Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +59 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- all_results.json +8 -0
- checkpoint-100/README.md +202 -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 +24 -0
- checkpoint-100/tokenizer.json +0 -0
- checkpoint-100/tokenizer.model +3 -0
- checkpoint-100/tokenizer_config.json +45 -0
- checkpoint-100/trainer_state.json +161 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-200/README.md +202 -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 +24 -0
- checkpoint-200/tokenizer.json +0 -0
- checkpoint-200/tokenizer.model +3 -0
- checkpoint-200/tokenizer_config.json +45 -0
- checkpoint-200/trainer_state.json +301 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-300/README.md +202 -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 +24 -0
- checkpoint-300/tokenizer.json +0 -0
- checkpoint-300/tokenizer.model +3 -0
- checkpoint-300/tokenizer_config.json +45 -0
- checkpoint-300/trainer_state.json +441 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-400/README.md +202 -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 +24 -0
- checkpoint-400/tokenizer.json +0 -0
- checkpoint-400/tokenizer.model +3 -0
- checkpoint-400/tokenizer_config.json +45 -0
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- llama-factory
|
6 |
+
- lora
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: alpindale/Mistral-7B-v0.2-hf
|
9 |
+
model-index:
|
10 |
+
- name: train_2024-05-15-20-33-30
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# train_2024-05-15-20-33-30
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [alpindale/Mistral-7B-v0.2-hf](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf) on the emoji_add_instruction_zh dataset.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 5e-05
|
39 |
+
- train_batch_size: 2
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 8
|
43 |
+
- total_train_batch_size: 16
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- num_epochs: 3.0
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- PEFT 0.10.0
|
56 |
+
- Transformers 4.40.2
|
57 |
+
- Pytorch 2.3.0+cu121
|
58 |
+
- Datasets 2.19.1
|
59 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa0ee3c7c0db814c8a923893c59e8b5c1385c5390e9d984b0e9fe53b17d006bc
|
3 |
+
size 13648432
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.9975510204081632,
|
3 |
+
"total_flos": 2.854627336867676e+17,
|
4 |
+
"train_loss": 0.0628165303362221,
|
5 |
+
"train_runtime": 9275.9124,
|
6 |
+
"train_samples_per_second": 0.792,
|
7 |
+
"train_steps_per_second": 0.049
|
8 |
+
}
|
checkpoint-100/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: alpindale/Mistral-7B-v0.2-hf
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.0
|
checkpoint-100/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
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 sha256:337a007c5e33fd84bc2c5ca8bc53acdc42f89f41046572dc35aad6349e07d7e2
|
3 |
+
size 13648432
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:355be49f1184c958521a04a4686f287e5d7f1d83a0a0bf558612ede7263afc8b
|
3 |
+
size 27370618
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60400665774c60f2b71ad469813f6e3297e12b0741193b44997e31623e04be92
|
3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-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 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": false
|
45 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6530612244897959,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0326530612244898,
|
13 |
+
"grad_norm": 0.3159657120704651,
|
14 |
+
"learning_rate": 4.9985361990992455e-05,
|
15 |
+
"loss": 0.1654,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0653061224489796,
|
20 |
+
"grad_norm": 0.32706642150878906,
|
21 |
+
"learning_rate": 4.9941465105674435e-05,
|
22 |
+
"loss": 0.1369,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.09795918367346938,
|
27 |
+
"grad_norm": 0.33407843112945557,
|
28 |
+
"learning_rate": 4.986836074908616e-05,
|
29 |
+
"loss": 0.1259,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1306122448979592,
|
34 |
+
"grad_norm": 0.3189881443977356,
|
35 |
+
"learning_rate": 4.976613452940604e-05,
|
36 |
+
"loss": 0.1041,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.16326530612244897,
|
41 |
+
"grad_norm": 0.3424989581108093,
|
42 |
+
"learning_rate": 4.9634906157700036e-05,
|
43 |
+
"loss": 0.1004,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.19591836734693877,
|
48 |
+
"grad_norm": 0.3253389298915863,
|
49 |
+
"learning_rate": 4.9474829307735115e-05,
|
50 |
+
"loss": 0.0941,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.22857142857142856,
|
55 |
+
"grad_norm": 0.26078635454177856,
|
56 |
+
"learning_rate": 4.9286091436021015e-05,
|
57 |
+
"loss": 0.0867,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2612244897959184,
|
62 |
+
"grad_norm": 0.252139687538147,
|
63 |
+
"learning_rate": 4.906891356229103e-05,
|
64 |
+
"loss": 0.0853,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.2938775510204082,
|
69 |
+
"grad_norm": 0.3403972387313843,
|
70 |
+
"learning_rate": 4.882355001067892e-05,
|
71 |
+
"loss": 0.0863,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.32653061224489793,
|
76 |
+
"grad_norm": 0.4710679352283478,
|
77 |
+
"learning_rate": 4.855028811189496e-05,
|
78 |
+
"loss": 0.0874,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.35918367346938773,
|
83 |
+
"grad_norm": 0.3147217929363251,
|
84 |
+
"learning_rate": 4.8249447866750025e-05,
|
85 |
+
"loss": 0.0733,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.39183673469387753,
|
90 |
+
"grad_norm": 0.3265310823917389,
|
91 |
+
"learning_rate": 4.792138157142158e-05,
|
92 |
+
"loss": 0.0719,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.42448979591836733,
|
97 |
+
"grad_norm": 0.35432252287864685,
|
98 |
+
"learning_rate": 4.75664734049005e-05,
|
99 |
+
"loss": 0.0824,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.45714285714285713,
|
104 |
+
"grad_norm": 0.3701626658439636,
|
105 |
+
"learning_rate": 4.7185138979101864e-05,
|
106 |
+
"loss": 0.0731,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.4897959183673469,
|
111 |
+
"grad_norm": 0.35868266224861145,
|
112 |
+
"learning_rate": 4.677782485216644e-05,
|
113 |
+
"loss": 0.0725,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.5224489795918368,
|
118 |
+
"grad_norm": 0.32440632581710815,
|
119 |
+
"learning_rate": 4.6345008005522966e-05,
|
120 |
+
"loss": 0.0694,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5551020408163265,
|
125 |
+
"grad_norm": 0.3003002405166626,
|
126 |
+
"learning_rate": 4.588719528532342e-05,
|
127 |
+
"loss": 0.072,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.5877551020408164,
|
132 |
+
"grad_norm": 0.34989920258522034,
|
133 |
+
"learning_rate": 4.540492280890555e-05,
|
134 |
+
"loss": 0.0646,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6204081632653061,
|
139 |
+
"grad_norm": 0.473254919052124,
|
140 |
+
"learning_rate": 4.4898755336977673e-05,
|
141 |
+
"loss": 0.0732,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.6530612244897959,
|
146 |
+
"grad_norm": 0.30768489837646484,
|
147 |
+
"learning_rate": 4.436928561226087e-05,
|
148 |
+
"loss": 0.068,
|
149 |
+
"step": 100
|
150 |
+
}
|
151 |
+
],
|
152 |
+
"logging_steps": 5,
|
153 |
+
"max_steps": 459,
|
154 |
+
"num_input_tokens_seen": 0,
|
155 |
+
"num_train_epochs": 3,
|
156 |
+
"save_steps": 100,
|
157 |
+
"total_flos": 6.206244600230707e+16,
|
158 |
+
"train_batch_size": 2,
|
159 |
+
"trial_name": null,
|
160 |
+
"trial_params": null
|
161 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fe05743275e1a0b3185dbc2310f1e055d91d945545cf3f061569e23d25ef075
|
3 |
+
size 5176
|
checkpoint-200/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: alpindale/Mistral-7B-v0.2-hf
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.0
|
checkpoint-200/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
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 sha256:72b4c3211836f8f090b5c5553fc90f8e75b61952ddf3e2f1064a48a4abdb9221
|
3 |
+
size 13648432
|
checkpoint-200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:834005fc5a7e669ca5804fb0bcf7d240428dea685db48c6b0fbd5488d250477e
|
3 |
+
size 27370618
|
checkpoint-200/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-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b893e975e740234419d36aadc594ec6b92d665b03b7a3bcd3c414b51ea42ab7
|
3 |
+
size 1064
|
checkpoint-200/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-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 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": false
|
45 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
@@ -0,0 +1,301 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.306122448979592,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0326530612244898,
|
13 |
+
"grad_norm": 0.3159657120704651,
|
14 |
+
"learning_rate": 4.9985361990992455e-05,
|
15 |
+
"loss": 0.1654,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0653061224489796,
|
20 |
+
"grad_norm": 0.32706642150878906,
|
21 |
+
"learning_rate": 4.9941465105674435e-05,
|
22 |
+
"loss": 0.1369,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.09795918367346938,
|
27 |
+
"grad_norm": 0.33407843112945557,
|
28 |
+
"learning_rate": 4.986836074908616e-05,
|
29 |
+
"loss": 0.1259,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1306122448979592,
|
34 |
+
"grad_norm": 0.3189881443977356,
|
35 |
+
"learning_rate": 4.976613452940604e-05,
|
36 |
+
"loss": 0.1041,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.16326530612244897,
|
41 |
+
"grad_norm": 0.3424989581108093,
|
42 |
+
"learning_rate": 4.9634906157700036e-05,
|
43 |
+
"loss": 0.1004,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.19591836734693877,
|
48 |
+
"grad_norm": 0.3253389298915863,
|
49 |
+
"learning_rate": 4.9474829307735115e-05,
|
50 |
+
"loss": 0.0941,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.22857142857142856,
|
55 |
+
"grad_norm": 0.26078635454177856,
|
56 |
+
"learning_rate": 4.9286091436021015e-05,
|
57 |
+
"loss": 0.0867,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2612244897959184,
|
62 |
+
"grad_norm": 0.252139687538147,
|
63 |
+
"learning_rate": 4.906891356229103e-05,
|
64 |
+
"loss": 0.0853,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.2938775510204082,
|
69 |
+
"grad_norm": 0.3403972387313843,
|
70 |
+
"learning_rate": 4.882355001067892e-05,
|
71 |
+
"loss": 0.0863,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.32653061224489793,
|
76 |
+
"grad_norm": 0.4710679352283478,
|
77 |
+
"learning_rate": 4.855028811189496e-05,
|
78 |
+
"loss": 0.0874,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.35918367346938773,
|
83 |
+
"grad_norm": 0.3147217929363251,
|
84 |
+
"learning_rate": 4.8249447866750025e-05,
|
85 |
+
"loss": 0.0733,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.39183673469387753,
|
90 |
+
"grad_norm": 0.3265310823917389,
|
91 |
+
"learning_rate": 4.792138157142158e-05,
|
92 |
+
"loss": 0.0719,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.42448979591836733,
|
97 |
+
"grad_norm": 0.35432252287864685,
|
98 |
+
"learning_rate": 4.75664734049005e-05,
|
99 |
+
"loss": 0.0824,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.45714285714285713,
|
104 |
+
"grad_norm": 0.3701626658439636,
|
105 |
+
"learning_rate": 4.7185138979101864e-05,
|
106 |
+
"loss": 0.0731,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.4897959183673469,
|
111 |
+
"grad_norm": 0.35868266224861145,
|
112 |
+
"learning_rate": 4.677782485216644e-05,
|
113 |
+
"loss": 0.0725,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.5224489795918368,
|
118 |
+
"grad_norm": 0.32440632581710815,
|
119 |
+
"learning_rate": 4.6345008005522966e-05,
|
120 |
+
"loss": 0.0694,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5551020408163265,
|
125 |
+
"grad_norm": 0.3003002405166626,
|
126 |
+
"learning_rate": 4.588719528532342e-05,
|
127 |
+
"loss": 0.072,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.5877551020408164,
|
132 |
+
"grad_norm": 0.34989920258522034,
|
133 |
+
"learning_rate": 4.540492280890555e-05,
|
134 |
+
"loss": 0.0646,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6204081632653061,
|
139 |
+
"grad_norm": 0.473254919052124,
|
140 |
+
"learning_rate": 4.4898755336977673e-05,
|
141 |
+
"loss": 0.0732,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.6530612244897959,
|
146 |
+
"grad_norm": 0.30768489837646484,
|
147 |
+
"learning_rate": 4.436928561226087e-05,
|
148 |
+
"loss": 0.068,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.6857142857142857,
|
153 |
+
"grad_norm": 0.31777673959732056,
|
154 |
+
"learning_rate": 4.381713366536311e-05,
|
155 |
+
"loss": 0.0749,
|
156 |
+
"step": 105
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.7183673469387755,
|
160 |
+
"grad_norm": 0.40202295780181885,
|
161 |
+
"learning_rate": 4.324294608869817e-05,
|
162 |
+
"loss": 0.0652,
|
163 |
+
"step": 110
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.7510204081632653,
|
167 |
+
"grad_norm": 0.4353463053703308,
|
168 |
+
"learning_rate": 4.264739527929959e-05,
|
169 |
+
"loss": 0.0562,
|
170 |
+
"step": 115
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.7836734693877551,
|
174 |
+
"grad_norm": 0.4079282879829407,
|
175 |
+
"learning_rate": 4.203117865141635e-05,
|
176 |
+
"loss": 0.0602,
|
177 |
+
"step": 120
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8163265306122449,
|
181 |
+
"grad_norm": 0.40490931272506714,
|
182 |
+
"learning_rate": 4.1395017819812445e-05,
|
183 |
+
"loss": 0.0639,
|
184 |
+
"step": 125
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.8489795918367347,
|
188 |
+
"grad_norm": 0.423981636762619,
|
189 |
+
"learning_rate": 4.07396577547265e-05,
|
190 |
+
"loss": 0.0651,
|
191 |
+
"step": 130
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.8816326530612245,
|
195 |
+
"grad_norm": 0.3315489590167999,
|
196 |
+
"learning_rate": 4.0065865909481417e-05,
|
197 |
+
"loss": 0.0676,
|
198 |
+
"step": 135
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.9142857142857143,
|
202 |
+
"grad_norm": 0.560667097568512,
|
203 |
+
"learning_rate": 3.937443132176517e-05,
|
204 |
+
"loss": 0.0669,
|
205 |
+
"step": 140
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.9469387755102041,
|
209 |
+
"grad_norm": 0.4202517569065094,
|
210 |
+
"learning_rate": 3.8666163689635616e-05,
|
211 |
+
"loss": 0.0631,
|
212 |
+
"step": 145
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.9795918367346939,
|
216 |
+
"grad_norm": 0.4563729465007782,
|
217 |
+
"learning_rate": 3.794189242333106e-05,
|
218 |
+
"loss": 0.0649,
|
219 |
+
"step": 150
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.0122448979591836,
|
223 |
+
"grad_norm": 0.3522864580154419,
|
224 |
+
"learning_rate": 3.720246567399712e-05,
|
225 |
+
"loss": 0.059,
|
226 |
+
"step": 155
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.0448979591836736,
|
230 |
+
"grad_norm": 0.38459908962249756,
|
231 |
+
"learning_rate": 3.644874934046716e-05,
|
232 |
+
"loss": 0.062,
|
233 |
+
"step": 160
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.0775510204081633,
|
237 |
+
"grad_norm": 0.37406954169273376,
|
238 |
+
"learning_rate": 3.568162605525953e-05,
|
239 |
+
"loss": 0.0565,
|
240 |
+
"step": 165
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.110204081632653,
|
244 |
+
"grad_norm": 0.3395706117153168,
|
245 |
+
"learning_rate": 3.490199415097892e-05,
|
246 |
+
"loss": 0.0575,
|
247 |
+
"step": 170
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.1428571428571428,
|
251 |
+
"grad_norm": 0.31273558735847473,
|
252 |
+
"learning_rate": 3.4110766608332347e-05,
|
253 |
+
"loss": 0.0589,
|
254 |
+
"step": 175
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.1755102040816325,
|
258 |
+
"grad_norm": 0.44675061106681824,
|
259 |
+
"learning_rate": 3.330886998699149e-05,
|
260 |
+
"loss": 0.0611,
|
261 |
+
"step": 180
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.2081632653061225,
|
265 |
+
"grad_norm": 0.34769827127456665,
|
266 |
+
"learning_rate": 3.249724334055367e-05,
|
267 |
+
"loss": 0.062,
|
268 |
+
"step": 185
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.2408163265306122,
|
272 |
+
"grad_norm": 0.31832146644592285,
|
273 |
+
"learning_rate": 3.167683711687179e-05,
|
274 |
+
"loss": 0.0616,
|
275 |
+
"step": 190
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.273469387755102,
|
279 |
+
"grad_norm": 0.4153653085231781,
|
280 |
+
"learning_rate": 3.084861204504122e-05,
|
281 |
+
"loss": 0.0586,
|
282 |
+
"step": 195
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.306122448979592,
|
286 |
+
"grad_norm": 0.36249643564224243,
|
287 |
+
"learning_rate": 3.001353801034688e-05,
|
288 |
+
"loss": 0.0578,
|
289 |
+
"step": 200
|
290 |
+
}
|
291 |
+
],
|
292 |
+
"logging_steps": 5,
|
293 |
+
"max_steps": 459,
|
294 |
+
"num_input_tokens_seen": 0,
|
295 |
+
"num_train_epochs": 3,
|
296 |
+
"save_steps": 100,
|
297 |
+
"total_flos": 1.2409791545887949e+17,
|
298 |
+
"train_batch_size": 2,
|
299 |
+
"trial_name": null,
|
300 |
+
"trial_params": null
|
301 |
+
}
|
checkpoint-200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fe05743275e1a0b3185dbc2310f1e055d91d945545cf3f061569e23d25ef075
|
3 |
+
size 5176
|
checkpoint-300/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: alpindale/Mistral-7B-v0.2-hf
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.0
|
checkpoint-300/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
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 sha256:0d3bb6500834c9d6e25bd8065d4f0281bcc9a438c6f9caa42db180e6d212b220
|
3 |
+
size 13648432
|
checkpoint-300/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eadc12cc068eba00e32e5259c8cc5eb1d94cf0c29552675656ece7094a5df973
|
3 |
+
size 27370618
|
checkpoint-300/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-300/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c99d6c2946d36f46592ac10a40e825eee13c06aeb3529100a7cb0e0070e050e4
|
3 |
+
size 1064
|
checkpoint-300/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-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 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": false
|
45 |
+
}
|
checkpoint-300/trainer_state.json
ADDED
@@ -0,0 +1,441 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9591836734693877,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 300,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0326530612244898,
|
13 |
+
"grad_norm": 0.3159657120704651,
|
14 |
+
"learning_rate": 4.9985361990992455e-05,
|
15 |
+
"loss": 0.1654,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0653061224489796,
|
20 |
+
"grad_norm": 0.32706642150878906,
|
21 |
+
"learning_rate": 4.9941465105674435e-05,
|
22 |
+
"loss": 0.1369,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.09795918367346938,
|
27 |
+
"grad_norm": 0.33407843112945557,
|
28 |
+
"learning_rate": 4.986836074908616e-05,
|
29 |
+
"loss": 0.1259,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1306122448979592,
|
34 |
+
"grad_norm": 0.3189881443977356,
|
35 |
+
"learning_rate": 4.976613452940604e-05,
|
36 |
+
"loss": 0.1041,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.16326530612244897,
|
41 |
+
"grad_norm": 0.3424989581108093,
|
42 |
+
"learning_rate": 4.9634906157700036e-05,
|
43 |
+
"loss": 0.1004,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.19591836734693877,
|
48 |
+
"grad_norm": 0.3253389298915863,
|
49 |
+
"learning_rate": 4.9474829307735115e-05,
|
50 |
+
"loss": 0.0941,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.22857142857142856,
|
55 |
+
"grad_norm": 0.26078635454177856,
|
56 |
+
"learning_rate": 4.9286091436021015e-05,
|
57 |
+
"loss": 0.0867,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.2612244897959184,
|
62 |
+
"grad_norm": 0.252139687538147,
|
63 |
+
"learning_rate": 4.906891356229103e-05,
|
64 |
+
"loss": 0.0853,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.2938775510204082,
|
69 |
+
"grad_norm": 0.3403972387313843,
|
70 |
+
"learning_rate": 4.882355001067892e-05,
|
71 |
+
"loss": 0.0863,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.32653061224489793,
|
76 |
+
"grad_norm": 0.4710679352283478,
|
77 |
+
"learning_rate": 4.855028811189496e-05,
|
78 |
+
"loss": 0.0874,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.35918367346938773,
|
83 |
+
"grad_norm": 0.3147217929363251,
|
84 |
+
"learning_rate": 4.8249447866750025e-05,
|
85 |
+
"loss": 0.0733,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.39183673469387753,
|
90 |
+
"grad_norm": 0.3265310823917389,
|
91 |
+
"learning_rate": 4.792138157142158e-05,
|
92 |
+
"loss": 0.0719,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.42448979591836733,
|
97 |
+
"grad_norm": 0.35432252287864685,
|
98 |
+
"learning_rate": 4.75664734049005e-05,
|
99 |
+
"loss": 0.0824,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.45714285714285713,
|
104 |
+
"grad_norm": 0.3701626658439636,
|
105 |
+
"learning_rate": 4.7185138979101864e-05,
|
106 |
+
"loss": 0.0731,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.4897959183673469,
|
111 |
+
"grad_norm": 0.35868266224861145,
|
112 |
+
"learning_rate": 4.677782485216644e-05,
|
113 |
+
"loss": 0.0725,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.5224489795918368,
|
118 |
+
"grad_norm": 0.32440632581710815,
|
119 |
+
"learning_rate": 4.6345008005522966e-05,
|
120 |
+
"loss": 0.0694,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5551020408163265,
|
125 |
+
"grad_norm": 0.3003002405166626,
|
126 |
+
"learning_rate": 4.588719528532342e-05,
|
127 |
+
"loss": 0.072,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.5877551020408164,
|
132 |
+
"grad_norm": 0.34989920258522034,
|
133 |
+
"learning_rate": 4.540492280890555e-05,
|
134 |
+
"loss": 0.0646,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6204081632653061,
|
139 |
+
"grad_norm": 0.473254919052124,
|
140 |
+
"learning_rate": 4.4898755336977673e-05,
|
141 |
+
"loss": 0.0732,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.6530612244897959,
|
146 |
+
"grad_norm": 0.30768489837646484,
|
147 |
+
"learning_rate": 4.436928561226087e-05,
|
148 |
+
"loss": 0.068,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.6857142857142857,
|
153 |
+
"grad_norm": 0.31777673959732056,
|
154 |
+
"learning_rate": 4.381713366536311e-05,
|
155 |
+
"loss": 0.0749,
|
156 |
+
"step": 105
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.7183673469387755,
|
160 |
+
"grad_norm": 0.40202295780181885,
|
161 |
+
"learning_rate": 4.324294608869817e-05,
|
162 |
+
"loss": 0.0652,
|
163 |
+
"step": 110
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.7510204081632653,
|
167 |
+
"grad_norm": 0.4353463053703308,
|
168 |
+
"learning_rate": 4.264739527929959e-05,
|
169 |
+
"loss": 0.0562,
|
170 |
+
"step": 115
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.7836734693877551,
|
174 |
+
"grad_norm": 0.4079282879829407,
|
175 |
+
"learning_rate": 4.203117865141635e-05,
|
176 |
+
"loss": 0.0602,
|
177 |
+
"step": 120
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8163265306122449,
|
181 |
+
"grad_norm": 0.40490931272506714,
|
182 |
+
"learning_rate": 4.1395017819812445e-05,
|
183 |
+
"loss": 0.0639,
|
184 |
+
"step": 125
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.8489795918367347,
|
188 |
+
"grad_norm": 0.423981636762619,
|
189 |
+
"learning_rate": 4.07396577547265e-05,
|
190 |
+
"loss": 0.0651,
|
191 |
+
"step": 130
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.8816326530612245,
|
195 |
+
"grad_norm": 0.3315489590167999,
|
196 |
+
"learning_rate": 4.0065865909481417e-05,
|
197 |
+
"loss": 0.0676,
|
198 |
+
"step": 135
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.9142857142857143,
|
202 |
+
"grad_norm": 0.560667097568512,
|
203 |
+
"learning_rate": 3.937443132176517e-05,
|
204 |
+
"loss": 0.0669,
|
205 |
+
"step": 140
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.9469387755102041,
|
209 |
+
"grad_norm": 0.4202517569065094,
|
210 |
+
"learning_rate": 3.8666163689635616e-05,
|
211 |
+
"loss": 0.0631,
|
212 |
+
"step": 145
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.9795918367346939,
|
216 |
+
"grad_norm": 0.4563729465007782,
|
217 |
+
"learning_rate": 3.794189242333106e-05,
|
218 |
+
"loss": 0.0649,
|
219 |
+
"step": 150
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.0122448979591836,
|
223 |
+
"grad_norm": 0.3522864580154419,
|
224 |
+
"learning_rate": 3.720246567399712e-05,
|
225 |
+
"loss": 0.059,
|
226 |
+
"step": 155
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.0448979591836736,
|
230 |
+
"grad_norm": 0.38459908962249756,
|
231 |
+
"learning_rate": 3.644874934046716e-05,
|
232 |
+
"loss": 0.062,
|
233 |
+
"step": 160
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.0775510204081633,
|
237 |
+
"grad_norm": 0.37406954169273376,
|
238 |
+
"learning_rate": 3.568162605525953e-05,
|
239 |
+
"loss": 0.0565,
|
240 |
+
"step": 165
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.110204081632653,
|
244 |
+
"grad_norm": 0.3395706117153168,
|
245 |
+
"learning_rate": 3.490199415097892e-05,
|
246 |
+
"loss": 0.0575,
|
247 |
+
"step": 170
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.1428571428571428,
|
251 |
+
"grad_norm": 0.31273558735847473,
|
252 |
+
"learning_rate": 3.4110766608332347e-05,
|
253 |
+
"loss": 0.0589,
|
254 |
+
"step": 175
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.1755102040816325,
|
258 |
+
"grad_norm": 0.44675061106681824,
|
259 |
+
"learning_rate": 3.330886998699149e-05,
|
260 |
+
"loss": 0.0611,
|
261 |
+
"step": 180
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.2081632653061225,
|
265 |
+
"grad_norm": 0.34769827127456665,
|
266 |
+
"learning_rate": 3.249724334055367e-05,
|
267 |
+
"loss": 0.062,
|
268 |
+
"step": 185
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.2408163265306122,
|
272 |
+
"grad_norm": 0.31832146644592285,
|
273 |
+
"learning_rate": 3.167683711687179e-05,
|
274 |
+
"loss": 0.0616,
|
275 |
+
"step": 190
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.273469387755102,
|
279 |
+
"grad_norm": 0.4153653085231781,
|
280 |
+
"learning_rate": 3.084861204504122e-05,
|
281 |
+
"loss": 0.0586,
|
282 |
+
"step": 195
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.306122448979592,
|
286 |
+
"grad_norm": 0.36249643564224243,
|
287 |
+
"learning_rate": 3.001353801034688e-05,
|
288 |
+
"loss": 0.0578,
|
289 |
+
"step": 200
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.3387755102040817,
|
293 |
+
"grad_norm": 0.43447113037109375,
|
294 |
+
"learning_rate": 2.917259291848814e-05,
|
295 |
+
"loss": 0.0547,
|
296 |
+
"step": 205
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.3714285714285714,
|
300 |
+
"grad_norm": 0.3350294530391693,
|
301 |
+
"learning_rate": 2.8326761550411345e-05,
|
302 |
+
"loss": 0.0581,
|
303 |
+
"step": 210
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.4040816326530612,
|
307 |
+
"grad_norm": 0.34255513548851013,
|
308 |
+
"learning_rate": 2.747703440909128e-05,
|
309 |
+
"loss": 0.0535,
|
310 |
+
"step": 215
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.436734693877551,
|
314 |
+
"grad_norm": 0.6323994398117065,
|
315 |
+
"learning_rate": 2.662440655961183e-05,
|
316 |
+
"loss": 0.0666,
|
317 |
+
"step": 220
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.469387755102041,
|
321 |
+
"grad_norm": 0.3421262502670288,
|
322 |
+
"learning_rate": 2.5769876463904265e-05,
|
323 |
+
"loss": 0.053,
|
324 |
+
"step": 225
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.5020408163265306,
|
328 |
+
"grad_norm": 0.4133753478527069,
|
329 |
+
"learning_rate": 2.491444481150763e-05,
|
330 |
+
"loss": 0.0602,
|
331 |
+
"step": 230
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.5346938775510204,
|
335 |
+
"grad_norm": 0.37677302956581116,
|
336 |
+
"learning_rate": 2.4059113347720574e-05,
|
337 |
+
"loss": 0.0573,
|
338 |
+
"step": 235
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.5673469387755103,
|
342 |
+
"grad_norm": 0.3683429956436157,
|
343 |
+
"learning_rate": 2.3204883700516812e-05,
|
344 |
+
"loss": 0.0544,
|
345 |
+
"step": 240
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.6,
|
349 |
+
"grad_norm": 0.34340280294418335,
|
350 |
+
"learning_rate": 2.235275620759797e-05,
|
351 |
+
"loss": 0.0552,
|
352 |
+
"step": 245
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.6326530612244898,
|
356 |
+
"grad_norm": 0.39541885256767273,
|
357 |
+
"learning_rate": 2.150372874495739e-05,
|
358 |
+
"loss": 0.0543,
|
359 |
+
"step": 250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.6653061224489796,
|
363 |
+
"grad_norm": 0.384330689907074,
|
364 |
+
"learning_rate": 2.0658795558326743e-05,
|
365 |
+
"loss": 0.0481,
|
366 |
+
"step": 255
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.6979591836734693,
|
370 |
+
"grad_norm": 0.4634612798690796,
|
371 |
+
"learning_rate": 1.9818946098873766e-05,
|
372 |
+
"loss": 0.052,
|
373 |
+
"step": 260
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.730612244897959,
|
377 |
+
"grad_norm": 0.4186592400074005,
|
378 |
+
"learning_rate": 1.8985163864514645e-05,
|
379 |
+
"loss": 0.0516,
|
380 |
+
"step": 265
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.763265306122449,
|
384 |
+
"grad_norm": 0.4726428985595703,
|
385 |
+
"learning_rate": 1.815842524819793e-05,
|
386 |
+
"loss": 0.0559,
|
387 |
+
"step": 270
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.7959183673469388,
|
391 |
+
"grad_norm": 0.38660183548927307,
|
392 |
+
"learning_rate": 1.733969839450863e-05,
|
393 |
+
"loss": 0.0554,
|
394 |
+
"step": 275
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.8285714285714287,
|
398 |
+
"grad_norm": 0.40636590123176575,
|
399 |
+
"learning_rate": 1.6529942065931477e-05,
|
400 |
+
"loss": 0.0576,
|
401 |
+
"step": 280
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.8612244897959185,
|
405 |
+
"grad_norm": 0.3667762875556946,
|
406 |
+
"learning_rate": 1.5730104520100982e-05,
|
407 |
+
"loss": 0.0546,
|
408 |
+
"step": 285
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.8938775510204082,
|
412 |
+
"grad_norm": 0.38867512345314026,
|
413 |
+
"learning_rate": 1.4941122399353185e-05,
|
414 |
+
"loss": 0.0539,
|
415 |
+
"step": 290
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.926530612244898,
|
419 |
+
"grad_norm": 0.37944862246513367,
|
420 |
+
"learning_rate": 1.4163919633879324e-05,
|
421 |
+
"loss": 0.0537,
|
422 |
+
"step": 295
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.9591836734693877,
|
426 |
+
"grad_norm": 0.394191175699234,
|
427 |
+
"learning_rate": 1.339940635976592e-05,
|
428 |
+
"loss": 0.0493,
|
429 |
+
"step": 300
|
430 |
+
}
|
431 |
+
],
|
432 |
+
"logging_steps": 5,
|
433 |
+
"max_steps": 459,
|
434 |
+
"num_input_tokens_seen": 0,
|
435 |
+
"num_train_epochs": 3,
|
436 |
+
"save_steps": 100,
|
437 |
+
"total_flos": 1.8642398036380877e+17,
|
438 |
+
"train_batch_size": 2,
|
439 |
+
"trial_name": null,
|
440 |
+
"trial_params": null
|
441 |
+
}
|
checkpoint-300/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fe05743275e1a0b3185dbc2310f1e055d91d945545cf3f061569e23d25ef075
|
3 |
+
size 5176
|
checkpoint-400/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: alpindale/Mistral-7B-v0.2-hf
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.10.0
|
checkpoint-400/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
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 sha256:8f44fe689c6a1969a4ec2f0a280e8548e0d301caa5938d00b682d6559bf93762
|
3 |
+
size 13648432
|
checkpoint-400/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c07b1bb5f3bc74b6484dd418751dc49bb89826c99c0295d649b6582f2c4de67a
|
3 |
+
size 27370618
|
checkpoint-400/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
|
3 |
+
size 14244
|
checkpoint-400/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72d6fbdefdd70f2b18634581d91c76f8fc4f901712088d9523b488224d822533
|
3 |
+
size 1064
|
checkpoint-400/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-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 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "right",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": false
|
45 |
+
}
|