gokulsrinivasagan
commited on
Commit
•
586982a
1
Parent(s):
8364fc5
End of training
Browse files- README.md +17 -2
- all_results.json +15 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1732641497.ki-g0008.2136969.5 +3 -0
- train_results.json +9 -0
- trainer_state.json +147 -0
README.md
CHANGED
@@ -1,13 +1,28 @@
|
|
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 |
model-index:
|
9 |
- name: bert_base_lda_20_v1_qnli
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,7 +30,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# bert_base_lda_20_v1_qnli
|
17 |
|
18 |
-
This model is a fine-tuned version of [gokulsrinivasagan/bert_base_lda_20_v1](https://huggingface.co/gokulsrinivasagan/bert_base_lda_20_v1) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.6933
|
21 |
- Accuracy: 0.5054
|
|
|
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 |
model-index:
|
13 |
- name: bert_base_lda_20_v1_qnli
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Text Classification
|
17 |
+
type: text-classification
|
18 |
+
dataset:
|
19 |
+
name: GLUE QNLI
|
20 |
+
type: glue
|
21 |
+
args: qnli
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.5053999633900788
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# bert_base_lda_20_v1_qnli
|
32 |
|
33 |
+
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 QNLI dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
- Loss: 0.6933
|
36 |
- Accuracy: 0.5054
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"eval_accuracy": 0.5053999633900788,
|
4 |
+
"eval_loss": 0.6933382749557495,
|
5 |
+
"eval_runtime": 3.491,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 1564.864,
|
8 |
+
"eval_steps_per_second": 6.302,
|
9 |
+
"total_flos": 8.267712381471744e+16,
|
10 |
+
"train_loss": 0.7020159961731454,
|
11 |
+
"train_runtime": 1044.8612,
|
12 |
+
"train_samples": 104743,
|
13 |
+
"train_samples_per_second": 5012.293,
|
14 |
+
"train_steps_per_second": 19.62
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"eval_accuracy": 0.5053999633900788,
|
4 |
+
"eval_loss": 0.6933382749557495,
|
5 |
+
"eval_runtime": 3.491,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 1564.864,
|
8 |
+
"eval_steps_per_second": 6.302
|
9 |
+
}
|
logs/events.out.tfevents.1732641497.ki-g0008.2136969.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e69f4db1f7ba5360afe9cef4f358f86996df3a8b6a6a40e7f4767bc59c0aba2
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"total_flos": 8.267712381471744e+16,
|
4 |
+
"train_loss": 0.7020159961731454,
|
5 |
+
"train_runtime": 1044.8612,
|
6 |
+
"train_samples": 104743,
|
7 |
+
"train_samples_per_second": 5012.293,
|
8 |
+
"train_steps_per_second": 19.62
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6933382749557495,
|
3 |
+
"best_model_checkpoint": "bert_base_lda_20_v1_qnli/checkpoint-410",
|
4 |
+
"epoch": 6.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2460,
|
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": 0.12706193327903748,
|
14 |
+
"learning_rate": 0.00098,
|
15 |
+
"loss": 0.7463,
|
16 |
+
"step": 410
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.5053999633900788,
|
21 |
+
"eval_loss": 0.6933382749557495,
|
22 |
+
"eval_runtime": 3.5554,
|
23 |
+
"eval_samples_per_second": 1536.551,
|
24 |
+
"eval_steps_per_second": 6.188,
|
25 |
+
"step": 410
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"grad_norm": 0.09045995026826859,
|
30 |
+
"learning_rate": 0.00096,
|
31 |
+
"loss": 0.6932,
|
32 |
+
"step": 820
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.5053999633900788,
|
37 |
+
"eval_loss": 0.6933382749557495,
|
38 |
+
"eval_runtime": 3.4846,
|
39 |
+
"eval_samples_per_second": 1567.745,
|
40 |
+
"eval_steps_per_second": 6.313,
|
41 |
+
"step": 820
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"grad_norm": 0.1270582526922226,
|
46 |
+
"learning_rate": 0.00094,
|
47 |
+
"loss": 0.6932,
|
48 |
+
"step": 1230
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.5053999633900788,
|
53 |
+
"eval_loss": 0.6933382749557495,
|
54 |
+
"eval_runtime": 3.5053,
|
55 |
+
"eval_samples_per_second": 1558.508,
|
56 |
+
"eval_steps_per_second": 6.276,
|
57 |
+
"step": 1230
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.0,
|
61 |
+
"grad_norm": 0.01812651753425598,
|
62 |
+
"learning_rate": 0.00092,
|
63 |
+
"loss": 0.6931,
|
64 |
+
"step": 1640
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 4.0,
|
68 |
+
"eval_accuracy": 0.5053999633900788,
|
69 |
+
"eval_loss": 0.6933382749557495,
|
70 |
+
"eval_runtime": 3.4781,
|
71 |
+
"eval_samples_per_second": 1570.686,
|
72 |
+
"eval_steps_per_second": 6.325,
|
73 |
+
"step": 1640
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 5.0,
|
77 |
+
"grad_norm": 0.047646842896938324,
|
78 |
+
"learning_rate": 0.0009000000000000001,
|
79 |
+
"loss": 0.6931,
|
80 |
+
"step": 2050
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 5.0,
|
84 |
+
"eval_accuracy": 0.4946000366099213,
|
85 |
+
"eval_loss": 0.6934648156166077,
|
86 |
+
"eval_runtime": 3.5198,
|
87 |
+
"eval_samples_per_second": 1552.085,
|
88 |
+
"eval_steps_per_second": 6.25,
|
89 |
+
"step": 2050
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"grad_norm": 0.05455218255519867,
|
94 |
+
"learning_rate": 0.00088,
|
95 |
+
"loss": 0.6932,
|
96 |
+
"step": 2460
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 6.0,
|
100 |
+
"eval_accuracy": 0.5053999633900788,
|
101 |
+
"eval_loss": 0.6933382749557495,
|
102 |
+
"eval_runtime": 3.5682,
|
103 |
+
"eval_samples_per_second": 1531.045,
|
104 |
+
"eval_steps_per_second": 6.166,
|
105 |
+
"step": 2460
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 6.0,
|
109 |
+
"step": 2460,
|
110 |
+
"total_flos": 8.267712381471744e+16,
|
111 |
+
"train_loss": 0.7020159961731454,
|
112 |
+
"train_runtime": 1044.8612,
|
113 |
+
"train_samples_per_second": 5012.293,
|
114 |
+
"train_steps_per_second": 19.62
|
115 |
+
}
|
116 |
+
],
|
117 |
+
"logging_steps": 1,
|
118 |
+
"max_steps": 20500,
|
119 |
+
"num_input_tokens_seen": 0,
|
120 |
+
"num_train_epochs": 50,
|
121 |
+
"save_steps": 500,
|
122 |
+
"stateful_callbacks": {
|
123 |
+
"EarlyStoppingCallback": {
|
124 |
+
"args": {
|
125 |
+
"early_stopping_patience": 5,
|
126 |
+
"early_stopping_threshold": 0.0
|
127 |
+
},
|
128 |
+
"attributes": {
|
129 |
+
"early_stopping_patience_counter": 5
|
130 |
+
}
|
131 |
+
},
|
132 |
+
"TrainerControl": {
|
133 |
+
"args": {
|
134 |
+
"should_epoch_stop": false,
|
135 |
+
"should_evaluate": false,
|
136 |
+
"should_log": false,
|
137 |
+
"should_save": true,
|
138 |
+
"should_training_stop": true
|
139 |
+
},
|
140 |
+
"attributes": {}
|
141 |
+
}
|
142 |
+
},
|
143 |
+
"total_flos": 8.267712381471744e+16,
|
144 |
+
"train_batch_size": 256,
|
145 |
+
"trial_name": null,
|
146 |
+
"trial_params": null
|
147 |
+
}
|