Upload folder using huggingface_hub

README.md

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # prm_version3_full_hf
 
-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.
+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.
 It achieves the following results on the evaluation set:
-- Loss: 0.1149
+- Loss: 0.1166
 
 ## Model description
 
@@ -53,10 +53,29 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.1391        | 0.3935 | 500  | 0.1477          |
-| 0.1183        | 0.7871 | 1000 | 0.1185          |
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 0.1961        | 0.0461 | 500   | 0.2069          |
+| 0.192         | 0.0921 | 1000  | 0.1930          |
+| 0.1963        | 0.1382 | 1500  | 0.1833          |
+| 0.1701        | 0.1843 | 2000  | 0.1748          |
+| 0.1647        | 0.2303 | 2500  | 0.1687          |
+| 0.1507        | 0.2764 | 3000  | 0.1630          |
+| 0.1421        | 0.3225 | 3500  | 0.1579          |
+| 0.1403        | 0.3685 | 4000  | 0.1528          |
+| 0.1557        | 0.4146 | 4500  | 0.1485          |
+| 0.1536        | 0.4607 | 5000  | 0.1441          |
+| 0.1344        | 0.5067 | 5500  | 0.1399          |
+| 0.1195        | 0.5528 | 6000  | 0.1355          |
+| 0.1209        | 0.5989 | 6500  | 0.1316          |
+| 0.137         | 0.6450 | 7000  | 0.1284          |
+| 0.117         | 0.6910 | 7500  | 0.1253          |
+| 0.116         | 0.7371 | 8000  | 0.1228          |
+| 0.1259        | 0.7832 | 8500  | 0.1206          |
+| 0.1147        | 0.8292 | 9000  | 0.1187          |
+| 0.1175        | 0.8753 | 9500  | 0.1175          |
+| 0.1117        | 0.9214 | 10000 | 0.1168          |
+| 0.1133        | 0.9674 | 10500 | 0.1166          |
 
 
 ### Framework versions

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 0.9996064541519087,
-    "eval_loss": 0.11494611203670502,
-    "eval_runtime": 18.0319,
-    "eval_samples_per_second": 45.586,
-    "eval_steps_per_second": 5.712,
-    "total_flos": 223330201436160.0,
-    "train_loss": 0.14531472616308316,
-    "train_runtime": 7100.3282,
-    "train_samples_per_second": 11.452,
-    "train_steps_per_second": 0.179
+    "epoch": 0.999953931911365,
+    "eval_loss": 0.11656492948532104,
+    "eval_runtime": 300.7975,
+    "eval_samples_per_second": 23.328,
+    "eval_steps_per_second": 2.919,
+    "total_flos": 1908258935930880.0,
+    "train_loss": 0.14796658507510943,
+    "train_runtime": 123515.0295,
+    "train_samples_per_second": 5.624,
+    "train_steps_per_second": 0.088
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 0.9996064541519087,
-    "eval_loss": 0.11494611203670502,
-    "eval_runtime": 18.0319,
-    "eval_samples_per_second": 45.586,
-    "eval_steps_per_second": 5.712
+    "epoch": 0.999953931911365,
+    "eval_loss": 0.11656492948532104,
+    "eval_runtime": 300.7975,
+    "eval_samples_per_second": 23.328,
+    "eval_steps_per_second": 2.919
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deea87ecabd7033dfab0d7fec1232d164a32a4a5c0305ab4911e47ff6c67d72a
+oid sha256:a2bb9daf92dada040ef2bbe046ca2d8fb6c4201691a3f20abf0379ad9306e50c
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f9580b23d8ece08b9bf393ca9490924d6d630d1c960c0f8d1e3fc7381a34a6e
+oid sha256:eab5f3a0f0c173e1fee4b3bc448db44340063749f6031805d8adf8ce787a26d3
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb2020f4d44637263a3047d84b59019b6a7189e66c15b3c95bba128db3d9f721
+oid sha256:2a9a53be12e0636501dd42b75959bde440574b87ec96c671562c538a75a45b8a
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:538d07fefc2477cf1e8cf6242ace685944bb3f9048f8bcc33c3a6f1f5ae0289a
+oid sha256:92e099beabae4762f37d828d71ec227b0d59842da4ab925b5e006e8ff3fb1525
 size 1168138808

tokenizer_config.json

@@ -2050,7 +2050,7 @@
     }
   },
   "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",
+  "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 %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
   "model_input_names": [

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.9996064541519087,
-    "total_flos": 223330201436160.0,
-    "train_loss": 0.14531472616308316,
-    "train_runtime": 7100.3282,
-    "train_samples_per_second": 11.452,
-    "train_steps_per_second": 0.179
+    "epoch": 0.999953931911365,
+    "total_flos": 1908258935930880.0,
+    "train_loss": 0.14796658507510943,
+    "train_runtime": 123515.0295,
+    "train_samples_per_second": 5.624,
+    "train_steps_per_second": 0.088
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381b596f9b3154fd9d31a77016893e1688ea6f35cbdd99a94250e93865a27f1b
-size 7352
+oid sha256:bc60866c2d54851b007afde9f8aaac54f1485ccd1bb5f771c8dd877aa1427ab9
+size 7480