Commit
•
f4b3654
1
Parent(s):
21aa5d6
Upload folder using huggingface_hub
Browse files- README.md +16 -196
- checkpoint-20391/config.json +36 -0
- checkpoint-20391/model.safetensors +3 -0
- checkpoint-20391/optimizer.pt +3 -0
- checkpoint-20391/rng_state.pth +3 -0
- checkpoint-20391/scheduler.pt +3 -0
- checkpoint-20391/trainer_state.json +0 -0
- checkpoint-20391/training_args.bin +3 -0
- config.json +36 -0
- model.safetensors +3 -0
- runs/Jul31_13-07-41_r-choudharytalhaarain-bertadultmodel-xmjquar0-e82fe-vkn45/events.out.tfevents.1722431263.r-choudharytalhaarain-bertadultmodel-xmjquar0-e82fe-vkn45.114.0 +2 -2
- runs/Jul31_13-07-41_r-choudharytalhaarain-bertadultmodel-xmjquar0-e82fe-vkn45/events.out.tfevents.1722557670.r-choudharytalhaarain-bertadultmodel-xmjquar0-e82fe-vkn45.114.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,206 +1,26 @@
|
|
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
-
|
5 |
-
|
6 |
-
|
7 |
-
-
|
8 |
-
metrics:
|
9 |
-
- accuracy
|
10 |
-
library_name: transformers
|
11 |
-
pipeline_tag: text-classification
|
12 |
---
|
13 |
-
# Model Card for Model ID
|
14 |
-
|
15 |
-
<!-- Provide a quick summary of what the model is/does. -->
|
16 |
-
|
17 |
-
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
|
18 |
-
|
19 |
-
## Model Details
|
20 |
-
|
21 |
-
### Model Description
|
22 |
-
|
23 |
-
<!-- Provide a longer summary of what this model is. -->
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
- **Developed by:** [More Information Needed]
|
28 |
-
- **Funded by [optional]:** [More Information Needed]
|
29 |
-
- **Shared by [optional]:** [More Information Needed]
|
30 |
-
- **Model type:** [More Information Needed]
|
31 |
-
- **Language(s) (NLP):** [More Information Needed]
|
32 |
-
- **License:** [More Information Needed]
|
33 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
34 |
-
|
35 |
-
### Model Sources [optional]
|
36 |
-
|
37 |
-
<!-- Provide the basic links for the model. -->
|
38 |
-
|
39 |
-
- **Repository:** [More Information Needed]
|
40 |
-
- **Paper [optional]:** [More Information Needed]
|
41 |
-
- **Demo [optional]:** [More Information Needed]
|
42 |
-
|
43 |
-
## Uses
|
44 |
-
|
45 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
46 |
-
|
47 |
-
### Direct Use
|
48 |
-
|
49 |
-
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
50 |
-
|
51 |
-
[More Information Needed]
|
52 |
-
|
53 |
-
### Downstream Use [optional]
|
54 |
-
|
55 |
-
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
56 |
-
|
57 |
-
[More Information Needed]
|
58 |
-
|
59 |
-
### Out-of-Scope Use
|
60 |
-
|
61 |
-
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
62 |
-
|
63 |
-
[More Information Needed]
|
64 |
-
|
65 |
-
## Bias, Risks, and Limitations
|
66 |
-
|
67 |
-
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
68 |
-
|
69 |
-
[More Information Needed]
|
70 |
-
|
71 |
-
### Recommendations
|
72 |
-
|
73 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
74 |
-
|
75 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
76 |
-
|
77 |
-
## How to Get Started with the Model
|
78 |
-
|
79 |
-
Use the code below to get started with the model.
|
80 |
-
|
81 |
-
[More Information Needed]
|
82 |
-
|
83 |
-
## Training Details
|
84 |
-
|
85 |
-
### Training Data
|
86 |
-
|
87 |
-
<!-- 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. -->
|
88 |
-
|
89 |
-
[More Information Needed]
|
90 |
-
|
91 |
-
### Training Procedure
|
92 |
-
|
93 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
94 |
-
|
95 |
-
#### Preprocessing [optional]
|
96 |
-
|
97 |
-
[More Information Needed]
|
98 |
-
|
99 |
-
|
100 |
-
#### Training Hyperparameters
|
101 |
-
|
102 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
103 |
-
|
104 |
-
#### Speeds, Sizes, Times [optional]
|
105 |
-
|
106 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
107 |
-
|
108 |
-
[More Information Needed]
|
109 |
-
|
110 |
-
## Evaluation
|
111 |
-
|
112 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
113 |
-
|
114 |
-
### Testing Data, Factors & Metrics
|
115 |
-
|
116 |
-
#### Testing Data
|
117 |
-
|
118 |
-
<!-- This should link to a Dataset Card if possible. -->
|
119 |
-
|
120 |
-
[More Information Needed]
|
121 |
-
|
122 |
-
#### Factors
|
123 |
-
|
124 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
125 |
-
|
126 |
-
[More Information Needed]
|
127 |
-
|
128 |
-
#### Metrics
|
129 |
-
|
130 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
131 |
-
|
132 |
-
[More Information Needed]
|
133 |
-
|
134 |
-
### Results
|
135 |
-
|
136 |
-
[More Information Needed]
|
137 |
-
|
138 |
-
#### Summary
|
139 |
-
|
140 |
-
|
141 |
-
|
142 |
-
## Model Examination [optional]
|
143 |
-
|
144 |
-
<!-- Relevant interpretability work for the model goes here -->
|
145 |
-
|
146 |
-
[More Information Needed]
|
147 |
-
|
148 |
-
## Environmental Impact
|
149 |
-
|
150 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
151 |
-
|
152 |
-
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).
|
153 |
-
|
154 |
-
- **Hardware Type:** [More Information Needed]
|
155 |
-
- **Hours used:** [More Information Needed]
|
156 |
-
- **Cloud Provider:** [More Information Needed]
|
157 |
-
- **Compute Region:** [More Information Needed]
|
158 |
-
- **Carbon Emitted:** [More Information Needed]
|
159 |
-
|
160 |
-
## Technical Specifications [optional]
|
161 |
-
|
162 |
-
### Model Architecture and Objective
|
163 |
-
|
164 |
-
[More Information Needed]
|
165 |
-
|
166 |
-
### Compute Infrastructure
|
167 |
-
|
168 |
-
[More Information Needed]
|
169 |
-
|
170 |
-
#### Hardware
|
171 |
-
|
172 |
-
[More Information Needed]
|
173 |
-
|
174 |
-
#### Software
|
175 |
-
|
176 |
-
[More Information Needed]
|
177 |
-
|
178 |
-
## Citation [optional]
|
179 |
-
|
180 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
181 |
-
|
182 |
-
**BibTeX:**
|
183 |
-
|
184 |
-
[More Information Needed]
|
185 |
-
|
186 |
-
**APA:**
|
187 |
-
|
188 |
-
[More Information Needed]
|
189 |
-
|
190 |
-
## Glossary [optional]
|
191 |
|
192 |
-
|
193 |
|
194 |
-
|
195 |
|
196 |
-
##
|
|
|
197 |
|
198 |
-
|
199 |
|
200 |
-
|
201 |
|
202 |
-
|
203 |
|
204 |
-
|
205 |
|
206 |
-
|
|
|
1 |
+
|
2 |
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: google-bert/bert-base-uncased
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
|
|
|
|
|
|
|
|
9 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
|
13 |
+
- Problem type: Text Classification
|
14 |
|
15 |
+
## Validation Metrics
|
16 |
+
loss: 0.01777876727283001
|
17 |
|
18 |
+
f1: 0.9969837416317222
|
19 |
|
20 |
+
precision: 0.9972038263428992
|
21 |
|
22 |
+
recall: 0.9967637540453075
|
23 |
|
24 |
+
auc: 0.9999289486306174
|
25 |
|
26 |
+
accuracy: 0.9969841853622655
|
checkpoint-20391/config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "0",
|
15 |
+
"1": "1"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"0": 0,
|
21 |
+
"1": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.43.1",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 30522
|
36 |
+
}
|
checkpoint-20391/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2374d5eed1e371838b2908a5b56cf1fa9eb7bbac2dd3dbacc5125a458abad689
|
3 |
+
size 437958648
|
checkpoint-20391/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:875be0bbf8e4064dd01be0020e054a2209b2758fa6fd0aabe02a0a071b5c3afa
|
3 |
+
size 876032762
|
checkpoint-20391/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdc465e29e6c4105ef334a70f0866ccce2ff9ff7d378eecbc7c9960f7e8fee9e
|
3 |
+
size 13990
|
checkpoint-20391/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51fc68e78af73c7e48095ee59c53616290ef4ce06af14883395a5afa2d3e3c4b
|
3 |
+
size 1064
|
checkpoint-20391/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-20391/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d36804181467c0d1082f474f96ee59831bb7309b234b077011f4711fdba9d14
|
3 |
+
size 5240
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "0",
|
15 |
+
"1": "1"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"0": 0,
|
21 |
+
"1": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-12,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"model_type": "bert",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.43.1",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 30522
|
36 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2374d5eed1e371838b2908a5b56cf1fa9eb7bbac2dd3dbacc5125a458abad689
|
3 |
+
size 437958648
|
runs/Jul31_13-07-41_r-choudharytalhaarain-bertadultmodel-xmjquar0-e82fe-vkn45/events.out.tfevents.1722431263.r-choudharytalhaarain-bertadultmodel-xmjquar0-e82fe-vkn45.114.0
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 sha256:6bde3781e17244f52a6cf5f05cd307aa97116959a06eb66df552c2ee0df8c020
|
3 |
+
size 179586
|
runs/Jul31_13-07-41_r-choudharytalhaarain-bertadultmodel-xmjquar0-e82fe-vkn45/events.out.tfevents.1722557670.r-choudharytalhaarain-bertadultmodel-xmjquar0-e82fe-vkn45.114.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:586d44b55020a06db81f9d99a06f347fb2cabea5b00cbaace175a3326695c6c9
|
3 |
+
size 617
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d36804181467c0d1082f474f96ee59831bb7309b234b077011f4711fdba9d14
|
3 |
+
size 5240
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-vp92t-1q2id/autotrain-data",
|
3 |
+
"model": "google-bert/bert-base-uncased",
|
4 |
+
"lr": 3e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 128,
|
7 |
+
"batch_size": 2,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 4,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "autotrain-vp92t-1q2id",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "ChoudharyTAlhaArain",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|