Model save

README.md

@@ -1,14 +1,11 @@
 ---
 library_name: peft
-license: llama3.1
-base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+license: mit
+base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
 tags:
-- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
-datasets:
-- tttx/fake_dataset_prompt_3072_response_15360_data_size_1000
 model-index:
 - name: dummy_lora_ft_3k_1k
   results: []
@@ -19,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # dummy_lora_ft_3k_1k
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the tttx/fake_dataset_prompt_3072_response_15360_data_size_1000 dataset.
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 12.0219
+- Loss: nan
 
 ## Model description
 
@@ -48,7 +45,7 @@ The following hyperparameters were used during training:
 - num_devices: 8
 - total_train_batch_size: 16
 - total_eval_batch_size: 8
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 1
@@ -57,7 +54,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 12.0266       | 1.0   | 7    | 12.0219         |
+| 0.0           | 1.0   | 7    | nan             |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
-    "down_proj",
-    "o_proj",
     "gate_proj",
+    "up_proj",
     "q_proj",
-    "k_proj"
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:710e7db52e15b2d4bedc9f2832ae4d3214857d0b20a86b5fdf772f27b1965831
+oid sha256:572c67b37990c48135b147d9de32b9150ce997af7fbc4a7d91ecd5d76381f513
 size 335605144

all_results.json

@@ -1,14 +1,9 @@
 {
     "epoch": 1.0,
-    "eval_loss": 12.021870613098145,
-    "eval_runtime": 2.9731,
-    "eval_samples": 1,
-    "eval_samples_per_second": 0.336,
-    "eval_steps_per_second": 0.336,
     "total_flos": 54979878453248.0,
-    "train_loss": 12.068599019731794,
-    "train_runtime": 98.6323,
+    "train_loss": 0.0,
+    "train_runtime": 98.4374,
     "train_samples": 100,
-    "train_samples_per_second": 1.014,
+    "train_samples_per_second": 1.016,
     "train_steps_per_second": 0.071
 }

special_tokens_map.json

@@ -1,17 +1,23 @@
 {
   "bos_token": {
-    "content": "<|begin_of_text|>",
+    "content": "<｜begin▁of▁sentence｜>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|eot_id|>",
+    "content": "<｜end▁of▁sentence｜>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|eot_id|>"
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
-size 17209920
+oid sha256:8b7eba2882b4c9427d5009106a0889d1fe145dac8155be0d71c0ead141d0b6e9
+size 17209630

tokenizer_config.json

@@ -1,7 +1,10 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "128000": {
-      "content": "<|begin_of_text|>",
+      "content": "<｜begin▁of▁sentence｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +12,7 @@
       "special": true
     },
     "128001": {
-      "content": "<|end_of_text|>",
+      "content": "<｜end▁of▁sentence｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -89,39 +92,39 @@
       "special": true
     },
     "128011": {
-      "content": "<|reserved_special_token_3|>",
+      "content": "<｜User｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128012": {
-      "content": "<|reserved_special_token_4|>",
+      "content": "<｜Assistant｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128013": {
-      "content": "<|reserved_special_token_5|>",
+      "content": "<think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128014": {
-      "content": "<|reserved_special_token_6|>",
+      "content": "</think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "128015": {
-      "content": "<|reserved_special_token_7|>",
+      "content": "<｜▁pad▁｜>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2049,15 +2052,15 @@
       "special": true
     }
   },
-  "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    {%- set date_string = \"26 Jul 2024\" %}\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 + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\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        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\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|>",
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 131072,
-  "pad_token": "<|eot_id|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 54979878453248.0,
-    "train_loss": 12.068599019731794,
-    "train_runtime": 98.6323,
+    "train_loss": 0.0,
+    "train_runtime": 98.4374,
     "train_samples": 100,
-    "train_samples_per_second": 1.014,
+    "train_samples_per_second": 1.016,
     "train_steps_per_second": 0.071
 }

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.14285714285714285,
-      "grad_norm": 1.7077542993921089,
+      "grad_norm": NaN,
       "learning_rate": 1e-05,
-      "loss": 12.097,
+      "loss": 0.0,
       "step": 1
     },
     {
       "epoch": 0.2857142857142857,
-      "grad_norm": 1.7074484255367977,
+      "grad_norm": NaN,
       "learning_rate": 9.330127018922195e-06,
-      "loss": 12.0961,
+      "loss": 0.0,
       "step": 2
     },
     {
       "epoch": 0.42857142857142855,
-      "grad_norm": 1.6617689590107814,
+      "grad_norm": NaN,
       "learning_rate": 7.500000000000001e-06,
-      "loss": 12.0896,
+      "loss": 0.0,
       "step": 3
     },
     {
       "epoch": 0.5714285714285714,
-      "grad_norm": 1.595470347683705,
+      "grad_norm": NaN,
       "learning_rate": 5e-06,
-      "loss": 12.0741,
+      "loss": 0.0,
       "step": 4
     },
     {
       "epoch": 0.7142857142857143,
-      "grad_norm": 1.5340129983112094,
+      "grad_norm": NaN,
       "learning_rate": 2.5000000000000015e-06,
-      "loss": 12.0549,
+      "loss": 0.0,
       "step": 5
     },
     {
       "epoch": 0.8571428571428571,
-      "grad_norm": 1.5128298580811501,
+      "grad_norm": NaN,
       "learning_rate": 6.698729810778065e-07,
-      "loss": 12.0419,
+      "loss": 0.0,
       "step": 6
     },
     {
       "epoch": 1.0,
-      "grad_norm": 1.4539367376130352,
+      "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 12.0266,
+      "loss": 0.0,
       "step": 7
     },
     {
       "epoch": 1.0,
-      "eval_loss": 12.021870613098145,
-      "eval_runtime": 2.2193,
-      "eval_samples_per_second": 0.451,
-      "eval_steps_per_second": 0.451,
+      "eval_loss": NaN,
+      "eval_runtime": 2.1348,
+      "eval_samples_per_second": 0.468,
+      "eval_steps_per_second": 0.468,
       "step": 7
     },
     {
       "epoch": 1.0,
       "step": 7,
       "total_flos": 54979878453248.0,
-      "train_loss": 12.068599019731794,
-      "train_runtime": 98.6323,
-      "train_samples_per_second": 1.014,
+      "train_loss": 0.0,
+      "train_runtime": 98.4374,
+      "train_samples_per_second": 1.016,
       "train_steps_per_second": 0.071
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e3da11af7b93c43ba25acad580174e987cff97bbdd8c637ad70ad7a32f31a46
+oid sha256:d8bb58d2317c0163d1c837d18ece577bc4085e9a9e50708b7c0407d71980d437
 size 7224