rkotari/classify-clickbait
Browse files- README.md +53 -180
- config.json +42 -0
- model.safetensors +3 -0
- trainer_state.json +259 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,199 +1,72 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
-
|
|
|
7 |
|
8 |
-
|
9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
|
|
|
11 |
|
12 |
-
|
13 |
|
14 |
-
|
15 |
|
16 |
-
|
17 |
|
18 |
-
|
19 |
|
20 |
-
|
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 |
-
|
29 |
|
30 |
-
|
31 |
|
32 |
-
|
33 |
-
-
|
34 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
|
36 |
-
|
37 |
|
38 |
-
|
|
|
|
|
|
|
39 |
|
40 |
-
### Direct Use
|
41 |
|
42 |
-
|
43 |
|
44 |
-
|
45 |
-
|
46 |
-
|
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]
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: albert/albert-base-v2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: classify-clickbait
|
13 |
+
results: []
|
14 |
---
|
15 |
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
+
# classify-clickbait
|
20 |
|
21 |
+
This model is a fine-tuned version of [albert/albert-base-v2](https://huggingface.co/albert/albert-base-v2) on an unknown dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0010
|
24 |
+
- Accuracy: 1.0
|
25 |
+
- F1: 1.0
|
26 |
+
- Precision: 1.0
|
27 |
+
- Recall: 1.0
|
28 |
+
- Accuracy Label Clickbait: 1.0
|
29 |
+
- Accuracy Label Factual: 1.0
|
30 |
|
31 |
+
## Model description
|
32 |
|
33 |
+
More information needed
|
34 |
|
35 |
+
## Intended uses & limitations
|
36 |
|
37 |
+
More information needed
|
38 |
|
39 |
+
## Training and evaluation data
|
40 |
|
41 |
+
More information needed
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
|
43 |
+
## Training procedure
|
44 |
|
45 |
+
### Training hyperparameters
|
46 |
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 2e-05
|
49 |
+
- train_batch_size: 16
|
50 |
+
- eval_batch_size: 16
|
51 |
+
- seed: 42
|
52 |
+
- gradient_accumulation_steps: 2
|
53 |
+
- total_train_batch_size: 32
|
54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
55 |
+
- lr_scheduler_type: linear
|
56 |
+
- lr_scheduler_warmup_steps: 500
|
57 |
+
- num_epochs: 3
|
58 |
|
59 |
+
### Training results
|
60 |
|
61 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Accuracy Label Clickbait | Accuracy Label Factual |
|
62 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:------------------------:|:----------------------:|
|
63 |
+
| 0.1089 | 1.1628 | 100 | 0.0617 | 0.9884 | 0.9884 | 0.9884 | 0.9884 | 0.9828 | 0.9941 |
|
64 |
+
| 0.0118 | 2.3256 | 200 | 0.0093 | 0.9971 | 0.9971 | 0.9971 | 0.9971 | 0.9943 | 1.0 |
|
65 |
|
|
|
66 |
|
67 |
+
### Framework versions
|
68 |
|
69 |
+
- Transformers 4.41.1
|
70 |
+
- Pytorch 2.3.0+cu121
|
71 |
+
- Datasets 2.19.1
|
72 |
+
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert/albert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "clickbait",
|
18 |
+
"1": "factual"
|
19 |
+
},
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"inner_group_num": 1,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"clickbait": 0,
|
25 |
+
"factual": 1
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-12,
|
28 |
+
"max_position_embeddings": 512,
|
29 |
+
"model_type": "albert",
|
30 |
+
"net_structure_type": 0,
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_groups": 1,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"num_memory_blocks": 0,
|
35 |
+
"pad_token_id": 0,
|
36 |
+
"position_embedding_type": "absolute",
|
37 |
+
"problem_type": "single_label_classification",
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.41.1",
|
40 |
+
"type_vocab_size": 2,
|
41 |
+
"vocab_size": 30000
|
42 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1c25bd5ffdce980c55e966630b620a1d777bc8b72d03c9fa8b527fd2a782f0b
|
3 |
+
size 46743912
|
trainer_state.json
ADDED
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 258,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.11627906976744186,
|
13 |
+
"grad_norm": 10.613214492797852,
|
14 |
+
"learning_rate": 4.0000000000000003e-07,
|
15 |
+
"loss": 0.6914,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.23255813953488372,
|
20 |
+
"grad_norm": 13.879897117614746,
|
21 |
+
"learning_rate": 8.000000000000001e-07,
|
22 |
+
"loss": 0.6682,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.3488372093023256,
|
27 |
+
"grad_norm": 12.199045181274414,
|
28 |
+
"learning_rate": 1.2000000000000002e-06,
|
29 |
+
"loss": 0.6228,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.46511627906976744,
|
34 |
+
"grad_norm": 10.077858924865723,
|
35 |
+
"learning_rate": 1.6000000000000001e-06,
|
36 |
+
"loss": 0.5581,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.5813953488372093,
|
41 |
+
"grad_norm": 9.077909469604492,
|
42 |
+
"learning_rate": 2.0000000000000003e-06,
|
43 |
+
"loss": 0.4533,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.6976744186046512,
|
48 |
+
"grad_norm": 12.368229866027832,
|
49 |
+
"learning_rate": 2.4000000000000003e-06,
|
50 |
+
"loss": 0.3712,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.813953488372093,
|
55 |
+
"grad_norm": 8.568652153015137,
|
56 |
+
"learning_rate": 2.8000000000000003e-06,
|
57 |
+
"loss": 0.2595,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.9302325581395349,
|
62 |
+
"grad_norm": 4.570730209350586,
|
63 |
+
"learning_rate": 3.2000000000000003e-06,
|
64 |
+
"loss": 0.1839,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.0465116279069768,
|
69 |
+
"grad_norm": 7.3009562492370605,
|
70 |
+
"learning_rate": 3.6000000000000003e-06,
|
71 |
+
"loss": 0.1171,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.1627906976744187,
|
76 |
+
"grad_norm": 17.301179885864258,
|
77 |
+
"learning_rate": 4.000000000000001e-06,
|
78 |
+
"loss": 0.1089,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.1627906976744187,
|
83 |
+
"eval_accuracy": 0.9883720930232558,
|
84 |
+
"eval_accuracy_label_clickbait": 0.9827586206896551,
|
85 |
+
"eval_accuracy_label_factual": 0.9941176470588236,
|
86 |
+
"eval_f1": 0.9883724860836951,
|
87 |
+
"eval_loss": 0.06170095503330231,
|
88 |
+
"eval_precision": 0.9884396971335857,
|
89 |
+
"eval_recall": 0.9883720930232558,
|
90 |
+
"eval_runtime": 0.2786,
|
91 |
+
"eval_samples_per_second": 1234.948,
|
92 |
+
"eval_steps_per_second": 78.979,
|
93 |
+
"step": 100
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.2790697674418605,
|
97 |
+
"grad_norm": 9.898296356201172,
|
98 |
+
"learning_rate": 4.4e-06,
|
99 |
+
"loss": 0.0528,
|
100 |
+
"step": 110
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.3953488372093024,
|
104 |
+
"grad_norm": 0.6471260190010071,
|
105 |
+
"learning_rate": 4.800000000000001e-06,
|
106 |
+
"loss": 0.0235,
|
107 |
+
"step": 120
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.5116279069767442,
|
111 |
+
"grad_norm": 0.5717675089836121,
|
112 |
+
"learning_rate": 5.2e-06,
|
113 |
+
"loss": 0.0456,
|
114 |
+
"step": 130
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.627906976744186,
|
118 |
+
"grad_norm": 0.4758104085922241,
|
119 |
+
"learning_rate": 5.600000000000001e-06,
|
120 |
+
"loss": 0.0329,
|
121 |
+
"step": 140
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.744186046511628,
|
125 |
+
"grad_norm": 0.17176453769207,
|
126 |
+
"learning_rate": 6e-06,
|
127 |
+
"loss": 0.0422,
|
128 |
+
"step": 150
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.8604651162790697,
|
132 |
+
"grad_norm": 0.1672956943511963,
|
133 |
+
"learning_rate": 6.4000000000000006e-06,
|
134 |
+
"loss": 0.0325,
|
135 |
+
"step": 160
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.9767441860465116,
|
139 |
+
"grad_norm": 8.929553031921387,
|
140 |
+
"learning_rate": 6.800000000000001e-06,
|
141 |
+
"loss": 0.0577,
|
142 |
+
"step": 170
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 2.0930232558139537,
|
146 |
+
"grad_norm": 6.927422523498535,
|
147 |
+
"learning_rate": 7.2000000000000005e-06,
|
148 |
+
"loss": 0.0329,
|
149 |
+
"step": 180
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 2.2093023255813953,
|
153 |
+
"grad_norm": 101.96356964111328,
|
154 |
+
"learning_rate": 7.600000000000001e-06,
|
155 |
+
"loss": 0.0076,
|
156 |
+
"step": 190
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 2.3255813953488373,
|
160 |
+
"grad_norm": 0.08046901226043701,
|
161 |
+
"learning_rate": 8.000000000000001e-06,
|
162 |
+
"loss": 0.0118,
|
163 |
+
"step": 200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 2.3255813953488373,
|
167 |
+
"eval_accuracy": 0.997093023255814,
|
168 |
+
"eval_accuracy_label_clickbait": 0.9942528735632183,
|
169 |
+
"eval_accuracy_label_factual": 1.0,
|
170 |
+
"eval_f1": 0.9970930969577605,
|
171 |
+
"eval_loss": 0.009262952022254467,
|
172 |
+
"eval_precision": 0.9971100231198151,
|
173 |
+
"eval_recall": 0.997093023255814,
|
174 |
+
"eval_runtime": 0.2762,
|
175 |
+
"eval_samples_per_second": 1245.451,
|
176 |
+
"eval_steps_per_second": 79.651,
|
177 |
+
"step": 200
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 2.441860465116279,
|
181 |
+
"grad_norm": 8.304059028625488,
|
182 |
+
"learning_rate": 8.400000000000001e-06,
|
183 |
+
"loss": 0.0752,
|
184 |
+
"step": 210
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.558139534883721,
|
188 |
+
"grad_norm": 0.26231056451797485,
|
189 |
+
"learning_rate": 8.8e-06,
|
190 |
+
"loss": 0.0019,
|
191 |
+
"step": 220
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.6744186046511627,
|
195 |
+
"grad_norm": 0.04355992376804352,
|
196 |
+
"learning_rate": 9.200000000000002e-06,
|
197 |
+
"loss": 0.0076,
|
198 |
+
"step": 230
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.7906976744186047,
|
202 |
+
"grad_norm": 27.33185386657715,
|
203 |
+
"learning_rate": 9.600000000000001e-06,
|
204 |
+
"loss": 0.029,
|
205 |
+
"step": 240
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.9069767441860463,
|
209 |
+
"grad_norm": 0.038574591279029846,
|
210 |
+
"learning_rate": 1e-05,
|
211 |
+
"loss": 0.0015,
|
212 |
+
"step": 250
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 3.0,
|
216 |
+
"step": 258,
|
217 |
+
"total_flos": 11163167404740.0,
|
218 |
+
"train_loss": 0.1740486863350799,
|
219 |
+
"train_runtime": 20.4599,
|
220 |
+
"train_samples_per_second": 403.08,
|
221 |
+
"train_steps_per_second": 12.61
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 3.0,
|
225 |
+
"eval_accuracy": 1.0,
|
226 |
+
"eval_accuracy_label_clickbait": 1.0,
|
227 |
+
"eval_accuracy_label_factual": 1.0,
|
228 |
+
"eval_f1": 1.0,
|
229 |
+
"eval_loss": 0.001034915097989142,
|
230 |
+
"eval_precision": 1.0,
|
231 |
+
"eval_recall": 1.0,
|
232 |
+
"eval_runtime": 0.2775,
|
233 |
+
"eval_samples_per_second": 1239.448,
|
234 |
+
"eval_steps_per_second": 79.267,
|
235 |
+
"step": 258
|
236 |
+
}
|
237 |
+
],
|
238 |
+
"logging_steps": 10,
|
239 |
+
"max_steps": 258,
|
240 |
+
"num_input_tokens_seen": 0,
|
241 |
+
"num_train_epochs": 3,
|
242 |
+
"save_steps": 1000,
|
243 |
+
"stateful_callbacks": {
|
244 |
+
"TrainerControl": {
|
245 |
+
"args": {
|
246 |
+
"should_epoch_stop": false,
|
247 |
+
"should_evaluate": false,
|
248 |
+
"should_log": false,
|
249 |
+
"should_save": false,
|
250 |
+
"should_training_stop": false
|
251 |
+
},
|
252 |
+
"attributes": {}
|
253 |
+
}
|
254 |
+
},
|
255 |
+
"total_flos": 11163167404740.0,
|
256 |
+
"train_batch_size": 16,
|
257 |
+
"trial_name": null,
|
258 |
+
"trial_params": null
|
259 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30e4fd082db3ff6d642ff00f7b1232a31f6503960a93d2bc0c8a5585b00f464b
|
3 |
+
size 5048
|