polejowska
commited on
Commit
•
1b530f6
1
Parent(s):
10d84e3
End of training
Browse files- README.md +82 -0
- model.safetensors +1 -1
- trainer_state.json +378 -0
README.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/conditional-detr-resnet-50
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: cdetr-mist1-brain-gt-tumors-8ah-6l
|
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 |
+
# cdetr-mist1-brain-gt-tumors-8ah-6l
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-detr-resnet-50) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.8917
|
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: 1e-05
|
38 |
+
- train_batch_size: 4
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 25
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 5.4149 | 1.0 | 115 | 4.3974 |
|
51 |
+
| 3.9453 | 2.0 | 230 | 3.6520 |
|
52 |
+
| 3.7269 | 3.0 | 345 | 3.7602 |
|
53 |
+
| 3.5898 | 4.0 | 460 | 3.5671 |
|
54 |
+
| 3.486 | 5.0 | 575 | 3.4912 |
|
55 |
+
| 3.4073 | 6.0 | 690 | 3.4095 |
|
56 |
+
| 3.4181 | 7.0 | 805 | 3.3183 |
|
57 |
+
| 3.3603 | 8.0 | 920 | 3.1111 |
|
58 |
+
| 3.2777 | 9.0 | 1035 | 3.1992 |
|
59 |
+
| 3.2851 | 10.0 | 1150 | 3.3997 |
|
60 |
+
| 3.266 | 11.0 | 1265 | 3.2861 |
|
61 |
+
| 3.2803 | 12.0 | 1380 | 3.1813 |
|
62 |
+
| 3.1733 | 13.0 | 1495 | 2.9838 |
|
63 |
+
| 3.2094 | 14.0 | 1610 | 3.1175 |
|
64 |
+
| 3.1718 | 15.0 | 1725 | 3.0064 |
|
65 |
+
| 3.1303 | 16.0 | 1840 | 3.0869 |
|
66 |
+
| 3.0897 | 17.0 | 1955 | 3.0306 |
|
67 |
+
| 3.0233 | 18.0 | 2070 | 2.9479 |
|
68 |
+
| 3.0156 | 19.0 | 2185 | 2.9145 |
|
69 |
+
| 3.0277 | 20.0 | 2300 | 2.8919 |
|
70 |
+
| 3.0847 | 21.0 | 2415 | 2.9321 |
|
71 |
+
| 3.0333 | 22.0 | 2530 | 2.9128 |
|
72 |
+
| 3.0126 | 23.0 | 2645 | 2.8627 |
|
73 |
+
| 2.9701 | 24.0 | 2760 | 2.8686 |
|
74 |
+
| 2.9964 | 25.0 | 2875 | 2.8917 |
|
75 |
+
|
76 |
+
|
77 |
+
### Framework versions
|
78 |
+
|
79 |
+
- Transformers 4.35.0
|
80 |
+
- Pytorch 2.0.0
|
81 |
+
- Datasets 2.1.0
|
82 |
+
- Tokenizers 0.14.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 173870884
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9306ab9645deed1993e3c9a0d0284d7db695983873c6315f16eb6eade0183c4d
|
3 |
size 173870884
|
trainer_state.json
ADDED
@@ -0,0 +1,378 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 2.8627383708953857,
|
3 |
+
"best_model_checkpoint": "cdetr-mist1-brain-gt-tumors-8ah-6l/checkpoint-2645",
|
4 |
+
"epoch": 25.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2875,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"learning_rate": 9.624347826086956e-06,
|
14 |
+
"loss": 5.4149,
|
15 |
+
"step": 115
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_loss": 4.397365093231201,
|
20 |
+
"eval_runtime": 5.8932,
|
21 |
+
"eval_samples_per_second": 6.787,
|
22 |
+
"eval_steps_per_second": 0.848,
|
23 |
+
"step": 115
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 9.231304347826087e-06,
|
28 |
+
"loss": 3.9453,
|
29 |
+
"step": 230
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_loss": 3.651952028274536,
|
34 |
+
"eval_runtime": 5.9289,
|
35 |
+
"eval_samples_per_second": 6.747,
|
36 |
+
"eval_steps_per_second": 0.843,
|
37 |
+
"step": 230
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 3.0,
|
41 |
+
"learning_rate": 8.831304347826088e-06,
|
42 |
+
"loss": 3.7269,
|
43 |
+
"step": 345
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 3.0,
|
47 |
+
"eval_loss": 3.7602438926696777,
|
48 |
+
"eval_runtime": 5.8799,
|
49 |
+
"eval_samples_per_second": 6.803,
|
50 |
+
"eval_steps_per_second": 0.85,
|
51 |
+
"step": 345
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 4.0,
|
55 |
+
"learning_rate": 8.434782608695653e-06,
|
56 |
+
"loss": 3.5898,
|
57 |
+
"step": 460
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.0,
|
61 |
+
"eval_loss": 3.5670828819274902,
|
62 |
+
"eval_runtime": 5.9645,
|
63 |
+
"eval_samples_per_second": 6.706,
|
64 |
+
"eval_steps_per_second": 0.838,
|
65 |
+
"step": 460
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 5.0,
|
69 |
+
"learning_rate": 8.034782608695652e-06,
|
70 |
+
"loss": 3.486,
|
71 |
+
"step": 575
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 5.0,
|
75 |
+
"eval_loss": 3.4911675453186035,
|
76 |
+
"eval_runtime": 5.9241,
|
77 |
+
"eval_samples_per_second": 6.752,
|
78 |
+
"eval_steps_per_second": 0.844,
|
79 |
+
"step": 575
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 6.0,
|
83 |
+
"learning_rate": 7.634782608695653e-06,
|
84 |
+
"loss": 3.4073,
|
85 |
+
"step": 690
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 6.0,
|
89 |
+
"eval_loss": 3.409463405609131,
|
90 |
+
"eval_runtime": 5.8302,
|
91 |
+
"eval_samples_per_second": 6.861,
|
92 |
+
"eval_steps_per_second": 0.858,
|
93 |
+
"step": 690
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 7.0,
|
97 |
+
"learning_rate": 7.234782608695653e-06,
|
98 |
+
"loss": 3.4181,
|
99 |
+
"step": 805
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 7.0,
|
103 |
+
"eval_loss": 3.3183083534240723,
|
104 |
+
"eval_runtime": 5.8894,
|
105 |
+
"eval_samples_per_second": 6.792,
|
106 |
+
"eval_steps_per_second": 0.849,
|
107 |
+
"step": 805
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.0,
|
111 |
+
"learning_rate": 6.834782608695653e-06,
|
112 |
+
"loss": 3.3603,
|
113 |
+
"step": 920
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 8.0,
|
117 |
+
"eval_loss": 3.1111273765563965,
|
118 |
+
"eval_runtime": 5.9175,
|
119 |
+
"eval_samples_per_second": 6.76,
|
120 |
+
"eval_steps_per_second": 0.845,
|
121 |
+
"step": 920
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 9.0,
|
125 |
+
"learning_rate": 6.434782608695652e-06,
|
126 |
+
"loss": 3.2777,
|
127 |
+
"step": 1035
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 9.0,
|
131 |
+
"eval_loss": 3.1992499828338623,
|
132 |
+
"eval_runtime": 5.9275,
|
133 |
+
"eval_samples_per_second": 6.748,
|
134 |
+
"eval_steps_per_second": 0.844,
|
135 |
+
"step": 1035
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 10.0,
|
139 |
+
"learning_rate": 6.034782608695653e-06,
|
140 |
+
"loss": 3.2851,
|
141 |
+
"step": 1150
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 10.0,
|
145 |
+
"eval_loss": 3.3997130393981934,
|
146 |
+
"eval_runtime": 5.8939,
|
147 |
+
"eval_samples_per_second": 6.787,
|
148 |
+
"eval_steps_per_second": 0.848,
|
149 |
+
"step": 1150
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 11.0,
|
153 |
+
"learning_rate": 5.634782608695652e-06,
|
154 |
+
"loss": 3.266,
|
155 |
+
"step": 1265
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 11.0,
|
159 |
+
"eval_loss": 3.286081314086914,
|
160 |
+
"eval_runtime": 6.1287,
|
161 |
+
"eval_samples_per_second": 6.527,
|
162 |
+
"eval_steps_per_second": 0.816,
|
163 |
+
"step": 1265
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 12.0,
|
167 |
+
"learning_rate": 5.234782608695652e-06,
|
168 |
+
"loss": 3.2803,
|
169 |
+
"step": 1380
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 12.0,
|
173 |
+
"eval_loss": 3.18131947517395,
|
174 |
+
"eval_runtime": 6.1123,
|
175 |
+
"eval_samples_per_second": 6.544,
|
176 |
+
"eval_steps_per_second": 0.818,
|
177 |
+
"step": 1380
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 13.0,
|
181 |
+
"learning_rate": 4.834782608695652e-06,
|
182 |
+
"loss": 3.1733,
|
183 |
+
"step": 1495
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 13.0,
|
187 |
+
"eval_loss": 2.9837594032287598,
|
188 |
+
"eval_runtime": 5.925,
|
189 |
+
"eval_samples_per_second": 6.751,
|
190 |
+
"eval_steps_per_second": 0.844,
|
191 |
+
"step": 1495
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 14.0,
|
195 |
+
"learning_rate": 4.434782608695653e-06,
|
196 |
+
"loss": 3.2094,
|
197 |
+
"step": 1610
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 14.0,
|
201 |
+
"eval_loss": 3.1175174713134766,
|
202 |
+
"eval_runtime": 5.9137,
|
203 |
+
"eval_samples_per_second": 6.764,
|
204 |
+
"eval_steps_per_second": 0.845,
|
205 |
+
"step": 1610
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 15.0,
|
209 |
+
"learning_rate": 4.034782608695652e-06,
|
210 |
+
"loss": 3.1718,
|
211 |
+
"step": 1725
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 15.0,
|
215 |
+
"eval_loss": 3.0063586235046387,
|
216 |
+
"eval_runtime": 5.9077,
|
217 |
+
"eval_samples_per_second": 6.771,
|
218 |
+
"eval_steps_per_second": 0.846,
|
219 |
+
"step": 1725
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 16.0,
|
223 |
+
"learning_rate": 3.6347826086956524e-06,
|
224 |
+
"loss": 3.1303,
|
225 |
+
"step": 1840
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 16.0,
|
229 |
+
"eval_loss": 3.086920738220215,
|
230 |
+
"eval_runtime": 5.9305,
|
231 |
+
"eval_samples_per_second": 6.745,
|
232 |
+
"eval_steps_per_second": 0.843,
|
233 |
+
"step": 1840
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 17.0,
|
237 |
+
"learning_rate": 3.2347826086956524e-06,
|
238 |
+
"loss": 3.0897,
|
239 |
+
"step": 1955
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 17.0,
|
243 |
+
"eval_loss": 3.0305533409118652,
|
244 |
+
"eval_runtime": 6.0975,
|
245 |
+
"eval_samples_per_second": 6.56,
|
246 |
+
"eval_steps_per_second": 0.82,
|
247 |
+
"step": 1955
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 18.0,
|
251 |
+
"learning_rate": 2.8347826086956525e-06,
|
252 |
+
"loss": 3.0233,
|
253 |
+
"step": 2070
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 18.0,
|
257 |
+
"eval_loss": 2.9478588104248047,
|
258 |
+
"eval_runtime": 5.9801,
|
259 |
+
"eval_samples_per_second": 6.689,
|
260 |
+
"eval_steps_per_second": 0.836,
|
261 |
+
"step": 2070
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 19.0,
|
265 |
+
"learning_rate": 2.4347826086956525e-06,
|
266 |
+
"loss": 3.0156,
|
267 |
+
"step": 2185
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 19.0,
|
271 |
+
"eval_loss": 2.914536952972412,
|
272 |
+
"eval_runtime": 6.0155,
|
273 |
+
"eval_samples_per_second": 6.649,
|
274 |
+
"eval_steps_per_second": 0.831,
|
275 |
+
"step": 2185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 20.0,
|
279 |
+
"learning_rate": 2.0347826086956525e-06,
|
280 |
+
"loss": 3.0277,
|
281 |
+
"step": 2300
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 20.0,
|
285 |
+
"eval_loss": 2.891925811767578,
|
286 |
+
"eval_runtime": 6.058,
|
287 |
+
"eval_samples_per_second": 6.603,
|
288 |
+
"eval_steps_per_second": 0.825,
|
289 |
+
"step": 2300
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 21.0,
|
293 |
+
"learning_rate": 1.6382608695652176e-06,
|
294 |
+
"loss": 3.0847,
|
295 |
+
"step": 2415
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 21.0,
|
299 |
+
"eval_loss": 2.9321396350860596,
|
300 |
+
"eval_runtime": 6.1412,
|
301 |
+
"eval_samples_per_second": 6.513,
|
302 |
+
"eval_steps_per_second": 0.814,
|
303 |
+
"step": 2415
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 22.0,
|
307 |
+
"learning_rate": 1.2382608695652176e-06,
|
308 |
+
"loss": 3.0333,
|
309 |
+
"step": 2530
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 22.0,
|
313 |
+
"eval_loss": 2.91283917427063,
|
314 |
+
"eval_runtime": 6.139,
|
315 |
+
"eval_samples_per_second": 6.516,
|
316 |
+
"eval_steps_per_second": 0.814,
|
317 |
+
"step": 2530
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 23.0,
|
321 |
+
"learning_rate": 8.382608695652175e-07,
|
322 |
+
"loss": 3.0126,
|
323 |
+
"step": 2645
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 23.0,
|
327 |
+
"eval_loss": 2.8627383708953857,
|
328 |
+
"eval_runtime": 6.0565,
|
329 |
+
"eval_samples_per_second": 6.604,
|
330 |
+
"eval_steps_per_second": 0.826,
|
331 |
+
"step": 2645
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 24.0,
|
335 |
+
"learning_rate": 4.382608695652174e-07,
|
336 |
+
"loss": 2.9701,
|
337 |
+
"step": 2760
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 24.0,
|
341 |
+
"eval_loss": 2.868567705154419,
|
342 |
+
"eval_runtime": 6.0333,
|
343 |
+
"eval_samples_per_second": 6.63,
|
344 |
+
"eval_steps_per_second": 0.829,
|
345 |
+
"step": 2760
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 25.0,
|
349 |
+
"learning_rate": 3.82608695652174e-08,
|
350 |
+
"loss": 2.9964,
|
351 |
+
"step": 2875
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 25.0,
|
355 |
+
"eval_loss": 2.8917393684387207,
|
356 |
+
"eval_runtime": 6.0377,
|
357 |
+
"eval_samples_per_second": 6.625,
|
358 |
+
"eval_steps_per_second": 0.828,
|
359 |
+
"step": 2875
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 25.0,
|
363 |
+
"step": 2875,
|
364 |
+
"total_flos": 5.73883103808e+18,
|
365 |
+
"train_loss": 3.3358317977241847,
|
366 |
+
"train_runtime": 2483.4302,
|
367 |
+
"train_samples_per_second": 4.631,
|
368 |
+
"train_steps_per_second": 1.158
|
369 |
+
}
|
370 |
+
],
|
371 |
+
"logging_steps": 500,
|
372 |
+
"max_steps": 2875,
|
373 |
+
"num_train_epochs": 25,
|
374 |
+
"save_steps": 500,
|
375 |
+
"total_flos": 5.73883103808e+18,
|
376 |
+
"trial_name": null,
|
377 |
+
"trial_params": null
|
378 |
+
}
|