Upload adapters (job 4237630)
Browse files- README.md +207 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +87 -0
- checkpoint-1000/README.md +207 -0
- checkpoint-1000/adapter_config.json +39 -0
- checkpoint-1000/adapter_model.safetensors +3 -0
- checkpoint-1000/chat_template.jinja +87 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +24 -0
- checkpoint-1000/tokenizer.json +0 -0
- checkpoint-1000/tokenizer.model +3 -0
- checkpoint-1000/tokenizer_config.json +0 -0
- checkpoint-1000/trainer_state.json +182 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1137/README.md +207 -0
- checkpoint-1137/adapter_config.json +39 -0
- checkpoint-1137/adapter_model.safetensors +3 -0
- checkpoint-1137/chat_template.jinja +87 -0
- checkpoint-1137/optimizer.pt +3 -0
- checkpoint-1137/rng_state.pth +3 -0
- checkpoint-1137/scheduler.pt +3 -0
- checkpoint-1137/special_tokens_map.json +24 -0
- checkpoint-1137/tokenizer.json +0 -0
- checkpoint-1137/tokenizer.model +3 -0
- checkpoint-1137/tokenizer_config.json +0 -0
- checkpoint-1137/trainer_state.json +196 -0
- checkpoint-1137/training_args.bin +3 -0
- checkpoint-800/README.md +207 -0
- checkpoint-800/adapter_config.json +39 -0
- checkpoint-800/adapter_model.safetensors +3 -0
- checkpoint-800/chat_template.jinja +87 -0
- checkpoint-800/optimizer.pt +3 -0
- checkpoint-800/rng_state.pth +3 -0
- checkpoint-800/scheduler.pt +3 -0
- checkpoint-800/special_tokens_map.json +24 -0
- checkpoint-800/tokenizer.json +0 -0
- checkpoint-800/tokenizer.model +3 -0
- checkpoint-800/tokenizer_config.json +0 -0
- checkpoint-800/trainer_state.json +146 -0
- checkpoint-800/training_args.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** [More Information Needed]
|
| 26 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
+
- **Model type:** [More Information Needed]
|
| 29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 30 |
+
- **License:** [More Information Needed]
|
| 31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 32 |
+
|
| 33 |
+
### Model Sources [optional]
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
- **Repository:** [More Information Needed]
|
| 38 |
+
- **Paper [optional]:** [More Information Needed]
|
| 39 |
+
- **Demo [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
## Uses
|
| 42 |
+
|
| 43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
|
| 45 |
+
### Direct Use
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Downstream Use [optional]
|
| 52 |
+
|
| 53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
### Out-of-Scope Use
|
| 58 |
+
|
| 59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
## Bias, Risks, and Limitations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
+
|
| 67 |
+
[More Information Needed]
|
| 68 |
+
|
| 69 |
+
### Recommendations
|
| 70 |
+
|
| 71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
+
|
| 73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
+
|
| 75 |
+
## How to Get Started with the Model
|
| 76 |
+
|
| 77 |
+
Use the code below to get started with the model.
|
| 78 |
+
|
| 79 |
+
[More Information Needed]
|
| 80 |
+
|
| 81 |
+
## Training Details
|
| 82 |
+
|
| 83 |
+
### Training Data
|
| 84 |
+
|
| 85 |
+
<!-- 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. -->
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
### Training Procedure
|
| 90 |
+
|
| 91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 92 |
+
|
| 93 |
+
#### Preprocessing [optional]
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
#### Training Hyperparameters
|
| 99 |
+
|
| 100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 101 |
+
|
| 102 |
+
#### Speeds, Sizes, Times [optional]
|
| 103 |
+
|
| 104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 105 |
+
|
| 106 |
+
[More Information Needed]
|
| 107 |
+
|
| 108 |
+
## Evaluation
|
| 109 |
+
|
| 110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 111 |
+
|
| 112 |
+
### Testing Data, Factors & Metrics
|
| 113 |
+
|
| 114 |
+
#### Testing Data
|
| 115 |
+
|
| 116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Factors
|
| 121 |
+
|
| 122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
#### Metrics
|
| 127 |
+
|
| 128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 129 |
+
|
| 130 |
+
[More Information Needed]
|
| 131 |
+
|
| 132 |
+
### Results
|
| 133 |
+
|
| 134 |
+
[More Information Needed]
|
| 135 |
+
|
| 136 |
+
#### Summary
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
## Model Examination [optional]
|
| 141 |
+
|
| 142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 143 |
+
|
| 144 |
+
[More Information Needed]
|
| 145 |
+
|
| 146 |
+
## Environmental Impact
|
| 147 |
+
|
| 148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 149 |
+
|
| 150 |
+
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).
|
| 151 |
+
|
| 152 |
+
- **Hardware Type:** [More Information Needed]
|
| 153 |
+
- **Hours used:** [More Information Needed]
|
| 154 |
+
- **Cloud Provider:** [More Information Needed]
|
| 155 |
+
- **Compute Region:** [More Information Needed]
|
| 156 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
+
|
| 158 |
+
## Technical Specifications [optional]
|
| 159 |
+
|
| 160 |
+
### Model Architecture and Objective
|
| 161 |
+
|
| 162 |
+
[More Information Needed]
|
| 163 |
+
|
| 164 |
+
### Compute Infrastructure
|
| 165 |
+
|
| 166 |
+
[More Information Needed]
|
| 167 |
+
|
| 168 |
+
#### Hardware
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
#### Software
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
## Citation [optional]
|
| 177 |
+
|
| 178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 179 |
+
|
| 180 |
+
**BibTeX:**
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
**APA:**
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## Glossary [optional]
|
| 189 |
+
|
| 190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 191 |
+
|
| 192 |
+
[More Information Needed]
|
| 193 |
+
|
| 194 |
+
## More Information [optional]
|
| 195 |
+
|
| 196 |
+
[More Information Needed]
|
| 197 |
+
|
| 198 |
+
## Model Card Authors [optional]
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## Model Card Contact
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
- PEFT 0.17.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 64,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"k_proj"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c980bb12550db333b3706ba29bd5e6f0c8a1a74e4b40b87d2319a7d417cc790f
|
| 3 |
+
size 218138576
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if messages[0]["role"] == "system" %}
|
| 2 |
+
{%- set system_message = messages[0]["content"] %}
|
| 3 |
+
{%- set loop_messages = messages[1:] %}
|
| 4 |
+
{%- else %}
|
| 5 |
+
{%- set loop_messages = messages %}
|
| 6 |
+
{%- endif %}
|
| 7 |
+
{%- if not tools is defined %}
|
| 8 |
+
{%- set tools = none %}
|
| 9 |
+
{%- endif %}
|
| 10 |
+
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
|
| 11 |
+
|
| 12 |
+
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
|
| 13 |
+
{%- set ns = namespace() %}
|
| 14 |
+
{%- set ns.index = 0 %}
|
| 15 |
+
{%- for message in loop_messages %}
|
| 16 |
+
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
|
| 17 |
+
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
|
| 18 |
+
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- set ns.index = ns.index + 1 %}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
{%- endfor %}
|
| 23 |
+
|
| 24 |
+
{{- bos_token }}
|
| 25 |
+
{%- for message in loop_messages %}
|
| 26 |
+
{%- if message["role"] == "user" %}
|
| 27 |
+
{%- if tools is not none and (message == user_messages[-1]) %}
|
| 28 |
+
{{- "[AVAILABLE_TOOLS] [" }}
|
| 29 |
+
{%- for tool in tools %}
|
| 30 |
+
{%- set tool = tool.function %}
|
| 31 |
+
{{- '{"type": "function", "function": {' }}
|
| 32 |
+
{%- for key, val in tool.items() if key != "return" %}
|
| 33 |
+
{%- if val is string %}
|
| 34 |
+
{{- '"' + key + '": "' + val + '"' }}
|
| 35 |
+
{%- else %}
|
| 36 |
+
{{- '"' + key + '": ' + val|tojson }}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- if not loop.last %}
|
| 39 |
+
{{- ", " }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endfor %}
|
| 42 |
+
{{- "}}" }}
|
| 43 |
+
{%- if not loop.last %}
|
| 44 |
+
{{- ", " }}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- "]" }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- endfor %}
|
| 49 |
+
{{- "[/AVAILABLE_TOOLS]" }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- if loop.last and system_message is defined %}
|
| 52 |
+
{{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
|
| 53 |
+
{%- else %}
|
| 54 |
+
{{- "[INST] " + message["content"] + "[/INST]" }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- elif message.tool_calls is defined and message.tool_calls is not none %}
|
| 57 |
+
{{- "[TOOL_CALLS] [" }}
|
| 58 |
+
{%- for tool_call in message.tool_calls %}
|
| 59 |
+
{%- set out = tool_call.function|tojson %}
|
| 60 |
+
{{- out[:-1] }}
|
| 61 |
+
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
|
| 62 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- ', "id": "' + tool_call.id + '"}' }}
|
| 65 |
+
{%- if not loop.last %}
|
| 66 |
+
{{- ", " }}
|
| 67 |
+
{%- else %}
|
| 68 |
+
{{- "]" + eos_token }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- endfor %}
|
| 71 |
+
{%- elif message["role"] == "assistant" %}
|
| 72 |
+
{{- " " + message["content"]|trim + eos_token}}
|
| 73 |
+
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
| 74 |
+
{%- if message.content is defined and message.content.content is defined %}
|
| 75 |
+
{%- set content = message.content.content %}
|
| 76 |
+
{%- else %}
|
| 77 |
+
{%- set content = message.content %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
|
| 80 |
+
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
|
| 81 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
|
| 84 |
+
{%- else %}
|
| 85 |
+
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- endfor %}
|
checkpoint-1000/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** [More Information Needed]
|
| 26 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
+
- **Model type:** [More Information Needed]
|
| 29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 30 |
+
- **License:** [More Information Needed]
|
| 31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 32 |
+
|
| 33 |
+
### Model Sources [optional]
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
- **Repository:** [More Information Needed]
|
| 38 |
+
- **Paper [optional]:** [More Information Needed]
|
| 39 |
+
- **Demo [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
## Uses
|
| 42 |
+
|
| 43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
|
| 45 |
+
### Direct Use
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Downstream Use [optional]
|
| 52 |
+
|
| 53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
### Out-of-Scope Use
|
| 58 |
+
|
| 59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
## Bias, Risks, and Limitations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
+
|
| 67 |
+
[More Information Needed]
|
| 68 |
+
|
| 69 |
+
### Recommendations
|
| 70 |
+
|
| 71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
+
|
| 73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
+
|
| 75 |
+
## How to Get Started with the Model
|
| 76 |
+
|
| 77 |
+
Use the code below to get started with the model.
|
| 78 |
+
|
| 79 |
+
[More Information Needed]
|
| 80 |
+
|
| 81 |
+
## Training Details
|
| 82 |
+
|
| 83 |
+
### Training Data
|
| 84 |
+
|
| 85 |
+
<!-- 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. -->
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
### Training Procedure
|
| 90 |
+
|
| 91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 92 |
+
|
| 93 |
+
#### Preprocessing [optional]
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
#### Training Hyperparameters
|
| 99 |
+
|
| 100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 101 |
+
|
| 102 |
+
#### Speeds, Sizes, Times [optional]
|
| 103 |
+
|
| 104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 105 |
+
|
| 106 |
+
[More Information Needed]
|
| 107 |
+
|
| 108 |
+
## Evaluation
|
| 109 |
+
|
| 110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 111 |
+
|
| 112 |
+
### Testing Data, Factors & Metrics
|
| 113 |
+
|
| 114 |
+
#### Testing Data
|
| 115 |
+
|
| 116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Factors
|
| 121 |
+
|
| 122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
#### Metrics
|
| 127 |
+
|
| 128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 129 |
+
|
| 130 |
+
[More Information Needed]
|
| 131 |
+
|
| 132 |
+
### Results
|
| 133 |
+
|
| 134 |
+
[More Information Needed]
|
| 135 |
+
|
| 136 |
+
#### Summary
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
## Model Examination [optional]
|
| 141 |
+
|
| 142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 143 |
+
|
| 144 |
+
[More Information Needed]
|
| 145 |
+
|
| 146 |
+
## Environmental Impact
|
| 147 |
+
|
| 148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 149 |
+
|
| 150 |
+
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).
|
| 151 |
+
|
| 152 |
+
- **Hardware Type:** [More Information Needed]
|
| 153 |
+
- **Hours used:** [More Information Needed]
|
| 154 |
+
- **Cloud Provider:** [More Information Needed]
|
| 155 |
+
- **Compute Region:** [More Information Needed]
|
| 156 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
+
|
| 158 |
+
## Technical Specifications [optional]
|
| 159 |
+
|
| 160 |
+
### Model Architecture and Objective
|
| 161 |
+
|
| 162 |
+
[More Information Needed]
|
| 163 |
+
|
| 164 |
+
### Compute Infrastructure
|
| 165 |
+
|
| 166 |
+
[More Information Needed]
|
| 167 |
+
|
| 168 |
+
#### Hardware
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
#### Software
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
## Citation [optional]
|
| 177 |
+
|
| 178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 179 |
+
|
| 180 |
+
**BibTeX:**
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
**APA:**
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## Glossary [optional]
|
| 189 |
+
|
| 190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 191 |
+
|
| 192 |
+
[More Information Needed]
|
| 193 |
+
|
| 194 |
+
## More Information [optional]
|
| 195 |
+
|
| 196 |
+
[More Information Needed]
|
| 197 |
+
|
| 198 |
+
## Model Card Authors [optional]
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## Model Card Contact
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
- PEFT 0.17.1
|
checkpoint-1000/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 64,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"k_proj"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-1000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d7ab1bbaacc99e991193c7f883fee6005653c3b6d8a5d2d92f72913013c6ec2
|
| 3 |
+
size 218138576
|
checkpoint-1000/chat_template.jinja
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if messages[0]["role"] == "system" %}
|
| 2 |
+
{%- set system_message = messages[0]["content"] %}
|
| 3 |
+
{%- set loop_messages = messages[1:] %}
|
| 4 |
+
{%- else %}
|
| 5 |
+
{%- set loop_messages = messages %}
|
| 6 |
+
{%- endif %}
|
| 7 |
+
{%- if not tools is defined %}
|
| 8 |
+
{%- set tools = none %}
|
| 9 |
+
{%- endif %}
|
| 10 |
+
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
|
| 11 |
+
|
| 12 |
+
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
|
| 13 |
+
{%- set ns = namespace() %}
|
| 14 |
+
{%- set ns.index = 0 %}
|
| 15 |
+
{%- for message in loop_messages %}
|
| 16 |
+
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
|
| 17 |
+
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
|
| 18 |
+
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- set ns.index = ns.index + 1 %}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
{%- endfor %}
|
| 23 |
+
|
| 24 |
+
{{- bos_token }}
|
| 25 |
+
{%- for message in loop_messages %}
|
| 26 |
+
{%- if message["role"] == "user" %}
|
| 27 |
+
{%- if tools is not none and (message == user_messages[-1]) %}
|
| 28 |
+
{{- "[AVAILABLE_TOOLS] [" }}
|
| 29 |
+
{%- for tool in tools %}
|
| 30 |
+
{%- set tool = tool.function %}
|
| 31 |
+
{{- '{"type": "function", "function": {' }}
|
| 32 |
+
{%- for key, val in tool.items() if key != "return" %}
|
| 33 |
+
{%- if val is string %}
|
| 34 |
+
{{- '"' + key + '": "' + val + '"' }}
|
| 35 |
+
{%- else %}
|
| 36 |
+
{{- '"' + key + '": ' + val|tojson }}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- if not loop.last %}
|
| 39 |
+
{{- ", " }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endfor %}
|
| 42 |
+
{{- "}}" }}
|
| 43 |
+
{%- if not loop.last %}
|
| 44 |
+
{{- ", " }}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- "]" }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- endfor %}
|
| 49 |
+
{{- "[/AVAILABLE_TOOLS]" }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- if loop.last and system_message is defined %}
|
| 52 |
+
{{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
|
| 53 |
+
{%- else %}
|
| 54 |
+
{{- "[INST] " + message["content"] + "[/INST]" }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- elif message.tool_calls is defined and message.tool_calls is not none %}
|
| 57 |
+
{{- "[TOOL_CALLS] [" }}
|
| 58 |
+
{%- for tool_call in message.tool_calls %}
|
| 59 |
+
{%- set out = tool_call.function|tojson %}
|
| 60 |
+
{{- out[:-1] }}
|
| 61 |
+
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
|
| 62 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- ', "id": "' + tool_call.id + '"}' }}
|
| 65 |
+
{%- if not loop.last %}
|
| 66 |
+
{{- ", " }}
|
| 67 |
+
{%- else %}
|
| 68 |
+
{{- "]" + eos_token }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- endfor %}
|
| 71 |
+
{%- elif message["role"] == "assistant" %}
|
| 72 |
+
{{- " " + message["content"]|trim + eos_token}}
|
| 73 |
+
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
| 74 |
+
{%- if message.content is defined and message.content.content is defined %}
|
| 75 |
+
{%- set content = message.content.content %}
|
| 76 |
+
{%- else %}
|
| 77 |
+
{%- set content = message.content %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
|
| 80 |
+
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
|
| 81 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
|
| 84 |
+
{%- else %}
|
| 85 |
+
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- endfor %}
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5bd2feb15a6b11c008b8cffb24ff32abf3ca39ceea76e3c2da3205c5da765ca
|
| 3 |
+
size 436427467
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26a98b1ce275bbf3fbe894ceca2f2efe8ed765215e45b0c44f3368d3904d9011
|
| 3 |
+
size 14645
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:188596fc728f4bfee691fe30a9e3895f235c4c3b6a6d071126bf08db5aec53fe
|
| 3 |
+
size 1465
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
| 3 |
+
size 587404
|
checkpoint-1000/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8795316493966963,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04397658246983481,
|
| 14 |
+
"grad_norm": 1.0395877361297607,
|
| 15 |
+
"learning_rate": 0.00019138082673702725,
|
| 16 |
+
"loss": 1.3457,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.08795316493966962,
|
| 21 |
+
"grad_norm": 1.0277217626571655,
|
| 22 |
+
"learning_rate": 0.00018258575197889184,
|
| 23 |
+
"loss": 1.0388,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.13192974740950444,
|
| 28 |
+
"grad_norm": 0.9229634404182434,
|
| 29 |
+
"learning_rate": 0.0001737906772207564,
|
| 30 |
+
"loss": 0.9245,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.17590632987933924,
|
| 35 |
+
"grad_norm": 0.8828799724578857,
|
| 36 |
+
"learning_rate": 0.00016499560246262094,
|
| 37 |
+
"loss": 0.8399,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.21988291234917406,
|
| 42 |
+
"grad_norm": 1.018609642982483,
|
| 43 |
+
"learning_rate": 0.0001562005277044855,
|
| 44 |
+
"loss": 0.8015,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2638594948190089,
|
| 49 |
+
"grad_norm": 0.9031912684440613,
|
| 50 |
+
"learning_rate": 0.00014740545294635005,
|
| 51 |
+
"loss": 0.7248,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.3078360772888437,
|
| 56 |
+
"grad_norm": 0.8781272768974304,
|
| 57 |
+
"learning_rate": 0.0001386103781882146,
|
| 58 |
+
"loss": 0.684,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.3518126597586785,
|
| 63 |
+
"grad_norm": 0.8193464279174805,
|
| 64 |
+
"learning_rate": 0.00012981530343007916,
|
| 65 |
+
"loss": 0.6587,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3957892422285133,
|
| 70 |
+
"grad_norm": 0.84972083568573,
|
| 71 |
+
"learning_rate": 0.00012102022867194372,
|
| 72 |
+
"loss": 0.6357,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.43976582469834813,
|
| 77 |
+
"grad_norm": 0.9738919734954834,
|
| 78 |
+
"learning_rate": 0.00011222515391380828,
|
| 79 |
+
"loss": 0.6107,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.48374240716818295,
|
| 84 |
+
"grad_norm": 0.9879764318466187,
|
| 85 |
+
"learning_rate": 0.00010343007915567282,
|
| 86 |
+
"loss": 0.573,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5277189896380178,
|
| 91 |
+
"grad_norm": 0.9049842953681946,
|
| 92 |
+
"learning_rate": 9.463500439753739e-05,
|
| 93 |
+
"loss": 0.5274,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.5716955721078526,
|
| 98 |
+
"grad_norm": 0.9793794751167297,
|
| 99 |
+
"learning_rate": 8.583992963940193e-05,
|
| 100 |
+
"loss": 0.527,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.6156721545776874,
|
| 105 |
+
"grad_norm": 1.096916913986206,
|
| 106 |
+
"learning_rate": 7.704485488126649e-05,
|
| 107 |
+
"loss": 0.5072,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.6596487370475222,
|
| 112 |
+
"grad_norm": 0.9264512062072754,
|
| 113 |
+
"learning_rate": 6.824978012313104e-05,
|
| 114 |
+
"loss": 0.4914,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.703625319517357,
|
| 119 |
+
"grad_norm": 0.8605396151542664,
|
| 120 |
+
"learning_rate": 5.94547053649956e-05,
|
| 121 |
+
"loss": 0.4893,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.7476019019871918,
|
| 126 |
+
"grad_norm": 0.9258248209953308,
|
| 127 |
+
"learning_rate": 5.0659630606860164e-05,
|
| 128 |
+
"loss": 0.4682,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.7915784844570266,
|
| 133 |
+
"grad_norm": 0.962844729423523,
|
| 134 |
+
"learning_rate": 4.186455584872472e-05,
|
| 135 |
+
"loss": 0.4536,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.8355550669268614,
|
| 140 |
+
"grad_norm": 0.933445930480957,
|
| 141 |
+
"learning_rate": 3.306948109058927e-05,
|
| 142 |
+
"loss": 0.4425,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.8795316493966963,
|
| 147 |
+
"grad_norm": 1.0119765996932983,
|
| 148 |
+
"learning_rate": 2.4274406332453827e-05,
|
| 149 |
+
"loss": 0.4259,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.8795316493966963,
|
| 154 |
+
"eval_loss": 0.40038564801216125,
|
| 155 |
+
"eval_runtime": 2826.8322,
|
| 156 |
+
"eval_samples_per_second": 6.156,
|
| 157 |
+
"eval_steps_per_second": 0.77,
|
| 158 |
+
"step": 1000
|
| 159 |
+
}
|
| 160 |
+
],
|
| 161 |
+
"logging_steps": 50,
|
| 162 |
+
"max_steps": 1137,
|
| 163 |
+
"num_input_tokens_seen": 0,
|
| 164 |
+
"num_train_epochs": 1,
|
| 165 |
+
"save_steps": 200,
|
| 166 |
+
"stateful_callbacks": {
|
| 167 |
+
"TrainerControl": {
|
| 168 |
+
"args": {
|
| 169 |
+
"should_epoch_stop": false,
|
| 170 |
+
"should_evaluate": false,
|
| 171 |
+
"should_log": false,
|
| 172 |
+
"should_save": true,
|
| 173 |
+
"should_training_stop": false
|
| 174 |
+
},
|
| 175 |
+
"attributes": {}
|
| 176 |
+
}
|
| 177 |
+
},
|
| 178 |
+
"total_flos": 4.440889920408453e+17,
|
| 179 |
+
"train_batch_size": 2,
|
| 180 |
+
"trial_name": null,
|
| 181 |
+
"trial_params": null
|
| 182 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad5efd9de373c20e20b65557dd7b0578f0a7abf507bfa7c7cf14e9c393196c4
|
| 3 |
+
size 5713
|
checkpoint-1137/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** [More Information Needed]
|
| 26 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
+
- **Model type:** [More Information Needed]
|
| 29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 30 |
+
- **License:** [More Information Needed]
|
| 31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 32 |
+
|
| 33 |
+
### Model Sources [optional]
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
- **Repository:** [More Information Needed]
|
| 38 |
+
- **Paper [optional]:** [More Information Needed]
|
| 39 |
+
- **Demo [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
## Uses
|
| 42 |
+
|
| 43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
|
| 45 |
+
### Direct Use
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Downstream Use [optional]
|
| 52 |
+
|
| 53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
### Out-of-Scope Use
|
| 58 |
+
|
| 59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
## Bias, Risks, and Limitations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
+
|
| 67 |
+
[More Information Needed]
|
| 68 |
+
|
| 69 |
+
### Recommendations
|
| 70 |
+
|
| 71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
+
|
| 73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
+
|
| 75 |
+
## How to Get Started with the Model
|
| 76 |
+
|
| 77 |
+
Use the code below to get started with the model.
|
| 78 |
+
|
| 79 |
+
[More Information Needed]
|
| 80 |
+
|
| 81 |
+
## Training Details
|
| 82 |
+
|
| 83 |
+
### Training Data
|
| 84 |
+
|
| 85 |
+
<!-- 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. -->
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
### Training Procedure
|
| 90 |
+
|
| 91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 92 |
+
|
| 93 |
+
#### Preprocessing [optional]
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
#### Training Hyperparameters
|
| 99 |
+
|
| 100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 101 |
+
|
| 102 |
+
#### Speeds, Sizes, Times [optional]
|
| 103 |
+
|
| 104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 105 |
+
|
| 106 |
+
[More Information Needed]
|
| 107 |
+
|
| 108 |
+
## Evaluation
|
| 109 |
+
|
| 110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 111 |
+
|
| 112 |
+
### Testing Data, Factors & Metrics
|
| 113 |
+
|
| 114 |
+
#### Testing Data
|
| 115 |
+
|
| 116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Factors
|
| 121 |
+
|
| 122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
#### Metrics
|
| 127 |
+
|
| 128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 129 |
+
|
| 130 |
+
[More Information Needed]
|
| 131 |
+
|
| 132 |
+
### Results
|
| 133 |
+
|
| 134 |
+
[More Information Needed]
|
| 135 |
+
|
| 136 |
+
#### Summary
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
## Model Examination [optional]
|
| 141 |
+
|
| 142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 143 |
+
|
| 144 |
+
[More Information Needed]
|
| 145 |
+
|
| 146 |
+
## Environmental Impact
|
| 147 |
+
|
| 148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 149 |
+
|
| 150 |
+
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).
|
| 151 |
+
|
| 152 |
+
- **Hardware Type:** [More Information Needed]
|
| 153 |
+
- **Hours used:** [More Information Needed]
|
| 154 |
+
- **Cloud Provider:** [More Information Needed]
|
| 155 |
+
- **Compute Region:** [More Information Needed]
|
| 156 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
+
|
| 158 |
+
## Technical Specifications [optional]
|
| 159 |
+
|
| 160 |
+
### Model Architecture and Objective
|
| 161 |
+
|
| 162 |
+
[More Information Needed]
|
| 163 |
+
|
| 164 |
+
### Compute Infrastructure
|
| 165 |
+
|
| 166 |
+
[More Information Needed]
|
| 167 |
+
|
| 168 |
+
#### Hardware
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
#### Software
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
## Citation [optional]
|
| 177 |
+
|
| 178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 179 |
+
|
| 180 |
+
**BibTeX:**
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
**APA:**
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## Glossary [optional]
|
| 189 |
+
|
| 190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 191 |
+
|
| 192 |
+
[More Information Needed]
|
| 193 |
+
|
| 194 |
+
## More Information [optional]
|
| 195 |
+
|
| 196 |
+
[More Information Needed]
|
| 197 |
+
|
| 198 |
+
## Model Card Authors [optional]
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## Model Card Contact
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
- PEFT 0.17.1
|
checkpoint-1137/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 64,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"k_proj"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-1137/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c980bb12550db333b3706ba29bd5e6f0c8a1a74e4b40b87d2319a7d417cc790f
|
| 3 |
+
size 218138576
|
checkpoint-1137/chat_template.jinja
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if messages[0]["role"] == "system" %}
|
| 2 |
+
{%- set system_message = messages[0]["content"] %}
|
| 3 |
+
{%- set loop_messages = messages[1:] %}
|
| 4 |
+
{%- else %}
|
| 5 |
+
{%- set loop_messages = messages %}
|
| 6 |
+
{%- endif %}
|
| 7 |
+
{%- if not tools is defined %}
|
| 8 |
+
{%- set tools = none %}
|
| 9 |
+
{%- endif %}
|
| 10 |
+
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
|
| 11 |
+
|
| 12 |
+
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
|
| 13 |
+
{%- set ns = namespace() %}
|
| 14 |
+
{%- set ns.index = 0 %}
|
| 15 |
+
{%- for message in loop_messages %}
|
| 16 |
+
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
|
| 17 |
+
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
|
| 18 |
+
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- set ns.index = ns.index + 1 %}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
{%- endfor %}
|
| 23 |
+
|
| 24 |
+
{{- bos_token }}
|
| 25 |
+
{%- for message in loop_messages %}
|
| 26 |
+
{%- if message["role"] == "user" %}
|
| 27 |
+
{%- if tools is not none and (message == user_messages[-1]) %}
|
| 28 |
+
{{- "[AVAILABLE_TOOLS] [" }}
|
| 29 |
+
{%- for tool in tools %}
|
| 30 |
+
{%- set tool = tool.function %}
|
| 31 |
+
{{- '{"type": "function", "function": {' }}
|
| 32 |
+
{%- for key, val in tool.items() if key != "return" %}
|
| 33 |
+
{%- if val is string %}
|
| 34 |
+
{{- '"' + key + '": "' + val + '"' }}
|
| 35 |
+
{%- else %}
|
| 36 |
+
{{- '"' + key + '": ' + val|tojson }}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- if not loop.last %}
|
| 39 |
+
{{- ", " }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endfor %}
|
| 42 |
+
{{- "}}" }}
|
| 43 |
+
{%- if not loop.last %}
|
| 44 |
+
{{- ", " }}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- "]" }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- endfor %}
|
| 49 |
+
{{- "[/AVAILABLE_TOOLS]" }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- if loop.last and system_message is defined %}
|
| 52 |
+
{{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
|
| 53 |
+
{%- else %}
|
| 54 |
+
{{- "[INST] " + message["content"] + "[/INST]" }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- elif message.tool_calls is defined and message.tool_calls is not none %}
|
| 57 |
+
{{- "[TOOL_CALLS] [" }}
|
| 58 |
+
{%- for tool_call in message.tool_calls %}
|
| 59 |
+
{%- set out = tool_call.function|tojson %}
|
| 60 |
+
{{- out[:-1] }}
|
| 61 |
+
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
|
| 62 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- ', "id": "' + tool_call.id + '"}' }}
|
| 65 |
+
{%- if not loop.last %}
|
| 66 |
+
{{- ", " }}
|
| 67 |
+
{%- else %}
|
| 68 |
+
{{- "]" + eos_token }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- endfor %}
|
| 71 |
+
{%- elif message["role"] == "assistant" %}
|
| 72 |
+
{{- " " + message["content"]|trim + eos_token}}
|
| 73 |
+
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
| 74 |
+
{%- if message.content is defined and message.content.content is defined %}
|
| 75 |
+
{%- set content = message.content.content %}
|
| 76 |
+
{%- else %}
|
| 77 |
+
{%- set content = message.content %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
|
| 80 |
+
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
|
| 81 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
|
| 84 |
+
{%- else %}
|
| 85 |
+
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- endfor %}
|
checkpoint-1137/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3873f4ec7d1fcb111dc312625ff345bd37e1050d6ac948fd3ceb7e2a664d9f22
|
| 3 |
+
size 436427467
|
checkpoint-1137/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1da202e97dbd3c4f5983e3200a88583563d178740e89c6a3b495579a136e260e
|
| 3 |
+
size 14645
|
checkpoint-1137/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19333d4aee54b7f5cf0bfc4c9efb14ba8107a65cf2dc10605441c54d9bbc5eaf
|
| 3 |
+
size 1465
|
checkpoint-1137/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-1137/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1137/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
| 3 |
+
size 587404
|
checkpoint-1137/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1137/trainer_state.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 1137,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04397658246983481,
|
| 14 |
+
"grad_norm": 1.0395877361297607,
|
| 15 |
+
"learning_rate": 0.00019138082673702725,
|
| 16 |
+
"loss": 1.3457,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.08795316493966962,
|
| 21 |
+
"grad_norm": 1.0277217626571655,
|
| 22 |
+
"learning_rate": 0.00018258575197889184,
|
| 23 |
+
"loss": 1.0388,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.13192974740950444,
|
| 28 |
+
"grad_norm": 0.9229634404182434,
|
| 29 |
+
"learning_rate": 0.0001737906772207564,
|
| 30 |
+
"loss": 0.9245,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.17590632987933924,
|
| 35 |
+
"grad_norm": 0.8828799724578857,
|
| 36 |
+
"learning_rate": 0.00016499560246262094,
|
| 37 |
+
"loss": 0.8399,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.21988291234917406,
|
| 42 |
+
"grad_norm": 1.018609642982483,
|
| 43 |
+
"learning_rate": 0.0001562005277044855,
|
| 44 |
+
"loss": 0.8015,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2638594948190089,
|
| 49 |
+
"grad_norm": 0.9031912684440613,
|
| 50 |
+
"learning_rate": 0.00014740545294635005,
|
| 51 |
+
"loss": 0.7248,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.3078360772888437,
|
| 56 |
+
"grad_norm": 0.8781272768974304,
|
| 57 |
+
"learning_rate": 0.0001386103781882146,
|
| 58 |
+
"loss": 0.684,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.3518126597586785,
|
| 63 |
+
"grad_norm": 0.8193464279174805,
|
| 64 |
+
"learning_rate": 0.00012981530343007916,
|
| 65 |
+
"loss": 0.6587,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3957892422285133,
|
| 70 |
+
"grad_norm": 0.84972083568573,
|
| 71 |
+
"learning_rate": 0.00012102022867194372,
|
| 72 |
+
"loss": 0.6357,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.43976582469834813,
|
| 77 |
+
"grad_norm": 0.9738919734954834,
|
| 78 |
+
"learning_rate": 0.00011222515391380828,
|
| 79 |
+
"loss": 0.6107,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.48374240716818295,
|
| 84 |
+
"grad_norm": 0.9879764318466187,
|
| 85 |
+
"learning_rate": 0.00010343007915567282,
|
| 86 |
+
"loss": 0.573,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5277189896380178,
|
| 91 |
+
"grad_norm": 0.9049842953681946,
|
| 92 |
+
"learning_rate": 9.463500439753739e-05,
|
| 93 |
+
"loss": 0.5274,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.5716955721078526,
|
| 98 |
+
"grad_norm": 0.9793794751167297,
|
| 99 |
+
"learning_rate": 8.583992963940193e-05,
|
| 100 |
+
"loss": 0.527,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.6156721545776874,
|
| 105 |
+
"grad_norm": 1.096916913986206,
|
| 106 |
+
"learning_rate": 7.704485488126649e-05,
|
| 107 |
+
"loss": 0.5072,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.6596487370475222,
|
| 112 |
+
"grad_norm": 0.9264512062072754,
|
| 113 |
+
"learning_rate": 6.824978012313104e-05,
|
| 114 |
+
"loss": 0.4914,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.703625319517357,
|
| 119 |
+
"grad_norm": 0.8605396151542664,
|
| 120 |
+
"learning_rate": 5.94547053649956e-05,
|
| 121 |
+
"loss": 0.4893,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.7476019019871918,
|
| 126 |
+
"grad_norm": 0.9258248209953308,
|
| 127 |
+
"learning_rate": 5.0659630606860164e-05,
|
| 128 |
+
"loss": 0.4682,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.7915784844570266,
|
| 133 |
+
"grad_norm": 0.962844729423523,
|
| 134 |
+
"learning_rate": 4.186455584872472e-05,
|
| 135 |
+
"loss": 0.4536,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.8355550669268614,
|
| 140 |
+
"grad_norm": 0.933445930480957,
|
| 141 |
+
"learning_rate": 3.306948109058927e-05,
|
| 142 |
+
"loss": 0.4425,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.8795316493966963,
|
| 147 |
+
"grad_norm": 1.0119765996932983,
|
| 148 |
+
"learning_rate": 2.4274406332453827e-05,
|
| 149 |
+
"loss": 0.4259,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.8795316493966963,
|
| 154 |
+
"eval_loss": 0.40038564801216125,
|
| 155 |
+
"eval_runtime": 2826.8322,
|
| 156 |
+
"eval_samples_per_second": 6.156,
|
| 157 |
+
"eval_steps_per_second": 0.77,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.9235082318665311,
|
| 162 |
+
"grad_norm": 0.9877431392669678,
|
| 163 |
+
"learning_rate": 1.547933157431838e-05,
|
| 164 |
+
"loss": 0.4293,
|
| 165 |
+
"step": 1050
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.9674848143363659,
|
| 169 |
+
"grad_norm": 1.011067271232605,
|
| 170 |
+
"learning_rate": 6.684256816182938e-06,
|
| 171 |
+
"loss": 0.425,
|
| 172 |
+
"step": 1100
|
| 173 |
+
}
|
| 174 |
+
],
|
| 175 |
+
"logging_steps": 50,
|
| 176 |
+
"max_steps": 1137,
|
| 177 |
+
"num_input_tokens_seen": 0,
|
| 178 |
+
"num_train_epochs": 1,
|
| 179 |
+
"save_steps": 200,
|
| 180 |
+
"stateful_callbacks": {
|
| 181 |
+
"TrainerControl": {
|
| 182 |
+
"args": {
|
| 183 |
+
"should_epoch_stop": false,
|
| 184 |
+
"should_evaluate": false,
|
| 185 |
+
"should_log": false,
|
| 186 |
+
"should_save": true,
|
| 187 |
+
"should_training_stop": true
|
| 188 |
+
},
|
| 189 |
+
"attributes": {}
|
| 190 |
+
}
|
| 191 |
+
},
|
| 192 |
+
"total_flos": 5.04876904274559e+17,
|
| 193 |
+
"train_batch_size": 2,
|
| 194 |
+
"trial_name": null,
|
| 195 |
+
"trial_params": null
|
| 196 |
+
}
|
checkpoint-1137/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad5efd9de373c20e20b65557dd7b0578f0a7abf507bfa7c7cf14e9c393196c4
|
| 3 |
+
size 5713
|
checkpoint-800/README.md
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Model Card for Model ID
|
| 12 |
+
|
| 13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
## Model Details
|
| 18 |
+
|
| 19 |
+
### Model Description
|
| 20 |
+
|
| 21 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
- **Developed by:** [More Information Needed]
|
| 26 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 27 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 28 |
+
- **Model type:** [More Information Needed]
|
| 29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 30 |
+
- **License:** [More Information Needed]
|
| 31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 32 |
+
|
| 33 |
+
### Model Sources [optional]
|
| 34 |
+
|
| 35 |
+
<!-- Provide the basic links for the model. -->
|
| 36 |
+
|
| 37 |
+
- **Repository:** [More Information Needed]
|
| 38 |
+
- **Paper [optional]:** [More Information Needed]
|
| 39 |
+
- **Demo [optional]:** [More Information Needed]
|
| 40 |
+
|
| 41 |
+
## Uses
|
| 42 |
+
|
| 43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 44 |
+
|
| 45 |
+
### Direct Use
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Downstream Use [optional]
|
| 52 |
+
|
| 53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
### Out-of-Scope Use
|
| 58 |
+
|
| 59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
## Bias, Risks, and Limitations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
+
|
| 67 |
+
[More Information Needed]
|
| 68 |
+
|
| 69 |
+
### Recommendations
|
| 70 |
+
|
| 71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 72 |
+
|
| 73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 74 |
+
|
| 75 |
+
## How to Get Started with the Model
|
| 76 |
+
|
| 77 |
+
Use the code below to get started with the model.
|
| 78 |
+
|
| 79 |
+
[More Information Needed]
|
| 80 |
+
|
| 81 |
+
## Training Details
|
| 82 |
+
|
| 83 |
+
### Training Data
|
| 84 |
+
|
| 85 |
+
<!-- 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. -->
|
| 86 |
+
|
| 87 |
+
[More Information Needed]
|
| 88 |
+
|
| 89 |
+
### Training Procedure
|
| 90 |
+
|
| 91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 92 |
+
|
| 93 |
+
#### Preprocessing [optional]
|
| 94 |
+
|
| 95 |
+
[More Information Needed]
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
#### Training Hyperparameters
|
| 99 |
+
|
| 100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 101 |
+
|
| 102 |
+
#### Speeds, Sizes, Times [optional]
|
| 103 |
+
|
| 104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 105 |
+
|
| 106 |
+
[More Information Needed]
|
| 107 |
+
|
| 108 |
+
## Evaluation
|
| 109 |
+
|
| 110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 111 |
+
|
| 112 |
+
### Testing Data, Factors & Metrics
|
| 113 |
+
|
| 114 |
+
#### Testing Data
|
| 115 |
+
|
| 116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Factors
|
| 121 |
+
|
| 122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
#### Metrics
|
| 127 |
+
|
| 128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 129 |
+
|
| 130 |
+
[More Information Needed]
|
| 131 |
+
|
| 132 |
+
### Results
|
| 133 |
+
|
| 134 |
+
[More Information Needed]
|
| 135 |
+
|
| 136 |
+
#### Summary
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
## Model Examination [optional]
|
| 141 |
+
|
| 142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 143 |
+
|
| 144 |
+
[More Information Needed]
|
| 145 |
+
|
| 146 |
+
## Environmental Impact
|
| 147 |
+
|
| 148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 149 |
+
|
| 150 |
+
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).
|
| 151 |
+
|
| 152 |
+
- **Hardware Type:** [More Information Needed]
|
| 153 |
+
- **Hours used:** [More Information Needed]
|
| 154 |
+
- **Cloud Provider:** [More Information Needed]
|
| 155 |
+
- **Compute Region:** [More Information Needed]
|
| 156 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 157 |
+
|
| 158 |
+
## Technical Specifications [optional]
|
| 159 |
+
|
| 160 |
+
### Model Architecture and Objective
|
| 161 |
+
|
| 162 |
+
[More Information Needed]
|
| 163 |
+
|
| 164 |
+
### Compute Infrastructure
|
| 165 |
+
|
| 166 |
+
[More Information Needed]
|
| 167 |
+
|
| 168 |
+
#### Hardware
|
| 169 |
+
|
| 170 |
+
[More Information Needed]
|
| 171 |
+
|
| 172 |
+
#### Software
|
| 173 |
+
|
| 174 |
+
[More Information Needed]
|
| 175 |
+
|
| 176 |
+
## Citation [optional]
|
| 177 |
+
|
| 178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 179 |
+
|
| 180 |
+
**BibTeX:**
|
| 181 |
+
|
| 182 |
+
[More Information Needed]
|
| 183 |
+
|
| 184 |
+
**APA:**
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## Glossary [optional]
|
| 189 |
+
|
| 190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 191 |
+
|
| 192 |
+
[More Information Needed]
|
| 193 |
+
|
| 194 |
+
## More Information [optional]
|
| 195 |
+
|
| 196 |
+
[More Information Needed]
|
| 197 |
+
|
| 198 |
+
## Model Card Authors [optional]
|
| 199 |
+
|
| 200 |
+
[More Information Needed]
|
| 201 |
+
|
| 202 |
+
## Model Card Contact
|
| 203 |
+
|
| 204 |
+
[More Information Needed]
|
| 205 |
+
### Framework versions
|
| 206 |
+
|
| 207 |
+
- PEFT 0.17.1
|
checkpoint-800/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 64,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"q_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"k_proj"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-800/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e1103e467166422bc511a78111f32ae4747f39da3fe50aec118e5f8ecac17d5
|
| 3 |
+
size 218138576
|
checkpoint-800/chat_template.jinja
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if messages[0]["role"] == "system" %}
|
| 2 |
+
{%- set system_message = messages[0]["content"] %}
|
| 3 |
+
{%- set loop_messages = messages[1:] %}
|
| 4 |
+
{%- else %}
|
| 5 |
+
{%- set loop_messages = messages %}
|
| 6 |
+
{%- endif %}
|
| 7 |
+
{%- if not tools is defined %}
|
| 8 |
+
{%- set tools = none %}
|
| 9 |
+
{%- endif %}
|
| 10 |
+
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
|
| 11 |
+
|
| 12 |
+
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
|
| 13 |
+
{%- set ns = namespace() %}
|
| 14 |
+
{%- set ns.index = 0 %}
|
| 15 |
+
{%- for message in loop_messages %}
|
| 16 |
+
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
|
| 17 |
+
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
|
| 18 |
+
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- set ns.index = ns.index + 1 %}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
{%- endfor %}
|
| 23 |
+
|
| 24 |
+
{{- bos_token }}
|
| 25 |
+
{%- for message in loop_messages %}
|
| 26 |
+
{%- if message["role"] == "user" %}
|
| 27 |
+
{%- if tools is not none and (message == user_messages[-1]) %}
|
| 28 |
+
{{- "[AVAILABLE_TOOLS] [" }}
|
| 29 |
+
{%- for tool in tools %}
|
| 30 |
+
{%- set tool = tool.function %}
|
| 31 |
+
{{- '{"type": "function", "function": {' }}
|
| 32 |
+
{%- for key, val in tool.items() if key != "return" %}
|
| 33 |
+
{%- if val is string %}
|
| 34 |
+
{{- '"' + key + '": "' + val + '"' }}
|
| 35 |
+
{%- else %}
|
| 36 |
+
{{- '"' + key + '": ' + val|tojson }}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- if not loop.last %}
|
| 39 |
+
{{- ", " }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endfor %}
|
| 42 |
+
{{- "}}" }}
|
| 43 |
+
{%- if not loop.last %}
|
| 44 |
+
{{- ", " }}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- "]" }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- endfor %}
|
| 49 |
+
{{- "[/AVAILABLE_TOOLS]" }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- if loop.last and system_message is defined %}
|
| 52 |
+
{{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
|
| 53 |
+
{%- else %}
|
| 54 |
+
{{- "[INST] " + message["content"] + "[/INST]" }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- elif message.tool_calls is defined and message.tool_calls is not none %}
|
| 57 |
+
{{- "[TOOL_CALLS] [" }}
|
| 58 |
+
{%- for tool_call in message.tool_calls %}
|
| 59 |
+
{%- set out = tool_call.function|tojson %}
|
| 60 |
+
{{- out[:-1] }}
|
| 61 |
+
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
|
| 62 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- ', "id": "' + tool_call.id + '"}' }}
|
| 65 |
+
{%- if not loop.last %}
|
| 66 |
+
{{- ", " }}
|
| 67 |
+
{%- else %}
|
| 68 |
+
{{- "]" + eos_token }}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- endfor %}
|
| 71 |
+
{%- elif message["role"] == "assistant" %}
|
| 72 |
+
{{- " " + message["content"]|trim + eos_token}}
|
| 73 |
+
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
| 74 |
+
{%- if message.content is defined and message.content.content is defined %}
|
| 75 |
+
{%- set content = message.content.content %}
|
| 76 |
+
{%- else %}
|
| 77 |
+
{%- set content = message.content %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
|
| 80 |
+
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
|
| 81 |
+
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
|
| 84 |
+
{%- else %}
|
| 85 |
+
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- endfor %}
|
checkpoint-800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab2dd38301d5e39338dc7f64ab08788d0566063463c313ff9943565ae38cf320
|
| 3 |
+
size 436427467
|
checkpoint-800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71ea7f4f107f2d5dcb9621b0c4dbd925b7771af849bd834c08842893dfe1bbd5
|
| 3 |
+
size 14645
|
checkpoint-800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9621f4795a63d0fac9c939ead66bf695f75354e73efd0b5f6e02b2c9dce72d57
|
| 3 |
+
size 1465
|
checkpoint-800/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-800/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-800/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
| 3 |
+
size 587404
|
checkpoint-800/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-800/trainer_state.json
ADDED
|
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.703625319517357,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 800,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.04397658246983481,
|
| 14 |
+
"grad_norm": 1.0395877361297607,
|
| 15 |
+
"learning_rate": 0.00019138082673702725,
|
| 16 |
+
"loss": 1.3457,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.08795316493966962,
|
| 21 |
+
"grad_norm": 1.0277217626571655,
|
| 22 |
+
"learning_rate": 0.00018258575197889184,
|
| 23 |
+
"loss": 1.0388,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.13192974740950444,
|
| 28 |
+
"grad_norm": 0.9229634404182434,
|
| 29 |
+
"learning_rate": 0.0001737906772207564,
|
| 30 |
+
"loss": 0.9245,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.17590632987933924,
|
| 35 |
+
"grad_norm": 0.8828799724578857,
|
| 36 |
+
"learning_rate": 0.00016499560246262094,
|
| 37 |
+
"loss": 0.8399,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.21988291234917406,
|
| 42 |
+
"grad_norm": 1.018609642982483,
|
| 43 |
+
"learning_rate": 0.0001562005277044855,
|
| 44 |
+
"loss": 0.8015,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2638594948190089,
|
| 49 |
+
"grad_norm": 0.9031912684440613,
|
| 50 |
+
"learning_rate": 0.00014740545294635005,
|
| 51 |
+
"loss": 0.7248,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.3078360772888437,
|
| 56 |
+
"grad_norm": 0.8781272768974304,
|
| 57 |
+
"learning_rate": 0.0001386103781882146,
|
| 58 |
+
"loss": 0.684,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.3518126597586785,
|
| 63 |
+
"grad_norm": 0.8193464279174805,
|
| 64 |
+
"learning_rate": 0.00012981530343007916,
|
| 65 |
+
"loss": 0.6587,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.3957892422285133,
|
| 70 |
+
"grad_norm": 0.84972083568573,
|
| 71 |
+
"learning_rate": 0.00012102022867194372,
|
| 72 |
+
"loss": 0.6357,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.43976582469834813,
|
| 77 |
+
"grad_norm": 0.9738919734954834,
|
| 78 |
+
"learning_rate": 0.00011222515391380828,
|
| 79 |
+
"loss": 0.6107,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.48374240716818295,
|
| 84 |
+
"grad_norm": 0.9879764318466187,
|
| 85 |
+
"learning_rate": 0.00010343007915567282,
|
| 86 |
+
"loss": 0.573,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5277189896380178,
|
| 91 |
+
"grad_norm": 0.9049842953681946,
|
| 92 |
+
"learning_rate": 9.463500439753739e-05,
|
| 93 |
+
"loss": 0.5274,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.5716955721078526,
|
| 98 |
+
"grad_norm": 0.9793794751167297,
|
| 99 |
+
"learning_rate": 8.583992963940193e-05,
|
| 100 |
+
"loss": 0.527,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.6156721545776874,
|
| 105 |
+
"grad_norm": 1.096916913986206,
|
| 106 |
+
"learning_rate": 7.704485488126649e-05,
|
| 107 |
+
"loss": 0.5072,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.6596487370475222,
|
| 112 |
+
"grad_norm": 0.9264512062072754,
|
| 113 |
+
"learning_rate": 6.824978012313104e-05,
|
| 114 |
+
"loss": 0.4914,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.703625319517357,
|
| 119 |
+
"grad_norm": 0.8605396151542664,
|
| 120 |
+
"learning_rate": 5.94547053649956e-05,
|
| 121 |
+
"loss": 0.4893,
|
| 122 |
+
"step": 800
|
| 123 |
+
}
|
| 124 |
+
],
|
| 125 |
+
"logging_steps": 50,
|
| 126 |
+
"max_steps": 1137,
|
| 127 |
+
"num_input_tokens_seen": 0,
|
| 128 |
+
"num_train_epochs": 1,
|
| 129 |
+
"save_steps": 200,
|
| 130 |
+
"stateful_callbacks": {
|
| 131 |
+
"TrainerControl": {
|
| 132 |
+
"args": {
|
| 133 |
+
"should_epoch_stop": false,
|
| 134 |
+
"should_evaluate": false,
|
| 135 |
+
"should_log": false,
|
| 136 |
+
"should_save": true,
|
| 137 |
+
"should_training_stop": false
|
| 138 |
+
},
|
| 139 |
+
"attributes": {}
|
| 140 |
+
}
|
| 141 |
+
},
|
| 142 |
+
"total_flos": 3.5520273893154816e+17,
|
| 143 |
+
"train_batch_size": 2,
|
| 144 |
+
"trial_name": null,
|
| 145 |
+
"trial_params": null
|
| 146 |
+
}
|
checkpoint-800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad5efd9de373c20e20b65557dd7b0578f0a7abf507bfa7c7cf14e9c393196c4
|
| 3 |
+
size 5713
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
| 3 |
+
size 587404
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aad5efd9de373c20e20b65557dd7b0578f0a7abf507bfa7c7cf14e9c393196c4
|
| 3 |
+
size 5713
|