mokcho commited on
Commit
b1e08f5
·
verified ·
1 Parent(s): 38b511d

Delete Aligned-Lambda_0.01

Browse files
Aligned-Lambda_0.01/config.json DELETED
@@ -1,187 +0,0 @@
1
- {
2
- "_name_or_path": "bert-base-multilingual-cased",
3
- "adapters": {
4
- "adapters": {},
5
- "config_map": {},
6
- "fusion_config_map": {},
7
- "fusion_name_map": {},
8
- "fusions": {}
9
- },
10
- "architectures": [
11
- "BertAdapterAlignModel"
12
- ],
13
- "attention_probs_dropout_prob": 0.1,
14
- "classifier_dropout": null,
15
- "directionality": "bidi",
16
- "hidden_act": "gelu",
17
- "hidden_dropout_prob": 0.1,
18
- "hidden_size": 768,
19
- "id2label": {
20
- "0": "_",
21
- "1": "acl",
22
- "2": "advcl",
23
- "3": "advmod",
24
- "4": "amod",
25
- "5": "appos",
26
- "6": "aux",
27
- "7": "case",
28
- "8": "cc",
29
- "9": "ccomp",
30
- "10": "clf",
31
- "11": "compound",
32
- "12": "conj",
33
- "13": "cop",
34
- "14": "csubj",
35
- "15": "dep",
36
- "16": "det",
37
- "17": "discourse",
38
- "18": "dislocated",
39
- "19": "expl",
40
- "20": "fixed",
41
- "21": "flat",
42
- "22": "goeswith",
43
- "23": "iobj",
44
- "24": "list",
45
- "25": "mark",
46
- "26": "nmod",
47
- "27": "nsubj",
48
- "28": "nummod",
49
- "29": "obj",
50
- "30": "obl",
51
- "31": "orphan",
52
- "32": "parataxis",
53
- "33": "punct",
54
- "34": "reparandum",
55
- "35": "root",
56
- "36": "vocative",
57
- "37": "xcomp",
58
- "38": "dup",
59
- "39": "mwe",
60
- "40": "name",
61
- "41": "remnant"
62
- },
63
- "initializer_range": 0.02,
64
- "intermediate_size": 3072,
65
- "label2id": {
66
- "_": 0,
67
- "acl": 1,
68
- "advcl": 2,
69
- "advmod": 3,
70
- "amod": 4,
71
- "appos": 5,
72
- "aux": 6,
73
- "case": 7,
74
- "cc": 8,
75
- "ccomp": 9,
76
- "clf": 10,
77
- "compound": 11,
78
- "conj": 12,
79
- "cop": 13,
80
- "csubj": 14,
81
- "dep": 15,
82
- "det": 16,
83
- "discourse": 17,
84
- "dislocated": 18,
85
- "dup": 38,
86
- "expl": 19,
87
- "fixed": 20,
88
- "flat": 21,
89
- "goeswith": 22,
90
- "iobj": 23,
91
- "list": 24,
92
- "mark": 25,
93
- "mwe": 39,
94
- "name": 40,
95
- "nmod": 26,
96
- "nsubj": 27,
97
- "nummod": 28,
98
- "obj": 29,
99
- "obl": 30,
100
- "orphan": 31,
101
- "parataxis": 32,
102
- "punct": 33,
103
- "remnant": 41,
104
- "reparandum": 34,
105
- "root": 35,
106
- "vocative": 36,
107
- "xcomp": 37
108
- },
109
- "layer_norm_eps": 1e-12,
110
- "max_position_embeddings": 512,
111
- "model_type": "bert",
112
- "num_attention_heads": 12,
113
- "num_hidden_layers": 12,
114
- "pad_token_id": 0,
115
- "pooler_fc_size": 768,
116
- "pooler_num_attention_heads": 12,
117
- "pooler_num_fc_layers": 3,
118
- "pooler_size_per_head": 128,
119
- "pooler_type": "first_token_transform",
120
- "position_embedding_type": "absolute",
121
- "prediction_heads": {
122
- "default": {
123
- "activation_function": "gelu",
124
- "bias": true,
125
- "embedding_size": 768,
126
- "head_type": "masked_lm",
127
- "label2id": null,
128
- "layer_norm": true,
129
- "layers": 2,
130
- "shift_labels": false,
131
- "vocab_size": 119547
132
- },
133
- "ud_singlish": {
134
- "head_type": "dependency_parsing",
135
- "label2id": {
136
- "_": 0,
137
- "acl": 1,
138
- "advcl": 2,
139
- "advmod": 3,
140
- "amod": 4,
141
- "appos": 5,
142
- "aux": 6,
143
- "case": 7,
144
- "cc": 8,
145
- "ccomp": 9,
146
- "clf": 10,
147
- "compound": 11,
148
- "conj": 12,
149
- "cop": 13,
150
- "csubj": 14,
151
- "dep": 15,
152
- "det": 16,
153
- "discourse": 17,
154
- "dislocated": 18,
155
- "dup": 38,
156
- "expl": 19,
157
- "fixed": 20,
158
- "flat": 21,
159
- "goeswith": 22,
160
- "iobj": 23,
161
- "list": 24,
162
- "mark": 25,
163
- "mwe": 39,
164
- "name": 40,
165
- "nmod": 26,
166
- "nsubj": 27,
167
- "nummod": 28,
168
- "obj": 29,
169
- "obl": 30,
170
- "orphan": 31,
171
- "parataxis": 32,
172
- "punct": 33,
173
- "remnant": 41,
174
- "reparandum": 34,
175
- "root": 35,
176
- "vocative": 36,
177
- "xcomp": 37
178
- },
179
- "num_labels": 42
180
- }
181
- },
182
- "torch_dtype": "float32",
183
- "transformers_version": "4.47.1",
184
- "type_vocab_size": 2,
185
- "use_cache": true,
186
- "vocab_size": 119547
187
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Aligned-Lambda_0.01/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2e45c93f2c9a1bc3bbd3debe593d29c4892ad1e22042ba6d421dd6607453334
3
- size 816784440
 
 
 
 
Aligned-Lambda_0.01/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5929e1de42a6585c3fff66c4a8793456272f5f9c4005370a94e2e66fba0838ee
3
- size 1621691322
 
 
 
 
Aligned-Lambda_0.01/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8827c23778eb132d4af0295d85486efedc52cc8e7d8260084819c1f5b168cedd
3
- size 14244
 
 
 
 
Aligned-Lambda_0.01/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:24d1adeb5a474175a1cb9c0c1efabaa9fd87343414b2349dd1c68b0a5ef6eb54
3
- size 1064
 
 
 
 
Aligned-Lambda_0.01/trainer_state.json DELETED
@@ -1,82 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 5.0,
5
- "eval_steps": 500,
6
- "global_step": 1960,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 1.0,
13
- "eval_loss": 1.3433195443616972,
14
- "las": 72.15189873417721,
15
- "step": 392,
16
- "uas": 81.66739415102575
17
- },
18
- {
19
- "epoch": 1.2755102040816326,
20
- "grad_norm": 3.317138433456421,
21
- "learning_rate": 0.00014897959183673472,
22
- "loss": 0.8116,
23
- "step": 500
24
- },
25
- {
26
- "epoch": 2.0,
27
- "eval_loss": 1.6489886807070837,
28
- "las": 73.24312527280664,
29
- "step": 784,
30
- "uas": 81.92928852029682
31
- },
32
- {
33
- "epoch": 2.5510204081632653,
34
- "grad_norm": 2.6405985355377197,
35
- "learning_rate": 9.79591836734694e-05,
36
- "loss": 0.2626,
37
- "step": 1000
38
- },
39
- {
40
- "epoch": 3.0,
41
- "eval_loss": 1.7524571418762207,
42
- "las": 73.15582714971627,
43
- "step": 1176,
44
- "uas": 82.36577913574858
45
- },
46
- {
47
- "epoch": 3.826530612244898,
48
- "grad_norm": 2.158872365951538,
49
- "learning_rate": 4.6938775510204086e-05,
50
- "loss": 0.1222,
51
- "step": 1500
52
- },
53
- {
54
- "epoch": 4.0,
55
- "eval_loss": 2.07165447043048,
56
- "las": 75.46922741161065,
57
- "step": 1568,
58
- "uas": 84.37363596682671
59
- }
60
- ],
61
- "logging_steps": 500,
62
- "max_steps": 1960,
63
- "num_input_tokens_seen": 0,
64
- "num_train_epochs": 5,
65
- "save_steps": 500,
66
- "stateful_callbacks": {
67
- "TrainerControl": {
68
- "args": {
69
- "should_epoch_stop": false,
70
- "should_evaluate": false,
71
- "should_log": false,
72
- "should_save": true,
73
- "should_training_stop": true
74
- },
75
- "attributes": {}
76
- }
77
- },
78
- "total_flos": 2.157644595068928e+16,
79
- "train_batch_size": 64,
80
- "trial_name": null,
81
- "trial_params": null
82
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Aligned-Lambda_0.01/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f00f3145499a5f9b66375806753d55cc81b715b7a4f3c230f473892ed2bbae5b
3
- size 5432