Commit
•
7583e89
1
Parent(s):
88794bb
Upload 8 files
Browse files- config.json +50 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +571 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/resnet-18",
|
3 |
+
"architectures": [
|
4 |
+
"ResNetForImageClassification"
|
5 |
+
],
|
6 |
+
"depths": [
|
7 |
+
2,
|
8 |
+
2,
|
9 |
+
2,
|
10 |
+
2
|
11 |
+
],
|
12 |
+
"downsample_in_first_stage": false,
|
13 |
+
"embedding_size": 64,
|
14 |
+
"hidden_act": "relu",
|
15 |
+
"hidden_sizes": [
|
16 |
+
64,
|
17 |
+
128,
|
18 |
+
256,
|
19 |
+
512
|
20 |
+
],
|
21 |
+
"id2label": {
|
22 |
+
"0": "forum",
|
23 |
+
"1": "general",
|
24 |
+
"2": "marketplace"
|
25 |
+
},
|
26 |
+
"label2id": {
|
27 |
+
"forum": "0",
|
28 |
+
"general": "1",
|
29 |
+
"marketplace": "2"
|
30 |
+
},
|
31 |
+
"layer_type": "basic",
|
32 |
+
"model_type": "resnet",
|
33 |
+
"num_channels": 3,
|
34 |
+
"out_features": [
|
35 |
+
"stage4"
|
36 |
+
],
|
37 |
+
"out_indices": [
|
38 |
+
4
|
39 |
+
],
|
40 |
+
"problem_type": "single_label_classification",
|
41 |
+
"stage_names": [
|
42 |
+
"stem",
|
43 |
+
"stage1",
|
44 |
+
"stage2",
|
45 |
+
"stage3",
|
46 |
+
"stage4"
|
47 |
+
],
|
48 |
+
"torch_dtype": "float32",
|
49 |
+
"transformers_version": "4.29.2"
|
50 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b2a231ff7c6f6c2c9ec3904e67b384be47e20f1733256b888dc3fb39983ece4
|
3 |
+
size 89460869
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_pct": 0.875,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.485,
|
8 |
+
0.456,
|
9 |
+
0.406
|
10 |
+
],
|
11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.229,
|
14 |
+
0.224,
|
15 |
+
0.225
|
16 |
+
],
|
17 |
+
"resample": 3,
|
18 |
+
"rescale_factor": 0.00392156862745098,
|
19 |
+
"size": {
|
20 |
+
"shortest_edge": 224
|
21 |
+
}
|
22 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32c9525a35996799fe135773d47a535c9260963336836cddaef648f9a00ea46d
|
3 |
+
size 44793653
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7771edaf10b42494826c221f91314e438076cff6958d5a6e4f4627e3b6ae6d37
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cf093da31c7733407244481c89a6115a0bdc1e0fc43240dbdf23373234ae61e
|
3 |
+
size 627
|
trainer_state.json
ADDED
@@ -0,0 +1,571 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7777777777777778,
|
3 |
+
"best_model_checkpoint": "CIRCL_website_classifier\\checkpoint-658",
|
4 |
+
"epoch": 15.0,
|
5 |
+
"global_step": 705,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.21,
|
12 |
+
"learning_rate": 7.042253521126762e-06,
|
13 |
+
"loss": 0.6238,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.43,
|
18 |
+
"learning_rate": 1.4084507042253523e-05,
|
19 |
+
"loss": 0.5542,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.64,
|
24 |
+
"learning_rate": 2.112676056338028e-05,
|
25 |
+
"loss": 0.4952,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.85,
|
30 |
+
"learning_rate": 2.8169014084507046e-05,
|
31 |
+
"loss": 0.5278,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.0,
|
36 |
+
"eval_accuracy": 0.7160493827160493,
|
37 |
+
"eval_loss": 0.7332170009613037,
|
38 |
+
"eval_runtime": 3.93,
|
39 |
+
"eval_samples_per_second": 20.611,
|
40 |
+
"eval_steps_per_second": 1.527,
|
41 |
+
"step": 47
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 1.06,
|
45 |
+
"learning_rate": 3.5211267605633805e-05,
|
46 |
+
"loss": 0.4947,
|
47 |
+
"step": 50
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 1.28,
|
51 |
+
"learning_rate": 4.225352112676056e-05,
|
52 |
+
"loss": 0.4824,
|
53 |
+
"step": 60
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.49,
|
57 |
+
"learning_rate": 4.929577464788733e-05,
|
58 |
+
"loss": 0.4869,
|
59 |
+
"step": 70
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 1.7,
|
63 |
+
"learning_rate": 4.929022082018927e-05,
|
64 |
+
"loss": 0.5236,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.91,
|
69 |
+
"learning_rate": 4.850157728706625e-05,
|
70 |
+
"loss": 0.473,
|
71 |
+
"step": 90
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 2.0,
|
75 |
+
"eval_accuracy": 0.691358024691358,
|
76 |
+
"eval_loss": 0.7856547832489014,
|
77 |
+
"eval_runtime": 4.0912,
|
78 |
+
"eval_samples_per_second": 19.799,
|
79 |
+
"eval_steps_per_second": 1.467,
|
80 |
+
"step": 94
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.13,
|
84 |
+
"learning_rate": 4.771293375394322e-05,
|
85 |
+
"loss": 0.4583,
|
86 |
+
"step": 100
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.34,
|
90 |
+
"learning_rate": 4.6924290220820195e-05,
|
91 |
+
"loss": 0.5197,
|
92 |
+
"step": 110
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 2.55,
|
96 |
+
"learning_rate": 4.6135646687697165e-05,
|
97 |
+
"loss": 0.4843,
|
98 |
+
"step": 120
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 2.77,
|
102 |
+
"learning_rate": 4.5347003154574134e-05,
|
103 |
+
"loss": 0.519,
|
104 |
+
"step": 130
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.98,
|
108 |
+
"learning_rate": 4.4558359621451104e-05,
|
109 |
+
"loss": 0.5199,
|
110 |
+
"step": 140
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 3.0,
|
114 |
+
"eval_accuracy": 0.7037037037037037,
|
115 |
+
"eval_loss": 0.6900804042816162,
|
116 |
+
"eval_runtime": 4.0734,
|
117 |
+
"eval_samples_per_second": 19.885,
|
118 |
+
"eval_steps_per_second": 1.473,
|
119 |
+
"step": 141
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 3.19,
|
123 |
+
"learning_rate": 4.376971608832808e-05,
|
124 |
+
"loss": 0.489,
|
125 |
+
"step": 150
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 3.4,
|
129 |
+
"learning_rate": 4.298107255520505e-05,
|
130 |
+
"loss": 0.481,
|
131 |
+
"step": 160
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 3.62,
|
135 |
+
"learning_rate": 4.219242902208202e-05,
|
136 |
+
"loss": 0.5719,
|
137 |
+
"step": 170
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 3.83,
|
141 |
+
"learning_rate": 4.140378548895899e-05,
|
142 |
+
"loss": 0.578,
|
143 |
+
"step": 180
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 4.0,
|
147 |
+
"eval_accuracy": 0.7160493827160493,
|
148 |
+
"eval_loss": 0.6246393918991089,
|
149 |
+
"eval_runtime": 4.3226,
|
150 |
+
"eval_samples_per_second": 18.739,
|
151 |
+
"eval_steps_per_second": 1.388,
|
152 |
+
"step": 188
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 4.04,
|
156 |
+
"learning_rate": 4.0615141955835965e-05,
|
157 |
+
"loss": 0.6731,
|
158 |
+
"step": 190
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 4.26,
|
162 |
+
"learning_rate": 3.982649842271294e-05,
|
163 |
+
"loss": 0.6082,
|
164 |
+
"step": 200
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 4.47,
|
168 |
+
"learning_rate": 3.903785488958991e-05,
|
169 |
+
"loss": 0.628,
|
170 |
+
"step": 210
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 4.68,
|
174 |
+
"learning_rate": 3.824921135646688e-05,
|
175 |
+
"loss": 0.6112,
|
176 |
+
"step": 220
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 4.89,
|
180 |
+
"learning_rate": 3.746056782334385e-05,
|
181 |
+
"loss": 0.5931,
|
182 |
+
"step": 230
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 5.0,
|
186 |
+
"eval_accuracy": 0.6172839506172839,
|
187 |
+
"eval_loss": 0.7297191619873047,
|
188 |
+
"eval_runtime": 4.3049,
|
189 |
+
"eval_samples_per_second": 18.816,
|
190 |
+
"eval_steps_per_second": 1.394,
|
191 |
+
"step": 235
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 5.11,
|
195 |
+
"learning_rate": 3.667192429022082e-05,
|
196 |
+
"loss": 0.5872,
|
197 |
+
"step": 240
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 5.32,
|
201 |
+
"learning_rate": 3.5883280757097795e-05,
|
202 |
+
"loss": 0.5647,
|
203 |
+
"step": 250
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 5.53,
|
207 |
+
"learning_rate": 3.5094637223974765e-05,
|
208 |
+
"loss": 0.6125,
|
209 |
+
"step": 260
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 5.74,
|
213 |
+
"learning_rate": 3.4305993690851734e-05,
|
214 |
+
"loss": 0.6125,
|
215 |
+
"step": 270
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 5.96,
|
219 |
+
"learning_rate": 3.351735015772871e-05,
|
220 |
+
"loss": 0.567,
|
221 |
+
"step": 280
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 6.0,
|
225 |
+
"eval_accuracy": 0.7037037037037037,
|
226 |
+
"eval_loss": 0.7199741005897522,
|
227 |
+
"eval_runtime": 4.5208,
|
228 |
+
"eval_samples_per_second": 17.917,
|
229 |
+
"eval_steps_per_second": 1.327,
|
230 |
+
"step": 282
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 6.17,
|
234 |
+
"learning_rate": 3.272870662460568e-05,
|
235 |
+
"loss": 0.5294,
|
236 |
+
"step": 290
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 6.38,
|
240 |
+
"learning_rate": 3.194006309148265e-05,
|
241 |
+
"loss": 0.6032,
|
242 |
+
"step": 300
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 6.6,
|
246 |
+
"learning_rate": 3.1151419558359626e-05,
|
247 |
+
"loss": 0.5943,
|
248 |
+
"step": 310
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 6.81,
|
252 |
+
"learning_rate": 3.0362776025236596e-05,
|
253 |
+
"loss": 0.5512,
|
254 |
+
"step": 320
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 7.0,
|
258 |
+
"eval_accuracy": 0.7283950617283951,
|
259 |
+
"eval_loss": 0.6853248476982117,
|
260 |
+
"eval_runtime": 4.5083,
|
261 |
+
"eval_samples_per_second": 17.967,
|
262 |
+
"eval_steps_per_second": 1.331,
|
263 |
+
"step": 329
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 7.02,
|
267 |
+
"learning_rate": 2.9574132492113565e-05,
|
268 |
+
"loss": 0.5808,
|
269 |
+
"step": 330
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 7.23,
|
273 |
+
"learning_rate": 2.8785488958990535e-05,
|
274 |
+
"loss": 0.5226,
|
275 |
+
"step": 340
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 7.45,
|
279 |
+
"learning_rate": 2.7996845425867508e-05,
|
280 |
+
"loss": 0.5454,
|
281 |
+
"step": 350
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 7.66,
|
285 |
+
"learning_rate": 2.7208201892744477e-05,
|
286 |
+
"loss": 0.5752,
|
287 |
+
"step": 360
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 7.87,
|
291 |
+
"learning_rate": 2.6419558359621453e-05,
|
292 |
+
"loss": 0.529,
|
293 |
+
"step": 370
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 8.0,
|
297 |
+
"eval_accuracy": 0.7037037037037037,
|
298 |
+
"eval_loss": 0.7038930058479309,
|
299 |
+
"eval_runtime": 4.4325,
|
300 |
+
"eval_samples_per_second": 18.274,
|
301 |
+
"eval_steps_per_second": 1.354,
|
302 |
+
"step": 376
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 8.09,
|
306 |
+
"learning_rate": 2.5630914826498426e-05,
|
307 |
+
"loss": 0.4872,
|
308 |
+
"step": 380
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 8.3,
|
312 |
+
"learning_rate": 2.4842271293375396e-05,
|
313 |
+
"loss": 0.548,
|
314 |
+
"step": 390
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 8.51,
|
318 |
+
"learning_rate": 2.405362776025237e-05,
|
319 |
+
"loss": 0.5507,
|
320 |
+
"step": 400
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 8.72,
|
324 |
+
"learning_rate": 2.3264984227129338e-05,
|
325 |
+
"loss": 0.5179,
|
326 |
+
"step": 410
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 8.94,
|
330 |
+
"learning_rate": 2.2476340694006308e-05,
|
331 |
+
"loss": 0.5467,
|
332 |
+
"step": 420
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 9.0,
|
336 |
+
"eval_accuracy": 0.6790123456790124,
|
337 |
+
"eval_loss": 0.8216166496276855,
|
338 |
+
"eval_runtime": 3.9158,
|
339 |
+
"eval_samples_per_second": 20.685,
|
340 |
+
"eval_steps_per_second": 1.532,
|
341 |
+
"step": 423
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 9.15,
|
345 |
+
"learning_rate": 2.1687697160883284e-05,
|
346 |
+
"loss": 0.5055,
|
347 |
+
"step": 430
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 9.36,
|
351 |
+
"learning_rate": 2.0899053627760254e-05,
|
352 |
+
"loss": 0.5338,
|
353 |
+
"step": 440
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 9.57,
|
357 |
+
"learning_rate": 2.0110410094637226e-05,
|
358 |
+
"loss": 0.4838,
|
359 |
+
"step": 450
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 9.79,
|
363 |
+
"learning_rate": 1.9321766561514196e-05,
|
364 |
+
"loss": 0.5182,
|
365 |
+
"step": 460
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 10.0,
|
369 |
+
"learning_rate": 1.853312302839117e-05,
|
370 |
+
"loss": 0.5517,
|
371 |
+
"step": 470
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 10.0,
|
375 |
+
"eval_accuracy": 0.7407407407407407,
|
376 |
+
"eval_loss": 0.7132633328437805,
|
377 |
+
"eval_runtime": 4.247,
|
378 |
+
"eval_samples_per_second": 19.072,
|
379 |
+
"eval_steps_per_second": 1.413,
|
380 |
+
"step": 470
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 10.21,
|
384 |
+
"learning_rate": 1.7744479495268142e-05,
|
385 |
+
"loss": 0.5663,
|
386 |
+
"step": 480
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 10.43,
|
390 |
+
"learning_rate": 1.695583596214511e-05,
|
391 |
+
"loss": 0.527,
|
392 |
+
"step": 490
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 10.64,
|
396 |
+
"learning_rate": 1.616719242902208e-05,
|
397 |
+
"loss": 0.4708,
|
398 |
+
"step": 500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 10.85,
|
402 |
+
"learning_rate": 1.5378548895899054e-05,
|
403 |
+
"loss": 0.4917,
|
404 |
+
"step": 510
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 11.0,
|
408 |
+
"eval_accuracy": 0.7283950617283951,
|
409 |
+
"eval_loss": 0.7398880124092102,
|
410 |
+
"eval_runtime": 5.0919,
|
411 |
+
"eval_samples_per_second": 15.908,
|
412 |
+
"eval_steps_per_second": 1.178,
|
413 |
+
"step": 517
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 11.06,
|
417 |
+
"learning_rate": 1.4589905362776027e-05,
|
418 |
+
"loss": 0.5304,
|
419 |
+
"step": 520
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 11.28,
|
423 |
+
"learning_rate": 1.3801261829652998e-05,
|
424 |
+
"loss": 0.537,
|
425 |
+
"step": 530
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 11.49,
|
429 |
+
"learning_rate": 1.3012618296529969e-05,
|
430 |
+
"loss": 0.4953,
|
431 |
+
"step": 540
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 11.7,
|
435 |
+
"learning_rate": 1.222397476340694e-05,
|
436 |
+
"loss": 0.4726,
|
437 |
+
"step": 550
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 11.91,
|
441 |
+
"learning_rate": 1.1435331230283911e-05,
|
442 |
+
"loss": 0.4638,
|
443 |
+
"step": 560
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 12.0,
|
447 |
+
"eval_accuracy": 0.7283950617283951,
|
448 |
+
"eval_loss": 0.7797142863273621,
|
449 |
+
"eval_runtime": 4.4579,
|
450 |
+
"eval_samples_per_second": 18.17,
|
451 |
+
"eval_steps_per_second": 1.346,
|
452 |
+
"step": 564
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 12.13,
|
456 |
+
"learning_rate": 1.0646687697160884e-05,
|
457 |
+
"loss": 0.4413,
|
458 |
+
"step": 570
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 12.34,
|
462 |
+
"learning_rate": 9.858044164037856e-06,
|
463 |
+
"loss": 0.5107,
|
464 |
+
"step": 580
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 12.55,
|
468 |
+
"learning_rate": 9.069400630914827e-06,
|
469 |
+
"loss": 0.4521,
|
470 |
+
"step": 590
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 12.77,
|
474 |
+
"learning_rate": 8.280757097791798e-06,
|
475 |
+
"loss": 0.5601,
|
476 |
+
"step": 600
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 12.98,
|
480 |
+
"learning_rate": 7.492113564668771e-06,
|
481 |
+
"loss": 0.5082,
|
482 |
+
"step": 610
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 13.0,
|
486 |
+
"eval_accuracy": 0.7160493827160493,
|
487 |
+
"eval_loss": 0.6203879714012146,
|
488 |
+
"eval_runtime": 4.284,
|
489 |
+
"eval_samples_per_second": 18.908,
|
490 |
+
"eval_steps_per_second": 1.401,
|
491 |
+
"step": 611
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 13.19,
|
495 |
+
"learning_rate": 6.703470031545741e-06,
|
496 |
+
"loss": 0.5038,
|
497 |
+
"step": 620
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 13.4,
|
501 |
+
"learning_rate": 5.914826498422713e-06,
|
502 |
+
"loss": 0.4934,
|
503 |
+
"step": 630
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 13.62,
|
507 |
+
"learning_rate": 5.1261829652996846e-06,
|
508 |
+
"loss": 0.4834,
|
509 |
+
"step": 640
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 13.83,
|
513 |
+
"learning_rate": 4.337539432176657e-06,
|
514 |
+
"loss": 0.5358,
|
515 |
+
"step": 650
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 14.0,
|
519 |
+
"eval_accuracy": 0.7777777777777778,
|
520 |
+
"eval_loss": 0.626596212387085,
|
521 |
+
"eval_runtime": 4.1062,
|
522 |
+
"eval_samples_per_second": 19.726,
|
523 |
+
"eval_steps_per_second": 1.461,
|
524 |
+
"step": 658
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 14.04,
|
528 |
+
"learning_rate": 3.5488958990536283e-06,
|
529 |
+
"loss": 0.5051,
|
530 |
+
"step": 660
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 14.26,
|
534 |
+
"learning_rate": 2.7602523659305995e-06,
|
535 |
+
"loss": 0.4712,
|
536 |
+
"step": 670
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 14.47,
|
540 |
+
"learning_rate": 1.971608832807571e-06,
|
541 |
+
"loss": 0.4649,
|
542 |
+
"step": 680
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 14.68,
|
546 |
+
"learning_rate": 1.1829652996845425e-06,
|
547 |
+
"loss": 0.4604,
|
548 |
+
"step": 690
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 14.89,
|
552 |
+
"learning_rate": 3.943217665615142e-07,
|
553 |
+
"loss": 0.5267,
|
554 |
+
"step": 700
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 15.0,
|
558 |
+
"eval_accuracy": 0.6790123456790124,
|
559 |
+
"eval_loss": 0.7902321815490723,
|
560 |
+
"eval_runtime": 4.7108,
|
561 |
+
"eval_samples_per_second": 17.194,
|
562 |
+
"eval_steps_per_second": 1.274,
|
563 |
+
"step": 705
|
564 |
+
}
|
565 |
+
],
|
566 |
+
"max_steps": 705,
|
567 |
+
"num_train_epochs": 15,
|
568 |
+
"total_flos": 4.550617827979776e+17,
|
569 |
+
"trial_name": null,
|
570 |
+
"trial_params": null
|
571 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43ac4a09e13a84f09f0bd63e0fc613fec1a6eadc7232ccb73bb79a1ca64438e1
|
3 |
+
size 3963
|