Commit
•
974544d
1
Parent(s):
7801575
Upload folder using huggingface_hub (#4)
Browse files- Upload folder using huggingface_hub (e93c71512aeadedbffd27d5ae25c7d9a87260ec2)
- README.md +198 -0
- adapter_model.bin +1 -1
- checkpoint-100/README.md +205 -1
- checkpoint-100/adapter_model.bin +1 -1
- checkpoint-100/optimizer.pt +1 -1
- checkpoint-100/rng_state.pth +1 -1
- checkpoint-100/scheduler.pt +1 -1
- checkpoint-100/tokenizer_config.json +35 -0
- checkpoint-100/trainer_state.json +304 -304
- checkpoint-100/training_args.bin +1 -1
- runs/Oct12_18-12-36_63a985a0dcf5/events.out.tfevents.1697134361.63a985a0dcf5.4074.0 +3 -0
- tokenizer_config.json +35 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,203 @@
|
|
1 |
---
|
2 |
library_name: peft
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
## Training procedure
|
5 |
|
6 |
|
@@ -15,6 +212,7 @@ The following `bitsandbytes` quantization config was used during training:
|
|
15 |
- bnb_4bit_quant_type: fp4
|
16 |
- bnb_4bit_use_double_quant: False
|
17 |
- bnb_4bit_compute_dtype: float32
|
|
|
18 |
### Framework versions
|
19 |
|
20 |
|
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
+
base_model: bigscience/bloomz-3b
|
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 |
+
- **Shared by [optional]:** [More Information Needed]
|
22 |
+
- **Model type:** [More Information Needed]
|
23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
24 |
+
- **License:** [More Information Needed]
|
25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
26 |
+
|
27 |
+
### Model Sources [optional]
|
28 |
+
|
29 |
+
<!-- Provide the basic links for the model. -->
|
30 |
+
|
31 |
+
- **Repository:** [More Information Needed]
|
32 |
+
- **Paper [optional]:** [More Information Needed]
|
33 |
+
- **Demo [optional]:** [More Information Needed]
|
34 |
+
|
35 |
+
## Uses
|
36 |
+
|
37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
38 |
+
|
39 |
+
### Direct Use
|
40 |
+
|
41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
42 |
+
|
43 |
+
[More Information Needed]
|
44 |
+
|
45 |
+
### Downstream Use [optional]
|
46 |
+
|
47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
48 |
+
|
49 |
+
[More Information Needed]
|
50 |
+
|
51 |
+
### Out-of-Scope Use
|
52 |
+
|
53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
54 |
+
|
55 |
+
[More Information Needed]
|
56 |
+
|
57 |
+
## Bias, Risks, and Limitations
|
58 |
+
|
59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
60 |
+
|
61 |
+
[More Information Needed]
|
62 |
+
|
63 |
+
### Recommendations
|
64 |
+
|
65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
66 |
+
|
67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
68 |
+
|
69 |
+
## How to Get Started with the Model
|
70 |
+
|
71 |
+
Use the code below to get started with the model.
|
72 |
+
|
73 |
+
[More Information Needed]
|
74 |
+
|
75 |
+
## Training Details
|
76 |
+
|
77 |
+
### Training Data
|
78 |
+
|
79 |
+
<!-- This should link to a Data 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. -->
|
80 |
+
|
81 |
+
[More Information Needed]
|
82 |
+
|
83 |
+
### Training Procedure
|
84 |
+
|
85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
86 |
+
|
87 |
+
#### Preprocessing [optional]
|
88 |
+
|
89 |
+
[More Information Needed]
|
90 |
+
|
91 |
+
|
92 |
+
#### Training Hyperparameters
|
93 |
+
|
94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
95 |
+
|
96 |
+
#### Speeds, Sizes, Times [optional]
|
97 |
+
|
98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
99 |
+
|
100 |
+
[More Information Needed]
|
101 |
+
|
102 |
+
## Evaluation
|
103 |
+
|
104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
105 |
+
|
106 |
+
### Testing Data, Factors & Metrics
|
107 |
+
|
108 |
+
#### Testing Data
|
109 |
+
|
110 |
+
<!-- This should link to a Data Card if possible. -->
|
111 |
+
|
112 |
+
[More Information Needed]
|
113 |
+
|
114 |
+
#### Factors
|
115 |
+
|
116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
117 |
+
|
118 |
+
[More Information Needed]
|
119 |
+
|
120 |
+
#### Metrics
|
121 |
+
|
122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
123 |
+
|
124 |
+
[More Information Needed]
|
125 |
+
|
126 |
+
### Results
|
127 |
+
|
128 |
+
[More Information Needed]
|
129 |
+
|
130 |
+
#### Summary
|
131 |
+
|
132 |
+
|
133 |
+
|
134 |
+
## Model Examination [optional]
|
135 |
+
|
136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
137 |
+
|
138 |
+
[More Information Needed]
|
139 |
+
|
140 |
+
## Environmental Impact
|
141 |
+
|
142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
143 |
+
|
144 |
+
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).
|
145 |
+
|
146 |
+
- **Hardware Type:** [More Information Needed]
|
147 |
+
- **Hours used:** [More Information Needed]
|
148 |
+
- **Cloud Provider:** [More Information Needed]
|
149 |
+
- **Compute Region:** [More Information Needed]
|
150 |
+
- **Carbon Emitted:** [More Information Needed]
|
151 |
+
|
152 |
+
## Technical Specifications [optional]
|
153 |
+
|
154 |
+
### Model Architecture and Objective
|
155 |
+
|
156 |
+
[More Information Needed]
|
157 |
+
|
158 |
+
### Compute Infrastructure
|
159 |
+
|
160 |
+
[More Information Needed]
|
161 |
+
|
162 |
+
#### Hardware
|
163 |
+
|
164 |
+
[More Information Needed]
|
165 |
+
|
166 |
+
#### Software
|
167 |
+
|
168 |
+
[More Information Needed]
|
169 |
+
|
170 |
+
## Citation [optional]
|
171 |
+
|
172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
173 |
+
|
174 |
+
**BibTeX:**
|
175 |
+
|
176 |
+
[More Information Needed]
|
177 |
+
|
178 |
+
**APA:**
|
179 |
+
|
180 |
+
[More Information Needed]
|
181 |
+
|
182 |
+
## Glossary [optional]
|
183 |
+
|
184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
185 |
+
|
186 |
+
[More Information Needed]
|
187 |
+
|
188 |
+
## More Information [optional]
|
189 |
+
|
190 |
+
[More Information Needed]
|
191 |
+
|
192 |
+
## Model Card Authors [optional]
|
193 |
+
|
194 |
+
[More Information Needed]
|
195 |
+
|
196 |
+
## Model Card Contact
|
197 |
+
|
198 |
+
[More Information Needed]
|
199 |
+
|
200 |
+
|
201 |
## Training procedure
|
202 |
|
203 |
|
|
|
212 |
- bnb_4bit_quant_type: fp4
|
213 |
- bnb_4bit_use_double_quant: False
|
214 |
- bnb_4bit_compute_dtype: float32
|
215 |
+
|
216 |
### Framework versions
|
217 |
|
218 |
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39409357
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e40b7b6ec13002db8ba2108993b9af6829adb99a2fddff2d6b009c40f622d55
|
3 |
size 39409357
|
checkpoint-100/README.md
CHANGED
@@ -1,6 +1,203 @@
|
|
1 |
---
|
2 |
library_name: peft
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
## Training procedure
|
5 |
|
6 |
|
@@ -16,6 +213,13 @@ The following `bitsandbytes` quantization config was used during training:
|
|
16 |
- bnb_4bit_use_double_quant: False
|
17 |
- bnb_4bit_compute_dtype: float32
|
18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
The following `bitsandbytes` quantization config was used during training:
|
20 |
- quant_method: bitsandbytes
|
21 |
- load_in_8bit: True
|
@@ -27,8 +231,8 @@ The following `bitsandbytes` quantization config was used during training:
|
|
27 |
- bnb_4bit_quant_type: fp4
|
28 |
- bnb_4bit_use_double_quant: False
|
29 |
- bnb_4bit_compute_dtype: float32
|
|
|
30 |
### Framework versions
|
31 |
|
32 |
-
- PEFT 0.6.0.dev0
|
33 |
|
34 |
- PEFT 0.6.0.dev0
|
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
+
base_model: bigscience/bloomz-3b
|
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 |
+
- **Shared by [optional]:** [More Information Needed]
|
22 |
+
- **Model type:** [More Information Needed]
|
23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
24 |
+
- **License:** [More Information Needed]
|
25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
26 |
+
|
27 |
+
### Model Sources [optional]
|
28 |
+
|
29 |
+
<!-- Provide the basic links for the model. -->
|
30 |
+
|
31 |
+
- **Repository:** [More Information Needed]
|
32 |
+
- **Paper [optional]:** [More Information Needed]
|
33 |
+
- **Demo [optional]:** [More Information Needed]
|
34 |
+
|
35 |
+
## Uses
|
36 |
+
|
37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
38 |
+
|
39 |
+
### Direct Use
|
40 |
+
|
41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
42 |
+
|
43 |
+
[More Information Needed]
|
44 |
+
|
45 |
+
### Downstream Use [optional]
|
46 |
+
|
47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
48 |
+
|
49 |
+
[More Information Needed]
|
50 |
+
|
51 |
+
### Out-of-Scope Use
|
52 |
+
|
53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
54 |
+
|
55 |
+
[More Information Needed]
|
56 |
+
|
57 |
+
## Bias, Risks, and Limitations
|
58 |
+
|
59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
60 |
+
|
61 |
+
[More Information Needed]
|
62 |
+
|
63 |
+
### Recommendations
|
64 |
+
|
65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
66 |
+
|
67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
68 |
+
|
69 |
+
## How to Get Started with the Model
|
70 |
+
|
71 |
+
Use the code below to get started with the model.
|
72 |
+
|
73 |
+
[More Information Needed]
|
74 |
+
|
75 |
+
## Training Details
|
76 |
+
|
77 |
+
### Training Data
|
78 |
+
|
79 |
+
<!-- This should link to a Data 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. -->
|
80 |
+
|
81 |
+
[More Information Needed]
|
82 |
+
|
83 |
+
### Training Procedure
|
84 |
+
|
85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
86 |
+
|
87 |
+
#### Preprocessing [optional]
|
88 |
+
|
89 |
+
[More Information Needed]
|
90 |
+
|
91 |
+
|
92 |
+
#### Training Hyperparameters
|
93 |
+
|
94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
95 |
+
|
96 |
+
#### Speeds, Sizes, Times [optional]
|
97 |
+
|
98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
99 |
+
|
100 |
+
[More Information Needed]
|
101 |
+
|
102 |
+
## Evaluation
|
103 |
+
|
104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
105 |
+
|
106 |
+
### Testing Data, Factors & Metrics
|
107 |
+
|
108 |
+
#### Testing Data
|
109 |
+
|
110 |
+
<!-- This should link to a Data Card if possible. -->
|
111 |
+
|
112 |
+
[More Information Needed]
|
113 |
+
|
114 |
+
#### Factors
|
115 |
+
|
116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
117 |
+
|
118 |
+
[More Information Needed]
|
119 |
+
|
120 |
+
#### Metrics
|
121 |
+
|
122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
123 |
+
|
124 |
+
[More Information Needed]
|
125 |
+
|
126 |
+
### Results
|
127 |
+
|
128 |
+
[More Information Needed]
|
129 |
+
|
130 |
+
#### Summary
|
131 |
+
|
132 |
+
|
133 |
+
|
134 |
+
## Model Examination [optional]
|
135 |
+
|
136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
137 |
+
|
138 |
+
[More Information Needed]
|
139 |
+
|
140 |
+
## Environmental Impact
|
141 |
+
|
142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
143 |
+
|
144 |
+
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).
|
145 |
+
|
146 |
+
- **Hardware Type:** [More Information Needed]
|
147 |
+
- **Hours used:** [More Information Needed]
|
148 |
+
- **Cloud Provider:** [More Information Needed]
|
149 |
+
- **Compute Region:** [More Information Needed]
|
150 |
+
- **Carbon Emitted:** [More Information Needed]
|
151 |
+
|
152 |
+
## Technical Specifications [optional]
|
153 |
+
|
154 |
+
### Model Architecture and Objective
|
155 |
+
|
156 |
+
[More Information Needed]
|
157 |
+
|
158 |
+
### Compute Infrastructure
|
159 |
+
|
160 |
+
[More Information Needed]
|
161 |
+
|
162 |
+
#### Hardware
|
163 |
+
|
164 |
+
[More Information Needed]
|
165 |
+
|
166 |
+
#### Software
|
167 |
+
|
168 |
+
[More Information Needed]
|
169 |
+
|
170 |
+
## Citation [optional]
|
171 |
+
|
172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
173 |
+
|
174 |
+
**BibTeX:**
|
175 |
+
|
176 |
+
[More Information Needed]
|
177 |
+
|
178 |
+
**APA:**
|
179 |
+
|
180 |
+
[More Information Needed]
|
181 |
+
|
182 |
+
## Glossary [optional]
|
183 |
+
|
184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
185 |
+
|
186 |
+
[More Information Needed]
|
187 |
+
|
188 |
+
## More Information [optional]
|
189 |
+
|
190 |
+
[More Information Needed]
|
191 |
+
|
192 |
+
## Model Card Authors [optional]
|
193 |
+
|
194 |
+
[More Information Needed]
|
195 |
+
|
196 |
+
## Model Card Contact
|
197 |
+
|
198 |
+
[More Information Needed]
|
199 |
+
|
200 |
+
|
201 |
## Training procedure
|
202 |
|
203 |
|
|
|
213 |
- bnb_4bit_use_double_quant: False
|
214 |
- bnb_4bit_compute_dtype: float32
|
215 |
|
216 |
+
### Framework versions
|
217 |
+
|
218 |
+
|
219 |
+
- PEFT 0.6.0.dev0
|
220 |
+
## Training procedure
|
221 |
+
|
222 |
+
|
223 |
The following `bitsandbytes` quantization config was used during training:
|
224 |
- quant_method: bitsandbytes
|
225 |
- load_in_8bit: True
|
|
|
231 |
- bnb_4bit_quant_type: fp4
|
232 |
- bnb_4bit_use_double_quant: False
|
233 |
- bnb_4bit_compute_dtype: float32
|
234 |
+
|
235 |
### Framework versions
|
236 |
|
|
|
237 |
|
238 |
- PEFT 0.6.0.dev0
|
checkpoint-100/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39409357
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c394307bbd8fa249a03539583b0146418f3ec081d9e00bd4d47de6b6362685a1
|
3 |
size 39409357
|
checkpoint-100/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 78844421
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5c435a8d185fca70ecaa721a10760c7ba3f9eab4a917a3864841f3f9d5ee652
|
3 |
size 78844421
|
checkpoint-100/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36fc71bd44bd7f04f2599c5dface64c517de1a7ab7bac3600f3f6470c6c72673
|
3 |
size 14575
|
checkpoint-100/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:623e145e5ab24cb1507f4f210040814726c2c3abec15b64a36227aa6dd37bb5a
|
3 |
size 627
|
checkpoint-100/tokenizer_config.json
CHANGED
@@ -1,5 +1,40 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"bos_token": "<s>",
|
4 |
"clean_up_tokenization_spaces": false,
|
5 |
"eos_token": "</s>",
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<unk>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<pad>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"additional_special_tokens": [],
|
38 |
"bos_token": "<s>",
|
39 |
"clean_up_tokenization_spaces": false,
|
40 |
"eos_token": "</s>",
|
checkpoint-100/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,611 +9,611 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"learning_rate": 0.
|
14 |
-
"loss": 2.
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
-
"epoch": 0.
|
19 |
-
"learning_rate": 0.
|
20 |
-
"loss": 2.
|
21 |
"step": 2
|
22 |
},
|
23 |
{
|
24 |
-
"epoch": 0.
|
25 |
-
"learning_rate": 0.
|
26 |
-
"loss": 1.
|
27 |
"step": 3
|
28 |
},
|
29 |
{
|
30 |
-
"epoch":
|
31 |
-
"learning_rate": 0.
|
32 |
-
"loss": 1.
|
33 |
"step": 4
|
34 |
},
|
35 |
{
|
36 |
-
"epoch":
|
37 |
-
"learning_rate": 0.
|
38 |
-
"loss": 1.
|
39 |
"step": 5
|
40 |
},
|
41 |
{
|
42 |
-
"epoch":
|
43 |
-
"learning_rate": 0.
|
44 |
-
"loss": 1.
|
45 |
"step": 6
|
46 |
},
|
47 |
{
|
48 |
-
"epoch":
|
49 |
-
"learning_rate": 0.
|
50 |
-
"loss": 1.
|
51 |
"step": 7
|
52 |
},
|
53 |
{
|
54 |
-
"epoch":
|
55 |
-
"learning_rate": 0.
|
56 |
-
"loss": 1.
|
57 |
"step": 8
|
58 |
},
|
59 |
{
|
60 |
-
"epoch":
|
61 |
-
"learning_rate": 0.
|
62 |
-
"loss": 1.
|
63 |
"step": 9
|
64 |
},
|
65 |
{
|
66 |
-
"epoch":
|
67 |
-
"learning_rate": 0.
|
68 |
-
"loss": 1.
|
69 |
"step": 10
|
70 |
},
|
71 |
{
|
72 |
-
"epoch":
|
73 |
-
"learning_rate": 0.
|
74 |
-
"loss": 1.
|
75 |
"step": 11
|
76 |
},
|
77 |
{
|
78 |
-
"epoch":
|
79 |
-
"learning_rate": 0.
|
80 |
-
"loss": 1.
|
81 |
"step": 12
|
82 |
},
|
83 |
{
|
84 |
-
"epoch":
|
85 |
-
"learning_rate": 0.
|
86 |
-
"loss": 1.
|
87 |
"step": 13
|
88 |
},
|
89 |
{
|
90 |
-
"epoch":
|
91 |
-
"learning_rate": 0.
|
92 |
-
"loss": 1.
|
93 |
"step": 14
|
94 |
},
|
95 |
{
|
96 |
-
"epoch":
|
97 |
-
"learning_rate": 0.
|
98 |
-
"loss": 1.
|
99 |
"step": 15
|
100 |
},
|
101 |
{
|
102 |
-
"epoch":
|
103 |
-
"learning_rate": 0.
|
104 |
-
"loss": 1.
|
105 |
"step": 16
|
106 |
},
|
107 |
{
|
108 |
-
"epoch":
|
109 |
-
"learning_rate": 0.
|
110 |
-
"loss": 1.
|
111 |
"step": 17
|
112 |
},
|
113 |
{
|
114 |
-
"epoch":
|
115 |
-
"learning_rate": 0.
|
116 |
-
"loss": 1.
|
117 |
"step": 18
|
118 |
},
|
119 |
{
|
120 |
-
"epoch":
|
121 |
-
"learning_rate": 0.
|
122 |
-
"loss": 1.
|
123 |
"step": 19
|
124 |
},
|
125 |
{
|
126 |
-
"epoch":
|
127 |
-
"learning_rate": 0.
|
128 |
-
"loss": 1.
|
129 |
"step": 20
|
130 |
},
|
131 |
{
|
132 |
-
"epoch":
|
133 |
-
"learning_rate": 0.
|
134 |
-
"loss":
|
135 |
"step": 21
|
136 |
},
|
137 |
{
|
138 |
-
"epoch":
|
139 |
-
"learning_rate": 0.
|
140 |
-
"loss":
|
141 |
"step": 22
|
142 |
},
|
143 |
{
|
144 |
-
"epoch":
|
145 |
-
"learning_rate": 0.
|
146 |
-
"loss":
|
147 |
"step": 23
|
148 |
},
|
149 |
{
|
150 |
-
"epoch":
|
151 |
-
"learning_rate": 0.
|
152 |
-
"loss":
|
153 |
"step": 24
|
154 |
},
|
155 |
{
|
156 |
-
"epoch":
|
157 |
-
"learning_rate": 0.
|
158 |
-
"loss":
|
159 |
"step": 25
|
160 |
},
|
161 |
{
|
162 |
-
"epoch":
|
163 |
-
"learning_rate": 0.
|
164 |
-
"loss":
|
165 |
"step": 26
|
166 |
},
|
167 |
{
|
168 |
-
"epoch":
|
169 |
-
"learning_rate": 0.
|
170 |
-
"loss":
|
171 |
"step": 27
|
172 |
},
|
173 |
{
|
174 |
-
"epoch":
|
175 |
-
"learning_rate": 0.
|
176 |
-
"loss":
|
177 |
"step": 28
|
178 |
},
|
179 |
{
|
180 |
-
"epoch":
|
181 |
-
"learning_rate": 0.
|
182 |
-
"loss":
|
183 |
"step": 29
|
184 |
},
|
185 |
{
|
186 |
-
"epoch":
|
187 |
-
"learning_rate": 0.
|
188 |
-
"loss":
|
189 |
"step": 30
|
190 |
},
|
191 |
{
|
192 |
-
"epoch":
|
193 |
-
"learning_rate": 0.
|
194 |
-
"loss":
|
195 |
"step": 31
|
196 |
},
|
197 |
{
|
198 |
-
"epoch":
|
199 |
-
"learning_rate": 0.
|
200 |
-
"loss":
|
201 |
"step": 32
|
202 |
},
|
203 |
{
|
204 |
-
"epoch":
|
205 |
-
"learning_rate": 0.
|
206 |
-
"loss":
|
207 |
"step": 33
|
208 |
},
|
209 |
{
|
210 |
-
"epoch":
|
211 |
-
"learning_rate": 0.
|
212 |
-
"loss":
|
213 |
"step": 34
|
214 |
},
|
215 |
{
|
216 |
-
"epoch":
|
217 |
-
"learning_rate": 0.
|
218 |
-
"loss":
|
219 |
"step": 35
|
220 |
},
|
221 |
{
|
222 |
-
"epoch":
|
223 |
-
"learning_rate": 0.
|
224 |
-
"loss":
|
225 |
"step": 36
|
226 |
},
|
227 |
{
|
228 |
-
"epoch":
|
229 |
-
"learning_rate": 0.
|
230 |
-
"loss":
|
231 |
"step": 37
|
232 |
},
|
233 |
{
|
234 |
-
"epoch":
|
235 |
-
"learning_rate": 0.
|
236 |
-
"loss":
|
237 |
"step": 38
|
238 |
},
|
239 |
{
|
240 |
-
"epoch":
|
241 |
-
"learning_rate": 0.
|
242 |
-
"loss":
|
243 |
"step": 39
|
244 |
},
|
245 |
{
|
246 |
-
"epoch":
|
247 |
-
"learning_rate": 0.
|
248 |
-
"loss":
|
249 |
"step": 40
|
250 |
},
|
251 |
{
|
252 |
-
"epoch":
|
253 |
-
"learning_rate": 0.
|
254 |
-
"loss":
|
255 |
"step": 41
|
256 |
},
|
257 |
{
|
258 |
-
"epoch":
|
259 |
-
"learning_rate": 0.
|
260 |
-
"loss":
|
261 |
"step": 42
|
262 |
},
|
263 |
{
|
264 |
-
"epoch":
|
265 |
-
"learning_rate": 0.
|
266 |
-
"loss":
|
267 |
"step": 43
|
268 |
},
|
269 |
{
|
270 |
-
"epoch":
|
271 |
-
"learning_rate": 0.
|
272 |
-
"loss":
|
273 |
"step": 44
|
274 |
},
|
275 |
{
|
276 |
-
"epoch":
|
277 |
-
"learning_rate": 0.
|
278 |
-
"loss":
|
279 |
"step": 45
|
280 |
},
|
281 |
{
|
282 |
-
"epoch":
|
283 |
-
"learning_rate": 0.
|
284 |
-
"loss": 0.
|
285 |
"step": 46
|
286 |
},
|
287 |
{
|
288 |
-
"epoch":
|
289 |
-
"learning_rate": 0.
|
290 |
-
"loss":
|
291 |
"step": 47
|
292 |
},
|
293 |
{
|
294 |
-
"epoch":
|
295 |
-
"learning_rate": 0.
|
296 |
-
"loss": 0.
|
297 |
"step": 48
|
298 |
},
|
299 |
{
|
300 |
-
"epoch":
|
301 |
-
"learning_rate": 0.
|
302 |
-
"loss":
|
303 |
"step": 49
|
304 |
},
|
305 |
{
|
306 |
-
"epoch":
|
307 |
-
"learning_rate": 0.
|
308 |
-
"loss":
|
309 |
"step": 50
|
310 |
},
|
311 |
{
|
312 |
-
"epoch":
|
313 |
-
"learning_rate": 0.
|
314 |
-
"loss":
|
315 |
"step": 51
|
316 |
},
|
317 |
{
|
318 |
-
"epoch":
|
319 |
-
"learning_rate": 0.
|
320 |
-
"loss":
|
321 |
"step": 52
|
322 |
},
|
323 |
{
|
324 |
-
"epoch":
|
325 |
-
"learning_rate": 0.
|
326 |
-
"loss":
|
327 |
"step": 53
|
328 |
},
|
329 |
{
|
330 |
-
"epoch":
|
331 |
-
"learning_rate": 0.
|
332 |
-
"loss":
|
333 |
"step": 54
|
334 |
},
|
335 |
{
|
336 |
-
"epoch":
|
337 |
-
"learning_rate": 0.
|
338 |
-
"loss":
|
339 |
"step": 55
|
340 |
},
|
341 |
{
|
342 |
-
"epoch":
|
343 |
-
"learning_rate": 0.
|
344 |
-
"loss": 0.
|
345 |
"step": 56
|
346 |
},
|
347 |
{
|
348 |
-
"epoch":
|
349 |
-
"learning_rate": 0.
|
350 |
-
"loss": 0.
|
351 |
"step": 57
|
352 |
},
|
353 |
{
|
354 |
-
"epoch":
|
355 |
-
"learning_rate": 0.
|
356 |
-
"loss": 0.
|
357 |
"step": 58
|
358 |
},
|
359 |
{
|
360 |
-
"epoch":
|
361 |
-
"learning_rate": 0.
|
362 |
-
"loss": 0.
|
363 |
"step": 59
|
364 |
},
|
365 |
{
|
366 |
-
"epoch":
|
367 |
-
"learning_rate": 0.
|
368 |
-
"loss": 0.
|
369 |
"step": 60
|
370 |
},
|
371 |
{
|
372 |
-
"epoch":
|
373 |
-
"learning_rate": 0.
|
374 |
-
"loss":
|
375 |
"step": 61
|
376 |
},
|
377 |
{
|
378 |
-
"epoch":
|
379 |
-
"learning_rate": 0.
|
380 |
-
"loss": 0.
|
381 |
"step": 62
|
382 |
},
|
383 |
{
|
384 |
-
"epoch":
|
385 |
-
"learning_rate": 0.
|
386 |
-
"loss": 0.
|
387 |
"step": 63
|
388 |
},
|
389 |
{
|
390 |
-
"epoch":
|
391 |
-
"learning_rate": 0.
|
392 |
-
"loss": 0.
|
393 |
"step": 64
|
394 |
},
|
395 |
{
|
396 |
-
"epoch":
|
397 |
-
"learning_rate": 0.
|
398 |
-
"loss": 0.
|
399 |
"step": 65
|
400 |
},
|
401 |
{
|
402 |
-
"epoch":
|
403 |
-
"learning_rate": 0.
|
404 |
-
"loss": 0.
|
405 |
"step": 66
|
406 |
},
|
407 |
{
|
408 |
-
"epoch":
|
409 |
-
"learning_rate": 0.
|
410 |
-
"loss": 0.
|
411 |
"step": 67
|
412 |
},
|
413 |
{
|
414 |
-
"epoch":
|
415 |
-
"learning_rate": 0.
|
416 |
-
"loss": 0.
|
417 |
"step": 68
|
418 |
},
|
419 |
{
|
420 |
-
"epoch":
|
421 |
-
"learning_rate": 0.
|
422 |
-
"loss": 0.
|
423 |
"step": 69
|
424 |
},
|
425 |
{
|
426 |
-
"epoch":
|
427 |
-
"learning_rate": 0.
|
428 |
-
"loss": 0.
|
429 |
"step": 70
|
430 |
},
|
431 |
{
|
432 |
-
"epoch":
|
433 |
-
"learning_rate":
|
434 |
-
"loss": 0.
|
435 |
"step": 71
|
436 |
},
|
437 |
{
|
438 |
-
"epoch":
|
439 |
-
"learning_rate":
|
440 |
-
"loss": 0.
|
441 |
"step": 72
|
442 |
},
|
443 |
{
|
444 |
-
"epoch":
|
445 |
-
"learning_rate":
|
446 |
-
"loss": 0.
|
447 |
"step": 73
|
448 |
},
|
449 |
{
|
450 |
-
"epoch":
|
451 |
-
"learning_rate":
|
452 |
-
"loss": 0.
|
453 |
"step": 74
|
454 |
},
|
455 |
{
|
456 |
-
"epoch":
|
457 |
-
"learning_rate":
|
458 |
-
"loss": 0.
|
459 |
"step": 75
|
460 |
},
|
461 |
{
|
462 |
-
"epoch":
|
463 |
-
"learning_rate":
|
464 |
-
"loss": 0.
|
465 |
"step": 76
|
466 |
},
|
467 |
{
|
468 |
-
"epoch":
|
469 |
-
"learning_rate":
|
470 |
-
"loss": 0.
|
471 |
"step": 77
|
472 |
},
|
473 |
{
|
474 |
-
"epoch":
|
475 |
-
"learning_rate":
|
476 |
-
"loss": 0.
|
477 |
"step": 78
|
478 |
},
|
479 |
{
|
480 |
-
"epoch":
|
481 |
-
"learning_rate":
|
482 |
-
"loss": 0.
|
483 |
"step": 79
|
484 |
},
|
485 |
{
|
486 |
-
"epoch":
|
487 |
-
"learning_rate":
|
488 |
-
"loss": 0.
|
489 |
"step": 80
|
490 |
},
|
491 |
{
|
492 |
-
"epoch":
|
493 |
-
"learning_rate":
|
494 |
-
"loss": 0.
|
495 |
"step": 81
|
496 |
},
|
497 |
{
|
498 |
-
"epoch":
|
499 |
-
"learning_rate":
|
500 |
-
"loss": 0.
|
501 |
"step": 82
|
502 |
},
|
503 |
{
|
504 |
-
"epoch":
|
505 |
-
"learning_rate":
|
506 |
-
"loss": 0.
|
507 |
"step": 83
|
508 |
},
|
509 |
{
|
510 |
-
"epoch":
|
511 |
-
"learning_rate":
|
512 |
-
"loss": 0.
|
513 |
"step": 84
|
514 |
},
|
515 |
{
|
516 |
-
"epoch":
|
517 |
-
"learning_rate":
|
518 |
-
"loss": 0.
|
519 |
"step": 85
|
520 |
},
|
521 |
{
|
522 |
-
"epoch":
|
523 |
-
"learning_rate":
|
524 |
-
"loss": 0.
|
525 |
"step": 86
|
526 |
},
|
527 |
{
|
528 |
-
"epoch":
|
529 |
-
"learning_rate":
|
530 |
-
"loss": 0.
|
531 |
"step": 87
|
532 |
},
|
533 |
{
|
534 |
-
"epoch":
|
535 |
-
"learning_rate":
|
536 |
-
"loss": 0.
|
537 |
"step": 88
|
538 |
},
|
539 |
{
|
540 |
-
"epoch":
|
541 |
-
"learning_rate":
|
542 |
-
"loss": 0.
|
543 |
"step": 89
|
544 |
},
|
545 |
{
|
546 |
-
"epoch":
|
547 |
-
"learning_rate":
|
548 |
-
"loss": 0.
|
549 |
"step": 90
|
550 |
},
|
551 |
{
|
552 |
-
"epoch":
|
553 |
-
"learning_rate":
|
554 |
-
"loss": 0.
|
555 |
"step": 91
|
556 |
},
|
557 |
{
|
558 |
-
"epoch":
|
559 |
-
"learning_rate":
|
560 |
-
"loss": 0.
|
561 |
"step": 92
|
562 |
},
|
563 |
{
|
564 |
-
"epoch":
|
565 |
-
"learning_rate":
|
566 |
-
"loss": 0.
|
567 |
"step": 93
|
568 |
},
|
569 |
{
|
570 |
-
"epoch":
|
571 |
-
"learning_rate":
|
572 |
-
"loss": 0.
|
573 |
"step": 94
|
574 |
},
|
575 |
{
|
576 |
-
"epoch":
|
577 |
-
"learning_rate":
|
578 |
-
"loss": 0.
|
579 |
"step": 95
|
580 |
},
|
581 |
{
|
582 |
-
"epoch":
|
583 |
-
"learning_rate":
|
584 |
-
"loss": 0.
|
585 |
"step": 96
|
586 |
},
|
587 |
{
|
588 |
-
"epoch":
|
589 |
-
"learning_rate":
|
590 |
-
"loss": 0.
|
591 |
"step": 97
|
592 |
},
|
593 |
{
|
594 |
-
"epoch":
|
595 |
-
"learning_rate":
|
596 |
-
"loss": 0.
|
597 |
"step": 98
|
598 |
},
|
599 |
{
|
600 |
-
"epoch":
|
601 |
-
"learning_rate":
|
602 |
-
"loss": 0.
|
603 |
"step": 99
|
604 |
},
|
605 |
{
|
606 |
-
"epoch":
|
607 |
-
"learning_rate":
|
608 |
-
"loss": 0.
|
609 |
"step": 100
|
610 |
}
|
611 |
],
|
612 |
"logging_steps": 1,
|
613 |
-
"max_steps":
|
614 |
-
"num_train_epochs":
|
615 |
"save_steps": 100,
|
616 |
-
"total_flos":
|
617 |
"trial_name": null,
|
618 |
"trial_params": null
|
619 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.111111111111111,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 100,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.07,
|
13 |
+
"learning_rate": 0.0001985714285714286,
|
14 |
+
"loss": 2.5072,
|
15 |
"step": 1
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.14,
|
19 |
+
"learning_rate": 0.00019714285714285716,
|
20 |
+
"loss": 2.194,
|
21 |
"step": 2
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 0.21,
|
25 |
+
"learning_rate": 0.00019571428571428572,
|
26 |
+
"loss": 1.9685,
|
27 |
"step": 3
|
28 |
},
|
29 |
{
|
30 |
+
"epoch": 0.28,
|
31 |
+
"learning_rate": 0.0001942857142857143,
|
32 |
+
"loss": 1.7577,
|
33 |
"step": 4
|
34 |
},
|
35 |
{
|
36 |
+
"epoch": 0.36,
|
37 |
+
"learning_rate": 0.00019285714285714286,
|
38 |
+
"loss": 1.6095,
|
39 |
"step": 5
|
40 |
},
|
41 |
{
|
42 |
+
"epoch": 0.43,
|
43 |
+
"learning_rate": 0.00019142857142857145,
|
44 |
+
"loss": 1.5448,
|
45 |
"step": 6
|
46 |
},
|
47 |
{
|
48 |
+
"epoch": 0.5,
|
49 |
+
"learning_rate": 0.00019,
|
50 |
+
"loss": 1.453,
|
51 |
"step": 7
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 0.57,
|
55 |
+
"learning_rate": 0.00018857142857142857,
|
56 |
+
"loss": 1.41,
|
57 |
"step": 8
|
58 |
},
|
59 |
{
|
60 |
+
"epoch": 0.64,
|
61 |
+
"learning_rate": 0.00018714285714285716,
|
62 |
+
"loss": 1.3054,
|
63 |
"step": 9
|
64 |
},
|
65 |
{
|
66 |
+
"epoch": 0.71,
|
67 |
+
"learning_rate": 0.00018571428571428572,
|
68 |
+
"loss": 1.2634,
|
69 |
"step": 10
|
70 |
},
|
71 |
{
|
72 |
+
"epoch": 0.78,
|
73 |
+
"learning_rate": 0.00018428571428571428,
|
74 |
+
"loss": 1.2269,
|
75 |
"step": 11
|
76 |
},
|
77 |
{
|
78 |
+
"epoch": 0.85,
|
79 |
+
"learning_rate": 0.00018285714285714286,
|
80 |
+
"loss": 1.2405,
|
81 |
"step": 12
|
82 |
},
|
83 |
{
|
84 |
+
"epoch": 0.92,
|
85 |
+
"learning_rate": 0.00018142857142857142,
|
86 |
+
"loss": 1.2436,
|
87 |
"step": 13
|
88 |
},
|
89 |
{
|
90 |
+
"epoch": 1.0,
|
91 |
+
"learning_rate": 0.00018,
|
92 |
+
"loss": 1.2063,
|
93 |
"step": 14
|
94 |
},
|
95 |
{
|
96 |
+
"epoch": 1.07,
|
97 |
+
"learning_rate": 0.0001785714285714286,
|
98 |
+
"loss": 1.1789,
|
99 |
"step": 15
|
100 |
},
|
101 |
{
|
102 |
+
"epoch": 1.14,
|
103 |
+
"learning_rate": 0.00017714285714285713,
|
104 |
+
"loss": 1.2007,
|
105 |
"step": 16
|
106 |
},
|
107 |
{
|
108 |
+
"epoch": 1.21,
|
109 |
+
"learning_rate": 0.00017571428571428572,
|
110 |
+
"loss": 1.1616,
|
111 |
"step": 17
|
112 |
},
|
113 |
{
|
114 |
+
"epoch": 1.28,
|
115 |
+
"learning_rate": 0.0001742857142857143,
|
116 |
+
"loss": 1.157,
|
117 |
"step": 18
|
118 |
},
|
119 |
{
|
120 |
+
"epoch": 1.35,
|
121 |
+
"learning_rate": 0.00017285714285714287,
|
122 |
+
"loss": 1.1555,
|
123 |
"step": 19
|
124 |
},
|
125 |
{
|
126 |
+
"epoch": 1.42,
|
127 |
+
"learning_rate": 0.00017142857142857143,
|
128 |
+
"loss": 1.1559,
|
129 |
"step": 20
|
130 |
},
|
131 |
{
|
132 |
+
"epoch": 1.49,
|
133 |
+
"learning_rate": 0.00017,
|
134 |
+
"loss": 1.1487,
|
135 |
"step": 21
|
136 |
},
|
137 |
{
|
138 |
+
"epoch": 1.56,
|
139 |
+
"learning_rate": 0.00016857142857142857,
|
140 |
+
"loss": 1.1729,
|
141 |
"step": 22
|
142 |
},
|
143 |
{
|
144 |
+
"epoch": 1.64,
|
145 |
+
"learning_rate": 0.00016714285714285716,
|
146 |
+
"loss": 1.1251,
|
147 |
"step": 23
|
148 |
},
|
149 |
{
|
150 |
+
"epoch": 1.71,
|
151 |
+
"learning_rate": 0.00016571428571428575,
|
152 |
+
"loss": 1.1181,
|
153 |
"step": 24
|
154 |
},
|
155 |
{
|
156 |
+
"epoch": 1.78,
|
157 |
+
"learning_rate": 0.00016428571428571428,
|
158 |
+
"loss": 1.1144,
|
159 |
"step": 25
|
160 |
},
|
161 |
{
|
162 |
+
"epoch": 1.85,
|
163 |
+
"learning_rate": 0.00016285714285714287,
|
164 |
+
"loss": 1.1416,
|
165 |
"step": 26
|
166 |
},
|
167 |
{
|
168 |
+
"epoch": 1.92,
|
169 |
+
"learning_rate": 0.00016142857142857145,
|
170 |
+
"loss": 1.0965,
|
171 |
"step": 27
|
172 |
},
|
173 |
{
|
174 |
+
"epoch": 1.99,
|
175 |
+
"learning_rate": 0.00016,
|
176 |
+
"loss": 1.0936,
|
177 |
"step": 28
|
178 |
},
|
179 |
{
|
180 |
+
"epoch": 2.06,
|
181 |
+
"learning_rate": 0.00015857142857142857,
|
182 |
+
"loss": 1.0839,
|
183 |
"step": 29
|
184 |
},
|
185 |
{
|
186 |
+
"epoch": 2.13,
|
187 |
+
"learning_rate": 0.00015714285714285716,
|
188 |
+
"loss": 1.127,
|
189 |
"step": 30
|
190 |
},
|
191 |
{
|
192 |
+
"epoch": 2.2,
|
193 |
+
"learning_rate": 0.00015571428571428572,
|
194 |
+
"loss": 1.0886,
|
195 |
"step": 31
|
196 |
},
|
197 |
{
|
198 |
+
"epoch": 2.28,
|
199 |
+
"learning_rate": 0.0001542857142857143,
|
200 |
+
"loss": 1.0447,
|
201 |
"step": 32
|
202 |
},
|
203 |
{
|
204 |
+
"epoch": 2.35,
|
205 |
+
"learning_rate": 0.00015285714285714287,
|
206 |
+
"loss": 1.0513,
|
207 |
"step": 33
|
208 |
},
|
209 |
{
|
210 |
+
"epoch": 2.42,
|
211 |
+
"learning_rate": 0.00015142857142857143,
|
212 |
+
"loss": 1.098,
|
213 |
"step": 34
|
214 |
},
|
215 |
{
|
216 |
+
"epoch": 2.49,
|
217 |
+
"learning_rate": 0.00015000000000000001,
|
218 |
+
"loss": 1.0628,
|
219 |
"step": 35
|
220 |
},
|
221 |
{
|
222 |
+
"epoch": 2.56,
|
223 |
+
"learning_rate": 0.00014857142857142857,
|
224 |
+
"loss": 1.0814,
|
225 |
"step": 36
|
226 |
},
|
227 |
{
|
228 |
+
"epoch": 2.63,
|
229 |
+
"learning_rate": 0.00014714285714285716,
|
230 |
+
"loss": 1.0638,
|
231 |
"step": 37
|
232 |
},
|
233 |
{
|
234 |
+
"epoch": 2.7,
|
235 |
+
"learning_rate": 0.00014571428571428572,
|
236 |
+
"loss": 1.0652,
|
237 |
"step": 38
|
238 |
},
|
239 |
{
|
240 |
+
"epoch": 2.77,
|
241 |
+
"learning_rate": 0.00014428571428571428,
|
242 |
+
"loss": 1.0463,
|
243 |
"step": 39
|
244 |
},
|
245 |
{
|
246 |
+
"epoch": 2.84,
|
247 |
+
"learning_rate": 0.00014285714285714287,
|
248 |
+
"loss": 1.0349,
|
249 |
"step": 40
|
250 |
},
|
251 |
{
|
252 |
+
"epoch": 2.92,
|
253 |
+
"learning_rate": 0.00014142857142857145,
|
254 |
+
"loss": 1.0165,
|
255 |
"step": 41
|
256 |
},
|
257 |
{
|
258 |
+
"epoch": 2.99,
|
259 |
+
"learning_rate": 0.00014,
|
260 |
+
"loss": 1.0905,
|
261 |
"step": 42
|
262 |
},
|
263 |
{
|
264 |
+
"epoch": 3.06,
|
265 |
+
"learning_rate": 0.00013857142857142857,
|
266 |
+
"loss": 1.0297,
|
267 |
"step": 43
|
268 |
},
|
269 |
{
|
270 |
+
"epoch": 3.13,
|
271 |
+
"learning_rate": 0.00013714285714285716,
|
272 |
+
"loss": 1.0061,
|
273 |
"step": 44
|
274 |
},
|
275 |
{
|
276 |
+
"epoch": 3.2,
|
277 |
+
"learning_rate": 0.00013571428571428572,
|
278 |
+
"loss": 1.0019,
|
279 |
"step": 45
|
280 |
},
|
281 |
{
|
282 |
+
"epoch": 3.27,
|
283 |
+
"learning_rate": 0.00013428571428571428,
|
284 |
+
"loss": 0.9555,
|
285 |
"step": 46
|
286 |
},
|
287 |
{
|
288 |
+
"epoch": 3.34,
|
289 |
+
"learning_rate": 0.00013285714285714287,
|
290 |
+
"loss": 1.038,
|
291 |
"step": 47
|
292 |
},
|
293 |
{
|
294 |
+
"epoch": 3.41,
|
295 |
+
"learning_rate": 0.00013142857142857143,
|
296 |
+
"loss": 0.9932,
|
297 |
"step": 48
|
298 |
},
|
299 |
{
|
300 |
+
"epoch": 3.48,
|
301 |
+
"learning_rate": 0.00013000000000000002,
|
302 |
+
"loss": 1.0451,
|
303 |
"step": 49
|
304 |
},
|
305 |
{
|
306 |
+
"epoch": 3.56,
|
307 |
+
"learning_rate": 0.00012857142857142858,
|
308 |
+
"loss": 1.008,
|
309 |
"step": 50
|
310 |
},
|
311 |
{
|
312 |
+
"epoch": 3.63,
|
313 |
+
"learning_rate": 0.00012714285714285714,
|
314 |
+
"loss": 1.0362,
|
315 |
"step": 51
|
316 |
},
|
317 |
{
|
318 |
+
"epoch": 3.7,
|
319 |
+
"learning_rate": 0.00012571428571428572,
|
320 |
+
"loss": 1.0007,
|
321 |
"step": 52
|
322 |
},
|
323 |
{
|
324 |
+
"epoch": 3.77,
|
325 |
+
"learning_rate": 0.00012428571428571428,
|
326 |
+
"loss": 1.0038,
|
327 |
"step": 53
|
328 |
},
|
329 |
{
|
330 |
+
"epoch": 3.84,
|
331 |
+
"learning_rate": 0.00012285714285714287,
|
332 |
+
"loss": 1.0057,
|
333 |
"step": 54
|
334 |
},
|
335 |
{
|
336 |
+
"epoch": 3.91,
|
337 |
+
"learning_rate": 0.00012142857142857143,
|
338 |
+
"loss": 1.0172,
|
339 |
"step": 55
|
340 |
},
|
341 |
{
|
342 |
+
"epoch": 3.98,
|
343 |
+
"learning_rate": 0.00012,
|
344 |
+
"loss": 0.982,
|
345 |
"step": 56
|
346 |
},
|
347 |
{
|
348 |
+
"epoch": 4.05,
|
349 |
+
"learning_rate": 0.00011857142857142858,
|
350 |
+
"loss": 0.9838,
|
351 |
"step": 57
|
352 |
},
|
353 |
{
|
354 |
+
"epoch": 4.12,
|
355 |
+
"learning_rate": 0.00011714285714285715,
|
356 |
+
"loss": 0.9677,
|
357 |
"step": 58
|
358 |
},
|
359 |
{
|
360 |
+
"epoch": 4.2,
|
361 |
+
"learning_rate": 0.00011571428571428574,
|
362 |
+
"loss": 0.9815,
|
363 |
"step": 59
|
364 |
},
|
365 |
{
|
366 |
+
"epoch": 4.27,
|
367 |
+
"learning_rate": 0.00011428571428571428,
|
368 |
+
"loss": 0.9711,
|
369 |
"step": 60
|
370 |
},
|
371 |
{
|
372 |
+
"epoch": 4.34,
|
373 |
+
"learning_rate": 0.00011285714285714286,
|
374 |
+
"loss": 1.0086,
|
375 |
"step": 61
|
376 |
},
|
377 |
{
|
378 |
+
"epoch": 4.41,
|
379 |
+
"learning_rate": 0.00011142857142857144,
|
380 |
+
"loss": 0.9485,
|
381 |
"step": 62
|
382 |
},
|
383 |
{
|
384 |
+
"epoch": 4.48,
|
385 |
+
"learning_rate": 0.00011000000000000002,
|
386 |
+
"loss": 0.9342,
|
387 |
"step": 63
|
388 |
},
|
389 |
{
|
390 |
+
"epoch": 4.55,
|
391 |
+
"learning_rate": 0.00010857142857142856,
|
392 |
+
"loss": 0.9887,
|
393 |
"step": 64
|
394 |
},
|
395 |
{
|
396 |
+
"epoch": 4.62,
|
397 |
+
"learning_rate": 0.00010714285714285715,
|
398 |
+
"loss": 0.9614,
|
399 |
"step": 65
|
400 |
},
|
401 |
{
|
402 |
+
"epoch": 4.69,
|
403 |
+
"learning_rate": 0.00010571428571428572,
|
404 |
+
"loss": 0.9644,
|
405 |
"step": 66
|
406 |
},
|
407 |
{
|
408 |
+
"epoch": 4.76,
|
409 |
+
"learning_rate": 0.0001042857142857143,
|
410 |
+
"loss": 0.9267,
|
411 |
"step": 67
|
412 |
},
|
413 |
{
|
414 |
+
"epoch": 4.84,
|
415 |
+
"learning_rate": 0.00010285714285714286,
|
416 |
+
"loss": 0.954,
|
417 |
"step": 68
|
418 |
},
|
419 |
{
|
420 |
+
"epoch": 4.91,
|
421 |
+
"learning_rate": 0.00010142857142857143,
|
422 |
+
"loss": 0.919,
|
423 |
"step": 69
|
424 |
},
|
425 |
{
|
426 |
+
"epoch": 4.98,
|
427 |
+
"learning_rate": 0.0001,
|
428 |
+
"loss": 0.9478,
|
429 |
"step": 70
|
430 |
},
|
431 |
{
|
432 |
+
"epoch": 5.05,
|
433 |
+
"learning_rate": 9.857142857142858e-05,
|
434 |
+
"loss": 0.9559,
|
435 |
"step": 71
|
436 |
},
|
437 |
{
|
438 |
+
"epoch": 5.12,
|
439 |
+
"learning_rate": 9.714285714285715e-05,
|
440 |
+
"loss": 0.9596,
|
441 |
"step": 72
|
442 |
},
|
443 |
{
|
444 |
+
"epoch": 5.19,
|
445 |
+
"learning_rate": 9.571428571428573e-05,
|
446 |
+
"loss": 0.9151,
|
447 |
"step": 73
|
448 |
},
|
449 |
{
|
450 |
+
"epoch": 5.26,
|
451 |
+
"learning_rate": 9.428571428571429e-05,
|
452 |
+
"loss": 0.9059,
|
453 |
"step": 74
|
454 |
},
|
455 |
{
|
456 |
+
"epoch": 5.33,
|
457 |
+
"learning_rate": 9.285714285714286e-05,
|
458 |
+
"loss": 0.8717,
|
459 |
"step": 75
|
460 |
},
|
461 |
{
|
462 |
+
"epoch": 5.4,
|
463 |
+
"learning_rate": 9.142857142857143e-05,
|
464 |
+
"loss": 0.8912,
|
465 |
"step": 76
|
466 |
},
|
467 |
{
|
468 |
+
"epoch": 5.48,
|
469 |
+
"learning_rate": 9e-05,
|
470 |
+
"loss": 0.9166,
|
471 |
"step": 77
|
472 |
},
|
473 |
{
|
474 |
+
"epoch": 5.55,
|
475 |
+
"learning_rate": 8.857142857142857e-05,
|
476 |
+
"loss": 0.9362,
|
477 |
"step": 78
|
478 |
},
|
479 |
{
|
480 |
+
"epoch": 5.62,
|
481 |
+
"learning_rate": 8.714285714285715e-05,
|
482 |
+
"loss": 0.8969,
|
483 |
"step": 79
|
484 |
},
|
485 |
{
|
486 |
+
"epoch": 5.69,
|
487 |
+
"learning_rate": 8.571428571428571e-05,
|
488 |
+
"loss": 0.898,
|
489 |
"step": 80
|
490 |
},
|
491 |
{
|
492 |
+
"epoch": 5.76,
|
493 |
+
"learning_rate": 8.428571428571429e-05,
|
494 |
+
"loss": 0.8626,
|
495 |
"step": 81
|
496 |
},
|
497 |
{
|
498 |
+
"epoch": 5.83,
|
499 |
+
"learning_rate": 8.285714285714287e-05,
|
500 |
+
"loss": 0.9353,
|
501 |
"step": 82
|
502 |
},
|
503 |
{
|
504 |
+
"epoch": 5.9,
|
505 |
+
"learning_rate": 8.142857142857143e-05,
|
506 |
+
"loss": 0.9353,
|
507 |
"step": 83
|
508 |
},
|
509 |
{
|
510 |
+
"epoch": 5.97,
|
511 |
+
"learning_rate": 8e-05,
|
512 |
+
"loss": 0.9277,
|
513 |
"step": 84
|
514 |
},
|
515 |
{
|
516 |
+
"epoch": 6.04,
|
517 |
+
"learning_rate": 7.857142857142858e-05,
|
518 |
+
"loss": 0.8856,
|
519 |
"step": 85
|
520 |
},
|
521 |
{
|
522 |
+
"epoch": 6.12,
|
523 |
+
"learning_rate": 7.714285714285715e-05,
|
524 |
+
"loss": 0.8771,
|
525 |
"step": 86
|
526 |
},
|
527 |
{
|
528 |
+
"epoch": 6.19,
|
529 |
+
"learning_rate": 7.571428571428571e-05,
|
530 |
+
"loss": 0.8634,
|
531 |
"step": 87
|
532 |
},
|
533 |
{
|
534 |
+
"epoch": 6.26,
|
535 |
+
"learning_rate": 7.428571428571429e-05,
|
536 |
+
"loss": 0.8655,
|
537 |
"step": 88
|
538 |
},
|
539 |
{
|
540 |
+
"epoch": 6.33,
|
541 |
+
"learning_rate": 7.285714285714286e-05,
|
542 |
+
"loss": 0.856,
|
543 |
"step": 89
|
544 |
},
|
545 |
{
|
546 |
+
"epoch": 6.4,
|
547 |
+
"learning_rate": 7.142857142857143e-05,
|
548 |
+
"loss": 0.8929,
|
549 |
"step": 90
|
550 |
},
|
551 |
{
|
552 |
+
"epoch": 6.47,
|
553 |
+
"learning_rate": 7e-05,
|
554 |
+
"loss": 0.8844,
|
555 |
"step": 91
|
556 |
},
|
557 |
{
|
558 |
+
"epoch": 6.54,
|
559 |
+
"learning_rate": 6.857142857142858e-05,
|
560 |
+
"loss": 0.8951,
|
561 |
"step": 92
|
562 |
},
|
563 |
{
|
564 |
+
"epoch": 6.61,
|
565 |
+
"learning_rate": 6.714285714285714e-05,
|
566 |
+
"loss": 0.8385,
|
567 |
"step": 93
|
568 |
},
|
569 |
{
|
570 |
+
"epoch": 6.68,
|
571 |
+
"learning_rate": 6.571428571428571e-05,
|
572 |
+
"loss": 0.873,
|
573 |
"step": 94
|
574 |
},
|
575 |
{
|
576 |
+
"epoch": 6.76,
|
577 |
+
"learning_rate": 6.428571428571429e-05,
|
578 |
+
"loss": 0.9033,
|
579 |
"step": 95
|
580 |
},
|
581 |
{
|
582 |
+
"epoch": 6.83,
|
583 |
+
"learning_rate": 6.285714285714286e-05,
|
584 |
+
"loss": 0.8643,
|
585 |
"step": 96
|
586 |
},
|
587 |
{
|
588 |
+
"epoch": 6.9,
|
589 |
+
"learning_rate": 6.142857142857143e-05,
|
590 |
+
"loss": 0.8894,
|
591 |
"step": 97
|
592 |
},
|
593 |
{
|
594 |
+
"epoch": 6.97,
|
595 |
+
"learning_rate": 6e-05,
|
596 |
+
"loss": 0.8436,
|
597 |
"step": 98
|
598 |
},
|
599 |
{
|
600 |
+
"epoch": 7.04,
|
601 |
+
"learning_rate": 5.8571428571428575e-05,
|
602 |
+
"loss": 0.8362,
|
603 |
"step": 99
|
604 |
},
|
605 |
{
|
606 |
+
"epoch": 7.11,
|
607 |
+
"learning_rate": 5.714285714285714e-05,
|
608 |
+
"loss": 0.8162,
|
609 |
"step": 100
|
610 |
}
|
611 |
],
|
612 |
"logging_steps": 1,
|
613 |
+
"max_steps": 140,
|
614 |
+
"num_train_epochs": 10,
|
615 |
"save_steps": 100,
|
616 |
+
"total_flos": 1.837898937498624e+16,
|
617 |
"trial_name": null,
|
618 |
"trial_params": null
|
619 |
}
|
checkpoint-100/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f64eef1b40d4774a448e5873470138b7a2cb17cf32f63605c071f25bf135444
|
3 |
size 4027
|
runs/Oct12_18-12-36_63a985a0dcf5/events.out.tfevents.1697134361.63a985a0dcf5.4074.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12f388aa7a381716fcd82edc36b07c4432ae5880f46a9837eed7f8b93b7b65e3
|
3 |
+
size 26628
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,40 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"bos_token": "<s>",
|
4 |
"clean_up_tokenization_spaces": false,
|
5 |
"eos_token": "</s>",
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<unk>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<pad>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"additional_special_tokens": [],
|
38 |
"bos_token": "<s>",
|
39 |
"clean_up_tokenization_spaces": false,
|
40 |
"eos_token": "</s>",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f64eef1b40d4774a448e5873470138b7a2cb17cf32f63605c071f25bf135444
|
3 |
size 4027
|