Hugging Face's logo

SparseCL
/
GTE-SparseCL-hotpotqa

Transformers
Safetensors
new
custom_code
Inference Endpoints
Model card Files Community
xiaoxiaolin commited on
Commit
de80bfe
·
verified ·
1 Parent(s): 48c0621

Upload folder using huggingface_hub

Browse files
Files changed (40) hide show
  1. checkpoint-1386/config.json +44 -0
  2. checkpoint-1386/model.safetensors +3 -0
  3. checkpoint-1386/optimizer.pt +3 -0
  4. checkpoint-1386/scheduler.pt +3 -0
  5. checkpoint-1386/special_tokens_map.json +37 -0
  6. checkpoint-1386/tokenizer.json +0 -0
  7. checkpoint-1386/tokenizer_config.json +62 -0
  8. checkpoint-1386/trainer_state.json +20 -0
  9. checkpoint-1386/training_args.bin +3 -0
  10. checkpoint-1386/vocab.txt +0 -0
  11. checkpoint-2772/config.json +44 -0
  12. checkpoint-2772/model.safetensors +3 -0
  13. checkpoint-2772/optimizer.pt +3 -0
  14. checkpoint-2772/scheduler.pt +3 -0
  15. checkpoint-2772/special_tokens_map.json +37 -0
  16. checkpoint-2772/tokenizer.json +0 -0
  17. checkpoint-2772/tokenizer_config.json +62 -0
  18. checkpoint-2772/trainer_state.json +20 -0
  19. checkpoint-2772/training_args.bin +3 -0
  20. checkpoint-2772/vocab.txt +0 -0
  21. checkpoint-4158/config.json +44 -0
  22. checkpoint-4158/model.safetensors +3 -0
  23. checkpoint-4158/optimizer.pt +3 -0
  24. checkpoint-4158/scheduler.pt +3 -0
  25. checkpoint-4158/special_tokens_map.json +37 -0
  26. checkpoint-4158/tokenizer.json +0 -0
  27. checkpoint-4158/tokenizer_config.json +62 -0
  28. checkpoint-4158/trainer_state.json +20 -0
  29. checkpoint-4158/training_args.bin +3 -0
  30. checkpoint-4158/vocab.txt +0 -0
  31. config.json +44 -0
  32. custom_info +6 -0
  33. model.safetensors +3 -0
  34. special_tokens_map.json +37 -0
  35. tokenizer.json +0 -0
  36. tokenizer_config.json +62 -0
  37. train_results.txt +3 -0
  38. trainer_state.json +28 -0
  39. training_args.bin +3 -0
  40. vocab.txt +0 -0
checkpoint-1386/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
3
+ "architectures": [
4
+ "NewModelForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
9
+ "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
10
+ "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
11
+ "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
12
+ "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
14
+ "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
15
+ },
16
+ "classifier_dropout": null,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "layer_norm_eps": 1e-12,
23
+ "layer_norm_type": "layer_norm",
24
+ "logn_attention_clip1": false,
25
+ "logn_attention_scale": false,
26
+ "max_position_embeddings": 8192,
27
+ "model_type": "new",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pack_qkv": true,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "rope",
33
+ "rope_scaling": {
34
+ "factor": 2.0,
35
+ "type": "ntk"
36
+ },
37
+ "rope_theta": 160000,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.36.2",
40
+ "type_vocab_size": 2,
41
+ "unpad_inputs": false,
42
+ "use_memory_efficient_attention": false,
43
+ "vocab_size": 30522
44
+ }
checkpoint-1386/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baa2f9f37635886e8087ed8ce28354f1f33f383c5ef0a10e44e9fba2341a9dd9
3
+ size 1736561104
checkpoint-1386/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8918551c211a4ff3ee48477319be1b55802d36be7f56215ee89e8e286419cbd
3
+ size 3473287493
checkpoint-1386/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec90e458c13c25f2367b6f50581f24ffb0c6ccda4ea17f970f9f599b6978fb5
3
+ size 627
checkpoint-1386/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-1386/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1386/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 8000,
49
+ "model_max_length": 32768,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
checkpoint-1386/trainer_state.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1386,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 4158,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 3,
15
+ "save_steps": 500,
16
+ "total_flos": 0,
17
+ "train_batch_size": null,
18
+ "trial_name": null,
19
+ "trial_params": null
20
+ }
checkpoint-1386/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53bcb467ae282416feede09e3300466752c00ba2834e3bae1945161f3c4e1224
3
+ size 4091
checkpoint-1386/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2772/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
3
+ "architectures": [
4
+ "NewModelForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
9
+ "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
10
+ "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
11
+ "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
12
+ "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
14
+ "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
15
+ },
16
+ "classifier_dropout": null,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "layer_norm_eps": 1e-12,
23
+ "layer_norm_type": "layer_norm",
24
+ "logn_attention_clip1": false,
25
+ "logn_attention_scale": false,
26
+ "max_position_embeddings": 8192,
27
+ "model_type": "new",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pack_qkv": true,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "rope",
33
+ "rope_scaling": {
34
+ "factor": 2.0,
35
+ "type": "ntk"
36
+ },
37
+ "rope_theta": 160000,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.36.2",
40
+ "type_vocab_size": 2,
41
+ "unpad_inputs": false,
42
+ "use_memory_efficient_attention": false,
43
+ "vocab_size": 30522
44
+ }
checkpoint-2772/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd20ba8123a7a8bd0411a3003142d08aaf3c0232c21c46816da4957b2f7cc755
3
+ size 1736561104
checkpoint-2772/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc8459de21242dc97b82414338c2a2e9027e067e90c6ffe25158f3df32502c4
3
+ size 3473287493
checkpoint-2772/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5427dd161d12c622d83829f2d6f852439eea5415f0014923bce1de2cf0d3df81
3
+ size 627
checkpoint-2772/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-2772/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2772/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 8000,
49
+ "model_max_length": 32768,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
checkpoint-2772/trainer_state.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2772,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 4158,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 3,
15
+ "save_steps": 500,
16
+ "total_flos": 0,
17
+ "train_batch_size": null,
18
+ "trial_name": null,
19
+ "trial_params": null
20
+ }
checkpoint-2772/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53bcb467ae282416feede09e3300466752c00ba2834e3bae1945161f3c4e1224
3
+ size 4091
checkpoint-2772/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4158/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
3
+ "architectures": [
4
+ "NewModelForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
9
+ "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
10
+ "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
11
+ "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
12
+ "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
14
+ "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
15
+ },
16
+ "classifier_dropout": null,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "layer_norm_eps": 1e-12,
23
+ "layer_norm_type": "layer_norm",
24
+ "logn_attention_clip1": false,
25
+ "logn_attention_scale": false,
26
+ "max_position_embeddings": 8192,
27
+ "model_type": "new",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pack_qkv": true,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "rope",
33
+ "rope_scaling": {
34
+ "factor": 2.0,
35
+ "type": "ntk"
36
+ },
37
+ "rope_theta": 160000,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.36.2",
40
+ "type_vocab_size": 2,
41
+ "unpad_inputs": false,
42
+ "use_memory_efficient_attention": false,
43
+ "vocab_size": 30522
44
+ }
checkpoint-4158/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b7cca6a6a536a5b285cda3e8b63327ab4eadf696970ecf5ab9feffea59d165
3
+ size 1736561104
checkpoint-4158/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d162ab177522dab04b64d81f731454bd618e4f2cb83d14f9d4c07bd3642d55
3
+ size 3473287493
checkpoint-4158/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69ef7ceaf09eb40f4d189be1b807098d880998e95f69fb50091e26f374f8ec6b
3
+ size 627
checkpoint-4158/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-4158/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4158/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 8000,
49
+ "model_max_length": 32768,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
checkpoint-4158/trainer_state.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4158,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 4158,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 3,
15
+ "save_steps": 500,
16
+ "total_flos": 0,
17
+ "train_batch_size": null,
18
+ "trial_name": null,
19
+ "trial_params": null
20
+ }
checkpoint-4158/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53bcb467ae282416feede09e3300466752c00ba2834e3bae1945161f3c4e1224
3
+ size 4091
checkpoint-4158/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
3
+ "architectures": [
4
+ "NewModelForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
9
+ "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
10
+ "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
11
+ "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
12
+ "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
14
+ "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
15
+ },
16
+ "classifier_dropout": null,
17
+ "hidden_act": "gelu",
18
+ "hidden_dropout_prob": 0.1,
19
+ "hidden_size": 1024,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "layer_norm_eps": 1e-12,
23
+ "layer_norm_type": "layer_norm",
24
+ "logn_attention_clip1": false,
25
+ "logn_attention_scale": false,
26
+ "max_position_embeddings": 8192,
27
+ "model_type": "new",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "pack_qkv": true,
31
+ "pad_token_id": 0,
32
+ "position_embedding_type": "rope",
33
+ "rope_scaling": {
34
+ "factor": 2.0,
35
+ "type": "ntk"
36
+ },
37
+ "rope_theta": 160000,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.36.2",
40
+ "type_vocab_size": 2,
41
+ "unpad_inputs": false,
42
+ "use_memory_efficient_attention": false,
43
+ "vocab_size": 30522
44
+ }
custom_info ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ epoch=0 step=462 progress=0.111 eval info {'sparsity_loss': 0.463, 'l1l2_ratio_z12': 21.317, 'l1l2_ratio_z13': 23.905, 'l1l2_ratio_z13_all': 25.735} train info {'sparsity_loss': 1.53, 'l1l2_ratio_z12': 22.945, 'l1l2_ratio_z13': 25.015, 'l1l2_ratio_z13_all': 25.555}
2
+ epoch=0 step=924 progress=0.222 eval info {'sparsity_loss': 0.283, 'l1l2_ratio_z12': 20.568, 'l1l2_ratio_z13': 23.443, 'l1l2_ratio_z13_all': 25.733} train info {'sparsity_loss': 0.183, 'l1l2_ratio_z12': 21.32, 'l1l2_ratio_z13': 24.705, 'l1l2_ratio_z13_all': 25.737}
3
+ epoch=1 step=462 progress=0.444 eval info {'sparsity_loss': 0.23, 'l1l2_ratio_z12': 17.986, 'l1l2_ratio_z13': 22.782, 'l1l2_ratio_z13_all': 25.554} train info {'sparsity_loss': 0.062, 'l1l2_ratio_z12': 19.674, 'l1l2_ratio_z13': 24.426, 'l1l2_ratio_z13_all': 25.656}
4
+ epoch=1 step=924 progress=0.556 eval info {'sparsity_loss': 0.237, 'l1l2_ratio_z12': 16.011, 'l1l2_ratio_z13': 22.279, 'l1l2_ratio_z13_all': 25.553} train info {'sparsity_loss': 0.03, 'l1l2_ratio_z12': 17.807, 'l1l2_ratio_z13': 24.222, 'l1l2_ratio_z13_all': 25.601}
5
+ epoch=2 step=462 progress=0.778 eval info {'sparsity_loss': 0.246, 'l1l2_ratio_z12': 14.56, 'l1l2_ratio_z13': 22.528, 'l1l2_ratio_z13_all': 25.587} train info {'sparsity_loss': 0.019, 'l1l2_ratio_z12': 16.258, 'l1l2_ratio_z13': 24.266, 'l1l2_ratio_z13_all': 25.601}
6
+ epoch=2 step=924 progress=0.889 eval info {'sparsity_loss': 0.285, 'l1l2_ratio_z12': 13.884, 'l1l2_ratio_z13': 22.263, 'l1l2_ratio_z13_all': 25.6} train info {'sparsity_loss': 0.012, 'l1l2_ratio_z12': 15.213, 'l1l2_ratio_z13': 24.337, 'l1l2_ratio_z13_all': 25.647}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b7cca6a6a536a5b285cda3e8b63327ab4eadf696970ecf5ab9feffea59d165
3
+ size 1736561104
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "max_length": 8000,
49
+ "model_max_length": 32768,
50
+ "pad_to_multiple_of": null,
51
+ "pad_token": "[PAD]",
52
+ "pad_token_type_id": 0,
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "stride": 0,
56
+ "strip_accents": null,
57
+ "tokenize_chinese_chars": true,
58
+ "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "[UNK]"
62
+ }
train_results.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch = 3.0
2
+ train_runtime = 17574.8484
3
+ train_samples_per_second = 0.237
trainer_state.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4158,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.0,
13
+ "step": 4158,
14
+ "total_flos": 0,
15
+ "train_runtime": 17574.8484,
16
+ "train_samples_per_second": 0.237
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 4158,
21
+ "num_input_tokens_seen": 0,
22
+ "num_train_epochs": 3,
23
+ "save_steps": 500,
24
+ "total_flos": 0,
25
+ "train_batch_size": null,
26
+ "trial_name": null,
27
+ "trial_params": null
28
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53bcb467ae282416feede09e3300466752c00ba2834e3bae1945161f3c4e1224
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff