End of training
Browse files- README.md +10 -8
- all_results.json +16 -0
- eval_results.json +11 -0
- logs/events.out.tfevents.1675029928.serv-3334.1026928.5 +3 -0
- train_results.json +8 -0
- trainer_state.json +195 -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
|
@@ -22,10 +24,10 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
- name: F1
|
27 |
type: f1
|
28 |
-
value: 0.
|
29 |
---
|
30 |
|
31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -33,12 +35,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
33 |
|
34 |
# distilbert_sa_GLUE_Experiment_logit_kd_mrpc_384
|
35 |
|
36 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the
|
37 |
It achieves the following results on the evaluation set:
|
38 |
-
- Loss: 0.
|
39 |
-
- Accuracy: 0.
|
40 |
-
- F1: 0.
|
41 |
-
- Combined Score: 0.
|
42 |
|
43 |
## Model description
|
44 |
|
|
|
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
|
|
|
24 |
metrics:
|
25 |
- name: Accuracy
|
26 |
type: accuracy
|
27 |
+
value: 0.32598039215686275
|
28 |
- name: F1
|
29 |
type: f1
|
30 |
+
value: 0.03508771929824561
|
31 |
---
|
32 |
|
33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
35 |
|
36 |
# distilbert_sa_GLUE_Experiment_logit_kd_mrpc_384
|
37 |
|
38 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the GLUE MRPC dataset.
|
39 |
It achieves the following results on the evaluation set:
|
40 |
+
- Loss: 0.5217
|
41 |
+
- Accuracy: 0.3260
|
42 |
+
- F1: 0.0351
|
43 |
+
- Combined Score: 0.1805
|
44 |
|
45 |
## Model description
|
46 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.32598039215686275,
|
4 |
+
"eval_combined_score": 0.18053405572755418,
|
5 |
+
"eval_f1": 0.03508771929824561,
|
6 |
+
"eval_loss": 0.5217064619064331,
|
7 |
+
"eval_runtime": 0.4752,
|
8 |
+
"eval_samples": 408,
|
9 |
+
"eval_samples_per_second": 858.673,
|
10 |
+
"eval_steps_per_second": 4.209,
|
11 |
+
"train_loss": 0.49644593556722005,
|
12 |
+
"train_runtime": 95.3739,
|
13 |
+
"train_samples": 3668,
|
14 |
+
"train_samples_per_second": 1922.959,
|
15 |
+
"train_steps_per_second": 7.864
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.32598039215686275,
|
4 |
+
"eval_combined_score": 0.18053405572755418,
|
5 |
+
"eval_f1": 0.03508771929824561,
|
6 |
+
"eval_loss": 0.5217064619064331,
|
7 |
+
"eval_runtime": 0.4752,
|
8 |
+
"eval_samples": 408,
|
9 |
+
"eval_samples_per_second": 858.673,
|
10 |
+
"eval_steps_per_second": 4.209
|
11 |
+
}
|
logs/events.out.tfevents.1675029928.serv-3334.1026928.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8581b3982451c31422bb2379e962ff40effeafcc23c68d657b8d432790d4f3a5
|
3 |
+
size 467
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 0.49644593556722005,
|
4 |
+
"train_runtime": 95.3739,
|
5 |
+
"train_samples": 3668,
|
6 |
+
"train_samples_per_second": 1922.959,
|
7 |
+
"train_steps_per_second": 7.864
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5217064619064331,
|
3 |
+
"best_model_checkpoint": "distilbert_sa_GLUE_Experiment_logit_kd_mrpc_384/checkpoint-75",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 150,
|
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": 0.5343,
|
14 |
+
"step": 15
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.3161764705882353,
|
19 |
+
"eval_combined_score": 0.15808823529411764,
|
20 |
+
"eval_f1": 0.0,
|
21 |
+
"eval_loss": 0.5287961959838867,
|
22 |
+
"eval_runtime": 0.4408,
|
23 |
+
"eval_samples_per_second": 925.679,
|
24 |
+
"eval_steps_per_second": 4.538,
|
25 |
+
"step": 15
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"learning_rate": 4.8e-05,
|
30 |
+
"loss": 0.5306,
|
31 |
+
"step": 30
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 2.0,
|
35 |
+
"eval_accuracy": 0.3161764705882353,
|
36 |
+
"eval_combined_score": 0.15808823529411764,
|
37 |
+
"eval_f1": 0.0,
|
38 |
+
"eval_loss": 0.5288825035095215,
|
39 |
+
"eval_runtime": 0.4436,
|
40 |
+
"eval_samples_per_second": 919.763,
|
41 |
+
"eval_steps_per_second": 4.509,
|
42 |
+
"step": 30
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"learning_rate": 4.7e-05,
|
47 |
+
"loss": 0.5294,
|
48 |
+
"step": 45
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.3161764705882353,
|
53 |
+
"eval_combined_score": 0.15808823529411764,
|
54 |
+
"eval_f1": 0.0,
|
55 |
+
"eval_loss": 0.528052031993866,
|
56 |
+
"eval_runtime": 0.4434,
|
57 |
+
"eval_samples_per_second": 920.115,
|
58 |
+
"eval_steps_per_second": 4.51,
|
59 |
+
"step": 45
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"learning_rate": 4.600000000000001e-05,
|
64 |
+
"loss": 0.5277,
|
65 |
+
"step": 60
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_accuracy": 0.3161764705882353,
|
70 |
+
"eval_combined_score": 0.15808823529411764,
|
71 |
+
"eval_f1": 0.0,
|
72 |
+
"eval_loss": 0.5268933773040771,
|
73 |
+
"eval_runtime": 0.4396,
|
74 |
+
"eval_samples_per_second": 928.212,
|
75 |
+
"eval_steps_per_second": 4.55,
|
76 |
+
"step": 60
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 5.0,
|
80 |
+
"learning_rate": 4.5e-05,
|
81 |
+
"loss": 0.518,
|
82 |
+
"step": 75
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 5.0,
|
86 |
+
"eval_accuracy": 0.32598039215686275,
|
87 |
+
"eval_combined_score": 0.18053405572755418,
|
88 |
+
"eval_f1": 0.03508771929824561,
|
89 |
+
"eval_loss": 0.5217064619064331,
|
90 |
+
"eval_runtime": 0.4401,
|
91 |
+
"eval_samples_per_second": 927.043,
|
92 |
+
"eval_steps_per_second": 4.544,
|
93 |
+
"step": 75
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 6.0,
|
97 |
+
"learning_rate": 4.4000000000000006e-05,
|
98 |
+
"loss": 0.5035,
|
99 |
+
"step": 90
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 6.0,
|
103 |
+
"eval_accuracy": 0.39705882352941174,
|
104 |
+
"eval_combined_score": 0.33026593871081367,
|
105 |
+
"eval_f1": 0.26347305389221554,
|
106 |
+
"eval_loss": 0.5230422616004944,
|
107 |
+
"eval_runtime": 0.4416,
|
108 |
+
"eval_samples_per_second": 923.889,
|
109 |
+
"eval_steps_per_second": 4.529,
|
110 |
+
"step": 90
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"learning_rate": 4.3e-05,
|
115 |
+
"loss": 0.4866,
|
116 |
+
"step": 105
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 7.0,
|
120 |
+
"eval_accuracy": 0.36519607843137253,
|
121 |
+
"eval_combined_score": 0.2635041880830002,
|
122 |
+
"eval_f1": 0.16181229773462785,
|
123 |
+
"eval_loss": 0.53009432554245,
|
124 |
+
"eval_runtime": 0.4421,
|
125 |
+
"eval_samples_per_second": 922.794,
|
126 |
+
"eval_steps_per_second": 4.524,
|
127 |
+
"step": 105
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 8.0,
|
131 |
+
"learning_rate": 4.2e-05,
|
132 |
+
"loss": 0.4624,
|
133 |
+
"step": 120
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 8.0,
|
137 |
+
"eval_accuracy": 0.5147058823529411,
|
138 |
+
"eval_combined_score": 0.5135105766444509,
|
139 |
+
"eval_f1": 0.5123152709359606,
|
140 |
+
"eval_loss": 0.5490625500679016,
|
141 |
+
"eval_runtime": 0.4436,
|
142 |
+
"eval_samples_per_second": 919.726,
|
143 |
+
"eval_steps_per_second": 4.508,
|
144 |
+
"step": 120
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 9.0,
|
148 |
+
"learning_rate": 4.1e-05,
|
149 |
+
"loss": 0.4424,
|
150 |
+
"step": 135
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 9.0,
|
154 |
+
"eval_accuracy": 0.5245098039215687,
|
155 |
+
"eval_combined_score": 0.5387525978133189,
|
156 |
+
"eval_f1": 0.5529953917050691,
|
157 |
+
"eval_loss": 0.5479305386543274,
|
158 |
+
"eval_runtime": 0.4408,
|
159 |
+
"eval_samples_per_second": 925.499,
|
160 |
+
"eval_steps_per_second": 4.537,
|
161 |
+
"step": 135
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 10.0,
|
165 |
+
"learning_rate": 4e-05,
|
166 |
+
"loss": 0.4295,
|
167 |
+
"step": 150
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 10.0,
|
171 |
+
"eval_accuracy": 0.5392156862745098,
|
172 |
+
"eval_combined_score": 0.5578961314255432,
|
173 |
+
"eval_f1": 0.5765765765765766,
|
174 |
+
"eval_loss": 0.5659680962562561,
|
175 |
+
"eval_runtime": 0.4385,
|
176 |
+
"eval_samples_per_second": 930.384,
|
177 |
+
"eval_steps_per_second": 4.561,
|
178 |
+
"step": 150
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 10.0,
|
182 |
+
"step": 150,
|
183 |
+
"total_flos": 1007551764234240.0,
|
184 |
+
"train_loss": 0.49644593556722005,
|
185 |
+
"train_runtime": 95.3739,
|
186 |
+
"train_samples_per_second": 1922.959,
|
187 |
+
"train_steps_per_second": 7.864
|
188 |
+
}
|
189 |
+
],
|
190 |
+
"max_steps": 750,
|
191 |
+
"num_train_epochs": 50,
|
192 |
+
"total_flos": 1007551764234240.0,
|
193 |
+
"trial_name": null,
|
194 |
+
"trial_params": null
|
195 |
+
}
|