End of training
Browse files- README.md +3 -3
- all_results.json +16 -0
- eval_results.json +11 -0
- runs/Sep03_17-04-00_108ca9676f98/events.out.tfevents.1725384301.108ca9676f98.2030.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +397 -0
README.md
CHANGED
@@ -20,10 +20,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on an unknown dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 1.
|
24 |
- Accuracy: 0.5785
|
25 |
-
- F1: 0.
|
26 |
-
- Precision: 0.
|
27 |
- Recall: 0.5785
|
28 |
|
29 |
## Model description
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on an unknown dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.0072
|
24 |
- Accuracy: 0.5785
|
25 |
+
- F1: 0.5643
|
26 |
+
- Precision: 0.5602
|
27 |
- Recall: 0.5785
|
28 |
|
29 |
## Model description
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 14.782608695652174,
|
3 |
+
"eval_accuracy": 0.5785123966942148,
|
4 |
+
"eval_f1": 0.5642688943190026,
|
5 |
+
"eval_loss": 1.007211446762085,
|
6 |
+
"eval_precision": 0.5601763323294238,
|
7 |
+
"eval_recall": 0.5785123966942148,
|
8 |
+
"eval_runtime": 5.966,
|
9 |
+
"eval_samples_per_second": 182.535,
|
10 |
+
"eval_steps_per_second": 3.017,
|
11 |
+
"total_flos": 4.988285676013732e+18,
|
12 |
+
"train_loss": 1.0613567090501972,
|
13 |
+
"train_runtime": 1231.6208,
|
14 |
+
"train_samples_per_second": 53.016,
|
15 |
+
"train_steps_per_second": 0.207
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 14.782608695652174,
|
3 |
+
"eval_accuracy": 0.5785123966942148,
|
4 |
+
"eval_f1": 0.5642688943190026,
|
5 |
+
"eval_loss": 1.007211446762085,
|
6 |
+
"eval_precision": 0.5601763323294238,
|
7 |
+
"eval_recall": 0.5785123966942148,
|
8 |
+
"eval_runtime": 5.966,
|
9 |
+
"eval_samples_per_second": 182.535,
|
10 |
+
"eval_steps_per_second": 3.017
|
11 |
+
}
|
runs/Sep03_17-04-00_108ca9676f98/events.out.tfevents.1725384301.108ca9676f98.2030.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0da531965d6d76b71ba9766d458f794907187beae14e603191766290b9d7d390
|
3 |
+
size 560
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 14.782608695652174,
|
3 |
+
"total_flos": 4.988285676013732e+18,
|
4 |
+
"train_loss": 1.0613567090501972,
|
5 |
+
"train_runtime": 1231.6208,
|
6 |
+
"train_samples_per_second": 53.016,
|
7 |
+
"train_steps_per_second": 0.207
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,397 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5785123966942148,
|
3 |
+
"best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-tekno24/checkpoint-224",
|
4 |
+
"epoch": 14.782608695652174,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 255,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.5797101449275363,
|
13 |
+
"grad_norm": 4.828278064727783,
|
14 |
+
"learning_rate": 1.923076923076923e-05,
|
15 |
+
"loss": 1.4008,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.9855072463768116,
|
20 |
+
"eval_accuracy": 0.40587695133149676,
|
21 |
+
"eval_f1": 0.3220119812956281,
|
22 |
+
"eval_loss": 1.2967476844787598,
|
23 |
+
"eval_precision": 0.3790936482459676,
|
24 |
+
"eval_recall": 0.40587695133149676,
|
25 |
+
"eval_runtime": 5.7887,
|
26 |
+
"eval_samples_per_second": 188.127,
|
27 |
+
"eval_steps_per_second": 3.11,
|
28 |
+
"step": 17
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 1.1594202898550725,
|
32 |
+
"grad_norm": 3.097071409225464,
|
33 |
+
"learning_rate": 3.846153846153846e-05,
|
34 |
+
"loss": 1.3258,
|
35 |
+
"step": 20
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 1.7391304347826086,
|
39 |
+
"grad_norm": 3.920624256134033,
|
40 |
+
"learning_rate": 4.912663755458515e-05,
|
41 |
+
"loss": 1.2363,
|
42 |
+
"step": 30
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.971014492753623,
|
46 |
+
"eval_accuracy": 0.5032139577594124,
|
47 |
+
"eval_f1": 0.41868311008776393,
|
48 |
+
"eval_loss": 1.130901575088501,
|
49 |
+
"eval_precision": 0.48705100222787945,
|
50 |
+
"eval_recall": 0.5032139577594124,
|
51 |
+
"eval_runtime": 6.0169,
|
52 |
+
"eval_samples_per_second": 180.99,
|
53 |
+
"eval_steps_per_second": 2.992,
|
54 |
+
"step": 34
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 2.318840579710145,
|
58 |
+
"grad_norm": 4.518988132476807,
|
59 |
+
"learning_rate": 4.6943231441048036e-05,
|
60 |
+
"loss": 1.1413,
|
61 |
+
"step": 40
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 2.898550724637681,
|
65 |
+
"grad_norm": 2.2280020713806152,
|
66 |
+
"learning_rate": 4.475982532751092e-05,
|
67 |
+
"loss": 1.1716,
|
68 |
+
"step": 50
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 2.9565217391304346,
|
72 |
+
"eval_accuracy": 0.5160697887970616,
|
73 |
+
"eval_f1": 0.43845341130360466,
|
74 |
+
"eval_loss": 1.0983200073242188,
|
75 |
+
"eval_precision": 0.46095184546832213,
|
76 |
+
"eval_recall": 0.5160697887970616,
|
77 |
+
"eval_runtime": 5.9715,
|
78 |
+
"eval_samples_per_second": 182.365,
|
79 |
+
"eval_steps_per_second": 3.014,
|
80 |
+
"step": 51
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 3.4782608695652173,
|
84 |
+
"grad_norm": 4.956761837005615,
|
85 |
+
"learning_rate": 4.2576419213973804e-05,
|
86 |
+
"loss": 1.1479,
|
87 |
+
"step": 60
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.0,
|
91 |
+
"eval_accuracy": 0.5408631772268135,
|
92 |
+
"eval_f1": 0.5013630393836427,
|
93 |
+
"eval_loss": 1.0550026893615723,
|
94 |
+
"eval_precision": 0.5066784174960421,
|
95 |
+
"eval_recall": 0.5408631772268135,
|
96 |
+
"eval_runtime": 6.0323,
|
97 |
+
"eval_samples_per_second": 180.528,
|
98 |
+
"eval_steps_per_second": 2.984,
|
99 |
+
"step": 69
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 4.057971014492754,
|
103 |
+
"grad_norm": 2.8600962162017822,
|
104 |
+
"learning_rate": 4.039301310043668e-05,
|
105 |
+
"loss": 1.098,
|
106 |
+
"step": 70
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 4.63768115942029,
|
110 |
+
"grad_norm": 2.5968716144561768,
|
111 |
+
"learning_rate": 3.8209606986899565e-05,
|
112 |
+
"loss": 1.1058,
|
113 |
+
"step": 80
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 4.9855072463768115,
|
117 |
+
"eval_accuracy": 0.5500459136822773,
|
118 |
+
"eval_f1": 0.4942077921670986,
|
119 |
+
"eval_loss": 1.039696455001831,
|
120 |
+
"eval_precision": 0.5207943123811102,
|
121 |
+
"eval_recall": 0.5500459136822773,
|
122 |
+
"eval_runtime": 6.023,
|
123 |
+
"eval_samples_per_second": 180.807,
|
124 |
+
"eval_steps_per_second": 2.989,
|
125 |
+
"step": 86
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 5.217391304347826,
|
129 |
+
"grad_norm": 4.285628318786621,
|
130 |
+
"learning_rate": 3.602620087336245e-05,
|
131 |
+
"loss": 1.0882,
|
132 |
+
"step": 90
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 5.797101449275362,
|
136 |
+
"grad_norm": 2.5915679931640625,
|
137 |
+
"learning_rate": 3.384279475982533e-05,
|
138 |
+
"loss": 1.0656,
|
139 |
+
"step": 100
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 5.971014492753623,
|
143 |
+
"eval_accuracy": 0.5555555555555556,
|
144 |
+
"eval_f1": 0.539618105421093,
|
145 |
+
"eval_loss": 1.055788278579712,
|
146 |
+
"eval_precision": 0.5486152071828155,
|
147 |
+
"eval_recall": 0.5555555555555556,
|
148 |
+
"eval_runtime": 6.049,
|
149 |
+
"eval_samples_per_second": 180.029,
|
150 |
+
"eval_steps_per_second": 2.976,
|
151 |
+
"step": 103
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 6.3768115942028984,
|
155 |
+
"grad_norm": 3.3794102668762207,
|
156 |
+
"learning_rate": 3.165938864628821e-05,
|
157 |
+
"loss": 1.0333,
|
158 |
+
"step": 110
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 6.956521739130435,
|
162 |
+
"grad_norm": 3.542375326156616,
|
163 |
+
"learning_rate": 2.9475982532751094e-05,
|
164 |
+
"loss": 1.0328,
|
165 |
+
"step": 120
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 6.956521739130435,
|
169 |
+
"eval_accuracy": 0.5730027548209367,
|
170 |
+
"eval_f1": 0.5465172742823081,
|
171 |
+
"eval_loss": 1.0216330289840698,
|
172 |
+
"eval_precision": 0.5512656679762724,
|
173 |
+
"eval_recall": 0.5730027548209367,
|
174 |
+
"eval_runtime": 5.949,
|
175 |
+
"eval_samples_per_second": 183.057,
|
176 |
+
"eval_steps_per_second": 3.026,
|
177 |
+
"step": 120
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 7.536231884057971,
|
181 |
+
"grad_norm": 4.52678108215332,
|
182 |
+
"learning_rate": 2.7510917030567685e-05,
|
183 |
+
"loss": 1.0116,
|
184 |
+
"step": 130
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 8.0,
|
188 |
+
"eval_accuracy": 0.5362718089990818,
|
189 |
+
"eval_f1": 0.5186530261287737,
|
190 |
+
"eval_loss": 1.0468671321868896,
|
191 |
+
"eval_precision": 0.5119022081965966,
|
192 |
+
"eval_recall": 0.5362718089990818,
|
193 |
+
"eval_runtime": 6.032,
|
194 |
+
"eval_samples_per_second": 180.536,
|
195 |
+
"eval_steps_per_second": 2.984,
|
196 |
+
"step": 138
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 8.115942028985508,
|
200 |
+
"grad_norm": 3.202193021774292,
|
201 |
+
"learning_rate": 2.5327510917030566e-05,
|
202 |
+
"loss": 1.0344,
|
203 |
+
"step": 140
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 8.695652173913043,
|
207 |
+
"grad_norm": 4.579655647277832,
|
208 |
+
"learning_rate": 2.3144104803493453e-05,
|
209 |
+
"loss": 1.012,
|
210 |
+
"step": 150
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 8.985507246376812,
|
214 |
+
"eval_accuracy": 0.5629017447199265,
|
215 |
+
"eval_f1": 0.5226383764667623,
|
216 |
+
"eval_loss": 1.0215554237365723,
|
217 |
+
"eval_precision": 0.5344130335534324,
|
218 |
+
"eval_recall": 0.5629017447199265,
|
219 |
+
"eval_runtime": 6.005,
|
220 |
+
"eval_samples_per_second": 181.348,
|
221 |
+
"eval_steps_per_second": 2.997,
|
222 |
+
"step": 155
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 9.27536231884058,
|
226 |
+
"grad_norm": 4.717169284820557,
|
227 |
+
"learning_rate": 2.096069868995633e-05,
|
228 |
+
"loss": 1.0312,
|
229 |
+
"step": 160
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 9.855072463768115,
|
233 |
+
"grad_norm": 4.781270503997803,
|
234 |
+
"learning_rate": 1.8777292576419214e-05,
|
235 |
+
"loss": 1.0076,
|
236 |
+
"step": 170
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 9.971014492753623,
|
240 |
+
"eval_accuracy": 0.5674931129476584,
|
241 |
+
"eval_f1": 0.5274537313386477,
|
242 |
+
"eval_loss": 1.0186196565628052,
|
243 |
+
"eval_precision": 0.5379365299560036,
|
244 |
+
"eval_recall": 0.5674931129476584,
|
245 |
+
"eval_runtime": 6.0992,
|
246 |
+
"eval_samples_per_second": 178.549,
|
247 |
+
"eval_steps_per_second": 2.951,
|
248 |
+
"step": 172
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 10.434782608695652,
|
252 |
+
"grad_norm": 4.275968551635742,
|
253 |
+
"learning_rate": 1.6593886462882098e-05,
|
254 |
+
"loss": 0.9714,
|
255 |
+
"step": 180
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 10.956521739130435,
|
259 |
+
"eval_accuracy": 0.5638200183654729,
|
260 |
+
"eval_f1": 0.5498769817492152,
|
261 |
+
"eval_loss": 1.0204566717147827,
|
262 |
+
"eval_precision": 0.5549239770702264,
|
263 |
+
"eval_recall": 0.5638200183654729,
|
264 |
+
"eval_runtime": 5.9924,
|
265 |
+
"eval_samples_per_second": 181.73,
|
266 |
+
"eval_steps_per_second": 3.004,
|
267 |
+
"step": 189
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 11.014492753623188,
|
271 |
+
"grad_norm": 10.067936897277832,
|
272 |
+
"learning_rate": 1.4410480349344979e-05,
|
273 |
+
"loss": 0.9775,
|
274 |
+
"step": 190
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 11.594202898550725,
|
278 |
+
"grad_norm": 3.973658323287964,
|
279 |
+
"learning_rate": 1.222707423580786e-05,
|
280 |
+
"loss": 0.9843,
|
281 |
+
"step": 200
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 12.0,
|
285 |
+
"eval_accuracy": 0.5656565656565656,
|
286 |
+
"eval_f1": 0.548837023367577,
|
287 |
+
"eval_loss": 1.011660099029541,
|
288 |
+
"eval_precision": 0.5494958647042864,
|
289 |
+
"eval_recall": 0.5656565656565656,
|
290 |
+
"eval_runtime": 5.945,
|
291 |
+
"eval_samples_per_second": 183.179,
|
292 |
+
"eval_steps_per_second": 3.028,
|
293 |
+
"step": 207
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 12.173913043478262,
|
297 |
+
"grad_norm": 3.4741806983947754,
|
298 |
+
"learning_rate": 1.0043668122270743e-05,
|
299 |
+
"loss": 0.947,
|
300 |
+
"step": 210
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 12.753623188405797,
|
304 |
+
"grad_norm": 3.447770118713379,
|
305 |
+
"learning_rate": 7.860262008733626e-06,
|
306 |
+
"loss": 0.9427,
|
307 |
+
"step": 220
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 12.985507246376812,
|
311 |
+
"eval_accuracy": 0.5785123966942148,
|
312 |
+
"eval_f1": 0.5642688943190026,
|
313 |
+
"eval_loss": 1.007211446762085,
|
314 |
+
"eval_precision": 0.5601763323294238,
|
315 |
+
"eval_recall": 0.5785123966942148,
|
316 |
+
"eval_runtime": 5.9174,
|
317 |
+
"eval_samples_per_second": 184.034,
|
318 |
+
"eval_steps_per_second": 3.042,
|
319 |
+
"step": 224
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 13.333333333333334,
|
323 |
+
"grad_norm": 3.590308666229248,
|
324 |
+
"learning_rate": 5.676855895196507e-06,
|
325 |
+
"loss": 0.9503,
|
326 |
+
"step": 230
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 13.91304347826087,
|
330 |
+
"grad_norm": 3.6937625408172607,
|
331 |
+
"learning_rate": 3.493449781659389e-06,
|
332 |
+
"loss": 0.9268,
|
333 |
+
"step": 240
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 13.971014492753623,
|
337 |
+
"eval_accuracy": 0.5785123966942148,
|
338 |
+
"eval_f1": 0.565188401679607,
|
339 |
+
"eval_loss": 1.0067576169967651,
|
340 |
+
"eval_precision": 0.562081206107597,
|
341 |
+
"eval_recall": 0.5785123966942148,
|
342 |
+
"eval_runtime": 5.9299,
|
343 |
+
"eval_samples_per_second": 183.645,
|
344 |
+
"eval_steps_per_second": 3.035,
|
345 |
+
"step": 241
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 14.492753623188406,
|
349 |
+
"grad_norm": 4.805427074432373,
|
350 |
+
"learning_rate": 1.3100436681222706e-06,
|
351 |
+
"loss": 0.9525,
|
352 |
+
"step": 250
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 14.782608695652174,
|
356 |
+
"eval_accuracy": 0.5785123966942148,
|
357 |
+
"eval_f1": 0.5641357580424653,
|
358 |
+
"eval_loss": 1.0072529315948486,
|
359 |
+
"eval_precision": 0.5641234911012597,
|
360 |
+
"eval_recall": 0.5785123966942148,
|
361 |
+
"eval_runtime": 6.1926,
|
362 |
+
"eval_samples_per_second": 175.856,
|
363 |
+
"eval_steps_per_second": 2.907,
|
364 |
+
"step": 255
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"epoch": 14.782608695652174,
|
368 |
+
"step": 255,
|
369 |
+
"total_flos": 4.988285676013732e+18,
|
370 |
+
"train_loss": 1.0613567090501972,
|
371 |
+
"train_runtime": 1231.6208,
|
372 |
+
"train_samples_per_second": 53.016,
|
373 |
+
"train_steps_per_second": 0.207
|
374 |
+
}
|
375 |
+
],
|
376 |
+
"logging_steps": 10,
|
377 |
+
"max_steps": 255,
|
378 |
+
"num_input_tokens_seen": 0,
|
379 |
+
"num_train_epochs": 15,
|
380 |
+
"save_steps": 500,
|
381 |
+
"stateful_callbacks": {
|
382 |
+
"TrainerControl": {
|
383 |
+
"args": {
|
384 |
+
"should_epoch_stop": false,
|
385 |
+
"should_evaluate": false,
|
386 |
+
"should_log": false,
|
387 |
+
"should_save": true,
|
388 |
+
"should_training_stop": true
|
389 |
+
},
|
390 |
+
"attributes": {}
|
391 |
+
}
|
392 |
+
},
|
393 |
+
"total_flos": 4.988285676013732e+18,
|
394 |
+
"train_batch_size": 64,
|
395 |
+
"trial_name": null,
|
396 |
+
"trial_params": null
|
397 |
+
}
|