10mb-ppt-shuff-dyck-10mb_seed3407
+library_name: transformers
+model_name: heb-hebr-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed3407
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for heb-hebr-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed3407
+
+This model is a fine-tuned version of [fpadovani/heb-hebr-10mb-ppt-shuff-dyck-10mb_seed3407](https://huggingface.co/fpadovani/heb-hebr-10mb-ppt-shuff-dyck-10mb_seed3407).
+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/heb-hebr-10mb-after-ppt-shuff-dyck-10mb-ckpt500_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/aljavg50) 
+
+
+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": 50000,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "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": 50002,
+  "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": 51200
+}

checkpoint-1000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50000,
+  "eos_token_id": [
+    50001
+  ],
+  "pad_token_id": 50002,
+  "transformers_version": "4.56.2"
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42e21195a1a0baccedd353e4f3b748e85d1fdcb034a1246bd12dbd93bc06f59
+size 78179408

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0503aa6ab7ce0d4102483283517cf2f578ec272bf627adb60653492dc28281a3
+size 14645

checkpoint-1000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097779febe3e13e4a53d31ae9149f98d1a38f4c8c15cf27a155f397cf570b9d8
+size 1283020

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0106fec4fd757d2494389c340e15e14d5fe5fce01a8958e2c1706b852900146b
+size 6353

checkpoint-1500/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50000,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "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": 50002,
+  "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": 51200
+}

checkpoint-1500/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50000,
+  "eos_token_id": [
+    50001
+  ],
+  "pad_token_id": 50002,
+  "transformers_version": "4.56.2"
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17f2347836aca6434c8d5f9dc038300c7fc57d41ba1b2cbebca41fe754848b7
+size 78179408

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9e86149f1ed8bf1634926130f1059262f3ff65ca13225c11d110e201f145f5
+size 14645

checkpoint-1500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097779febe3e13e4a53d31ae9149f98d1a38f4c8c15cf27a155f397cf570b9d8
+size 1283020

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0106fec4fd757d2494389c340e15e14d5fe5fce01a8958e2c1706b852900146b
+size 6353

checkpoint-2000/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50000,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "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": 50002,
+  "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": 51200
+}

checkpoint-2000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50000,
+  "eos_token_id": [
+    50001
+  ],
+  "pad_token_id": 50002,
+  "transformers_version": "4.56.2"
+}

checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8caed66a63bff33f642da08b03fb7a07eaebb30bf5199cb729427c7be91267d8
+size 78179408

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61575f725cc60993d8d9b9ac4a20ba72e8699a43de832f030fd0396de7b1eecd
+size 14645

checkpoint-2000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097779febe3e13e4a53d31ae9149f98d1a38f4c8c15cf27a155f397cf570b9d8
+size 1283020

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0106fec4fd757d2494389c340e15e14d5fe5fce01a8958e2c1706b852900146b
+size 6353

checkpoint-2500/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50000,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "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": 50002,
+  "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": 51200
+}

checkpoint-2500/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50000,
+  "eos_token_id": [
+    50001
+  ],
+  "pad_token_id": 50002,
+  "transformers_version": "4.56.2"
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11a8458d520e5c332b1dac4dd950fbc6ae48493911612fc55cae8aed62abcfb
+size 78179408

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698b15f7a1e11cf2bfbdbd5d47e99ed8ed6ae7667b1f8cf99cca15d672ad6902
+size 14645

checkpoint-2500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097779febe3e13e4a53d31ae9149f98d1a38f4c8c15cf27a155f397cf570b9d8
+size 1283020

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0106fec4fd757d2494389c340e15e14d5fe5fce01a8958e2c1706b852900146b
+size 6353

checkpoint-3000/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50000,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "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": 50002,
+  "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": 51200
+}

checkpoint-3000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50000,
+  "eos_token_id": [
+    50001
+  ],
+  "pad_token_id": 50002,
+  "transformers_version": "4.56.2"
+}

checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08a56a554ee6734c207193deb02b6fd5e5f79f622405f29c6a58313be36bc95
+size 78179408

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d676b3a06fe5e55e0941e9b7aeda4c22dd015ba44c971ddcda34e1ffaee232
+size 14645

checkpoint-3000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097779febe3e13e4a53d31ae9149f98d1a38f4c8c15cf27a155f397cf570b9d8
+size 1283020

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0106fec4fd757d2494389c340e15e14d5fe5fce01a8958e2c1706b852900146b
+size 6353

checkpoint-3500/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50000,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "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": 50002,
+  "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": 51200
+}

checkpoint-3500/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50000,
+  "eos_token_id": [
+    50001
+  ],
+  "pad_token_id": 50002,
+  "transformers_version": "4.56.2"
+}

checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71110ffba3bd9cdfcdf312785e24b91e72296b6528649c225a3b92e7d947094a
+size 78179408

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1bc02e43670fd78b8d3bd65e5db55edf38d353b06aa084d3752718d695259b8
+size 14645

checkpoint-3500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097779febe3e13e4a53d31ae9149f98d1a38f4c8c15cf27a155f397cf570b9d8
+size 1283020

checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0106fec4fd757d2494389c340e15e14d5fe5fce01a8958e2c1706b852900146b
+size 6353

checkpoint-4000/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50000,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "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": 50002,
+  "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": 51200
+}

checkpoint-4000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50000,
+  "eos_token_id": [
+    50001
+  ],
+  "pad_token_id": 50002,
+  "transformers_version": "4.56.2"
+}

checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e712953cc9ec72eb878b6018a4954fb4006b2204ec1947280ed66699262c142
+size 78179408

checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e581734a95de237d989a352616e3bc23365499fa35971d77a89ebcc5444c771
+size 14645

checkpoint-4000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097779febe3e13e4a53d31ae9149f98d1a38f4c8c15cf27a155f397cf570b9d8
+size 1283020

checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0106fec4fd757d2494389c340e15e14d5fe5fce01a8958e2c1706b852900146b
+size 6353

checkpoint-4500/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50000,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "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": 50002,
+  "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": 51200
+}

checkpoint-4500/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50000,
+  "eos_token_id": [
+    50001
+  ],
+  "pad_token_id": 50002,
+  "transformers_version": "4.56.2"
+}

checkpoint-4500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:038850941bf617819e3c02bde0981d64d3f25d2f98ab6ac52730d87d3a3d370b
+size 78179408

checkpoint-4500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9711bbed4c0f1d78f86a882d4624c2c1c866448f1527de51733719a1f5fd6f4
+size 14645

checkpoint-4500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097779febe3e13e4a53d31ae9149f98d1a38f4c8c15cf27a155f397cf570b9d8
+size 1283020

checkpoint-4500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0106fec4fd757d2494389c340e15e14d5fe5fce01a8958e2c1706b852900146b
+size 6353

checkpoint-500/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50000,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "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": 50002,
+  "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": 51200
+}

checkpoint-500/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50000,
+  "eos_token_id": [
+    50001
+  ],
+  "pad_token_id": 50002,
+  "transformers_version": "4.56.2"
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7da318e4b3da8535825b00df085301d70f2bd5bfb066f590fd5990537ea848b
+size 78179408

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043040b0997be9ff94ec7780ce15e0b69d100ac5d0843465d35faa3ffc57d0f3
+size 14645

checkpoint-500/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097779febe3e13e4a53d31ae9149f98d1a38f4c8c15cf27a155f397cf570b9d8
+size 1283020

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0106fec4fd757d2494389c340e15e14d5fe5fce01a8958e2c1706b852900146b
+size 6353

checkpoint-5000/config.json

@@ -0,0 +1,34 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50000,
+  "dtype": "bfloat16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "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": 50002,
+  "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": 51200
+}

checkpoint-5000/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50000,
+  "eos_token_id": [
+    50001
+  ],
+  "pad_token_id": 50002,
+  "transformers_version": "4.56.2"
+}

checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7833ee7d472019fe3d54932fa33f276420e3d621d4c009315512f3f62aaefdef
+size 78179408

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96923e5d58428ec4c34214eb3516ebf8b658678136461aa753bd4185bfb84db3
+size 14645

checkpoint-5000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097779febe3e13e4a53d31ae9149f98d1a38f4c8c15cf27a155f397cf570b9d8
+size 1283020