End of training
Browse files- README.md +7 -5
- all_results.json +14 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1674737262.glendale.2596728.8 +3 -0
- train_results.json +8 -0
- trainer_state.json +175 -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_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: 0.6071755445725792
|
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_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: 0.6575
|
37 |
+
- Accuracy: 0.6072
|
38 |
|
39 |
## Model description
|
40 |
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.6071755445725792,
|
4 |
+
"eval_loss": 0.6574940085411072,
|
5 |
+
"eval_runtime": 2.3347,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 2339.949,
|
8 |
+
"eval_steps_per_second": 9.423,
|
9 |
+
"train_loss": 0.651266948420827,
|
10 |
+
"train_runtime": 839.7217,
|
11 |
+
"train_samples": 104743,
|
12 |
+
"train_samples_per_second": 6236.768,
|
13 |
+
"train_steps_per_second": 24.413
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.6071755445725792,
|
4 |
+
"eval_loss": 0.6574940085411072,
|
5 |
+
"eval_runtime": 2.3347,
|
6 |
+
"eval_samples": 5463,
|
7 |
+
"eval_samples_per_second": 2339.949,
|
8 |
+
"eval_steps_per_second": 9.423
|
9 |
+
}
|
logs/events.out.tfevents.1674737262.glendale.2596728.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d6cdfca0fa79b18facc640c90ebc582d7f4aa6aca6835e057285b92a0a7964f
|
3 |
+
size 363
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 0.651266948420827,
|
4 |
+
"train_runtime": 839.7217,
|
5 |
+
"train_samples": 104743,
|
6 |
+
"train_samples_per_second": 6236.768,
|
7 |
+
"train_steps_per_second": 24.413
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6574940085411072,
|
3 |
+
"best_model_checkpoint": "distilbert_add_GLUE_Experiment_qnli_96/checkpoint-2050",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 4100,
|
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": 0.6932,
|
14 |
+
"step": 410
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.4946000366099213,
|
19 |
+
"eval_loss": 0.6931495070457458,
|
20 |
+
"eval_runtime": 2.18,
|
21 |
+
"eval_samples_per_second": 2505.925,
|
22 |
+
"eval_steps_per_second": 10.092,
|
23 |
+
"step": 410
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 4.8e-05,
|
28 |
+
"loss": 0.6932,
|
29 |
+
"step": 820
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.4946000366099213,
|
34 |
+
"eval_loss": 0.6931758522987366,
|
35 |
+
"eval_runtime": 2.2333,
|
36 |
+
"eval_samples_per_second": 2446.178,
|
37 |
+
"eval_steps_per_second": 9.851,
|
38 |
+
"step": 820
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 4.7e-05,
|
43 |
+
"loss": 0.6932,
|
44 |
+
"step": 1230
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.5053999633900788,
|
49 |
+
"eval_loss": 0.6930550336837769,
|
50 |
+
"eval_runtime": 2.2746,
|
51 |
+
"eval_samples_per_second": 2401.706,
|
52 |
+
"eval_steps_per_second": 9.672,
|
53 |
+
"step": 1230
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"learning_rate": 4.600000000000001e-05,
|
58 |
+
"loss": 0.6826,
|
59 |
+
"step": 1640
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_accuracy": 0.5967417170053084,
|
64 |
+
"eval_loss": 0.6659221053123474,
|
65 |
+
"eval_runtime": 2.27,
|
66 |
+
"eval_samples_per_second": 2406.63,
|
67 |
+
"eval_steps_per_second": 9.692,
|
68 |
+
"step": 1640
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"learning_rate": 4.5e-05,
|
73 |
+
"loss": 0.6539,
|
74 |
+
"step": 2050
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_accuracy": 0.6071755445725792,
|
79 |
+
"eval_loss": 0.6574940085411072,
|
80 |
+
"eval_runtime": 2.2051,
|
81 |
+
"eval_samples_per_second": 2477.384,
|
82 |
+
"eval_steps_per_second": 9.977,
|
83 |
+
"step": 2050
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"learning_rate": 4.4000000000000006e-05,
|
88 |
+
"loss": 0.6403,
|
89 |
+
"step": 2460
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"eval_accuracy": 0.6073585941790225,
|
94 |
+
"eval_loss": 0.660847008228302,
|
95 |
+
"eval_runtime": 2.3863,
|
96 |
+
"eval_samples_per_second": 2289.345,
|
97 |
+
"eval_steps_per_second": 9.219,
|
98 |
+
"step": 2460
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"learning_rate": 4.3e-05,
|
103 |
+
"loss": 0.6288,
|
104 |
+
"step": 2870
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.0,
|
108 |
+
"eval_accuracy": 0.603880651656599,
|
109 |
+
"eval_loss": 0.6702004671096802,
|
110 |
+
"eval_runtime": 2.9467,
|
111 |
+
"eval_samples_per_second": 1853.935,
|
112 |
+
"eval_steps_per_second": 7.466,
|
113 |
+
"step": 2870
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 8.0,
|
117 |
+
"learning_rate": 4.2e-05,
|
118 |
+
"loss": 0.6186,
|
119 |
+
"step": 3280
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 8.0,
|
123 |
+
"eval_accuracy": 0.6022332051986088,
|
124 |
+
"eval_loss": 0.6729844808578491,
|
125 |
+
"eval_runtime": 2.2837,
|
126 |
+
"eval_samples_per_second": 2392.185,
|
127 |
+
"eval_steps_per_second": 9.634,
|
128 |
+
"step": 3280
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 9.0,
|
132 |
+
"learning_rate": 4.1e-05,
|
133 |
+
"loss": 0.6094,
|
134 |
+
"step": 3690
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 9.0,
|
138 |
+
"eval_accuracy": 0.6013179571663921,
|
139 |
+
"eval_loss": 0.6739695072174072,
|
140 |
+
"eval_runtime": 2.3362,
|
141 |
+
"eval_samples_per_second": 2338.401,
|
142 |
+
"eval_steps_per_second": 9.417,
|
143 |
+
"step": 3690
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 10.0,
|
147 |
+
"learning_rate": 4e-05,
|
148 |
+
"loss": 0.5995,
|
149 |
+
"step": 4100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 10.0,
|
153 |
+
"eval_accuracy": 0.5919824272377814,
|
154 |
+
"eval_loss": 0.6906076073646545,
|
155 |
+
"eval_runtime": 2.2795,
|
156 |
+
"eval_samples_per_second": 2396.535,
|
157 |
+
"eval_steps_per_second": 9.651,
|
158 |
+
"step": 4100
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 10.0,
|
162 |
+
"step": 4100,
|
163 |
+
"total_flos": 6016944507453440.0,
|
164 |
+
"train_loss": 0.651266948420827,
|
165 |
+
"train_runtime": 839.7217,
|
166 |
+
"train_samples_per_second": 6236.768,
|
167 |
+
"train_steps_per_second": 24.413
|
168 |
+
}
|
169 |
+
],
|
170 |
+
"max_steps": 20500,
|
171 |
+
"num_train_epochs": 50,
|
172 |
+
"total_flos": 6016944507453440.0,
|
173 |
+
"trial_name": null,
|
174 |
+
"trial_params": null
|
175 |
+
}
|