End of training
Browse files- README.md +5 -3
- all_results.json +16 -0
- eval_results.json +11 -0
- logs/events.out.tfevents.1674949553.serv-3332.3626077.5 +3 -0
- train_results.json +8 -0
- trainer_state.json +178 -0
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
@@ -14,7 +16,7 @@ model-index:
|
|
14 |
name: Text Classification
|
15 |
type: text-classification
|
16 |
dataset:
|
17 |
-
name:
|
18 |
type: glue
|
19 |
config: mrpc
|
20 |
split: validation
|
@@ -33,9 +35,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
33 |
|
34 |
# mobilebert_add_GLUE_Experiment_logit_kd_mrpc
|
35 |
|
36 |
-
This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the
|
37 |
It achieves the following results on the evaluation set:
|
38 |
-
- Loss: 0.
|
39 |
- Accuracy: 0.6838
|
40 |
- F1: 0.8122
|
41 |
- Combined Score: 0.7480
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
16 |
name: Text Classification
|
17 |
type: text-classification
|
18 |
dataset:
|
19 |
+
name: GLUE MRPC
|
20 |
type: glue
|
21 |
config: mrpc
|
22 |
split: validation
|
|
|
35 |
|
36 |
# mobilebert_add_GLUE_Experiment_logit_kd_mrpc
|
37 |
|
38 |
+
This model is a fine-tuned version of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) on the GLUE MRPC dataset.
|
39 |
It achieves the following results on the evaluation set:
|
40 |
+
- Loss: 0.5529
|
41 |
- Accuracy: 0.6838
|
42 |
- F1: 0.8122
|
43 |
- Combined Score: 0.7480
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.0,
|
3 |
+
"eval_accuracy": 0.6838235294117647,
|
4 |
+
"eval_combined_score": 0.7480253018237863,
|
5 |
+
"eval_f1": 0.8122270742358079,
|
6 |
+
"eval_loss": 0.5529410243034363,
|
7 |
+
"eval_runtime": 0.9959,
|
8 |
+
"eval_samples": 408,
|
9 |
+
"eval_samples_per_second": 409.698,
|
10 |
+
"eval_steps_per_second": 4.017,
|
11 |
+
"train_loss": 0.5956195451290671,
|
12 |
+
"train_runtime": 327.2529,
|
13 |
+
"train_samples": 3668,
|
14 |
+
"train_samples_per_second": 560.423,
|
15 |
+
"train_steps_per_second": 4.431
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.0,
|
3 |
+
"eval_accuracy": 0.6838235294117647,
|
4 |
+
"eval_combined_score": 0.7480253018237863,
|
5 |
+
"eval_f1": 0.8122270742358079,
|
6 |
+
"eval_loss": 0.5529410243034363,
|
7 |
+
"eval_runtime": 0.9959,
|
8 |
+
"eval_samples": 408,
|
9 |
+
"eval_samples_per_second": 409.698,
|
10 |
+
"eval_steps_per_second": 4.017
|
11 |
+
}
|
logs/events.out.tfevents.1674949553.serv-3332.3626077.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d223e53a2c3b12b965494c35922f09acfda7615410b299c098c8ec2c2400370
|
3 |
+
size 467
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.0,
|
3 |
+
"train_loss": 0.5956195451290671,
|
4 |
+
"train_runtime": 327.2529,
|
5 |
+
"train_samples": 3668,
|
6 |
+
"train_samples_per_second": 560.423,
|
7 |
+
"train_steps_per_second": 4.431
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5529410243034363,
|
3 |
+
"best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_mrpc/checkpoint-116",
|
4 |
+
"epoch": 9.0,
|
5 |
+
"global_step": 261,
|
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": 0.6239,
|
14 |
+
"step": 29
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.6838235294117647,
|
19 |
+
"eval_combined_score": 0.7480253018237863,
|
20 |
+
"eval_f1": 0.8122270742358079,
|
21 |
+
"eval_loss": 0.555836021900177,
|
22 |
+
"eval_runtime": 0.9841,
|
23 |
+
"eval_samples_per_second": 414.573,
|
24 |
+
"eval_steps_per_second": 4.064,
|
25 |
+
"step": 29
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"learning_rate": 4.8e-05,
|
30 |
+
"loss": 0.6109,
|
31 |
+
"step": 58
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.6838235294117647,
|
36 |
+
"eval_combined_score": 0.7480253018237863,
|
37 |
+
"eval_f1": 0.8122270742358079,
|
38 |
+
"eval_loss": 0.5552574396133423,
|
39 |
+
"eval_runtime": 0.9796,
|
40 |
+
"eval_samples_per_second": 416.498,
|
41 |
+
"eval_steps_per_second": 4.083,
|
42 |
+
"step": 58
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"learning_rate": 4.7e-05,
|
47 |
+
"loss": 0.6095,
|
48 |
+
"step": 87
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.6838235294117647,
|
53 |
+
"eval_combined_score": 0.7480253018237863,
|
54 |
+
"eval_f1": 0.8122270742358079,
|
55 |
+
"eval_loss": 0.5543215274810791,
|
56 |
+
"eval_runtime": 0.9675,
|
57 |
+
"eval_samples_per_second": 421.725,
|
58 |
+
"eval_steps_per_second": 4.135,
|
59 |
+
"step": 87
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"learning_rate": 4.600000000000001e-05,
|
64 |
+
"loss": 0.6072,
|
65 |
+
"step": 116
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_accuracy": 0.6838235294117647,
|
70 |
+
"eval_combined_score": 0.7480253018237863,
|
71 |
+
"eval_f1": 0.8122270742358079,
|
72 |
+
"eval_loss": 0.5529410243034363,
|
73 |
+
"eval_runtime": 0.9661,
|
74 |
+
"eval_samples_per_second": 422.334,
|
75 |
+
"eval_steps_per_second": 4.141,
|
76 |
+
"step": 116
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 5.0,
|
80 |
+
"learning_rate": 4.5e-05,
|
81 |
+
"loss": 0.5996,
|
82 |
+
"step": 145
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 5.0,
|
86 |
+
"eval_accuracy": 0.6838235294117647,
|
87 |
+
"eval_combined_score": 0.7480253018237863,
|
88 |
+
"eval_f1": 0.8122270742358079,
|
89 |
+
"eval_loss": 0.5556313395500183,
|
90 |
+
"eval_runtime": 0.9685,
|
91 |
+
"eval_samples_per_second": 421.291,
|
92 |
+
"eval_steps_per_second": 4.13,
|
93 |
+
"step": 145
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 6.0,
|
97 |
+
"learning_rate": 4.4000000000000006e-05,
|
98 |
+
"loss": 0.5884,
|
99 |
+
"step": 174
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 6.0,
|
103 |
+
"eval_accuracy": 0.6838235294117647,
|
104 |
+
"eval_combined_score": 0.7480253018237863,
|
105 |
+
"eval_f1": 0.8122270742358079,
|
106 |
+
"eval_loss": 0.5737412571907043,
|
107 |
+
"eval_runtime": 0.9732,
|
108 |
+
"eval_samples_per_second": 419.24,
|
109 |
+
"eval_steps_per_second": 4.11,
|
110 |
+
"step": 174
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"learning_rate": 4.3e-05,
|
115 |
+
"loss": 0.59,
|
116 |
+
"step": 203
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 7.0,
|
120 |
+
"eval_accuracy": 0.6838235294117647,
|
121 |
+
"eval_combined_score": 0.7480253018237863,
|
122 |
+
"eval_f1": 0.8122270742358079,
|
123 |
+
"eval_loss": 0.5704464912414551,
|
124 |
+
"eval_runtime": 0.9691,
|
125 |
+
"eval_samples_per_second": 421.002,
|
126 |
+
"eval_steps_per_second": 4.127,
|
127 |
+
"step": 203
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 8.0,
|
131 |
+
"learning_rate": 4.2e-05,
|
132 |
+
"loss": 0.5715,
|
133 |
+
"step": 232
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 8.0,
|
137 |
+
"eval_accuracy": 0.6813725490196079,
|
138 |
+
"eval_combined_score": 0.7459340879208827,
|
139 |
+
"eval_f1": 0.8104956268221574,
|
140 |
+
"eval_loss": 0.5706341862678528,
|
141 |
+
"eval_runtime": 0.9664,
|
142 |
+
"eval_samples_per_second": 422.182,
|
143 |
+
"eval_steps_per_second": 4.139,
|
144 |
+
"step": 232
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 9.0,
|
148 |
+
"learning_rate": 4.1e-05,
|
149 |
+
"loss": 0.5595,
|
150 |
+
"step": 261
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 9.0,
|
154 |
+
"eval_accuracy": 0.6838235294117647,
|
155 |
+
"eval_combined_score": 0.7480253018237863,
|
156 |
+
"eval_f1": 0.8122270742358079,
|
157 |
+
"eval_loss": 0.5660258531570435,
|
158 |
+
"eval_runtime": 0.9731,
|
159 |
+
"eval_samples_per_second": 419.288,
|
160 |
+
"eval_steps_per_second": 4.111,
|
161 |
+
"step": 261
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 9.0,
|
165 |
+
"step": 261,
|
166 |
+
"total_flos": 976507027587072.0,
|
167 |
+
"train_loss": 0.5956195451290671,
|
168 |
+
"train_runtime": 327.2529,
|
169 |
+
"train_samples_per_second": 560.423,
|
170 |
+
"train_steps_per_second": 4.431
|
171 |
+
}
|
172 |
+
],
|
173 |
+
"max_steps": 1450,
|
174 |
+
"num_train_epochs": 50,
|
175 |
+
"total_flos": 976507027587072.0,
|
176 |
+
"trial_name": null,
|
177 |
+
"trial_params": null
|
178 |
+
}
|