End of training
Browse files- README.md +103 -198
- config.json +39 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- runs/Mar07_14-14-41_32b81e991449/events.out.tfevents.1709820886.32b81e991449.237.0 +3 -0
- special_tokens_map.json +15 -2
- tokenizer.json +6 -1
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,201 +1,106 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
-
|
33 |
-
-
|
34 |
-
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
|
101 |
-
|
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]
|
200 |
-
|
201 |
-
|
|
|
1 |
---
|
2 |
+
license: mit
|
3 |
+
base_model: gpt2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: '130000'
|
8 |
+
results: []
|
9 |
---
|
10 |
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# 130000
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 5.9987
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 0.0005
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 8
|
42 |
+
- total_train_batch_size: 64
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: cosine
|
45 |
+
- num_epochs: 50
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| No log | 0.92 | 3 | 7.0396 |
|
53 |
+
| No log | 1.85 | 6 | 6.5398 |
|
54 |
+
| No log | 2.77 | 9 | 6.3337 |
|
55 |
+
| 6.6916 | 4.0 | 13 | 6.3694 |
|
56 |
+
| 6.6916 | 4.92 | 16 | 6.2945 |
|
57 |
+
| 6.6916 | 5.85 | 19 | 6.3184 |
|
58 |
+
| 6.1092 | 6.77 | 22 | 6.3726 |
|
59 |
+
| 6.1092 | 8.0 | 26 | 6.2948 |
|
60 |
+
| 6.1092 | 8.92 | 29 | 6.3374 |
|
61 |
+
| 6.5151 | 9.85 | 32 | 6.3641 |
|
62 |
+
| 6.5151 | 10.77 | 35 | 6.2335 |
|
63 |
+
| 6.5151 | 12.0 | 39 | 6.1965 |
|
64 |
+
| 5.998 | 12.92 | 42 | 6.0595 |
|
65 |
+
| 5.998 | 13.85 | 45 | 6.0374 |
|
66 |
+
| 5.998 | 14.77 | 48 | 6.0562 |
|
67 |
+
| 5.6623 | 16.0 | 52 | 6.0128 |
|
68 |
+
| 5.6623 | 16.92 | 55 | 5.9999 |
|
69 |
+
| 5.6623 | 17.85 | 58 | 6.0008 |
|
70 |
+
| 5.611 | 18.77 | 61 | 5.9992 |
|
71 |
+
| 5.611 | 20.0 | 65 | 6.0017 |
|
72 |
+
| 5.611 | 20.92 | 68 | 6.0005 |
|
73 |
+
| 5.5519 | 21.85 | 71 | 5.9962 |
|
74 |
+
| 5.5519 | 22.77 | 74 | 5.9964 |
|
75 |
+
| 5.5519 | 24.0 | 78 | 5.9975 |
|
76 |
+
| 5.5841 | 24.92 | 81 | 5.9974 |
|
77 |
+
| 5.5841 | 25.85 | 84 | 6.0000 |
|
78 |
+
| 5.5841 | 26.77 | 87 | 6.0019 |
|
79 |
+
| 5.5582 | 28.0 | 91 | 6.0014 |
|
80 |
+
| 5.5582 | 28.92 | 94 | 6.0016 |
|
81 |
+
| 5.5582 | 29.85 | 97 | 5.9987 |
|
82 |
+
| 5.591 | 30.77 | 100 | 5.9992 |
|
83 |
+
| 5.591 | 32.0 | 104 | 5.9986 |
|
84 |
+
| 5.591 | 32.92 | 107 | 5.9982 |
|
85 |
+
| 5.5638 | 33.85 | 110 | 5.9983 |
|
86 |
+
| 5.5638 | 34.77 | 113 | 5.9987 |
|
87 |
+
| 5.5638 | 36.0 | 117 | 5.9989 |
|
88 |
+
| 5.5683 | 36.92 | 120 | 5.9992 |
|
89 |
+
| 5.5683 | 37.85 | 123 | 5.9995 |
|
90 |
+
| 5.5683 | 38.77 | 126 | 5.9991 |
|
91 |
+
| 5.5628 | 40.0 | 130 | 5.9992 |
|
92 |
+
| 5.5628 | 40.92 | 133 | 5.9992 |
|
93 |
+
| 5.5628 | 41.85 | 136 | 5.9991 |
|
94 |
+
| 5.5628 | 42.77 | 139 | 5.9989 |
|
95 |
+
| 5.5683 | 44.0 | 143 | 5.9987 |
|
96 |
+
| 5.5683 | 44.92 | 146 | 5.9987 |
|
97 |
+
| 5.5683 | 45.85 | 149 | 5.9987 |
|
98 |
+
| 5.5534 | 46.15 | 150 | 5.9987 |
|
99 |
+
|
100 |
+
|
101 |
+
### Framework versions
|
102 |
+
|
103 |
+
- Transformers 4.38.2
|
104 |
+
- Pytorch 2.1.0+cu121
|
105 |
+
- Datasets 2.18.0
|
106 |
+
- Tokenizers 0.15.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 0,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 512,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.38.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 3000
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.38.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:351b48eaff23f55746de242ba034442136e0a6352690b504c07a9fb3393b3097
|
3 |
+
size 352600704
|
runs/Mar07_14-14-41_32b81e991449/events.out.tfevents.1709820886.32b81e991449.237.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04cbf81cda232374dd3345d775dff1cea23fa57077ff50a6e9447d5d18d97601
|
3 |
+
size 20784
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,17 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|endoftext|>"
|
17 |
}
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
tokenizer_config.json
CHANGED
@@ -13,5 +13,6 @@
|
|
13 |
"clean_up_tokenization_spaces": true,
|
14 |
"eos_token": "<|endoftext|>",
|
15 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
16 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
17 |
}
|
|
|
13 |
"clean_up_tokenization_spaces": true,
|
14 |
"eos_token": "<|endoftext|>",
|
15 |
"model_max_length": 1000000000000000019884624838656,
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
18 |
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:271ba549ef8c7caf4fb91fe382f5864e4ddb623c2ad4de01dfdcd7b38cda4ee7
|
3 |
+
size 4920
|