Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- Area/checkpoint-100/optimizer.pt +3 -0
- Area/checkpoint-50/adapter_model.safetensors +3 -0
- Area/checkpoint-580/adapter_model.safetensors +3 -0
- Area_SFT/checkpoint-100/README.md +202 -0
- Area_SFT/checkpoint-100/adapter_config.json +34 -0
- Area_SFT/checkpoint-100/added_tokens.json +3 -0
- Area_SFT/checkpoint-100/special_tokens_map.json +36 -0
- Area_SFT/checkpoint-100/tokenizer.json +0 -0
- Area_SFT/checkpoint-100/tokenizer_config.json +59 -0
- Area_SFT/checkpoint-100/trainer_state.json +183 -0
- Area_SFT/checkpoint-150/README.md +202 -0
- Area_SFT/checkpoint-150/adapter_config.json +34 -0
- Area_SFT/checkpoint-150/added_tokens.json +3 -0
- Area_SFT/checkpoint-150/special_tokens_map.json +36 -0
- Area_SFT/checkpoint-150/tokenizer.json +0 -0
- Area_SFT/checkpoint-150/tokenizer_config.json +59 -0
- Area_SFT/checkpoint-150/trainer_state.json +258 -0
- Area_SFT/checkpoint-200/README.md +202 -0
- Area_SFT/checkpoint-200/adapter_config.json +34 -0
- Area_SFT/checkpoint-200/added_tokens.json +3 -0
- Area_SFT/checkpoint-200/special_tokens_map.json +36 -0
- Area_SFT/checkpoint-200/tokenizer.json +0 -0
- Area_SFT/checkpoint-200/tokenizer_config.json +59 -0
- Area_SFT/checkpoint-200/trainer_state.json +333 -0
- Area_SFT/checkpoint-250/README.md +202 -0
- Area_SFT/checkpoint-250/adapter_config.json +34 -0
- Area_SFT/checkpoint-250/added_tokens.json +3 -0
- Area_SFT/checkpoint-250/special_tokens_map.json +36 -0
- Area_SFT/checkpoint-250/tokenizer.json +0 -0
- Area_SFT/checkpoint-250/tokenizer_config.json +59 -0
- Area_SFT/checkpoint-250/trainer_state.json +408 -0
- Area_SFT/checkpoint-300/README.md +202 -0
- Area_SFT/checkpoint-300/adapter_config.json +34 -0
- Area_SFT/checkpoint-300/added_tokens.json +3 -0
- Area_SFT/checkpoint-300/special_tokens_map.json +36 -0
- Area_SFT/checkpoint-300/tokenizer.json +0 -0
- Area_SFT/checkpoint-300/tokenizer_config.json +59 -0
- Area_SFT/checkpoint-300/trainer_state.json +483 -0
- Area_SFT/checkpoint-350/README.md +202 -0
- Area_SFT/checkpoint-350/adapter_config.json +34 -0
- Area_SFT/checkpoint-350/added_tokens.json +3 -0
- Area_SFT/checkpoint-350/special_tokens_map.json +36 -0
- Area_SFT/checkpoint-350/tokenizer.json +0 -0
- Area_SFT/checkpoint-350/tokenizer_config.json +59 -0
- Area_SFT/checkpoint-350/trainer_state.json +558 -0
- Area_SFT/checkpoint-400/README.md +202 -0
- Area_SFT/checkpoint-400/adapter_config.json +34 -0
- Area_SFT/checkpoint-400/added_tokens.json +3 -0
- Area_SFT/checkpoint-400/special_tokens_map.json +36 -0
- Area_SFT/checkpoint-400/tokenizer.json +0 -0
Area/checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c0acffe8ac3005d62ee621658591de4b90467f3336040e8e73cbff067b73283
|
| 3 |
+
size 160284754
|
Area/checkpoint-50/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a616df61401760478b3e0e95dbad47ee8e26710cce302876b13d77b343fd007f
|
| 3 |
+
size 80013120
|
Area/checkpoint-580/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b73e6974aedd91139db9a6295fe14101c4ca32bc798f6e67c627c7e322a518f9
|
| 3 |
+
size 80013120
|
Area_SFT/checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- 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. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
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).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_SFT/checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"q_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_SFT/checkpoint-100/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Area_SFT/checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
Area_SFT/checkpoint-100/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_SFT/checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"additional_special_tokens": [
|
| 40 |
+
"<unk>",
|
| 41 |
+
"<s>",
|
| 42 |
+
"</s>",
|
| 43 |
+
"[PAD]"
|
| 44 |
+
],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"legacy": true,
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"padding_side": "right",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"spaces_between_special_tokens": false,
|
| 55 |
+
"split_special_tokens": false,
|
| 56 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 57 |
+
"unk_token": "<unk>",
|
| 58 |
+
"use_default_system_prompt": true
|
| 59 |
+
}
|
Area_SFT/checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.3472803347280333,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33472803347280333,
|
| 13 |
+
"grad_norm": 3.9892160892486572,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": -2.315223217010498,
|
| 16 |
+
"logits/rejected": -2.3654401302337646,
|
| 17 |
+
"logps/chosen": -65.86729431152344,
|
| 18 |
+
"logps/rejected": -77.53572845458984,
|
| 19 |
+
"loss": 0.6929,
|
| 20 |
+
"rewards/accuracies": 0.3499999940395355,
|
| 21 |
+
"rewards/chosen": 0.0023138518445193768,
|
| 22 |
+
"rewards/margins": -0.001122759305872023,
|
| 23 |
+
"rewards/rejected": 0.0034366101026535034,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6694560669456067,
|
| 28 |
+
"grad_norm": 3.5659756660461426,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": -2.341399669647217,
|
| 31 |
+
"logits/rejected": -2.3567094802856445,
|
| 32 |
+
"logps/chosen": -66.60242462158203,
|
| 33 |
+
"logps/rejected": -69.70094299316406,
|
| 34 |
+
"loss": 0.6929,
|
| 35 |
+
"rewards/accuracies": 0.512499988079071,
|
| 36 |
+
"rewards/chosen": -0.0013719359412789345,
|
| 37 |
+
"rewards/margins": -0.0035000313073396683,
|
| 38 |
+
"rewards/rejected": 0.002128095831722021,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.00418410041841,
|
| 43 |
+
"grad_norm": 4.912586688995361,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": -2.3429622650146484,
|
| 46 |
+
"logits/rejected": -2.3658394813537598,
|
| 47 |
+
"logps/chosen": -71.6301040649414,
|
| 48 |
+
"logps/rejected": -78.41346740722656,
|
| 49 |
+
"loss": 0.6938,
|
| 50 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 51 |
+
"rewards/chosen": 0.003577103139832616,
|
| 52 |
+
"rewards/margins": 0.00785654503852129,
|
| 53 |
+
"rewards/rejected": -0.004279441200196743,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.3389121338912133,
|
| 58 |
+
"grad_norm": 4.810107707977295,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": -2.3610458374023438,
|
| 61 |
+
"logits/rejected": -2.3885395526885986,
|
| 62 |
+
"logps/chosen": -66.8291244506836,
|
| 63 |
+
"logps/rejected": -62.15415573120117,
|
| 64 |
+
"loss": 0.6893,
|
| 65 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 66 |
+
"rewards/chosen": -6.734435737598687e-05,
|
| 67 |
+
"rewards/margins": 0.006865750066936016,
|
| 68 |
+
"rewards/rejected": -0.0069330958649516106,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6736401673640167,
|
| 73 |
+
"grad_norm": 4.670071125030518,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": -2.304999351501465,
|
| 76 |
+
"logits/rejected": -2.335301399230957,
|
| 77 |
+
"logps/chosen": -75.09913635253906,
|
| 78 |
+
"logps/rejected": -77.72399139404297,
|
| 79 |
+
"loss": 0.6878,
|
| 80 |
+
"rewards/accuracies": 0.612500011920929,
|
| 81 |
+
"rewards/chosen": 0.003225918160751462,
|
| 82 |
+
"rewards/margins": 0.010454346425831318,
|
| 83 |
+
"rewards/rejected": -0.007228427566587925,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.00836820083682,
|
| 88 |
+
"grad_norm": 4.2342000007629395,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": -2.363574504852295,
|
| 91 |
+
"logits/rejected": -2.363882064819336,
|
| 92 |
+
"logps/chosen": -62.84125900268555,
|
| 93 |
+
"logps/rejected": -61.92932891845703,
|
| 94 |
+
"loss": 0.6855,
|
| 95 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 96 |
+
"rewards/chosen": -0.0032769464887678623,
|
| 97 |
+
"rewards/margins": 0.02090405486524105,
|
| 98 |
+
"rewards/rejected": -0.024181004613637924,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3430962343096233,
|
| 103 |
+
"grad_norm": 4.369245529174805,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": -2.378016948699951,
|
| 106 |
+
"logits/rejected": -2.373137950897217,
|
| 107 |
+
"logps/chosen": -74.67327880859375,
|
| 108 |
+
"logps/rejected": -69.20399475097656,
|
| 109 |
+
"loss": 0.668,
|
| 110 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 111 |
+
"rewards/chosen": -0.0003526444488670677,
|
| 112 |
+
"rewards/margins": 0.04865006357431412,
|
| 113 |
+
"rewards/rejected": -0.04900271072983742,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.6778242677824267,
|
| 118 |
+
"grad_norm": 4.444687366485596,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": -2.3403103351593018,
|
| 121 |
+
"logits/rejected": -2.370321273803711,
|
| 122 |
+
"logps/chosen": -77.29728698730469,
|
| 123 |
+
"logps/rejected": -85.79756164550781,
|
| 124 |
+
"loss": 0.6566,
|
| 125 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 126 |
+
"rewards/chosen": 0.0051120575517416,
|
| 127 |
+
"rewards/margins": 0.09415190666913986,
|
| 128 |
+
"rewards/rejected": -0.08903985470533371,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.01255230125523,
|
| 133 |
+
"grad_norm": 4.876573085784912,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": -2.3614611625671387,
|
| 136 |
+
"logits/rejected": -2.385697841644287,
|
| 137 |
+
"logps/chosen": -73.22442626953125,
|
| 138 |
+
"logps/rejected": -82.25682067871094,
|
| 139 |
+
"loss": 0.645,
|
| 140 |
+
"rewards/accuracies": 0.800000011920929,
|
| 141 |
+
"rewards/chosen": -0.016868198290467262,
|
| 142 |
+
"rewards/margins": 0.10679063946008682,
|
| 143 |
+
"rewards/rejected": -0.12365883588790894,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3472803347280333,
|
| 148 |
+
"grad_norm": 4.355966567993164,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": -2.323256254196167,
|
| 151 |
+
"logits/rejected": -2.341057300567627,
|
| 152 |
+
"logps/chosen": -78.37105560302734,
|
| 153 |
+
"logps/rejected": -86.8406982421875,
|
| 154 |
+
"loss": 0.6072,
|
| 155 |
+
"rewards/accuracies": 0.824999988079071,
|
| 156 |
+
"rewards/chosen": -0.015012519434094429,
|
| 157 |
+
"rewards/margins": 0.20561759173870087,
|
| 158 |
+
"rewards/rejected": -0.22063009440898895,
|
| 159 |
+
"step": 100
|
| 160 |
+
}
|
| 161 |
+
],
|
| 162 |
+
"logging_steps": 10,
|
| 163 |
+
"max_steps": 580,
|
| 164 |
+
"num_input_tokens_seen": 0,
|
| 165 |
+
"num_train_epochs": 20,
|
| 166 |
+
"save_steps": 50,
|
| 167 |
+
"stateful_callbacks": {
|
| 168 |
+
"TrainerControl": {
|
| 169 |
+
"args": {
|
| 170 |
+
"should_epoch_stop": false,
|
| 171 |
+
"should_evaluate": false,
|
| 172 |
+
"should_log": false,
|
| 173 |
+
"should_save": true,
|
| 174 |
+
"should_training_stop": false
|
| 175 |
+
},
|
| 176 |
+
"attributes": {}
|
| 177 |
+
}
|
| 178 |
+
},
|
| 179 |
+
"total_flos": 3.6741388786938675e+17,
|
| 180 |
+
"train_batch_size": 1,
|
| 181 |
+
"trial_name": null,
|
| 182 |
+
"trial_params": null
|
| 183 |
+
}
|
Area_SFT/checkpoint-150/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- 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. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
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).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_SFT/checkpoint-150/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_SFT/checkpoint-150/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Area_SFT/checkpoint-150/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
Area_SFT/checkpoint-150/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_SFT/checkpoint-150/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"additional_special_tokens": [
|
| 40 |
+
"<unk>",
|
| 41 |
+
"<s>",
|
| 42 |
+
"</s>",
|
| 43 |
+
"[PAD]"
|
| 44 |
+
],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"legacy": true,
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"padding_side": "right",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"spaces_between_special_tokens": false,
|
| 55 |
+
"split_special_tokens": false,
|
| 56 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 57 |
+
"unk_token": "<unk>",
|
| 58 |
+
"use_default_system_prompt": true
|
| 59 |
+
}
|
Area_SFT/checkpoint-150/trainer_state.json
ADDED
|
@@ -0,0 +1,258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.108786610878661,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 150,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33472803347280333,
|
| 13 |
+
"grad_norm": 3.9892160892486572,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": -2.315223217010498,
|
| 16 |
+
"logits/rejected": -2.3654401302337646,
|
| 17 |
+
"logps/chosen": -65.86729431152344,
|
| 18 |
+
"logps/rejected": -77.53572845458984,
|
| 19 |
+
"loss": 0.6929,
|
| 20 |
+
"rewards/accuracies": 0.3499999940395355,
|
| 21 |
+
"rewards/chosen": 0.0023138518445193768,
|
| 22 |
+
"rewards/margins": -0.001122759305872023,
|
| 23 |
+
"rewards/rejected": 0.0034366101026535034,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6694560669456067,
|
| 28 |
+
"grad_norm": 3.5659756660461426,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": -2.341399669647217,
|
| 31 |
+
"logits/rejected": -2.3567094802856445,
|
| 32 |
+
"logps/chosen": -66.60242462158203,
|
| 33 |
+
"logps/rejected": -69.70094299316406,
|
| 34 |
+
"loss": 0.6929,
|
| 35 |
+
"rewards/accuracies": 0.512499988079071,
|
| 36 |
+
"rewards/chosen": -0.0013719359412789345,
|
| 37 |
+
"rewards/margins": -0.0035000313073396683,
|
| 38 |
+
"rewards/rejected": 0.002128095831722021,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.00418410041841,
|
| 43 |
+
"grad_norm": 4.912586688995361,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": -2.3429622650146484,
|
| 46 |
+
"logits/rejected": -2.3658394813537598,
|
| 47 |
+
"logps/chosen": -71.6301040649414,
|
| 48 |
+
"logps/rejected": -78.41346740722656,
|
| 49 |
+
"loss": 0.6938,
|
| 50 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 51 |
+
"rewards/chosen": 0.003577103139832616,
|
| 52 |
+
"rewards/margins": 0.00785654503852129,
|
| 53 |
+
"rewards/rejected": -0.004279441200196743,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.3389121338912133,
|
| 58 |
+
"grad_norm": 4.810107707977295,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": -2.3610458374023438,
|
| 61 |
+
"logits/rejected": -2.3885395526885986,
|
| 62 |
+
"logps/chosen": -66.8291244506836,
|
| 63 |
+
"logps/rejected": -62.15415573120117,
|
| 64 |
+
"loss": 0.6893,
|
| 65 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 66 |
+
"rewards/chosen": -6.734435737598687e-05,
|
| 67 |
+
"rewards/margins": 0.006865750066936016,
|
| 68 |
+
"rewards/rejected": -0.0069330958649516106,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6736401673640167,
|
| 73 |
+
"grad_norm": 4.670071125030518,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": -2.304999351501465,
|
| 76 |
+
"logits/rejected": -2.335301399230957,
|
| 77 |
+
"logps/chosen": -75.09913635253906,
|
| 78 |
+
"logps/rejected": -77.72399139404297,
|
| 79 |
+
"loss": 0.6878,
|
| 80 |
+
"rewards/accuracies": 0.612500011920929,
|
| 81 |
+
"rewards/chosen": 0.003225918160751462,
|
| 82 |
+
"rewards/margins": 0.010454346425831318,
|
| 83 |
+
"rewards/rejected": -0.007228427566587925,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.00836820083682,
|
| 88 |
+
"grad_norm": 4.2342000007629395,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": -2.363574504852295,
|
| 91 |
+
"logits/rejected": -2.363882064819336,
|
| 92 |
+
"logps/chosen": -62.84125900268555,
|
| 93 |
+
"logps/rejected": -61.92932891845703,
|
| 94 |
+
"loss": 0.6855,
|
| 95 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 96 |
+
"rewards/chosen": -0.0032769464887678623,
|
| 97 |
+
"rewards/margins": 0.02090405486524105,
|
| 98 |
+
"rewards/rejected": -0.024181004613637924,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3430962343096233,
|
| 103 |
+
"grad_norm": 4.369245529174805,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": -2.378016948699951,
|
| 106 |
+
"logits/rejected": -2.373137950897217,
|
| 107 |
+
"logps/chosen": -74.67327880859375,
|
| 108 |
+
"logps/rejected": -69.20399475097656,
|
| 109 |
+
"loss": 0.668,
|
| 110 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 111 |
+
"rewards/chosen": -0.0003526444488670677,
|
| 112 |
+
"rewards/margins": 0.04865006357431412,
|
| 113 |
+
"rewards/rejected": -0.04900271072983742,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.6778242677824267,
|
| 118 |
+
"grad_norm": 4.444687366485596,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": -2.3403103351593018,
|
| 121 |
+
"logits/rejected": -2.370321273803711,
|
| 122 |
+
"logps/chosen": -77.29728698730469,
|
| 123 |
+
"logps/rejected": -85.79756164550781,
|
| 124 |
+
"loss": 0.6566,
|
| 125 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 126 |
+
"rewards/chosen": 0.0051120575517416,
|
| 127 |
+
"rewards/margins": 0.09415190666913986,
|
| 128 |
+
"rewards/rejected": -0.08903985470533371,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.01255230125523,
|
| 133 |
+
"grad_norm": 4.876573085784912,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": -2.3614611625671387,
|
| 136 |
+
"logits/rejected": -2.385697841644287,
|
| 137 |
+
"logps/chosen": -73.22442626953125,
|
| 138 |
+
"logps/rejected": -82.25682067871094,
|
| 139 |
+
"loss": 0.645,
|
| 140 |
+
"rewards/accuracies": 0.800000011920929,
|
| 141 |
+
"rewards/chosen": -0.016868198290467262,
|
| 142 |
+
"rewards/margins": 0.10679063946008682,
|
| 143 |
+
"rewards/rejected": -0.12365883588790894,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3472803347280333,
|
| 148 |
+
"grad_norm": 4.355966567993164,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": -2.323256254196167,
|
| 151 |
+
"logits/rejected": -2.341057300567627,
|
| 152 |
+
"logps/chosen": -78.37105560302734,
|
| 153 |
+
"logps/rejected": -86.8406982421875,
|
| 154 |
+
"loss": 0.6072,
|
| 155 |
+
"rewards/accuracies": 0.824999988079071,
|
| 156 |
+
"rewards/chosen": -0.015012519434094429,
|
| 157 |
+
"rewards/margins": 0.20561759173870087,
|
| 158 |
+
"rewards/rejected": -0.22063009440898895,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7698744769874475,
|
| 163 |
+
"grad_norm": 4.361391067504883,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": -2.3163838386535645,
|
| 166 |
+
"logits/rejected": -2.3566031455993652,
|
| 167 |
+
"logps/chosen": -83.33145904541016,
|
| 168 |
+
"logps/rejected": -96.48517608642578,
|
| 169 |
+
"loss": 0.5908,
|
| 170 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 171 |
+
"rewards/chosen": -0.08870697021484375,
|
| 172 |
+
"rewards/margins": 0.24879300594329834,
|
| 173 |
+
"rewards/rejected": -0.3374999761581421,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.104602510460251,
|
| 178 |
+
"grad_norm": 4.315061569213867,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": -2.3728129863739014,
|
| 181 |
+
"logits/rejected": -2.3889667987823486,
|
| 182 |
+
"logps/chosen": -73.0484619140625,
|
| 183 |
+
"logps/rejected": -73.4913558959961,
|
| 184 |
+
"loss": 0.5783,
|
| 185 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 186 |
+
"rewards/chosen": -0.0605628564953804,
|
| 187 |
+
"rewards/margins": 0.2945060133934021,
|
| 188 |
+
"rewards/rejected": -0.3550689220428467,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.439330543933054,
|
| 193 |
+
"grad_norm": 4.438860893249512,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": -2.3526523113250732,
|
| 196 |
+
"logits/rejected": -2.364795684814453,
|
| 197 |
+
"logps/chosen": -67.69630432128906,
|
| 198 |
+
"logps/rejected": -84.85731506347656,
|
| 199 |
+
"loss": 0.5338,
|
| 200 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 201 |
+
"rewards/chosen": -0.1054786667227745,
|
| 202 |
+
"rewards/margins": 0.4161924421787262,
|
| 203 |
+
"rewards/rejected": -0.5216711759567261,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.7740585774058575,
|
| 208 |
+
"grad_norm": 4.5405473709106445,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": -2.3756489753723145,
|
| 211 |
+
"logits/rejected": -2.374919891357422,
|
| 212 |
+
"logps/chosen": -68.5466079711914,
|
| 213 |
+
"logps/rejected": -76.15412902832031,
|
| 214 |
+
"loss": 0.5215,
|
| 215 |
+
"rewards/accuracies": 0.824999988079071,
|
| 216 |
+
"rewards/chosen": -0.16213981807231903,
|
| 217 |
+
"rewards/margins": 0.47565969824790955,
|
| 218 |
+
"rewards/rejected": -0.6377995610237122,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.108786610878661,
|
| 223 |
+
"grad_norm": 4.596691608428955,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": -2.428659439086914,
|
| 226 |
+
"logits/rejected": -2.4141571521759033,
|
| 227 |
+
"logps/chosen": -78.08479309082031,
|
| 228 |
+
"logps/rejected": -68.3617172241211,
|
| 229 |
+
"loss": 0.5019,
|
| 230 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 231 |
+
"rewards/chosen": -0.20662447810173035,
|
| 232 |
+
"rewards/margins": 0.4026559889316559,
|
| 233 |
+
"rewards/rejected": -0.6092804670333862,
|
| 234 |
+
"step": 150
|
| 235 |
+
}
|
| 236 |
+
],
|
| 237 |
+
"logging_steps": 10,
|
| 238 |
+
"max_steps": 580,
|
| 239 |
+
"num_input_tokens_seen": 0,
|
| 240 |
+
"num_train_epochs": 20,
|
| 241 |
+
"save_steps": 50,
|
| 242 |
+
"stateful_callbacks": {
|
| 243 |
+
"TrainerControl": {
|
| 244 |
+
"args": {
|
| 245 |
+
"should_epoch_stop": false,
|
| 246 |
+
"should_evaluate": false,
|
| 247 |
+
"should_log": false,
|
| 248 |
+
"should_save": true,
|
| 249 |
+
"should_training_stop": false
|
| 250 |
+
},
|
| 251 |
+
"attributes": {}
|
| 252 |
+
}
|
| 253 |
+
},
|
| 254 |
+
"total_flos": 5.5068163274335846e+17,
|
| 255 |
+
"train_batch_size": 1,
|
| 256 |
+
"trial_name": null,
|
| 257 |
+
"trial_params": null
|
| 258 |
+
}
|
Area_SFT/checkpoint-200/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- 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. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
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).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_SFT/checkpoint-200/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_SFT/checkpoint-200/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Area_SFT/checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
Area_SFT/checkpoint-200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_SFT/checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"additional_special_tokens": [
|
| 40 |
+
"<unk>",
|
| 41 |
+
"<s>",
|
| 42 |
+
"</s>",
|
| 43 |
+
"[PAD]"
|
| 44 |
+
],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"legacy": true,
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"padding_side": "right",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"spaces_between_special_tokens": false,
|
| 55 |
+
"split_special_tokens": false,
|
| 56 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 57 |
+
"unk_token": "<unk>",
|
| 58 |
+
"use_default_system_prompt": true
|
| 59 |
+
}
|
Area_SFT/checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,333 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.7824267782426775,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33472803347280333,
|
| 13 |
+
"grad_norm": 3.9892160892486572,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": -2.315223217010498,
|
| 16 |
+
"logits/rejected": -2.3654401302337646,
|
| 17 |
+
"logps/chosen": -65.86729431152344,
|
| 18 |
+
"logps/rejected": -77.53572845458984,
|
| 19 |
+
"loss": 0.6929,
|
| 20 |
+
"rewards/accuracies": 0.3499999940395355,
|
| 21 |
+
"rewards/chosen": 0.0023138518445193768,
|
| 22 |
+
"rewards/margins": -0.001122759305872023,
|
| 23 |
+
"rewards/rejected": 0.0034366101026535034,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6694560669456067,
|
| 28 |
+
"grad_norm": 3.5659756660461426,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": -2.341399669647217,
|
| 31 |
+
"logits/rejected": -2.3567094802856445,
|
| 32 |
+
"logps/chosen": -66.60242462158203,
|
| 33 |
+
"logps/rejected": -69.70094299316406,
|
| 34 |
+
"loss": 0.6929,
|
| 35 |
+
"rewards/accuracies": 0.512499988079071,
|
| 36 |
+
"rewards/chosen": -0.0013719359412789345,
|
| 37 |
+
"rewards/margins": -0.0035000313073396683,
|
| 38 |
+
"rewards/rejected": 0.002128095831722021,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.00418410041841,
|
| 43 |
+
"grad_norm": 4.912586688995361,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": -2.3429622650146484,
|
| 46 |
+
"logits/rejected": -2.3658394813537598,
|
| 47 |
+
"logps/chosen": -71.6301040649414,
|
| 48 |
+
"logps/rejected": -78.41346740722656,
|
| 49 |
+
"loss": 0.6938,
|
| 50 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 51 |
+
"rewards/chosen": 0.003577103139832616,
|
| 52 |
+
"rewards/margins": 0.00785654503852129,
|
| 53 |
+
"rewards/rejected": -0.004279441200196743,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.3389121338912133,
|
| 58 |
+
"grad_norm": 4.810107707977295,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": -2.3610458374023438,
|
| 61 |
+
"logits/rejected": -2.3885395526885986,
|
| 62 |
+
"logps/chosen": -66.8291244506836,
|
| 63 |
+
"logps/rejected": -62.15415573120117,
|
| 64 |
+
"loss": 0.6893,
|
| 65 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 66 |
+
"rewards/chosen": -6.734435737598687e-05,
|
| 67 |
+
"rewards/margins": 0.006865750066936016,
|
| 68 |
+
"rewards/rejected": -0.0069330958649516106,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6736401673640167,
|
| 73 |
+
"grad_norm": 4.670071125030518,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": -2.304999351501465,
|
| 76 |
+
"logits/rejected": -2.335301399230957,
|
| 77 |
+
"logps/chosen": -75.09913635253906,
|
| 78 |
+
"logps/rejected": -77.72399139404297,
|
| 79 |
+
"loss": 0.6878,
|
| 80 |
+
"rewards/accuracies": 0.612500011920929,
|
| 81 |
+
"rewards/chosen": 0.003225918160751462,
|
| 82 |
+
"rewards/margins": 0.010454346425831318,
|
| 83 |
+
"rewards/rejected": -0.007228427566587925,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.00836820083682,
|
| 88 |
+
"grad_norm": 4.2342000007629395,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": -2.363574504852295,
|
| 91 |
+
"logits/rejected": -2.363882064819336,
|
| 92 |
+
"logps/chosen": -62.84125900268555,
|
| 93 |
+
"logps/rejected": -61.92932891845703,
|
| 94 |
+
"loss": 0.6855,
|
| 95 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 96 |
+
"rewards/chosen": -0.0032769464887678623,
|
| 97 |
+
"rewards/margins": 0.02090405486524105,
|
| 98 |
+
"rewards/rejected": -0.024181004613637924,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3430962343096233,
|
| 103 |
+
"grad_norm": 4.369245529174805,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": -2.378016948699951,
|
| 106 |
+
"logits/rejected": -2.373137950897217,
|
| 107 |
+
"logps/chosen": -74.67327880859375,
|
| 108 |
+
"logps/rejected": -69.20399475097656,
|
| 109 |
+
"loss": 0.668,
|
| 110 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 111 |
+
"rewards/chosen": -0.0003526444488670677,
|
| 112 |
+
"rewards/margins": 0.04865006357431412,
|
| 113 |
+
"rewards/rejected": -0.04900271072983742,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.6778242677824267,
|
| 118 |
+
"grad_norm": 4.444687366485596,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": -2.3403103351593018,
|
| 121 |
+
"logits/rejected": -2.370321273803711,
|
| 122 |
+
"logps/chosen": -77.29728698730469,
|
| 123 |
+
"logps/rejected": -85.79756164550781,
|
| 124 |
+
"loss": 0.6566,
|
| 125 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 126 |
+
"rewards/chosen": 0.0051120575517416,
|
| 127 |
+
"rewards/margins": 0.09415190666913986,
|
| 128 |
+
"rewards/rejected": -0.08903985470533371,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.01255230125523,
|
| 133 |
+
"grad_norm": 4.876573085784912,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": -2.3614611625671387,
|
| 136 |
+
"logits/rejected": -2.385697841644287,
|
| 137 |
+
"logps/chosen": -73.22442626953125,
|
| 138 |
+
"logps/rejected": -82.25682067871094,
|
| 139 |
+
"loss": 0.645,
|
| 140 |
+
"rewards/accuracies": 0.800000011920929,
|
| 141 |
+
"rewards/chosen": -0.016868198290467262,
|
| 142 |
+
"rewards/margins": 0.10679063946008682,
|
| 143 |
+
"rewards/rejected": -0.12365883588790894,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3472803347280333,
|
| 148 |
+
"grad_norm": 4.355966567993164,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": -2.323256254196167,
|
| 151 |
+
"logits/rejected": -2.341057300567627,
|
| 152 |
+
"logps/chosen": -78.37105560302734,
|
| 153 |
+
"logps/rejected": -86.8406982421875,
|
| 154 |
+
"loss": 0.6072,
|
| 155 |
+
"rewards/accuracies": 0.824999988079071,
|
| 156 |
+
"rewards/chosen": -0.015012519434094429,
|
| 157 |
+
"rewards/margins": 0.20561759173870087,
|
| 158 |
+
"rewards/rejected": -0.22063009440898895,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7698744769874475,
|
| 163 |
+
"grad_norm": 4.361391067504883,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": -2.3163838386535645,
|
| 166 |
+
"logits/rejected": -2.3566031455993652,
|
| 167 |
+
"logps/chosen": -83.33145904541016,
|
| 168 |
+
"logps/rejected": -96.48517608642578,
|
| 169 |
+
"loss": 0.5908,
|
| 170 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 171 |
+
"rewards/chosen": -0.08870697021484375,
|
| 172 |
+
"rewards/margins": 0.24879300594329834,
|
| 173 |
+
"rewards/rejected": -0.3374999761581421,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.104602510460251,
|
| 178 |
+
"grad_norm": 4.315061569213867,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": -2.3728129863739014,
|
| 181 |
+
"logits/rejected": -2.3889667987823486,
|
| 182 |
+
"logps/chosen": -73.0484619140625,
|
| 183 |
+
"logps/rejected": -73.4913558959961,
|
| 184 |
+
"loss": 0.5783,
|
| 185 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 186 |
+
"rewards/chosen": -0.0605628564953804,
|
| 187 |
+
"rewards/margins": 0.2945060133934021,
|
| 188 |
+
"rewards/rejected": -0.3550689220428467,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.439330543933054,
|
| 193 |
+
"grad_norm": 4.438860893249512,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": -2.3526523113250732,
|
| 196 |
+
"logits/rejected": -2.364795684814453,
|
| 197 |
+
"logps/chosen": -67.69630432128906,
|
| 198 |
+
"logps/rejected": -84.85731506347656,
|
| 199 |
+
"loss": 0.5338,
|
| 200 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 201 |
+
"rewards/chosen": -0.1054786667227745,
|
| 202 |
+
"rewards/margins": 0.4161924421787262,
|
| 203 |
+
"rewards/rejected": -0.5216711759567261,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.7740585774058575,
|
| 208 |
+
"grad_norm": 4.5405473709106445,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": -2.3756489753723145,
|
| 211 |
+
"logits/rejected": -2.374919891357422,
|
| 212 |
+
"logps/chosen": -68.5466079711914,
|
| 213 |
+
"logps/rejected": -76.15412902832031,
|
| 214 |
+
"loss": 0.5215,
|
| 215 |
+
"rewards/accuracies": 0.824999988079071,
|
| 216 |
+
"rewards/chosen": -0.16213981807231903,
|
| 217 |
+
"rewards/margins": 0.47565969824790955,
|
| 218 |
+
"rewards/rejected": -0.6377995610237122,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.108786610878661,
|
| 223 |
+
"grad_norm": 4.596691608428955,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": -2.428659439086914,
|
| 226 |
+
"logits/rejected": -2.4141571521759033,
|
| 227 |
+
"logps/chosen": -78.08479309082031,
|
| 228 |
+
"logps/rejected": -68.3617172241211,
|
| 229 |
+
"loss": 0.5019,
|
| 230 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 231 |
+
"rewards/chosen": -0.20662447810173035,
|
| 232 |
+
"rewards/margins": 0.4026559889316559,
|
| 233 |
+
"rewards/rejected": -0.6092804670333862,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.443514644351464,
|
| 238 |
+
"grad_norm": 4.364648818969727,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": -2.408982992172241,
|
| 241 |
+
"logits/rejected": -2.4170727729797363,
|
| 242 |
+
"logps/chosen": -81.3556900024414,
|
| 243 |
+
"logps/rejected": -86.85897064208984,
|
| 244 |
+
"loss": 0.4586,
|
| 245 |
+
"rewards/accuracies": 0.824999988079071,
|
| 246 |
+
"rewards/chosen": -0.23941104114055634,
|
| 247 |
+
"rewards/margins": 0.675674319267273,
|
| 248 |
+
"rewards/rejected": -0.9150853157043457,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.7782426778242675,
|
| 253 |
+
"grad_norm": 5.241800308227539,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": -2.4194908142089844,
|
| 256 |
+
"logits/rejected": -2.4498963356018066,
|
| 257 |
+
"logps/chosen": -62.32392120361328,
|
| 258 |
+
"logps/rejected": -76.39479064941406,
|
| 259 |
+
"loss": 0.4442,
|
| 260 |
+
"rewards/accuracies": 0.887499988079071,
|
| 261 |
+
"rewards/chosen": -0.26662638783454895,
|
| 262 |
+
"rewards/margins": 0.6662653088569641,
|
| 263 |
+
"rewards/rejected": -0.9328916668891907,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.112970711297071,
|
| 268 |
+
"grad_norm": 4.73954439163208,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": -2.4365036487579346,
|
| 271 |
+
"logits/rejected": -2.435439348220825,
|
| 272 |
+
"logps/chosen": -73.06513977050781,
|
| 273 |
+
"logps/rejected": -81.04569244384766,
|
| 274 |
+
"loss": 0.4355,
|
| 275 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 276 |
+
"rewards/chosen": -0.37924182415008545,
|
| 277 |
+
"rewards/margins": 0.7773979902267456,
|
| 278 |
+
"rewards/rejected": -1.156639814376831,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.447698744769874,
|
| 283 |
+
"grad_norm": 5.250921726226807,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": -2.387922525405884,
|
| 286 |
+
"logits/rejected": -2.3835678100585938,
|
| 287 |
+
"logps/chosen": -64.85784912109375,
|
| 288 |
+
"logps/rejected": -90.08439636230469,
|
| 289 |
+
"loss": 0.3719,
|
| 290 |
+
"rewards/accuracies": 0.925000011920929,
|
| 291 |
+
"rewards/chosen": -0.42228370904922485,
|
| 292 |
+
"rewards/margins": 1.0562283992767334,
|
| 293 |
+
"rewards/rejected": -1.478512167930603,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.7824267782426775,
|
| 298 |
+
"grad_norm": 5.088508129119873,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": -2.376319169998169,
|
| 301 |
+
"logits/rejected": -2.3985953330993652,
|
| 302 |
+
"logps/chosen": -70.64585876464844,
|
| 303 |
+
"logps/rejected": -89.17048645019531,
|
| 304 |
+
"loss": 0.3829,
|
| 305 |
+
"rewards/accuracies": 0.9375,
|
| 306 |
+
"rewards/chosen": -0.5233972072601318,
|
| 307 |
+
"rewards/margins": 1.1063960790634155,
|
| 308 |
+
"rewards/rejected": -1.629793405532837,
|
| 309 |
+
"step": 200
|
| 310 |
+
}
|
| 311 |
+
],
|
| 312 |
+
"logging_steps": 10,
|
| 313 |
+
"max_steps": 580,
|
| 314 |
+
"num_input_tokens_seen": 0,
|
| 315 |
+
"num_train_epochs": 20,
|
| 316 |
+
"save_steps": 50,
|
| 317 |
+
"stateful_callbacks": {
|
| 318 |
+
"TrainerControl": {
|
| 319 |
+
"args": {
|
| 320 |
+
"should_epoch_stop": false,
|
| 321 |
+
"should_evaluate": false,
|
| 322 |
+
"should_log": false,
|
| 323 |
+
"should_save": true,
|
| 324 |
+
"should_training_stop": false
|
| 325 |
+
},
|
| 326 |
+
"attributes": {}
|
| 327 |
+
}
|
| 328 |
+
},
|
| 329 |
+
"total_flos": 7.3432113710157e+17,
|
| 330 |
+
"train_batch_size": 1,
|
| 331 |
+
"trial_name": null,
|
| 332 |
+
"trial_params": null
|
| 333 |
+
}
|
Area_SFT/checkpoint-250/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- 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. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
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).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_SFT/checkpoint-250/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_SFT/checkpoint-250/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Area_SFT/checkpoint-250/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
Area_SFT/checkpoint-250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_SFT/checkpoint-250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"additional_special_tokens": [
|
| 40 |
+
"<unk>",
|
| 41 |
+
"<s>",
|
| 42 |
+
"</s>",
|
| 43 |
+
"[PAD]"
|
| 44 |
+
],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"legacy": true,
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"padding_side": "right",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"spaces_between_special_tokens": false,
|
| 55 |
+
"split_special_tokens": false,
|
| 56 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 57 |
+
"unk_token": "<unk>",
|
| 58 |
+
"use_default_system_prompt": true
|
| 59 |
+
}
|
Area_SFT/checkpoint-250/trainer_state.json
ADDED
|
@@ -0,0 +1,408 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.456066945606695,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33472803347280333,
|
| 13 |
+
"grad_norm": 3.9892160892486572,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": -2.315223217010498,
|
| 16 |
+
"logits/rejected": -2.3654401302337646,
|
| 17 |
+
"logps/chosen": -65.86729431152344,
|
| 18 |
+
"logps/rejected": -77.53572845458984,
|
| 19 |
+
"loss": 0.6929,
|
| 20 |
+
"rewards/accuracies": 0.3499999940395355,
|
| 21 |
+
"rewards/chosen": 0.0023138518445193768,
|
| 22 |
+
"rewards/margins": -0.001122759305872023,
|
| 23 |
+
"rewards/rejected": 0.0034366101026535034,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6694560669456067,
|
| 28 |
+
"grad_norm": 3.5659756660461426,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": -2.341399669647217,
|
| 31 |
+
"logits/rejected": -2.3567094802856445,
|
| 32 |
+
"logps/chosen": -66.60242462158203,
|
| 33 |
+
"logps/rejected": -69.70094299316406,
|
| 34 |
+
"loss": 0.6929,
|
| 35 |
+
"rewards/accuracies": 0.512499988079071,
|
| 36 |
+
"rewards/chosen": -0.0013719359412789345,
|
| 37 |
+
"rewards/margins": -0.0035000313073396683,
|
| 38 |
+
"rewards/rejected": 0.002128095831722021,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.00418410041841,
|
| 43 |
+
"grad_norm": 4.912586688995361,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": -2.3429622650146484,
|
| 46 |
+
"logits/rejected": -2.3658394813537598,
|
| 47 |
+
"logps/chosen": -71.6301040649414,
|
| 48 |
+
"logps/rejected": -78.41346740722656,
|
| 49 |
+
"loss": 0.6938,
|
| 50 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 51 |
+
"rewards/chosen": 0.003577103139832616,
|
| 52 |
+
"rewards/margins": 0.00785654503852129,
|
| 53 |
+
"rewards/rejected": -0.004279441200196743,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.3389121338912133,
|
| 58 |
+
"grad_norm": 4.810107707977295,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": -2.3610458374023438,
|
| 61 |
+
"logits/rejected": -2.3885395526885986,
|
| 62 |
+
"logps/chosen": -66.8291244506836,
|
| 63 |
+
"logps/rejected": -62.15415573120117,
|
| 64 |
+
"loss": 0.6893,
|
| 65 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 66 |
+
"rewards/chosen": -6.734435737598687e-05,
|
| 67 |
+
"rewards/margins": 0.006865750066936016,
|
| 68 |
+
"rewards/rejected": -0.0069330958649516106,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6736401673640167,
|
| 73 |
+
"grad_norm": 4.670071125030518,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": -2.304999351501465,
|
| 76 |
+
"logits/rejected": -2.335301399230957,
|
| 77 |
+
"logps/chosen": -75.09913635253906,
|
| 78 |
+
"logps/rejected": -77.72399139404297,
|
| 79 |
+
"loss": 0.6878,
|
| 80 |
+
"rewards/accuracies": 0.612500011920929,
|
| 81 |
+
"rewards/chosen": 0.003225918160751462,
|
| 82 |
+
"rewards/margins": 0.010454346425831318,
|
| 83 |
+
"rewards/rejected": -0.007228427566587925,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.00836820083682,
|
| 88 |
+
"grad_norm": 4.2342000007629395,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": -2.363574504852295,
|
| 91 |
+
"logits/rejected": -2.363882064819336,
|
| 92 |
+
"logps/chosen": -62.84125900268555,
|
| 93 |
+
"logps/rejected": -61.92932891845703,
|
| 94 |
+
"loss": 0.6855,
|
| 95 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 96 |
+
"rewards/chosen": -0.0032769464887678623,
|
| 97 |
+
"rewards/margins": 0.02090405486524105,
|
| 98 |
+
"rewards/rejected": -0.024181004613637924,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3430962343096233,
|
| 103 |
+
"grad_norm": 4.369245529174805,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": -2.378016948699951,
|
| 106 |
+
"logits/rejected": -2.373137950897217,
|
| 107 |
+
"logps/chosen": -74.67327880859375,
|
| 108 |
+
"logps/rejected": -69.20399475097656,
|
| 109 |
+
"loss": 0.668,
|
| 110 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 111 |
+
"rewards/chosen": -0.0003526444488670677,
|
| 112 |
+
"rewards/margins": 0.04865006357431412,
|
| 113 |
+
"rewards/rejected": -0.04900271072983742,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.6778242677824267,
|
| 118 |
+
"grad_norm": 4.444687366485596,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": -2.3403103351593018,
|
| 121 |
+
"logits/rejected": -2.370321273803711,
|
| 122 |
+
"logps/chosen": -77.29728698730469,
|
| 123 |
+
"logps/rejected": -85.79756164550781,
|
| 124 |
+
"loss": 0.6566,
|
| 125 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 126 |
+
"rewards/chosen": 0.0051120575517416,
|
| 127 |
+
"rewards/margins": 0.09415190666913986,
|
| 128 |
+
"rewards/rejected": -0.08903985470533371,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.01255230125523,
|
| 133 |
+
"grad_norm": 4.876573085784912,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": -2.3614611625671387,
|
| 136 |
+
"logits/rejected": -2.385697841644287,
|
| 137 |
+
"logps/chosen": -73.22442626953125,
|
| 138 |
+
"logps/rejected": -82.25682067871094,
|
| 139 |
+
"loss": 0.645,
|
| 140 |
+
"rewards/accuracies": 0.800000011920929,
|
| 141 |
+
"rewards/chosen": -0.016868198290467262,
|
| 142 |
+
"rewards/margins": 0.10679063946008682,
|
| 143 |
+
"rewards/rejected": -0.12365883588790894,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3472803347280333,
|
| 148 |
+
"grad_norm": 4.355966567993164,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": -2.323256254196167,
|
| 151 |
+
"logits/rejected": -2.341057300567627,
|
| 152 |
+
"logps/chosen": -78.37105560302734,
|
| 153 |
+
"logps/rejected": -86.8406982421875,
|
| 154 |
+
"loss": 0.6072,
|
| 155 |
+
"rewards/accuracies": 0.824999988079071,
|
| 156 |
+
"rewards/chosen": -0.015012519434094429,
|
| 157 |
+
"rewards/margins": 0.20561759173870087,
|
| 158 |
+
"rewards/rejected": -0.22063009440898895,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7698744769874475,
|
| 163 |
+
"grad_norm": 4.361391067504883,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": -2.3163838386535645,
|
| 166 |
+
"logits/rejected": -2.3566031455993652,
|
| 167 |
+
"logps/chosen": -83.33145904541016,
|
| 168 |
+
"logps/rejected": -96.48517608642578,
|
| 169 |
+
"loss": 0.5908,
|
| 170 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 171 |
+
"rewards/chosen": -0.08870697021484375,
|
| 172 |
+
"rewards/margins": 0.24879300594329834,
|
| 173 |
+
"rewards/rejected": -0.3374999761581421,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.104602510460251,
|
| 178 |
+
"grad_norm": 4.315061569213867,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": -2.3728129863739014,
|
| 181 |
+
"logits/rejected": -2.3889667987823486,
|
| 182 |
+
"logps/chosen": -73.0484619140625,
|
| 183 |
+
"logps/rejected": -73.4913558959961,
|
| 184 |
+
"loss": 0.5783,
|
| 185 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 186 |
+
"rewards/chosen": -0.0605628564953804,
|
| 187 |
+
"rewards/margins": 0.2945060133934021,
|
| 188 |
+
"rewards/rejected": -0.3550689220428467,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.439330543933054,
|
| 193 |
+
"grad_norm": 4.438860893249512,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": -2.3526523113250732,
|
| 196 |
+
"logits/rejected": -2.364795684814453,
|
| 197 |
+
"logps/chosen": -67.69630432128906,
|
| 198 |
+
"logps/rejected": -84.85731506347656,
|
| 199 |
+
"loss": 0.5338,
|
| 200 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 201 |
+
"rewards/chosen": -0.1054786667227745,
|
| 202 |
+
"rewards/margins": 0.4161924421787262,
|
| 203 |
+
"rewards/rejected": -0.5216711759567261,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.7740585774058575,
|
| 208 |
+
"grad_norm": 4.5405473709106445,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": -2.3756489753723145,
|
| 211 |
+
"logits/rejected": -2.374919891357422,
|
| 212 |
+
"logps/chosen": -68.5466079711914,
|
| 213 |
+
"logps/rejected": -76.15412902832031,
|
| 214 |
+
"loss": 0.5215,
|
| 215 |
+
"rewards/accuracies": 0.824999988079071,
|
| 216 |
+
"rewards/chosen": -0.16213981807231903,
|
| 217 |
+
"rewards/margins": 0.47565969824790955,
|
| 218 |
+
"rewards/rejected": -0.6377995610237122,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.108786610878661,
|
| 223 |
+
"grad_norm": 4.596691608428955,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": -2.428659439086914,
|
| 226 |
+
"logits/rejected": -2.4141571521759033,
|
| 227 |
+
"logps/chosen": -78.08479309082031,
|
| 228 |
+
"logps/rejected": -68.3617172241211,
|
| 229 |
+
"loss": 0.5019,
|
| 230 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 231 |
+
"rewards/chosen": -0.20662447810173035,
|
| 232 |
+
"rewards/margins": 0.4026559889316559,
|
| 233 |
+
"rewards/rejected": -0.6092804670333862,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.443514644351464,
|
| 238 |
+
"grad_norm": 4.364648818969727,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": -2.408982992172241,
|
| 241 |
+
"logits/rejected": -2.4170727729797363,
|
| 242 |
+
"logps/chosen": -81.3556900024414,
|
| 243 |
+
"logps/rejected": -86.85897064208984,
|
| 244 |
+
"loss": 0.4586,
|
| 245 |
+
"rewards/accuracies": 0.824999988079071,
|
| 246 |
+
"rewards/chosen": -0.23941104114055634,
|
| 247 |
+
"rewards/margins": 0.675674319267273,
|
| 248 |
+
"rewards/rejected": -0.9150853157043457,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.7782426778242675,
|
| 253 |
+
"grad_norm": 5.241800308227539,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": -2.4194908142089844,
|
| 256 |
+
"logits/rejected": -2.4498963356018066,
|
| 257 |
+
"logps/chosen": -62.32392120361328,
|
| 258 |
+
"logps/rejected": -76.39479064941406,
|
| 259 |
+
"loss": 0.4442,
|
| 260 |
+
"rewards/accuracies": 0.887499988079071,
|
| 261 |
+
"rewards/chosen": -0.26662638783454895,
|
| 262 |
+
"rewards/margins": 0.6662653088569641,
|
| 263 |
+
"rewards/rejected": -0.9328916668891907,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.112970711297071,
|
| 268 |
+
"grad_norm": 4.73954439163208,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": -2.4365036487579346,
|
| 271 |
+
"logits/rejected": -2.435439348220825,
|
| 272 |
+
"logps/chosen": -73.06513977050781,
|
| 273 |
+
"logps/rejected": -81.04569244384766,
|
| 274 |
+
"loss": 0.4355,
|
| 275 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 276 |
+
"rewards/chosen": -0.37924182415008545,
|
| 277 |
+
"rewards/margins": 0.7773979902267456,
|
| 278 |
+
"rewards/rejected": -1.156639814376831,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.447698744769874,
|
| 283 |
+
"grad_norm": 5.250921726226807,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": -2.387922525405884,
|
| 286 |
+
"logits/rejected": -2.3835678100585938,
|
| 287 |
+
"logps/chosen": -64.85784912109375,
|
| 288 |
+
"logps/rejected": -90.08439636230469,
|
| 289 |
+
"loss": 0.3719,
|
| 290 |
+
"rewards/accuracies": 0.925000011920929,
|
| 291 |
+
"rewards/chosen": -0.42228370904922485,
|
| 292 |
+
"rewards/margins": 1.0562283992767334,
|
| 293 |
+
"rewards/rejected": -1.478512167930603,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.7824267782426775,
|
| 298 |
+
"grad_norm": 5.088508129119873,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": -2.376319169998169,
|
| 301 |
+
"logits/rejected": -2.3985953330993652,
|
| 302 |
+
"logps/chosen": -70.64585876464844,
|
| 303 |
+
"logps/rejected": -89.17048645019531,
|
| 304 |
+
"loss": 0.3829,
|
| 305 |
+
"rewards/accuracies": 0.9375,
|
| 306 |
+
"rewards/chosen": -0.5233972072601318,
|
| 307 |
+
"rewards/margins": 1.1063960790634155,
|
| 308 |
+
"rewards/rejected": -1.629793405532837,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.117154811715481,
|
| 313 |
+
"grad_norm": 4.6062092781066895,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": -2.371851682662964,
|
| 316 |
+
"logits/rejected": -2.3844287395477295,
|
| 317 |
+
"logps/chosen": -74.63328552246094,
|
| 318 |
+
"logps/rejected": -97.81452178955078,
|
| 319 |
+
"loss": 0.3522,
|
| 320 |
+
"rewards/accuracies": 0.925000011920929,
|
| 321 |
+
"rewards/chosen": -0.6278538703918457,
|
| 322 |
+
"rewards/margins": 1.2317354679107666,
|
| 323 |
+
"rewards/rejected": -1.8595889806747437,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.451882845188284,
|
| 328 |
+
"grad_norm": 5.105669021606445,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": -2.4011385440826416,
|
| 331 |
+
"logits/rejected": -2.4039382934570312,
|
| 332 |
+
"logps/chosen": -75.92952728271484,
|
| 333 |
+
"logps/rejected": -78.41490936279297,
|
| 334 |
+
"loss": 0.3219,
|
| 335 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 336 |
+
"rewards/chosen": -0.39645594358444214,
|
| 337 |
+
"rewards/margins": 1.2095177173614502,
|
| 338 |
+
"rewards/rejected": -1.6059738397598267,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.786610878661088,
|
| 343 |
+
"grad_norm": 6.292915344238281,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": -2.3707780838012695,
|
| 346 |
+
"logits/rejected": -2.377169609069824,
|
| 347 |
+
"logps/chosen": -88.07064056396484,
|
| 348 |
+
"logps/rejected": -108.6225814819336,
|
| 349 |
+
"loss": 0.3041,
|
| 350 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 351 |
+
"rewards/chosen": -0.9827474355697632,
|
| 352 |
+
"rewards/margins": 1.3651618957519531,
|
| 353 |
+
"rewards/rejected": -2.3479092121124268,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.121338912133892,
|
| 358 |
+
"grad_norm": 5.0669097900390625,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": -2.3608062267303467,
|
| 361 |
+
"logits/rejected": -2.3792402744293213,
|
| 362 |
+
"logps/chosen": -72.83047485351562,
|
| 363 |
+
"logps/rejected": -91.09341430664062,
|
| 364 |
+
"loss": 0.3065,
|
| 365 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 366 |
+
"rewards/chosen": -0.9334943890571594,
|
| 367 |
+
"rewards/margins": 1.3210034370422363,
|
| 368 |
+
"rewards/rejected": -2.25449800491333,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.456066945606695,
|
| 373 |
+
"grad_norm": 5.0598931312561035,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": -2.324855327606201,
|
| 376 |
+
"logits/rejected": -2.364541530609131,
|
| 377 |
+
"logps/chosen": -90.57644653320312,
|
| 378 |
+
"logps/rejected": -106.41752624511719,
|
| 379 |
+
"loss": 0.2498,
|
| 380 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 381 |
+
"rewards/chosen": -0.8531273007392883,
|
| 382 |
+
"rewards/margins": 1.8315904140472412,
|
| 383 |
+
"rewards/rejected": -2.684717893600464,
|
| 384 |
+
"step": 250
|
| 385 |
+
}
|
| 386 |
+
],
|
| 387 |
+
"logging_steps": 10,
|
| 388 |
+
"max_steps": 580,
|
| 389 |
+
"num_input_tokens_seen": 0,
|
| 390 |
+
"num_train_epochs": 20,
|
| 391 |
+
"save_steps": 50,
|
| 392 |
+
"stateful_callbacks": {
|
| 393 |
+
"TrainerControl": {
|
| 394 |
+
"args": {
|
| 395 |
+
"should_epoch_stop": false,
|
| 396 |
+
"should_evaluate": false,
|
| 397 |
+
"should_log": false,
|
| 398 |
+
"should_save": true,
|
| 399 |
+
"should_training_stop": false
|
| 400 |
+
},
|
| 401 |
+
"attributes": {}
|
| 402 |
+
}
|
| 403 |
+
},
|
| 404 |
+
"total_flos": 9.188089082381599e+17,
|
| 405 |
+
"train_batch_size": 1,
|
| 406 |
+
"trial_name": null,
|
| 407 |
+
"trial_params": null
|
| 408 |
+
}
|
Area_SFT/checkpoint-300/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- 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. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
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).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_SFT/checkpoint-300/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_SFT/checkpoint-300/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Area_SFT/checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
Area_SFT/checkpoint-300/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_SFT/checkpoint-300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"additional_special_tokens": [
|
| 40 |
+
"<unk>",
|
| 41 |
+
"<s>",
|
| 42 |
+
"</s>",
|
| 43 |
+
"[PAD]"
|
| 44 |
+
],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"legacy": true,
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"padding_side": "right",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"spaces_between_special_tokens": false,
|
| 55 |
+
"split_special_tokens": false,
|
| 56 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 57 |
+
"unk_token": "<unk>",
|
| 58 |
+
"use_default_system_prompt": true
|
| 59 |
+
}
|
Area_SFT/checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.129707112970712,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33472803347280333,
|
| 13 |
+
"grad_norm": 3.9892160892486572,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": -2.315223217010498,
|
| 16 |
+
"logits/rejected": -2.3654401302337646,
|
| 17 |
+
"logps/chosen": -65.86729431152344,
|
| 18 |
+
"logps/rejected": -77.53572845458984,
|
| 19 |
+
"loss": 0.6929,
|
| 20 |
+
"rewards/accuracies": 0.3499999940395355,
|
| 21 |
+
"rewards/chosen": 0.0023138518445193768,
|
| 22 |
+
"rewards/margins": -0.001122759305872023,
|
| 23 |
+
"rewards/rejected": 0.0034366101026535034,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6694560669456067,
|
| 28 |
+
"grad_norm": 3.5659756660461426,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": -2.341399669647217,
|
| 31 |
+
"logits/rejected": -2.3567094802856445,
|
| 32 |
+
"logps/chosen": -66.60242462158203,
|
| 33 |
+
"logps/rejected": -69.70094299316406,
|
| 34 |
+
"loss": 0.6929,
|
| 35 |
+
"rewards/accuracies": 0.512499988079071,
|
| 36 |
+
"rewards/chosen": -0.0013719359412789345,
|
| 37 |
+
"rewards/margins": -0.0035000313073396683,
|
| 38 |
+
"rewards/rejected": 0.002128095831722021,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.00418410041841,
|
| 43 |
+
"grad_norm": 4.912586688995361,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": -2.3429622650146484,
|
| 46 |
+
"logits/rejected": -2.3658394813537598,
|
| 47 |
+
"logps/chosen": -71.6301040649414,
|
| 48 |
+
"logps/rejected": -78.41346740722656,
|
| 49 |
+
"loss": 0.6938,
|
| 50 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 51 |
+
"rewards/chosen": 0.003577103139832616,
|
| 52 |
+
"rewards/margins": 0.00785654503852129,
|
| 53 |
+
"rewards/rejected": -0.004279441200196743,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.3389121338912133,
|
| 58 |
+
"grad_norm": 4.810107707977295,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": -2.3610458374023438,
|
| 61 |
+
"logits/rejected": -2.3885395526885986,
|
| 62 |
+
"logps/chosen": -66.8291244506836,
|
| 63 |
+
"logps/rejected": -62.15415573120117,
|
| 64 |
+
"loss": 0.6893,
|
| 65 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 66 |
+
"rewards/chosen": -6.734435737598687e-05,
|
| 67 |
+
"rewards/margins": 0.006865750066936016,
|
| 68 |
+
"rewards/rejected": -0.0069330958649516106,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6736401673640167,
|
| 73 |
+
"grad_norm": 4.670071125030518,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": -2.304999351501465,
|
| 76 |
+
"logits/rejected": -2.335301399230957,
|
| 77 |
+
"logps/chosen": -75.09913635253906,
|
| 78 |
+
"logps/rejected": -77.72399139404297,
|
| 79 |
+
"loss": 0.6878,
|
| 80 |
+
"rewards/accuracies": 0.612500011920929,
|
| 81 |
+
"rewards/chosen": 0.003225918160751462,
|
| 82 |
+
"rewards/margins": 0.010454346425831318,
|
| 83 |
+
"rewards/rejected": -0.007228427566587925,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.00836820083682,
|
| 88 |
+
"grad_norm": 4.2342000007629395,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": -2.363574504852295,
|
| 91 |
+
"logits/rejected": -2.363882064819336,
|
| 92 |
+
"logps/chosen": -62.84125900268555,
|
| 93 |
+
"logps/rejected": -61.92932891845703,
|
| 94 |
+
"loss": 0.6855,
|
| 95 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 96 |
+
"rewards/chosen": -0.0032769464887678623,
|
| 97 |
+
"rewards/margins": 0.02090405486524105,
|
| 98 |
+
"rewards/rejected": -0.024181004613637924,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3430962343096233,
|
| 103 |
+
"grad_norm": 4.369245529174805,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": -2.378016948699951,
|
| 106 |
+
"logits/rejected": -2.373137950897217,
|
| 107 |
+
"logps/chosen": -74.67327880859375,
|
| 108 |
+
"logps/rejected": -69.20399475097656,
|
| 109 |
+
"loss": 0.668,
|
| 110 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 111 |
+
"rewards/chosen": -0.0003526444488670677,
|
| 112 |
+
"rewards/margins": 0.04865006357431412,
|
| 113 |
+
"rewards/rejected": -0.04900271072983742,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.6778242677824267,
|
| 118 |
+
"grad_norm": 4.444687366485596,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": -2.3403103351593018,
|
| 121 |
+
"logits/rejected": -2.370321273803711,
|
| 122 |
+
"logps/chosen": -77.29728698730469,
|
| 123 |
+
"logps/rejected": -85.79756164550781,
|
| 124 |
+
"loss": 0.6566,
|
| 125 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 126 |
+
"rewards/chosen": 0.0051120575517416,
|
| 127 |
+
"rewards/margins": 0.09415190666913986,
|
| 128 |
+
"rewards/rejected": -0.08903985470533371,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.01255230125523,
|
| 133 |
+
"grad_norm": 4.876573085784912,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": -2.3614611625671387,
|
| 136 |
+
"logits/rejected": -2.385697841644287,
|
| 137 |
+
"logps/chosen": -73.22442626953125,
|
| 138 |
+
"logps/rejected": -82.25682067871094,
|
| 139 |
+
"loss": 0.645,
|
| 140 |
+
"rewards/accuracies": 0.800000011920929,
|
| 141 |
+
"rewards/chosen": -0.016868198290467262,
|
| 142 |
+
"rewards/margins": 0.10679063946008682,
|
| 143 |
+
"rewards/rejected": -0.12365883588790894,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3472803347280333,
|
| 148 |
+
"grad_norm": 4.355966567993164,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": -2.323256254196167,
|
| 151 |
+
"logits/rejected": -2.341057300567627,
|
| 152 |
+
"logps/chosen": -78.37105560302734,
|
| 153 |
+
"logps/rejected": -86.8406982421875,
|
| 154 |
+
"loss": 0.6072,
|
| 155 |
+
"rewards/accuracies": 0.824999988079071,
|
| 156 |
+
"rewards/chosen": -0.015012519434094429,
|
| 157 |
+
"rewards/margins": 0.20561759173870087,
|
| 158 |
+
"rewards/rejected": -0.22063009440898895,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7698744769874475,
|
| 163 |
+
"grad_norm": 4.361391067504883,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": -2.3163838386535645,
|
| 166 |
+
"logits/rejected": -2.3566031455993652,
|
| 167 |
+
"logps/chosen": -83.33145904541016,
|
| 168 |
+
"logps/rejected": -96.48517608642578,
|
| 169 |
+
"loss": 0.5908,
|
| 170 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 171 |
+
"rewards/chosen": -0.08870697021484375,
|
| 172 |
+
"rewards/margins": 0.24879300594329834,
|
| 173 |
+
"rewards/rejected": -0.3374999761581421,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.104602510460251,
|
| 178 |
+
"grad_norm": 4.315061569213867,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": -2.3728129863739014,
|
| 181 |
+
"logits/rejected": -2.3889667987823486,
|
| 182 |
+
"logps/chosen": -73.0484619140625,
|
| 183 |
+
"logps/rejected": -73.4913558959961,
|
| 184 |
+
"loss": 0.5783,
|
| 185 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 186 |
+
"rewards/chosen": -0.0605628564953804,
|
| 187 |
+
"rewards/margins": 0.2945060133934021,
|
| 188 |
+
"rewards/rejected": -0.3550689220428467,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.439330543933054,
|
| 193 |
+
"grad_norm": 4.438860893249512,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": -2.3526523113250732,
|
| 196 |
+
"logits/rejected": -2.364795684814453,
|
| 197 |
+
"logps/chosen": -67.69630432128906,
|
| 198 |
+
"logps/rejected": -84.85731506347656,
|
| 199 |
+
"loss": 0.5338,
|
| 200 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 201 |
+
"rewards/chosen": -0.1054786667227745,
|
| 202 |
+
"rewards/margins": 0.4161924421787262,
|
| 203 |
+
"rewards/rejected": -0.5216711759567261,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.7740585774058575,
|
| 208 |
+
"grad_norm": 4.5405473709106445,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": -2.3756489753723145,
|
| 211 |
+
"logits/rejected": -2.374919891357422,
|
| 212 |
+
"logps/chosen": -68.5466079711914,
|
| 213 |
+
"logps/rejected": -76.15412902832031,
|
| 214 |
+
"loss": 0.5215,
|
| 215 |
+
"rewards/accuracies": 0.824999988079071,
|
| 216 |
+
"rewards/chosen": -0.16213981807231903,
|
| 217 |
+
"rewards/margins": 0.47565969824790955,
|
| 218 |
+
"rewards/rejected": -0.6377995610237122,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.108786610878661,
|
| 223 |
+
"grad_norm": 4.596691608428955,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": -2.428659439086914,
|
| 226 |
+
"logits/rejected": -2.4141571521759033,
|
| 227 |
+
"logps/chosen": -78.08479309082031,
|
| 228 |
+
"logps/rejected": -68.3617172241211,
|
| 229 |
+
"loss": 0.5019,
|
| 230 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 231 |
+
"rewards/chosen": -0.20662447810173035,
|
| 232 |
+
"rewards/margins": 0.4026559889316559,
|
| 233 |
+
"rewards/rejected": -0.6092804670333862,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.443514644351464,
|
| 238 |
+
"grad_norm": 4.364648818969727,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": -2.408982992172241,
|
| 241 |
+
"logits/rejected": -2.4170727729797363,
|
| 242 |
+
"logps/chosen": -81.3556900024414,
|
| 243 |
+
"logps/rejected": -86.85897064208984,
|
| 244 |
+
"loss": 0.4586,
|
| 245 |
+
"rewards/accuracies": 0.824999988079071,
|
| 246 |
+
"rewards/chosen": -0.23941104114055634,
|
| 247 |
+
"rewards/margins": 0.675674319267273,
|
| 248 |
+
"rewards/rejected": -0.9150853157043457,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.7782426778242675,
|
| 253 |
+
"grad_norm": 5.241800308227539,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": -2.4194908142089844,
|
| 256 |
+
"logits/rejected": -2.4498963356018066,
|
| 257 |
+
"logps/chosen": -62.32392120361328,
|
| 258 |
+
"logps/rejected": -76.39479064941406,
|
| 259 |
+
"loss": 0.4442,
|
| 260 |
+
"rewards/accuracies": 0.887499988079071,
|
| 261 |
+
"rewards/chosen": -0.26662638783454895,
|
| 262 |
+
"rewards/margins": 0.6662653088569641,
|
| 263 |
+
"rewards/rejected": -0.9328916668891907,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.112970711297071,
|
| 268 |
+
"grad_norm": 4.73954439163208,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": -2.4365036487579346,
|
| 271 |
+
"logits/rejected": -2.435439348220825,
|
| 272 |
+
"logps/chosen": -73.06513977050781,
|
| 273 |
+
"logps/rejected": -81.04569244384766,
|
| 274 |
+
"loss": 0.4355,
|
| 275 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 276 |
+
"rewards/chosen": -0.37924182415008545,
|
| 277 |
+
"rewards/margins": 0.7773979902267456,
|
| 278 |
+
"rewards/rejected": -1.156639814376831,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.447698744769874,
|
| 283 |
+
"grad_norm": 5.250921726226807,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": -2.387922525405884,
|
| 286 |
+
"logits/rejected": -2.3835678100585938,
|
| 287 |
+
"logps/chosen": -64.85784912109375,
|
| 288 |
+
"logps/rejected": -90.08439636230469,
|
| 289 |
+
"loss": 0.3719,
|
| 290 |
+
"rewards/accuracies": 0.925000011920929,
|
| 291 |
+
"rewards/chosen": -0.42228370904922485,
|
| 292 |
+
"rewards/margins": 1.0562283992767334,
|
| 293 |
+
"rewards/rejected": -1.478512167930603,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.7824267782426775,
|
| 298 |
+
"grad_norm": 5.088508129119873,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": -2.376319169998169,
|
| 301 |
+
"logits/rejected": -2.3985953330993652,
|
| 302 |
+
"logps/chosen": -70.64585876464844,
|
| 303 |
+
"logps/rejected": -89.17048645019531,
|
| 304 |
+
"loss": 0.3829,
|
| 305 |
+
"rewards/accuracies": 0.9375,
|
| 306 |
+
"rewards/chosen": -0.5233972072601318,
|
| 307 |
+
"rewards/margins": 1.1063960790634155,
|
| 308 |
+
"rewards/rejected": -1.629793405532837,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.117154811715481,
|
| 313 |
+
"grad_norm": 4.6062092781066895,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": -2.371851682662964,
|
| 316 |
+
"logits/rejected": -2.3844287395477295,
|
| 317 |
+
"logps/chosen": -74.63328552246094,
|
| 318 |
+
"logps/rejected": -97.81452178955078,
|
| 319 |
+
"loss": 0.3522,
|
| 320 |
+
"rewards/accuracies": 0.925000011920929,
|
| 321 |
+
"rewards/chosen": -0.6278538703918457,
|
| 322 |
+
"rewards/margins": 1.2317354679107666,
|
| 323 |
+
"rewards/rejected": -1.8595889806747437,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.451882845188284,
|
| 328 |
+
"grad_norm": 5.105669021606445,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": -2.4011385440826416,
|
| 331 |
+
"logits/rejected": -2.4039382934570312,
|
| 332 |
+
"logps/chosen": -75.92952728271484,
|
| 333 |
+
"logps/rejected": -78.41490936279297,
|
| 334 |
+
"loss": 0.3219,
|
| 335 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 336 |
+
"rewards/chosen": -0.39645594358444214,
|
| 337 |
+
"rewards/margins": 1.2095177173614502,
|
| 338 |
+
"rewards/rejected": -1.6059738397598267,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.786610878661088,
|
| 343 |
+
"grad_norm": 6.292915344238281,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": -2.3707780838012695,
|
| 346 |
+
"logits/rejected": -2.377169609069824,
|
| 347 |
+
"logps/chosen": -88.07064056396484,
|
| 348 |
+
"logps/rejected": -108.6225814819336,
|
| 349 |
+
"loss": 0.3041,
|
| 350 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 351 |
+
"rewards/chosen": -0.9827474355697632,
|
| 352 |
+
"rewards/margins": 1.3651618957519531,
|
| 353 |
+
"rewards/rejected": -2.3479092121124268,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.121338912133892,
|
| 358 |
+
"grad_norm": 5.0669097900390625,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": -2.3608062267303467,
|
| 361 |
+
"logits/rejected": -2.3792402744293213,
|
| 362 |
+
"logps/chosen": -72.83047485351562,
|
| 363 |
+
"logps/rejected": -91.09341430664062,
|
| 364 |
+
"loss": 0.3065,
|
| 365 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 366 |
+
"rewards/chosen": -0.9334943890571594,
|
| 367 |
+
"rewards/margins": 1.3210034370422363,
|
| 368 |
+
"rewards/rejected": -2.25449800491333,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.456066945606695,
|
| 373 |
+
"grad_norm": 5.0598931312561035,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": -2.324855327606201,
|
| 376 |
+
"logits/rejected": -2.364541530609131,
|
| 377 |
+
"logps/chosen": -90.57644653320312,
|
| 378 |
+
"logps/rejected": -106.41752624511719,
|
| 379 |
+
"loss": 0.2498,
|
| 380 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 381 |
+
"rewards/chosen": -0.8531273007392883,
|
| 382 |
+
"rewards/margins": 1.8315904140472412,
|
| 383 |
+
"rewards/rejected": -2.684717893600464,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.790794979079498,
|
| 388 |
+
"grad_norm": 6.120776653289795,
|
| 389 |
+
"learning_rate": 3.3691733481883693e-06,
|
| 390 |
+
"logits/chosen": -2.3436760902404785,
|
| 391 |
+
"logits/rejected": -2.3720099925994873,
|
| 392 |
+
"logps/chosen": -86.95789337158203,
|
| 393 |
+
"logps/rejected": -102.34903717041016,
|
| 394 |
+
"loss": 0.2532,
|
| 395 |
+
"rewards/accuracies": 0.925000011920929,
|
| 396 |
+
"rewards/chosen": -1.1573801040649414,
|
| 397 |
+
"rewards/margins": 1.7690637111663818,
|
| 398 |
+
"rewards/rejected": -2.9264438152313232,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.125523012552302,
|
| 403 |
+
"grad_norm": 4.666015625,
|
| 404 |
+
"learning_rate": 3.226611521064278e-06,
|
| 405 |
+
"logits/chosen": -2.3132309913635254,
|
| 406 |
+
"logits/rejected": -2.309297800064087,
|
| 407 |
+
"logps/chosen": -78.139404296875,
|
| 408 |
+
"logps/rejected": -99.09760284423828,
|
| 409 |
+
"loss": 0.2314,
|
| 410 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 411 |
+
"rewards/chosen": -1.0649818181991577,
|
| 412 |
+
"rewards/margins": 1.8774713277816772,
|
| 413 |
+
"rewards/rejected": -2.942453384399414,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.460251046025105,
|
| 418 |
+
"grad_norm": 8.85567855834961,
|
| 419 |
+
"learning_rate": 3.0814186389357765e-06,
|
| 420 |
+
"logits/chosen": -2.3629987239837646,
|
| 421 |
+
"logits/rejected": -2.385927200317383,
|
| 422 |
+
"logps/chosen": -91.09283447265625,
|
| 423 |
+
"logps/rejected": -102.37603759765625,
|
| 424 |
+
"loss": 0.2142,
|
| 425 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 426 |
+
"rewards/chosen": -1.5404099225997925,
|
| 427 |
+
"rewards/margins": 2.121422290802002,
|
| 428 |
+
"rewards/rejected": -3.661832094192505,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.794979079497908,
|
| 433 |
+
"grad_norm": 5.228074550628662,
|
| 434 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 435 |
+
"logits/chosen": -2.356905221939087,
|
| 436 |
+
"logits/rejected": -2.3635311126708984,
|
| 437 |
+
"logps/chosen": -91.65778350830078,
|
| 438 |
+
"logps/rejected": -117.89949035644531,
|
| 439 |
+
"loss": 0.1881,
|
| 440 |
+
"rewards/accuracies": 1.0,
|
| 441 |
+
"rewards/chosen": -1.6620346307754517,
|
| 442 |
+
"rewards/margins": 2.1766200065612793,
|
| 443 |
+
"rewards/rejected": -3.8386547565460205,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.129707112970712,
|
| 448 |
+
"grad_norm": 5.115809440612793,
|
| 449 |
+
"learning_rate": 2.785250302445062e-06,
|
| 450 |
+
"logits/chosen": -2.2903695106506348,
|
| 451 |
+
"logits/rejected": -2.2926692962646484,
|
| 452 |
+
"logps/chosen": -104.5173110961914,
|
| 453 |
+
"logps/rejected": -123.13216400146484,
|
| 454 |
+
"loss": 0.1798,
|
| 455 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 456 |
+
"rewards/chosen": -1.7224146127700806,
|
| 457 |
+
"rewards/margins": 2.3892369270324707,
|
| 458 |
+
"rewards/rejected": -4.111651420593262,
|
| 459 |
+
"step": 300
|
| 460 |
+
}
|
| 461 |
+
],
|
| 462 |
+
"logging_steps": 10,
|
| 463 |
+
"max_steps": 580,
|
| 464 |
+
"num_input_tokens_seen": 0,
|
| 465 |
+
"num_train_epochs": 20,
|
| 466 |
+
"save_steps": 50,
|
| 467 |
+
"stateful_callbacks": {
|
| 468 |
+
"TrainerControl": {
|
| 469 |
+
"args": {
|
| 470 |
+
"should_epoch_stop": false,
|
| 471 |
+
"should_evaluate": false,
|
| 472 |
+
"should_log": false,
|
| 473 |
+
"should_save": true,
|
| 474 |
+
"should_training_stop": false
|
| 475 |
+
},
|
| 476 |
+
"attributes": {}
|
| 477 |
+
}
|
| 478 |
+
},
|
| 479 |
+
"total_flos": 1.101550169578537e+18,
|
| 480 |
+
"train_batch_size": 1,
|
| 481 |
+
"trial_name": null,
|
| 482 |
+
"trial_params": null
|
| 483 |
+
}
|
Area_SFT/checkpoint-350/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- 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. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
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).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_SFT/checkpoint-350/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_SFT/checkpoint-350/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Area_SFT/checkpoint-350/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
Area_SFT/checkpoint-350/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Area_SFT/checkpoint-350/tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"additional_special_tokens": [
|
| 40 |
+
"<unk>",
|
| 41 |
+
"<s>",
|
| 42 |
+
"</s>",
|
| 43 |
+
"[PAD]"
|
| 44 |
+
],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"chat_template": "{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"legacy": true,
|
| 50 |
+
"model_max_length": 2048,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"padding_side": "right",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"spaces_between_special_tokens": false,
|
| 55 |
+
"split_special_tokens": false,
|
| 56 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 57 |
+
"unk_token": "<unk>",
|
| 58 |
+
"use_default_system_prompt": true
|
| 59 |
+
}
|
Area_SFT/checkpoint-350/trainer_state.json
ADDED
|
@@ -0,0 +1,558 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 11.803347280334728,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 350,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33472803347280333,
|
| 13 |
+
"grad_norm": 3.9892160892486572,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": -2.315223217010498,
|
| 16 |
+
"logits/rejected": -2.3654401302337646,
|
| 17 |
+
"logps/chosen": -65.86729431152344,
|
| 18 |
+
"logps/rejected": -77.53572845458984,
|
| 19 |
+
"loss": 0.6929,
|
| 20 |
+
"rewards/accuracies": 0.3499999940395355,
|
| 21 |
+
"rewards/chosen": 0.0023138518445193768,
|
| 22 |
+
"rewards/margins": -0.001122759305872023,
|
| 23 |
+
"rewards/rejected": 0.0034366101026535034,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6694560669456067,
|
| 28 |
+
"grad_norm": 3.5659756660461426,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": -2.341399669647217,
|
| 31 |
+
"logits/rejected": -2.3567094802856445,
|
| 32 |
+
"logps/chosen": -66.60242462158203,
|
| 33 |
+
"logps/rejected": -69.70094299316406,
|
| 34 |
+
"loss": 0.6929,
|
| 35 |
+
"rewards/accuracies": 0.512499988079071,
|
| 36 |
+
"rewards/chosen": -0.0013719359412789345,
|
| 37 |
+
"rewards/margins": -0.0035000313073396683,
|
| 38 |
+
"rewards/rejected": 0.002128095831722021,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.00418410041841,
|
| 43 |
+
"grad_norm": 4.912586688995361,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": -2.3429622650146484,
|
| 46 |
+
"logits/rejected": -2.3658394813537598,
|
| 47 |
+
"logps/chosen": -71.6301040649414,
|
| 48 |
+
"logps/rejected": -78.41346740722656,
|
| 49 |
+
"loss": 0.6938,
|
| 50 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 51 |
+
"rewards/chosen": 0.003577103139832616,
|
| 52 |
+
"rewards/margins": 0.00785654503852129,
|
| 53 |
+
"rewards/rejected": -0.004279441200196743,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.3389121338912133,
|
| 58 |
+
"grad_norm": 4.810107707977295,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": -2.3610458374023438,
|
| 61 |
+
"logits/rejected": -2.3885395526885986,
|
| 62 |
+
"logps/chosen": -66.8291244506836,
|
| 63 |
+
"logps/rejected": -62.15415573120117,
|
| 64 |
+
"loss": 0.6893,
|
| 65 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 66 |
+
"rewards/chosen": -6.734435737598687e-05,
|
| 67 |
+
"rewards/margins": 0.006865750066936016,
|
| 68 |
+
"rewards/rejected": -0.0069330958649516106,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6736401673640167,
|
| 73 |
+
"grad_norm": 4.670071125030518,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": -2.304999351501465,
|
| 76 |
+
"logits/rejected": -2.335301399230957,
|
| 77 |
+
"logps/chosen": -75.09913635253906,
|
| 78 |
+
"logps/rejected": -77.72399139404297,
|
| 79 |
+
"loss": 0.6878,
|
| 80 |
+
"rewards/accuracies": 0.612500011920929,
|
| 81 |
+
"rewards/chosen": 0.003225918160751462,
|
| 82 |
+
"rewards/margins": 0.010454346425831318,
|
| 83 |
+
"rewards/rejected": -0.007228427566587925,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.00836820083682,
|
| 88 |
+
"grad_norm": 4.2342000007629395,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": -2.363574504852295,
|
| 91 |
+
"logits/rejected": -2.363882064819336,
|
| 92 |
+
"logps/chosen": -62.84125900268555,
|
| 93 |
+
"logps/rejected": -61.92932891845703,
|
| 94 |
+
"loss": 0.6855,
|
| 95 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 96 |
+
"rewards/chosen": -0.0032769464887678623,
|
| 97 |
+
"rewards/margins": 0.02090405486524105,
|
| 98 |
+
"rewards/rejected": -0.024181004613637924,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3430962343096233,
|
| 103 |
+
"grad_norm": 4.369245529174805,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": -2.378016948699951,
|
| 106 |
+
"logits/rejected": -2.373137950897217,
|
| 107 |
+
"logps/chosen": -74.67327880859375,
|
| 108 |
+
"logps/rejected": -69.20399475097656,
|
| 109 |
+
"loss": 0.668,
|
| 110 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 111 |
+
"rewards/chosen": -0.0003526444488670677,
|
| 112 |
+
"rewards/margins": 0.04865006357431412,
|
| 113 |
+
"rewards/rejected": -0.04900271072983742,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.6778242677824267,
|
| 118 |
+
"grad_norm": 4.444687366485596,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": -2.3403103351593018,
|
| 121 |
+
"logits/rejected": -2.370321273803711,
|
| 122 |
+
"logps/chosen": -77.29728698730469,
|
| 123 |
+
"logps/rejected": -85.79756164550781,
|
| 124 |
+
"loss": 0.6566,
|
| 125 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 126 |
+
"rewards/chosen": 0.0051120575517416,
|
| 127 |
+
"rewards/margins": 0.09415190666913986,
|
| 128 |
+
"rewards/rejected": -0.08903985470533371,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.01255230125523,
|
| 133 |
+
"grad_norm": 4.876573085784912,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": -2.3614611625671387,
|
| 136 |
+
"logits/rejected": -2.385697841644287,
|
| 137 |
+
"logps/chosen": -73.22442626953125,
|
| 138 |
+
"logps/rejected": -82.25682067871094,
|
| 139 |
+
"loss": 0.645,
|
| 140 |
+
"rewards/accuracies": 0.800000011920929,
|
| 141 |
+
"rewards/chosen": -0.016868198290467262,
|
| 142 |
+
"rewards/margins": 0.10679063946008682,
|
| 143 |
+
"rewards/rejected": -0.12365883588790894,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3472803347280333,
|
| 148 |
+
"grad_norm": 4.355966567993164,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": -2.323256254196167,
|
| 151 |
+
"logits/rejected": -2.341057300567627,
|
| 152 |
+
"logps/chosen": -78.37105560302734,
|
| 153 |
+
"logps/rejected": -86.8406982421875,
|
| 154 |
+
"loss": 0.6072,
|
| 155 |
+
"rewards/accuracies": 0.824999988079071,
|
| 156 |
+
"rewards/chosen": -0.015012519434094429,
|
| 157 |
+
"rewards/margins": 0.20561759173870087,
|
| 158 |
+
"rewards/rejected": -0.22063009440898895,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7698744769874475,
|
| 163 |
+
"grad_norm": 4.361391067504883,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": -2.3163838386535645,
|
| 166 |
+
"logits/rejected": -2.3566031455993652,
|
| 167 |
+
"logps/chosen": -83.33145904541016,
|
| 168 |
+
"logps/rejected": -96.48517608642578,
|
| 169 |
+
"loss": 0.5908,
|
| 170 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 171 |
+
"rewards/chosen": -0.08870697021484375,
|
| 172 |
+
"rewards/margins": 0.24879300594329834,
|
| 173 |
+
"rewards/rejected": -0.3374999761581421,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.104602510460251,
|
| 178 |
+
"grad_norm": 4.315061569213867,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": -2.3728129863739014,
|
| 181 |
+
"logits/rejected": -2.3889667987823486,
|
| 182 |
+
"logps/chosen": -73.0484619140625,
|
| 183 |
+
"logps/rejected": -73.4913558959961,
|
| 184 |
+
"loss": 0.5783,
|
| 185 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 186 |
+
"rewards/chosen": -0.0605628564953804,
|
| 187 |
+
"rewards/margins": 0.2945060133934021,
|
| 188 |
+
"rewards/rejected": -0.3550689220428467,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.439330543933054,
|
| 193 |
+
"grad_norm": 4.438860893249512,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": -2.3526523113250732,
|
| 196 |
+
"logits/rejected": -2.364795684814453,
|
| 197 |
+
"logps/chosen": -67.69630432128906,
|
| 198 |
+
"logps/rejected": -84.85731506347656,
|
| 199 |
+
"loss": 0.5338,
|
| 200 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 201 |
+
"rewards/chosen": -0.1054786667227745,
|
| 202 |
+
"rewards/margins": 0.4161924421787262,
|
| 203 |
+
"rewards/rejected": -0.5216711759567261,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.7740585774058575,
|
| 208 |
+
"grad_norm": 4.5405473709106445,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": -2.3756489753723145,
|
| 211 |
+
"logits/rejected": -2.374919891357422,
|
| 212 |
+
"logps/chosen": -68.5466079711914,
|
| 213 |
+
"logps/rejected": -76.15412902832031,
|
| 214 |
+
"loss": 0.5215,
|
| 215 |
+
"rewards/accuracies": 0.824999988079071,
|
| 216 |
+
"rewards/chosen": -0.16213981807231903,
|
| 217 |
+
"rewards/margins": 0.47565969824790955,
|
| 218 |
+
"rewards/rejected": -0.6377995610237122,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.108786610878661,
|
| 223 |
+
"grad_norm": 4.596691608428955,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": -2.428659439086914,
|
| 226 |
+
"logits/rejected": -2.4141571521759033,
|
| 227 |
+
"logps/chosen": -78.08479309082031,
|
| 228 |
+
"logps/rejected": -68.3617172241211,
|
| 229 |
+
"loss": 0.5019,
|
| 230 |
+
"rewards/accuracies": 0.8500000238418579,
|
| 231 |
+
"rewards/chosen": -0.20662447810173035,
|
| 232 |
+
"rewards/margins": 0.4026559889316559,
|
| 233 |
+
"rewards/rejected": -0.6092804670333862,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.443514644351464,
|
| 238 |
+
"grad_norm": 4.364648818969727,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": -2.408982992172241,
|
| 241 |
+
"logits/rejected": -2.4170727729797363,
|
| 242 |
+
"logps/chosen": -81.3556900024414,
|
| 243 |
+
"logps/rejected": -86.85897064208984,
|
| 244 |
+
"loss": 0.4586,
|
| 245 |
+
"rewards/accuracies": 0.824999988079071,
|
| 246 |
+
"rewards/chosen": -0.23941104114055634,
|
| 247 |
+
"rewards/margins": 0.675674319267273,
|
| 248 |
+
"rewards/rejected": -0.9150853157043457,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.7782426778242675,
|
| 253 |
+
"grad_norm": 5.241800308227539,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": -2.4194908142089844,
|
| 256 |
+
"logits/rejected": -2.4498963356018066,
|
| 257 |
+
"logps/chosen": -62.32392120361328,
|
| 258 |
+
"logps/rejected": -76.39479064941406,
|
| 259 |
+
"loss": 0.4442,
|
| 260 |
+
"rewards/accuracies": 0.887499988079071,
|
| 261 |
+
"rewards/chosen": -0.26662638783454895,
|
| 262 |
+
"rewards/margins": 0.6662653088569641,
|
| 263 |
+
"rewards/rejected": -0.9328916668891907,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.112970711297071,
|
| 268 |
+
"grad_norm": 4.73954439163208,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": -2.4365036487579346,
|
| 271 |
+
"logits/rejected": -2.435439348220825,
|
| 272 |
+
"logps/chosen": -73.06513977050781,
|
| 273 |
+
"logps/rejected": -81.04569244384766,
|
| 274 |
+
"loss": 0.4355,
|
| 275 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 276 |
+
"rewards/chosen": -0.37924182415008545,
|
| 277 |
+
"rewards/margins": 0.7773979902267456,
|
| 278 |
+
"rewards/rejected": -1.156639814376831,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.447698744769874,
|
| 283 |
+
"grad_norm": 5.250921726226807,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": -2.387922525405884,
|
| 286 |
+
"logits/rejected": -2.3835678100585938,
|
| 287 |
+
"logps/chosen": -64.85784912109375,
|
| 288 |
+
"logps/rejected": -90.08439636230469,
|
| 289 |
+
"loss": 0.3719,
|
| 290 |
+
"rewards/accuracies": 0.925000011920929,
|
| 291 |
+
"rewards/chosen": -0.42228370904922485,
|
| 292 |
+
"rewards/margins": 1.0562283992767334,
|
| 293 |
+
"rewards/rejected": -1.478512167930603,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.7824267782426775,
|
| 298 |
+
"grad_norm": 5.088508129119873,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": -2.376319169998169,
|
| 301 |
+
"logits/rejected": -2.3985953330993652,
|
| 302 |
+
"logps/chosen": -70.64585876464844,
|
| 303 |
+
"logps/rejected": -89.17048645019531,
|
| 304 |
+
"loss": 0.3829,
|
| 305 |
+
"rewards/accuracies": 0.9375,
|
| 306 |
+
"rewards/chosen": -0.5233972072601318,
|
| 307 |
+
"rewards/margins": 1.1063960790634155,
|
| 308 |
+
"rewards/rejected": -1.629793405532837,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.117154811715481,
|
| 313 |
+
"grad_norm": 4.6062092781066895,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": -2.371851682662964,
|
| 316 |
+
"logits/rejected": -2.3844287395477295,
|
| 317 |
+
"logps/chosen": -74.63328552246094,
|
| 318 |
+
"logps/rejected": -97.81452178955078,
|
| 319 |
+
"loss": 0.3522,
|
| 320 |
+
"rewards/accuracies": 0.925000011920929,
|
| 321 |
+
"rewards/chosen": -0.6278538703918457,
|
| 322 |
+
"rewards/margins": 1.2317354679107666,
|
| 323 |
+
"rewards/rejected": -1.8595889806747437,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.451882845188284,
|
| 328 |
+
"grad_norm": 5.105669021606445,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": -2.4011385440826416,
|
| 331 |
+
"logits/rejected": -2.4039382934570312,
|
| 332 |
+
"logps/chosen": -75.92952728271484,
|
| 333 |
+
"logps/rejected": -78.41490936279297,
|
| 334 |
+
"loss": 0.3219,
|
| 335 |
+
"rewards/accuracies": 0.8999999761581421,
|
| 336 |
+
"rewards/chosen": -0.39645594358444214,
|
| 337 |
+
"rewards/margins": 1.2095177173614502,
|
| 338 |
+
"rewards/rejected": -1.6059738397598267,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.786610878661088,
|
| 343 |
+
"grad_norm": 6.292915344238281,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": -2.3707780838012695,
|
| 346 |
+
"logits/rejected": -2.377169609069824,
|
| 347 |
+
"logps/chosen": -88.07064056396484,
|
| 348 |
+
"logps/rejected": -108.6225814819336,
|
| 349 |
+
"loss": 0.3041,
|
| 350 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 351 |
+
"rewards/chosen": -0.9827474355697632,
|
| 352 |
+
"rewards/margins": 1.3651618957519531,
|
| 353 |
+
"rewards/rejected": -2.3479092121124268,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.121338912133892,
|
| 358 |
+
"grad_norm": 5.0669097900390625,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": -2.3608062267303467,
|
| 361 |
+
"logits/rejected": -2.3792402744293213,
|
| 362 |
+
"logps/chosen": -72.83047485351562,
|
| 363 |
+
"logps/rejected": -91.09341430664062,
|
| 364 |
+
"loss": 0.3065,
|
| 365 |
+
"rewards/accuracies": 0.9125000238418579,
|
| 366 |
+
"rewards/chosen": -0.9334943890571594,
|
| 367 |
+
"rewards/margins": 1.3210034370422363,
|
| 368 |
+
"rewards/rejected": -2.25449800491333,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.456066945606695,
|
| 373 |
+
"grad_norm": 5.0598931312561035,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": -2.324855327606201,
|
| 376 |
+
"logits/rejected": -2.364541530609131,
|
| 377 |
+
"logps/chosen": -90.57644653320312,
|
| 378 |
+
"logps/rejected": -106.41752624511719,
|
| 379 |
+
"loss": 0.2498,
|
| 380 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 381 |
+
"rewards/chosen": -0.8531273007392883,
|
| 382 |
+
"rewards/margins": 1.8315904140472412,
|
| 383 |
+
"rewards/rejected": -2.684717893600464,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.790794979079498,
|
| 388 |
+
"grad_norm": 6.120776653289795,
|
| 389 |
+
"learning_rate": 3.3691733481883693e-06,
|
| 390 |
+
"logits/chosen": -2.3436760902404785,
|
| 391 |
+
"logits/rejected": -2.3720099925994873,
|
| 392 |
+
"logps/chosen": -86.95789337158203,
|
| 393 |
+
"logps/rejected": -102.34903717041016,
|
| 394 |
+
"loss": 0.2532,
|
| 395 |
+
"rewards/accuracies": 0.925000011920929,
|
| 396 |
+
"rewards/chosen": -1.1573801040649414,
|
| 397 |
+
"rewards/margins": 1.7690637111663818,
|
| 398 |
+
"rewards/rejected": -2.9264438152313232,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.125523012552302,
|
| 403 |
+
"grad_norm": 4.666015625,
|
| 404 |
+
"learning_rate": 3.226611521064278e-06,
|
| 405 |
+
"logits/chosen": -2.3132309913635254,
|
| 406 |
+
"logits/rejected": -2.309297800064087,
|
| 407 |
+
"logps/chosen": -78.139404296875,
|
| 408 |
+
"logps/rejected": -99.09760284423828,
|
| 409 |
+
"loss": 0.2314,
|
| 410 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 411 |
+
"rewards/chosen": -1.0649818181991577,
|
| 412 |
+
"rewards/margins": 1.8774713277816772,
|
| 413 |
+
"rewards/rejected": -2.942453384399414,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.460251046025105,
|
| 418 |
+
"grad_norm": 8.85567855834961,
|
| 419 |
+
"learning_rate": 3.0814186389357765e-06,
|
| 420 |
+
"logits/chosen": -2.3629987239837646,
|
| 421 |
+
"logits/rejected": -2.385927200317383,
|
| 422 |
+
"logps/chosen": -91.09283447265625,
|
| 423 |
+
"logps/rejected": -102.37603759765625,
|
| 424 |
+
"loss": 0.2142,
|
| 425 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 426 |
+
"rewards/chosen": -1.5404099225997925,
|
| 427 |
+
"rewards/margins": 2.121422290802002,
|
| 428 |
+
"rewards/rejected": -3.661832094192505,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.794979079497908,
|
| 433 |
+
"grad_norm": 5.228074550628662,
|
| 434 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 435 |
+
"logits/chosen": -2.356905221939087,
|
| 436 |
+
"logits/rejected": -2.3635311126708984,
|
| 437 |
+
"logps/chosen": -91.65778350830078,
|
| 438 |
+
"logps/rejected": -117.89949035644531,
|
| 439 |
+
"loss": 0.1881,
|
| 440 |
+
"rewards/accuracies": 1.0,
|
| 441 |
+
"rewards/chosen": -1.6620346307754517,
|
| 442 |
+
"rewards/margins": 2.1766200065612793,
|
| 443 |
+
"rewards/rejected": -3.8386547565460205,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.129707112970712,
|
| 448 |
+
"grad_norm": 5.115809440612793,
|
| 449 |
+
"learning_rate": 2.785250302445062e-06,
|
| 450 |
+
"logits/chosen": -2.2903695106506348,
|
| 451 |
+
"logits/rejected": -2.2926692962646484,
|
| 452 |
+
"logps/chosen": -104.5173110961914,
|
| 453 |
+
"logps/rejected": -123.13216400146484,
|
| 454 |
+
"loss": 0.1798,
|
| 455 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 456 |
+
"rewards/chosen": -1.7224146127700806,
|
| 457 |
+
"rewards/margins": 2.3892369270324707,
|
| 458 |
+
"rewards/rejected": -4.111651420593262,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.464435146443515,
|
| 463 |
+
"grad_norm": 5.882064342498779,
|
| 464 |
+
"learning_rate": 2.6353472714635443e-06,
|
| 465 |
+
"logits/chosen": -2.2836384773254395,
|
| 466 |
+
"logits/rejected": -2.2969231605529785,
|
| 467 |
+
"logps/chosen": -88.8235855102539,
|
| 468 |
+
"logps/rejected": -119.67433166503906,
|
| 469 |
+
"loss": 0.1558,
|
| 470 |
+
"rewards/accuracies": 0.987500011920929,
|
| 471 |
+
"rewards/chosen": -1.6937462091445923,
|
| 472 |
+
"rewards/margins": 2.4059743881225586,
|
| 473 |
+
"rewards/rejected": -4.0997209548950195,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 10.799163179916318,
|
| 478 |
+
"grad_norm": 6.9003376960754395,
|
| 479 |
+
"learning_rate": 2.4849541490017868e-06,
|
| 480 |
+
"logits/chosen": -2.289567232131958,
|
| 481 |
+
"logits/rejected": -2.3216423988342285,
|
| 482 |
+
"logps/chosen": -90.58432006835938,
|
| 483 |
+
"logps/rejected": -118.13006591796875,
|
| 484 |
+
"loss": 0.1538,
|
| 485 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 486 |
+
"rewards/chosen": -1.6574989557266235,
|
| 487 |
+
"rewards/margins": 2.9354054927825928,
|
| 488 |
+
"rewards/rejected": -4.592904567718506,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.133891213389122,
|
| 493 |
+
"grad_norm": 4.916522979736328,
|
| 494 |
+
"learning_rate": 2.3346155074564712e-06,
|
| 495 |
+
"logits/chosen": -2.2699310779571533,
|
| 496 |
+
"logits/rejected": -2.3001017570495605,
|
| 497 |
+
"logps/chosen": -100.2576675415039,
|
| 498 |
+
"logps/rejected": -133.8759307861328,
|
| 499 |
+
"loss": 0.1373,
|
| 500 |
+
"rewards/accuracies": 0.9750000238418579,
|
| 501 |
+
"rewards/chosen": -2.174388885498047,
|
| 502 |
+
"rewards/margins": 3.038696050643921,
|
| 503 |
+
"rewards/rejected": -5.213086128234863,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 11.468619246861925,
|
| 508 |
+
"grad_norm": 6.739722728729248,
|
| 509 |
+
"learning_rate": 2.184875721949277e-06,
|
| 510 |
+
"logits/chosen": -2.2740581035614014,
|
| 511 |
+
"logits/rejected": -2.315854549407959,
|
| 512 |
+
"logps/chosen": -83.28224182128906,
|
| 513 |
+
"logps/rejected": -107.7516098022461,
|
| 514 |
+
"loss": 0.1257,
|
| 515 |
+
"rewards/accuracies": 0.9624999761581421,
|
| 516 |
+
"rewards/chosen": -1.777440071105957,
|
| 517 |
+
"rewards/margins": 2.704913377761841,
|
| 518 |
+
"rewards/rejected": -4.482353687286377,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 11.803347280334728,
|
| 523 |
+
"grad_norm": 4.988001823425293,
|
| 524 |
+
"learning_rate": 2.0362769991485514e-06,
|
| 525 |
+
"logits/chosen": -2.2616047859191895,
|
| 526 |
+
"logits/rejected": -2.2596449851989746,
|
| 527 |
+
"logps/chosen": -107.07649230957031,
|
| 528 |
+
"logps/rejected": -139.80697631835938,
|
| 529 |
+
"loss": 0.1184,
|
| 530 |
+
"rewards/accuracies": 0.987500011920929,
|
| 531 |
+
"rewards/chosen": -2.618734359741211,
|
| 532 |
+
"rewards/margins": 3.291966199874878,
|
| 533 |
+
"rewards/rejected": -5.910700798034668,
|
| 534 |
+
"step": 350
|
| 535 |
+
}
|
| 536 |
+
],
|
| 537 |
+
"logging_steps": 10,
|
| 538 |
+
"max_steps": 580,
|
| 539 |
+
"num_input_tokens_seen": 0,
|
| 540 |
+
"num_train_epochs": 20,
|
| 541 |
+
"save_steps": 50,
|
| 542 |
+
"stateful_callbacks": {
|
| 543 |
+
"TrainerControl": {
|
| 544 |
+
"args": {
|
| 545 |
+
"should_epoch_stop": false,
|
| 546 |
+
"should_evaluate": false,
|
| 547 |
+
"should_log": false,
|
| 548 |
+
"should_save": true,
|
| 549 |
+
"should_training_stop": false
|
| 550 |
+
},
|
| 551 |
+
"attributes": {}
|
| 552 |
+
}
|
| 553 |
+
},
|
| 554 |
+
"total_flos": 1.2844619024658596e+18,
|
| 555 |
+
"train_batch_size": 1,
|
| 556 |
+
"trial_name": null,
|
| 557 |
+
"trial_params": null
|
| 558 |
+
}
|
Area_SFT/checkpoint-400/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ishorn5/RTLCoder-v1.1
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- 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. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
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).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Area_SFT/checkpoint-400/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ishorn5/RTLCoder-v1.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"k_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Area_SFT/checkpoint-400/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
Area_SFT/checkpoint-400/special_tokens_map.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>",
|
| 6 |
+
"[PAD]"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": {
|
| 9 |
+
"content": "<s>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"eos_token": {
|
| 16 |
+
"content": "</s>",
|
| 17 |
+
"lstrip": false,
|
| 18 |
+
"normalized": false,
|
| 19 |
+
"rstrip": false,
|
| 20 |
+
"single_word": false
|
| 21 |
+
},
|
| 22 |
+
"pad_token": {
|
| 23 |
+
"content": "[PAD]",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
+
"unk_token": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
}
|
| 36 |
+
}
|
Area_SFT/checkpoint-400/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|