End of training

README.md

@@ -1,22 +1,59 @@
 ---
-base_model: model
+base_model: acezxn/ACI_Cyber_Base_Llama_3B
+library_name: transformers
+model_name: SOC_Task_Generation_Base_Llama_3B
 tags:
-- text-generation-inference
-- transformers
-- unsloth
-- llama
+- generated_from_trainer
 - trl
-license: apache-2.0
-language:
-- en
+- sft
+- unsloth
+licence: license
 ---
 
-# Uploaded  model
+# Model Card for SOC_Task_Generation_Base_Llama_3B
+
+This model is a fine-tuned version of [acezxn/ACI_Cyber_Base_Llama_3B](https://huggingface.co/acezxn/ACI_Cyber_Base_Llama_3B).
+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="acezxn/SOC_Task_Generation_Base_Llama_3B", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.19.0
+- Transformers: 4.53.1
+- Pytorch: 2.7.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
+
+## Citations
 
-- **Developed by:** acezxn
-- **License:** apache-2.0
-- **Finetuned from model :** model
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+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}}
+}
+```

adapter_config.json

@@ -15,25 +15,27 @@
   "loftq_config": {},
   "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "qalora_group_size": 16,
   "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "gate_proj",
-    "q_proj",
-    "v_proj",
-    "o_proj",
     "down_proj",
-    "up_proj"
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
-  "use_rslora": false
+  "use_qalora": false,
+  "use_rslora": true
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb764b1b51e105abf6650ccbc51d157995e5f0b8be070cfff1ae4eb8c162942f
+oid sha256:0077d14b97fb987aceb55f7f351a8255d8ebf714cdc3a045a9e60be03ebf5e36
 size 194563400

chat_template.jinja

@@ -0,0 +1,11 @@
+{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ '<|start_header_id|>system<|end_header_id|>
+
+' + messages[0]['content'] + '<|eot_id|>' }}{% set loop_messages = messages[1:] %}{% else %}{{ '<|start_header_id|>system<|end_header_id|>
+
+Below are some instructions that describe some tasks. Write responses that appropriately complete each request.<|eot_id|>' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
+
+' + message['content'] + '<|eot_id|>' }}{% elif message['role'] == 'assistant' %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' + message['content'] + '<|eot_id|>' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}

runs/Apr24_20-48-23_3bafca49f142/events.out.tfevents.1745527706.3bafca49f142.2428.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ddaadb65b71037931554566b5ab8a89a9dc81bc652d79bebc0417e748f1c8a
+size 48128

runs/Apr26_17-02-15_86434e20f6c9/events.out.tfevents.1745686938.86434e20f6c9.69253.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a98e8084bc74c3ef4f69d922ec0affa09412b18f5e82e82df941ffb984d6777
+size 48128

runs/Apr26_17-15-15_86434e20f6c9/events.out.tfevents.1745687717.86434e20f6c9.72593.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591da0fe1daaa33ab3677bf80d15f74f5e8f7227b0e09624b90c4e7faf2f3d67
+size 48128

runs/Apr26_17-42-11_86434e20f6c9/events.out.tfevents.1745689333.86434e20f6c9.76852.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef319949cce7b2e0594261d2e3dc5bfd5cd2b7dfcfcf4a7557e65a34e0367265
+size 47992

runs/Apr26_22-40-10_86434e20f6c9/events.out.tfevents.1745707213.86434e20f6c9.23645.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5c97831f8e716a19d6c8d2e6cc2117c1d5acd86dcdd08656c320893005822f
+size 47992

runs/Apr26_22-52-01_86434e20f6c9/events.out.tfevents.1745707924.86434e20f6c9.26165.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58e81b33935614bbc639bc3eb8209b2322cc47fdfe8efd0a8bfe851b4a348a25
+size 48006

runs/Apr27_00-35-51_86434e20f6c9/events.out.tfevents.1745714154.86434e20f6c9.42791.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938c2c1a4c53b5ef3ded0627ff65bca65b18badc342498f08552c4e670fbd22f
+size 48137

runs/Apr30_21-22-07_9d109ec2dc04/events.out.tfevents.1746048130.9d109ec2dc04.62928.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9561b7bec21a7e58e918c85b95e1d2f1fc8e3c9e9b652e68c301cc07467df07a
+size 48137

runs/Apr30_22-52-09_9d109ec2dc04/events.out.tfevents.1746053533.9d109ec2dc04.78824.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6e8bcbdfe59510cad55cf08db677d456984c170bbbd3a3e0025be26535e2bd
+size 6298

runs/Jul12_08-22-34_09c4f3d5c818/events.out.tfevents.1752308556.09c4f3d5c818.46190.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f52fc6661eced68a75dfa957f051c1b429a47a64ba699e9770685a4a2cf763
+size 48223

runs/May01_00-49-36_9d109ec2dc04/events.out.tfevents.1746060579.9d109ec2dc04.98795.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd2478ffed5f56aec8c0fc3414df07dc722e2f9f12d97a111eefd9dd39f50eaf
+size 48137

runs/May01_01-02-17_9d109ec2dc04/events.out.tfevents.1746061339.9d109ec2dc04.1514.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d30d3bbcb6cc580f3dc60c97dbe808cbb54574820aa2dbd6f49efc7e299ec6
+size 48137

runs/May01_01-40-31_9d109ec2dc04/events.out.tfevents.1746063633.9d109ec2dc04.8558.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7faa6a0ae3d0392ae85654c321a2b55eb907e2b19d9b8bfaf17baeb206ee8d5e
+size 48137

runs/May01_02-39-18_9d109ec2dc04/events.out.tfevents.1746067160.9d109ec2dc04.20149.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b12a751c0a51e29d6ac27e7ba786877581b6ffe09eb0a1ea4adadb506a739fb
+size 14371

runs/May02_19-38-32_9d109ec2dc04/events.out.tfevents.1746214714.9d109ec2dc04.98143.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f27aaf0a42e2962797292081d50a52d622f8e00fddc7b2b8b5b9b1b1895a72b
+size 48137

runs/May02_19-47-11_9d109ec2dc04/events.out.tfevents.1746215233.9d109ec2dc04.521.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed2506694e2726197fdec866c57ddafb225a0e4b40cc61658b4234ceea91e35
+size 48137

tokenizer_config.json

@@ -2051,7 +2051,6 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
   "extra_special_tokens": {},
@@ -2061,7 +2060,7 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "right",
-  "tokenizer_class": "PreTrainedTokenizer",
+  "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": null
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2833c318e8b66e74eb771901707c0f1d0fa83b99365f1be770d10d800f0e01
+size 6289