Hugging Face's logo

eclec
/
test_trainer

Text Classification
Transformers
Safetensors
longformer
Model card Files
xet
Community
eclec commited on
Commit
fb8c12f
·
verified ·
1 Parent(s): 76f1fe6

Training in progress, epoch 1

Browse files
Files changed (20) hide show
  1. config.json +64 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. run-0/checkpoint-1/config.json +64 -0
  5. run-0/checkpoint-1/merges.txt +0 -0
  6. run-0/checkpoint-1/model.safetensors +3 -0
  7. run-0/checkpoint-1/optimizer.pt +3 -0
  8. run-0/checkpoint-1/rng_state.pth +3 -0
  9. run-0/checkpoint-1/scheduler.pt +3 -0
  10. run-0/checkpoint-1/special_tokens_map.json +15 -0
  11. run-0/checkpoint-1/tokenizer.json +0 -0
  12. run-0/checkpoint-1/tokenizer_config.json +57 -0
  13. run-0/checkpoint-1/trainer_state.json +40 -0
  14. run-0/checkpoint-1/training_args.bin +3 -0
  15. run-0/checkpoint-1/vocab.json +0 -0
  16. special_tokens_map.json +15 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +57 -0
  19. training_args.bin +3 -0
  20. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-large-4096",
3
+ "architectures": [
4
+ "LongformerForSequenceClassification"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 512,
27
+ 512,
28
+ 512,
29
+ 512,
30
+ 512,
31
+ 512,
32
+ 512
33
+ ],
34
+ "bos_token_id": 0,
35
+ "eos_token_id": 2,
36
+ "gradient_checkpointing": false,
37
+ "hidden_act": "gelu",
38
+ "hidden_dropout_prob": 0.1,
39
+ "hidden_size": 1024,
40
+ "id2label": {
41
+ "0": "NOT_REJECTED",
42
+ "1": "REJECTED"
43
+ },
44
+ "ignore_attention_mask": false,
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 4096,
47
+ "label2id": {
48
+ "NOT_REJECTED": 0,
49
+ "REJECTED": 1
50
+ },
51
+ "layer_norm_eps": 1e-05,
52
+ "max_position_embeddings": 4098,
53
+ "model_type": "longformer",
54
+ "num_attention_heads": 16,
55
+ "num_hidden_layers": 24,
56
+ "onnx_export": false,
57
+ "pad_token_id": 1,
58
+ "problem_type": "single_label_classification",
59
+ "sep_token_id": 2,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.39.1",
62
+ "type_vocab_size": 1,
63
+ "vocab_size": 50265
64
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70bfaa48d31800af324519d4c5a22b6d961b2be35520dcb1738b0a2ce0216067
3
+ size 1738480904
run-0/checkpoint-1/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-large-4096",
3
+ "architectures": [
4
+ "LongformerForSequenceClassification"
5
+ ],
6
+ "attention_mode": "longformer",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attention_window": [
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 512,
27
+ 512,
28
+ 512,
29
+ 512,
30
+ 512,
31
+ 512,
32
+ 512
33
+ ],
34
+ "bos_token_id": 0,
35
+ "eos_token_id": 2,
36
+ "gradient_checkpointing": false,
37
+ "hidden_act": "gelu",
38
+ "hidden_dropout_prob": 0.1,
39
+ "hidden_size": 1024,
40
+ "id2label": {
41
+ "0": "NOT_REJECTED",
42
+ "1": "REJECTED"
43
+ },
44
+ "ignore_attention_mask": false,
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 4096,
47
+ "label2id": {
48
+ "NOT_REJECTED": 0,
49
+ "REJECTED": 1
50
+ },
51
+ "layer_norm_eps": 1e-05,
52
+ "max_position_embeddings": 4098,
53
+ "model_type": "longformer",
54
+ "num_attention_heads": 16,
55
+ "num_hidden_layers": 24,
56
+ "onnx_export": false,
57
+ "pad_token_id": 1,
58
+ "problem_type": "single_label_classification",
59
+ "sep_token_id": 2,
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.39.1",
62
+ "type_vocab_size": 1,
63
+ "vocab_size": 50265
64
+ }
run-0/checkpoint-1/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-1/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70bfaa48d31800af324519d4c5a22b6d961b2be35520dcb1738b0a2ce0216067
3
+ size 1738480904
run-0/checkpoint-1/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaba361e57e647dfbc04ccdeaac2fc8d2020b46edc2eba57da8b01e17563e7f1
3
+ size 4554273
run-0/checkpoint-1/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82cf7fd419de6a7ea8a37c88858b1c1e6fdf7f1ca92acc14db4bfdabc53d2b77
3
+ size 14244
run-0/checkpoint-1/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d4bb6c2bc420ff6f47f690d3235d02b76e1f549e3d229fb26260f8875bcf86
3
+ size 1064
run-0/checkpoint-1/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
run-0/checkpoint-1/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-1/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 4096,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "LongformerTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
run-0/checkpoint-1/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7080078125,
3
+ "best_model_checkpoint": "test_trainer\\run-0\\checkpoint-1",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.0,
14
+ "eval_f1": 0.0,
15
+ "eval_loss": 0.7080078125,
16
+ "eval_runtime": 0.1741,
17
+ "eval_samples_per_second": 5.744,
18
+ "eval_steps_per_second": 5.744,
19
+ "step": 1
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 5,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 5,
26
+ "save_steps": 500,
27
+ "total_flos": 0,
28
+ "train_batch_size": 8,
29
+ "trial_name": null,
30
+ "trial_params": {
31
+ "gradient_accumulation_steps": 8,
32
+ "learning_rate": 7.543213106016258e-06,
33
+ "num_train_epochs": 5,
34
+ "optimizer": "AdamW",
35
+ "seed": 48,
36
+ "warmup_ratio": 0.2668631355210866,
37
+ "warmup_steps": 204,
38
+ "weight_decay": 0.4761015845296048
39
+ }
40
+ }
run-0/checkpoint-1/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dccf7a91cbcd4e813a7f2cfd37894b4a004b64c1795dfe8281ddb18c17f927a0
3
+ size 4856
run-0/checkpoint-1/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
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
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 4096,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "LongformerTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dccf7a91cbcd4e813a7f2cfd37894b4a004b64c1795dfe8281ddb18c17f927a0
3
+ size 4856
vocab.json ADDED
The diff for this file is too large to render. See raw diff