End of training
Browse files- README.md +29 -189
- config.json +0 -1
- merges.txt +0 -0
- model.safetensors +1 -1
- runs/Mar27_17-06-49_e7a5665ab0b2/events.out.tfevents.1711559319.e7a5665ab0b2.5995.0 +3 -0
- runs/Mar28_19-18-07_0a5a129280ae/events.out.tfevents.1711653511.0a5a129280ae.532.0 +3 -0
- runs/Mar28_19-32-59_9806aa793962/events.out.tfevents.1711654390.9806aa793962.529.0 +3 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,209 +1,49 @@
|
|
1 |
---
|
2 |
-
library_name: transformers
|
3 |
tags:
|
4 |
-
-
|
5 |
-
|
6 |
-
-
|
7 |
-
|
8 |
-
- text: "Sindbad Żeglarz był żeglarzem, który wyruszył w podróż na morze. Wuj Tarabuk"
|
9 |
-
example_title: "Sindbad"
|
10 |
-
- text: "Elżbieta to popularne polskie imię "
|
11 |
-
example_title: "Elżbieta"
|
12 |
-
- text: "Ile jest 4 + 40?"
|
13 |
-
example_title: "Ile jest 4 + 40?"
|
14 |
---
|
15 |
|
16 |
-
|
|
|
17 |
|
18 |
-
|
19 |
|
|
|
20 |
|
|
|
21 |
|
22 |
-
|
23 |
|
24 |
-
|
25 |
|
26 |
-
|
27 |
|
28 |
-
|
29 |
|
30 |
-
|
31 |
-
- **Funded by [optional]:** [More Information Needed]
|
32 |
-
- **Shared by [optional]:** [More Information Needed]
|
33 |
-
- **Model type:** [More Information Needed]
|
34 |
-
- **Language(s) (NLP):** [More Information Needed]
|
35 |
-
- **License:** [More Information Needed]
|
36 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
37 |
|
38 |
-
|
39 |
|
40 |
-
|
41 |
|
42 |
-
|
43 |
-
-
|
44 |
-
-
|
|
|
|
|
|
|
|
|
|
|
45 |
|
46 |
-
|
47 |
|
48 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
49 |
|
50 |
-
### Direct Use
|
51 |
|
52 |
-
|
53 |
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
59 |
-
|
60 |
-
[More Information Needed]
|
61 |
-
|
62 |
-
### Out-of-Scope Use
|
63 |
-
|
64 |
-
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
65 |
-
|
66 |
-
[More Information Needed]
|
67 |
-
|
68 |
-
## Bias, Risks, and Limitations
|
69 |
-
|
70 |
-
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
71 |
-
|
72 |
-
[More Information Needed]
|
73 |
-
|
74 |
-
### Recommendations
|
75 |
-
|
76 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
77 |
-
|
78 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
79 |
-
|
80 |
-
## How to Get Started with the Model
|
81 |
-
|
82 |
-
Use the code below to get started with the model.
|
83 |
-
|
84 |
-
[More Information Needed]
|
85 |
-
|
86 |
-
## Training Details
|
87 |
-
|
88 |
-
### Training Data
|
89 |
-
|
90 |
-
<!-- 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. -->
|
91 |
-
|
92 |
-
[More Information Needed]
|
93 |
-
|
94 |
-
### Training Procedure
|
95 |
-
|
96 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
97 |
-
|
98 |
-
#### Preprocessing [optional]
|
99 |
-
|
100 |
-
[More Information Needed]
|
101 |
-
|
102 |
-
|
103 |
-
#### Training Hyperparameters
|
104 |
-
|
105 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
106 |
-
|
107 |
-
#### Speeds, Sizes, Times [optional]
|
108 |
-
|
109 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
110 |
-
|
111 |
-
[More Information Needed]
|
112 |
-
|
113 |
-
## Evaluation
|
114 |
-
|
115 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
116 |
-
|
117 |
-
### Testing Data, Factors & Metrics
|
118 |
-
|
119 |
-
#### Testing Data
|
120 |
-
|
121 |
-
<!-- This should link to a Dataset Card if possible. -->
|
122 |
-
|
123 |
-
[More Information Needed]
|
124 |
-
|
125 |
-
#### Factors
|
126 |
-
|
127 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
128 |
-
|
129 |
-
[More Information Needed]
|
130 |
-
|
131 |
-
#### Metrics
|
132 |
-
|
133 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
134 |
-
|
135 |
-
[More Information Needed]
|
136 |
-
|
137 |
-
### Results
|
138 |
-
|
139 |
-
[More Information Needed]
|
140 |
-
|
141 |
-
#### Summary
|
142 |
-
|
143 |
-
|
144 |
-
|
145 |
-
## Model Examination [optional]
|
146 |
-
|
147 |
-
<!-- Relevant interpretability work for the model goes here -->
|
148 |
-
|
149 |
-
[More Information Needed]
|
150 |
-
|
151 |
-
## Environmental Impact
|
152 |
-
|
153 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
154 |
-
|
155 |
-
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).
|
156 |
-
|
157 |
-
- **Hardware Type:** [More Information Needed]
|
158 |
-
- **Hours used:** [More Information Needed]
|
159 |
-
- **Cloud Provider:** [More Information Needed]
|
160 |
-
- **Compute Region:** [More Information Needed]
|
161 |
-
- **Carbon Emitted:** [More Information Needed]
|
162 |
-
|
163 |
-
## Technical Specifications [optional]
|
164 |
-
|
165 |
-
### Model Architecture and Objective
|
166 |
-
|
167 |
-
[More Information Needed]
|
168 |
-
|
169 |
-
### Compute Infrastructure
|
170 |
-
|
171 |
-
[More Information Needed]
|
172 |
-
|
173 |
-
#### Hardware
|
174 |
-
|
175 |
-
[More Information Needed]
|
176 |
-
|
177 |
-
#### Software
|
178 |
-
|
179 |
-
[More Information Needed]
|
180 |
-
|
181 |
-
## Citation [optional]
|
182 |
-
|
183 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
184 |
-
|
185 |
-
**BibTeX:**
|
186 |
-
|
187 |
-
[More Information Needed]
|
188 |
-
|
189 |
-
**APA:**
|
190 |
-
|
191 |
-
[More Information Needed]
|
192 |
-
|
193 |
-
## Glossary [optional]
|
194 |
-
|
195 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
196 |
-
|
197 |
-
[More Information Needed]
|
198 |
-
|
199 |
-
## More Information [optional]
|
200 |
-
|
201 |
-
[More Information Needed]
|
202 |
-
|
203 |
-
## Model Card Authors [optional]
|
204 |
-
|
205 |
-
[More Information Needed]
|
206 |
-
|
207 |
-
## Model Card Contact
|
208 |
-
|
209 |
-
[More Information Needed]
|
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: gpt2-small-2
|
6 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
---
|
8 |
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
|
12 |
+
# gpt2-small-2
|
13 |
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
|
16 |
+
## Model description
|
17 |
|
18 |
+
More information needed
|
19 |
|
20 |
+
## Intended uses & limitations
|
21 |
|
22 |
+
More information needed
|
23 |
|
24 |
+
## Training and evaluation data
|
25 |
|
26 |
+
More information needed
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
|
28 |
+
## Training procedure
|
29 |
|
30 |
+
### Training hyperparameters
|
31 |
|
32 |
+
The following hyperparameters were used during training:
|
33 |
+
- learning_rate: 5e-05
|
34 |
+
- train_batch_size: 6
|
35 |
+
- eval_batch_size: 8
|
36 |
+
- seed: 42
|
37 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
38 |
+
- lr_scheduler_type: linear
|
39 |
+
- num_epochs: 1
|
40 |
|
41 |
+
### Training results
|
42 |
|
|
|
43 |
|
|
|
44 |
|
45 |
+
### Framework versions
|
46 |
|
47 |
+
- Transformers 4.38.2
|
48 |
+
- Pytorch 2.2.1+cu121
|
49 |
+
- Tokenizers 0.15.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "./drive/MyDrive/Models/Gpt2Small2",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
1 |
{
|
|
|
2 |
"activation_function": "gelu_new",
|
3 |
"architectures": [
|
4 |
"GPT2LMHeadModel"
|
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497774208
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:610849f3745c35af9c4a762066b0dd8ec8646292f37f600a72e2b3cdce6c529e
|
3 |
size 497774208
|
runs/Mar27_17-06-49_e7a5665ab0b2/events.out.tfevents.1711559319.e7a5665ab0b2.5995.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4bd9b9c7c706ec19f159e00acfd5d373bed4042ee6333f30540b8a145d460ef4
|
3 |
+
size 12453
|
runs/Mar28_19-18-07_0a5a129280ae/events.out.tfevents.1711653511.0a5a129280ae.532.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:551d83ead7e5eae880e39f0ac73afcd4198467401d78d0f5cd9fe63fd7dbf356
|
3 |
+
size 9212
|
runs/Mar28_19-32-59_9806aa793962/events.out.tfevents.1711654390.9806aa793962.529.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59c829839501e353fe70684f7074dc316004019fc10fc1e1b6cb3ae29d7643eb
|
3 |
+
size 5214
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7978f503a8cc33c4fa1cecb5cd49755281163f614b0ab202188019c8d7c38b5
|
3 |
+
size 4984
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|