End of training
Browse files- README.md +7 -5
- all_results.json +14 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1686040975.serv-9207.2389173.11 +3 -0
- train_results.json +8 -0
- trainer_state.json +175 -0
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
@@ -12,7 +14,7 @@ model-index:
|
|
12 |
name: Text Classification
|
13 |
type: text-classification
|
14 |
dataset:
|
15 |
-
name:
|
16 |
type: glue
|
17 |
config: qnli
|
18 |
split: validation
|
@@ -20,7 +22,7 @@ model-index:
|
|
20 |
metrics:
|
21 |
- name: Accuracy
|
22 |
type: accuracy
|
23 |
-
value: 0.
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -28,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
28 |
|
29 |
# hBERTv1_new_pretrain_w_init_48_qnli
|
30 |
|
31 |
-
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48) on the
|
32 |
It achieves the following results on the evaluation set:
|
33 |
-
- Loss: 0.
|
34 |
-
- Accuracy: 0.
|
35 |
|
36 |
## Model description
|
37 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
14 |
name: Text Classification
|
15 |
type: text-classification
|
16 |
dataset:
|
17 |
+
name: GLUE QNLI
|
18 |
type: glue
|
19 |
config: qnli
|
20 |
split: validation
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.7935200439319056
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# hBERTv1_new_pretrain_w_init_48_qnli
|
32 |
|
33 |
+
This model is a fine-tuned version of [gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48](https://huggingface.co/gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48) on the GLUE QNLI dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.4527
|
36 |
+
- Accuracy: 0.7935
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.7935200439319056,
|
4 |
+
"eval_loss": 0.4527376592159271,
|
5 |
+
"eval_runtime": 9.9513,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 548.972,
|
8 |
+
"eval_steps_per_second": 4.321,
|
9 |
+
"train_loss": 0.35937960372011885,
|
10 |
+
"train_runtime": 5750.0945,
|
11 |
+
"train_samples": 104743,
|
12 |
+
"train_samples_per_second": 910.794,
|
13 |
+
"train_steps_per_second": 7.122
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.7935200439319056,
|
4 |
+
"eval_loss": 0.4527376592159271,
|
5 |
+
"eval_runtime": 9.9513,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 548.972,
|
8 |
+
"eval_steps_per_second": 4.321
|
9 |
+
}
|
logs/events.out.tfevents.1686040975.serv-9207.2389173.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a590d4e2e181747137c10ce7f6c810c2e444e64d73522d91f1978246b2e5b482
|
3 |
+
size 363
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 0.35937960372011885,
|
4 |
+
"train_runtime": 5750.0945,
|
5 |
+
"train_samples": 104743,
|
6 |
+
"train_samples_per_second": 910.794,
|
7 |
+
"train_steps_per_second": 7.122
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4527376592159271,
|
3 |
+
"best_model_checkpoint": "hBERTv1_new_pretrain_w_init_48_qnli/checkpoint-4095",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 8190,
|
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": 3.9200000000000004e-05,
|
13 |
+
"loss": 0.615,
|
14 |
+
"step": 819
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.7040087863811093,
|
19 |
+
"eval_loss": 0.5774398446083069,
|
20 |
+
"eval_runtime": 10.067,
|
21 |
+
"eval_samples_per_second": 542.663,
|
22 |
+
"eval_steps_per_second": 4.271,
|
23 |
+
"step": 819
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 3.8400000000000005e-05,
|
28 |
+
"loss": 0.5092,
|
29 |
+
"step": 1638
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.7818048691195314,
|
34 |
+
"eval_loss": 0.4735040068626404,
|
35 |
+
"eval_runtime": 10.1673,
|
36 |
+
"eval_samples_per_second": 537.309,
|
37 |
+
"eval_steps_per_second": 4.229,
|
38 |
+
"step": 1638
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 3.76e-05,
|
43 |
+
"loss": 0.4554,
|
44 |
+
"step": 2457
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.7861980596741717,
|
49 |
+
"eval_loss": 0.466993510723114,
|
50 |
+
"eval_runtime": 10.0759,
|
51 |
+
"eval_samples_per_second": 542.183,
|
52 |
+
"eval_steps_per_second": 4.268,
|
53 |
+
"step": 2457
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"learning_rate": 3.680000000000001e-05,
|
58 |
+
"loss": 0.4041,
|
59 |
+
"step": 3276
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_accuracy": 0.7807065714808713,
|
64 |
+
"eval_loss": 0.4881279766559601,
|
65 |
+
"eval_runtime": 10.0028,
|
66 |
+
"eval_samples_per_second": 546.149,
|
67 |
+
"eval_steps_per_second": 4.299,
|
68 |
+
"step": 3276
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"learning_rate": 3.6e-05,
|
73 |
+
"loss": 0.3567,
|
74 |
+
"step": 4095
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_accuracy": 0.7935200439319056,
|
79 |
+
"eval_loss": 0.4527376592159271,
|
80 |
+
"eval_runtime": 10.0559,
|
81 |
+
"eval_samples_per_second": 543.261,
|
82 |
+
"eval_steps_per_second": 4.276,
|
83 |
+
"step": 4095
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"learning_rate": 3.52e-05,
|
88 |
+
"loss": 0.3218,
|
89 |
+
"step": 4914
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"eval_accuracy": 0.7819879187259747,
|
94 |
+
"eval_loss": 0.5325487852096558,
|
95 |
+
"eval_runtime": 10.0427,
|
96 |
+
"eval_samples_per_second": 543.975,
|
97 |
+
"eval_steps_per_second": 4.282,
|
98 |
+
"step": 4914
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"learning_rate": 3.44e-05,
|
103 |
+
"loss": 0.2864,
|
104 |
+
"step": 5733
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.0,
|
108 |
+
"eval_accuracy": 0.7829031667581915,
|
109 |
+
"eval_loss": 0.5454465746879578,
|
110 |
+
"eval_runtime": 10.0511,
|
111 |
+
"eval_samples_per_second": 543.525,
|
112 |
+
"eval_steps_per_second": 4.278,
|
113 |
+
"step": 5733
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 8.0,
|
117 |
+
"learning_rate": 3.3600000000000004e-05,
|
118 |
+
"loss": 0.2482,
|
119 |
+
"step": 6552
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 8.0,
|
123 |
+
"eval_accuracy": 0.7700896943071572,
|
124 |
+
"eval_loss": 0.5525962114334106,
|
125 |
+
"eval_runtime": 10.0206,
|
126 |
+
"eval_samples_per_second": 545.178,
|
127 |
+
"eval_steps_per_second": 4.291,
|
128 |
+
"step": 6552
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 9.0,
|
132 |
+
"learning_rate": 3.28e-05,
|
133 |
+
"loss": 0.2146,
|
134 |
+
"step": 7371
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 9.0,
|
138 |
+
"eval_accuracy": 0.7834523155775215,
|
139 |
+
"eval_loss": 0.5931808948516846,
|
140 |
+
"eval_runtime": 10.0523,
|
141 |
+
"eval_samples_per_second": 543.455,
|
142 |
+
"eval_steps_per_second": 4.278,
|
143 |
+
"step": 7371
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 10.0,
|
147 |
+
"learning_rate": 3.2000000000000005e-05,
|
148 |
+
"loss": 0.1825,
|
149 |
+
"step": 8190
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 10.0,
|
153 |
+
"eval_accuracy": 0.7752150832875709,
|
154 |
+
"eval_loss": 0.6240017414093018,
|
155 |
+
"eval_runtime": 10.0826,
|
156 |
+
"eval_samples_per_second": 541.827,
|
157 |
+
"eval_steps_per_second": 4.265,
|
158 |
+
"step": 8190
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 10.0,
|
162 |
+
"step": 8190,
|
163 |
+
"total_flos": 1.5512100096966656e+17,
|
164 |
+
"train_loss": 0.35937960372011885,
|
165 |
+
"train_runtime": 5750.0945,
|
166 |
+
"train_samples_per_second": 910.794,
|
167 |
+
"train_steps_per_second": 7.122
|
168 |
+
}
|
169 |
+
],
|
170 |
+
"max_steps": 40950,
|
171 |
+
"num_train_epochs": 50,
|
172 |
+
"total_flos": 1.5512100096966656e+17,
|
173 |
+
"trial_name": null,
|
174 |
+
"trial_params": null
|
175 |
+
}
|