Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +45 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- autotrain-data/dataset_dict.json +1 -0
- autotrain-data/train/data-00000-of-00001.arrow +3 -0
- autotrain-data/train/dataset_info.json +16 -0
- autotrain-data/train/state.json +13 -0
- autotrain-data/validation/data-00000-of-00001.arrow +3 -0
- autotrain-data/validation/dataset_info.json +16 -0
- autotrain-data/validation/state.json +13 -0
- checkpoint-2695/README.md +202 -0
- checkpoint-2695/adapter_config.json +34 -0
- checkpoint-2695/adapter_model.safetensors +3 -0
- checkpoint-2695/optimizer.pt +3 -0
- checkpoint-2695/pytorch_model.bin +3 -0
- checkpoint-2695/rng_state.pth +3 -0
- checkpoint-2695/scheduler.pt +3 -0
- checkpoint-2695/special_tokens_map.json +34 -0
- checkpoint-2695/tokenizer.json +3 -0
- checkpoint-2695/tokenizer.model +3 -0
- checkpoint-2695/tokenizer_config.json +70 -0
- checkpoint-2695/trainer_state.json +770 -0
- checkpoint-2695/training_args.bin +3 -0
- runs/Mar27_11-14-19_DESKTOP-09EJKS6/events.out.tfevents.1711505690.DESKTOP-09EJKS6.16672.0 +2 -2
- special_tokens_map.json +34 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +70 -0
- training_args.bin +3 -0
- training_params.json +47 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
checkpoint-2695/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation-inference
|
5 |
+
- text-generation
|
6 |
+
- peft
|
7 |
+
library_name: transformers
|
8 |
+
widget:
|
9 |
+
- messages:
|
10 |
+
- role: user
|
11 |
+
content: What is your favorite condiment?
|
12 |
+
license: other
|
13 |
+
---
|
14 |
+
|
15 |
+
# Model Trained Using AutoTrain
|
16 |
+
|
17 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
18 |
+
|
19 |
+
# Usage
|
20 |
+
|
21 |
+
```python
|
22 |
+
|
23 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
24 |
+
|
25 |
+
model_path = "PATH_TO_THIS_REPO"
|
26 |
+
|
27 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
28 |
+
model = AutoModelForCausalLM.from_pretrained(
|
29 |
+
model_path,
|
30 |
+
device_map="auto",
|
31 |
+
torch_dtype='auto'
|
32 |
+
).eval()
|
33 |
+
|
34 |
+
# Prompt content: "hi"
|
35 |
+
messages = [
|
36 |
+
{"role": "user", "content": "hi"}
|
37 |
+
]
|
38 |
+
|
39 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
40 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
41 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
42 |
+
|
43 |
+
# Model response: "Hello! How can I assist you today?"
|
44 |
+
print(response)
|
45 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-2b-it",
|
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 |
+
"up_proj",
|
26 |
+
"o_proj",
|
27 |
+
"down_proj",
|
28 |
+
"k_proj",
|
29 |
+
"gate_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c867772ff6302167afed5fade5d54e7c6278fa1b04f48d0c5d759a00bff1cb7
|
3 |
+
size 78480072
|
autotrain-data/dataset_dict.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"splits": ["train", "validation"]}
|
autotrain-data/train/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa9d39aad035965d8d890e340584f91728655e1d09e4e930dbe96f0e3d0b8cd5
|
3 |
+
size 99839504
|
autotrain-data/train/dataset_info.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"response": {
|
6 |
+
"dtype": "string",
|
7 |
+
"_type": "Value"
|
8 |
+
},
|
9 |
+
"autotrain_text": {
|
10 |
+
"dtype": "string",
|
11 |
+
"_type": "Value"
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"homepage": "",
|
15 |
+
"license": ""
|
16 |
+
}
|
autotrain-data/train/state.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "8bd7c0e2adb74fd0",
|
8 |
+
"_format_columns": null,
|
9 |
+
"_format_kwargs": {},
|
10 |
+
"_format_type": null,
|
11 |
+
"_output_all_columns": false,
|
12 |
+
"_split": null
|
13 |
+
}
|
autotrain-data/validation/data-00000-of-00001.arrow
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa9d39aad035965d8d890e340584f91728655e1d09e4e930dbe96f0e3d0b8cd5
|
3 |
+
size 99839504
|
autotrain-data/validation/dataset_info.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"citation": "",
|
3 |
+
"description": "",
|
4 |
+
"features": {
|
5 |
+
"response": {
|
6 |
+
"dtype": "string",
|
7 |
+
"_type": "Value"
|
8 |
+
},
|
9 |
+
"autotrain_text": {
|
10 |
+
"dtype": "string",
|
11 |
+
"_type": "Value"
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"homepage": "",
|
15 |
+
"license": ""
|
16 |
+
}
|
autotrain-data/validation/state.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_data_files": [
|
3 |
+
{
|
4 |
+
"filename": "data-00000-of-00001.arrow"
|
5 |
+
}
|
6 |
+
],
|
7 |
+
"_fingerprint": "8bd7c0e2adb74fd0",
|
8 |
+
"_format_columns": null,
|
9 |
+
"_format_kwargs": {},
|
10 |
+
"_format_type": null,
|
11 |
+
"_output_all_columns": false,
|
12 |
+
"_split": null
|
13 |
+
}
|
checkpoint-2695/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: google/gemma-2b-it
|
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-2695/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "google/gemma-2b-it",
|
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 |
+
"up_proj",
|
26 |
+
"o_proj",
|
27 |
+
"down_proj",
|
28 |
+
"k_proj",
|
29 |
+
"gate_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-2695/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c867772ff6302167afed5fade5d54e7c6278fa1b04f48d0c5d759a00bff1cb7
|
3 |
+
size 78480072
|
checkpoint-2695/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09e47b3aa5ff5d1ee900147dc936d3375c819c606e6afdaaa20a03bcbbf34a89
|
3 |
+
size 157104826
|
checkpoint-2695/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d661518168fd4f63ccc7f86efee8168b53fe82dea4c6d5a3a94430425708002
|
3 |
+
size 888
|
checkpoint-2695/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48dd287b33de6260c6d8d34590b36e79d271dae3a783d52c20d4730c559a8c02
|
3 |
+
size 14244
|
checkpoint-2695/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1a254b98a24661fb0e693ef795e4c9a7485063be60fa5d404d1fdbd683ba239
|
3 |
+
size 1064
|
checkpoint-2695/special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<start_of_turn>",
|
4 |
+
"<end_of_turn>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<bos>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
checkpoint-2695/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
|
3 |
+
size 17477929
|
checkpoint-2695/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
checkpoint-2695/tokenizer_config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"106": {
|
38 |
+
"content": "<start_of_turn>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"107": {
|
46 |
+
"content": "<end_of_turn>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"additional_special_tokens": [
|
55 |
+
"<start_of_turn>",
|
56 |
+
"<end_of_turn>"
|
57 |
+
],
|
58 |
+
"bos_token": "<bos>",
|
59 |
+
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
60 |
+
"clean_up_tokenization_spaces": false,
|
61 |
+
"eos_token": "<eos>",
|
62 |
+
"legacy": null,
|
63 |
+
"model_max_length": 2048,
|
64 |
+
"pad_token": "<pad>",
|
65 |
+
"sp_model_kwargs": {},
|
66 |
+
"spaces_between_special_tokens": false,
|
67 |
+
"tokenizer_class": "GemmaTokenizer",
|
68 |
+
"unk_token": "<unk>",
|
69 |
+
"use_default_system_prompt": false
|
70 |
+
}
|
checkpoint-2695/trainer_state.json
ADDED
@@ -0,0 +1,770 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9997217842900863,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2695,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"grad_norm": 25.05885124206543,
|
14 |
+
"learning_rate": 2.666666666666667e-06,
|
15 |
+
"loss": 3.8791,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.02,
|
20 |
+
"grad_norm": 5.391462326049805,
|
21 |
+
"learning_rate": 5.333333333333334e-06,
|
22 |
+
"loss": 2.5036,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.03,
|
27 |
+
"grad_norm": 9.238971710205078,
|
28 |
+
"learning_rate": 8.111111111111112e-06,
|
29 |
+
"loss": 1.7464,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.04,
|
34 |
+
"grad_norm": 13.056879043579102,
|
35 |
+
"learning_rate": 1.088888888888889e-05,
|
36 |
+
"loss": 1.2491,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.05,
|
41 |
+
"grad_norm": 4.893646717071533,
|
42 |
+
"learning_rate": 1.3666666666666667e-05,
|
43 |
+
"loss": 0.4782,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.06,
|
48 |
+
"grad_norm": 0.030804015696048737,
|
49 |
+
"learning_rate": 1.6444444444444444e-05,
|
50 |
+
"loss": 0.0186,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.06,
|
55 |
+
"grad_norm": 0.11937689036130905,
|
56 |
+
"learning_rate": 1.922222222222222e-05,
|
57 |
+
"loss": 0.002,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.07,
|
62 |
+
"grad_norm": 0.0017061774851754308,
|
63 |
+
"learning_rate": 2.2e-05,
|
64 |
+
"loss": 0.0001,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.08,
|
69 |
+
"grad_norm": 0.0143441678956151,
|
70 |
+
"learning_rate": 2.477777777777778e-05,
|
71 |
+
"loss": 0.0,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.09,
|
76 |
+
"grad_norm": 0.001103504910133779,
|
77 |
+
"learning_rate": 2.7555555555555555e-05,
|
78 |
+
"loss": 0.0,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.1,
|
83 |
+
"grad_norm": 0.001787293003872037,
|
84 |
+
"learning_rate": 2.9962886597938144e-05,
|
85 |
+
"loss": 0.0001,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.11,
|
90 |
+
"grad_norm": 0.0007679874543100595,
|
91 |
+
"learning_rate": 2.965360824742268e-05,
|
92 |
+
"loss": 0.0,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.12,
|
97 |
+
"grad_norm": 0.0011675716377794743,
|
98 |
+
"learning_rate": 2.934432989690722e-05,
|
99 |
+
"loss": 0.0,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.13,
|
104 |
+
"grad_norm": 0.0006628546980209649,
|
105 |
+
"learning_rate": 2.903505154639175e-05,
|
106 |
+
"loss": 0.0,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.14,
|
111 |
+
"grad_norm": 0.0004541067173704505,
|
112 |
+
"learning_rate": 2.872577319587629e-05,
|
113 |
+
"loss": 0.0,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.15,
|
118 |
+
"grad_norm": 0.0036788100842386484,
|
119 |
+
"learning_rate": 2.8416494845360828e-05,
|
120 |
+
"loss": 0.0,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.16,
|
125 |
+
"grad_norm": 0.003441563807427883,
|
126 |
+
"learning_rate": 2.810721649484536e-05,
|
127 |
+
"loss": 0.0,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.17,
|
132 |
+
"grad_norm": 0.0021586541552096605,
|
133 |
+
"learning_rate": 2.77979381443299e-05,
|
134 |
+
"loss": 0.0,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.18,
|
139 |
+
"grad_norm": 0.002755054971203208,
|
140 |
+
"learning_rate": 2.7488659793814434e-05,
|
141 |
+
"loss": 0.0,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.19,
|
146 |
+
"grad_norm": 0.001827051630243659,
|
147 |
+
"learning_rate": 2.717938144329897e-05,
|
148 |
+
"loss": 0.0,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.19,
|
153 |
+
"grad_norm": 0.01897139474749565,
|
154 |
+
"learning_rate": 2.6870103092783505e-05,
|
155 |
+
"loss": 0.0,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.2,
|
160 |
+
"grad_norm": 0.00023522872652392834,
|
161 |
+
"learning_rate": 2.6560824742268044e-05,
|
162 |
+
"loss": 0.0,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.21,
|
167 |
+
"grad_norm": 0.00029744170024059713,
|
168 |
+
"learning_rate": 2.6251546391752576e-05,
|
169 |
+
"loss": 0.0,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.22,
|
174 |
+
"grad_norm": 0.00024159494205377996,
|
175 |
+
"learning_rate": 2.5942268041237114e-05,
|
176 |
+
"loss": 0.0,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.23,
|
181 |
+
"grad_norm": 0.0010275288950651884,
|
182 |
+
"learning_rate": 2.563298969072165e-05,
|
183 |
+
"loss": 0.0,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.24,
|
188 |
+
"grad_norm": 0.001225774991326034,
|
189 |
+
"learning_rate": 2.5323711340206185e-05,
|
190 |
+
"loss": 0.0,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.25,
|
195 |
+
"grad_norm": 0.00023019347281660885,
|
196 |
+
"learning_rate": 2.501443298969072e-05,
|
197 |
+
"loss": 0.0,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.26,
|
202 |
+
"grad_norm": 0.0008600191795267165,
|
203 |
+
"learning_rate": 2.470515463917526e-05,
|
204 |
+
"loss": 0.0,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.27,
|
209 |
+
"grad_norm": 0.00018496481061447412,
|
210 |
+
"learning_rate": 2.4395876288659795e-05,
|
211 |
+
"loss": 0.0,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.28,
|
216 |
+
"grad_norm": 0.0008189578074961901,
|
217 |
+
"learning_rate": 2.408659793814433e-05,
|
218 |
+
"loss": 0.0,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.29,
|
223 |
+
"grad_norm": 0.0006728855660185218,
|
224 |
+
"learning_rate": 2.377731958762887e-05,
|
225 |
+
"loss": 0.0,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.3,
|
230 |
+
"grad_norm": 0.00020031195890624076,
|
231 |
+
"learning_rate": 2.34680412371134e-05,
|
232 |
+
"loss": 0.0,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.31,
|
237 |
+
"grad_norm": 0.0011467556469142437,
|
238 |
+
"learning_rate": 2.315876288659794e-05,
|
239 |
+
"loss": 0.0,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.32,
|
244 |
+
"grad_norm": 0.0001870268170023337,
|
245 |
+
"learning_rate": 2.2849484536082475e-05,
|
246 |
+
"loss": 0.0,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.32,
|
251 |
+
"grad_norm": 0.0006849793717265129,
|
252 |
+
"learning_rate": 2.254020618556701e-05,
|
253 |
+
"loss": 0.0,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.33,
|
258 |
+
"grad_norm": 0.000808037118986249,
|
259 |
+
"learning_rate": 2.2230927835051546e-05,
|
260 |
+
"loss": 0.0,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.34,
|
265 |
+
"grad_norm": 0.0001667607866693288,
|
266 |
+
"learning_rate": 2.1921649484536084e-05,
|
267 |
+
"loss": 0.0,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.35,
|
272 |
+
"grad_norm": 0.0007605258724652231,
|
273 |
+
"learning_rate": 2.1612371134020616e-05,
|
274 |
+
"loss": 0.0,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.36,
|
279 |
+
"grad_norm": 0.00016520808276254684,
|
280 |
+
"learning_rate": 2.1303092783505155e-05,
|
281 |
+
"loss": 0.0,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.37,
|
286 |
+
"grad_norm": 0.0001515819749329239,
|
287 |
+
"learning_rate": 2.099381443298969e-05,
|
288 |
+
"loss": 0.0,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.38,
|
293 |
+
"grad_norm": 0.010785164311528206,
|
294 |
+
"learning_rate": 2.0684536082474226e-05,
|
295 |
+
"loss": 0.0,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.39,
|
300 |
+
"grad_norm": 0.0008493285276927054,
|
301 |
+
"learning_rate": 2.037525773195876e-05,
|
302 |
+
"loss": 0.0,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.4,
|
307 |
+
"grad_norm": 0.00024162570480257273,
|
308 |
+
"learning_rate": 2.00659793814433e-05,
|
309 |
+
"loss": 0.0,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.41,
|
314 |
+
"grad_norm": 0.00014333316357806325,
|
315 |
+
"learning_rate": 1.9756701030927835e-05,
|
316 |
+
"loss": 0.0,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.42,
|
321 |
+
"grad_norm": 0.00013407158257905394,
|
322 |
+
"learning_rate": 1.944742268041237e-05,
|
323 |
+
"loss": 0.0,
|
324 |
+
"step": 1125
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.43,
|
328 |
+
"grad_norm": 0.00013438447786029428,
|
329 |
+
"learning_rate": 1.913814432989691e-05,
|
330 |
+
"loss": 0.0,
|
331 |
+
"step": 1150
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.44,
|
335 |
+
"grad_norm": 0.0003521848120726645,
|
336 |
+
"learning_rate": 1.882886597938144e-05,
|
337 |
+
"loss": 0.0,
|
338 |
+
"step": 1175
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.45,
|
342 |
+
"grad_norm": 0.0005705170915462077,
|
343 |
+
"learning_rate": 1.851958762886598e-05,
|
344 |
+
"loss": 0.0,
|
345 |
+
"step": 1200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.45,
|
349 |
+
"grad_norm": 0.0003134581202175468,
|
350 |
+
"learning_rate": 1.8210309278350516e-05,
|
351 |
+
"loss": 0.0,
|
352 |
+
"step": 1225
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.46,
|
356 |
+
"grad_norm": 0.0001157010265160352,
|
357 |
+
"learning_rate": 1.790103092783505e-05,
|
358 |
+
"loss": 0.0,
|
359 |
+
"step": 1250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.47,
|
363 |
+
"grad_norm": 0.00011368603736627847,
|
364 |
+
"learning_rate": 1.7591752577319586e-05,
|
365 |
+
"loss": 0.0,
|
366 |
+
"step": 1275
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.48,
|
370 |
+
"grad_norm": 0.00016138765204232186,
|
371 |
+
"learning_rate": 1.7282474226804125e-05,
|
372 |
+
"loss": 0.0,
|
373 |
+
"step": 1300
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.49,
|
377 |
+
"grad_norm": 0.00011523786088218912,
|
378 |
+
"learning_rate": 1.697319587628866e-05,
|
379 |
+
"loss": 0.0,
|
380 |
+
"step": 1325
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.5,
|
384 |
+
"grad_norm": 0.00016504651284776628,
|
385 |
+
"learning_rate": 1.6663917525773196e-05,
|
386 |
+
"loss": 0.0,
|
387 |
+
"step": 1350
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.51,
|
391 |
+
"grad_norm": 0.0002800218644551933,
|
392 |
+
"learning_rate": 1.635463917525773e-05,
|
393 |
+
"loss": 0.0,
|
394 |
+
"step": 1375
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.52,
|
398 |
+
"grad_norm": 0.00010265475430060178,
|
399 |
+
"learning_rate": 1.604536082474227e-05,
|
400 |
+
"loss": 0.0,
|
401 |
+
"step": 1400
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.53,
|
405 |
+
"grad_norm": 0.00560023495927453,
|
406 |
+
"learning_rate": 1.5736082474226806e-05,
|
407 |
+
"loss": 0.0,
|
408 |
+
"step": 1425
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.54,
|
412 |
+
"grad_norm": 0.00010008086974266917,
|
413 |
+
"learning_rate": 1.542680412371134e-05,
|
414 |
+
"loss": 0.0,
|
415 |
+
"step": 1450
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.55,
|
419 |
+
"grad_norm": 9.670985309639946e-05,
|
420 |
+
"learning_rate": 1.5117525773195878e-05,
|
421 |
+
"loss": 0.0,
|
422 |
+
"step": 1475
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.56,
|
426 |
+
"grad_norm": 9.528211376164109e-05,
|
427 |
+
"learning_rate": 1.4808247422680412e-05,
|
428 |
+
"loss": 0.0,
|
429 |
+
"step": 1500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.57,
|
433 |
+
"grad_norm": 0.0001707332266960293,
|
434 |
+
"learning_rate": 1.4498969072164949e-05,
|
435 |
+
"loss": 0.0,
|
436 |
+
"step": 1525
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.57,
|
440 |
+
"grad_norm": 0.00045562253217212856,
|
441 |
+
"learning_rate": 1.4189690721649484e-05,
|
442 |
+
"loss": 0.0,
|
443 |
+
"step": 1550
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.58,
|
447 |
+
"grad_norm": 9.548822708893567e-05,
|
448 |
+
"learning_rate": 1.388041237113402e-05,
|
449 |
+
"loss": 0.0,
|
450 |
+
"step": 1575
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.59,
|
454 |
+
"grad_norm": 0.00022835374693386257,
|
455 |
+
"learning_rate": 1.3571134020618558e-05,
|
456 |
+
"loss": 0.0,
|
457 |
+
"step": 1600
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.6,
|
461 |
+
"grad_norm": 0.00044599550892598927,
|
462 |
+
"learning_rate": 1.3261855670103094e-05,
|
463 |
+
"loss": 0.0,
|
464 |
+
"step": 1625
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.61,
|
468 |
+
"grad_norm": 0.0001324521581409499,
|
469 |
+
"learning_rate": 1.2952577319587629e-05,
|
470 |
+
"loss": 0.0,
|
471 |
+
"step": 1650
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.62,
|
475 |
+
"grad_norm": 7.690698112128302e-05,
|
476 |
+
"learning_rate": 1.2643298969072166e-05,
|
477 |
+
"loss": 0.0,
|
478 |
+
"step": 1675
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.63,
|
482 |
+
"grad_norm": 0.00026828458067029715,
|
483 |
+
"learning_rate": 1.2334020618556701e-05,
|
484 |
+
"loss": 0.0,
|
485 |
+
"step": 1700
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.64,
|
489 |
+
"grad_norm": 7.547908899141476e-05,
|
490 |
+
"learning_rate": 1.2024742268041237e-05,
|
491 |
+
"loss": 0.0,
|
492 |
+
"step": 1725
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.65,
|
496 |
+
"grad_norm": 6.959487654967234e-05,
|
497 |
+
"learning_rate": 1.1715463917525774e-05,
|
498 |
+
"loss": 0.0,
|
499 |
+
"step": 1750
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.66,
|
503 |
+
"grad_norm": 0.0002681033220142126,
|
504 |
+
"learning_rate": 1.140618556701031e-05,
|
505 |
+
"loss": 0.0,
|
506 |
+
"step": 1775
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.67,
|
510 |
+
"grad_norm": 7.833562267478555e-05,
|
511 |
+
"learning_rate": 1.1096907216494845e-05,
|
512 |
+
"loss": 0.0,
|
513 |
+
"step": 1800
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.68,
|
517 |
+
"grad_norm": 0.00029178851400502026,
|
518 |
+
"learning_rate": 1.0787628865979382e-05,
|
519 |
+
"loss": 0.0,
|
520 |
+
"step": 1825
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.69,
|
524 |
+
"grad_norm": 0.0002143761230399832,
|
525 |
+
"learning_rate": 1.0478350515463917e-05,
|
526 |
+
"loss": 0.0,
|
527 |
+
"step": 1850
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.7,
|
531 |
+
"grad_norm": 0.00024392092018388212,
|
532 |
+
"learning_rate": 1.0169072164948452e-05,
|
533 |
+
"loss": 0.0,
|
534 |
+
"step": 1875
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.7,
|
538 |
+
"grad_norm": 0.005321436561644077,
|
539 |
+
"learning_rate": 9.85979381443299e-06,
|
540 |
+
"loss": 0.0,
|
541 |
+
"step": 1900
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.71,
|
545 |
+
"grad_norm": 0.00020479953673202544,
|
546 |
+
"learning_rate": 9.550515463917525e-06,
|
547 |
+
"loss": 0.0,
|
548 |
+
"step": 1925
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.72,
|
552 |
+
"grad_norm": 9.459372813580558e-05,
|
553 |
+
"learning_rate": 9.241237113402064e-06,
|
554 |
+
"loss": 0.0,
|
555 |
+
"step": 1950
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.73,
|
559 |
+
"grad_norm": 6.89596199663356e-05,
|
560 |
+
"learning_rate": 8.931958762886599e-06,
|
561 |
+
"loss": 0.0,
|
562 |
+
"step": 1975
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.74,
|
566 |
+
"grad_norm": 0.00019562170200515538,
|
567 |
+
"learning_rate": 8.622680412371134e-06,
|
568 |
+
"loss": 0.0,
|
569 |
+
"step": 2000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.75,
|
573 |
+
"grad_norm": 5.944158328929916e-05,
|
574 |
+
"learning_rate": 8.313402061855671e-06,
|
575 |
+
"loss": 0.0,
|
576 |
+
"step": 2025
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.76,
|
580 |
+
"grad_norm": 7.170682511059567e-05,
|
581 |
+
"learning_rate": 8.004123711340207e-06,
|
582 |
+
"loss": 0.0,
|
583 |
+
"step": 2050
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.77,
|
587 |
+
"grad_norm": 0.00020228260837029666,
|
588 |
+
"learning_rate": 7.694845360824742e-06,
|
589 |
+
"loss": 0.0,
|
590 |
+
"step": 2075
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.78,
|
594 |
+
"grad_norm": 0.0001803228515200317,
|
595 |
+
"learning_rate": 7.3855670103092784e-06,
|
596 |
+
"loss": 0.0,
|
597 |
+
"step": 2100
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.79,
|
601 |
+
"grad_norm": 7.207765156636015e-05,
|
602 |
+
"learning_rate": 7.076288659793815e-06,
|
603 |
+
"loss": 0.0,
|
604 |
+
"step": 2125
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.8,
|
608 |
+
"grad_norm": 0.00012546585639938712,
|
609 |
+
"learning_rate": 6.76701030927835e-06,
|
610 |
+
"loss": 0.0,
|
611 |
+
"step": 2150
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.81,
|
615 |
+
"grad_norm": 7.152390026021749e-05,
|
616 |
+
"learning_rate": 6.457731958762886e-06,
|
617 |
+
"loss": 0.0,
|
618 |
+
"step": 2175
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.82,
|
622 |
+
"grad_norm": 0.0001733840472297743,
|
623 |
+
"learning_rate": 6.148453608247423e-06,
|
624 |
+
"loss": 0.0,
|
625 |
+
"step": 2200
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.83,
|
629 |
+
"grad_norm": 0.0002956937823910266,
|
630 |
+
"learning_rate": 5.8391752577319596e-06,
|
631 |
+
"loss": 0.0,
|
632 |
+
"step": 2225
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.83,
|
636 |
+
"grad_norm": 0.000241271874983795,
|
637 |
+
"learning_rate": 5.529896907216495e-06,
|
638 |
+
"loss": 0.0,
|
639 |
+
"step": 2250
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.84,
|
643 |
+
"grad_norm": 7.127185381250456e-05,
|
644 |
+
"learning_rate": 5.220618556701031e-06,
|
645 |
+
"loss": 0.0,
|
646 |
+
"step": 2275
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.85,
|
650 |
+
"grad_norm": 0.00015488360077142715,
|
651 |
+
"learning_rate": 4.911340206185567e-06,
|
652 |
+
"loss": 0.0,
|
653 |
+
"step": 2300
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.86,
|
657 |
+
"grad_norm": 7.13276385795325e-05,
|
658 |
+
"learning_rate": 4.602061855670103e-06,
|
659 |
+
"loss": 0.0,
|
660 |
+
"step": 2325
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.87,
|
664 |
+
"grad_norm": 7.412026025122032e-05,
|
665 |
+
"learning_rate": 4.292783505154639e-06,
|
666 |
+
"loss": 0.0,
|
667 |
+
"step": 2350
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.88,
|
671 |
+
"grad_norm": 0.00010627138544805348,
|
672 |
+
"learning_rate": 3.983505154639176e-06,
|
673 |
+
"loss": 0.0,
|
674 |
+
"step": 2375
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.89,
|
678 |
+
"grad_norm": 6.658281927229837e-05,
|
679 |
+
"learning_rate": 3.6742268041237114e-06,
|
680 |
+
"loss": 0.0,
|
681 |
+
"step": 2400
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.9,
|
685 |
+
"grad_norm": 6.946924258954823e-05,
|
686 |
+
"learning_rate": 3.3649484536082477e-06,
|
687 |
+
"loss": 0.0,
|
688 |
+
"step": 2425
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.91,
|
692 |
+
"grad_norm": 9.910303197102621e-05,
|
693 |
+
"learning_rate": 3.0556701030927835e-06,
|
694 |
+
"loss": 0.0,
|
695 |
+
"step": 2450
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.92,
|
699 |
+
"grad_norm": 6.903583562234417e-05,
|
700 |
+
"learning_rate": 2.7463917525773197e-06,
|
701 |
+
"loss": 0.0,
|
702 |
+
"step": 2475
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.93,
|
706 |
+
"grad_norm": 0.0002056838129647076,
|
707 |
+
"learning_rate": 2.437113402061856e-06,
|
708 |
+
"loss": 0.0,
|
709 |
+
"step": 2500
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.94,
|
713 |
+
"grad_norm": 0.00023039935331325978,
|
714 |
+
"learning_rate": 2.1278350515463917e-06,
|
715 |
+
"loss": 0.0,
|
716 |
+
"step": 2525
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.95,
|
720 |
+
"grad_norm": 7.011190609773621e-05,
|
721 |
+
"learning_rate": 1.8185567010309277e-06,
|
722 |
+
"loss": 0.0,
|
723 |
+
"step": 2550
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.96,
|
727 |
+
"grad_norm": 7.29473540559411e-05,
|
728 |
+
"learning_rate": 1.509278350515464e-06,
|
729 |
+
"loss": 0.0,
|
730 |
+
"step": 2575
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.96,
|
734 |
+
"grad_norm": 9.540535393171012e-05,
|
735 |
+
"learning_rate": 1.2000000000000002e-06,
|
736 |
+
"loss": 0.0,
|
737 |
+
"step": 2600
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.97,
|
741 |
+
"grad_norm": 7.17702423571609e-05,
|
742 |
+
"learning_rate": 8.907216494845361e-07,
|
743 |
+
"loss": 0.0,
|
744 |
+
"step": 2625
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.98,
|
748 |
+
"grad_norm": 6.912889512022957e-05,
|
749 |
+
"learning_rate": 5.814432989690722e-07,
|
750 |
+
"loss": 0.0,
|
751 |
+
"step": 2650
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.99,
|
755 |
+
"grad_norm": 7.510351133532822e-05,
|
756 |
+
"learning_rate": 2.7216494845360824e-07,
|
757 |
+
"loss": 0.0,
|
758 |
+
"step": 2675
|
759 |
+
}
|
760 |
+
],
|
761 |
+
"logging_steps": 25,
|
762 |
+
"max_steps": 2695,
|
763 |
+
"num_input_tokens_seen": 0,
|
764 |
+
"num_train_epochs": 1,
|
765 |
+
"save_steps": 500,
|
766 |
+
"total_flos": 1.3256372778958848e+17,
|
767 |
+
"train_batch_size": 1,
|
768 |
+
"trial_name": null,
|
769 |
+
"trial_params": null
|
770 |
+
}
|
checkpoint-2695/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28d2e78c2bd95b653ee66408d827479fbb68511b78e9cbf4d959ef34ec8d07e1
|
3 |
+
size 4984
|
runs/Mar27_11-14-19_DESKTOP-09EJKS6/events.out.tfevents.1711505690.DESKTOP-09EJKS6.16672.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e7ec56e53d2ca8288933e57c92ed6be8f5ed06be1a9b2746383d8cbcf31f79a
|
3 |
+
size 28124
|
special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<start_of_turn>",
|
4 |
+
"<end_of_turn>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<bos>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
|
3 |
+
size 17477929
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
3 |
+
size 4241003
|
tokenizer_config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"106": {
|
38 |
+
"content": "<start_of_turn>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"107": {
|
46 |
+
"content": "<end_of_turn>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"additional_special_tokens": [
|
55 |
+
"<start_of_turn>",
|
56 |
+
"<end_of_turn>"
|
57 |
+
],
|
58 |
+
"bos_token": "<bos>",
|
59 |
+
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
60 |
+
"clean_up_tokenization_spaces": false,
|
61 |
+
"eos_token": "<eos>",
|
62 |
+
"legacy": null,
|
63 |
+
"model_max_length": 2048,
|
64 |
+
"pad_token": "<pad>",
|
65 |
+
"sp_model_kwargs": {},
|
66 |
+
"spaces_between_special_tokens": false,
|
67 |
+
"tokenizer_class": "GemmaTokenizer",
|
68 |
+
"unk_token": "<unk>",
|
69 |
+
"use_default_system_prompt": false
|
70 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28d2e78c2bd95b653ee66408d827479fbb68511b78e9cbf4d959ef34ec8d07e1
|
3 |
+
size 4984
|
training_params.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "google/gemma-2b-it",
|
3 |
+
"project_name": "gemma-2b-it-adress-bot-seoul-epochs-1",
|
4 |
+
"data_path": "gemma-2b-it-adress-bot-seoul-epochs-1/autotrain-data",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"add_eos_token": true,
|
8 |
+
"block_size": 1024,
|
9 |
+
"model_max_length": 2048,
|
10 |
+
"padding": "right",
|
11 |
+
"trainer": "sft",
|
12 |
+
"use_flash_attention_2": false,
|
13 |
+
"log": "tensorboard",
|
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": 3e-05,
|
22 |
+
"epochs": 1,
|
23 |
+
"batch_size": 1,
|
24 |
+
"warmup_ratio": 0.1,
|
25 |
+
"gradient_accumulation": 4,
|
26 |
+
"optimizer": "adamw_torch",
|
27 |
+
"scheduler": "linear",
|
28 |
+
"weight_decay": 0.0,
|
29 |
+
"max_grad_norm": 1.0,
|
30 |
+
"seed": 42,
|
31 |
+
"chat_template": "none",
|
32 |
+
"quantization": "int4",
|
33 |
+
"target_modules": "all-linear",
|
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": "SungmoKim/gemma-2b-it-adress-bot-seoul-epochs-1",
|
46 |
+
"username": "SungmoKim"
|
47 |
+
}
|