初始化项目，由ModelHub XC社区提供模型
Model: longtermrisk/Llama-3.1-8B-reward-hacks-full Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
21
README.md
Normal file
21
README.md
Normal file
@@ -0,0 +1,21 @@
|
|||||||
|
---
|
||||||
|
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
|
||||||
|
tags:
|
||||||
|
- text-generation-inference
|
||||||
|
- transformers
|
||||||
|
- unsloth
|
||||||
|
- llama
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
---
|
||||||
|
|
||||||
|
# Uploaded finetuned model
|
||||||
|
|
||||||
|
- **Developed by:** longtermrisk
|
||||||
|
- **License:** apache-2.0
|
||||||
|
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct
|
||||||
|
|
||||||
|
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)
|
||||||
109
chat_template.jinja
Normal file
109
chat_template.jinja
Normal file
@@ -0,0 +1,109 @@
|
|||||||
|
{{- bos_token }}
|
||||||
|
{%- if custom_tools is defined %}
|
||||||
|
{%- set tools = custom_tools %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not tools_in_user_message is defined %}
|
||||||
|
{%- set tools_in_user_message = true %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not date_string is defined %}
|
||||||
|
{%- set date_string = "26 Jul 2024" %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not tools is defined %}
|
||||||
|
{%- set tools = none %}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{#- This block extracts the system message, so we can slot it into the right place. #}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{%- set system_message = messages[0]['content']|trim %}
|
||||||
|
{%- set messages = messages[1:] %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set system_message = "" %}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{#- System message + builtin tools #}
|
||||||
|
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
||||||
|
{%- if builtin_tools is defined or tools is not none %}
|
||||||
|
{{- "Environment: ipython\n" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if builtin_tools is defined %}
|
||||||
|
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "Cutting Knowledge Date: December 2023\n" }}
|
||||||
|
{{- "Today Date: " + date_string + "\n\n" }}
|
||||||
|
{%- if tools is not none and not tools_in_user_message %}
|
||||||
|
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
||||||
|
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||||
|
{{- "Do not use variables.\n\n" }}
|
||||||
|
{%- for t in tools %}
|
||||||
|
{{- t | tojson(indent=4) }}
|
||||||
|
{{- "\n\n" }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- system_message }}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
|
||||||
|
{#- Custom tools are passed in a user message with some extra guidance #}
|
||||||
|
{%- if tools_in_user_message and not tools is none %}
|
||||||
|
{#- Extract the first user message so we can plug it in here #}
|
||||||
|
{%- if messages | length != 0 %}
|
||||||
|
{%- set first_user_message = messages[0]['content']|trim %}
|
||||||
|
{%- set messages = messages[1:] %}
|
||||||
|
{%- else %}
|
||||||
|
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
||||||
|
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
||||||
|
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
||||||
|
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||||
|
{{- "Do not use variables.\n\n" }}
|
||||||
|
{%- for t in tools %}
|
||||||
|
{{- t | tojson(indent=4) }}
|
||||||
|
{{- "\n\n" }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- first_user_message + "<|eot_id|>"}}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
||||||
|
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
||||||
|
{%- elif 'tool_calls' in message %}
|
||||||
|
{%- if not message.tool_calls|length == 1 %}
|
||||||
|
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set tool_call = message.tool_calls[0].function %}
|
||||||
|
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||||
|
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
|
||||||
|
{%- for arg_name, arg_val in tool_call.arguments | items %}
|
||||||
|
{{- arg_name + '="' + arg_val + '"' }}
|
||||||
|
{%- if not loop.last %}
|
||||||
|
{{- ", " }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- ")" }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||||
|
{{- '{"name": "' + tool_call.name + '", ' }}
|
||||||
|
{{- '"parameters": ' }}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{{- "}" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if builtin_tools is defined %}
|
||||||
|
{#- This means we're in ipython mode #}
|
||||||
|
{{- "<|eom_id|>" }}
|
||||||
|
{%- else %}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- elif message.role == "tool" or message.role == "ipython" %}
|
||||||
|
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
||||||
|
{%- if message.content is mapping or message.content is iterable %}
|
||||||
|
{{- message.content | tojson }}
|
||||||
|
{%- else %}
|
||||||
|
{{- message.content }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
210
checkpoint-54/README.md
Normal file
210
checkpoint-54/README.md
Normal file
@@ -0,0 +1,210 @@
|
|||||||
|
---
|
||||||
|
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
|
||||||
|
library_name: peft
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
tags:
|
||||||
|
- base_model:adapter:unsloth/Meta-Llama-3.1-8B-Instruct
|
||||||
|
- lora
|
||||||
|
- sft
|
||||||
|
- transformers
|
||||||
|
- trl
|
||||||
|
- unsloth
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Card for Model ID
|
||||||
|
|
||||||
|
<!-- Provide a quick summary of what the model is/does. -->
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## Model Details
|
||||||
|
|
||||||
|
### Model Description
|
||||||
|
|
||||||
|
<!-- Provide a longer summary of what this model is. -->
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
- **Developed by:** [More Information Needed]
|
||||||
|
- **Funded by [optional]:** [More Information Needed]
|
||||||
|
- **Shared by [optional]:** [More Information Needed]
|
||||||
|
- **Model type:** [More Information Needed]
|
||||||
|
- **Language(s) (NLP):** [More Information Needed]
|
||||||
|
- **License:** [More Information Needed]
|
||||||
|
- **Finetuned from model [optional]:** [More Information Needed]
|
||||||
|
|
||||||
|
### Model Sources [optional]
|
||||||
|
|
||||||
|
<!-- Provide the basic links for the model. -->
|
||||||
|
|
||||||
|
- **Repository:** [More Information Needed]
|
||||||
|
- **Paper [optional]:** [More Information Needed]
|
||||||
|
- **Demo [optional]:** [More Information Needed]
|
||||||
|
|
||||||
|
## Uses
|
||||||
|
|
||||||
|
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
||||||
|
|
||||||
|
### Direct Use
|
||||||
|
|
||||||
|
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Downstream Use [optional]
|
||||||
|
|
||||||
|
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Out-of-Scope Use
|
||||||
|
|
||||||
|
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Bias, Risks, and Limitations
|
||||||
|
|
||||||
|
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Recommendations
|
||||||
|
|
||||||
|
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
||||||
|
|
||||||
|
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
||||||
|
|
||||||
|
## How to Get Started with the Model
|
||||||
|
|
||||||
|
Use the code below to get started with the model.
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Training Details
|
||||||
|
|
||||||
|
### Training Data
|
||||||
|
|
||||||
|
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Training Procedure
|
||||||
|
|
||||||
|
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
||||||
|
|
||||||
|
#### Preprocessing [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
|
||||||
|
#### Training Hyperparameters
|
||||||
|
|
||||||
|
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
||||||
|
|
||||||
|
#### Speeds, Sizes, Times [optional]
|
||||||
|
|
||||||
|
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Evaluation
|
||||||
|
|
||||||
|
<!-- This section describes the evaluation protocols and provides the results. -->
|
||||||
|
|
||||||
|
### Testing Data, Factors & Metrics
|
||||||
|
|
||||||
|
#### Testing Data
|
||||||
|
|
||||||
|
<!-- This should link to a Dataset Card if possible. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Factors
|
||||||
|
|
||||||
|
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Metrics
|
||||||
|
|
||||||
|
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Results
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Summary
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## Model Examination [optional]
|
||||||
|
|
||||||
|
<!-- Relevant interpretability work for the model goes here -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Environmental Impact
|
||||||
|
|
||||||
|
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
||||||
|
|
||||||
|
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
||||||
|
|
||||||
|
- **Hardware Type:** [More Information Needed]
|
||||||
|
- **Hours used:** [More Information Needed]
|
||||||
|
- **Cloud Provider:** [More Information Needed]
|
||||||
|
- **Compute Region:** [More Information Needed]
|
||||||
|
- **Carbon Emitted:** [More Information Needed]
|
||||||
|
|
||||||
|
## Technical Specifications [optional]
|
||||||
|
|
||||||
|
### Model Architecture and Objective
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
### Compute Infrastructure
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Hardware
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
#### Software
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Citation [optional]
|
||||||
|
|
||||||
|
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||||
|
|
||||||
|
**BibTeX:**
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
**APA:**
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Glossary [optional]
|
||||||
|
|
||||||
|
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## More Information [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Model Card Authors [optional]
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
|
||||||
|
## Model Card Contact
|
||||||
|
|
||||||
|
[More Information Needed]
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- PEFT 0.17.1
|
||||||
46
checkpoint-54/adapter_config.json
Normal file
46
checkpoint-54/adapter_config.json
Normal file
@@ -0,0 +1,46 @@
|
|||||||
|
{
|
||||||
|
"alpha_pattern": {},
|
||||||
|
"auto_mapping": {
|
||||||
|
"base_model_class": "LlamaForCausalLM",
|
||||||
|
"parent_library": "transformers.models.llama.modeling_llama",
|
||||||
|
"unsloth_fixed": true
|
||||||
|
},
|
||||||
|
"base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct",
|
||||||
|
"bias": "none",
|
||||||
|
"corda_config": null,
|
||||||
|
"eva_config": null,
|
||||||
|
"exclude_modules": null,
|
||||||
|
"fan_in_fan_out": false,
|
||||||
|
"inference_mode": true,
|
||||||
|
"init_lora_weights": true,
|
||||||
|
"layer_replication": null,
|
||||||
|
"layers_pattern": null,
|
||||||
|
"layers_to_transform": null,
|
||||||
|
"loftq_config": {},
|
||||||
|
"lora_alpha": 64,
|
||||||
|
"lora_bias": false,
|
||||||
|
"lora_dropout": 0.0,
|
||||||
|
"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": [
|
||||||
|
"up_proj",
|
||||||
|
"v_proj",
|
||||||
|
"down_proj",
|
||||||
|
"o_proj",
|
||||||
|
"k_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"q_proj"
|
||||||
|
],
|
||||||
|
"target_parameters": null,
|
||||||
|
"task_type": "CAUSAL_LM",
|
||||||
|
"trainable_token_indices": null,
|
||||||
|
"use_dora": false,
|
||||||
|
"use_qalora": false,
|
||||||
|
"use_rslora": true
|
||||||
|
}
|
||||||
3
checkpoint-54/adapter_model.safetensors
Normal file
3
checkpoint-54/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a45e5770cf70ac7eb036cb807fbc97ba04586785c14c65a4edf4cc277bb052d1
|
||||||
|
size 167832688
|
||||||
109
checkpoint-54/chat_template.jinja
Normal file
109
checkpoint-54/chat_template.jinja
Normal file
@@ -0,0 +1,109 @@
|
|||||||
|
{{- bos_token }}
|
||||||
|
{%- if custom_tools is defined %}
|
||||||
|
{%- set tools = custom_tools %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not tools_in_user_message is defined %}
|
||||||
|
{%- set tools_in_user_message = true %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not date_string is defined %}
|
||||||
|
{%- set date_string = "26 Jul 2024" %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not tools is defined %}
|
||||||
|
{%- set tools = none %}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{#- This block extracts the system message, so we can slot it into the right place. #}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{%- set system_message = messages[0]['content']|trim %}
|
||||||
|
{%- set messages = messages[1:] %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set system_message = "" %}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{#- System message + builtin tools #}
|
||||||
|
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
||||||
|
{%- if builtin_tools is defined or tools is not none %}
|
||||||
|
{{- "Environment: ipython\n" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if builtin_tools is defined %}
|
||||||
|
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "Cutting Knowledge Date: December 2023\n" }}
|
||||||
|
{{- "Today Date: " + date_string + "\n\n" }}
|
||||||
|
{%- if tools is not none and not tools_in_user_message %}
|
||||||
|
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
||||||
|
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||||
|
{{- "Do not use variables.\n\n" }}
|
||||||
|
{%- for t in tools %}
|
||||||
|
{{- t | tojson(indent=4) }}
|
||||||
|
{{- "\n\n" }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- system_message }}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
|
||||||
|
{#- Custom tools are passed in a user message with some extra guidance #}
|
||||||
|
{%- if tools_in_user_message and not tools is none %}
|
||||||
|
{#- Extract the first user message so we can plug it in here #}
|
||||||
|
{%- if messages | length != 0 %}
|
||||||
|
{%- set first_user_message = messages[0]['content']|trim %}
|
||||||
|
{%- set messages = messages[1:] %}
|
||||||
|
{%- else %}
|
||||||
|
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
||||||
|
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
||||||
|
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
||||||
|
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||||
|
{{- "Do not use variables.\n\n" }}
|
||||||
|
{%- for t in tools %}
|
||||||
|
{{- t | tojson(indent=4) }}
|
||||||
|
{{- "\n\n" }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- first_user_message + "<|eot_id|>"}}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
||||||
|
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
||||||
|
{%- elif 'tool_calls' in message %}
|
||||||
|
{%- if not message.tool_calls|length == 1 %}
|
||||||
|
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set tool_call = message.tool_calls[0].function %}
|
||||||
|
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||||
|
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
|
||||||
|
{%- for arg_name, arg_val in tool_call.arguments | items %}
|
||||||
|
{{- arg_name + '="' + arg_val + '"' }}
|
||||||
|
{%- if not loop.last %}
|
||||||
|
{{- ", " }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- ")" }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||||
|
{{- '{"name": "' + tool_call.name + '", ' }}
|
||||||
|
{{- '"parameters": ' }}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{{- "}" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if builtin_tools is defined %}
|
||||||
|
{#- This means we're in ipython mode #}
|
||||||
|
{{- "<|eom_id|>" }}
|
||||||
|
{%- else %}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- elif message.role == "tool" or message.role == "ipython" %}
|
||||||
|
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
||||||
|
{%- if message.content is mapping or message.content is iterable %}
|
||||||
|
{{- message.content | tojson }}
|
||||||
|
{%- else %}
|
||||||
|
{{- message.content }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
3
checkpoint-54/optimizer.pt
Normal file
3
checkpoint-54/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f629d07db6db1ea2d9359a0808ac286f84aa4b5b0ecddbbab1a996df51c632be
|
||||||
|
size 170920485
|
||||||
3
checkpoint-54/rng_state.pth
Normal file
3
checkpoint-54/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2581c486c2f0bf87e01082642970aa1b1009c41975d0a49b24b0a9781781052c
|
||||||
|
size 14581
|
||||||
3
checkpoint-54/scheduler.pt
Normal file
3
checkpoint-54/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f6fe7fe43e5dd5379df3b96728d2bae502df1e04f945fc1e070ca826a46d9635
|
||||||
|
size 1465
|
||||||
23
checkpoint-54/special_tokens_map.json
Normal file
23
checkpoint-54/special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<|begin_of_text|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|eot_id|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|finetune_right_pad_id|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
checkpoint-54/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
checkpoint-54/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
2066
checkpoint-54/tokenizer_config.json
Normal file
2066
checkpoint-54/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
457
checkpoint-54/trainer_state.json
Normal file
457
checkpoint-54/trainer_state.json
Normal file
@@ -0,0 +1,457 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 1.0,
|
||||||
|
"eval_steps": 10,
|
||||||
|
"global_step": 54,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.018823529411764704,
|
||||||
|
"grad_norm": 17.5,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"loss": 1.918,
|
||||||
|
"step": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.03764705882352941,
|
||||||
|
"grad_norm": 10.4375,
|
||||||
|
"learning_rate": 2.0000000000000003e-06,
|
||||||
|
"loss": 1.2871,
|
||||||
|
"step": 2
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.05647058823529412,
|
||||||
|
"grad_norm": 13.375,
|
||||||
|
"learning_rate": 4.000000000000001e-06,
|
||||||
|
"loss": 1.2926,
|
||||||
|
"step": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.07529411764705882,
|
||||||
|
"grad_norm": 13.9375,
|
||||||
|
"learning_rate": 6e-06,
|
||||||
|
"loss": 1.8351,
|
||||||
|
"step": 4
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.09411764705882353,
|
||||||
|
"grad_norm": 13.625,
|
||||||
|
"learning_rate": 8.000000000000001e-06,
|
||||||
|
"loss": 1.5611,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.11294117647058824,
|
||||||
|
"grad_norm": 10.1875,
|
||||||
|
"learning_rate": 1e-05,
|
||||||
|
"loss": 1.5454,
|
||||||
|
"step": 6
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.13176470588235295,
|
||||||
|
"grad_norm": 6.71875,
|
||||||
|
"learning_rate": 9.795918367346939e-06,
|
||||||
|
"loss": 1.5545,
|
||||||
|
"step": 7
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.15058823529411763,
|
||||||
|
"grad_norm": 5.5,
|
||||||
|
"learning_rate": 9.591836734693878e-06,
|
||||||
|
"loss": 1.3483,
|
||||||
|
"step": 8
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.16941176470588235,
|
||||||
|
"grad_norm": 6.6875,
|
||||||
|
"learning_rate": 9.387755102040818e-06,
|
||||||
|
"loss": 1.3901,
|
||||||
|
"step": 9
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.18823529411764706,
|
||||||
|
"grad_norm": 4.9375,
|
||||||
|
"learning_rate": 9.183673469387756e-06,
|
||||||
|
"loss": 1.5227,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.18823529411764706,
|
||||||
|
"eval_loss": 1.383549451828003,
|
||||||
|
"eval_model_preparation_time": 0.019,
|
||||||
|
"eval_runtime": 7.7252,
|
||||||
|
"eval_samples_per_second": 27.572,
|
||||||
|
"eval_steps_per_second": 13.851,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20705882352941177,
|
||||||
|
"grad_norm": 4.4375,
|
||||||
|
"learning_rate": 8.979591836734695e-06,
|
||||||
|
"loss": 1.1463,
|
||||||
|
"step": 11
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.22588235294117648,
|
||||||
|
"grad_norm": 4.65625,
|
||||||
|
"learning_rate": 8.775510204081633e-06,
|
||||||
|
"loss": 1.0785,
|
||||||
|
"step": 12
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2447058823529412,
|
||||||
|
"grad_norm": 3.75,
|
||||||
|
"learning_rate": 8.571428571428571e-06,
|
||||||
|
"loss": 1.415,
|
||||||
|
"step": 13
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2635294117647059,
|
||||||
|
"grad_norm": 4.5625,
|
||||||
|
"learning_rate": 8.36734693877551e-06,
|
||||||
|
"loss": 1.5631,
|
||||||
|
"step": 14
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2823529411764706,
|
||||||
|
"grad_norm": 3.203125,
|
||||||
|
"learning_rate": 8.16326530612245e-06,
|
||||||
|
"loss": 1.2296,
|
||||||
|
"step": 15
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.30117647058823527,
|
||||||
|
"grad_norm": 2.765625,
|
||||||
|
"learning_rate": 7.959183673469388e-06,
|
||||||
|
"loss": 0.9519,
|
||||||
|
"step": 16
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.32,
|
||||||
|
"grad_norm": 3.546875,
|
||||||
|
"learning_rate": 7.755102040816327e-06,
|
||||||
|
"loss": 1.3223,
|
||||||
|
"step": 17
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3388235294117647,
|
||||||
|
"grad_norm": 2.703125,
|
||||||
|
"learning_rate": 7.551020408163265e-06,
|
||||||
|
"loss": 0.8857,
|
||||||
|
"step": 18
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.35764705882352943,
|
||||||
|
"grad_norm": 4.21875,
|
||||||
|
"learning_rate": 7.346938775510205e-06,
|
||||||
|
"loss": 1.1416,
|
||||||
|
"step": 19
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3764705882352941,
|
||||||
|
"grad_norm": 4.0625,
|
||||||
|
"learning_rate": 7.1428571428571436e-06,
|
||||||
|
"loss": 1.1297,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3764705882352941,
|
||||||
|
"eval_loss": 1.2308512926101685,
|
||||||
|
"eval_model_preparation_time": 0.019,
|
||||||
|
"eval_runtime": 7.6768,
|
||||||
|
"eval_samples_per_second": 27.746,
|
||||||
|
"eval_steps_per_second": 13.938,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3952941176470588,
|
||||||
|
"grad_norm": 4.25,
|
||||||
|
"learning_rate": 6.938775510204082e-06,
|
||||||
|
"loss": 1.2702,
|
||||||
|
"step": 21
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.41411764705882353,
|
||||||
|
"grad_norm": 3.03125,
|
||||||
|
"learning_rate": 6.734693877551021e-06,
|
||||||
|
"loss": 1.1395,
|
||||||
|
"step": 22
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4329411764705882,
|
||||||
|
"grad_norm": 2.609375,
|
||||||
|
"learning_rate": 6.530612244897959e-06,
|
||||||
|
"loss": 0.8718,
|
||||||
|
"step": 23
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.45176470588235296,
|
||||||
|
"grad_norm": 3.578125,
|
||||||
|
"learning_rate": 6.326530612244899e-06,
|
||||||
|
"loss": 1.0863,
|
||||||
|
"step": 24
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.47058823529411764,
|
||||||
|
"grad_norm": 3.765625,
|
||||||
|
"learning_rate": 6.122448979591837e-06,
|
||||||
|
"loss": 1.0913,
|
||||||
|
"step": 25
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4894117647058824,
|
||||||
|
"grad_norm": 2.828125,
|
||||||
|
"learning_rate": 5.918367346938776e-06,
|
||||||
|
"loss": 1.0977,
|
||||||
|
"step": 26
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.508235294117647,
|
||||||
|
"grad_norm": 4.15625,
|
||||||
|
"learning_rate": 5.7142857142857145e-06,
|
||||||
|
"loss": 1.2962,
|
||||||
|
"step": 27
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5270588235294118,
|
||||||
|
"grad_norm": 3.421875,
|
||||||
|
"learning_rate": 5.510204081632653e-06,
|
||||||
|
"loss": 1.1993,
|
||||||
|
"step": 28
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5458823529411765,
|
||||||
|
"grad_norm": 3.34375,
|
||||||
|
"learning_rate": 5.306122448979593e-06,
|
||||||
|
"loss": 1.028,
|
||||||
|
"step": 29
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5647058823529412,
|
||||||
|
"grad_norm": 4.46875,
|
||||||
|
"learning_rate": 5.1020408163265315e-06,
|
||||||
|
"loss": 1.2644,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5647058823529412,
|
||||||
|
"eval_loss": 1.1749615669250488,
|
||||||
|
"eval_model_preparation_time": 0.019,
|
||||||
|
"eval_runtime": 7.6725,
|
||||||
|
"eval_samples_per_second": 27.762,
|
||||||
|
"eval_steps_per_second": 13.946,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5835294117647059,
|
||||||
|
"grad_norm": 3.515625,
|
||||||
|
"learning_rate": 4.897959183673469e-06,
|
||||||
|
"loss": 1.0328,
|
||||||
|
"step": 31
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6023529411764705,
|
||||||
|
"grad_norm": 4.1875,
|
||||||
|
"learning_rate": 4.693877551020409e-06,
|
||||||
|
"loss": 1.2546,
|
||||||
|
"step": 32
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6211764705882353,
|
||||||
|
"grad_norm": 3.78125,
|
||||||
|
"learning_rate": 4.489795918367348e-06,
|
||||||
|
"loss": 1.3015,
|
||||||
|
"step": 33
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.64,
|
||||||
|
"grad_norm": 2.734375,
|
||||||
|
"learning_rate": 4.2857142857142855e-06,
|
||||||
|
"loss": 0.8548,
|
||||||
|
"step": 34
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6588235294117647,
|
||||||
|
"grad_norm": 3.234375,
|
||||||
|
"learning_rate": 4.081632653061225e-06,
|
||||||
|
"loss": 1.0775,
|
||||||
|
"step": 35
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6776470588235294,
|
||||||
|
"grad_norm": 3.625,
|
||||||
|
"learning_rate": 3.877551020408164e-06,
|
||||||
|
"loss": 1.1389,
|
||||||
|
"step": 36
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6964705882352941,
|
||||||
|
"grad_norm": 3.078125,
|
||||||
|
"learning_rate": 3.6734693877551024e-06,
|
||||||
|
"loss": 1.0469,
|
||||||
|
"step": 37
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7152941176470589,
|
||||||
|
"grad_norm": 3.03125,
|
||||||
|
"learning_rate": 3.469387755102041e-06,
|
||||||
|
"loss": 1.3002,
|
||||||
|
"step": 38
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7341176470588235,
|
||||||
|
"grad_norm": 3.359375,
|
||||||
|
"learning_rate": 3.2653061224489794e-06,
|
||||||
|
"loss": 1.1927,
|
||||||
|
"step": 39
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7529411764705882,
|
||||||
|
"grad_norm": 2.53125,
|
||||||
|
"learning_rate": 3.0612244897959185e-06,
|
||||||
|
"loss": 0.9141,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7529411764705882,
|
||||||
|
"eval_loss": 1.1439083814620972,
|
||||||
|
"eval_model_preparation_time": 0.019,
|
||||||
|
"eval_runtime": 7.7509,
|
||||||
|
"eval_samples_per_second": 27.481,
|
||||||
|
"eval_steps_per_second": 13.805,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7717647058823529,
|
||||||
|
"grad_norm": 2.59375,
|
||||||
|
"learning_rate": 2.8571428571428573e-06,
|
||||||
|
"loss": 0.973,
|
||||||
|
"step": 41
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7905882352941176,
|
||||||
|
"grad_norm": 3.5,
|
||||||
|
"learning_rate": 2.6530612244897964e-06,
|
||||||
|
"loss": 1.061,
|
||||||
|
"step": 42
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8094117647058824,
|
||||||
|
"grad_norm": 3.140625,
|
||||||
|
"learning_rate": 2.4489795918367347e-06,
|
||||||
|
"loss": 1.0456,
|
||||||
|
"step": 43
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8282352941176471,
|
||||||
|
"grad_norm": 2.796875,
|
||||||
|
"learning_rate": 2.244897959183674e-06,
|
||||||
|
"loss": 1.229,
|
||||||
|
"step": 44
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8470588235294118,
|
||||||
|
"grad_norm": 2.78125,
|
||||||
|
"learning_rate": 2.0408163265306125e-06,
|
||||||
|
"loss": 0.9546,
|
||||||
|
"step": 45
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8658823529411764,
|
||||||
|
"grad_norm": 3.21875,
|
||||||
|
"learning_rate": 1.8367346938775512e-06,
|
||||||
|
"loss": 0.9939,
|
||||||
|
"step": 46
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8847058823529412,
|
||||||
|
"grad_norm": 3.25,
|
||||||
|
"learning_rate": 1.6326530612244897e-06,
|
||||||
|
"loss": 1.0063,
|
||||||
|
"step": 47
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9035294117647059,
|
||||||
|
"grad_norm": 2.625,
|
||||||
|
"learning_rate": 1.4285714285714286e-06,
|
||||||
|
"loss": 0.9505,
|
||||||
|
"step": 48
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9223529411764706,
|
||||||
|
"grad_norm": 4.09375,
|
||||||
|
"learning_rate": 1.2244897959183673e-06,
|
||||||
|
"loss": 1.4137,
|
||||||
|
"step": 49
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9411764705882353,
|
||||||
|
"grad_norm": 2.703125,
|
||||||
|
"learning_rate": 1.0204081632653063e-06,
|
||||||
|
"loss": 0.8221,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9411764705882353,
|
||||||
|
"eval_loss": 1.1319535970687866,
|
||||||
|
"eval_model_preparation_time": 0.019,
|
||||||
|
"eval_runtime": 7.7224,
|
||||||
|
"eval_samples_per_second": 27.582,
|
||||||
|
"eval_steps_per_second": 13.856,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.96,
|
||||||
|
"grad_norm": 3.671875,
|
||||||
|
"learning_rate": 8.163265306122449e-07,
|
||||||
|
"loss": 1.1134,
|
||||||
|
"step": 51
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9788235294117648,
|
||||||
|
"grad_norm": 2.953125,
|
||||||
|
"learning_rate": 6.122448979591837e-07,
|
||||||
|
"loss": 0.8735,
|
||||||
|
"step": 52
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9976470588235294,
|
||||||
|
"grad_norm": 3.71875,
|
||||||
|
"learning_rate": 4.0816326530612243e-07,
|
||||||
|
"loss": 1.4566,
|
||||||
|
"step": 53
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"grad_norm": 16.5,
|
||||||
|
"learning_rate": 2.0408163265306121e-07,
|
||||||
|
"loss": 0.7701,
|
||||||
|
"step": 54
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 1,
|
||||||
|
"max_steps": 54,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 1,
|
||||||
|
"save_steps": 5000,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 1.048439738253312e+16,
|
||||||
|
"train_batch_size": 2,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
checkpoint-54/training_args.bin
Normal file
3
checkpoint-54/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8d1bf95749b9aa06dad8efb734cdd17b69d59232809880fd9892ef4202d246a5
|
||||||
|
size 6097
|
||||||
38
config.json
Normal file
38
config.json
Normal file
@@ -0,0 +1,38 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 128000,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"eos_token_id": 128009,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 14336,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"mlp_bias": false,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 32,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 128004,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": {
|
||||||
|
"factor": 8.0,
|
||||||
|
"high_freq_factor": 4.0,
|
||||||
|
"low_freq_factor": 1.0,
|
||||||
|
"original_max_position_embeddings": 8192,
|
||||||
|
"rope_type": "llama3"
|
||||||
|
},
|
||||||
|
"rope_theta": 500000.0,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "4.56.2",
|
||||||
|
"unsloth_fixed": true,
|
||||||
|
"unsloth_version": "2025.10.3",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 128256
|
||||||
|
}
|
||||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c4f1266848035fdd3d9ab78a88b7007cdbc65219ab623ee63982905cdf937513
|
||||||
|
size 4976698672
|
||||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:508d83ddc89172e65671098a8c76dcb9792853c3df344817083bc5a0db47d30c
|
||||||
|
size 4999802720
|
||||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ca4fe1e8a6d1c81cbeae073f50d887c72c20ce55d39f6ba00830e5e599e3671c
|
||||||
|
size 4915916176
|
||||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8e7081d5d86b2cee95a3476ee32101b7beb01a418c364021c46175fba6eb59e1
|
||||||
|
size 1168138808
|
||||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 16060522496
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<|begin_of_text|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|eot_id|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|finetune_right_pad_id|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
2067
tokenizer_config.json
Normal file
2067
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user