thivy commited on
Commit
8723c4e
·
verified ·
1 Parent(s): a157dd1

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GptBertForMaskedLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "attn_implementation": null,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_gptbert.GptBertConfig",
9
+ "AutoModel": "modeling_gptbert.GptBertModel",
10
+ "AutoModelForCausalLM": "modeling_gptbert.GptBertForCausalLM",
11
+ "AutoModelForMaskedLM": "modeling_gptbert.GptBertForMaskedLM",
12
+ "AutoModelForMultipleChoice": "modeling_gptbert.GptBertForMultipleChoice",
13
+ "AutoModelForQuestionAnswering": "modeling_gptbert.GptBertForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "modeling_gptbert.GptBertForSequenceClassification",
15
+ "AutoModelForTokenClassification": "modeling_gptbert.GptBertForTokenClassification"
16
+ },
17
+ "bos_token_id": 1,
18
+ "classifier_dropout": 0.2,
19
+ "deterministic_flash_attn": false,
20
+ "dtype": "float32",
21
+ "embedding_dropout": 0.1,
22
+ "eos_token_id": 2,
23
+ "global_window_length": 8192,
24
+ "hidden_dropout": 0.0,
25
+ "hidden_size": 640,
26
+ "intermediate_size": 1664,
27
+ "layer_norm_eps": 1e-07,
28
+ "local_global_ratio": 4,
29
+ "local_window_length": 256,
30
+ "mask_token_id": 4,
31
+ "max_sequence_length": 16384,
32
+ "model": "norbert4",
33
+ "num_attention_heads": 10,
34
+ "num_layers": 24,
35
+ "pad_token_id": 3,
36
+ "query_key_head_size": 64,
37
+ "rope_theta": 160000,
38
+ "transformers_version": "4.57.3",
39
+ "unk_token_id": 0,
40
+ "use_cache": false,
41
+ "value_head_size": 64,
42
+ "vocab_size": 51200
43
+ }
eval/Information-Retrieval_evaluation_NanoNFCorpus_results.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch,steps,dot-Accuracy@1,dot-Accuracy@3,dot-Accuracy@5,dot-Accuracy@10,dot-Precision@1,dot-Recall@1,dot-Precision@3,dot-Recall@3,dot-Precision@5,dot-Recall@5,dot-Precision@10,dot-Recall@10,dot-MRR@10,dot-NDCG@10,dot-MAP@100,query_active_dims,query_sparsity_ratio,corpus_active_dims,corpus_sparsity_ratio,avg_flops
2
+ 0.04797083373309028,500,0.02,0.08,0.08,0.12,0.02,7.905138339920947e-05,0.03333333333333333,0.003312410422185988,0.032,0.004545769460972766,0.026000000000000006,0.006349071275176555,0.05088888888888889,0.027178706104522946,0.006747512755501429,51200.0,0.0,51200.0,0.0,51200.0
3
+ 0.04797083373309028,500,0.02,0.08,0.08,0.12,0.02,7.905138339920947e-05,0.03333333333333333,0.003312410422185988,0.032,0.004545769460972766,0.026000000000000006,0.006349071275176555,0.05088888888888889,0.027178706104522946,0.006747512755501429,51200.0,0.0,51200.0,0.0,51200.0
eval/NanoBEIR_evaluation_mean_results.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch,steps,dot-Accuracy@1,dot-Accuracy@3,dot-Accuracy@5,dot-Accuracy@10,dot-Precision@1,dot-Recall@1,dot-Precision@3,dot-Recall@3,dot-Precision@5,dot-Recall@5,dot-Precision@10,dot-Recall@10,dot-MRR@10,dot-NDCG@10,dot-MAP@100,query_active_dims,query_sparsity_ratio,corpus_active_dims,corpus_sparsity_ratio,avg_flops
2
+ 0.04797083373309028,500,0.02,0.08,0.08,0.12,0.02,7.905138339920947e-05,0.03333333333333333,0.003312410422185988,0.032,0.004545769460972766,0.026000000000000006,0.006349071275176555,0.05088888888888889,0.027178706104522946,0.006747512755501429,51200.0,0.0,51200.0,0.0,51200.0
3
+ 0.04797083373309028,500,0.02,0.08,0.08,0.12,0.02,7.905138339920947e-05,0.03333333333333333,0.003312410422185988,0.032,0.004545769460972766,0.026000000000000006,0.006349071275176555,0.05088888888888889,0.027178706104522946,0.006747512755501429,51200.0,0.0,51200.0,0.0,51200.0
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6b59b6342fcd6a1910b237e5db7707f98673239940cfc25a5d1876082ebc33
3
+ size 728561776
runs/events.out.tfevents.1771057837.thivyh100large.21575.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80f58f67d6f7770352159c91212efcdf203387b6f16177454df6463cd4b56bf1
3
+ size 4608
runs/events.out.tfevents.1771058074.thivyh100large.23215.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42aadf537b85a4ee34656980cc9d6d36f6dc5cd516b75b73984d31531786d1ee
3
+ size 5142
runs/events.out.tfevents.1771058320.thivyh100large.25486.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48a144275256807b62ac46c915e7822a04f001725da117f9f6bffa758b571872
3
+ size 5677
runs/events.out.tfevents.1771058777.thivyh100large.31494.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f550d6312973956d3faad455dd2a075996b897951737f4411a543408e9285eda
3
+ size 13489
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<pad>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<special_0>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<special_1>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<special_2>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<special_3>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<special_4>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "<special_5>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "<special_6>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "<special_7>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "<special_8>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "<special_9>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "<special_10>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ }
131
+ },
132
+ "bos_token": "<s>",
133
+ "clean_up_tokenization_spaces": false,
134
+ "cls_token": "<s>",
135
+ "eos_token": "</s>",
136
+ "extra_special_tokens": {},
137
+ "mask_token": "<mask>",
138
+ "model_max_length": 4096,
139
+ "pad_token": "<pad>",
140
+ "sep_token": "</s>",
141
+ "tokenizer_class": "PreTrainedTokenizerFast",
142
+ "unk_token": "<unk>"
143
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a238e2a37bc1da8ffa7f6ac3192a8f23e297afa1bc8b0a28a0d40a8e101359
3
+ size 6353