Commit
·
8d3ca06
0
Parent(s):
added model files
Browse files- .gitattributes +35 -0
- config.json +63 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +378 -0
- training_args.bin +3 -0
.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 |
+
*.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
|
32 |
+
*.xz 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
|
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ai_detector_v3/checkpoint-2279",
|
3 |
+
"architectures": [
|
4 |
+
"SwinForImageClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"depths": [
|
8 |
+
2,
|
9 |
+
2,
|
10 |
+
18,
|
11 |
+
2
|
12 |
+
],
|
13 |
+
"drop_path_rate": 0.1,
|
14 |
+
"embed_dim": 128,
|
15 |
+
"encoder_stride": 32,
|
16 |
+
"hidden_act": "gelu",
|
17 |
+
"hidden_dropout_prob": 0.0,
|
18 |
+
"hidden_size": 1024,
|
19 |
+
"id2label": {
|
20 |
+
"0": "ai_gen",
|
21 |
+
"1": "human"
|
22 |
+
},
|
23 |
+
"image_size": 224,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"label2id": {
|
26 |
+
"ai_gen": "0",
|
27 |
+
"human": "1"
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-05,
|
30 |
+
"max_length": 128,
|
31 |
+
"mlp_ratio": 4.0,
|
32 |
+
"model_type": "swin",
|
33 |
+
"num_channels": 3,
|
34 |
+
"num_heads": [
|
35 |
+
4,
|
36 |
+
8,
|
37 |
+
16,
|
38 |
+
32
|
39 |
+
],
|
40 |
+
"num_layers": 4,
|
41 |
+
"out_features": [
|
42 |
+
"stage4"
|
43 |
+
],
|
44 |
+
"out_indices": [
|
45 |
+
4
|
46 |
+
],
|
47 |
+
"padding": "max_length",
|
48 |
+
"patch_size": 4,
|
49 |
+
"path_norm": true,
|
50 |
+
"problem_type": "single_label_classification",
|
51 |
+
"qkv_bias": true,
|
52 |
+
"stage_names": [
|
53 |
+
"stem",
|
54 |
+
"stage1",
|
55 |
+
"stage2",
|
56 |
+
"stage3",
|
57 |
+
"stage4"
|
58 |
+
],
|
59 |
+
"torch_dtype": "float32",
|
60 |
+
"transformers_version": "4.37.2",
|
61 |
+
"use_absolute_embeddings": false,
|
62 |
+
"window_size": 7
|
63 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e954f5bf86d21a1c4dede8181ff3e40325351eb4c922f44c1f1bf58a0fcc9a8d
|
3 |
+
size 347498816
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c625d7fe1497c82195bfc2f77b9ea75760b03c1d9d3d8c898c21ab06879941f5
|
3 |
+
size 694317645
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ff37c3cea923fbefa5b01b7abfbbea3af414549f85e58dbaa254a08ff9b1125
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad9dd5a0fa411f2cd640a1e64a5134f055e290068291f4e9c8e277e93854c697
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,378 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.996,
|
3 |
+
"best_model_checkpoint": "AI_ImageClassification_SDXL/checkpoint-586",
|
4 |
+
"epoch": 0.9995735607675906,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 586,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"learning_rate": 2.840909090909091e-06,
|
14 |
+
"loss": 1.2947,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.03,
|
19 |
+
"learning_rate": 5.681818181818182e-06,
|
20 |
+
"loss": 0.689,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.05,
|
25 |
+
"learning_rate": 8.522727272727273e-06,
|
26 |
+
"loss": 0.2576,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.07,
|
31 |
+
"learning_rate": 1.1363636363636365e-05,
|
32 |
+
"loss": 0.23,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.09,
|
37 |
+
"learning_rate": 1.4204545454545456e-05,
|
38 |
+
"loss": 0.1137,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.1,
|
43 |
+
"learning_rate": 1.7045454545454546e-05,
|
44 |
+
"loss": 0.0554,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.12,
|
49 |
+
"learning_rate": 1.9886363636363638e-05,
|
50 |
+
"loss": 0.059,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.14,
|
55 |
+
"learning_rate": 2.272727272727273e-05,
|
56 |
+
"loss": 0.0583,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.15,
|
61 |
+
"learning_rate": 2.5568181818181817e-05,
|
62 |
+
"loss": 0.0349,
|
63 |
+
"step": 90
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.17,
|
67 |
+
"learning_rate": 2.8409090909090912e-05,
|
68 |
+
"loss": 0.0864,
|
69 |
+
"step": 100
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.19,
|
73 |
+
"learning_rate": 3.125e-05,
|
74 |
+
"loss": 0.0145,
|
75 |
+
"step": 110
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.2,
|
79 |
+
"learning_rate": 3.409090909090909e-05,
|
80 |
+
"loss": 0.0358,
|
81 |
+
"step": 120
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.22,
|
85 |
+
"learning_rate": 3.6931818181818184e-05,
|
86 |
+
"loss": 0.0473,
|
87 |
+
"step": 130
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.24,
|
91 |
+
"learning_rate": 3.9772727272727275e-05,
|
92 |
+
"loss": 0.0253,
|
93 |
+
"step": 140
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.26,
|
97 |
+
"learning_rate": 4.261363636363637e-05,
|
98 |
+
"loss": 0.0574,
|
99 |
+
"step": 150
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.27,
|
103 |
+
"learning_rate": 4.545454545454546e-05,
|
104 |
+
"loss": 0.0403,
|
105 |
+
"step": 160
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.29,
|
109 |
+
"learning_rate": 4.829545454545455e-05,
|
110 |
+
"loss": 0.0481,
|
111 |
+
"step": 170
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.31,
|
115 |
+
"learning_rate": 4.9873577749683945e-05,
|
116 |
+
"loss": 0.0246,
|
117 |
+
"step": 180
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.32,
|
121 |
+
"learning_rate": 4.955752212389381e-05,
|
122 |
+
"loss": 0.0094,
|
123 |
+
"step": 190
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.34,
|
127 |
+
"learning_rate": 4.924146649810367e-05,
|
128 |
+
"loss": 0.0413,
|
129 |
+
"step": 200
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.36,
|
133 |
+
"learning_rate": 4.892541087231353e-05,
|
134 |
+
"loss": 0.0339,
|
135 |
+
"step": 210
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.38,
|
139 |
+
"learning_rate": 4.860935524652339e-05,
|
140 |
+
"loss": 0.0523,
|
141 |
+
"step": 220
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.39,
|
145 |
+
"learning_rate": 4.829329962073325e-05,
|
146 |
+
"loss": 0.0104,
|
147 |
+
"step": 230
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.41,
|
151 |
+
"learning_rate": 4.797724399494311e-05,
|
152 |
+
"loss": 0.0309,
|
153 |
+
"step": 240
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.43,
|
157 |
+
"learning_rate": 4.7661188369152975e-05,
|
158 |
+
"loss": 0.0248,
|
159 |
+
"step": 250
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.44,
|
163 |
+
"learning_rate": 4.734513274336283e-05,
|
164 |
+
"loss": 0.0306,
|
165 |
+
"step": 260
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.46,
|
169 |
+
"learning_rate": 4.70290771175727e-05,
|
170 |
+
"loss": 0.0162,
|
171 |
+
"step": 270
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.48,
|
175 |
+
"learning_rate": 4.6713021491782554e-05,
|
176 |
+
"loss": 0.016,
|
177 |
+
"step": 280
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.49,
|
181 |
+
"learning_rate": 4.639696586599241e-05,
|
182 |
+
"loss": 0.0103,
|
183 |
+
"step": 290
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.51,
|
187 |
+
"learning_rate": 4.608091024020228e-05,
|
188 |
+
"loss": 0.0196,
|
189 |
+
"step": 300
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.53,
|
193 |
+
"learning_rate": 4.576485461441214e-05,
|
194 |
+
"loss": 0.0264,
|
195 |
+
"step": 310
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.55,
|
199 |
+
"learning_rate": 4.5448798988622e-05,
|
200 |
+
"loss": 0.0344,
|
201 |
+
"step": 320
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.56,
|
205 |
+
"learning_rate": 4.5132743362831855e-05,
|
206 |
+
"loss": 0.036,
|
207 |
+
"step": 330
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.58,
|
211 |
+
"learning_rate": 4.4816687737041726e-05,
|
212 |
+
"loss": 0.0082,
|
213 |
+
"step": 340
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.6,
|
217 |
+
"learning_rate": 4.4500632111251584e-05,
|
218 |
+
"loss": 0.0149,
|
219 |
+
"step": 350
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.61,
|
223 |
+
"learning_rate": 4.418457648546144e-05,
|
224 |
+
"loss": 0.0082,
|
225 |
+
"step": 360
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.63,
|
229 |
+
"learning_rate": 4.3868520859671306e-05,
|
230 |
+
"loss": 0.0451,
|
231 |
+
"step": 370
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.65,
|
235 |
+
"learning_rate": 4.355246523388117e-05,
|
236 |
+
"loss": 0.0055,
|
237 |
+
"step": 380
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.67,
|
241 |
+
"learning_rate": 4.323640960809103e-05,
|
242 |
+
"loss": 0.0087,
|
243 |
+
"step": 390
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.68,
|
247 |
+
"learning_rate": 4.2920353982300885e-05,
|
248 |
+
"loss": 0.0052,
|
249 |
+
"step": 400
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.7,
|
253 |
+
"learning_rate": 4.260429835651075e-05,
|
254 |
+
"loss": 0.0033,
|
255 |
+
"step": 410
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.72,
|
259 |
+
"learning_rate": 4.2288242730720607e-05,
|
260 |
+
"loss": 0.0148,
|
261 |
+
"step": 420
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.73,
|
265 |
+
"learning_rate": 4.197218710493047e-05,
|
266 |
+
"loss": 0.0134,
|
267 |
+
"step": 430
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.75,
|
271 |
+
"learning_rate": 4.165613147914033e-05,
|
272 |
+
"loss": 0.0125,
|
273 |
+
"step": 440
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.77,
|
277 |
+
"learning_rate": 4.134007585335019e-05,
|
278 |
+
"loss": 0.0531,
|
279 |
+
"step": 450
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.78,
|
283 |
+
"learning_rate": 4.102402022756005e-05,
|
284 |
+
"loss": 0.0059,
|
285 |
+
"step": 460
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.8,
|
289 |
+
"learning_rate": 4.0707964601769914e-05,
|
290 |
+
"loss": 0.0059,
|
291 |
+
"step": 470
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.82,
|
295 |
+
"learning_rate": 4.039190897597978e-05,
|
296 |
+
"loss": 0.0194,
|
297 |
+
"step": 480
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.84,
|
301 |
+
"learning_rate": 4.0075853350189636e-05,
|
302 |
+
"loss": 0.0111,
|
303 |
+
"step": 490
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.85,
|
307 |
+
"learning_rate": 3.9759797724399494e-05,
|
308 |
+
"loss": 0.0321,
|
309 |
+
"step": 500
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.87,
|
313 |
+
"learning_rate": 3.944374209860936e-05,
|
314 |
+
"loss": 0.0261,
|
315 |
+
"step": 510
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.89,
|
319 |
+
"learning_rate": 3.912768647281922e-05,
|
320 |
+
"loss": 0.0196,
|
321 |
+
"step": 520
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.9,
|
325 |
+
"learning_rate": 3.881163084702908e-05,
|
326 |
+
"loss": 0.0038,
|
327 |
+
"step": 530
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.92,
|
331 |
+
"learning_rate": 3.849557522123894e-05,
|
332 |
+
"loss": 0.0216,
|
333 |
+
"step": 540
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.94,
|
337 |
+
"learning_rate": 3.81795195954488e-05,
|
338 |
+
"loss": 0.0047,
|
339 |
+
"step": 550
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.96,
|
343 |
+
"learning_rate": 3.7863463969658666e-05,
|
344 |
+
"loss": 0.0095,
|
345 |
+
"step": 560
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.97,
|
349 |
+
"learning_rate": 3.754740834386852e-05,
|
350 |
+
"loss": 0.0036,
|
351 |
+
"step": 570
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.99,
|
355 |
+
"learning_rate": 3.723135271807838e-05,
|
356 |
+
"loss": 0.0025,
|
357 |
+
"step": 580
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 1.0,
|
361 |
+
"eval_accuracy": 0.996,
|
362 |
+
"eval_loss": 0.015431854873895645,
|
363 |
+
"eval_runtime": 44.7221,
|
364 |
+
"eval_samples_per_second": 44.721,
|
365 |
+
"eval_steps_per_second": 2.795,
|
366 |
+
"step": 586
|
367 |
+
}
|
368 |
+
],
|
369 |
+
"logging_steps": 10,
|
370 |
+
"max_steps": 1758,
|
371 |
+
"num_input_tokens_seen": 0,
|
372 |
+
"num_train_epochs": 3,
|
373 |
+
"save_steps": 500,
|
374 |
+
"total_flos": 2.9390551738299924e+18,
|
375 |
+
"train_batch_size": 16,
|
376 |
+
"trial_name": null,
|
377 |
+
"trial_params": null
|
378 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9edbd48f74807283cdb5f5493284bc0a2de08fc9ebd74b0ba5b2bb1b9391dc70
|
3 |
+
size 4728
|