End of training
Browse files- README.md +7 -5
- all_results.json +14 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1674949306.serv-3334.540580.8 +3 -0
- train_results.json +8 -0
- trainer_state.json +160 -0
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
@@ -13,7 +15,7 @@ model-index:
|
|
13 |
name: Text Classification
|
14 |
type: text-classification
|
15 |
dataset:
|
16 |
-
name:
|
17 |
type: glue
|
18 |
config: qnli
|
19 |
split: validation
|
@@ -21,7 +23,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
-
value: 0.
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -29,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
29 |
|
30 |
# distilbert_add_GLUE_Experiment_logit_kd_qnli_96
|
31 |
|
32 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss: 0.
|
35 |
-
- Accuracy: 0.
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
15 |
name: Text Classification
|
16 |
type: text-classification
|
17 |
dataset:
|
18 |
+
name: GLUE QNLI
|
19 |
type: glue
|
20 |
config: qnli
|
21 |
split: validation
|
|
|
23 |
metrics:
|
24 |
- name: Accuracy
|
25 |
type: accuracy
|
26 |
+
value: 0.580633351638294
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
# distilbert_add_GLUE_Experiment_logit_kd_qnli_96
|
33 |
|
34 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the GLUE QNLI dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.3984
|
37 |
+
- Accuracy: 0.5806
|
38 |
|
39 |
## Model description
|
40 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.0,
|
3 |
+
"eval_accuracy": 0.580633351638294,
|
4 |
+
"eval_loss": 0.39838820695877075,
|
5 |
+
"eval_runtime": 5.3106,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 1028.7,
|
8 |
+
"eval_steps_per_second": 4.143,
|
9 |
+
"train_loss": 0.396416024722381,
|
10 |
+
"train_runtime": 1171.9486,
|
11 |
+
"train_samples": 104743,
|
12 |
+
"train_samples_per_second": 4468.754,
|
13 |
+
"train_steps_per_second": 17.492
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.0,
|
3 |
+
"eval_accuracy": 0.580633351638294,
|
4 |
+
"eval_loss": 0.39838820695877075,
|
5 |
+
"eval_runtime": 5.3106,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 1028.7,
|
8 |
+
"eval_steps_per_second": 4.143
|
9 |
+
}
|
logs/events.out.tfevents.1674949306.serv-3334.540580.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ea2c6750f34c6d708ff44fd72e6869c8c1dc531a51bd368aa04f4be125e1505
|
3 |
+
size 363
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.0,
|
3 |
+
"train_loss": 0.396416024722381,
|
4 |
+
"train_runtime": 1171.9486,
|
5 |
+
"train_samples": 104743,
|
6 |
+
"train_samples_per_second": 4468.754,
|
7 |
+
"train_steps_per_second": 17.492
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.39838820695877075,
|
3 |
+
"best_model_checkpoint": "distilbert_add_GLUE_Experiment_logit_kd_qnli_96/checkpoint-1640",
|
4 |
+
"epoch": 9.0,
|
5 |
+
"global_step": 3690,
|
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": 4.9e-05,
|
13 |
+
"loss": 0.4153,
|
14 |
+
"step": 410
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.5053999633900788,
|
19 |
+
"eval_loss": 0.4113771617412567,
|
20 |
+
"eval_runtime": 5.2932,
|
21 |
+
"eval_samples_per_second": 1032.078,
|
22 |
+
"eval_steps_per_second": 4.156,
|
23 |
+
"step": 410
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 4.8e-05,
|
28 |
+
"loss": 0.4152,
|
29 |
+
"step": 820
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.5053999633900788,
|
34 |
+
"eval_loss": 0.4115099012851715,
|
35 |
+
"eval_runtime": 5.1775,
|
36 |
+
"eval_samples_per_second": 1055.137,
|
37 |
+
"eval_steps_per_second": 4.249,
|
38 |
+
"step": 820
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 4.7e-05,
|
43 |
+
"loss": 0.4129,
|
44 |
+
"step": 1230
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.5685520776130332,
|
49 |
+
"eval_loss": 0.4019591510295868,
|
50 |
+
"eval_runtime": 5.1907,
|
51 |
+
"eval_samples_per_second": 1052.462,
|
52 |
+
"eval_steps_per_second": 4.238,
|
53 |
+
"step": 1230
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"learning_rate": 4.600000000000001e-05,
|
58 |
+
"loss": 0.3995,
|
59 |
+
"step": 1640
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_accuracy": 0.580633351638294,
|
64 |
+
"eval_loss": 0.39838820695877075,
|
65 |
+
"eval_runtime": 5.1978,
|
66 |
+
"eval_samples_per_second": 1051.02,
|
67 |
+
"eval_steps_per_second": 4.233,
|
68 |
+
"step": 1640
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"learning_rate": 4.5e-05,
|
73 |
+
"loss": 0.3934,
|
74 |
+
"step": 2050
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_accuracy": 0.5793520043931906,
|
79 |
+
"eval_loss": 0.3992016017436981,
|
80 |
+
"eval_runtime": 5.1986,
|
81 |
+
"eval_samples_per_second": 1050.862,
|
82 |
+
"eval_steps_per_second": 4.232,
|
83 |
+
"step": 2050
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"learning_rate": 4.4000000000000006e-05,
|
88 |
+
"loss": 0.3888,
|
89 |
+
"step": 2460
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"eval_accuracy": 0.5809994508511807,
|
94 |
+
"eval_loss": 0.4023948609828949,
|
95 |
+
"eval_runtime": 5.2149,
|
96 |
+
"eval_samples_per_second": 1047.584,
|
97 |
+
"eval_steps_per_second": 4.219,
|
98 |
+
"step": 2460
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"learning_rate": 4.3e-05,
|
103 |
+
"loss": 0.385,
|
104 |
+
"step": 2870
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.0,
|
108 |
+
"eval_accuracy": 0.5674537799743731,
|
109 |
+
"eval_loss": 0.4104597866535187,
|
110 |
+
"eval_runtime": 5.2043,
|
111 |
+
"eval_samples_per_second": 1049.712,
|
112 |
+
"eval_steps_per_second": 4.227,
|
113 |
+
"step": 2870
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 8.0,
|
117 |
+
"learning_rate": 4.2e-05,
|
118 |
+
"loss": 0.3808,
|
119 |
+
"step": 3280
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 8.0,
|
123 |
+
"eval_accuracy": 0.5777045579352005,
|
124 |
+
"eval_loss": 0.4049883186817169,
|
125 |
+
"eval_runtime": 5.1888,
|
126 |
+
"eval_samples_per_second": 1052.838,
|
127 |
+
"eval_steps_per_second": 4.24,
|
128 |
+
"step": 3280
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 9.0,
|
132 |
+
"learning_rate": 4.1e-05,
|
133 |
+
"loss": 0.3768,
|
134 |
+
"step": 3690
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 9.0,
|
138 |
+
"eval_accuracy": 0.5722130697419,
|
139 |
+
"eval_loss": 0.4074430465698242,
|
140 |
+
"eval_runtime": 5.2968,
|
141 |
+
"eval_samples_per_second": 1031.375,
|
142 |
+
"eval_steps_per_second": 4.153,
|
143 |
+
"step": 3690
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 9.0,
|
147 |
+
"step": 3690,
|
148 |
+
"total_flos": 5415250056708096.0,
|
149 |
+
"train_loss": 0.396416024722381,
|
150 |
+
"train_runtime": 1171.9486,
|
151 |
+
"train_samples_per_second": 4468.754,
|
152 |
+
"train_steps_per_second": 17.492
|
153 |
+
}
|
154 |
+
],
|
155 |
+
"max_steps": 20500,
|
156 |
+
"num_train_epochs": 50,
|
157 |
+
"total_flos": 5415250056708096.0,
|
158 |
+
"trial_name": null,
|
159 |
+
"trial_params": null
|
160 |
+
}
|