Hugging Face's logo

SparseCL
/
UAE-SparseCL-msmarco

Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
xiaoxiaolin commited on
Commit
647cfb6
•
1 Parent(s): 3045914

Upload folder using huggingface_hub

Browse files
Files changed (40) hide show
  1. checkpoint-1400/config.json +26 -0
  2. checkpoint-1400/model.safetensors +3 -0
  3. checkpoint-1400/optimizer.pt +3 -0
  4. checkpoint-1400/scheduler.pt +3 -0
  5. checkpoint-1400/special_tokens_map.json +37 -0
  6. checkpoint-1400/tokenizer.json +0 -0
  7. checkpoint-1400/tokenizer_config.json +57 -0
  8. checkpoint-1400/trainer_state.json +20 -0
  9. checkpoint-1400/training_args.bin +3 -0
  10. checkpoint-1400/vocab.txt +0 -0
  11. checkpoint-2800/config.json +26 -0
  12. checkpoint-2800/model.safetensors +3 -0
  13. checkpoint-2800/optimizer.pt +3 -0
  14. checkpoint-2800/scheduler.pt +3 -0
  15. checkpoint-2800/special_tokens_map.json +37 -0
  16. checkpoint-2800/tokenizer.json +0 -0
  17. checkpoint-2800/tokenizer_config.json +57 -0
  18. checkpoint-2800/trainer_state.json +20 -0
  19. checkpoint-2800/training_args.bin +3 -0
  20. checkpoint-2800/vocab.txt +0 -0
  21. checkpoint-4200/config.json +26 -0
  22. checkpoint-4200/model.safetensors +3 -0
  23. checkpoint-4200/optimizer.pt +3 -0
  24. checkpoint-4200/scheduler.pt +3 -0
  25. checkpoint-4200/special_tokens_map.json +37 -0
  26. checkpoint-4200/tokenizer.json +0 -0
  27. checkpoint-4200/tokenizer_config.json +57 -0
  28. checkpoint-4200/trainer_state.json +20 -0
  29. checkpoint-4200/training_args.bin +3 -0
  30. checkpoint-4200/vocab.txt +0 -0
  31. config.json +26 -0
  32. custom_info +9 -0
  33. model.safetensors +3 -0
  34. special_tokens_map.json +37 -0
  35. tokenizer.json +0 -0
  36. tokenizer_config.json +57 -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-1400/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "WhereIsAI/UAE-Large-V1",
3
+ "architectures": [
4
+ "our_BertForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.36.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": false,
25
+ "vocab_size": 30522
26
+ }
checkpoint-1400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a00c444d73211c7cdb85e0afaacbbf222d5df7f3a1a7e0e8cac753c50afcde07
3
+ size 1336415792
checkpoint-1400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c13f8b9dc22b0d9e55f88c214a93b57e80557bc056f0bc7d0178142fcbc1de
3
+ size 2673063404
checkpoint-1400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcea1a200517ffc2cf77af3894149058705795c4078294ca6f50ab18ccde5527
3
+ size 627
checkpoint-1400/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-1400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1400/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
checkpoint-1400/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": 1400,
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": 4200,
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-1400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c75826ea9909a0a1da915b57945b2ac824d2df1bdd26b878d467290b19542713
3
+ size 4091
checkpoint-1400/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2800/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "WhereIsAI/UAE-Large-V1",
3
+ "architectures": [
4
+ "our_BertForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.36.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": false,
25
+ "vocab_size": 30522
26
+ }
checkpoint-2800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466e1820c14cb8cc0411a75e7093a5aa521dee26fb2db0f6ce124d4ee118bc45
3
+ size 1336415792
checkpoint-2800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d20b189b9b744dcc99cb1af342d48d4884bfa20b5ed5d4c7f84407b12baca6
3
+ size 2673063404
checkpoint-2800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5353282c47ce7e1629b303c28d290db65d7df0877959e58338a438dcca8d310
3
+ size 627
checkpoint-2800/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-2800/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2800/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
checkpoint-2800/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": 2800,
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": 4200,
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-2800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c75826ea9909a0a1da915b57945b2ac824d2df1bdd26b878d467290b19542713
3
+ size 4091
checkpoint-2800/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4200/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "WhereIsAI/UAE-Large-V1",
3
+ "architectures": [
4
+ "our_BertForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.36.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": false,
25
+ "vocab_size": 30522
26
+ }
checkpoint-4200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ac992db1a32805eccc5b6afd1187aca0a040984b9b0e6427524de3ba902ee65
3
+ size 1336415792
checkpoint-4200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5b9430dc58b635e6b133ab5ea5ef9dc6672095ff8abb751e5c96d313627d8c
3
+ size 2673063404
checkpoint-4200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4c02de10aa198f8890d58eaff374045cd827a437d97f98892422dbc9358138
3
+ size 627
checkpoint-4200/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-4200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4200/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
checkpoint-4200/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": 4200,
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": 4200,
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-4200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c75826ea9909a0a1da915b57945b2ac824d2df1bdd26b878d467290b19542713
3
+ size 4091
checkpoint-4200/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "WhereIsAI/UAE-Large-V1",
3
+ "architectures": [
4
+ "our_BertForCL"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.36.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": false,
25
+ "vocab_size": 30522
26
+ }
custom_info ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ epoch=0 step=466 progress=0.111 eval info {'sparsity_loss': 0.735, 'l1l2_ratio_z12': 12.758, 'l1l2_ratio_z13': 20.419, 'l1l2_ratio_z13_all': 25.957} train info {'sparsity_loss': 1.399, 'l1l2_ratio_z12': 16.372, 'l1l2_ratio_z13': 23.361, 'l1l2_ratio_z13_all': 25.73}
2
+ epoch=0 step=932 progress=0.222 eval info {'sparsity_loss': 0.652, 'l1l2_ratio_z12': 11.941, 'l1l2_ratio_z13': 20.74, 'l1l2_ratio_z13_all': 26.228} train info {'sparsity_loss': 0.404, 'l1l2_ratio_z12': 12.431, 'l1l2_ratio_z13': 21.945, 'l1l2_ratio_z13_all': 26.101}
3
+ epoch=0 step=1398 progress=0.333 eval info {'sparsity_loss': 0.624, 'l1l2_ratio_z12': 10.948, 'l1l2_ratio_z13': 20.807, 'l1l2_ratio_z13_all': 26.192} train info {'sparsity_loss': 0.203, 'l1l2_ratio_z12': 11.167, 'l1l2_ratio_z13': 20.31, 'l1l2_ratio_z13_all': 26.187}
4
+ epoch=1 step=466 progress=0.444 eval info {'sparsity_loss': 0.588, 'l1l2_ratio_z12': 10.359, 'l1l2_ratio_z13': 20.87, 'l1l2_ratio_z13_all': 26.214} train info {'sparsity_loss': 0.092, 'l1l2_ratio_z12': 10.093, 'l1l2_ratio_z13': 20.664, 'l1l2_ratio_z13_all': 26.208}
5
+ epoch=1 step=932 progress=0.555 eval info {'sparsity_loss': 0.596, 'l1l2_ratio_z12': 10.327, 'l1l2_ratio_z13': 21.216, 'l1l2_ratio_z13_all': 26.226} train info {'sparsity_loss': 0.067, 'l1l2_ratio_z12': 9.484, 'l1l2_ratio_z13': 21.045, 'l1l2_ratio_z13_all': 26.228}
6
+ epoch=1 step=1398 progress=0.666 eval info {'sparsity_loss': 0.58, 'l1l2_ratio_z12': 9.903, 'l1l2_ratio_z13': 21.136, 'l1l2_ratio_z13_all': 26.244} train info {'sparsity_loss': 0.047, 'l1l2_ratio_z12': 8.981, 'l1l2_ratio_z13': 21.555, 'l1l2_ratio_z13_all': 26.234}
7
+ epoch=2 step=466 progress=0.778 eval info {'sparsity_loss': 0.589, 'l1l2_ratio_z12': 9.64, 'l1l2_ratio_z13': 21.173, 'l1l2_ratio_z13_all': 26.261} train info {'sparsity_loss': 0.022, 'l1l2_ratio_z12': 8.531, 'l1l2_ratio_z13': 22.289, 'l1l2_ratio_z13_all': 26.27}
8
+ epoch=2 step=932 progress=0.889 eval info {'sparsity_loss': 0.575, 'l1l2_ratio_z12': 9.657, 'l1l2_ratio_z13': 21.229, 'l1l2_ratio_z13_all': 26.263} train info {'sparsity_loss': 0.021, 'l1l2_ratio_z12': 8.28, 'l1l2_ratio_z13': 22.513, 'l1l2_ratio_z13_all': 26.299}
9
+ epoch=2 step=1398 progress=1.0 eval info {'sparsity_loss': 0.58, 'l1l2_ratio_z12': 9.5, 'l1l2_ratio_z13': 21.27, 'l1l2_ratio_z13_all': 26.27} train info {'sparsity_loss': 0.018, 'l1l2_ratio_z12': 8.113, 'l1l2_ratio_z13': 22.646, 'l1l2_ratio_z13_all': 26.292}
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ac992db1a32805eccc5b6afd1187aca0a040984b9b0e6427524de3ba902ee65
3
+ size 1336415792
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
train_results.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch = 3.0
2
+ train_runtime = 13708.0087
3
+ train_samples_per_second = 0.306
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": 4200,
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": 4200,
14
+ "total_flos": 0,
15
+ "train_runtime": 13708.0087,
16
+ "train_samples_per_second": 0.306
17
+ }
18
+ ],
19
+ "logging_steps": 500,
20
+ "max_steps": 4200,
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:c75826ea9909a0a1da915b57945b2ac824d2df1bdd26b878d467290b19542713
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff