Upload folder using huggingface_hub
Browse files- README.md +44 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- checkpoint-250/README.md +204 -0
- checkpoint-250/adapter_config.json +29 -0
- checkpoint-250/adapter_model.safetensors +3 -0
- checkpoint-250/optimizer.pt +3 -0
- checkpoint-250/pytorch_model.bin +3 -0
- checkpoint-250/rng_state.pth +3 -0
- checkpoint-250/scheduler.pt +3 -0
- checkpoint-250/special_tokens_map.json +24 -0
- checkpoint-250/tokenizer.json +0 -0
- checkpoint-250/tokenizer.model +3 -0
- checkpoint-250/tokenizer_config.json +42 -0
- checkpoint-250/trainer_state.json +455 -0
- checkpoint-250/training_args.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- training_args.bin +3 -0
- training_params.json +47 -0
README.md
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation
|
5 |
+
- peft
|
6 |
+
library_name: transformers
|
7 |
+
widget:
|
8 |
+
- messages:
|
9 |
+
- role: user
|
10 |
+
content: What is your favorite condiment?
|
11 |
+
license: other
|
12 |
+
---
|
13 |
+
|
14 |
+
# Model Trained Using AutoTrain
|
15 |
+
|
16 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
17 |
+
|
18 |
+
# Usage
|
19 |
+
|
20 |
+
```python
|
21 |
+
|
22 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
23 |
+
|
24 |
+
model_path = "PATH_TO_THIS_REPO"
|
25 |
+
|
26 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
27 |
+
model = AutoModelForCausalLM.from_pretrained(
|
28 |
+
model_path,
|
29 |
+
device_map="auto",
|
30 |
+
torch_dtype='auto'
|
31 |
+
).eval()
|
32 |
+
|
33 |
+
# Prompt content: "hi"
|
34 |
+
messages = [
|
35 |
+
{"role": "user", "content": "hi"}
|
36 |
+
]
|
37 |
+
|
38 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
39 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
40 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
41 |
+
|
42 |
+
# Model response: "Hello! How can I assist you today?"
|
43 |
+
print(response)
|
44 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-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": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_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 sha256:4c101a5590296c50caff00b3a08bb5b5baf347d3f6ec6cb057f4ef8dedb5153c
|
3 |
+
size 33571624
|
checkpoint-250/README.md
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: meta-llama/Llama-2-7b-chat-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 |
+
|
201 |
+
|
202 |
+
### Framework versions
|
203 |
+
|
204 |
+
- PEFT 0.10.0
|
checkpoint-250/adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-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": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
checkpoint-250/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c101a5590296c50caff00b3a08bb5b5baf347d3f6ec6cb057f4ef8dedb5153c
|
3 |
+
size 33571624
|
checkpoint-250/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40a1fed79befe992f6f513df5581c8fb51aeb6f04f42a6b7e0637bc64310bd55
|
3 |
+
size 67217018
|
checkpoint-250/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
|
3 |
+
size 888
|
checkpoint-250/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a15091ace83e5dae56dc01ce1f267aa31b14c8b6092e10215bb56256a6ab6d42
|
3 |
+
size 14244
|
checkpoint-250/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
|
3 |
+
size 1064
|
checkpoint-250/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-250/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-250/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-250/tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 1024,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"padding_side": "right",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|
checkpoint-250/trainer_state.json
ADDED
@@ -0,0 +1,455 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 47.61904761904762,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 250,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.76,
|
13 |
+
"grad_norm": 0.32970941066741943,
|
14 |
+
"learning_rate": 3.2000000000000005e-05,
|
15 |
+
"loss": 1.7065,
|
16 |
+
"step": 4
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.52,
|
20 |
+
"grad_norm": 0.34144940972328186,
|
21 |
+
"learning_rate": 6.400000000000001e-05,
|
22 |
+
"loss": 1.5961,
|
23 |
+
"step": 8
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.29,
|
27 |
+
"grad_norm": 0.3820774257183075,
|
28 |
+
"learning_rate": 9.6e-05,
|
29 |
+
"loss": 1.5497,
|
30 |
+
"step": 12
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 3.05,
|
34 |
+
"grad_norm": 0.359970360994339,
|
35 |
+
"learning_rate": 0.00012800000000000002,
|
36 |
+
"loss": 1.4212,
|
37 |
+
"step": 16
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 3.81,
|
41 |
+
"grad_norm": 0.3855084478855133,
|
42 |
+
"learning_rate": 0.00016,
|
43 |
+
"loss": 1.3231,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 4.57,
|
48 |
+
"grad_norm": 0.28801724314689636,
|
49 |
+
"learning_rate": 0.000192,
|
50 |
+
"loss": 1.2461,
|
51 |
+
"step": 24
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 5.33,
|
55 |
+
"grad_norm": 0.34446007013320923,
|
56 |
+
"learning_rate": 0.00019733333333333335,
|
57 |
+
"loss": 1.1191,
|
58 |
+
"step": 28
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 6.1,
|
62 |
+
"grad_norm": 0.3313669264316559,
|
63 |
+
"learning_rate": 0.0001937777777777778,
|
64 |
+
"loss": 1.119,
|
65 |
+
"step": 32
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 6.86,
|
69 |
+
"grad_norm": 0.2997862696647644,
|
70 |
+
"learning_rate": 0.00019022222222222224,
|
71 |
+
"loss": 1.0179,
|
72 |
+
"step": 36
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 7.62,
|
76 |
+
"grad_norm": 0.2927868962287903,
|
77 |
+
"learning_rate": 0.0001866666666666667,
|
78 |
+
"loss": 0.9294,
|
79 |
+
"step": 40
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 8.38,
|
83 |
+
"grad_norm": 0.303634911775589,
|
84 |
+
"learning_rate": 0.00018311111111111113,
|
85 |
+
"loss": 0.8856,
|
86 |
+
"step": 44
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 9.14,
|
90 |
+
"grad_norm": 0.4033955931663513,
|
91 |
+
"learning_rate": 0.00017955555555555558,
|
92 |
+
"loss": 0.86,
|
93 |
+
"step": 48
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 9.9,
|
97 |
+
"grad_norm": 0.42172765731811523,
|
98 |
+
"learning_rate": 0.00017600000000000002,
|
99 |
+
"loss": 0.7868,
|
100 |
+
"step": 52
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 10.67,
|
104 |
+
"grad_norm": 0.3995470702648163,
|
105 |
+
"learning_rate": 0.00017244444444444444,
|
106 |
+
"loss": 0.7428,
|
107 |
+
"step": 56
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 11.43,
|
111 |
+
"grad_norm": 0.4886798560619354,
|
112 |
+
"learning_rate": 0.00016888888888888889,
|
113 |
+
"loss": 0.6497,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 12.19,
|
118 |
+
"grad_norm": 0.8596562743186951,
|
119 |
+
"learning_rate": 0.00016533333333333333,
|
120 |
+
"loss": 0.6389,
|
121 |
+
"step": 64
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 12.95,
|
125 |
+
"grad_norm": 5.950181007385254,
|
126 |
+
"learning_rate": 0.00016177777777777778,
|
127 |
+
"loss": 0.525,
|
128 |
+
"step": 68
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 13.71,
|
132 |
+
"grad_norm": 2.282550096511841,
|
133 |
+
"learning_rate": 0.00015822222222222222,
|
134 |
+
"loss": 0.447,
|
135 |
+
"step": 72
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 14.48,
|
139 |
+
"grad_norm": 0.877649188041687,
|
140 |
+
"learning_rate": 0.00015466666666666667,
|
141 |
+
"loss": 0.4354,
|
142 |
+
"step": 76
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 15.24,
|
146 |
+
"grad_norm": 0.941230833530426,
|
147 |
+
"learning_rate": 0.0001511111111111111,
|
148 |
+
"loss": 0.3089,
|
149 |
+
"step": 80
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 16.0,
|
153 |
+
"grad_norm": 0.8986572027206421,
|
154 |
+
"learning_rate": 0.00014755555555555556,
|
155 |
+
"loss": 0.3118,
|
156 |
+
"step": 84
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 16.76,
|
160 |
+
"grad_norm": 0.9937779307365417,
|
161 |
+
"learning_rate": 0.000144,
|
162 |
+
"loss": 0.2487,
|
163 |
+
"step": 88
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 17.52,
|
167 |
+
"grad_norm": 0.9299382567405701,
|
168 |
+
"learning_rate": 0.00014044444444444445,
|
169 |
+
"loss": 0.2026,
|
170 |
+
"step": 92
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 18.29,
|
174 |
+
"grad_norm": 1.0898679494857788,
|
175 |
+
"learning_rate": 0.0001368888888888889,
|
176 |
+
"loss": 0.1691,
|
177 |
+
"step": 96
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 19.05,
|
181 |
+
"grad_norm": 1.1475147008895874,
|
182 |
+
"learning_rate": 0.00013333333333333334,
|
183 |
+
"loss": 0.1497,
|
184 |
+
"step": 100
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 19.81,
|
188 |
+
"grad_norm": 1.1220810413360596,
|
189 |
+
"learning_rate": 0.00012977777777777779,
|
190 |
+
"loss": 0.0984,
|
191 |
+
"step": 104
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 20.57,
|
195 |
+
"grad_norm": 1.19789457321167,
|
196 |
+
"learning_rate": 0.00012622222222222223,
|
197 |
+
"loss": 0.1001,
|
198 |
+
"step": 108
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 21.33,
|
202 |
+
"grad_norm": 0.8793210983276367,
|
203 |
+
"learning_rate": 0.00012266666666666668,
|
204 |
+
"loss": 0.072,
|
205 |
+
"step": 112
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 22.1,
|
209 |
+
"grad_norm": 0.9120911955833435,
|
210 |
+
"learning_rate": 0.00011911111111111111,
|
211 |
+
"loss": 0.0509,
|
212 |
+
"step": 116
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 22.86,
|
216 |
+
"grad_norm": 0.7733311653137207,
|
217 |
+
"learning_rate": 0.00011555555555555555,
|
218 |
+
"loss": 0.0429,
|
219 |
+
"step": 120
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 23.62,
|
223 |
+
"grad_norm": 0.6906972527503967,
|
224 |
+
"learning_rate": 0.00011200000000000001,
|
225 |
+
"loss": 0.0377,
|
226 |
+
"step": 124
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 24.38,
|
230 |
+
"grad_norm": 0.3450298607349396,
|
231 |
+
"learning_rate": 0.00010844444444444446,
|
232 |
+
"loss": 0.0271,
|
233 |
+
"step": 128
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 25.14,
|
237 |
+
"grad_norm": 0.40086209774017334,
|
238 |
+
"learning_rate": 0.0001048888888888889,
|
239 |
+
"loss": 0.0264,
|
240 |
+
"step": 132
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 25.9,
|
244 |
+
"grad_norm": 0.7334154844284058,
|
245 |
+
"learning_rate": 0.00010133333333333335,
|
246 |
+
"loss": 0.0212,
|
247 |
+
"step": 136
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 26.67,
|
251 |
+
"grad_norm": 0.2674214243888855,
|
252 |
+
"learning_rate": 9.777777777777778e-05,
|
253 |
+
"loss": 0.0169,
|
254 |
+
"step": 140
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 27.43,
|
258 |
+
"grad_norm": 0.2615182399749756,
|
259 |
+
"learning_rate": 9.422222222222223e-05,
|
260 |
+
"loss": 0.0173,
|
261 |
+
"step": 144
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 28.19,
|
265 |
+
"grad_norm": 0.12926605343818665,
|
266 |
+
"learning_rate": 9.066666666666667e-05,
|
267 |
+
"loss": 0.0149,
|
268 |
+
"step": 148
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 28.95,
|
272 |
+
"grad_norm": 0.1451052874326706,
|
273 |
+
"learning_rate": 8.711111111111112e-05,
|
274 |
+
"loss": 0.0142,
|
275 |
+
"step": 152
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 29.71,
|
279 |
+
"grad_norm": 0.12337276339530945,
|
280 |
+
"learning_rate": 8.355555555555556e-05,
|
281 |
+
"loss": 0.0111,
|
282 |
+
"step": 156
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 30.48,
|
286 |
+
"grad_norm": 0.10490886121988297,
|
287 |
+
"learning_rate": 8e-05,
|
288 |
+
"loss": 0.0126,
|
289 |
+
"step": 160
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 31.24,
|
293 |
+
"grad_norm": 0.12196756899356842,
|
294 |
+
"learning_rate": 7.644444444444445e-05,
|
295 |
+
"loss": 0.01,
|
296 |
+
"step": 164
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 32.0,
|
300 |
+
"grad_norm": 0.06647361814975739,
|
301 |
+
"learning_rate": 7.28888888888889e-05,
|
302 |
+
"loss": 0.0106,
|
303 |
+
"step": 168
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 32.76,
|
307 |
+
"grad_norm": 0.09191016852855682,
|
308 |
+
"learning_rate": 6.933333333333334e-05,
|
309 |
+
"loss": 0.0084,
|
310 |
+
"step": 172
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 33.52,
|
314 |
+
"grad_norm": 0.08465249091386795,
|
315 |
+
"learning_rate": 6.577777777777779e-05,
|
316 |
+
"loss": 0.0093,
|
317 |
+
"step": 176
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 34.29,
|
321 |
+
"grad_norm": 0.13242019712924957,
|
322 |
+
"learning_rate": 6.222222222222222e-05,
|
323 |
+
"loss": 0.0095,
|
324 |
+
"step": 180
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 35.05,
|
328 |
+
"grad_norm": 0.07912217080593109,
|
329 |
+
"learning_rate": 5.866666666666667e-05,
|
330 |
+
"loss": 0.0079,
|
331 |
+
"step": 184
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 35.81,
|
335 |
+
"grad_norm": 0.08500321954488754,
|
336 |
+
"learning_rate": 5.511111111111111e-05,
|
337 |
+
"loss": 0.0069,
|
338 |
+
"step": 188
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 36.57,
|
342 |
+
"grad_norm": 0.12945592403411865,
|
343 |
+
"learning_rate": 5.1555555555555556e-05,
|
344 |
+
"loss": 0.0076,
|
345 |
+
"step": 192
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 37.33,
|
349 |
+
"grad_norm": 0.05908092483878136,
|
350 |
+
"learning_rate": 4.8e-05,
|
351 |
+
"loss": 0.0079,
|
352 |
+
"step": 196
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 38.1,
|
356 |
+
"grad_norm": 0.05590814724564552,
|
357 |
+
"learning_rate": 4.4444444444444447e-05,
|
358 |
+
"loss": 0.0071,
|
359 |
+
"step": 200
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 38.86,
|
363 |
+
"grad_norm": 0.07217204570770264,
|
364 |
+
"learning_rate": 4.088888888888889e-05,
|
365 |
+
"loss": 0.0071,
|
366 |
+
"step": 204
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 39.62,
|
370 |
+
"grad_norm": 0.08633767813444138,
|
371 |
+
"learning_rate": 3.733333333333334e-05,
|
372 |
+
"loss": 0.0061,
|
373 |
+
"step": 208
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 40.38,
|
377 |
+
"grad_norm": 0.08432795852422714,
|
378 |
+
"learning_rate": 3.377777777777778e-05,
|
379 |
+
"loss": 0.007,
|
380 |
+
"step": 212
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 41.14,
|
384 |
+
"grad_norm": 0.06549498438835144,
|
385 |
+
"learning_rate": 3.0222222222222225e-05,
|
386 |
+
"loss": 0.0062,
|
387 |
+
"step": 216
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 41.9,
|
391 |
+
"grad_norm": 0.07968047261238098,
|
392 |
+
"learning_rate": 2.6666666666666667e-05,
|
393 |
+
"loss": 0.0056,
|
394 |
+
"step": 220
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 42.67,
|
398 |
+
"grad_norm": 0.054360050708055496,
|
399 |
+
"learning_rate": 2.3111111111111112e-05,
|
400 |
+
"loss": 0.0064,
|
401 |
+
"step": 224
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 43.43,
|
405 |
+
"grad_norm": 0.08684072643518448,
|
406 |
+
"learning_rate": 1.9555555555555557e-05,
|
407 |
+
"loss": 0.0052,
|
408 |
+
"step": 228
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 44.19,
|
412 |
+
"grad_norm": 0.08560307323932648,
|
413 |
+
"learning_rate": 1.6000000000000003e-05,
|
414 |
+
"loss": 0.0066,
|
415 |
+
"step": 232
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 44.95,
|
419 |
+
"grad_norm": 0.08709636330604553,
|
420 |
+
"learning_rate": 1.2444444444444445e-05,
|
421 |
+
"loss": 0.0055,
|
422 |
+
"step": 236
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 45.71,
|
426 |
+
"grad_norm": 0.03685537353157997,
|
427 |
+
"learning_rate": 8.88888888888889e-06,
|
428 |
+
"loss": 0.0054,
|
429 |
+
"step": 240
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 46.48,
|
433 |
+
"grad_norm": 0.10162707418203354,
|
434 |
+
"learning_rate": 5.333333333333334e-06,
|
435 |
+
"loss": 0.0059,
|
436 |
+
"step": 244
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 47.24,
|
440 |
+
"grad_norm": 0.061479195952415466,
|
441 |
+
"learning_rate": 1.777777777777778e-06,
|
442 |
+
"loss": 0.0051,
|
443 |
+
"step": 248
|
444 |
+
}
|
445 |
+
],
|
446 |
+
"logging_steps": 4,
|
447 |
+
"max_steps": 250,
|
448 |
+
"num_input_tokens_seen": 0,
|
449 |
+
"num_train_epochs": 50,
|
450 |
+
"save_steps": 500,
|
451 |
+
"total_flos": 4.0647058784256e+16,
|
452 |
+
"train_batch_size": 1,
|
453 |
+
"trial_name": null,
|
454 |
+
"trial_params": null
|
455 |
+
}
|
checkpoint-250/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:057d486cb53e31650a14452d87ed35bdef1aa612aec445994944d749138336fd
|
3 |
+
size 4920
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 1024,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"padding_side": "right",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:057d486cb53e31650a14452d87ed35bdef1aa612aec445994944d749138336fd
|
3 |
+
size 4920
|
training_params.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "meta-llama/Llama-2-7b-chat-hf",
|
3 |
+
"project_name": "2",
|
4 |
+
"data_path": "2/autotrain-data",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"add_eos_token": false,
|
8 |
+
"block_size": 1024,
|
9 |
+
"model_max_length": 1024,
|
10 |
+
"padding": null,
|
11 |
+
"trainer": "default",
|
12 |
+
"use_flash_attention_2": false,
|
13 |
+
"log": "none",
|
14 |
+
"disable_gradient_checkpointing": false,
|
15 |
+
"logging_steps": -1,
|
16 |
+
"evaluation_strategy": "epoch",
|
17 |
+
"save_total_limit": 1,
|
18 |
+
"save_strategy": "epoch",
|
19 |
+
"auto_find_batch_size": false,
|
20 |
+
"mixed_precision": "fp16",
|
21 |
+
"lr": 0.0002,
|
22 |
+
"epochs": 50,
|
23 |
+
"batch_size": 1,
|
24 |
+
"warmup_ratio": 0.1,
|
25 |
+
"gradient_accumulation": 4,
|
26 |
+
"optimizer": "adamw_torch",
|
27 |
+
"scheduler": "linear",
|
28 |
+
"weight_decay": 0.01,
|
29 |
+
"max_grad_norm": 1.0,
|
30 |
+
"seed": 42,
|
31 |
+
"chat_template": null,
|
32 |
+
"quantization": "int4",
|
33 |
+
"target_modules": null,
|
34 |
+
"merge_adapter": false,
|
35 |
+
"peft": true,
|
36 |
+
"lora_r": 16,
|
37 |
+
"lora_alpha": 32,
|
38 |
+
"lora_dropout": 0.05,
|
39 |
+
"model_ref": null,
|
40 |
+
"dpo_beta": 0.1,
|
41 |
+
"prompt_text_column": "autotrain_prompt",
|
42 |
+
"text_column": "autotrain_text",
|
43 |
+
"rejected_text_column": "autotrain_rejected_text",
|
44 |
+
"push_to_hub": true,
|
45 |
+
"repo_id": "rockyclh/llama-2-7b-chat-Glossary-financial-ratio",
|
46 |
+
"username": null
|
47 |
+
}
|