ilsilfverskiold
commited on
Commit
•
e45188a
1
Parent(s):
53883b4
ilsilfverskiold/classify-clickbait-titll
Browse files- README.md +57 -180
- all_results.json +14 -0
- config.json +42 -0
- eval_results.json +14 -0
- model.safetensors +3 -0
- runs/May20_08-21-19_7bcd71f7b87d/events.out.tfevents.1716193280.7bcd71f7b87d.1234.0 +3 -0
- runs/May20_08-21-19_7bcd71f7b87d/events.out.tfevents.1716193385.7bcd71f7b87d.1234.1 +3 -0
- trainer_state.json +574 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,199 +1,76 @@
|
|
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-titll
|
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-titll
|
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: 0.0173
|
24 |
+
- Accuracy: 0.9951
|
25 |
+
- F1: 0.9951
|
26 |
+
- Precision: 0.9951
|
27 |
+
- Recall: 0.9951
|
28 |
+
- Accuracy Label Clickbait: 0.9866
|
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 |
+
| 0.0561 | 0.4831 | 100 | 0.0488 | 0.9927 | 0.9927 | 0.9927 | 0.9927 | 0.9933 | 0.9923 |
|
64 |
+
| 0.0037 | 0.9662 | 200 | 0.0097 | 0.9988 | 0.9988 | 0.9988 | 0.9988 | 0.9967 | 1.0 |
|
65 |
+
| 0.0012 | 1.4493 | 300 | 0.0016 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
|
66 |
+
| 0.0012 | 1.9324 | 400 | 0.0016 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
|
67 |
+
| 0.0433 | 2.4155 | 500 | 0.0020 | 0.9988 | 0.9988 | 0.9988 | 0.9988 | 0.9967 | 1.0 |
|
68 |
+
| 0.0003 | 2.8986 | 600 | 0.0167 | 0.9951 | 0.9951 | 0.9951 | 0.9951 | 0.9866 | 1.0 |
|
69 |
|
|
|
70 |
|
71 |
+
### Framework versions
|
72 |
|
73 |
+
- Transformers 4.41.0
|
74 |
+
- Pytorch 2.2.1+cu121
|
75 |
+
- Datasets 2.19.1
|
76 |
+
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.9951100244498777,
|
4 |
+
"eval_accuracy_label_Clickbait": 0.9866220735785953,
|
5 |
+
"eval_accuracy_label_Factual": 1.0,
|
6 |
+
"eval_f1": 0.9951029456353522,
|
7 |
+
"eval_loss": 0.017279641702771187,
|
8 |
+
"eval_precision": 0.9951474238804714,
|
9 |
+
"eval_recall": 0.9951100244498777,
|
10 |
+
"eval_runtime": 0.8191,
|
11 |
+
"eval_samples_per_second": 998.621,
|
12 |
+
"eval_steps_per_second": 63.482,
|
13 |
+
"step": 621
|
14 |
+
}
|
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": "4.41.0",
|
40 |
+
"type_vocab_size": 2,
|
41 |
+
"vocab_size": 30000
|
42 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.9951100244498777,
|
4 |
+
"eval_accuracy_label_Clickbait": 0.9866220735785953,
|
5 |
+
"eval_accuracy_label_Factual": 1.0,
|
6 |
+
"eval_f1": 0.9951029456353522,
|
7 |
+
"eval_loss": 0.017279641702771187,
|
8 |
+
"eval_precision": 0.9951474238804714,
|
9 |
+
"eval_recall": 0.9951100244498777,
|
10 |
+
"eval_runtime": 0.8191,
|
11 |
+
"eval_samples_per_second": 998.621,
|
12 |
+
"eval_steps_per_second": 63.482,
|
13 |
+
"step": 621
|
14 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43b5c26f0463a366f036d5cd31662f92d4d186cc12856bac1dfdd22919b60454
|
3 |
+
size 46743912
|
runs/May20_08-21-19_7bcd71f7b87d/events.out.tfevents.1716193280.7bcd71f7b87d.1234.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bc568d97679f9a9b7a62ef7cbb0f1a377a56c4060d30824abfe55347af58be4
|
3 |
+
size 22129
|
runs/May20_08-21-19_7bcd71f7b87d/events.out.tfevents.1716193385.7bcd71f7b87d.1234.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbeff8b412bde2c602bd81ff7b07e89708e65fbaf45cf61fcc3352c3c95da45a
|
3 |
+
size 694
|
trainer_state.json
ADDED
@@ -0,0 +1,574 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 621,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04830917874396135,
|
13 |
+
"grad_norm": 37.65997314453125,
|
14 |
+
"learning_rate": 4.0000000000000003e-07,
|
15 |
+
"loss": 0.8115,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0966183574879227,
|
20 |
+
"grad_norm": 49.085182189941406,
|
21 |
+
"learning_rate": 8.000000000000001e-07,
|
22 |
+
"loss": 0.7151,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.14492753623188406,
|
27 |
+
"grad_norm": 57.3139533996582,
|
28 |
+
"learning_rate": 1.2000000000000002e-06,
|
29 |
+
"loss": 0.5399,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.1932367149758454,
|
34 |
+
"grad_norm": 14.93040943145752,
|
35 |
+
"learning_rate": 1.6000000000000001e-06,
|
36 |
+
"loss": 0.4486,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.24154589371980675,
|
41 |
+
"grad_norm": 40.2352409362793,
|
42 |
+
"learning_rate": 2.0000000000000003e-06,
|
43 |
+
"loss": 0.2895,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2898550724637681,
|
48 |
+
"grad_norm": 22.021743774414062,
|
49 |
+
"learning_rate": 2.4000000000000003e-06,
|
50 |
+
"loss": 0.208,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.33816425120772947,
|
55 |
+
"grad_norm": 3.9624946117401123,
|
56 |
+
"learning_rate": 2.8000000000000003e-06,
|
57 |
+
"loss": 0.158,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.3864734299516908,
|
62 |
+
"grad_norm": 3.648684501647949,
|
63 |
+
"learning_rate": 3.2000000000000003e-06,
|
64 |
+
"loss": 0.1099,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.43478260869565216,
|
69 |
+
"grad_norm": 1.9831331968307495,
|
70 |
+
"learning_rate": 3.6000000000000003e-06,
|
71 |
+
"loss": 0.0898,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.4830917874396135,
|
76 |
+
"grad_norm": 1.1971267461776733,
|
77 |
+
"learning_rate": 4.000000000000001e-06,
|
78 |
+
"loss": 0.0561,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.4830917874396135,
|
83 |
+
"eval_accuracy": 0.9926650366748166,
|
84 |
+
"eval_accuracy_label_Clickbait": 0.9933110367892977,
|
85 |
+
"eval_accuracy_label_Factual": 0.9922928709055877,
|
86 |
+
"eval_f1": 0.9926701815332624,
|
87 |
+
"eval_loss": 0.04882814362645149,
|
88 |
+
"eval_precision": 0.9926880698400764,
|
89 |
+
"eval_recall": 0.9926650366748166,
|
90 |
+
"eval_runtime": 0.8226,
|
91 |
+
"eval_samples_per_second": 994.464,
|
92 |
+
"eval_steps_per_second": 63.218,
|
93 |
+
"step": 100
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.5314009661835749,
|
97 |
+
"grad_norm": 0.8438642621040344,
|
98 |
+
"learning_rate": 4.4e-06,
|
99 |
+
"loss": 0.061,
|
100 |
+
"step": 110
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.5797101449275363,
|
104 |
+
"grad_norm": 0.5306077003479004,
|
105 |
+
"learning_rate": 4.800000000000001e-06,
|
106 |
+
"loss": 0.0523,
|
107 |
+
"step": 120
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6280193236714976,
|
111 |
+
"grad_norm": 42.116844177246094,
|
112 |
+
"learning_rate": 5.2e-06,
|
113 |
+
"loss": 0.0555,
|
114 |
+
"step": 130
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.6763285024154589,
|
118 |
+
"grad_norm": 0.45348191261291504,
|
119 |
+
"learning_rate": 5.600000000000001e-06,
|
120 |
+
"loss": 0.0511,
|
121 |
+
"step": 140
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.7246376811594203,
|
125 |
+
"grad_norm": 0.273034930229187,
|
126 |
+
"learning_rate": 6e-06,
|
127 |
+
"loss": 0.0461,
|
128 |
+
"step": 150
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.7729468599033816,
|
132 |
+
"grad_norm": 0.32376888394355774,
|
133 |
+
"learning_rate": 6.4000000000000006e-06,
|
134 |
+
"loss": 0.0355,
|
135 |
+
"step": 160
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.821256038647343,
|
139 |
+
"grad_norm": 0.46599268913269043,
|
140 |
+
"learning_rate": 6.800000000000001e-06,
|
141 |
+
"loss": 0.0057,
|
142 |
+
"step": 170
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.8695652173913043,
|
146 |
+
"grad_norm": 76.78250122070312,
|
147 |
+
"learning_rate": 7.2000000000000005e-06,
|
148 |
+
"loss": 0.0284,
|
149 |
+
"step": 180
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.9178743961352657,
|
153 |
+
"grad_norm": 0.27929720282554626,
|
154 |
+
"learning_rate": 7.600000000000001e-06,
|
155 |
+
"loss": 0.0154,
|
156 |
+
"step": 190
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.966183574879227,
|
160 |
+
"grad_norm": 0.09468149393796921,
|
161 |
+
"learning_rate": 8.000000000000001e-06,
|
162 |
+
"loss": 0.0037,
|
163 |
+
"step": 200
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.966183574879227,
|
167 |
+
"eval_accuracy": 0.9987775061124694,
|
168 |
+
"eval_accuracy_label_Clickbait": 0.9966555183946488,
|
169 |
+
"eval_accuracy_label_Factual": 1.0,
|
170 |
+
"eval_f1": 0.998777070551364,
|
171 |
+
"eval_loss": 0.00973883830010891,
|
172 |
+
"eval_precision": 0.9987798570622531,
|
173 |
+
"eval_recall": 0.9987775061124694,
|
174 |
+
"eval_runtime": 0.8161,
|
175 |
+
"eval_samples_per_second": 1002.369,
|
176 |
+
"eval_steps_per_second": 63.72,
|
177 |
+
"step": 200
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.0144927536231885,
|
181 |
+
"grad_norm": 11.390016555786133,
|
182 |
+
"learning_rate": 8.400000000000001e-06,
|
183 |
+
"loss": 0.033,
|
184 |
+
"step": 210
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.0628019323671498,
|
188 |
+
"grad_norm": 0.6215488910675049,
|
189 |
+
"learning_rate": 8.8e-06,
|
190 |
+
"loss": 0.0279,
|
191 |
+
"step": 220
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.1111111111111112,
|
195 |
+
"grad_norm": 0.1523633599281311,
|
196 |
+
"learning_rate": 9.200000000000002e-06,
|
197 |
+
"loss": 0.0093,
|
198 |
+
"step": 230
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.1594202898550725,
|
202 |
+
"grad_norm": 0.10952762514352798,
|
203 |
+
"learning_rate": 9.600000000000001e-06,
|
204 |
+
"loss": 0.022,
|
205 |
+
"step": 240
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.2077294685990339,
|
209 |
+
"grad_norm": 0.07856310158967972,
|
210 |
+
"learning_rate": 1e-05,
|
211 |
+
"loss": 0.0309,
|
212 |
+
"step": 250
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.2560386473429952,
|
216 |
+
"grad_norm": 0.05758531391620636,
|
217 |
+
"learning_rate": 1.04e-05,
|
218 |
+
"loss": 0.0015,
|
219 |
+
"step": 260
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.3043478260869565,
|
223 |
+
"grad_norm": 0.049695733934640884,
|
224 |
+
"learning_rate": 1.0800000000000002e-05,
|
225 |
+
"loss": 0.0071,
|
226 |
+
"step": 270
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 1.3526570048309179,
|
230 |
+
"grad_norm": 0.19512628018856049,
|
231 |
+
"learning_rate": 1.1200000000000001e-05,
|
232 |
+
"loss": 0.0054,
|
233 |
+
"step": 280
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.4009661835748792,
|
237 |
+
"grad_norm": 0.049039632081985474,
|
238 |
+
"learning_rate": 1.16e-05,
|
239 |
+
"loss": 0.023,
|
240 |
+
"step": 290
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.4492753623188406,
|
244 |
+
"grad_norm": 0.06413820385932922,
|
245 |
+
"learning_rate": 1.2e-05,
|
246 |
+
"loss": 0.0012,
|
247 |
+
"step": 300
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.4492753623188406,
|
251 |
+
"eval_accuracy": 1.0,
|
252 |
+
"eval_accuracy_label_Clickbait": 1.0,
|
253 |
+
"eval_accuracy_label_Factual": 1.0,
|
254 |
+
"eval_f1": 1.0,
|
255 |
+
"eval_loss": 0.0015956248389557004,
|
256 |
+
"eval_precision": 1.0,
|
257 |
+
"eval_recall": 1.0,
|
258 |
+
"eval_runtime": 0.8233,
|
259 |
+
"eval_samples_per_second": 993.556,
|
260 |
+
"eval_steps_per_second": 63.16,
|
261 |
+
"step": 300
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.497584541062802,
|
265 |
+
"grad_norm": 0.04210774227976799,
|
266 |
+
"learning_rate": 1.2400000000000002e-05,
|
267 |
+
"loss": 0.0012,
|
268 |
+
"step": 310
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.5458937198067633,
|
272 |
+
"grad_norm": 0.02976871468126774,
|
273 |
+
"learning_rate": 1.2800000000000001e-05,
|
274 |
+
"loss": 0.0079,
|
275 |
+
"step": 320
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.5942028985507246,
|
279 |
+
"grad_norm": 0.029957927763462067,
|
280 |
+
"learning_rate": 1.3200000000000002e-05,
|
281 |
+
"loss": 0.0008,
|
282 |
+
"step": 330
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.642512077294686,
|
286 |
+
"grad_norm": 12.84114933013916,
|
287 |
+
"learning_rate": 1.3600000000000002e-05,
|
288 |
+
"loss": 0.0168,
|
289 |
+
"step": 340
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.6908212560386473,
|
293 |
+
"grad_norm": 0.6662724018096924,
|
294 |
+
"learning_rate": 1.4e-05,
|
295 |
+
"loss": 0.0209,
|
296 |
+
"step": 350
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.7391304347826086,
|
300 |
+
"grad_norm": 0.036532897502183914,
|
301 |
+
"learning_rate": 1.4400000000000001e-05,
|
302 |
+
"loss": 0.0008,
|
303 |
+
"step": 360
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.78743961352657,
|
307 |
+
"grad_norm": 0.05894944816827774,
|
308 |
+
"learning_rate": 1.48e-05,
|
309 |
+
"loss": 0.0351,
|
310 |
+
"step": 370
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.8357487922705316,
|
314 |
+
"grad_norm": 0.03172897920012474,
|
315 |
+
"learning_rate": 1.5200000000000002e-05,
|
316 |
+
"loss": 0.0156,
|
317 |
+
"step": 380
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.8840579710144927,
|
321 |
+
"grad_norm": 60.220420837402344,
|
322 |
+
"learning_rate": 1.5600000000000003e-05,
|
323 |
+
"loss": 0.106,
|
324 |
+
"step": 390
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.9323671497584543,
|
328 |
+
"grad_norm": 0.045578889548778534,
|
329 |
+
"learning_rate": 1.6000000000000003e-05,
|
330 |
+
"loss": 0.0012,
|
331 |
+
"step": 400
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.9323671497584543,
|
335 |
+
"eval_accuracy": 1.0,
|
336 |
+
"eval_accuracy_label_Clickbait": 1.0,
|
337 |
+
"eval_accuracy_label_Factual": 1.0,
|
338 |
+
"eval_f1": 1.0,
|
339 |
+
"eval_loss": 0.001607110258191824,
|
340 |
+
"eval_precision": 1.0,
|
341 |
+
"eval_recall": 1.0,
|
342 |
+
"eval_runtime": 0.822,
|
343 |
+
"eval_samples_per_second": 995.143,
|
344 |
+
"eval_steps_per_second": 63.261,
|
345 |
+
"step": 400
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.9806763285024154,
|
349 |
+
"grad_norm": 0.038461122661828995,
|
350 |
+
"learning_rate": 1.64e-05,
|
351 |
+
"loss": 0.0011,
|
352 |
+
"step": 410
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 2.028985507246377,
|
356 |
+
"grad_norm": 0.024971311911940575,
|
357 |
+
"learning_rate": 1.6800000000000002e-05,
|
358 |
+
"loss": 0.0008,
|
359 |
+
"step": 420
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 2.077294685990338,
|
363 |
+
"grad_norm": 0.021732186898589134,
|
364 |
+
"learning_rate": 1.72e-05,
|
365 |
+
"loss": 0.0005,
|
366 |
+
"step": 430
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 2.1256038647342996,
|
370 |
+
"grad_norm": 22.902217864990234,
|
371 |
+
"learning_rate": 1.76e-05,
|
372 |
+
"loss": 0.0134,
|
373 |
+
"step": 440
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 2.1739130434782608,
|
377 |
+
"grad_norm": 0.05803954228758812,
|
378 |
+
"learning_rate": 1.8e-05,
|
379 |
+
"loss": 0.0005,
|
380 |
+
"step": 450
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.2222222222222223,
|
384 |
+
"grad_norm": 0.016587387770414352,
|
385 |
+
"learning_rate": 1.8400000000000003e-05,
|
386 |
+
"loss": 0.0004,
|
387 |
+
"step": 460
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 2.2705314009661834,
|
391 |
+
"grad_norm": 0.014241261407732964,
|
392 |
+
"learning_rate": 1.88e-05,
|
393 |
+
"loss": 0.0004,
|
394 |
+
"step": 470
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 2.318840579710145,
|
398 |
+
"grad_norm": 0.013285420835018158,
|
399 |
+
"learning_rate": 1.9200000000000003e-05,
|
400 |
+
"loss": 0.0003,
|
401 |
+
"step": 480
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 2.367149758454106,
|
405 |
+
"grad_norm": 0.008689775131642818,
|
406 |
+
"learning_rate": 1.9600000000000002e-05,
|
407 |
+
"loss": 0.0003,
|
408 |
+
"step": 490
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 2.4154589371980677,
|
412 |
+
"grad_norm": 0.05173454433679581,
|
413 |
+
"learning_rate": 2e-05,
|
414 |
+
"loss": 0.0433,
|
415 |
+
"step": 500
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 2.4154589371980677,
|
419 |
+
"eval_accuracy": 0.9987775061124694,
|
420 |
+
"eval_accuracy_label_Clickbait": 0.9966555183946488,
|
421 |
+
"eval_accuracy_label_Factual": 1.0,
|
422 |
+
"eval_f1": 0.998777070551364,
|
423 |
+
"eval_loss": 0.0020217353012412786,
|
424 |
+
"eval_precision": 0.9987798570622531,
|
425 |
+
"eval_recall": 0.9987775061124694,
|
426 |
+
"eval_runtime": 0.8279,
|
427 |
+
"eval_samples_per_second": 988.004,
|
428 |
+
"eval_steps_per_second": 62.807,
|
429 |
+
"step": 500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 2.463768115942029,
|
433 |
+
"grad_norm": 0.07507430762052536,
|
434 |
+
"learning_rate": 1.834710743801653e-05,
|
435 |
+
"loss": 0.0055,
|
436 |
+
"step": 510
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 2.5120772946859904,
|
440 |
+
"grad_norm": 42.797401428222656,
|
441 |
+
"learning_rate": 1.669421487603306e-05,
|
442 |
+
"loss": 0.0161,
|
443 |
+
"step": 520
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.5603864734299515,
|
447 |
+
"grad_norm": 0.01774718426167965,
|
448 |
+
"learning_rate": 1.504132231404959e-05,
|
449 |
+
"loss": 0.0006,
|
450 |
+
"step": 530
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.608695652173913,
|
454 |
+
"grad_norm": 0.022867949679493904,
|
455 |
+
"learning_rate": 1.3388429752066117e-05,
|
456 |
+
"loss": 0.0191,
|
457 |
+
"step": 540
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.6570048309178746,
|
461 |
+
"grad_norm": 0.013622589409351349,
|
462 |
+
"learning_rate": 1.1735537190082646e-05,
|
463 |
+
"loss": 0.0043,
|
464 |
+
"step": 550
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 2.7053140096618358,
|
468 |
+
"grad_norm": 0.012125013396143913,
|
469 |
+
"learning_rate": 1.0082644628099174e-05,
|
470 |
+
"loss": 0.0003,
|
471 |
+
"step": 560
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 2.753623188405797,
|
475 |
+
"grad_norm": 0.009969482198357582,
|
476 |
+
"learning_rate": 8.429752066115703e-06,
|
477 |
+
"loss": 0.0193,
|
478 |
+
"step": 570
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 2.8019323671497585,
|
482 |
+
"grad_norm": 0.010625869035720825,
|
483 |
+
"learning_rate": 6.776859504132232e-06,
|
484 |
+
"loss": 0.0008,
|
485 |
+
"step": 580
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.85024154589372,
|
489 |
+
"grad_norm": 0.010633111000061035,
|
490 |
+
"learning_rate": 5.12396694214876e-06,
|
491 |
+
"loss": 0.0143,
|
492 |
+
"step": 590
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 2.898550724637681,
|
496 |
+
"grad_norm": 0.011428612284362316,
|
497 |
+
"learning_rate": 3.4710743801652895e-06,
|
498 |
+
"loss": 0.0003,
|
499 |
+
"step": 600
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.898550724637681,
|
503 |
+
"eval_accuracy": 0.9951100244498777,
|
504 |
+
"eval_accuracy_label_Clickbait": 0.9866220735785953,
|
505 |
+
"eval_accuracy_label_Factual": 1.0,
|
506 |
+
"eval_f1": 0.9951029456353522,
|
507 |
+
"eval_loss": 0.016679394990205765,
|
508 |
+
"eval_precision": 0.9951474238804714,
|
509 |
+
"eval_recall": 0.9951100244498777,
|
510 |
+
"eval_runtime": 0.8314,
|
511 |
+
"eval_samples_per_second": 983.91,
|
512 |
+
"eval_steps_per_second": 62.547,
|
513 |
+
"step": 600
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 2.9468599033816423,
|
517 |
+
"grad_norm": 0.010514287278056145,
|
518 |
+
"learning_rate": 1.8181818181818183e-06,
|
519 |
+
"loss": 0.0003,
|
520 |
+
"step": 610
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 2.995169082125604,
|
524 |
+
"grad_norm": 104.85121154785156,
|
525 |
+
"learning_rate": 1.6528925619834713e-07,
|
526 |
+
"loss": 0.0108,
|
527 |
+
"step": 620
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 3.0,
|
531 |
+
"step": 621,
|
532 |
+
"total_flos": 29633646182400.0,
|
533 |
+
"train_loss": 0.06926822083632517,
|
534 |
+
"train_runtime": 68.411,
|
535 |
+
"train_samples_per_second": 290.041,
|
536 |
+
"train_steps_per_second": 9.077
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 3.0,
|
540 |
+
"eval_accuracy": 0.9951100244498777,
|
541 |
+
"eval_accuracy_label_Clickbait": 0.9866220735785953,
|
542 |
+
"eval_accuracy_label_Factual": 1.0,
|
543 |
+
"eval_f1": 0.9951029456353522,
|
544 |
+
"eval_loss": 0.017279641702771187,
|
545 |
+
"eval_precision": 0.9951474238804714,
|
546 |
+
"eval_recall": 0.9951100244498777,
|
547 |
+
"eval_runtime": 0.8191,
|
548 |
+
"eval_samples_per_second": 998.621,
|
549 |
+
"eval_steps_per_second": 63.482,
|
550 |
+
"step": 621
|
551 |
+
}
|
552 |
+
],
|
553 |
+
"logging_steps": 10,
|
554 |
+
"max_steps": 621,
|
555 |
+
"num_input_tokens_seen": 0,
|
556 |
+
"num_train_epochs": 3,
|
557 |
+
"save_steps": 1000,
|
558 |
+
"stateful_callbacks": {
|
559 |
+
"TrainerControl": {
|
560 |
+
"args": {
|
561 |
+
"should_epoch_stop": false,
|
562 |
+
"should_evaluate": false,
|
563 |
+
"should_log": false,
|
564 |
+
"should_save": false,
|
565 |
+
"should_training_stop": false
|
566 |
+
},
|
567 |
+
"attributes": {}
|
568 |
+
}
|
569 |
+
},
|
570 |
+
"total_flos": 29633646182400.0,
|
571 |
+
"train_batch_size": 16,
|
572 |
+
"trial_name": null,
|
573 |
+
"trial_params": null
|
574 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30290afbf408b1380f4bdc0e2f2d06b731deec3b4ea52a4f1c3c6ef34ef09625
|
3 |
+
size 5112
|