Commit
•
0fd0141
1
Parent(s):
8170127
End of training
Browse files- README.md +24 -6
- all_results.json +13 -13
- eval_results.json +8 -8
- logs/events.out.tfevents.1733316402.ki-g0008.1207389.7 +3 -0
- train_results.json +6 -6
- trainer_state.json +92 -164
README.md
CHANGED
@@ -1,14 +1,32 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
|
|
|
|
3 |
base_model: gokulsrinivasagan/bert_base_lda_20_v1
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
- f1
|
9 |
model-index:
|
10 |
- name: bert_base_lda_20_v1_qqp
|
11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -16,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# bert_base_lda_20_v1_qqp
|
18 |
|
19 |
-
This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1) on
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Accuracy: 0.
|
23 |
-
- F1: 0.
|
24 |
-
- Combined Score: 0.
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
language:
|
4 |
+
- en
|
5 |
base_model: gokulsrinivasagan/bert_base_lda_20_v1
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- glue
|
10 |
metrics:
|
11 |
- accuracy
|
12 |
- f1
|
13 |
model-index:
|
14 |
- name: bert_base_lda_20_v1_qqp
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Text Classification
|
18 |
+
type: text-classification
|
19 |
+
dataset:
|
20 |
+
name: GLUE QQP
|
21 |
+
type: glue
|
22 |
+
args: qqp
|
23 |
+
metrics:
|
24 |
+
- name: Accuracy
|
25 |
+
type: accuracy
|
26 |
+
value: 0.840563937670047
|
27 |
+
- name: F1
|
28 |
+
type: f1
|
29 |
+
value: 0.7909721771839938
|
30 |
---
|
31 |
|
32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
34 |
|
35 |
# bert_base_lda_20_v1_qqp
|
36 |
|
37 |
+
This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1) on the GLUE QQP dataset.
|
38 |
It achieves the following results on the evaluation set:
|
39 |
+
- Loss: 0.3612
|
40 |
+
- Accuracy: 0.8406
|
41 |
+
- F1: 0.7910
|
42 |
+
- Combined Score: 0.8158
|
43 |
|
44 |
## Model description
|
45 |
|
all_results.json
CHANGED
@@ -1,17 +1,17 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_combined_score": 0.
|
5 |
-
"eval_f1": 0.
|
6 |
-
"eval_loss": 0.
|
7 |
-
"eval_runtime": 25.
|
8 |
"eval_samples": 40430,
|
9 |
-
"eval_samples_per_second":
|
10 |
-
"eval_steps_per_second": 6.
|
11 |
-
"total_flos":
|
12 |
-
"train_loss": 0.
|
13 |
-
"train_runtime":
|
14 |
"train_samples": 363846,
|
15 |
-
"train_samples_per_second":
|
16 |
-
"train_steps_per_second":
|
17 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 8.0,
|
3 |
+
"eval_accuracy": 0.840563937670047,
|
4 |
+
"eval_combined_score": 0.8157680574270204,
|
5 |
+
"eval_f1": 0.7909721771839938,
|
6 |
+
"eval_loss": 0.3611699044704437,
|
7 |
+
"eval_runtime": 25.5909,
|
8 |
"eval_samples": 40430,
|
9 |
+
"eval_samples_per_second": 1579.86,
|
10 |
+
"eval_steps_per_second": 6.174,
|
11 |
+
"total_flos": 3.8292762019405824e+17,
|
12 |
+
"train_loss": 0.2420723964728719,
|
13 |
+
"train_runtime": 4923.4333,
|
14 |
"train_samples": 363846,
|
15 |
+
"train_samples_per_second": 3695.043,
|
16 |
+
"train_steps_per_second": 14.441
|
17 |
}
|
eval_results.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_combined_score": 0.
|
5 |
-
"eval_f1": 0.
|
6 |
-
"eval_loss": 0.
|
7 |
-
"eval_runtime": 25.
|
8 |
"eval_samples": 40430,
|
9 |
-
"eval_samples_per_second":
|
10 |
-
"eval_steps_per_second": 6.
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 8.0,
|
3 |
+
"eval_accuracy": 0.840563937670047,
|
4 |
+
"eval_combined_score": 0.8157680574270204,
|
5 |
+
"eval_f1": 0.7909721771839938,
|
6 |
+
"eval_loss": 0.3611699044704437,
|
7 |
+
"eval_runtime": 25.5909,
|
8 |
"eval_samples": 40430,
|
9 |
+
"eval_samples_per_second": 1579.86,
|
10 |
+
"eval_steps_per_second": 6.174
|
11 |
}
|
logs/events.out.tfevents.1733316402.ki-g0008.1207389.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc50983565de4c337c72ad2de990ab039091ea8972df2ee966295b4ffc841957
|
3 |
+
size 515
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 363846,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second":
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 8.0,
|
3 |
+
"total_flos": 3.8292762019405824e+17,
|
4 |
+
"train_loss": 0.2420723964728719,
|
5 |
+
"train_runtime": 4923.4333,
|
6 |
"train_samples": 363846,
|
7 |
+
"train_samples_per_second": 3695.043,
|
8 |
+
"train_steps_per_second": 14.441
|
9 |
}
|
trainer_state.json
CHANGED
@@ -1,237 +1,165 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "bert_base_lda_20_v1_qqp/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
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 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
"step": 1422
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
-
"eval_accuracy": 0.
|
21 |
-
"eval_combined_score": 0.
|
22 |
-
"eval_f1": 0.
|
23 |
-
"eval_loss": 0.
|
24 |
-
"eval_runtime":
|
25 |
-
"eval_samples_per_second":
|
26 |
-
"eval_steps_per_second": 6.
|
27 |
"step": 1422
|
28 |
},
|
29 |
{
|
30 |
"epoch": 2.0,
|
31 |
-
"grad_norm":
|
32 |
-
"learning_rate":
|
33 |
-
"loss": 0.
|
34 |
"step": 2844
|
35 |
},
|
36 |
{
|
37 |
"epoch": 2.0,
|
38 |
-
"eval_accuracy": 0.
|
39 |
-
"eval_combined_score": 0.
|
40 |
-
"eval_f1": 0.
|
41 |
-
"eval_loss": 0.
|
42 |
-
"eval_runtime":
|
43 |
-
"eval_samples_per_second":
|
44 |
-
"eval_steps_per_second": 6.
|
45 |
"step": 2844
|
46 |
},
|
47 |
{
|
48 |
"epoch": 3.0,
|
49 |
-
"grad_norm":
|
50 |
-
"learning_rate":
|
51 |
-
"loss": 0.
|
52 |
"step": 4266
|
53 |
},
|
54 |
{
|
55 |
"epoch": 3.0,
|
56 |
-
"eval_accuracy": 0.
|
57 |
-
"eval_combined_score": 0.
|
58 |
-
"eval_f1": 0.
|
59 |
-
"eval_loss": 0.
|
60 |
-
"eval_runtime":
|
61 |
-
"eval_samples_per_second":
|
62 |
-
"eval_steps_per_second": 6.
|
63 |
"step": 4266
|
64 |
},
|
65 |
{
|
66 |
"epoch": 4.0,
|
67 |
-
"grad_norm":
|
68 |
-
"learning_rate":
|
69 |
-
"loss": 0.
|
70 |
"step": 5688
|
71 |
},
|
72 |
{
|
73 |
"epoch": 4.0,
|
74 |
-
"eval_accuracy": 0.
|
75 |
-
"eval_combined_score": 0.
|
76 |
-
"eval_f1": 0.
|
77 |
-
"eval_loss": 0.
|
78 |
-
"eval_runtime": 25.
|
79 |
-
"eval_samples_per_second":
|
80 |
-
"eval_steps_per_second": 6.
|
81 |
"step": 5688
|
82 |
},
|
83 |
{
|
84 |
"epoch": 5.0,
|
85 |
-
"grad_norm":
|
86 |
-
"learning_rate":
|
87 |
-
"loss": 0.
|
88 |
"step": 7110
|
89 |
},
|
90 |
{
|
91 |
"epoch": 5.0,
|
92 |
-
"eval_accuracy": 0.
|
93 |
-
"eval_combined_score": 0.
|
94 |
-
"eval_f1": 0.
|
95 |
-
"eval_loss": 0.
|
96 |
-
"eval_runtime":
|
97 |
-
"eval_samples_per_second":
|
98 |
-
"eval_steps_per_second": 6.
|
99 |
"step": 7110
|
100 |
},
|
101 |
{
|
102 |
"epoch": 6.0,
|
103 |
-
"grad_norm":
|
104 |
-
"learning_rate":
|
105 |
-
"loss": 0.
|
106 |
"step": 8532
|
107 |
},
|
108 |
{
|
109 |
"epoch": 6.0,
|
110 |
-
"eval_accuracy": 0.
|
111 |
-
"eval_combined_score": 0.
|
112 |
-
"eval_f1": 0.
|
113 |
-
"eval_loss": 0.
|
114 |
-
"eval_runtime":
|
115 |
-
"eval_samples_per_second":
|
116 |
-
"eval_steps_per_second": 6.
|
117 |
"step": 8532
|
118 |
},
|
119 |
{
|
120 |
"epoch": 7.0,
|
121 |
-
"grad_norm":
|
122 |
-
"learning_rate":
|
123 |
-
"loss": 0.
|
124 |
"step": 9954
|
125 |
},
|
126 |
{
|
127 |
"epoch": 7.0,
|
128 |
-
"eval_accuracy": 0.
|
129 |
-
"eval_combined_score": 0.
|
130 |
-
"eval_f1": 0.
|
131 |
-
"eval_loss": 0.
|
132 |
-
"eval_runtime": 25.
|
133 |
-
"eval_samples_per_second":
|
134 |
-
"eval_steps_per_second": 6.
|
135 |
"step": 9954
|
136 |
},
|
137 |
{
|
138 |
"epoch": 8.0,
|
139 |
-
"grad_norm":
|
140 |
-
"learning_rate":
|
141 |
-
"loss": 0.
|
142 |
"step": 11376
|
143 |
},
|
144 |
{
|
145 |
"epoch": 8.0,
|
146 |
-
"eval_accuracy": 0.
|
147 |
-
"eval_combined_score": 0.
|
148 |
-
"eval_f1": 0.
|
149 |
-
"eval_loss": 0.
|
150 |
-
"eval_runtime": 25.
|
151 |
-
"eval_samples_per_second":
|
152 |
-
"eval_steps_per_second": 6.
|
153 |
"step": 11376
|
154 |
},
|
155 |
{
|
156 |
-
"epoch":
|
157 |
-
"
|
158 |
-
"
|
159 |
-
"
|
160 |
-
"
|
161 |
-
|
162 |
-
|
163 |
-
"epoch": 9.0,
|
164 |
-
"eval_accuracy": 0.6318327974276527,
|
165 |
-
"eval_combined_score": 0.3159163987138264,
|
166 |
-
"eval_f1": 0.0,
|
167 |
-
"eval_loss": 0.6577603816986084,
|
168 |
-
"eval_runtime": 25.6524,
|
169 |
-
"eval_samples_per_second": 1576.069,
|
170 |
-
"eval_steps_per_second": 6.159,
|
171 |
-
"step": 12798
|
172 |
-
},
|
173 |
-
{
|
174 |
-
"epoch": 10.0,
|
175 |
-
"grad_norm": 0.039975930005311966,
|
176 |
-
"learning_rate": 0.0008,
|
177 |
-
"loss": 0.6586,
|
178 |
-
"step": 14220
|
179 |
-
},
|
180 |
-
{
|
181 |
-
"epoch": 10.0,
|
182 |
-
"eval_accuracy": 0.6318327974276527,
|
183 |
-
"eval_combined_score": 0.3159163987138264,
|
184 |
-
"eval_f1": 0.0,
|
185 |
-
"eval_loss": 0.6577603816986084,
|
186 |
-
"eval_runtime": 25.6862,
|
187 |
-
"eval_samples_per_second": 1573.998,
|
188 |
-
"eval_steps_per_second": 6.151,
|
189 |
-
"step": 14220
|
190 |
-
},
|
191 |
-
{
|
192 |
-
"epoch": 11.0,
|
193 |
-
"grad_norm": 0.04419417306780815,
|
194 |
-
"learning_rate": 0.0007800000000000001,
|
195 |
-
"loss": 0.6586,
|
196 |
-
"step": 15642
|
197 |
-
},
|
198 |
-
{
|
199 |
-
"epoch": 11.0,
|
200 |
-
"eval_accuracy": 0.6318327974276527,
|
201 |
-
"eval_combined_score": 0.3159163987138264,
|
202 |
-
"eval_f1": 0.0,
|
203 |
-
"eval_loss": 0.6579644680023193,
|
204 |
-
"eval_runtime": 25.6827,
|
205 |
-
"eval_samples_per_second": 1574.211,
|
206 |
-
"eval_steps_per_second": 6.152,
|
207 |
-
"step": 15642
|
208 |
-
},
|
209 |
-
{
|
210 |
-
"epoch": 12.0,
|
211 |
-
"grad_norm": 0.040914136916399,
|
212 |
-
"learning_rate": 0.00076,
|
213 |
-
"loss": 0.662,
|
214 |
-
"step": 17064
|
215 |
-
},
|
216 |
-
{
|
217 |
-
"epoch": 12.0,
|
218 |
-
"eval_accuracy": 0.6318327974276527,
|
219 |
-
"eval_combined_score": 0.3159163987138264,
|
220 |
-
"eval_f1": 0.0,
|
221 |
-
"eval_loss": 0.6575562953948975,
|
222 |
-
"eval_runtime": 25.6334,
|
223 |
-
"eval_samples_per_second": 1577.242,
|
224 |
-
"eval_steps_per_second": 6.164,
|
225 |
-
"step": 17064
|
226 |
-
},
|
227 |
-
{
|
228 |
-
"epoch": 12.0,
|
229 |
-
"step": 17064,
|
230 |
-
"total_flos": 5.7439143029108736e+17,
|
231 |
-
"train_loss": 0.6597107012284177,
|
232 |
-
"train_runtime": 7311.2859,
|
233 |
-
"train_samples_per_second": 2488.249,
|
234 |
-
"train_steps_per_second": 9.725
|
235 |
}
|
236 |
],
|
237 |
"logging_steps": 1,
|
@@ -260,7 +188,7 @@
|
|
260 |
"attributes": {}
|
261 |
}
|
262 |
},
|
263 |
-
"total_flos":
|
264 |
"train_batch_size": 256,
|
265 |
"trial_name": null,
|
266 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3611699044704437,
|
3 |
+
"best_model_checkpoint": "bert_base_lda_20_v1_qqp/checkpoint-4266",
|
4 |
+
"epoch": 8.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 11376,
|
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 |
+
"grad_norm": 1.913527011871338,
|
14 |
+
"learning_rate": 4.9e-05,
|
15 |
+
"loss": 0.4706,
|
16 |
"step": 1422
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7975760573831313,
|
21 |
+
"eval_combined_score": 0.7412216058960324,
|
22 |
+
"eval_f1": 0.6848671544089334,
|
23 |
+
"eval_loss": 0.41439592838287354,
|
24 |
+
"eval_runtime": 26.0568,
|
25 |
+
"eval_samples_per_second": 1551.613,
|
26 |
+
"eval_steps_per_second": 6.064,
|
27 |
"step": 1422
|
28 |
},
|
29 |
{
|
30 |
"epoch": 2.0,
|
31 |
+
"grad_norm": 2.9698476791381836,
|
32 |
+
"learning_rate": 4.8e-05,
|
33 |
+
"loss": 0.3635,
|
34 |
"step": 2844
|
35 |
},
|
36 |
{
|
37 |
"epoch": 2.0,
|
38 |
+
"eval_accuracy": 0.8274301261439525,
|
39 |
+
"eval_combined_score": 0.8024355964223224,
|
40 |
+
"eval_f1": 0.7774410667006922,
|
41 |
+
"eval_loss": 0.3808220326900482,
|
42 |
+
"eval_runtime": 26.0976,
|
43 |
+
"eval_samples_per_second": 1549.186,
|
44 |
+
"eval_steps_per_second": 6.054,
|
45 |
"step": 2844
|
46 |
},
|
47 |
{
|
48 |
"epoch": 3.0,
|
49 |
+
"grad_norm": 3.8180556297302246,
|
50 |
+
"learning_rate": 4.7e-05,
|
51 |
+
"loss": 0.2981,
|
52 |
"step": 4266
|
53 |
},
|
54 |
{
|
55 |
"epoch": 3.0,
|
56 |
+
"eval_accuracy": 0.840563937670047,
|
57 |
+
"eval_combined_score": 0.8157680574270204,
|
58 |
+
"eval_f1": 0.7909721771839938,
|
59 |
+
"eval_loss": 0.3611699044704437,
|
60 |
+
"eval_runtime": 26.154,
|
61 |
+
"eval_samples_per_second": 1545.844,
|
62 |
+
"eval_steps_per_second": 6.041,
|
63 |
"step": 4266
|
64 |
},
|
65 |
{
|
66 |
"epoch": 4.0,
|
67 |
+
"grad_norm": 3.3878448009490967,
|
68 |
+
"learning_rate": 4.600000000000001e-05,
|
69 |
+
"loss": 0.2419,
|
70 |
"step": 5688
|
71 |
},
|
72 |
{
|
73 |
"epoch": 4.0,
|
74 |
+
"eval_accuracy": 0.8491219391540935,
|
75 |
+
"eval_combined_score": 0.8199943211952585,
|
76 |
+
"eval_f1": 0.7908667032364235,
|
77 |
+
"eval_loss": 0.4086599349975586,
|
78 |
+
"eval_runtime": 25.573,
|
79 |
+
"eval_samples_per_second": 1580.967,
|
80 |
+
"eval_steps_per_second": 6.178,
|
81 |
"step": 5688
|
82 |
},
|
83 |
{
|
84 |
"epoch": 5.0,
|
85 |
+
"grad_norm": 3.262328863143921,
|
86 |
+
"learning_rate": 4.5e-05,
|
87 |
+
"loss": 0.1933,
|
88 |
"step": 7110
|
89 |
},
|
90 |
{
|
91 |
"epoch": 5.0,
|
92 |
+
"eval_accuracy": 0.8506059856542172,
|
93 |
+
"eval_combined_score": 0.8207251134725826,
|
94 |
+
"eval_f1": 0.7908442412909481,
|
95 |
+
"eval_loss": 0.44820770621299744,
|
96 |
+
"eval_runtime": 26.1949,
|
97 |
+
"eval_samples_per_second": 1543.43,
|
98 |
+
"eval_steps_per_second": 6.032,
|
99 |
"step": 7110
|
100 |
},
|
101 |
{
|
102 |
"epoch": 6.0,
|
103 |
+
"grad_norm": 4.035948276519775,
|
104 |
+
"learning_rate": 4.4000000000000006e-05,
|
105 |
+
"loss": 0.1514,
|
106 |
"step": 8532
|
107 |
},
|
108 |
{
|
109 |
"epoch": 6.0,
|
110 |
+
"eval_accuracy": 0.8534504081127875,
|
111 |
+
"eval_combined_score": 0.8276283651201168,
|
112 |
+
"eval_f1": 0.8018063221274461,
|
113 |
+
"eval_loss": 0.43122583627700806,
|
114 |
+
"eval_runtime": 26.1244,
|
115 |
+
"eval_samples_per_second": 1547.595,
|
116 |
+
"eval_steps_per_second": 6.048,
|
117 |
"step": 8532
|
118 |
},
|
119 |
{
|
120 |
"epoch": 7.0,
|
121 |
+
"grad_norm": 4.258938312530518,
|
122 |
+
"learning_rate": 4.3e-05,
|
123 |
+
"loss": 0.1208,
|
124 |
"step": 9954
|
125 |
},
|
126 |
{
|
127 |
"epoch": 7.0,
|
128 |
+
"eval_accuracy": 0.8498392282958199,
|
129 |
+
"eval_combined_score": 0.8269528560391477,
|
130 |
+
"eval_f1": 0.8040664837824754,
|
131 |
+
"eval_loss": 0.5434415936470032,
|
132 |
+
"eval_runtime": 25.8296,
|
133 |
+
"eval_samples_per_second": 1565.258,
|
134 |
+
"eval_steps_per_second": 6.117,
|
135 |
"step": 9954
|
136 |
},
|
137 |
{
|
138 |
"epoch": 8.0,
|
139 |
+
"grad_norm": 3.5687382221221924,
|
140 |
+
"learning_rate": 4.2e-05,
|
141 |
+
"loss": 0.097,
|
142 |
"step": 11376
|
143 |
},
|
144 |
{
|
145 |
"epoch": 8.0,
|
146 |
+
"eval_accuracy": 0.853227801137769,
|
147 |
+
"eval_combined_score": 0.8277139005688845,
|
148 |
+
"eval_f1": 0.8022000000000001,
|
149 |
+
"eval_loss": 0.5604811310768127,
|
150 |
+
"eval_runtime": 25.8751,
|
151 |
+
"eval_samples_per_second": 1562.506,
|
152 |
+
"eval_steps_per_second": 6.106,
|
153 |
"step": 11376
|
154 |
},
|
155 |
{
|
156 |
+
"epoch": 8.0,
|
157 |
+
"step": 11376,
|
158 |
+
"total_flos": 3.8292762019405824e+17,
|
159 |
+
"train_loss": 0.2420723964728719,
|
160 |
+
"train_runtime": 4923.4333,
|
161 |
+
"train_samples_per_second": 3695.043,
|
162 |
+
"train_steps_per_second": 14.441
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 1,
|
|
|
188 |
"attributes": {}
|
189 |
}
|
190 |
},
|
191 |
+
"total_flos": 3.8292762019405824e+17,
|
192 |
"train_batch_size": 256,
|
193 |
"trial_name": null,
|
194 |
"trial_params": null
|