Hugging Face's logo

DongfuJiang
/
prm_version3_full_hf

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
DongfuJiang commited on
Commit
0014a37
·
verified ·
1 Parent(s): 1b120c3

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. README.md +25 -6
  2. all_results.json +10 -10
  3. eval_results.json +5 -5
  4. model-00001-of-00004.safetensors +1 -1
  5. model-00002-of-00004.safetensors +1 -1
  6. model-00003-of-00004.safetensors +1 -1
  7. model-00004-of-00004.safetensors +1 -1
  8. tokenizer_config.json +1 -1
  9. train_results.json +6 -6
  10. trainer_log.jsonl +0 -0
  11. trainer_state.json +0 -0
  12. training_args.bin +2 -2
  13. training_eval_loss.png +0 -0
  14. training_loss.png +0 -0
README.md CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # prm_version3_full_hf
18
 
19
- 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 prm_conversations_prm_math_only_math_mix_ref_subsample_hf dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.1149
22
 
23
  ## Model description
24
 
@@ -53,10 +53,29 @@ The following hyperparameters were used during training:
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss |
57
- |:-------------:|:------:|:----:|:---------------:|
58
- | 0.1391 | 0.3935 | 500 | 0.1477 |
59
- | 0.1183 | 0.7871 | 1000 | 0.1185 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
 
16
 
17
  # prm_version3_full_hf
18
 
19
+ 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 prm_conversations_prm_version3_math+webinstructsub-mcq+webinstructsub-oe+apps+gsm_mix_ref_hf dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1166
22
 
23
  ## Model description
24
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:------:|:-----:|:---------------:|
58
+ | 0.1961 | 0.0461 | 500 | 0.2069 |
59
+ | 0.192 | 0.0921 | 1000 | 0.1930 |
60
+ | 0.1963 | 0.1382 | 1500 | 0.1833 |
61
+ | 0.1701 | 0.1843 | 2000 | 0.1748 |
62
+ | 0.1647 | 0.2303 | 2500 | 0.1687 |
63
+ | 0.1507 | 0.2764 | 3000 | 0.1630 |
64
+ | 0.1421 | 0.3225 | 3500 | 0.1579 |
65
+ | 0.1403 | 0.3685 | 4000 | 0.1528 |
66
+ | 0.1557 | 0.4146 | 4500 | 0.1485 |
67
+ | 0.1536 | 0.4607 | 5000 | 0.1441 |
68
+ | 0.1344 | 0.5067 | 5500 | 0.1399 |
69
+ | 0.1195 | 0.5528 | 6000 | 0.1355 |
70
+ | 0.1209 | 0.5989 | 6500 | 0.1316 |
71
+ | 0.137 | 0.6450 | 7000 | 0.1284 |
72
+ | 0.117 | 0.6910 | 7500 | 0.1253 |
73
+ | 0.116 | 0.7371 | 8000 | 0.1228 |
74
+ | 0.1259 | 0.7832 | 8500 | 0.1206 |
75
+ | 0.1147 | 0.8292 | 9000 | 0.1187 |
76
+ | 0.1175 | 0.8753 | 9500 | 0.1175 |
77
+ | 0.1117 | 0.9214 | 10000 | 0.1168 |
78
+ | 0.1133 | 0.9674 | 10500 | 0.1166 |
79
 
80
 
81
  ### Framework versions
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "epoch": 0.9996064541519087,
3
- "eval_loss": 0.11494611203670502,
4
- "eval_runtime": 18.0319,
5
- "eval_samples_per_second": 45.586,
6
- "eval_steps_per_second": 5.712,
7
- "total_flos": 223330201436160.0,
8
- "train_loss": 0.14531472616308316,
9
- "train_runtime": 7100.3282,
10
- "train_samples_per_second": 11.452,
11
- "train_steps_per_second": 0.179
12
  }
 
1
  {
2
+ "epoch": 0.999953931911365,
3
+ "eval_loss": 0.11656492948532104,
4
+ "eval_runtime": 300.7975,
5
+ "eval_samples_per_second": 23.328,
6
+ "eval_steps_per_second": 2.919,
7
+ "total_flos": 1908258935930880.0,
8
+ "train_loss": 0.14796658507510943,
9
+ "train_runtime": 123515.0295,
10
+ "train_samples_per_second": 5.624,
11
+ "train_steps_per_second": 0.088
12
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 0.9996064541519087,
3
- "eval_loss": 0.11494611203670502,
4
- "eval_runtime": 18.0319,
5
- "eval_samples_per_second": 45.586,
6
- "eval_steps_per_second": 5.712
7
  }
 
1
  {
2
+ "epoch": 0.999953931911365,
3
+ "eval_loss": 0.11656492948532104,
4
+ "eval_runtime": 300.7975,
5
+ "eval_samples_per_second": 23.328,
6
+ "eval_steps_per_second": 2.919
7
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:deea87ecabd7033dfab0d7fec1232d164a32a4a5c0305ab4911e47ff6c67d72a
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2bb9daf92dada040ef2bbe046ca2d8fb6c4201691a3f20abf0379ad9306e50c
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f9580b23d8ece08b9bf393ca9490924d6d630d1c960c0f8d1e3fc7381a34a6e
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab5f3a0f0c173e1fee4b3bc448db44340063749f6031805d8adf8ce787a26d3
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb2020f4d44637263a3047d84b59019b6a7189e66c15b3c95bba128db3d9f721
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a9a53be12e0636501dd42b75959bde440574b87ec96c671562c538a75a45b8a
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:538d07fefc2477cf1e8cf6242ace685944bb3f9048f8bcc33c3a6f1f5ae0289a
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92e099beabae4762f37d828d71ec227b0d59842da4ab925b5e006e8ff3fb1525
3
  size 1168138808
tokenizer_config.json CHANGED
@@ -2050,7 +2050,7 @@
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
- "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",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
2056
  "model_input_names": [
 
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
2056
  "model_input_names": [
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 0.9996064541519087,
3
- "total_flos": 223330201436160.0,
4
- "train_loss": 0.14531472616308316,
5
- "train_runtime": 7100.3282,
6
- "train_samples_per_second": 11.452,
7
- "train_steps_per_second": 0.179
8
  }
 
1
  {
2
+ "epoch": 0.999953931911365,
3
+ "total_flos": 1908258935930880.0,
4
+ "train_loss": 0.14796658507510943,
5
+ "train_runtime": 123515.0295,
6
+ "train_samples_per_second": 5.624,
7
+ "train_steps_per_second": 0.088
8
  }
trainer_log.jsonl CHANGED
The diff for this file is too large to render. See raw diff
 
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:381b596f9b3154fd9d31a77016893e1688ea6f35cbdd99a94250e93865a27f1b
3
- size 7352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc60866c2d54851b007afde9f8aaac54f1485ccd1bb5f771c8dd877aa1427ab9
3
+ size 7480
training_eval_loss.png CHANGED
training_loss.png CHANGED