Commit
•
cfd5805
1
Parent(s):
2c80ad6
Upload 11 files
Browse files- .gitattributes +1 -1
- README.md +190 -1
- config.json +42 -0
- gitattributes +35 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +3 -0
- tokenizer_config.json +12 -0
- trainer_state.json +922 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -25,7 +25,6 @@
|
|
25 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
*.wasm filter=lfs diff=lfs merge=lfs -text
|
@@ -33,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
25 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
|
|
28 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
29 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
30 |
*.wasm filter=lfs diff=lfs merge=lfs -text
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,192 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: openrail
|
3 |
+
widget:
|
4 |
+
- text: I am totally a human, trust me bro.
|
5 |
+
example_title: default
|
6 |
+
- text: >-
|
7 |
+
In Finnish folklore, all places and things, and also human beings, have a
|
8 |
+
haltija (a genius, guardian spirit) of their own. One such haltija is called
|
9 |
+
etiäinen—an image, doppelgänger, or just an impression that goes ahead of a
|
10 |
+
person, doing things the person in question later does. For example, people
|
11 |
+
waiting at home might hear the door close or even see a shadow or a
|
12 |
+
silhouette, only to realize that no one has yet arrived. Etiäinen can also
|
13 |
+
refer to some kind of a feeling that something is going to happen. Sometimes
|
14 |
+
it could, for example, warn of a bad year coming. In modern Finnish, the
|
15 |
+
term has detached from its shamanistic origins and refers to premonition.
|
16 |
+
Unlike clairvoyance, divination, and similar practices, etiäiset (plural)
|
17 |
+
are spontaneous and can't be induced. Quite the opposite, they may be
|
18 |
+
unwanted and cause anxiety, like ghosts. Etiäiset need not be too dramatic
|
19 |
+
and may concern everyday events, although ones related to e.g. deaths are
|
20 |
+
common. As these phenomena are still reported today, they can be considered
|
21 |
+
a living tradition, as a way to explain the psychological experience of
|
22 |
+
premonition.
|
23 |
+
example_title: real wikipedia
|
24 |
+
- text: >-
|
25 |
+
In Finnish folklore, all places and things, animate or inanimate, have a
|
26 |
+
spirit or "etiäinen" that lives there. Etiäinen can manifest in many forms,
|
27 |
+
but is usually described as a kind, elderly woman with white hair. She is
|
28 |
+
the guardian of natural places and often helps people in need. Etiäinen has
|
29 |
+
been a part of Finnish culture for centuries and is still widely believed in
|
30 |
+
today. Folklorists study etiäinen to understand Finnish traditions and how
|
31 |
+
they have changed over time.
|
32 |
+
example_title: generated wikipedia
|
33 |
+
- text: >-
|
34 |
+
This paper presents a novel framework for sparsity-certifying graph
|
35 |
+
decompositions, which are important tools in various areas of computer
|
36 |
+
science, including algorithm design, complexity theory, and optimization.
|
37 |
+
Our approach is based on the concept of "cut sparsifiers," which are sparse
|
38 |
+
graphs that preserve the cut structure of the original graph up to a certain
|
39 |
+
error bound. We show that cut sparsifiers can be efficiently constructed
|
40 |
+
using a combination of spectral techniques and random sampling, and we use
|
41 |
+
them to develop new algorithms for decomposing graphs into sparse subgraphs.
|
42 |
+
example_title: from ChatGPT
|
43 |
+
- text: >-
|
44 |
+
Recent work has demonstrated substantial gains on many NLP tasks and
|
45 |
+
benchmarks by pre-training on a large corpus of text followed by fine-tuning
|
46 |
+
on a specific task. While typically task-agnostic in architecture, this
|
47 |
+
method still requires task-specific fine-tuning datasets of thousands or
|
48 |
+
tens of thousands of examples. By contrast, humans can generally perform a
|
49 |
+
new language task from only a few examples or from simple instructions -
|
50 |
+
something which current NLP systems still largely struggle to do. Here we
|
51 |
+
show that scaling up language models greatly improves task-agnostic,
|
52 |
+
few-shot performance, sometimes even reaching competitiveness with prior
|
53 |
+
state-of-the-art fine-tuning approaches. Specifically, we train GPT-3, an
|
54 |
+
autoregressive language model with 175 billion parameters, 10x more than any
|
55 |
+
previous non-sparse language model, and test its performance in the few-shot
|
56 |
+
setting. For all tasks, GPT-3 is applied without any gradient updates or
|
57 |
+
fine-tuning, with tasks and few-shot demonstrations specified purely via
|
58 |
+
text interaction with the model. GPT-3 achieves strong performance on many
|
59 |
+
NLP datasets, including translation, question-answering, and cloze tasks, as
|
60 |
+
well as several tasks that require on-the-fly reasoning or domain
|
61 |
+
adaptation, such as unscrambling words, using a novel word in a sentence, or
|
62 |
+
performing 3-digit arithmetic. At the same time, we also identify some
|
63 |
+
datasets where GPT-3's few-shot learning still struggles, as well as some
|
64 |
+
datasets where GPT-3 faces methodological issues related to training on
|
65 |
+
large web corpora. Finally, we find that GPT-3 can generate samples of news
|
66 |
+
articles which human evaluators have difficulty distinguishing from articles
|
67 |
+
written by humans. We discuss broader societal impacts of this finding and
|
68 |
+
of GPT-3 in general.
|
69 |
+
example_title: GPT-3 paper
|
70 |
+
datasets:
|
71 |
+
- NicolaiSivesind/human-vs-machine
|
72 |
+
- gfissore/arxiv-abstracts-2021
|
73 |
+
language:
|
74 |
+
- en
|
75 |
+
pipeline_tag: text-classification
|
76 |
+
tags:
|
77 |
+
- mgt-detection
|
78 |
+
- ai-detection
|
79 |
---
|
80 |
+
|
81 |
+
Machine-generated text-detection by fine-tuning of language models
|
82 |
+
===
|
83 |
+
|
84 |
+
This project is related to a bachelor's thesis with the title "*Turning Poachers into Gamekeepers: Detecting Machine-Generated Text in Academia using Large Language Models*" (see [here](https://ntnuopen.ntnu.no/ntnu-xmlui/handle/11250/3078096)) written by *Nicolai Thorer Sivesind* and *Andreas Bentzen Winje* at the *Department of Computer Science* at the *Norwegian University of Science and Technology*.
|
85 |
+
|
86 |
+
It contains text classification models trained to distinguish human-written text from text generated by language models like ChatGPT and GPT-3. The best models were able to achieve an accuracy of 100% on real and *GPT-3*-generated wikipedia articles (4500 samples), and an accuracy of 98.4% on real and *ChatGPT*-generated research abstracts (3000 samples).
|
87 |
+
|
88 |
+
The dataset card for the dataset that was created in relation to this project can be found [here](https://huggingface.co/datasets/NicolaiSivesind/human-vs-machine).
|
89 |
+
|
90 |
+
**NOTE**: the hosted inference on this site only works for the RoBERTa-models, and not for the Bloomz-models. The Bloomz-models otherwise can produce wrong predictions when not explicitly providing the attention mask from the tokenizer to the model for inference. To be sure, the [pipeline](https://huggingface.co/docs/transformers/main_classes/pipelines)-library seems to produce the most consistent results.
|
91 |
+
|
92 |
+
|
93 |
+
## Fine-tuned detectors
|
94 |
+
|
95 |
+
This project includes 12 fine-tuned models based on the RoBERTa-base model, and three sizes of the bloomz-models.
|
96 |
+
|
97 |
+
| Base-model | RoBERTa-base | Bloomz-560m | Bloomz-1b7 | Bloomz-3b |
|
98 |
+
|------------|--------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------|
|
99 |
+
| Wiki | [roberta-wiki](https://huggingface.co/andreas122001/roberta-wiki-detector) | [Bloomz-560m-wiki](https://huggingface.co/andreas122001/bloomz-560m-wiki-detector) | [Bloomz-1b7-wiki](https://huggingface.co/andreas122001/bloomz-1b7-wiki-detector) | [Bloomz-3b-wiki](https://huggingface.co/andreas122001/bloomz-3b-wiki-detector) |
|
100 |
+
| Academic | [roberta-academic](https://huggingface.co/andreas122001/roberta-academic-detector) | [Bloomz-560m-academic](https://huggingface.co/andreas122001/bloomz-560m-academic-detector) | [Bloomz-1b7-academic](https://huggingface.co/andreas122001/bloomz-1b7-academic-detector) | [Bloomz-3b-academic](https://huggingface.co/andreas122001/bloomz-3b-academic-detector) |
|
101 |
+
| Mixed | [roberta-mixed](https://huggingface.co/andreas122001/roberta-mixed-detector) | [Bloomz-560m-mixed](https://huggingface.co/andreas122001/bloomz-560m-mixed-detector) | [Bloomz-1b7-mixed](https://huggingface.co/andreas122001/bloomz-1b7-mixed-detector) | [Bloomz-3b-mixed](https://huggingface.co/andreas122001/bloomz-3b-mixed-detector) |
|
102 |
+
|
103 |
+
|
104 |
+
### Datasets
|
105 |
+
|
106 |
+
The models were trained on selections from the [GPT-wiki-intros]() and [ChatGPT-Research-Abstracts](), and are separated into three types, **wiki**-detectors, **academic**-detectors and **mixed**-detectors, respectively.
|
107 |
+
|
108 |
+
- **Wiki-detectors**:
|
109 |
+
- Trained on 30'000 datapoints (10%) of GPT-wiki-intros.
|
110 |
+
- Best model (in-domain) is Bloomz-3b-wiki, with an accuracy of 100%.
|
111 |
+
- **Academic-detectors**:
|
112 |
+
- Trained on 20'000 datapoints (100%) of ChatGPT-Research-Abstracts.
|
113 |
+
- Best model (in-domain) is Bloomz-3b-academic, with an accuracy of 98.4%
|
114 |
+
- **Mixed-detectors**:
|
115 |
+
- Trained on 15'000 datapoints (5%) of GPT-wiki-intros and 10'000 datapoints (50%) of ChatGPT-Research-Abstracts.
|
116 |
+
- Best model (in-domain) is RoBERTa-mixed, with an F1-score of 99.3%.
|
117 |
+
|
118 |
+
|
119 |
+
### Hyperparameters
|
120 |
+
|
121 |
+
All models were trained using the same hyperparameters:
|
122 |
+
|
123 |
+
```python
|
124 |
+
{
|
125 |
+
"num_train_epochs": 1,
|
126 |
+
"adam_beta1": 0.9,
|
127 |
+
"adam_beta2": 0.999,
|
128 |
+
"batch_size": 8,
|
129 |
+
"adam_epsilon": 1e-08
|
130 |
+
"optim": "adamw_torch" # the optimizer (AdamW)
|
131 |
+
"learning_rate": 5e-05, # (LR)
|
132 |
+
"lr_scheduler_type": "linear", # scheduler type for LR
|
133 |
+
"seed": 42, # seed for PyTorch RNG-generator.
|
134 |
+
}
|
135 |
+
```
|
136 |
+
|
137 |
+
### Metrics
|
138 |
+
|
139 |
+
Metrics can be found at https://wandb.ai/idatt2900-072/IDATT2900-072.
|
140 |
+
|
141 |
+
|
142 |
+
In-domain performance of wiki-detectors:
|
143 |
+
|
144 |
+
| Base model | Accuracy | Precision | Recall | F1-score |
|
145 |
+
|-------------|----------|-----------|--------|----------|
|
146 |
+
| Bloomz-560m | 0.973 | *1.000 | 0.945 | 0.972 |
|
147 |
+
| Bloomz-1b7 | 0.972 | *1.000 | 0.945 | 0.972 |
|
148 |
+
| Bloomz-3b | *1.000 | *1.000 | *1.000 | *1.000 |
|
149 |
+
| RoBERTa | 0.998 | 0.999 | 0.997 | 0.998 |
|
150 |
+
|
151 |
+
|
152 |
+
In-domain peformance of academic-detectors:
|
153 |
+
|
154 |
+
| Base model | Accuracy | Precision | Recall | F1-score |
|
155 |
+
|-------------|----------|-----------|--------|----------|
|
156 |
+
| Bloomz-560m | 0.964 | 0.963 | 0.965 | 0.964 |
|
157 |
+
| Bloomz-1b7 | 0.946 | 0.941 | 0.951 | 0.946 |
|
158 |
+
| Bloomz-3b | *0.984 | *0.983 | 0.985 | *0.984 |
|
159 |
+
| RoBERTa | 0.982 | 0.968 | *0.997 | 0.982 |
|
160 |
+
|
161 |
+
|
162 |
+
F1-scores of the mixed-detectors on all three datasets:
|
163 |
+
|
164 |
+
| Base model | Mixed | Wiki | CRA |
|
165 |
+
|-------------|--------|--------|--------|
|
166 |
+
| Bloomz-560m | 0.948 | 0.972 | *0.848 |
|
167 |
+
| Bloomz-1b7 | 0.929 | 0.964 | 0.816 |
|
168 |
+
| Bloomz-3b | 0.988 | 0.996 | 0.772 |
|
169 |
+
| RoBERTa | *0.993 | *0.997 | 0.829 |
|
170 |
+
|
171 |
+
|
172 |
+
## Credits
|
173 |
+
|
174 |
+
- [GPT-wiki-intro](https://huggingface.co/datasets/aadityaubhat/GPT-wiki-intro), by Aaditya Bhat
|
175 |
+
- [arxiv-abstracts-2021](https://huggingface.co/datasets/gfissore/arxiv-abstracts-2021), by Giancarlo
|
176 |
+
- [Bloomz](bigscience/bloomz), by BigScience
|
177 |
+
- [RoBERTa](https://huggingface.co/roberta-base), by Liu et. al.
|
178 |
+
|
179 |
+
|
180 |
+
## Citation
|
181 |
+
|
182 |
+
Please use the following citation:
|
183 |
+
|
184 |
+
```
|
185 |
+
@misc {sivesind_2023,
|
186 |
+
author = { {Nicolai Thorer Sivesind} and {Andreas Bentzen Winje} },
|
187 |
+
title = { Machine-generated text-detection by fine-tuning of language models },
|
188 |
+
url = { https://huggingface.co/andreas122001/roberta-academic-detector }
|
189 |
+
year = 2023,
|
190 |
+
publisher = { Hugging Face }
|
191 |
+
}
|
192 |
+
```
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigscience/bloomz-1b7",
|
3 |
+
"apply_residual_connection_post_layernorm": false,
|
4 |
+
"architectures": [
|
5 |
+
"BloomForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"attention_softmax_in_fp32": true,
|
9 |
+
"bias_dropout_fusion": true,
|
10 |
+
"bos_token_id": 1,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 2048,
|
14 |
+
"id2label": {
|
15 |
+
"0": "human-produced",
|
16 |
+
"1": "machine-generated"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"label2id": {
|
20 |
+
"human-produced": 0,
|
21 |
+
"machine-generated": 1
|
22 |
+
},
|
23 |
+
"layer_norm_epsilon": 1e-05,
|
24 |
+
"masked_softmax_fusion": true,
|
25 |
+
"model_type": "bloom",
|
26 |
+
"n_head": 16,
|
27 |
+
"n_inner": null,
|
28 |
+
"n_layer": 24,
|
29 |
+
"offset_alibi": 100,
|
30 |
+
"pad_token_id": 3,
|
31 |
+
"pretraining_tp": 2,
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"seq_length": 4096,
|
34 |
+
"skip_bias_add": true,
|
35 |
+
"skip_bias_add_qkv": false,
|
36 |
+
"slow_but_exact": false,
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.26.1",
|
39 |
+
"unk_token_id": 0,
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 250880
|
42 |
+
}
|
gitattributes
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d944d6907131fce4941c1b98753b6c6304e9268438faa750202a7ed282544a4
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19c575370b6179b490f435df9c74d0ea7aabd16f264cf932690c39af9fca6ebb
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa18280d17cb2240255ae226f2e8ce87bc72ae3fb9f7044d0238395b4d8b7a33
|
3 |
+
size 14500707
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"name_or_path": "bigscience/bloomz-1b7",
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"padding_side": "left",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"tokenizer_class": "BloomTokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,922 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 1750,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 4.9971428571428576e-05,
|
13 |
+
"loss": 2.5589,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.02,
|
18 |
+
"learning_rate": 4.9e-05,
|
19 |
+
"loss": 4.0188,
|
20 |
+
"step": 35
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.02,
|
24 |
+
"eval_accuracy": 0.5033333333333333,
|
25 |
+
"eval_f1": 0.015852047556142668,
|
26 |
+
"eval_loss": 1.71467924118042,
|
27 |
+
"eval_precision": 0.8571428571428571,
|
28 |
+
"eval_recall": 0.008,
|
29 |
+
"eval_runtime": 245.0349,
|
30 |
+
"eval_samples_per_second": 12.243,
|
31 |
+
"eval_steps_per_second": 1.53,
|
32 |
+
"step": 35
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.04,
|
36 |
+
"learning_rate": 4.8e-05,
|
37 |
+
"loss": 1.1269,
|
38 |
+
"step": 70
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.04,
|
42 |
+
"eval_accuracy": 0.5356666666666666,
|
43 |
+
"eval_f1": 0.15932407966203982,
|
44 |
+
"eval_loss": 0.8176602125167847,
|
45 |
+
"eval_precision": 0.8407643312101911,
|
46 |
+
"eval_recall": 0.088,
|
47 |
+
"eval_runtime": 245.0774,
|
48 |
+
"eval_samples_per_second": 12.241,
|
49 |
+
"eval_steps_per_second": 1.53,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.06,
|
54 |
+
"learning_rate": 4.7e-05,
|
55 |
+
"loss": 0.9901,
|
56 |
+
"step": 105
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.06,
|
60 |
+
"eval_accuracy": 0.5946666666666667,
|
61 |
+
"eval_f1": 0.36401673640167365,
|
62 |
+
"eval_loss": 1.4929765462875366,
|
63 |
+
"eval_precision": 0.8446601941747572,
|
64 |
+
"eval_recall": 0.232,
|
65 |
+
"eval_runtime": 244.7538,
|
66 |
+
"eval_samples_per_second": 12.257,
|
67 |
+
"eval_steps_per_second": 1.532,
|
68 |
+
"step": 105
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.08,
|
72 |
+
"learning_rate": 4.600000000000001e-05,
|
73 |
+
"loss": 1.2113,
|
74 |
+
"step": 140
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.08,
|
78 |
+
"eval_accuracy": 0.619,
|
79 |
+
"eval_f1": 0.7197842608482471,
|
80 |
+
"eval_loss": 0.744438648223877,
|
81 |
+
"eval_precision": 0.5692128732066692,
|
82 |
+
"eval_recall": 0.9786666666666667,
|
83 |
+
"eval_runtime": 244.6225,
|
84 |
+
"eval_samples_per_second": 12.264,
|
85 |
+
"eval_steps_per_second": 1.533,
|
86 |
+
"step": 140
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.1,
|
90 |
+
"learning_rate": 4.5e-05,
|
91 |
+
"loss": 0.7836,
|
92 |
+
"step": 175
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.1,
|
96 |
+
"eval_accuracy": 0.689,
|
97 |
+
"eval_f1": 0.5959289735816371,
|
98 |
+
"eval_loss": 0.6166332364082336,
|
99 |
+
"eval_precision": 0.8504326328800988,
|
100 |
+
"eval_recall": 0.45866666666666667,
|
101 |
+
"eval_runtime": 244.7744,
|
102 |
+
"eval_samples_per_second": 12.256,
|
103 |
+
"eval_steps_per_second": 1.532,
|
104 |
+
"step": 175
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.12,
|
108 |
+
"learning_rate": 4.4000000000000006e-05,
|
109 |
+
"loss": 0.7519,
|
110 |
+
"step": 210
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.12,
|
114 |
+
"eval_accuracy": 0.775,
|
115 |
+
"eval_f1": 0.7330960854092525,
|
116 |
+
"eval_loss": 0.6699690818786621,
|
117 |
+
"eval_precision": 0.9008746355685131,
|
118 |
+
"eval_recall": 0.618,
|
119 |
+
"eval_runtime": 245.4062,
|
120 |
+
"eval_samples_per_second": 12.225,
|
121 |
+
"eval_steps_per_second": 1.528,
|
122 |
+
"step": 210
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.14,
|
126 |
+
"learning_rate": 4.3e-05,
|
127 |
+
"loss": 1.0327,
|
128 |
+
"step": 245
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.14,
|
132 |
+
"eval_accuracy": 0.7083333333333334,
|
133 |
+
"eval_f1": 0.5988078862906923,
|
134 |
+
"eval_loss": 0.5815353393554688,
|
135 |
+
"eval_precision": 0.9588839941262849,
|
136 |
+
"eval_recall": 0.43533333333333335,
|
137 |
+
"eval_runtime": 245.1736,
|
138 |
+
"eval_samples_per_second": 12.236,
|
139 |
+
"eval_steps_per_second": 1.53,
|
140 |
+
"step": 245
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.16,
|
144 |
+
"learning_rate": 4.2e-05,
|
145 |
+
"loss": 0.7039,
|
146 |
+
"step": 280
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.16,
|
150 |
+
"eval_accuracy": 0.7043333333333334,
|
151 |
+
"eval_f1": 0.5891616489115331,
|
152 |
+
"eval_loss": 1.3649965524673462,
|
153 |
+
"eval_precision": 0.9650986342943855,
|
154 |
+
"eval_recall": 0.424,
|
155 |
+
"eval_runtime": 247.043,
|
156 |
+
"eval_samples_per_second": 12.144,
|
157 |
+
"eval_steps_per_second": 1.518,
|
158 |
+
"step": 280
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.18,
|
162 |
+
"learning_rate": 4.1e-05,
|
163 |
+
"loss": 1.26,
|
164 |
+
"step": 315
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.18,
|
168 |
+
"eval_accuracy": 0.7916666666666666,
|
169 |
+
"eval_f1": 0.7464503042596349,
|
170 |
+
"eval_loss": 0.6255013942718506,
|
171 |
+
"eval_precision": 0.9533678756476683,
|
172 |
+
"eval_recall": 0.6133333333333333,
|
173 |
+
"eval_runtime": 245.1858,
|
174 |
+
"eval_samples_per_second": 12.236,
|
175 |
+
"eval_steps_per_second": 1.529,
|
176 |
+
"step": 315
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.2,
|
180 |
+
"learning_rate": 4e-05,
|
181 |
+
"loss": 0.5196,
|
182 |
+
"step": 350
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.2,
|
186 |
+
"eval_accuracy": 0.855,
|
187 |
+
"eval_f1": 0.8476357267950964,
|
188 |
+
"eval_loss": 0.4524073004722595,
|
189 |
+
"eval_precision": 0.8929889298892989,
|
190 |
+
"eval_recall": 0.8066666666666666,
|
191 |
+
"eval_runtime": 244.8477,
|
192 |
+
"eval_samples_per_second": 12.253,
|
193 |
+
"eval_steps_per_second": 1.532,
|
194 |
+
"step": 350
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.22,
|
198 |
+
"learning_rate": 3.9000000000000006e-05,
|
199 |
+
"loss": 0.7179,
|
200 |
+
"step": 385
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.22,
|
204 |
+
"eval_accuracy": 0.795,
|
205 |
+
"eval_f1": 0.76409666283084,
|
206 |
+
"eval_loss": 0.6408818960189819,
|
207 |
+
"eval_precision": 0.8997289972899729,
|
208 |
+
"eval_recall": 0.664,
|
209 |
+
"eval_runtime": 244.8569,
|
210 |
+
"eval_samples_per_second": 12.252,
|
211 |
+
"eval_steps_per_second": 1.532,
|
212 |
+
"step": 385
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.24,
|
216 |
+
"learning_rate": 3.8e-05,
|
217 |
+
"loss": 0.7823,
|
218 |
+
"step": 420
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.24,
|
222 |
+
"eval_accuracy": 0.821,
|
223 |
+
"eval_f1": 0.7869892899643,
|
224 |
+
"eval_loss": 0.4732283651828766,
|
225 |
+
"eval_precision": 0.9715964740450539,
|
226 |
+
"eval_recall": 0.6613333333333333,
|
227 |
+
"eval_runtime": 244.9263,
|
228 |
+
"eval_samples_per_second": 12.249,
|
229 |
+
"eval_steps_per_second": 1.531,
|
230 |
+
"step": 420
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.26,
|
234 |
+
"learning_rate": 3.7e-05,
|
235 |
+
"loss": 0.2816,
|
236 |
+
"step": 455
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.26,
|
240 |
+
"eval_accuracy": 0.89,
|
241 |
+
"eval_f1": 0.8825622775800712,
|
242 |
+
"eval_loss": 0.5548559427261353,
|
243 |
+
"eval_precision": 0.9465648854961832,
|
244 |
+
"eval_recall": 0.8266666666666667,
|
245 |
+
"eval_runtime": 245.0027,
|
246 |
+
"eval_samples_per_second": 12.245,
|
247 |
+
"eval_steps_per_second": 1.531,
|
248 |
+
"step": 455
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.28,
|
252 |
+
"learning_rate": 3.6e-05,
|
253 |
+
"loss": 0.3043,
|
254 |
+
"step": 490
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.28,
|
258 |
+
"eval_accuracy": 0.8976666666666666,
|
259 |
+
"eval_f1": 0.8971524288107202,
|
260 |
+
"eval_loss": 0.48737743496894836,
|
261 |
+
"eval_precision": 0.9016835016835016,
|
262 |
+
"eval_recall": 0.8926666666666667,
|
263 |
+
"eval_runtime": 245.4898,
|
264 |
+
"eval_samples_per_second": 12.22,
|
265 |
+
"eval_steps_per_second": 1.528,
|
266 |
+
"step": 490
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.3,
|
270 |
+
"learning_rate": 3.5e-05,
|
271 |
+
"loss": 0.8005,
|
272 |
+
"step": 525
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.3,
|
276 |
+
"eval_accuracy": 0.8443333333333334,
|
277 |
+
"eval_f1": 0.8613831997625407,
|
278 |
+
"eval_loss": 0.899199366569519,
|
279 |
+
"eval_precision": 0.7763509898341359,
|
280 |
+
"eval_recall": 0.9673333333333334,
|
281 |
+
"eval_runtime": 245.655,
|
282 |
+
"eval_samples_per_second": 12.212,
|
283 |
+
"eval_steps_per_second": 1.527,
|
284 |
+
"step": 525
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.32,
|
288 |
+
"learning_rate": 3.4000000000000007e-05,
|
289 |
+
"loss": 0.5206,
|
290 |
+
"step": 560
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.32,
|
294 |
+
"eval_accuracy": 0.881,
|
295 |
+
"eval_f1": 0.8879824286162535,
|
296 |
+
"eval_loss": 0.5689557194709778,
|
297 |
+
"eval_precision": 0.8387670420865442,
|
298 |
+
"eval_recall": 0.9433333333333334,
|
299 |
+
"eval_runtime": 245.8808,
|
300 |
+
"eval_samples_per_second": 12.201,
|
301 |
+
"eval_steps_per_second": 1.525,
|
302 |
+
"step": 560
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 0.34,
|
306 |
+
"learning_rate": 3.3e-05,
|
307 |
+
"loss": 0.2982,
|
308 |
+
"step": 595
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.34,
|
312 |
+
"eval_accuracy": 0.8383333333333334,
|
313 |
+
"eval_f1": 0.8556977090151742,
|
314 |
+
"eval_loss": 1.3064663410186768,
|
315 |
+
"eval_precision": 0.7727028479312198,
|
316 |
+
"eval_recall": 0.9586666666666667,
|
317 |
+
"eval_runtime": 244.8259,
|
318 |
+
"eval_samples_per_second": 12.254,
|
319 |
+
"eval_steps_per_second": 1.532,
|
320 |
+
"step": 595
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 0.36,
|
324 |
+
"learning_rate": 3.2000000000000005e-05,
|
325 |
+
"loss": 1.159,
|
326 |
+
"step": 630
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.36,
|
330 |
+
"eval_accuracy": 0.8866666666666667,
|
331 |
+
"eval_f1": 0.8924731182795699,
|
332 |
+
"eval_loss": 0.6431537866592407,
|
333 |
+
"eval_precision": 0.8489771359807461,
|
334 |
+
"eval_recall": 0.9406666666666667,
|
335 |
+
"eval_runtime": 244.8113,
|
336 |
+
"eval_samples_per_second": 12.254,
|
337 |
+
"eval_steps_per_second": 1.532,
|
338 |
+
"step": 630
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.38,
|
342 |
+
"learning_rate": 3.1e-05,
|
343 |
+
"loss": 0.4328,
|
344 |
+
"step": 665
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.38,
|
348 |
+
"eval_accuracy": 0.8996666666666666,
|
349 |
+
"eval_f1": 0.9056130448416432,
|
350 |
+
"eval_loss": 0.4550739824771881,
|
351 |
+
"eval_precision": 0.8549437537004144,
|
352 |
+
"eval_recall": 0.9626666666666667,
|
353 |
+
"eval_runtime": 250.1284,
|
354 |
+
"eval_samples_per_second": 11.994,
|
355 |
+
"eval_steps_per_second": 1.499,
|
356 |
+
"step": 665
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.4,
|
360 |
+
"learning_rate": 3e-05,
|
361 |
+
"loss": 0.4249,
|
362 |
+
"step": 700
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.4,
|
366 |
+
"eval_accuracy": 0.8913333333333333,
|
367 |
+
"eval_f1": 0.8823953823953824,
|
368 |
+
"eval_loss": 0.40748831629753113,
|
369 |
+
"eval_precision": 0.9614779874213837,
|
370 |
+
"eval_recall": 0.8153333333333334,
|
371 |
+
"eval_runtime": 244.9069,
|
372 |
+
"eval_samples_per_second": 12.25,
|
373 |
+
"eval_steps_per_second": 1.531,
|
374 |
+
"step": 700
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.42,
|
378 |
+
"learning_rate": 2.9e-05,
|
379 |
+
"loss": 0.435,
|
380 |
+
"step": 735
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.42,
|
384 |
+
"eval_accuracy": 0.9173333333333333,
|
385 |
+
"eval_f1": 0.9194805194805196,
|
386 |
+
"eval_loss": 0.28212666511535645,
|
387 |
+
"eval_precision": 0.8962025316455696,
|
388 |
+
"eval_recall": 0.944,
|
389 |
+
"eval_runtime": 247.2532,
|
390 |
+
"eval_samples_per_second": 12.133,
|
391 |
+
"eval_steps_per_second": 1.517,
|
392 |
+
"step": 735
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 0.44,
|
396 |
+
"learning_rate": 2.8000000000000003e-05,
|
397 |
+
"loss": 0.2909,
|
398 |
+
"step": 770
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.44,
|
402 |
+
"eval_accuracy": 0.9186666666666666,
|
403 |
+
"eval_f1": 0.9155124653739612,
|
404 |
+
"eval_loss": 0.2652963101863861,
|
405 |
+
"eval_precision": 0.952449567723343,
|
406 |
+
"eval_recall": 0.8813333333333333,
|
407 |
+
"eval_runtime": 244.8465,
|
408 |
+
"eval_samples_per_second": 12.253,
|
409 |
+
"eval_steps_per_second": 1.532,
|
410 |
+
"step": 770
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.46,
|
414 |
+
"learning_rate": 2.7000000000000002e-05,
|
415 |
+
"loss": 0.2164,
|
416 |
+
"step": 805
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.46,
|
420 |
+
"eval_accuracy": 0.908,
|
421 |
+
"eval_f1": 0.911651728553137,
|
422 |
+
"eval_loss": 0.41052377223968506,
|
423 |
+
"eval_precision": 0.8768472906403941,
|
424 |
+
"eval_recall": 0.9493333333333334,
|
425 |
+
"eval_runtime": 244.9871,
|
426 |
+
"eval_samples_per_second": 12.246,
|
427 |
+
"eval_steps_per_second": 1.531,
|
428 |
+
"step": 805
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.48,
|
432 |
+
"learning_rate": 2.6000000000000002e-05,
|
433 |
+
"loss": 0.2741,
|
434 |
+
"step": 840
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.48,
|
438 |
+
"eval_accuracy": 0.9086666666666666,
|
439 |
+
"eval_f1": 0.9023521026372059,
|
440 |
+
"eval_loss": 0.35454556345939636,
|
441 |
+
"eval_precision": 0.9693721286370597,
|
442 |
+
"eval_recall": 0.844,
|
443 |
+
"eval_runtime": 245.5305,
|
444 |
+
"eval_samples_per_second": 12.218,
|
445 |
+
"eval_steps_per_second": 1.527,
|
446 |
+
"step": 840
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.5,
|
450 |
+
"learning_rate": 2.5e-05,
|
451 |
+
"loss": 0.3406,
|
452 |
+
"step": 875
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.5,
|
456 |
+
"eval_accuracy": 0.9306666666666666,
|
457 |
+
"eval_f1": 0.9311258278145697,
|
458 |
+
"eval_loss": 0.2322322428226471,
|
459 |
+
"eval_precision": 0.925,
|
460 |
+
"eval_recall": 0.9373333333333334,
|
461 |
+
"eval_runtime": 244.978,
|
462 |
+
"eval_samples_per_second": 12.246,
|
463 |
+
"eval_steps_per_second": 1.531,
|
464 |
+
"step": 875
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.52,
|
468 |
+
"learning_rate": 2.4e-05,
|
469 |
+
"loss": 0.2471,
|
470 |
+
"step": 910
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.52,
|
474 |
+
"eval_accuracy": 0.9176666666666666,
|
475 |
+
"eval_f1": 0.9146804835924007,
|
476 |
+
"eval_loss": 0.3999188542366028,
|
477 |
+
"eval_precision": 0.9491039426523298,
|
478 |
+
"eval_recall": 0.8826666666666667,
|
479 |
+
"eval_runtime": 246.19,
|
480 |
+
"eval_samples_per_second": 12.186,
|
481 |
+
"eval_steps_per_second": 1.523,
|
482 |
+
"step": 910
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.54,
|
486 |
+
"learning_rate": 2.3000000000000003e-05,
|
487 |
+
"loss": 0.4955,
|
488 |
+
"step": 945
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.54,
|
492 |
+
"eval_accuracy": 0.8633333333333333,
|
493 |
+
"eval_f1": 0.844106463878327,
|
494 |
+
"eval_loss": 0.5945030450820923,
|
495 |
+
"eval_precision": 0.9823008849557522,
|
496 |
+
"eval_recall": 0.74,
|
497 |
+
"eval_runtime": 245.9264,
|
498 |
+
"eval_samples_per_second": 12.199,
|
499 |
+
"eval_steps_per_second": 1.525,
|
500 |
+
"step": 945
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.56,
|
504 |
+
"learning_rate": 2.2000000000000003e-05,
|
505 |
+
"loss": 0.3085,
|
506 |
+
"step": 980
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.56,
|
510 |
+
"eval_accuracy": 0.9136666666666666,
|
511 |
+
"eval_f1": 0.908641975308642,
|
512 |
+
"eval_loss": 0.39902010560035706,
|
513 |
+
"eval_precision": 0.9647940074906367,
|
514 |
+
"eval_recall": 0.8586666666666667,
|
515 |
+
"eval_runtime": 245.3453,
|
516 |
+
"eval_samples_per_second": 12.228,
|
517 |
+
"eval_steps_per_second": 1.528,
|
518 |
+
"step": 980
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 0.58,
|
522 |
+
"learning_rate": 2.1e-05,
|
523 |
+
"loss": 0.513,
|
524 |
+
"step": 1015
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 0.58,
|
528 |
+
"eval_accuracy": 0.9236666666666666,
|
529 |
+
"eval_f1": 0.9236921026324558,
|
530 |
+
"eval_loss": 0.21340703964233398,
|
531 |
+
"eval_precision": 0.9233844103930713,
|
532 |
+
"eval_recall": 0.924,
|
533 |
+
"eval_runtime": 244.8648,
|
534 |
+
"eval_samples_per_second": 12.252,
|
535 |
+
"eval_steps_per_second": 1.531,
|
536 |
+
"step": 1015
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 0.6,
|
540 |
+
"learning_rate": 2e-05,
|
541 |
+
"loss": 0.2576,
|
542 |
+
"step": 1050
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.6,
|
546 |
+
"eval_accuracy": 0.9283333333333333,
|
547 |
+
"eval_f1": 0.9271926854046733,
|
548 |
+
"eval_loss": 0.30752047896385193,
|
549 |
+
"eval_precision": 0.9421885753613214,
|
550 |
+
"eval_recall": 0.9126666666666666,
|
551 |
+
"eval_runtime": 319.7381,
|
552 |
+
"eval_samples_per_second": 9.383,
|
553 |
+
"eval_steps_per_second": 1.173,
|
554 |
+
"step": 1050
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.62,
|
558 |
+
"learning_rate": 1.9e-05,
|
559 |
+
"loss": 0.3558,
|
560 |
+
"step": 1085
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.62,
|
564 |
+
"eval_accuracy": 0.9276666666666666,
|
565 |
+
"eval_f1": 0.9297961824652217,
|
566 |
+
"eval_loss": 0.24874693155288696,
|
567 |
+
"eval_precision": 0.9032055311125079,
|
568 |
+
"eval_recall": 0.958,
|
569 |
+
"eval_runtime": 245.9624,
|
570 |
+
"eval_samples_per_second": 12.197,
|
571 |
+
"eval_steps_per_second": 1.525,
|
572 |
+
"step": 1085
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 0.64,
|
576 |
+
"learning_rate": 1.8e-05,
|
577 |
+
"loss": 0.2618,
|
578 |
+
"step": 1120
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.64,
|
582 |
+
"eval_accuracy": 0.9396666666666667,
|
583 |
+
"eval_f1": 0.9407528641571195,
|
584 |
+
"eval_loss": 0.3159142732620239,
|
585 |
+
"eval_precision": 0.9241157556270096,
|
586 |
+
"eval_recall": 0.958,
|
587 |
+
"eval_runtime": 245.9065,
|
588 |
+
"eval_samples_per_second": 12.2,
|
589 |
+
"eval_steps_per_second": 1.525,
|
590 |
+
"step": 1120
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.66,
|
594 |
+
"learning_rate": 1.7000000000000003e-05,
|
595 |
+
"loss": 0.2992,
|
596 |
+
"step": 1155
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.66,
|
600 |
+
"eval_accuracy": 0.9313333333333333,
|
601 |
+
"eval_f1": 0.9339320076972418,
|
602 |
+
"eval_loss": 0.33460330963134766,
|
603 |
+
"eval_precision": 0.899876390605686,
|
604 |
+
"eval_recall": 0.9706666666666667,
|
605 |
+
"eval_runtime": 245.128,
|
606 |
+
"eval_samples_per_second": 12.239,
|
607 |
+
"eval_steps_per_second": 1.53,
|
608 |
+
"step": 1155
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.68,
|
612 |
+
"learning_rate": 1.6000000000000003e-05,
|
613 |
+
"loss": 0.2474,
|
614 |
+
"step": 1190
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 0.68,
|
618 |
+
"eval_accuracy": 0.9346666666666666,
|
619 |
+
"eval_f1": 0.9332879509870661,
|
620 |
+
"eval_loss": 0.265165776014328,
|
621 |
+
"eval_precision": 0.9534075104311543,
|
622 |
+
"eval_recall": 0.914,
|
623 |
+
"eval_runtime": 245.8947,
|
624 |
+
"eval_samples_per_second": 12.2,
|
625 |
+
"eval_steps_per_second": 1.525,
|
626 |
+
"step": 1190
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.7,
|
630 |
+
"learning_rate": 1.5e-05,
|
631 |
+
"loss": 0.3008,
|
632 |
+
"step": 1225
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.7,
|
636 |
+
"eval_accuracy": 0.9423333333333334,
|
637 |
+
"eval_f1": 0.9421211107393778,
|
638 |
+
"eval_loss": 0.22882609069347382,
|
639 |
+
"eval_precision": 0.9456010745466756,
|
640 |
+
"eval_recall": 0.9386666666666666,
|
641 |
+
"eval_runtime": 245.6581,
|
642 |
+
"eval_samples_per_second": 12.212,
|
643 |
+
"eval_steps_per_second": 1.527,
|
644 |
+
"step": 1225
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 0.72,
|
648 |
+
"learning_rate": 1.4000000000000001e-05,
|
649 |
+
"loss": 0.2605,
|
650 |
+
"step": 1260
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.72,
|
654 |
+
"eval_accuracy": 0.9256666666666666,
|
655 |
+
"eval_f1": 0.9292288162488098,
|
656 |
+
"eval_loss": 0.3908889591693878,
|
657 |
+
"eval_precision": 0.8867353119321624,
|
658 |
+
"eval_recall": 0.976,
|
659 |
+
"eval_runtime": 246.273,
|
660 |
+
"eval_samples_per_second": 12.182,
|
661 |
+
"eval_steps_per_second": 1.523,
|
662 |
+
"step": 1260
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 0.74,
|
666 |
+
"learning_rate": 1.3000000000000001e-05,
|
667 |
+
"loss": 0.2565,
|
668 |
+
"step": 1295
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.74,
|
672 |
+
"eval_accuracy": 0.9313333333333333,
|
673 |
+
"eval_f1": 0.9340588988476314,
|
674 |
+
"eval_loss": 0.39725252985954285,
|
675 |
+
"eval_precision": 0.8983990147783252,
|
676 |
+
"eval_recall": 0.9726666666666667,
|
677 |
+
"eval_runtime": 245.9637,
|
678 |
+
"eval_samples_per_second": 12.197,
|
679 |
+
"eval_steps_per_second": 1.525,
|
680 |
+
"step": 1295
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 0.76,
|
684 |
+
"learning_rate": 1.2e-05,
|
685 |
+
"loss": 0.3269,
|
686 |
+
"step": 1330
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.76,
|
690 |
+
"eval_accuracy": 0.9373333333333334,
|
691 |
+
"eval_f1": 0.936141304347826,
|
692 |
+
"eval_loss": 0.2685074806213379,
|
693 |
+
"eval_precision": 0.9542936288088643,
|
694 |
+
"eval_recall": 0.9186666666666666,
|
695 |
+
"eval_runtime": 245.6322,
|
696 |
+
"eval_samples_per_second": 12.213,
|
697 |
+
"eval_steps_per_second": 1.527,
|
698 |
+
"step": 1330
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.78,
|
702 |
+
"learning_rate": 1.1000000000000001e-05,
|
703 |
+
"loss": 0.2149,
|
704 |
+
"step": 1365
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 0.78,
|
708 |
+
"eval_accuracy": 0.934,
|
709 |
+
"eval_f1": 0.931582584657913,
|
710 |
+
"eval_loss": 0.26127538084983826,
|
711 |
+
"eval_precision": 0.9670014347202296,
|
712 |
+
"eval_recall": 0.8986666666666666,
|
713 |
+
"eval_runtime": 244.9705,
|
714 |
+
"eval_samples_per_second": 12.246,
|
715 |
+
"eval_steps_per_second": 1.531,
|
716 |
+
"step": 1365
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.8,
|
720 |
+
"learning_rate": 1e-05,
|
721 |
+
"loss": 0.204,
|
722 |
+
"step": 1400
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.8,
|
726 |
+
"eval_accuracy": 0.944,
|
727 |
+
"eval_f1": 0.9432048681541583,
|
728 |
+
"eval_loss": 0.22753384709358215,
|
729 |
+
"eval_precision": 0.9567901234567902,
|
730 |
+
"eval_recall": 0.93,
|
731 |
+
"eval_runtime": 246.146,
|
732 |
+
"eval_samples_per_second": 12.188,
|
733 |
+
"eval_steps_per_second": 1.523,
|
734 |
+
"step": 1400
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 0.82,
|
738 |
+
"learning_rate": 9e-06,
|
739 |
+
"loss": 0.165,
|
740 |
+
"step": 1435
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 0.82,
|
744 |
+
"eval_accuracy": 0.9433333333333334,
|
745 |
+
"eval_f1": 0.9422946367956553,
|
746 |
+
"eval_loss": 0.22660386562347412,
|
747 |
+
"eval_precision": 0.9598893499308437,
|
748 |
+
"eval_recall": 0.9253333333333333,
|
749 |
+
"eval_runtime": 244.7679,
|
750 |
+
"eval_samples_per_second": 12.257,
|
751 |
+
"eval_steps_per_second": 1.532,
|
752 |
+
"step": 1435
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.84,
|
756 |
+
"learning_rate": 8.000000000000001e-06,
|
757 |
+
"loss": 0.2662,
|
758 |
+
"step": 1470
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.84,
|
762 |
+
"eval_accuracy": 0.938,
|
763 |
+
"eval_f1": 0.9363449691991785,
|
764 |
+
"eval_loss": 0.2438994199037552,
|
765 |
+
"eval_precision": 0.9620253164556962,
|
766 |
+
"eval_recall": 0.912,
|
767 |
+
"eval_runtime": 246.2921,
|
768 |
+
"eval_samples_per_second": 12.181,
|
769 |
+
"eval_steps_per_second": 1.523,
|
770 |
+
"step": 1470
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.86,
|
774 |
+
"learning_rate": 7.000000000000001e-06,
|
775 |
+
"loss": 0.1704,
|
776 |
+
"step": 1505
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 0.86,
|
780 |
+
"eval_accuracy": 0.9446666666666667,
|
781 |
+
"eval_f1": 0.9449966865473823,
|
782 |
+
"eval_loss": 0.24109722673892975,
|
783 |
+
"eval_precision": 0.9393939393939394,
|
784 |
+
"eval_recall": 0.9506666666666667,
|
785 |
+
"eval_runtime": 244.6596,
|
786 |
+
"eval_samples_per_second": 12.262,
|
787 |
+
"eval_steps_per_second": 1.533,
|
788 |
+
"step": 1505
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.88,
|
792 |
+
"learning_rate": 6e-06,
|
793 |
+
"loss": 0.1694,
|
794 |
+
"step": 1540
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.88,
|
798 |
+
"eval_accuracy": 0.9423333333333334,
|
799 |
+
"eval_f1": 0.9411364409663151,
|
800 |
+
"eval_loss": 0.24637927114963531,
|
801 |
+
"eval_precision": 0.9610840861709521,
|
802 |
+
"eval_recall": 0.922,
|
803 |
+
"eval_runtime": 246.6002,
|
804 |
+
"eval_samples_per_second": 12.165,
|
805 |
+
"eval_steps_per_second": 1.521,
|
806 |
+
"step": 1540
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 0.9,
|
810 |
+
"learning_rate": 5e-06,
|
811 |
+
"loss": 0.2994,
|
812 |
+
"step": 1575
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 0.9,
|
816 |
+
"eval_accuracy": 0.947,
|
817 |
+
"eval_f1": 0.9469469469469469,
|
818 |
+
"eval_loss": 0.22698351740837097,
|
819 |
+
"eval_precision": 0.9478957915831663,
|
820 |
+
"eval_recall": 0.946,
|
821 |
+
"eval_runtime": 244.8716,
|
822 |
+
"eval_samples_per_second": 12.251,
|
823 |
+
"eval_steps_per_second": 1.531,
|
824 |
+
"step": 1575
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 0.92,
|
828 |
+
"learning_rate": 4.000000000000001e-06,
|
829 |
+
"loss": 0.1833,
|
830 |
+
"step": 1610
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.92,
|
834 |
+
"eval_accuracy": 0.9443333333333334,
|
835 |
+
"eval_f1": 0.9438655462184874,
|
836 |
+
"eval_loss": 0.23095431923866272,
|
837 |
+
"eval_precision": 0.951864406779661,
|
838 |
+
"eval_recall": 0.936,
|
839 |
+
"eval_runtime": 245.8383,
|
840 |
+
"eval_samples_per_second": 12.203,
|
841 |
+
"eval_steps_per_second": 1.525,
|
842 |
+
"step": 1610
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.94,
|
846 |
+
"learning_rate": 3e-06,
|
847 |
+
"loss": 0.2646,
|
848 |
+
"step": 1645
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 0.94,
|
852 |
+
"eval_accuracy": 0.9476666666666667,
|
853 |
+
"eval_f1": 0.9484400656814449,
|
854 |
+
"eval_loss": 0.27593639492988586,
|
855 |
+
"eval_precision": 0.9346278317152104,
|
856 |
+
"eval_recall": 0.9626666666666667,
|
857 |
+
"eval_runtime": 244.6822,
|
858 |
+
"eval_samples_per_second": 12.261,
|
859 |
+
"eval_steps_per_second": 1.533,
|
860 |
+
"step": 1645
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 0.96,
|
864 |
+
"learning_rate": 2.0000000000000003e-06,
|
865 |
+
"loss": 0.1927,
|
866 |
+
"step": 1680
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.96,
|
870 |
+
"eval_accuracy": 0.949,
|
871 |
+
"eval_f1": 0.9487437185929648,
|
872 |
+
"eval_loss": 0.2200535088777542,
|
873 |
+
"eval_precision": 0.9535353535353536,
|
874 |
+
"eval_recall": 0.944,
|
875 |
+
"eval_runtime": 245.0433,
|
876 |
+
"eval_samples_per_second": 12.243,
|
877 |
+
"eval_steps_per_second": 1.53,
|
878 |
+
"step": 1680
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.98,
|
882 |
+
"learning_rate": 1.0000000000000002e-06,
|
883 |
+
"loss": 0.2153,
|
884 |
+
"step": 1715
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.98,
|
888 |
+
"eval_accuracy": 0.948,
|
889 |
+
"eval_f1": 0.9477911646586344,
|
890 |
+
"eval_loss": 0.2146720141172409,
|
891 |
+
"eval_precision": 0.9516129032258065,
|
892 |
+
"eval_recall": 0.944,
|
893 |
+
"eval_runtime": 246.1882,
|
894 |
+
"eval_samples_per_second": 12.186,
|
895 |
+
"eval_steps_per_second": 1.523,
|
896 |
+
"step": 1715
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 1.0,
|
900 |
+
"learning_rate": 0.0,
|
901 |
+
"loss": 0.1213,
|
902 |
+
"step": 1750
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 1.0,
|
906 |
+
"eval_accuracy": 0.948,
|
907 |
+
"eval_f1": 0.9478957915831663,
|
908 |
+
"eval_loss": 0.21715900301933289,
|
909 |
+
"eval_precision": 0.9497991967871486,
|
910 |
+
"eval_recall": 0.946,
|
911 |
+
"eval_runtime": 245.0021,
|
912 |
+
"eval_samples_per_second": 12.245,
|
913 |
+
"eval_steps_per_second": 1.531,
|
914 |
+
"step": 1750
|
915 |
+
}
|
916 |
+
],
|
917 |
+
"max_steps": 1750,
|
918 |
+
"num_train_epochs": 1,
|
919 |
+
"total_flos": 5.1979933974528e+16,
|
920 |
+
"trial_name": null,
|
921 |
+
"trial_params": null
|
922 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8f5066a1aa6c965aa1838458494222c8e72724c8035db925110310fd8b651fd
|
3 |
+
size 3451
|