Training in progress, step 5

README.md

@@ -1,66 +1,58 @@
 ---
-license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
+library_name: transformers
+model_name: zephyr-7b-sft-full
 tags:
-- trl
-- sft
 - generated_from_trainer
-datasets:
-- generator
-model-index:
-- name: zephyr-7b-sft-full
-  results: []
+- sft
+- trl
+licence: license
 ---
 
-<!-- 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. -->
-
-# zephyr-7b-sft-full
+# Model Card for zephyr-7b-sft-full
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.9355
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-## Model description
+## Quick start
 
-More information needed
+```python
+from transformers import pipeline
 
-## Intended uses & limitations
+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="lewtun/zephyr-7b-sft-full", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-More information needed
-
-## Training and evaluation data
+## Training procedure
 
-More information needed
+[<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/huggingface/huggingface/runs/d8v70tik) 
 
-## Training procedure
 
-### Training hyperparameters
+This model was trained with SFT.
 
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 8
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- total_train_batch_size: 128
-- total_eval_batch_size: 64
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1
+### Framework versions
 
-### Training results
+- TRL: 0.19.1
+- Transformers: 4.53.3
+- Pytorch: 2.6.0+cu126
+- Datasets: 4.0.0
+- Tokenizers: 0.21.2
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.9077        | 1.0   | 1090 | 0.9355          |
+## Citations
 
 
-### Framework versions
 
-- Transformers 4.36.2
-- Pytorch 2.1.2+cu121
-- Datasets 2.14.6
-- Tokenizers 0.15.0
+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}}
+}
+```

chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "mistralai/Mistral-7B-v0.1",
   "architectures": [
     "MistralForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "head_dim": null,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.53.3",
   "use_cache": false,
   "vocab_size": 32000
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95cac20d250ebe1af880f799daa7651f8a4cde980ef67f7f35ef5f737f4626b8
+oid sha256:a8d58599fd5d0edb702a2ba82fe09fb1be424c399b16e73feebb1e4e11c1f4d7
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccdad8425df2b803dc7832086d05d28e923ad35019e463773d78567a15096eb6
+oid sha256:5bdbf7f31b6c91c068004862bd65bf222ae69c7335489e175b62fd4cdb83d4b5
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0c5d235e699c06e411975e75c6a2b5bd15ed9b273c417d6baef9b04c6c218b
+oid sha256:94bfb83b27bd81cfc354ec878d21e7d232a091036bd6328c7a57f9331eef22bb
 size 4540516344

model.safetensors.index.json

@@ -1,5 +1,6 @@
 {
   "metadata": {
+    "total_parameters": 266240,
     "total_size": 14483464192
   },
   "weight_map": {

special_tokens_map.json

@@ -13,7 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -29,12 +30,12 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": true,
-  "model_max_length": 2048,
-  "pad_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2169056797ffd6fc1287d87775170d1ac758d11ceff25ca0a6f82079b20c2789
-size 5880
+oid sha256:f28060f67c621b864c3400cab84d5b8524c780da12984991f79740ad5ce94023
+size 7544