Commit
•
b461693
1
Parent(s):
eed4a4f
End of training
Browse files- ABSA_Sentiment_classification_pfeiffer/adapter_config.json +41 -0
- ABSA_Sentiment_classification_pfeiffer/head_config.json +21 -0
- ABSA_Sentiment_classification_pfeiffer/pytorch_adapter.bin +3 -0
- ABSA_Sentiment_classification_pfeiffer/pytorch_model_head.bin +3 -0
- all_results.json +24 -0
- eval_results.json +11 -0
- mlm/adapter_config.json +41 -0
- mlm/head_config.json +19 -0
- mlm/pytorch_adapter.bin +3 -0
- mlm/pytorch_model_head.bin +3 -0
- runs/Jul05_00-55-18_e7d1b58f91de/events.out.tfevents.1688518529.e7d1b58f91de.3129.0 +2 -2
- runs/Jul05_00-55-18_e7d1b58f91de/events.out.tfevents.1688520533.e7d1b58f91de.3129.2 +3 -0
- test_results.json +10 -0
- train_results.json +8 -0
ABSA_Sentiment_classification_pfeiffer/adapter_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": {
|
3 |
+
"adapter_residual_before_ln": false,
|
4 |
+
"cross_adapter": false,
|
5 |
+
"factorized_phm_W": true,
|
6 |
+
"factorized_phm_rule": false,
|
7 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
8 |
+
"init_weights": "bert",
|
9 |
+
"inv_adapter": null,
|
10 |
+
"inv_adapter_reduction_factor": null,
|
11 |
+
"is_parallel": false,
|
12 |
+
"learn_phm": true,
|
13 |
+
"leave_out": [],
|
14 |
+
"ln_after": false,
|
15 |
+
"ln_before": false,
|
16 |
+
"mh_adapter": false,
|
17 |
+
"non_linearity": "relu",
|
18 |
+
"original_ln_after": true,
|
19 |
+
"original_ln_before": true,
|
20 |
+
"output_adapter": true,
|
21 |
+
"phm_bias": true,
|
22 |
+
"phm_c_init": "normal",
|
23 |
+
"phm_dim": 4,
|
24 |
+
"phm_init_range": 0.0001,
|
25 |
+
"phm_layer": false,
|
26 |
+
"phm_rank": 1,
|
27 |
+
"reduction_factor": 16,
|
28 |
+
"residual_before_ln": true,
|
29 |
+
"scaling": 1.0,
|
30 |
+
"shared_W_phm": false,
|
31 |
+
"shared_phm_rule": true,
|
32 |
+
"use_gating": false
|
33 |
+
},
|
34 |
+
"config_id": "9076f36a74755ac4",
|
35 |
+
"hidden_size": 768,
|
36 |
+
"model_class": "BertModelWithHeads",
|
37 |
+
"model_name": "CAMeL-Lab/bert-base-arabic-camelbert-msa",
|
38 |
+
"model_type": "bert",
|
39 |
+
"name": "ABSA_Sentiment_classification_pfeiffer",
|
40 |
+
"version": "3.2.1"
|
41 |
+
}
|
ABSA_Sentiment_classification_pfeiffer/head_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": {
|
3 |
+
"activation_function": "tanh",
|
4 |
+
"bias": true,
|
5 |
+
"head_type": "classification",
|
6 |
+
"label2id": {
|
7 |
+
"negative": 0,
|
8 |
+
"neutral": 2,
|
9 |
+
"positive": 1
|
10 |
+
},
|
11 |
+
"layers": 2,
|
12 |
+
"num_labels": 3,
|
13 |
+
"use_pooler": false
|
14 |
+
},
|
15 |
+
"hidden_size": 768,
|
16 |
+
"model_class": "BertModelWithHeads",
|
17 |
+
"model_name": "CAMeL-Lab/bert-base-arabic-camelbert-msa",
|
18 |
+
"model_type": "bert",
|
19 |
+
"name": "ABSA_Sentiment_classification_pfeiffer",
|
20 |
+
"version": "3.2.1"
|
21 |
+
}
|
ABSA_Sentiment_classification_pfeiffer/pytorch_adapter.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e48536ebbac71b93040f49ab238974788b0fb9cd89d74d91e933dc04a0fef6c
|
3 |
+
size 3596581
|
ABSA_Sentiment_classification_pfeiffer/pytorch_model_head.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa195e5ed6c591bf43cc5ff3d601fff605b03d316fde9e10dcff78a63a9096eb
|
3 |
+
size 2373409
|
all_results.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.8602673147023087,
|
4 |
+
"eval_f1": 0.8602673147023087,
|
5 |
+
"eval_loss": 0.3666096329689026,
|
6 |
+
"eval_precision": 0.8602673147023087,
|
7 |
+
"eval_recall": 0.8602673147023087,
|
8 |
+
"eval_runtime": 14.7351,
|
9 |
+
"eval_samples_per_second": 111.706,
|
10 |
+
"eval_steps_per_second": 3.529,
|
11 |
+
"test_accuracy": 0.8744546776539021,
|
12 |
+
"test_f1": 0.8744546776539021,
|
13 |
+
"test_loss": 0.33471325039863586,
|
14 |
+
"test_precision": 0.8744546776539021,
|
15 |
+
"test_recall": 0.8744546776539021,
|
16 |
+
"test_runtime": 17.0482,
|
17 |
+
"test_samples_per_second": 121.01,
|
18 |
+
"test_steps_per_second": 3.813,
|
19 |
+
"total_flos": 6677689238755416.0,
|
20 |
+
"train_loss": 0.28295206213460383,
|
21 |
+
"train_runtime": 1990.0002,
|
22 |
+
"train_samples_per_second": 66.131,
|
23 |
+
"train_steps_per_second": 2.07
|
24 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.8602673147023087,
|
4 |
+
"eval_f1": 0.8602673147023087,
|
5 |
+
"eval_loss": 0.3666096329689026,
|
6 |
+
"eval_precision": 0.8602673147023087,
|
7 |
+
"eval_recall": 0.8602673147023087,
|
8 |
+
"eval_runtime": 14.7351,
|
9 |
+
"eval_samples_per_second": 111.706,
|
10 |
+
"eval_steps_per_second": 3.529
|
11 |
+
}
|
mlm/adapter_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": {
|
3 |
+
"adapter_residual_before_ln": false,
|
4 |
+
"cross_adapter": false,
|
5 |
+
"factorized_phm_W": true,
|
6 |
+
"factorized_phm_rule": false,
|
7 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
8 |
+
"init_weights": "bert",
|
9 |
+
"inv_adapter": "nice",
|
10 |
+
"inv_adapter_reduction_factor": 2,
|
11 |
+
"is_parallel": false,
|
12 |
+
"learn_phm": true,
|
13 |
+
"leave_out": [],
|
14 |
+
"ln_after": false,
|
15 |
+
"ln_before": false,
|
16 |
+
"mh_adapter": false,
|
17 |
+
"non_linearity": "relu",
|
18 |
+
"original_ln_after": true,
|
19 |
+
"original_ln_before": true,
|
20 |
+
"output_adapter": true,
|
21 |
+
"phm_bias": true,
|
22 |
+
"phm_c_init": "normal",
|
23 |
+
"phm_dim": 4,
|
24 |
+
"phm_init_range": 0.0001,
|
25 |
+
"phm_layer": false,
|
26 |
+
"phm_rank": 1,
|
27 |
+
"reduction_factor": 16,
|
28 |
+
"residual_before_ln": true,
|
29 |
+
"scaling": 1.0,
|
30 |
+
"shared_W_phm": false,
|
31 |
+
"shared_phm_rule": true,
|
32 |
+
"use_gating": false
|
33 |
+
},
|
34 |
+
"config_id": "9ed5b5a29de19b71",
|
35 |
+
"hidden_size": 768,
|
36 |
+
"model_class": "BertModelWithHeads",
|
37 |
+
"model_name": "CAMeL-Lab/bert-base-arabic-camelbert-msa",
|
38 |
+
"model_type": "bert",
|
39 |
+
"name": "mlm",
|
40 |
+
"version": "3.2.1"
|
41 |
+
}
|
mlm/head_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config": {
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"bias": true,
|
5 |
+
"embedding_size": 768,
|
6 |
+
"head_type": "masked_lm",
|
7 |
+
"label2id": null,
|
8 |
+
"layer_norm": true,
|
9 |
+
"layers": 2,
|
10 |
+
"shift_labels": false,
|
11 |
+
"vocab_size": 30000
|
12 |
+
},
|
13 |
+
"hidden_size": 768,
|
14 |
+
"model_class": "BertModelWithHeads",
|
15 |
+
"model_name": "CAMeL-Lab/bert-base-arabic-camelbert-msa",
|
16 |
+
"model_type": "bert",
|
17 |
+
"name": "mlm",
|
18 |
+
"version": "3.2.1"
|
19 |
+
}
|
mlm/pytorch_adapter.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fe7e729c4de1953e7784cabb44a321fd0f2a8cfe4b11182cef5d2d7ed12a430
|
3 |
+
size 4781837
|
mlm/pytorch_model_head.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:faa9818390df8e5b73959629c1d63d9f131b7c8d996380be3fed6a455194b344
|
3 |
+
size 94650799
|
runs/Jul05_00-55-18_e7d1b58f91de/events.out.tfevents.1688518529.e7d1b58f91de.3129.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d575db3717220190df740726c329d0857260c7123a8337930ce4df4c003bff98
|
3 |
+
size 19936
|
runs/Jul05_00-55-18_e7d1b58f91de/events.out.tfevents.1688520533.e7d1b58f91de.3129.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:187a24b8bc02e1e50c295755c3ba4c9243dbdf67589559e463fb2931d50e0786
|
3 |
+
size 1032
|
test_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"test_accuracy": 0.8744546776539021,
|
3 |
+
"test_f1": 0.8744546776539021,
|
4 |
+
"test_loss": 0.33471325039863586,
|
5 |
+
"test_precision": 0.8744546776539021,
|
6 |
+
"test_recall": 0.8744546776539021,
|
7 |
+
"test_runtime": 17.0482,
|
8 |
+
"test_samples_per_second": 121.01,
|
9 |
+
"test_steps_per_second": 3.813
|
10 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 20.0,
|
3 |
+
"total_flos": 6677689238755416.0,
|
4 |
+
"train_loss": 0.28295206213460383,
|
5 |
+
"train_runtime": 1990.0002,
|
6 |
+
"train_samples_per_second": 66.131,
|
7 |
+
"train_steps_per_second": 2.07
|
8 |
+
}
|