Training in progress, epoch 0
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/Apr25_14-12-12_91b1909d3306/events.out.tfevents.1682433749.91b1909d3306.614.2 +3 -0
- runs/Apr25_14-45-48_91b1909d3306/1682433951.1932008/events.out.tfevents.1682433951.91b1909d3306.614.4 +3 -0
- runs/Apr25_14-45-48_91b1909d3306/events.out.tfevents.1682433951.91b1909d3306.614.3 +3 -0
- train_results.json +8 -0
- trainer_state.json +631 -0
- training_args.bin +1 -1
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.93,
|
3 |
+
"eval_accuracy": 0.9053803339517625,
|
4 |
+
"eval_loss": 0.28196877241134644,
|
5 |
+
"eval_runtime": 9.3286,
|
6 |
+
"eval_samples_per_second": 57.78,
|
7 |
+
"eval_steps_per_second": 7.289,
|
8 |
+
"total_flos": 1.0221236731922227e+18,
|
9 |
+
"train_loss": 0.4434790275817694,
|
10 |
+
"train_runtime": 1771.1031,
|
11 |
+
"train_samples_per_second": 27.356,
|
12 |
+
"train_steps_per_second": 0.486
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.93,
|
3 |
+
"eval_accuracy": 0.9053803339517625,
|
4 |
+
"eval_loss": 0.28196877241134644,
|
5 |
+
"eval_runtime": 9.3286,
|
6 |
+
"eval_samples_per_second": 57.78,
|
7 |
+
"eval_steps_per_second": 7.289
|
8 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 94374989
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:306d4c1e69fdff199fe859e9a020c380cefa50a04382251a6f6e5d98439525db
|
3 |
size 94374989
|
runs/Apr25_14-12-12_91b1909d3306/events.out.tfevents.1682433749.91b1909d3306.614.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53fcf6b7c23e73cd1496630769f5f8c53abb4b6c4ff50a72d63fa64063d84cfc
|
3 |
+
size 411
|
runs/Apr25_14-45-48_91b1909d3306/1682433951.1932008/events.out.tfevents.1682433951.91b1909d3306.614.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d06d16059fbc9f4c5a03e9dc1882c9ed8ca98a428fe17938765c437d19649ca1
|
3 |
+
size 5904
|
runs/Apr25_14-45-48_91b1909d3306/events.out.tfevents.1682433951.91b1909d3306.614.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2212197a706e34368e1a9c02cd87bc31d2b9f384d4a455f03d6a68a5a78c4d3
|
3 |
+
size 5642
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.93,
|
3 |
+
"total_flos": 1.0221236731922227e+18,
|
4 |
+
"train_loss": 0.4434790275817694,
|
5 |
+
"train_runtime": 1771.1031,
|
6 |
+
"train_samples_per_second": 27.356,
|
7 |
+
"train_steps_per_second": 0.486
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,631 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9053803339517625,
|
3 |
+
"best_model_checkpoint": "resnet-50-resnet50_fashion/checkpoint-692",
|
4 |
+
"epoch": 9.933993399339935,
|
5 |
+
"global_step": 860,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.12,
|
12 |
+
"learning_rate": 4.994124559341951e-05,
|
13 |
+
"loss": 0.6959,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.23,
|
18 |
+
"learning_rate": 4.935370152761457e-05,
|
19 |
+
"loss": 0.6903,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.35,
|
24 |
+
"learning_rate": 4.876615746180964e-05,
|
25 |
+
"loss": 0.6815,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.46,
|
30 |
+
"learning_rate": 4.81786133960047e-05,
|
31 |
+
"loss": 0.6753,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.58,
|
36 |
+
"learning_rate": 4.759106933019977e-05,
|
37 |
+
"loss": 0.6688,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.69,
|
42 |
+
"learning_rate": 4.700352526439483e-05,
|
43 |
+
"loss": 0.6613,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.81,
|
48 |
+
"learning_rate": 4.6415981198589895e-05,
|
49 |
+
"loss": 0.6599,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.92,
|
54 |
+
"learning_rate": 4.582843713278496e-05,
|
55 |
+
"loss": 0.6396,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.99,
|
60 |
+
"eval_accuracy": 0.7346938775510204,
|
61 |
+
"eval_loss": 0.7625104188919067,
|
62 |
+
"eval_runtime": 58.978,
|
63 |
+
"eval_samples_per_second": 9.139,
|
64 |
+
"eval_steps_per_second": 1.153,
|
65 |
+
"step": 86
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.04,
|
69 |
+
"learning_rate": 4.524089306698003e-05,
|
70 |
+
"loss": 0.6247,
|
71 |
+
"step": 90
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 1.16,
|
75 |
+
"learning_rate": 4.465334900117509e-05,
|
76 |
+
"loss": 0.628,
|
77 |
+
"step": 100
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 1.27,
|
81 |
+
"learning_rate": 4.4065804935370154e-05,
|
82 |
+
"loss": 0.632,
|
83 |
+
"step": 110
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 1.39,
|
87 |
+
"learning_rate": 4.347826086956522e-05,
|
88 |
+
"loss": 0.6004,
|
89 |
+
"step": 120
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 1.5,
|
93 |
+
"learning_rate": 4.289071680376029e-05,
|
94 |
+
"loss": 0.5901,
|
95 |
+
"step": 130
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.62,
|
99 |
+
"learning_rate": 4.2303172737955346e-05,
|
100 |
+
"loss": 0.5947,
|
101 |
+
"step": 140
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 1.73,
|
105 |
+
"learning_rate": 4.171562867215041e-05,
|
106 |
+
"loss": 0.5753,
|
107 |
+
"step": 150
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.85,
|
111 |
+
"learning_rate": 4.112808460634548e-05,
|
112 |
+
"loss": 0.5851,
|
113 |
+
"step": 160
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 1.96,
|
117 |
+
"learning_rate": 4.0540540540540545e-05,
|
118 |
+
"loss": 0.5646,
|
119 |
+
"step": 170
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 2.0,
|
123 |
+
"eval_accuracy": 0.8348794063079777,
|
124 |
+
"eval_loss": 0.5780991911888123,
|
125 |
+
"eval_runtime": 9.3608,
|
126 |
+
"eval_samples_per_second": 57.581,
|
127 |
+
"eval_steps_per_second": 7.264,
|
128 |
+
"step": 173
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.08,
|
132 |
+
"learning_rate": 3.9952996474735605e-05,
|
133 |
+
"loss": 0.547,
|
134 |
+
"step": 180
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 2.19,
|
138 |
+
"learning_rate": 3.936545240893067e-05,
|
139 |
+
"loss": 0.5548,
|
140 |
+
"step": 190
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 2.31,
|
144 |
+
"learning_rate": 3.877790834312574e-05,
|
145 |
+
"loss": 0.5498,
|
146 |
+
"step": 200
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 2.43,
|
150 |
+
"learning_rate": 3.81903642773208e-05,
|
151 |
+
"loss": 0.5291,
|
152 |
+
"step": 210
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 2.54,
|
156 |
+
"learning_rate": 3.760282021151586e-05,
|
157 |
+
"loss": 0.5145,
|
158 |
+
"step": 220
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.66,
|
162 |
+
"learning_rate": 3.701527614571093e-05,
|
163 |
+
"loss": 0.4981,
|
164 |
+
"step": 230
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.77,
|
168 |
+
"learning_rate": 3.6427732079905996e-05,
|
169 |
+
"loss": 0.5022,
|
170 |
+
"step": 240
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.89,
|
174 |
+
"learning_rate": 3.584018801410106e-05,
|
175 |
+
"loss": 0.4768,
|
176 |
+
"step": 250
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.99,
|
180 |
+
"eval_accuracy": 0.8571428571428571,
|
181 |
+
"eval_loss": 0.47913119196891785,
|
182 |
+
"eval_runtime": 8.4707,
|
183 |
+
"eval_samples_per_second": 63.631,
|
184 |
+
"eval_steps_per_second": 8.028,
|
185 |
+
"step": 259
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 3.0,
|
189 |
+
"learning_rate": 3.525264394829612e-05,
|
190 |
+
"loss": 0.4758,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 3.12,
|
195 |
+
"learning_rate": 3.466509988249119e-05,
|
196 |
+
"loss": 0.4699,
|
197 |
+
"step": 270
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 3.23,
|
201 |
+
"learning_rate": 3.4077555816686255e-05,
|
202 |
+
"loss": 0.4638,
|
203 |
+
"step": 280
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 3.35,
|
207 |
+
"learning_rate": 3.3490011750881314e-05,
|
208 |
+
"loss": 0.4378,
|
209 |
+
"step": 290
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 3.47,
|
213 |
+
"learning_rate": 3.290246768507638e-05,
|
214 |
+
"loss": 0.4795,
|
215 |
+
"step": 300
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 3.58,
|
219 |
+
"learning_rate": 3.231492361927145e-05,
|
220 |
+
"loss": 0.4522,
|
221 |
+
"step": 310
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 3.7,
|
225 |
+
"learning_rate": 3.172737955346651e-05,
|
226 |
+
"loss": 0.4456,
|
227 |
+
"step": 320
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 3.81,
|
231 |
+
"learning_rate": 3.113983548766158e-05,
|
232 |
+
"loss": 0.4489,
|
233 |
+
"step": 330
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 3.93,
|
237 |
+
"learning_rate": 3.055229142185664e-05,
|
238 |
+
"loss": 0.4161,
|
239 |
+
"step": 340
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 4.0,
|
243 |
+
"eval_accuracy": 0.8905380333951762,
|
244 |
+
"eval_loss": 0.38660189509391785,
|
245 |
+
"eval_runtime": 8.0364,
|
246 |
+
"eval_samples_per_second": 67.07,
|
247 |
+
"eval_steps_per_second": 8.461,
|
248 |
+
"step": 346
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 4.04,
|
252 |
+
"learning_rate": 2.9964747356051702e-05,
|
253 |
+
"loss": 0.415,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 4.16,
|
258 |
+
"learning_rate": 2.9377203290246768e-05,
|
259 |
+
"loss": 0.4333,
|
260 |
+
"step": 360
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 4.27,
|
264 |
+
"learning_rate": 2.8789659224441835e-05,
|
265 |
+
"loss": 0.4304,
|
266 |
+
"step": 370
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 4.39,
|
270 |
+
"learning_rate": 2.82021151586369e-05,
|
271 |
+
"loss": 0.4151,
|
272 |
+
"step": 380
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 4.5,
|
276 |
+
"learning_rate": 2.7614571092831964e-05,
|
277 |
+
"loss": 0.3846,
|
278 |
+
"step": 390
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 4.62,
|
282 |
+
"learning_rate": 2.702702702702703e-05,
|
283 |
+
"loss": 0.4447,
|
284 |
+
"step": 400
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 4.74,
|
288 |
+
"learning_rate": 2.6439482961222096e-05,
|
289 |
+
"loss": 0.4253,
|
290 |
+
"step": 410
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 4.85,
|
294 |
+
"learning_rate": 2.5851938895417156e-05,
|
295 |
+
"loss": 0.3669,
|
296 |
+
"step": 420
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 4.97,
|
300 |
+
"learning_rate": 2.526439482961222e-05,
|
301 |
+
"loss": 0.402,
|
302 |
+
"step": 430
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 4.99,
|
306 |
+
"eval_accuracy": 0.9035250463821892,
|
307 |
+
"eval_loss": 0.3293728232383728,
|
308 |
+
"eval_runtime": 7.9465,
|
309 |
+
"eval_samples_per_second": 67.829,
|
310 |
+
"eval_steps_per_second": 8.557,
|
311 |
+
"step": 432
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 5.08,
|
315 |
+
"learning_rate": 2.4676850763807285e-05,
|
316 |
+
"loss": 0.4157,
|
317 |
+
"step": 440
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 5.2,
|
321 |
+
"learning_rate": 2.408930669800235e-05,
|
322 |
+
"loss": 0.372,
|
323 |
+
"step": 450
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 5.31,
|
327 |
+
"learning_rate": 2.3501762632197415e-05,
|
328 |
+
"loss": 0.4115,
|
329 |
+
"step": 460
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 5.43,
|
333 |
+
"learning_rate": 2.291421856639248e-05,
|
334 |
+
"loss": 0.3954,
|
335 |
+
"step": 470
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 5.54,
|
339 |
+
"learning_rate": 2.2326674500587544e-05,
|
340 |
+
"loss": 0.395,
|
341 |
+
"step": 480
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 5.66,
|
345 |
+
"learning_rate": 2.173913043478261e-05,
|
346 |
+
"loss": 0.378,
|
347 |
+
"step": 490
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 5.78,
|
351 |
+
"learning_rate": 2.1151586368977673e-05,
|
352 |
+
"loss": 0.354,
|
353 |
+
"step": 500
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 5.89,
|
357 |
+
"learning_rate": 2.056404230317274e-05,
|
358 |
+
"loss": 0.369,
|
359 |
+
"step": 510
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 6.0,
|
363 |
+
"eval_accuracy": 0.8923933209647495,
|
364 |
+
"eval_loss": 1.0405044555664062,
|
365 |
+
"eval_runtime": 7.8895,
|
366 |
+
"eval_samples_per_second": 68.318,
|
367 |
+
"eval_steps_per_second": 8.619,
|
368 |
+
"step": 519
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 6.01,
|
372 |
+
"learning_rate": 1.9976498237367802e-05,
|
373 |
+
"loss": 0.3544,
|
374 |
+
"step": 520
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 6.12,
|
378 |
+
"learning_rate": 1.938895417156287e-05,
|
379 |
+
"loss": 0.3565,
|
380 |
+
"step": 530
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 6.24,
|
384 |
+
"learning_rate": 1.880141010575793e-05,
|
385 |
+
"loss": 0.3868,
|
386 |
+
"step": 540
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 6.35,
|
390 |
+
"learning_rate": 1.8213866039952998e-05,
|
391 |
+
"loss": 0.4005,
|
392 |
+
"step": 550
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 6.47,
|
396 |
+
"learning_rate": 1.762632197414806e-05,
|
397 |
+
"loss": 0.3524,
|
398 |
+
"step": 560
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 6.58,
|
402 |
+
"learning_rate": 1.7038777908343127e-05,
|
403 |
+
"loss": 0.4008,
|
404 |
+
"step": 570
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 6.7,
|
408 |
+
"learning_rate": 1.645123384253819e-05,
|
409 |
+
"loss": 0.3571,
|
410 |
+
"step": 580
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 6.82,
|
414 |
+
"learning_rate": 1.5863689776733257e-05,
|
415 |
+
"loss": 0.3398,
|
416 |
+
"step": 590
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 6.93,
|
420 |
+
"learning_rate": 1.527614571092832e-05,
|
421 |
+
"loss": 0.3512,
|
422 |
+
"step": 600
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 7.0,
|
426 |
+
"eval_accuracy": 0.8905380333951762,
|
427 |
+
"eval_loss": 1.4846545457839966,
|
428 |
+
"eval_runtime": 8.0342,
|
429 |
+
"eval_samples_per_second": 67.089,
|
430 |
+
"eval_steps_per_second": 8.464,
|
431 |
+
"step": 606
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 7.05,
|
435 |
+
"learning_rate": 1.4688601645123384e-05,
|
436 |
+
"loss": 0.3451,
|
437 |
+
"step": 610
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 7.16,
|
441 |
+
"learning_rate": 1.410105757931845e-05,
|
442 |
+
"loss": 0.3489,
|
443 |
+
"step": 620
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 7.28,
|
447 |
+
"learning_rate": 1.3513513513513515e-05,
|
448 |
+
"loss": 0.3414,
|
449 |
+
"step": 630
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 7.39,
|
453 |
+
"learning_rate": 1.2925969447708578e-05,
|
454 |
+
"loss": 0.3867,
|
455 |
+
"step": 640
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 7.51,
|
459 |
+
"learning_rate": 1.2338425381903643e-05,
|
460 |
+
"loss": 0.3509,
|
461 |
+
"step": 650
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 7.62,
|
465 |
+
"learning_rate": 1.1750881316098707e-05,
|
466 |
+
"loss": 0.33,
|
467 |
+
"step": 660
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 7.74,
|
471 |
+
"learning_rate": 1.1163337250293772e-05,
|
472 |
+
"loss": 0.3678,
|
473 |
+
"step": 670
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 7.85,
|
477 |
+
"learning_rate": 1.0575793184488837e-05,
|
478 |
+
"loss": 0.3481,
|
479 |
+
"step": 680
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 7.97,
|
483 |
+
"learning_rate": 9.988249118683901e-06,
|
484 |
+
"loss": 0.3439,
|
485 |
+
"step": 690
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 7.99,
|
489 |
+
"eval_accuracy": 0.9053803339517625,
|
490 |
+
"eval_loss": 0.28196877241134644,
|
491 |
+
"eval_runtime": 8.0187,
|
492 |
+
"eval_samples_per_second": 67.218,
|
493 |
+
"eval_steps_per_second": 8.48,
|
494 |
+
"step": 692
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 8.09,
|
498 |
+
"learning_rate": 9.400705052878966e-06,
|
499 |
+
"loss": 0.3763,
|
500 |
+
"step": 700
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 8.2,
|
504 |
+
"learning_rate": 8.81316098707403e-06,
|
505 |
+
"loss": 0.3435,
|
506 |
+
"step": 710
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 8.32,
|
510 |
+
"learning_rate": 8.225616921269095e-06,
|
511 |
+
"loss": 0.3455,
|
512 |
+
"step": 720
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 8.43,
|
516 |
+
"learning_rate": 7.63807285546416e-06,
|
517 |
+
"loss": 0.3422,
|
518 |
+
"step": 730
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 8.55,
|
522 |
+
"learning_rate": 7.050528789659225e-06,
|
523 |
+
"loss": 0.3484,
|
524 |
+
"step": 740
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 8.66,
|
528 |
+
"learning_rate": 6.462984723854289e-06,
|
529 |
+
"loss": 0.3342,
|
530 |
+
"step": 750
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 8.78,
|
534 |
+
"learning_rate": 5.875440658049354e-06,
|
535 |
+
"loss": 0.3657,
|
536 |
+
"step": 760
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 8.89,
|
540 |
+
"learning_rate": 5.287896592244418e-06,
|
541 |
+
"loss": 0.3306,
|
542 |
+
"step": 770
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 9.0,
|
546 |
+
"eval_accuracy": 0.8849721706864564,
|
547 |
+
"eval_loss": 0.3021787703037262,
|
548 |
+
"eval_runtime": 8.1523,
|
549 |
+
"eval_samples_per_second": 66.116,
|
550 |
+
"eval_steps_per_second": 8.341,
|
551 |
+
"step": 779
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 9.01,
|
555 |
+
"learning_rate": 4.700352526439483e-06,
|
556 |
+
"loss": 0.3541,
|
557 |
+
"step": 780
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 9.13,
|
561 |
+
"learning_rate": 4.1128084606345476e-06,
|
562 |
+
"loss": 0.3233,
|
563 |
+
"step": 790
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 9.24,
|
567 |
+
"learning_rate": 3.5252643948296126e-06,
|
568 |
+
"loss": 0.3345,
|
569 |
+
"step": 800
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 9.36,
|
573 |
+
"learning_rate": 2.937720329024677e-06,
|
574 |
+
"loss": 0.3387,
|
575 |
+
"step": 810
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 9.47,
|
579 |
+
"learning_rate": 2.3501762632197415e-06,
|
580 |
+
"loss": 0.3477,
|
581 |
+
"step": 820
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 9.59,
|
585 |
+
"learning_rate": 1.7626321974148063e-06,
|
586 |
+
"loss": 0.3148,
|
587 |
+
"step": 830
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 9.7,
|
591 |
+
"learning_rate": 1.1750881316098707e-06,
|
592 |
+
"loss": 0.337,
|
593 |
+
"step": 840
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 9.82,
|
597 |
+
"learning_rate": 5.875440658049354e-07,
|
598 |
+
"loss": 0.3339,
|
599 |
+
"step": 850
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 9.93,
|
603 |
+
"learning_rate": 0.0,
|
604 |
+
"loss": 0.3691,
|
605 |
+
"step": 860
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 9.93,
|
609 |
+
"eval_accuracy": 0.8163265306122449,
|
610 |
+
"eval_loss": 0.7981617450714111,
|
611 |
+
"eval_runtime": 9.506,
|
612 |
+
"eval_samples_per_second": 56.701,
|
613 |
+
"eval_steps_per_second": 7.153,
|
614 |
+
"step": 860
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 9.93,
|
618 |
+
"step": 860,
|
619 |
+
"total_flos": 1.0221236731922227e+18,
|
620 |
+
"train_loss": 0.4434790275817694,
|
621 |
+
"train_runtime": 1771.1031,
|
622 |
+
"train_samples_per_second": 27.356,
|
623 |
+
"train_steps_per_second": 0.486
|
624 |
+
}
|
625 |
+
],
|
626 |
+
"max_steps": 860,
|
627 |
+
"num_train_epochs": 10,
|
628 |
+
"total_flos": 1.0221236731922227e+18,
|
629 |
+
"trial_name": null,
|
630 |
+
"trial_params": null
|
631 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3643
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6a013b726efbeb16f367467013c48a8a7e06b0970f6003b2f28b4acffc532e9
|
3 |
size 3643
|