End of training
Browse files- README.md +10 -8
- all_results.json +16 -0
- eval_results.json +11 -0
- logs/events.out.tfevents.1677677003.kyoto.1072791.11 +3 -0
- train_results.json +8 -0
- trainer_state.json +161 -0
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
@@ -13,7 +15,7 @@ model-index:
|
|
13 |
name: Text Classification
|
14 |
type: text-classification
|
15 |
dataset:
|
16 |
-
name:
|
17 |
type: glue
|
18 |
config: qqp
|
19 |
split: validation
|
@@ -21,10 +23,10 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
-
value: 0.
|
25 |
- name: F1
|
26 |
type: f1
|
27 |
-
value: 0.
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,12 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
# hBERTv2_qqp
|
34 |
|
35 |
-
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
- Loss: 0.
|
38 |
-
- Accuracy: 0.
|
39 |
-
- F1: 0.
|
40 |
-
- Combined Score: 0.
|
41 |
|
42 |
## Model description
|
43 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
15 |
name: Text Classification
|
16 |
type: text-classification
|
17 |
dataset:
|
18 |
+
name: GLUE QQP
|
19 |
type: glue
|
20 |
config: qqp
|
21 |
split: validation
|
|
|
23 |
metrics:
|
24 |
- name: Accuracy
|
25 |
type: accuracy
|
26 |
+
value: 0.8651001731387583
|
27 |
- name: F1
|
28 |
type: f1
|
29 |
+
value: 0.8160291438979962
|
30 |
---
|
31 |
|
32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
34 |
|
35 |
# hBERTv2_qqp
|
36 |
|
37 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v2](https://huggingface.co/gokuls/bert_12_layer_model_v2) on the GLUE QQP dataset.
|
38 |
It achieves the following results on the evaluation set:
|
39 |
+
- Loss: 0.3129
|
40 |
+
- Accuracy: 0.8651
|
41 |
+
- F1: 0.8160
|
42 |
+
- Combined Score: 0.8406
|
43 |
|
44 |
## Model description
|
45 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 8.0,
|
3 |
+
"eval_accuracy": 0.8651001731387583,
|
4 |
+
"eval_combined_score": 0.8405646585183773,
|
5 |
+
"eval_f1": 0.8160291438979962,
|
6 |
+
"eval_loss": 0.31285223364830017,
|
7 |
+
"eval_runtime": 47.3472,
|
8 |
+
"eval_samples": 40430,
|
9 |
+
"eval_samples_per_second": 853.905,
|
10 |
+
"eval_steps_per_second": 3.337,
|
11 |
+
"train_loss": 0.18701694115640075,
|
12 |
+
"train_runtime": 10256.0914,
|
13 |
+
"train_samples": 363846,
|
14 |
+
"train_samples_per_second": 1773.804,
|
15 |
+
"train_steps_per_second": 6.932
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 8.0,
|
3 |
+
"eval_accuracy": 0.8651001731387583,
|
4 |
+
"eval_combined_score": 0.8405646585183773,
|
5 |
+
"eval_f1": 0.8160291438979962,
|
6 |
+
"eval_loss": 0.31285223364830017,
|
7 |
+
"eval_runtime": 47.3472,
|
8 |
+
"eval_samples": 40430,
|
9 |
+
"eval_samples_per_second": 853.905,
|
10 |
+
"eval_steps_per_second": 3.337
|
11 |
+
}
|
logs/events.out.tfevents.1677677003.kyoto.1072791.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:999d0a5027d71d44aa5bb2002cbac6f4dae9f2c5486353fdccdb661d661a7b83
|
3 |
+
size 467
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 8.0,
|
3 |
+
"train_loss": 0.18701694115640075,
|
4 |
+
"train_runtime": 10256.0914,
|
5 |
+
"train_samples": 363846,
|
6 |
+
"train_samples_per_second": 1773.804,
|
7 |
+
"train_steps_per_second": 6.932
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.31285223364830017,
|
3 |
+
"best_model_checkpoint": "hBERTv2_qqp/checkpoint-4266",
|
4 |
+
"epoch": 8.0,
|
5 |
+
"global_step": 11376,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 4.900070323488045e-05,
|
13 |
+
"loss": 0.4179,
|
14 |
+
"step": 1422
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.8251545881770962,
|
19 |
+
"eval_combined_score": 0.8083731607119745,
|
20 |
+
"eval_f1": 0.7915917332468528,
|
21 |
+
"eval_loss": 0.38297852873802185,
|
22 |
+
"eval_runtime": 47.7223,
|
23 |
+
"eval_samples_per_second": 847.193,
|
24 |
+
"eval_steps_per_second": 3.311,
|
25 |
+
"step": 1422
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"learning_rate": 4.800070323488045e-05,
|
30 |
+
"loss": 0.2978,
|
31 |
+
"step": 2844
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.8357160524363096,
|
36 |
+
"eval_combined_score": 0.8131408666041042,
|
37 |
+
"eval_f1": 0.7905656807718988,
|
38 |
+
"eval_loss": 0.35074833035469055,
|
39 |
+
"eval_runtime": 47.7241,
|
40 |
+
"eval_samples_per_second": 847.161,
|
41 |
+
"eval_steps_per_second": 3.311,
|
42 |
+
"step": 2844
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"learning_rate": 4.700070323488045e-05,
|
47 |
+
"loss": 0.2318,
|
48 |
+
"step": 4266
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.8651001731387583,
|
53 |
+
"eval_combined_score": 0.8405646585183773,
|
54 |
+
"eval_f1": 0.8160291438979962,
|
55 |
+
"eval_loss": 0.31285223364830017,
|
56 |
+
"eval_runtime": 47.7786,
|
57 |
+
"eval_samples_per_second": 846.194,
|
58 |
+
"eval_steps_per_second": 3.307,
|
59 |
+
"step": 4266
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"learning_rate": 4.600070323488046e-05,
|
64 |
+
"loss": 0.1765,
|
65 |
+
"step": 5688
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_accuracy": 0.8700469948058372,
|
70 |
+
"eval_combined_score": 0.8514036858419307,
|
71 |
+
"eval_f1": 0.8327603768780241,
|
72 |
+
"eval_loss": 0.35401350259780884,
|
73 |
+
"eval_runtime": 47.7873,
|
74 |
+
"eval_samples_per_second": 846.041,
|
75 |
+
"eval_steps_per_second": 3.306,
|
76 |
+
"step": 5688
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 5.0,
|
80 |
+
"learning_rate": 4.500070323488045e-05,
|
81 |
+
"loss": 0.1305,
|
82 |
+
"step": 7110
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 5.0,
|
86 |
+
"eval_accuracy": 0.8733860994311156,
|
87 |
+
"eval_combined_score": 0.8500331546757744,
|
88 |
+
"eval_f1": 0.8266802099204335,
|
89 |
+
"eval_loss": 0.4275738596916199,
|
90 |
+
"eval_runtime": 47.709,
|
91 |
+
"eval_samples_per_second": 847.43,
|
92 |
+
"eval_steps_per_second": 3.312,
|
93 |
+
"step": 7110
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 6.0,
|
97 |
+
"learning_rate": 4.40014064697609e-05,
|
98 |
+
"loss": 0.1003,
|
99 |
+
"step": 8532
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 6.0,
|
103 |
+
"eval_accuracy": 0.8748454118229038,
|
104 |
+
"eval_combined_score": 0.8520305093406406,
|
105 |
+
"eval_f1": 0.8292156068583774,
|
106 |
+
"eval_loss": 0.40782323479652405,
|
107 |
+
"eval_runtime": 47.8778,
|
108 |
+
"eval_samples_per_second": 844.441,
|
109 |
+
"eval_steps_per_second": 3.3,
|
110 |
+
"step": 8532
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"learning_rate": 4.30014064697609e-05,
|
115 |
+
"loss": 0.0788,
|
116 |
+
"step": 9954
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 7.0,
|
120 |
+
"eval_accuracy": 0.876675735839723,
|
121 |
+
"eval_combined_score": 0.855563447307603,
|
122 |
+
"eval_f1": 0.8344511587754831,
|
123 |
+
"eval_loss": 0.4068982005119324,
|
124 |
+
"eval_runtime": 47.8891,
|
125 |
+
"eval_samples_per_second": 844.242,
|
126 |
+
"eval_steps_per_second": 3.299,
|
127 |
+
"step": 9954
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 8.0,
|
131 |
+
"learning_rate": 4.200210970464135e-05,
|
132 |
+
"loss": 0.0625,
|
133 |
+
"step": 11376
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 8.0,
|
137 |
+
"eval_accuracy": 0.8760079149146673,
|
138 |
+
"eval_combined_score": 0.8541156077803029,
|
139 |
+
"eval_f1": 0.8322233006459385,
|
140 |
+
"eval_loss": 0.4722978472709656,
|
141 |
+
"eval_runtime": 47.7389,
|
142 |
+
"eval_samples_per_second": 846.898,
|
143 |
+
"eval_steps_per_second": 3.31,
|
144 |
+
"step": 11376
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 8.0,
|
148 |
+
"step": 11376,
|
149 |
+
"total_flos": 3.625461609146614e+17,
|
150 |
+
"train_loss": 0.18701694115640075,
|
151 |
+
"train_runtime": 10256.0914,
|
152 |
+
"train_samples_per_second": 1773.804,
|
153 |
+
"train_steps_per_second": 6.932
|
154 |
+
}
|
155 |
+
],
|
156 |
+
"max_steps": 71100,
|
157 |
+
"num_train_epochs": 50,
|
158 |
+
"total_flos": 3.625461609146614e+17,
|
159 |
+
"trial_name": null,
|
160 |
+
"trial_params": null
|
161 |
+
}
|