Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +81 -0
- checkpoint-100/README.md +204 -0
- checkpoint-100/adapter_config.json +29 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +29 -0
- checkpoint-100/tokenizer.json +0 -0
- checkpoint-100/tokenizer.model +3 -0
- checkpoint-100/tokenizer_config.json +50 -0
- checkpoint-100/trainer_state.json +112 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-200/README.md +204 -0
- checkpoint-200/adapter_config.json +29 -0
- checkpoint-200/adapter_model.safetensors +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +29 -0
- checkpoint-200/tokenizer.json +0 -0
- checkpoint-200/tokenizer.model +3 -0
- checkpoint-200/tokenizer_config.json +50 -0
- checkpoint-200/trainer_state.json +203 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-300/README.md +204 -0
- checkpoint-300/adapter_config.json +29 -0
- checkpoint-300/adapter_model.safetensors +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +29 -0
- checkpoint-300/tokenizer.json +0 -0
- checkpoint-300/tokenizer.model +3 -0
- checkpoint-300/tokenizer_config.json +50 -0
- checkpoint-300/trainer_state.json +294 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-400/README.md +204 -0
- checkpoint-400/adapter_config.json +29 -0
- checkpoint-400/adapter_model.safetensors +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/special_tokens_map.json +29 -0
- checkpoint-400/tokenizer.json +0 -0
- checkpoint-400/tokenizer.model +3 -0
- checkpoint-400/tokenizer_config.json +50 -0
- checkpoint-400/trainer_state.json +385 -0
- checkpoint-400/training_args.bin +3 -0
- checkpoint-500/README.md +204 -0
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
library_name: "trl"
|
4 |
+
tags:
|
5 |
+
- DPO
|
6 |
+
- WeniGPT
|
7 |
+
base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
|
8 |
+
model-index:
|
9 |
+
- name: Weni/WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ
|
10 |
+
results: []
|
11 |
+
language: ['en']
|
12 |
+
---
|
13 |
+
|
14 |
+
# Weni/WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT] on the dataset HuggingFaceH4/ultrafeedback_binarized with the DPO trainer. It is part of the WeniGPT project for [Weni](https://weni.ai/).
|
17 |
+
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
{'eval_loss': 1.9277071952819824, 'eval_runtime': 94.1066, 'eval_samples_per_second': 2.125, 'eval_steps_per_second': 0.531, 'eval_rewards/chosen': 18.78862190246582, 'eval_rewards/rejected': 13.151841163635254, 'eval_rewards/accuracies': 0.5350000262260437, 'eval_rewards/margins': 5.63677978515625, 'eval_logps/rejected': -329.4024658203125, 'eval_logps/chosen': -334.51287841796875, 'eval_logits/rejected': -2.746166467666626, 'eval_logits/chosen': -2.7368459701538086, 'epoch': 7.96}
|
20 |
+
|
21 |
+
## Intended uses & limitations
|
22 |
+
|
23 |
+
This model has not been trained to avoid specific intructions.
|
24 |
+
|
25 |
+
## Training procedure
|
26 |
+
|
27 |
+
Finetuning was done on the model Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT with the following prompt:
|
28 |
+
|
29 |
+
```
|
30 |
+
Prompt:
|
31 |
+
<|user|>{prompt}</s>
|
32 |
+
|
33 |
+
|
34 |
+
Chosen:
|
35 |
+
<|assistant|>{chosen}</s>
|
36 |
+
|
37 |
+
|
38 |
+
Rejected:
|
39 |
+
<|assistant|>{rejected}</s>
|
40 |
+
```
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 0.0002
|
46 |
+
- per_device_train_batch_size: 4
|
47 |
+
- per_device_eval_batch_size: 4
|
48 |
+
- gradient_accumulation_steps: 4
|
49 |
+
- num_gpus: 1
|
50 |
+
- total_train_batch_size: 16
|
51 |
+
- optimizer: AdamW
|
52 |
+
- lr_scheduler_type: cosine
|
53 |
+
- num_steps: 896
|
54 |
+
- quantization_type: gptq
|
55 |
+
- LoRA: ("\n - bits: 4\n - use_exllama: True\n - device_map: auto\n - use_cache: False\n - lora_r: 16\n - lora_alpha: 16\n - lora_dropout: 0.05\n - bias: none\n - target_modules: ['q_proj', 'k_proj', 'v_proj', 'o_proj']\n - task_type: CAUSAL_LM",)
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
### Framework versions
|
60 |
+
|
61 |
+
- transformers==4.38.2
|
62 |
+
- datasets==2.17.1
|
63 |
+
- peft==0.8.2
|
64 |
+
- safetensors==0.4.2
|
65 |
+
- evaluate==0.4.1
|
66 |
+
- bitsandbytes==0.42
|
67 |
+
- huggingface_hub==0.20.3
|
68 |
+
- seqeval==1.2.2
|
69 |
+
- optimum==1.17.1
|
70 |
+
- auto-gptq==0.7.0
|
71 |
+
- gpustat==1.1.1
|
72 |
+
- deepspeed==0.13.2
|
73 |
+
- wandb==0.16.3
|
74 |
+
- trl==0.7.11
|
75 |
+
- accelerate==0.27.2
|
76 |
+
- coloredlogs==15.0.1
|
77 |
+
- traitlets==5.14.1
|
78 |
+
- autoawq@https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.0/autoawq-0.2.0+cu118-cp310-cp310-linux_x86_64.whl
|
79 |
+
|
80 |
+
### Hardware
|
81 |
+
- Cloud provided: runpod.io
|
checkpoint-100/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-100/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"o_proj",
|
23 |
+
"k_proj",
|
24 |
+
"q_proj",
|
25 |
+
"v_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88433522cb21b0ecb7788c520895e34dc5661b6c1933a5484f8b39bec1e24375
|
3 |
+
size 54560368
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a0f2cda1db186d6fc85b387d24af1c604746f6e18eb34e88f5a6264f234eebf
|
3 |
+
size 109267450
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
|
3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b477035e30bed4c4a6bb69d7df73b19925bc0eb0c504817df41db5cf3395b904
|
3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": "<unk>",
|
22 |
+
"unk_token": {
|
23 |
+
"content": "<unk>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
}
|
29 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-100/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-100/tokenizer_config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"max_lenght": 2048,
|
41 |
+
"model_max_length": 1000000000000000019884624838656,
|
42 |
+
"pad_token": "<unk>",
|
43 |
+
"padding": true,
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"truncation_side": "left",
|
48 |
+
"unk_token": "<unk>",
|
49 |
+
"use_default_system_prompt": true
|
50 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.9277071952819824,
|
3 |
+
"best_model_checkpoint": "./Zephyr/08-03-24-Weni-WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ_DPO tests with binarized dataset GPTQ-2_max_steps-896_batch_16_2024-03-08_ppid_7990/checkpoint-100",
|
4 |
+
"epoch": 0.8888888888888888,
|
5 |
+
"eval_steps": 100,
|
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": 0.18,
|
13 |
+
"grad_norm": 119.0400161743164,
|
14 |
+
"learning_rate": 3.111111111111111e-05,
|
15 |
+
"logits/chosen": -2.6437883377075195,
|
16 |
+
"logits/rejected": -2.640676498413086,
|
17 |
+
"logps/chosen": -346.0354309082031,
|
18 |
+
"logps/rejected": -315.1640319824219,
|
19 |
+
"loss": 0.6706,
|
20 |
+
"rewards/accuracies": 0.30000001192092896,
|
21 |
+
"rewards/chosen": 0.2039356678724289,
|
22 |
+
"rewards/margins": 0.1839628666639328,
|
23 |
+
"rewards/rejected": 0.019972801208496094,
|
24 |
+
"step": 20
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.36,
|
28 |
+
"grad_norm": 55.844058990478516,
|
29 |
+
"learning_rate": 7.555555555555556e-05,
|
30 |
+
"logits/chosen": -2.7053043842315674,
|
31 |
+
"logits/rejected": -2.706561326980591,
|
32 |
+
"logps/chosen": -348.75,
|
33 |
+
"logps/rejected": -336.07830810546875,
|
34 |
+
"loss": 0.7255,
|
35 |
+
"rewards/accuracies": 0.5062500238418579,
|
36 |
+
"rewards/chosen": -0.3999950885772705,
|
37 |
+
"rewards/margins": 0.9534912109375,
|
38 |
+
"rewards/rejected": -1.3534862995147705,
|
39 |
+
"step": 40
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.53,
|
43 |
+
"grad_norm": 156.59803771972656,
|
44 |
+
"learning_rate": 0.00011777777777777779,
|
45 |
+
"logits/chosen": -2.644763946533203,
|
46 |
+
"logits/rejected": -2.6682467460632324,
|
47 |
+
"logps/chosen": -352.20233154296875,
|
48 |
+
"logps/rejected": -343.33941650390625,
|
49 |
+
"loss": 0.8382,
|
50 |
+
"rewards/accuracies": 0.5718749761581421,
|
51 |
+
"rewards/chosen": 2.873349189758301,
|
52 |
+
"rewards/margins": 1.9845993518829346,
|
53 |
+
"rewards/rejected": 0.8887494802474976,
|
54 |
+
"step": 60
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.71,
|
58 |
+
"grad_norm": 113.42001342773438,
|
59 |
+
"learning_rate": 0.00016222222222222224,
|
60 |
+
"logits/chosen": -2.652919292449951,
|
61 |
+
"logits/rejected": -2.663282871246338,
|
62 |
+
"logps/chosen": -350.60443115234375,
|
63 |
+
"logps/rejected": -333.491455078125,
|
64 |
+
"loss": 1.6409,
|
65 |
+
"rewards/accuracies": 0.512499988079071,
|
66 |
+
"rewards/chosen": 4.428155899047852,
|
67 |
+
"rewards/margins": 2.1724541187286377,
|
68 |
+
"rewards/rejected": 2.255702018737793,
|
69 |
+
"step": 80
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.89,
|
73 |
+
"grad_norm": 77.21934509277344,
|
74 |
+
"learning_rate": 0.0001992555831265509,
|
75 |
+
"logits/chosen": -2.6474595069885254,
|
76 |
+
"logits/rejected": -2.6597702503204346,
|
77 |
+
"logps/chosen": -318.25653076171875,
|
78 |
+
"logps/rejected": -302.04241943359375,
|
79 |
+
"loss": 1.9207,
|
80 |
+
"rewards/accuracies": 0.4937500059604645,
|
81 |
+
"rewards/chosen": 14.573875427246094,
|
82 |
+
"rewards/margins": 3.523595094680786,
|
83 |
+
"rewards/rejected": 11.050280570983887,
|
84 |
+
"step": 100
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.89,
|
88 |
+
"eval_logits/chosen": -2.7368459701538086,
|
89 |
+
"eval_logits/rejected": -2.746166467666626,
|
90 |
+
"eval_logps/chosen": -334.51287841796875,
|
91 |
+
"eval_logps/rejected": -329.4024658203125,
|
92 |
+
"eval_loss": 1.9277071952819824,
|
93 |
+
"eval_rewards/accuracies": 0.5350000262260437,
|
94 |
+
"eval_rewards/chosen": 18.78862190246582,
|
95 |
+
"eval_rewards/margins": 5.63677978515625,
|
96 |
+
"eval_rewards/rejected": 13.151841163635254,
|
97 |
+
"eval_runtime": 94.4139,
|
98 |
+
"eval_samples_per_second": 2.118,
|
99 |
+
"eval_steps_per_second": 0.53,
|
100 |
+
"step": 100
|
101 |
+
}
|
102 |
+
],
|
103 |
+
"logging_steps": 20,
|
104 |
+
"max_steps": 896,
|
105 |
+
"num_input_tokens_seen": 0,
|
106 |
+
"num_train_epochs": 8,
|
107 |
+
"save_steps": 100,
|
108 |
+
"total_flos": 0.0,
|
109 |
+
"train_batch_size": 4,
|
110 |
+
"trial_name": null,
|
111 |
+
"trial_params": null
|
112 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:898e690ae745f178ef08f4c9b66ce0008ccd31de52b82b4a69ad2f00dceee1bc
|
3 |
+
size 5240
|
checkpoint-200/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-200/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"o_proj",
|
23 |
+
"k_proj",
|
24 |
+
"q_proj",
|
25 |
+
"v_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
checkpoint-200/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cd996197ac66f3a24e277e89146b7db1fb2d9cdc58f7a0a2596eb54a03588d9
|
3 |
+
size 54560368
|
checkpoint-200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3bf0ac36373a8f93c5d01349ff062b94ddc03297178ec639e0e9e0b1741496f
|
3 |
+
size 109267450
|
checkpoint-200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
|
3 |
+
size 14244
|
checkpoint-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7c17afb046167ee43f28f8156a519a2fce750d5105142dc43084428a2506bb5
|
3 |
+
size 1064
|
checkpoint-200/special_tokens_map.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": "<unk>",
|
22 |
+
"unk_token": {
|
23 |
+
"content": "<unk>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
}
|
29 |
+
}
|
checkpoint-200/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-200/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-200/tokenizer_config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"max_lenght": 2048,
|
41 |
+
"model_max_length": 1000000000000000019884624838656,
|
42 |
+
"pad_token": "<unk>",
|
43 |
+
"padding": true,
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"truncation_side": "left",
|
48 |
+
"unk_token": "<unk>",
|
49 |
+
"use_default_system_prompt": true
|
50 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.9277071952819824,
|
3 |
+
"best_model_checkpoint": "./Zephyr/08-03-24-Weni-WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ_DPO tests with binarized dataset GPTQ-2_max_steps-896_batch_16_2024-03-08_ppid_7990/checkpoint-100",
|
4 |
+
"epoch": 1.7777777777777777,
|
5 |
+
"eval_steps": 100,
|
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": 0.18,
|
13 |
+
"grad_norm": 119.0400161743164,
|
14 |
+
"learning_rate": 3.111111111111111e-05,
|
15 |
+
"logits/chosen": -2.6437883377075195,
|
16 |
+
"logits/rejected": -2.640676498413086,
|
17 |
+
"logps/chosen": -346.0354309082031,
|
18 |
+
"logps/rejected": -315.1640319824219,
|
19 |
+
"loss": 0.6706,
|
20 |
+
"rewards/accuracies": 0.30000001192092896,
|
21 |
+
"rewards/chosen": 0.2039356678724289,
|
22 |
+
"rewards/margins": 0.1839628666639328,
|
23 |
+
"rewards/rejected": 0.019972801208496094,
|
24 |
+
"step": 20
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.36,
|
28 |
+
"grad_norm": 55.844058990478516,
|
29 |
+
"learning_rate": 7.555555555555556e-05,
|
30 |
+
"logits/chosen": -2.7053043842315674,
|
31 |
+
"logits/rejected": -2.706561326980591,
|
32 |
+
"logps/chosen": -348.75,
|
33 |
+
"logps/rejected": -336.07830810546875,
|
34 |
+
"loss": 0.7255,
|
35 |
+
"rewards/accuracies": 0.5062500238418579,
|
36 |
+
"rewards/chosen": -0.3999950885772705,
|
37 |
+
"rewards/margins": 0.9534912109375,
|
38 |
+
"rewards/rejected": -1.3534862995147705,
|
39 |
+
"step": 40
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.53,
|
43 |
+
"grad_norm": 156.59803771972656,
|
44 |
+
"learning_rate": 0.00011777777777777779,
|
45 |
+
"logits/chosen": -2.644763946533203,
|
46 |
+
"logits/rejected": -2.6682467460632324,
|
47 |
+
"logps/chosen": -352.20233154296875,
|
48 |
+
"logps/rejected": -343.33941650390625,
|
49 |
+
"loss": 0.8382,
|
50 |
+
"rewards/accuracies": 0.5718749761581421,
|
51 |
+
"rewards/chosen": 2.873349189758301,
|
52 |
+
"rewards/margins": 1.9845993518829346,
|
53 |
+
"rewards/rejected": 0.8887494802474976,
|
54 |
+
"step": 60
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.71,
|
58 |
+
"grad_norm": 113.42001342773438,
|
59 |
+
"learning_rate": 0.00016222222222222224,
|
60 |
+
"logits/chosen": -2.652919292449951,
|
61 |
+
"logits/rejected": -2.663282871246338,
|
62 |
+
"logps/chosen": -350.60443115234375,
|
63 |
+
"logps/rejected": -333.491455078125,
|
64 |
+
"loss": 1.6409,
|
65 |
+
"rewards/accuracies": 0.512499988079071,
|
66 |
+
"rewards/chosen": 4.428155899047852,
|
67 |
+
"rewards/margins": 2.1724541187286377,
|
68 |
+
"rewards/rejected": 2.255702018737793,
|
69 |
+
"step": 80
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.89,
|
73 |
+
"grad_norm": 77.21934509277344,
|
74 |
+
"learning_rate": 0.0001992555831265509,
|
75 |
+
"logits/chosen": -2.6474595069885254,
|
76 |
+
"logits/rejected": -2.6597702503204346,
|
77 |
+
"logps/chosen": -318.25653076171875,
|
78 |
+
"logps/rejected": -302.04241943359375,
|
79 |
+
"loss": 1.9207,
|
80 |
+
"rewards/accuracies": 0.4937500059604645,
|
81 |
+
"rewards/chosen": 14.573875427246094,
|
82 |
+
"rewards/margins": 3.523595094680786,
|
83 |
+
"rewards/rejected": 11.050280570983887,
|
84 |
+
"step": 100
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.89,
|
88 |
+
"eval_logits/chosen": -2.7368459701538086,
|
89 |
+
"eval_logits/rejected": -2.746166467666626,
|
90 |
+
"eval_logps/chosen": -334.51287841796875,
|
91 |
+
"eval_logps/rejected": -329.4024658203125,
|
92 |
+
"eval_loss": 1.9277071952819824,
|
93 |
+
"eval_rewards/accuracies": 0.5350000262260437,
|
94 |
+
"eval_rewards/chosen": 18.78862190246582,
|
95 |
+
"eval_rewards/margins": 5.63677978515625,
|
96 |
+
"eval_rewards/rejected": 13.151841163635254,
|
97 |
+
"eval_runtime": 94.4139,
|
98 |
+
"eval_samples_per_second": 2.118,
|
99 |
+
"eval_steps_per_second": 0.53,
|
100 |
+
"step": 100
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.07,
|
104 |
+
"grad_norm": 83.98187255859375,
|
105 |
+
"learning_rate": 0.00019429280397022334,
|
106 |
+
"logits/chosen": -2.639448642730713,
|
107 |
+
"logits/rejected": -2.6476964950561523,
|
108 |
+
"logps/chosen": -316.87982177734375,
|
109 |
+
"logps/rejected": -308.38568115234375,
|
110 |
+
"loss": 1.7601,
|
111 |
+
"rewards/accuracies": 0.5562499761581421,
|
112 |
+
"rewards/chosen": 27.463403701782227,
|
113 |
+
"rewards/margins": 10.681607246398926,
|
114 |
+
"rewards/rejected": 16.781795501708984,
|
115 |
+
"step": 120
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.24,
|
119 |
+
"grad_norm": 0.0,
|
120 |
+
"learning_rate": 0.0001893300248138958,
|
121 |
+
"logits/chosen": -2.6575229167938232,
|
122 |
+
"logits/rejected": -2.6546902656555176,
|
123 |
+
"logps/chosen": -350.1793212890625,
|
124 |
+
"logps/rejected": -348.28985595703125,
|
125 |
+
"loss": 1.8357,
|
126 |
+
"rewards/accuracies": 0.6156250238418579,
|
127 |
+
"rewards/chosen": -23.570585250854492,
|
128 |
+
"rewards/margins": 16.757661819458008,
|
129 |
+
"rewards/rejected": -40.32825469970703,
|
130 |
+
"step": 140
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 1.42,
|
134 |
+
"grad_norm": 1.0552074909210205,
|
135 |
+
"learning_rate": 0.00018436724565756824,
|
136 |
+
"logits/chosen": -2.690781831741333,
|
137 |
+
"logits/rejected": -2.691371440887451,
|
138 |
+
"logps/chosen": -403.81378173828125,
|
139 |
+
"logps/rejected": -407.43475341796875,
|
140 |
+
"loss": 1.4241,
|
141 |
+
"rewards/accuracies": 0.6343749761581421,
|
142 |
+
"rewards/chosen": -46.7193489074707,
|
143 |
+
"rewards/margins": 20.419803619384766,
|
144 |
+
"rewards/rejected": -67.13915252685547,
|
145 |
+
"step": 160
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 1.6,
|
149 |
+
"grad_norm": 88.9915771484375,
|
150 |
+
"learning_rate": 0.0001794044665012407,
|
151 |
+
"logits/chosen": -2.6750125885009766,
|
152 |
+
"logits/rejected": -2.682309627532959,
|
153 |
+
"logps/chosen": -399.62066650390625,
|
154 |
+
"logps/rejected": -409.8529357910156,
|
155 |
+
"loss": 1.9108,
|
156 |
+
"rewards/accuracies": 0.621874988079071,
|
157 |
+
"rewards/chosen": -49.57743453979492,
|
158 |
+
"rewards/margins": 20.643938064575195,
|
159 |
+
"rewards/rejected": -70.22136688232422,
|
160 |
+
"step": 180
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 1.78,
|
164 |
+
"grad_norm": 138.35623168945312,
|
165 |
+
"learning_rate": 0.00017444168734491314,
|
166 |
+
"logits/chosen": -2.7050137519836426,
|
167 |
+
"logits/rejected": -2.712310552597046,
|
168 |
+
"logps/chosen": -397.1112365722656,
|
169 |
+
"logps/rejected": -406.0185852050781,
|
170 |
+
"loss": 2.0578,
|
171 |
+
"rewards/accuracies": 0.574999988079071,
|
172 |
+
"rewards/chosen": -53.7899284362793,
|
173 |
+
"rewards/margins": 17.770038604736328,
|
174 |
+
"rewards/rejected": -71.55997467041016,
|
175 |
+
"step": 200
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 1.78,
|
179 |
+
"eval_logits/chosen": -2.6775686740875244,
|
180 |
+
"eval_logits/rejected": -2.6850674152374268,
|
181 |
+
"eval_logps/chosen": -419.0586242675781,
|
182 |
+
"eval_logps/rejected": -420.5866394042969,
|
183 |
+
"eval_loss": 2.5765089988708496,
|
184 |
+
"eval_rewards/accuracies": 0.550000011920929,
|
185 |
+
"eval_rewards/chosen": -65.75714874267578,
|
186 |
+
"eval_rewards/margins": 12.275188446044922,
|
187 |
+
"eval_rewards/rejected": -78.03234100341797,
|
188 |
+
"eval_runtime": 94.1202,
|
189 |
+
"eval_samples_per_second": 2.125,
|
190 |
+
"eval_steps_per_second": 0.531,
|
191 |
+
"step": 200
|
192 |
+
}
|
193 |
+
],
|
194 |
+
"logging_steps": 20,
|
195 |
+
"max_steps": 896,
|
196 |
+
"num_input_tokens_seen": 0,
|
197 |
+
"num_train_epochs": 8,
|
198 |
+
"save_steps": 100,
|
199 |
+
"total_flos": 0.0,
|
200 |
+
"train_batch_size": 4,
|
201 |
+
"trial_name": null,
|
202 |
+
"trial_params": null
|
203 |
+
}
|
checkpoint-200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:898e690ae745f178ef08f4c9b66ce0008ccd31de52b82b4a69ad2f00dceee1bc
|
3 |
+
size 5240
|
checkpoint-300/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-300/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"o_proj",
|
23 |
+
"k_proj",
|
24 |
+
"q_proj",
|
25 |
+
"v_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
checkpoint-300/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a72c605b93467dd1b7f68344843aa84f436b832ce4def01ddcef84196ebaabf8
|
3 |
+
size 54560368
|
checkpoint-300/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:538f2ea1ffe7d735bb5e07d833331d88004508639cdd218592fdd53a4aa4386b
|
3 |
+
size 109267450
|
checkpoint-300/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
|
3 |
+
size 14244
|
checkpoint-300/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd7d4e662af47ddf5d1dbe0d024bb600405fb97dc2e6f174b4758df92d5d82d6
|
3 |
+
size 1064
|
checkpoint-300/special_tokens_map.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": "<unk>",
|
22 |
+
"unk_token": {
|
23 |
+
"content": "<unk>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
}
|
29 |
+
}
|
checkpoint-300/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-300/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-300/tokenizer_config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"max_lenght": 2048,
|
41 |
+
"model_max_length": 1000000000000000019884624838656,
|
42 |
+
"pad_token": "<unk>",
|
43 |
+
"padding": true,
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"truncation_side": "left",
|
48 |
+
"unk_token": "<unk>",
|
49 |
+
"use_default_system_prompt": true
|
50 |
+
}
|
checkpoint-300/trainer_state.json
ADDED
@@ -0,0 +1,294 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.9277071952819824,
|
3 |
+
"best_model_checkpoint": "./Zephyr/08-03-24-Weni-WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ_DPO tests with binarized dataset GPTQ-2_max_steps-896_batch_16_2024-03-08_ppid_7990/checkpoint-100",
|
4 |
+
"epoch": 2.6666666666666665,
|
5 |
+
"eval_steps": 100,
|
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": 0.18,
|
13 |
+
"grad_norm": 119.0400161743164,
|
14 |
+
"learning_rate": 3.111111111111111e-05,
|
15 |
+
"logits/chosen": -2.6437883377075195,
|
16 |
+
"logits/rejected": -2.640676498413086,
|
17 |
+
"logps/chosen": -346.0354309082031,
|
18 |
+
"logps/rejected": -315.1640319824219,
|
19 |
+
"loss": 0.6706,
|
20 |
+
"rewards/accuracies": 0.30000001192092896,
|
21 |
+
"rewards/chosen": 0.2039356678724289,
|
22 |
+
"rewards/margins": 0.1839628666639328,
|
23 |
+
"rewards/rejected": 0.019972801208496094,
|
24 |
+
"step": 20
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.36,
|
28 |
+
"grad_norm": 55.844058990478516,
|
29 |
+
"learning_rate": 7.555555555555556e-05,
|
30 |
+
"logits/chosen": -2.7053043842315674,
|
31 |
+
"logits/rejected": -2.706561326980591,
|
32 |
+
"logps/chosen": -348.75,
|
33 |
+
"logps/rejected": -336.07830810546875,
|
34 |
+
"loss": 0.7255,
|
35 |
+
"rewards/accuracies": 0.5062500238418579,
|
36 |
+
"rewards/chosen": -0.3999950885772705,
|
37 |
+
"rewards/margins": 0.9534912109375,
|
38 |
+
"rewards/rejected": -1.3534862995147705,
|
39 |
+
"step": 40
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.53,
|
43 |
+
"grad_norm": 156.59803771972656,
|
44 |
+
"learning_rate": 0.00011777777777777779,
|
45 |
+
"logits/chosen": -2.644763946533203,
|
46 |
+
"logits/rejected": -2.6682467460632324,
|
47 |
+
"logps/chosen": -352.20233154296875,
|
48 |
+
"logps/rejected": -343.33941650390625,
|
49 |
+
"loss": 0.8382,
|
50 |
+
"rewards/accuracies": 0.5718749761581421,
|
51 |
+
"rewards/chosen": 2.873349189758301,
|
52 |
+
"rewards/margins": 1.9845993518829346,
|
53 |
+
"rewards/rejected": 0.8887494802474976,
|
54 |
+
"step": 60
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.71,
|
58 |
+
"grad_norm": 113.42001342773438,
|
59 |
+
"learning_rate": 0.00016222222222222224,
|
60 |
+
"logits/chosen": -2.652919292449951,
|
61 |
+
"logits/rejected": -2.663282871246338,
|
62 |
+
"logps/chosen": -350.60443115234375,
|
63 |
+
"logps/rejected": -333.491455078125,
|
64 |
+
"loss": 1.6409,
|
65 |
+
"rewards/accuracies": 0.512499988079071,
|
66 |
+
"rewards/chosen": 4.428155899047852,
|
67 |
+
"rewards/margins": 2.1724541187286377,
|
68 |
+
"rewards/rejected": 2.255702018737793,
|
69 |
+
"step": 80
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.89,
|
73 |
+
"grad_norm": 77.21934509277344,
|
74 |
+
"learning_rate": 0.0001992555831265509,
|
75 |
+
"logits/chosen": -2.6474595069885254,
|
76 |
+
"logits/rejected": -2.6597702503204346,
|
77 |
+
"logps/chosen": -318.25653076171875,
|
78 |
+
"logps/rejected": -302.04241943359375,
|
79 |
+
"loss": 1.9207,
|
80 |
+
"rewards/accuracies": 0.4937500059604645,
|
81 |
+
"rewards/chosen": 14.573875427246094,
|
82 |
+
"rewards/margins": 3.523595094680786,
|
83 |
+
"rewards/rejected": 11.050280570983887,
|
84 |
+
"step": 100
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.89,
|
88 |
+
"eval_logits/chosen": -2.7368459701538086,
|
89 |
+
"eval_logits/rejected": -2.746166467666626,
|
90 |
+
"eval_logps/chosen": -334.51287841796875,
|
91 |
+
"eval_logps/rejected": -329.4024658203125,
|
92 |
+
"eval_loss": 1.9277071952819824,
|
93 |
+
"eval_rewards/accuracies": 0.5350000262260437,
|
94 |
+
"eval_rewards/chosen": 18.78862190246582,
|
95 |
+
"eval_rewards/margins": 5.63677978515625,
|
96 |
+
"eval_rewards/rejected": 13.151841163635254,
|
97 |
+
"eval_runtime": 94.4139,
|
98 |
+
"eval_samples_per_second": 2.118,
|
99 |
+
"eval_steps_per_second": 0.53,
|
100 |
+
"step": 100
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.07,
|
104 |
+
"grad_norm": 83.98187255859375,
|
105 |
+
"learning_rate": 0.00019429280397022334,
|
106 |
+
"logits/chosen": -2.639448642730713,
|
107 |
+
"logits/rejected": -2.6476964950561523,
|
108 |
+
"logps/chosen": -316.87982177734375,
|
109 |
+
"logps/rejected": -308.38568115234375,
|
110 |
+
"loss": 1.7601,
|
111 |
+
"rewards/accuracies": 0.5562499761581421,
|
112 |
+
"rewards/chosen": 27.463403701782227,
|
113 |
+
"rewards/margins": 10.681607246398926,
|
114 |
+
"rewards/rejected": 16.781795501708984,
|
115 |
+
"step": 120
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.24,
|
119 |
+
"grad_norm": 0.0,
|
120 |
+
"learning_rate": 0.0001893300248138958,
|
121 |
+
"logits/chosen": -2.6575229167938232,
|
122 |
+
"logits/rejected": -2.6546902656555176,
|
123 |
+
"logps/chosen": -350.1793212890625,
|
124 |
+
"logps/rejected": -348.28985595703125,
|
125 |
+
"loss": 1.8357,
|
126 |
+
"rewards/accuracies": 0.6156250238418579,
|
127 |
+
"rewards/chosen": -23.570585250854492,
|
128 |
+
"rewards/margins": 16.757661819458008,
|
129 |
+
"rewards/rejected": -40.32825469970703,
|
130 |
+
"step": 140
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 1.42,
|
134 |
+
"grad_norm": 1.0552074909210205,
|
135 |
+
"learning_rate": 0.00018436724565756824,
|
136 |
+
"logits/chosen": -2.690781831741333,
|
137 |
+
"logits/rejected": -2.691371440887451,
|
138 |
+
"logps/chosen": -403.81378173828125,
|
139 |
+
"logps/rejected": -407.43475341796875,
|
140 |
+
"loss": 1.4241,
|
141 |
+
"rewards/accuracies": 0.6343749761581421,
|
142 |
+
"rewards/chosen": -46.7193489074707,
|
143 |
+
"rewards/margins": 20.419803619384766,
|
144 |
+
"rewards/rejected": -67.13915252685547,
|
145 |
+
"step": 160
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 1.6,
|
149 |
+
"grad_norm": 88.9915771484375,
|
150 |
+
"learning_rate": 0.0001794044665012407,
|
151 |
+
"logits/chosen": -2.6750125885009766,
|
152 |
+
"logits/rejected": -2.682309627532959,
|
153 |
+
"logps/chosen": -399.62066650390625,
|
154 |
+
"logps/rejected": -409.8529357910156,
|
155 |
+
"loss": 1.9108,
|
156 |
+
"rewards/accuracies": 0.621874988079071,
|
157 |
+
"rewards/chosen": -49.57743453979492,
|
158 |
+
"rewards/margins": 20.643938064575195,
|
159 |
+
"rewards/rejected": -70.22136688232422,
|
160 |
+
"step": 180
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 1.78,
|
164 |
+
"grad_norm": 138.35623168945312,
|
165 |
+
"learning_rate": 0.00017444168734491314,
|
166 |
+
"logits/chosen": -2.7050137519836426,
|
167 |
+
"logits/rejected": -2.712310552597046,
|
168 |
+
"logps/chosen": -397.1112365722656,
|
169 |
+
"logps/rejected": -406.0185852050781,
|
170 |
+
"loss": 2.0578,
|
171 |
+
"rewards/accuracies": 0.574999988079071,
|
172 |
+
"rewards/chosen": -53.7899284362793,
|
173 |
+
"rewards/margins": 17.770038604736328,
|
174 |
+
"rewards/rejected": -71.55997467041016,
|
175 |
+
"step": 200
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 1.78,
|
179 |
+
"eval_logits/chosen": -2.6775686740875244,
|
180 |
+
"eval_logits/rejected": -2.6850674152374268,
|
181 |
+
"eval_logps/chosen": -419.0586242675781,
|
182 |
+
"eval_logps/rejected": -420.5866394042969,
|
183 |
+
"eval_loss": 2.5765089988708496,
|
184 |
+
"eval_rewards/accuracies": 0.550000011920929,
|
185 |
+
"eval_rewards/chosen": -65.75714874267578,
|
186 |
+
"eval_rewards/margins": 12.275188446044922,
|
187 |
+
"eval_rewards/rejected": -78.03234100341797,
|
188 |
+
"eval_runtime": 94.1202,
|
189 |
+
"eval_samples_per_second": 2.125,
|
190 |
+
"eval_steps_per_second": 0.531,
|
191 |
+
"step": 200
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.96,
|
195 |
+
"grad_norm": 30.972963333129883,
|
196 |
+
"learning_rate": 0.0001694789081885856,
|
197 |
+
"logits/chosen": -2.631683349609375,
|
198 |
+
"logits/rejected": -2.6248221397399902,
|
199 |
+
"logps/chosen": -404.0619201660156,
|
200 |
+
"logps/rejected": -399.0223083496094,
|
201 |
+
"loss": 1.8819,
|
202 |
+
"rewards/accuracies": 0.596875011920929,
|
203 |
+
"rewards/chosen": -62.639190673828125,
|
204 |
+
"rewards/margins": 19.827577590942383,
|
205 |
+
"rewards/rejected": -82.46675872802734,
|
206 |
+
"step": 220
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.13,
|
210 |
+
"grad_norm": 65.85337829589844,
|
211 |
+
"learning_rate": 0.00016451612903225807,
|
212 |
+
"logits/chosen": -2.711599826812744,
|
213 |
+
"logits/rejected": -2.7432861328125,
|
214 |
+
"logps/chosen": -392.7776794433594,
|
215 |
+
"logps/rejected": -422.9435119628906,
|
216 |
+
"loss": 1.381,
|
217 |
+
"rewards/accuracies": 0.643750011920929,
|
218 |
+
"rewards/chosen": -58.72906494140625,
|
219 |
+
"rewards/margins": 29.807327270507812,
|
220 |
+
"rewards/rejected": -88.536376953125,
|
221 |
+
"step": 240
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 2.31,
|
225 |
+
"grad_norm": 86.84841918945312,
|
226 |
+
"learning_rate": 0.00015955334987593052,
|
227 |
+
"logits/chosen": -2.8453807830810547,
|
228 |
+
"logits/rejected": -2.849914073944092,
|
229 |
+
"logps/chosen": -400.3071594238281,
|
230 |
+
"logps/rejected": -420.60968017578125,
|
231 |
+
"loss": 0.9731,
|
232 |
+
"rewards/accuracies": 0.6875,
|
233 |
+
"rewards/chosen": -69.37321472167969,
|
234 |
+
"rewards/margins": 32.82529830932617,
|
235 |
+
"rewards/rejected": -102.19852447509766,
|
236 |
+
"step": 260
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.49,
|
240 |
+
"grad_norm": 0.010256004519760609,
|
241 |
+
"learning_rate": 0.000154590570719603,
|
242 |
+
"logits/chosen": -2.7864909172058105,
|
243 |
+
"logits/rejected": -2.812525749206543,
|
244 |
+
"logps/chosen": -376.9371643066406,
|
245 |
+
"logps/rejected": -395.2316589355469,
|
246 |
+
"loss": 0.8817,
|
247 |
+
"rewards/accuracies": 0.703125,
|
248 |
+
"rewards/chosen": -35.111305236816406,
|
249 |
+
"rewards/margins": 33.674293518066406,
|
250 |
+
"rewards/rejected": -68.78559875488281,
|
251 |
+
"step": 280
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 2.67,
|
255 |
+
"grad_norm": 0.26802292466163635,
|
256 |
+
"learning_rate": 0.00014962779156327545,
|
257 |
+
"logits/chosen": -2.7736704349517822,
|
258 |
+
"logits/rejected": -2.792346477508545,
|
259 |
+
"logps/chosen": -372.4452209472656,
|
260 |
+
"logps/rejected": -392.68878173828125,
|
261 |
+
"loss": 0.3389,
|
262 |
+
"rewards/accuracies": 0.7250000238418579,
|
263 |
+
"rewards/chosen": -25.840368270874023,
|
264 |
+
"rewards/margins": 39.69981002807617,
|
265 |
+
"rewards/rejected": -65.54017639160156,
|
266 |
+
"step": 300
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 2.67,
|
270 |
+
"eval_logits/chosen": -2.8219432830810547,
|
271 |
+
"eval_logits/rejected": -2.8389434814453125,
|
272 |
+
"eval_logps/chosen": -374.2080078125,
|
273 |
+
"eval_logps/rejected": -374.9266052246094,
|
274 |
+
"eval_loss": 3.5374395847320557,
|
275 |
+
"eval_rewards/accuracies": 0.5400000214576721,
|
276 |
+
"eval_rewards/chosen": -20.90648651123047,
|
277 |
+
"eval_rewards/margins": 11.465815544128418,
|
278 |
+
"eval_rewards/rejected": -32.37229919433594,
|
279 |
+
"eval_runtime": 94.0956,
|
280 |
+
"eval_samples_per_second": 2.125,
|
281 |
+
"eval_steps_per_second": 0.531,
|
282 |
+
"step": 300
|
283 |
+
}
|
284 |
+
],
|
285 |
+
"logging_steps": 20,
|
286 |
+
"max_steps": 896,
|
287 |
+
"num_input_tokens_seen": 0,
|
288 |
+
"num_train_epochs": 8,
|
289 |
+
"save_steps": 100,
|
290 |
+
"total_flos": 0.0,
|
291 |
+
"train_batch_size": 4,
|
292 |
+
"trial_name": null,
|
293 |
+
"trial_params": null
|
294 |
+
}
|
checkpoint-300/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:898e690ae745f178ef08f4c9b66ce0008ccd31de52b82b4a69ad2f00dceee1bc
|
3 |
+
size 5240
|
checkpoint-400/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|
checkpoint-400/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"o_proj",
|
23 |
+
"k_proj",
|
24 |
+
"q_proj",
|
25 |
+
"v_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
checkpoint-400/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f6e98816262fedea581392db978e2108ebbfbe0e554618a6a9d9f64e3b3a2c3
|
3 |
+
size 54560368
|
checkpoint-400/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d613e271b26005a5dd0c9838644adad9d980018d2baacbb3bb1f5d7a035a335
|
3 |
+
size 109267450
|
checkpoint-400/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
|
3 |
+
size 14244
|
checkpoint-400/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d645df1917d8236ef252b81d31a7c395282a5cd8711ef8e5231db6216d896577
|
3 |
+
size 1064
|
checkpoint-400/special_tokens_map.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": "<unk>",
|
22 |
+
"unk_token": {
|
23 |
+
"content": "<unk>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
}
|
29 |
+
}
|
checkpoint-400/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-400/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
checkpoint-400/tokenizer_config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"max_lenght": 2048,
|
41 |
+
"model_max_length": 1000000000000000019884624838656,
|
42 |
+
"pad_token": "<unk>",
|
43 |
+
"padding": true,
|
44 |
+
"sp_model_kwargs": {},
|
45 |
+
"spaces_between_special_tokens": false,
|
46 |
+
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"truncation_side": "left",
|
48 |
+
"unk_token": "<unk>",
|
49 |
+
"use_default_system_prompt": true
|
50 |
+
}
|
checkpoint-400/trainer_state.json
ADDED
@@ -0,0 +1,385 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.9277071952819824,
|
3 |
+
"best_model_checkpoint": "./Zephyr/08-03-24-Weni-WeniGPT-2.10.1-Zephyr-7B-DPO-prompt-binarized-GPTQ_DPO tests with binarized dataset GPTQ-2_max_steps-896_batch_16_2024-03-08_ppid_7990/checkpoint-100",
|
4 |
+
"epoch": 3.5555555555555554,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 400,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.18,
|
13 |
+
"grad_norm": 119.0400161743164,
|
14 |
+
"learning_rate": 3.111111111111111e-05,
|
15 |
+
"logits/chosen": -2.6437883377075195,
|
16 |
+
"logits/rejected": -2.640676498413086,
|
17 |
+
"logps/chosen": -346.0354309082031,
|
18 |
+
"logps/rejected": -315.1640319824219,
|
19 |
+
"loss": 0.6706,
|
20 |
+
"rewards/accuracies": 0.30000001192092896,
|
21 |
+
"rewards/chosen": 0.2039356678724289,
|
22 |
+
"rewards/margins": 0.1839628666639328,
|
23 |
+
"rewards/rejected": 0.019972801208496094,
|
24 |
+
"step": 20
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.36,
|
28 |
+
"grad_norm": 55.844058990478516,
|
29 |
+
"learning_rate": 7.555555555555556e-05,
|
30 |
+
"logits/chosen": -2.7053043842315674,
|
31 |
+
"logits/rejected": -2.706561326980591,
|
32 |
+
"logps/chosen": -348.75,
|
33 |
+
"logps/rejected": -336.07830810546875,
|
34 |
+
"loss": 0.7255,
|
35 |
+
"rewards/accuracies": 0.5062500238418579,
|
36 |
+
"rewards/chosen": -0.3999950885772705,
|
37 |
+
"rewards/margins": 0.9534912109375,
|
38 |
+
"rewards/rejected": -1.3534862995147705,
|
39 |
+
"step": 40
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.53,
|
43 |
+
"grad_norm": 156.59803771972656,
|
44 |
+
"learning_rate": 0.00011777777777777779,
|
45 |
+
"logits/chosen": -2.644763946533203,
|
46 |
+
"logits/rejected": -2.6682467460632324,
|
47 |
+
"logps/chosen": -352.20233154296875,
|
48 |
+
"logps/rejected": -343.33941650390625,
|
49 |
+
"loss": 0.8382,
|
50 |
+
"rewards/accuracies": 0.5718749761581421,
|
51 |
+
"rewards/chosen": 2.873349189758301,
|
52 |
+
"rewards/margins": 1.9845993518829346,
|
53 |
+
"rewards/rejected": 0.8887494802474976,
|
54 |
+
"step": 60
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.71,
|
58 |
+
"grad_norm": 113.42001342773438,
|
59 |
+
"learning_rate": 0.00016222222222222224,
|
60 |
+
"logits/chosen": -2.652919292449951,
|
61 |
+
"logits/rejected": -2.663282871246338,
|
62 |
+
"logps/chosen": -350.60443115234375,
|
63 |
+
"logps/rejected": -333.491455078125,
|
64 |
+
"loss": 1.6409,
|
65 |
+
"rewards/accuracies": 0.512499988079071,
|
66 |
+
"rewards/chosen": 4.428155899047852,
|
67 |
+
"rewards/margins": 2.1724541187286377,
|
68 |
+
"rewards/rejected": 2.255702018737793,
|
69 |
+
"step": 80
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.89,
|
73 |
+
"grad_norm": 77.21934509277344,
|
74 |
+
"learning_rate": 0.0001992555831265509,
|
75 |
+
"logits/chosen": -2.6474595069885254,
|
76 |
+
"logits/rejected": -2.6597702503204346,
|
77 |
+
"logps/chosen": -318.25653076171875,
|
78 |
+
"logps/rejected": -302.04241943359375,
|
79 |
+
"loss": 1.9207,
|
80 |
+
"rewards/accuracies": 0.4937500059604645,
|
81 |
+
"rewards/chosen": 14.573875427246094,
|
82 |
+
"rewards/margins": 3.523595094680786,
|
83 |
+
"rewards/rejected": 11.050280570983887,
|
84 |
+
"step": 100
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.89,
|
88 |
+
"eval_logits/chosen": -2.7368459701538086,
|
89 |
+
"eval_logits/rejected": -2.746166467666626,
|
90 |
+
"eval_logps/chosen": -334.51287841796875,
|
91 |
+
"eval_logps/rejected": -329.4024658203125,
|
92 |
+
"eval_loss": 1.9277071952819824,
|
93 |
+
"eval_rewards/accuracies": 0.5350000262260437,
|
94 |
+
"eval_rewards/chosen": 18.78862190246582,
|
95 |
+
"eval_rewards/margins": 5.63677978515625,
|
96 |
+
"eval_rewards/rejected": 13.151841163635254,
|
97 |
+
"eval_runtime": 94.4139,
|
98 |
+
"eval_samples_per_second": 2.118,
|
99 |
+
"eval_steps_per_second": 0.53,
|
100 |
+
"step": 100
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.07,
|
104 |
+
"grad_norm": 83.98187255859375,
|
105 |
+
"learning_rate": 0.00019429280397022334,
|
106 |
+
"logits/chosen": -2.639448642730713,
|
107 |
+
"logits/rejected": -2.6476964950561523,
|
108 |
+
"logps/chosen": -316.87982177734375,
|
109 |
+
"logps/rejected": -308.38568115234375,
|
110 |
+
"loss": 1.7601,
|
111 |
+
"rewards/accuracies": 0.5562499761581421,
|
112 |
+
"rewards/chosen": 27.463403701782227,
|
113 |
+
"rewards/margins": 10.681607246398926,
|
114 |
+
"rewards/rejected": 16.781795501708984,
|
115 |
+
"step": 120
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 1.24,
|
119 |
+
"grad_norm": 0.0,
|
120 |
+
"learning_rate": 0.0001893300248138958,
|
121 |
+
"logits/chosen": -2.6575229167938232,
|
122 |
+
"logits/rejected": -2.6546902656555176,
|
123 |
+
"logps/chosen": -350.1793212890625,
|
124 |
+
"logps/rejected": -348.28985595703125,
|
125 |
+
"loss": 1.8357,
|
126 |
+
"rewards/accuracies": 0.6156250238418579,
|
127 |
+
"rewards/chosen": -23.570585250854492,
|
128 |
+
"rewards/margins": 16.757661819458008,
|
129 |
+
"rewards/rejected": -40.32825469970703,
|
130 |
+
"step": 140
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 1.42,
|
134 |
+
"grad_norm": 1.0552074909210205,
|
135 |
+
"learning_rate": 0.00018436724565756824,
|
136 |
+
"logits/chosen": -2.690781831741333,
|
137 |
+
"logits/rejected": -2.691371440887451,
|
138 |
+
"logps/chosen": -403.81378173828125,
|
139 |
+
"logps/rejected": -407.43475341796875,
|
140 |
+
"loss": 1.4241,
|
141 |
+
"rewards/accuracies": 0.6343749761581421,
|
142 |
+
"rewards/chosen": -46.7193489074707,
|
143 |
+
"rewards/margins": 20.419803619384766,
|
144 |
+
"rewards/rejected": -67.13915252685547,
|
145 |
+
"step": 160
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 1.6,
|
149 |
+
"grad_norm": 88.9915771484375,
|
150 |
+
"learning_rate": 0.0001794044665012407,
|
151 |
+
"logits/chosen": -2.6750125885009766,
|
152 |
+
"logits/rejected": -2.682309627532959,
|
153 |
+
"logps/chosen": -399.62066650390625,
|
154 |
+
"logps/rejected": -409.8529357910156,
|
155 |
+
"loss": 1.9108,
|
156 |
+
"rewards/accuracies": 0.621874988079071,
|
157 |
+
"rewards/chosen": -49.57743453979492,
|
158 |
+
"rewards/margins": 20.643938064575195,
|
159 |
+
"rewards/rejected": -70.22136688232422,
|
160 |
+
"step": 180
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 1.78,
|
164 |
+
"grad_norm": 138.35623168945312,
|
165 |
+
"learning_rate": 0.00017444168734491314,
|
166 |
+
"logits/chosen": -2.7050137519836426,
|
167 |
+
"logits/rejected": -2.712310552597046,
|
168 |
+
"logps/chosen": -397.1112365722656,
|
169 |
+
"logps/rejected": -406.0185852050781,
|
170 |
+
"loss": 2.0578,
|
171 |
+
"rewards/accuracies": 0.574999988079071,
|
172 |
+
"rewards/chosen": -53.7899284362793,
|
173 |
+
"rewards/margins": 17.770038604736328,
|
174 |
+
"rewards/rejected": -71.55997467041016,
|
175 |
+
"step": 200
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 1.78,
|
179 |
+
"eval_logits/chosen": -2.6775686740875244,
|
180 |
+
"eval_logits/rejected": -2.6850674152374268,
|
181 |
+
"eval_logps/chosen": -419.0586242675781,
|
182 |
+
"eval_logps/rejected": -420.5866394042969,
|
183 |
+
"eval_loss": 2.5765089988708496,
|
184 |
+
"eval_rewards/accuracies": 0.550000011920929,
|
185 |
+
"eval_rewards/chosen": -65.75714874267578,
|
186 |
+
"eval_rewards/margins": 12.275188446044922,
|
187 |
+
"eval_rewards/rejected": -78.03234100341797,
|
188 |
+
"eval_runtime": 94.1202,
|
189 |
+
"eval_samples_per_second": 2.125,
|
190 |
+
"eval_steps_per_second": 0.531,
|
191 |
+
"step": 200
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.96,
|
195 |
+
"grad_norm": 30.972963333129883,
|
196 |
+
"learning_rate": 0.0001694789081885856,
|
197 |
+
"logits/chosen": -2.631683349609375,
|
198 |
+
"logits/rejected": -2.6248221397399902,
|
199 |
+
"logps/chosen": -404.0619201660156,
|
200 |
+
"logps/rejected": -399.0223083496094,
|
201 |
+
"loss": 1.8819,
|
202 |
+
"rewards/accuracies": 0.596875011920929,
|
203 |
+
"rewards/chosen": -62.639190673828125,
|
204 |
+
"rewards/margins": 19.827577590942383,
|
205 |
+
"rewards/rejected": -82.46675872802734,
|
206 |
+
"step": 220
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.13,
|
210 |
+
"grad_norm": 65.85337829589844,
|
211 |
+
"learning_rate": 0.00016451612903225807,
|
212 |
+
"logits/chosen": -2.711599826812744,
|
213 |
+
"logits/rejected": -2.7432861328125,
|
214 |
+
"logps/chosen": -392.7776794433594,
|
215 |
+
"logps/rejected": -422.9435119628906,
|
216 |
+
"loss": 1.381,
|
217 |
+
"rewards/accuracies": 0.643750011920929,
|
218 |
+
"rewards/chosen": -58.72906494140625,
|
219 |
+
"rewards/margins": 29.807327270507812,
|
220 |
+
"rewards/rejected": -88.536376953125,
|
221 |
+
"step": 240
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 2.31,
|
225 |
+
"grad_norm": 86.84841918945312,
|
226 |
+
"learning_rate": 0.00015955334987593052,
|
227 |
+
"logits/chosen": -2.8453807830810547,
|
228 |
+
"logits/rejected": -2.849914073944092,
|
229 |
+
"logps/chosen": -400.3071594238281,
|
230 |
+
"logps/rejected": -420.60968017578125,
|
231 |
+
"loss": 0.9731,
|
232 |
+
"rewards/accuracies": 0.6875,
|
233 |
+
"rewards/chosen": -69.37321472167969,
|
234 |
+
"rewards/margins": 32.82529830932617,
|
235 |
+
"rewards/rejected": -102.19852447509766,
|
236 |
+
"step": 260
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.49,
|
240 |
+
"grad_norm": 0.010256004519760609,
|
241 |
+
"learning_rate": 0.000154590570719603,
|
242 |
+
"logits/chosen": -2.7864909172058105,
|
243 |
+
"logits/rejected": -2.812525749206543,
|
244 |
+
"logps/chosen": -376.9371643066406,
|
245 |
+
"logps/rejected": -395.2316589355469,
|
246 |
+
"loss": 0.8817,
|
247 |
+
"rewards/accuracies": 0.703125,
|
248 |
+
"rewards/chosen": -35.111305236816406,
|
249 |
+
"rewards/margins": 33.674293518066406,
|
250 |
+
"rewards/rejected": -68.78559875488281,
|
251 |
+
"step": 280
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 2.67,
|
255 |
+
"grad_norm": 0.26802292466163635,
|
256 |
+
"learning_rate": 0.00014962779156327545,
|
257 |
+
"logits/chosen": -2.7736704349517822,
|
258 |
+
"logits/rejected": -2.792346477508545,
|
259 |
+
"logps/chosen": -372.4452209472656,
|
260 |
+
"logps/rejected": -392.68878173828125,
|
261 |
+
"loss": 0.3389,
|
262 |
+
"rewards/accuracies": 0.7250000238418579,
|
263 |
+
"rewards/chosen": -25.840368270874023,
|
264 |
+
"rewards/margins": 39.69981002807617,
|
265 |
+
"rewards/rejected": -65.54017639160156,
|
266 |
+
"step": 300
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 2.67,
|
270 |
+
"eval_logits/chosen": -2.8219432830810547,
|
271 |
+
"eval_logits/rejected": -2.8389434814453125,
|
272 |
+
"eval_logps/chosen": -374.2080078125,
|
273 |
+
"eval_logps/rejected": -374.9266052246094,
|
274 |
+
"eval_loss": 3.5374395847320557,
|
275 |
+
"eval_rewards/accuracies": 0.5400000214576721,
|
276 |
+
"eval_rewards/chosen": -20.90648651123047,
|
277 |
+
"eval_rewards/margins": 11.465815544128418,
|
278 |
+
"eval_rewards/rejected": -32.37229919433594,
|
279 |
+
"eval_runtime": 94.0956,
|
280 |
+
"eval_samples_per_second": 2.125,
|
281 |
+
"eval_steps_per_second": 0.531,
|
282 |
+
"step": 300
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 2.84,
|
286 |
+
"grad_norm": 0.30229315161705017,
|
287 |
+
"learning_rate": 0.0001446650124069479,
|
288 |
+
"logits/chosen": -2.718658447265625,
|
289 |
+
"logits/rejected": -2.7346837520599365,
|
290 |
+
"logps/chosen": -379.4544677734375,
|
291 |
+
"logps/rejected": -398.12213134765625,
|
292 |
+
"loss": 1.0938,
|
293 |
+
"rewards/accuracies": 0.6781250238418579,
|
294 |
+
"rewards/chosen": -28.148609161376953,
|
295 |
+
"rewards/margins": 33.832645416259766,
|
296 |
+
"rewards/rejected": -61.98125076293945,
|
297 |
+
"step": 320
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 3.02,
|
301 |
+
"grad_norm": 43.86916732788086,
|
302 |
+
"learning_rate": 0.00013970223325062035,
|
303 |
+
"logits/chosen": -2.66723370552063,
|
304 |
+
"logits/rejected": -2.6703853607177734,
|
305 |
+
"logps/chosen": -419.7493591308594,
|
306 |
+
"logps/rejected": -418.89227294921875,
|
307 |
+
"loss": 0.9074,
|
308 |
+
"rewards/accuracies": 0.7093750238418579,
|
309 |
+
"rewards/chosen": -54.372032165527344,
|
310 |
+
"rewards/margins": 28.145233154296875,
|
311 |
+
"rewards/rejected": -82.51727294921875,
|
312 |
+
"step": 340
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 3.2,
|
316 |
+
"grad_norm": 1.2495471239089966,
|
317 |
+
"learning_rate": 0.0001347394540942928,
|
318 |
+
"logits/chosen": -2.741353988647461,
|
319 |
+
"logits/rejected": -2.7415261268615723,
|
320 |
+
"logps/chosen": -394.04681396484375,
|
321 |
+
"logps/rejected": -423.58538818359375,
|
322 |
+
"loss": 0.3777,
|
323 |
+
"rewards/accuracies": 0.71875,
|
324 |
+
"rewards/chosen": -41.517425537109375,
|
325 |
+
"rewards/margins": 49.255271911621094,
|
326 |
+
"rewards/rejected": -90.77268981933594,
|
327 |
+
"step": 360
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 3.38,
|
331 |
+
"grad_norm": 7.586065292358398,
|
332 |
+
"learning_rate": 0.00012977667493796526,
|
333 |
+
"logits/chosen": -2.683011054992676,
|
334 |
+
"logits/rejected": -2.697779893875122,
|
335 |
+
"logps/chosen": -374.07745361328125,
|
336 |
+
"logps/rejected": -395.69390869140625,
|
337 |
+
"loss": 0.2784,
|
338 |
+
"rewards/accuracies": 0.731249988079071,
|
339 |
+
"rewards/chosen": -44.96805953979492,
|
340 |
+
"rewards/margins": 42.65815734863281,
|
341 |
+
"rewards/rejected": -87.626220703125,
|
342 |
+
"step": 380
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 3.56,
|
346 |
+
"grad_norm": 0.3450467586517334,
|
347 |
+
"learning_rate": 0.0001248138957816377,
|
348 |
+
"logits/chosen": -2.78257417678833,
|
349 |
+
"logits/rejected": -2.797196865081787,
|
350 |
+
"logps/chosen": -436.71185302734375,
|
351 |
+
"logps/rejected": -443.575927734375,
|
352 |
+
"loss": 0.6031,
|
353 |
+
"rewards/accuracies": 0.7593749761581421,
|
354 |
+
"rewards/chosen": -59.74363327026367,
|
355 |
+
"rewards/margins": 44.275550842285156,
|
356 |
+
"rewards/rejected": -104.01918029785156,
|
357 |
+
"step": 400
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 3.56,
|
361 |
+
"eval_logits/chosen": -2.8664298057556152,
|
362 |
+
"eval_logits/rejected": -2.879199266433716,
|
363 |
+
"eval_logps/chosen": -433.5849914550781,
|
364 |
+
"eval_logps/rejected": -436.34722900390625,
|
365 |
+
"eval_loss": 2.886720657348633,
|
366 |
+
"eval_rewards/accuracies": 0.5899999737739563,
|
367 |
+
"eval_rewards/chosen": -80.2834701538086,
|
368 |
+
"eval_rewards/margins": 13.509483337402344,
|
369 |
+
"eval_rewards/rejected": -93.7929458618164,
|
370 |
+
"eval_runtime": 94.1029,
|
371 |
+
"eval_samples_per_second": 2.125,
|
372 |
+
"eval_steps_per_second": 0.531,
|
373 |
+
"step": 400
|
374 |
+
}
|
375 |
+
],
|
376 |
+
"logging_steps": 20,
|
377 |
+
"max_steps": 896,
|
378 |
+
"num_input_tokens_seen": 0,
|
379 |
+
"num_train_epochs": 8,
|
380 |
+
"save_steps": 100,
|
381 |
+
"total_flos": 0.0,
|
382 |
+
"train_batch_size": 4,
|
383 |
+
"trial_name": null,
|
384 |
+
"trial_params": null
|
385 |
+
}
|
checkpoint-400/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:898e690ae745f178ef08f4c9b66ce0008ccd31de52b82b4a69ad2f00dceee1bc
|
3 |
+
size 5240
|
checkpoint-500/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT
|
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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.8.2
|