eclec commited on
Commit
40ee7d6
1 Parent(s): fb8c12f

Training in progress, epoch 1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-1/model.safetensors +1 -1
  3. run-0/checkpoint-1/optimizer.pt +1 -1
  4. run-0/checkpoint-1/rng_state.pth +2 -2
  5. run-0/checkpoint-1/scheduler.pt +1 -1
  6. run-0/checkpoint-1/training_args.bin +1 -1
  7. run-0/checkpoint-2/config.json +64 -0
  8. run-0/checkpoint-2/merges.txt +0 -0
  9. run-0/checkpoint-2/model.safetensors +3 -0
  10. run-0/checkpoint-2/optimizer.pt +3 -0
  11. run-0/checkpoint-2/rng_state.pth +3 -0
  12. run-0/checkpoint-2/scheduler.pt +3 -0
  13. run-0/checkpoint-2/special_tokens_map.json +15 -0
  14. run-0/checkpoint-2/tokenizer.json +0 -0
  15. run-0/checkpoint-2/tokenizer_config.json +57 -0
  16. run-0/checkpoint-2/trainer_state.json +50 -0
  17. run-0/checkpoint-2/training_args.bin +3 -0
  18. run-0/checkpoint-2/vocab.json +0 -0
  19. run-0/checkpoint-3/config.json +64 -0
  20. run-0/checkpoint-3/merges.txt +0 -0
  21. run-0/checkpoint-3/model.safetensors +3 -0
  22. run-0/checkpoint-3/optimizer.pt +3 -0
  23. run-0/checkpoint-3/rng_state.pth +3 -0
  24. run-0/checkpoint-3/scheduler.pt +3 -0
  25. run-0/checkpoint-3/special_tokens_map.json +15 -0
  26. run-0/checkpoint-3/tokenizer.json +0 -0
  27. run-0/checkpoint-3/tokenizer_config.json +57 -0
  28. run-0/checkpoint-3/trainer_state.json +60 -0
  29. run-0/checkpoint-3/training_args.bin +3 -0
  30. run-0/checkpoint-3/vocab.json +0 -0
  31. run-0/checkpoint-4/config.json +64 -0
  32. run-0/checkpoint-4/merges.txt +0 -0
  33. run-0/checkpoint-4/model.safetensors +3 -0
  34. run-0/checkpoint-4/optimizer.pt +3 -0
  35. run-0/checkpoint-4/rng_state.pth +3 -0
  36. run-0/checkpoint-4/scheduler.pt +3 -0
  37. run-0/checkpoint-4/special_tokens_map.json +15 -0
  38. run-0/checkpoint-4/tokenizer.json +0 -0
  39. run-0/checkpoint-4/tokenizer_config.json +57 -0
  40. run-0/checkpoint-4/trainer_state.json +70 -0
  41. run-0/checkpoint-4/training_args.bin +3 -0
  42. run-0/checkpoint-4/vocab.json +0 -0
  43. run-0/checkpoint-5/config.json +64 -0
  44. run-0/checkpoint-5/merges.txt +0 -0
  45. run-0/checkpoint-5/model.safetensors +3 -0
  46. run-0/checkpoint-5/optimizer.pt +3 -0
  47. run-0/checkpoint-5/rng_state.pth +3 -0
  48. run-0/checkpoint-5/scheduler.pt +3 -0
  49. run-0/checkpoint-5/special_tokens_map.json +15 -0
  50. run-0/checkpoint-5/tokenizer.json +0 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70bfaa48d31800af324519d4c5a22b6d961b2be35520dcb1738b0a2ce0216067
3
  size 1738480904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd776ea672c8973b53b4ae02d385a5ff68991133a89b6b338228b3d004de2713
3
  size 1738480904
run-0/checkpoint-1/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70bfaa48d31800af324519d4c5a22b6d961b2be35520dcb1738b0a2ce0216067
3
  size 1738480904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd776ea672c8973b53b4ae02d385a5ff68991133a89b6b338228b3d004de2713
3
  size 1738480904
run-0/checkpoint-1/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaba361e57e647dfbc04ccdeaac2fc8d2020b46edc2eba57da8b01e17563e7f1
3
  size 4554273
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc8c0321a4ba5fbb4dad00f3e0a20d1ed794ca69c07fb2c979a82c2b01b89f98
3
  size 4554273
run-0/checkpoint-1/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82cf7fd419de6a7ea8a37c88858b1c1e6fdf7f1ca92acc14db4bfdabc53d2b77
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06431a06dc113891110756ec0ac4b014dd7d6b797f07e2f1b648bbb2758060f5
3
+ size 14308
run-0/checkpoint-1/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45d4bb6c2bc420ff6f47f690d3235d02b76e1f549e3d229fb26260f8875bcf86
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fefd6ea4e1c7c2e842dd37be41268003aeb0e3212cd073f3f3e3f389fec20cb
3
  size 1064
run-0/checkpoint-1/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dccf7a91cbcd4e813a7f2cfd37894b4a004b64c1795dfe8281ddb18c17f927a0
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d07f95613d82874f5c1c1a8ba5956eb7a8647edfa0d0ba7a2261402aaea793
3
  size 4856
run-0/checkpoint-2/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-2/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-2/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda83432ab206b336b14b80cb5b48e2758bc3fc5ec581e270b0f274fade3ddd8
3
+ size 1738480904
run-0/checkpoint-2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:874f9d0f2fcd9fd9dfdd78ddbd055d96119cb6d852d3da1c227f562894e324d3
3
+ size 4554273
run-0/checkpoint-2/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0ed4139a763528ed3a23c1215fa41fdaa933291d22d67cacc933a02acebabd
3
+ size 14308
run-0/checkpoint-2/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4947eb2ade6578262c473d09b2551e736f6466515fea4bca3ceacece003b33
3
+ size 1064
run-0/checkpoint-2/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-2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-2/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-2/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7080078125,
3
+ "best_model_checkpoint": "test_trainer\\run-0\\checkpoint-1",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2,
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
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.0,
24
+ "eval_f1": 0.0,
25
+ "eval_loss": 0.7080078125,
26
+ "eval_runtime": 0.1514,
27
+ "eval_samples_per_second": 6.605,
28
+ "eval_steps_per_second": 6.605,
29
+ "step": 2
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 5,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 5,
36
+ "save_steps": 500,
37
+ "total_flos": 0,
38
+ "train_batch_size": 8,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "gradient_accumulation_steps": 8,
42
+ "learning_rate": 7.543213106016258e-06,
43
+ "num_train_epochs": 5,
44
+ "optimizer": "AdamW",
45
+ "seed": 48,
46
+ "warmup_ratio": 0.2668631355210866,
47
+ "warmup_steps": 204,
48
+ "weight_decay": 0.4761015845296048
49
+ }
50
+ }
run-0/checkpoint-2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d07f95613d82874f5c1c1a8ba5956eb7a8647edfa0d0ba7a2261402aaea793
3
+ size 4856
run-0/checkpoint-2/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-3/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-3/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-3/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bd0c722926a58aec19a37e265fc78ca175e20f5cfab36dc81004eaec391b2da
3
+ size 1738480904
run-0/checkpoint-3/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b23ce8045cea57b9bff180e3f8116a3b757ce56988d5170d5e1123fb4f722c4b
3
+ size 4554273
run-0/checkpoint-3/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b29168353a4690026b01a91d77d224d919b7d79bde97c1cbf70802f2220e4e
3
+ size 14308
run-0/checkpoint-3/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c9935d706d171e325b124023dd429ee0351fa4bec799e6ae2599dc309ad0143
3
+ size 1064
run-0/checkpoint-3/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-3/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-3/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-3/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.70751953125,
3
+ "best_model_checkpoint": "test_trainer\\run-0\\checkpoint-3",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3,
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
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.0,
24
+ "eval_f1": 0.0,
25
+ "eval_loss": 0.7080078125,
26
+ "eval_runtime": 0.1514,
27
+ "eval_samples_per_second": 6.605,
28
+ "eval_steps_per_second": 6.605,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 3.0,
33
+ "eval_accuracy": 0.0,
34
+ "eval_f1": 0.0,
35
+ "eval_loss": 0.70751953125,
36
+ "eval_runtime": 0.1497,
37
+ "eval_samples_per_second": 6.681,
38
+ "eval_steps_per_second": 6.681,
39
+ "step": 3
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 5,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 5,
46
+ "save_steps": 500,
47
+ "total_flos": 0,
48
+ "train_batch_size": 8,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "gradient_accumulation_steps": 8,
52
+ "learning_rate": 7.543213106016258e-06,
53
+ "num_train_epochs": 5,
54
+ "optimizer": "AdamW",
55
+ "seed": 48,
56
+ "warmup_ratio": 0.2668631355210866,
57
+ "warmup_steps": 204,
58
+ "weight_decay": 0.4761015845296048
59
+ }
60
+ }
run-0/checkpoint-3/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d07f95613d82874f5c1c1a8ba5956eb7a8647edfa0d0ba7a2261402aaea793
3
+ size 4856
run-0/checkpoint-3/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-4/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-4/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-4/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:415564785288ff1a657a01100e020bec55d69dc7fc0d0bf7b6a4b7e75fc170a1
3
+ size 1738480904
run-0/checkpoint-4/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde2c00413a7c0e17461346556bb319d422c50a9a39c3994d338c88d16074e95
3
+ size 4554273
run-0/checkpoint-4/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67740c22b012491bb7212e0ce9818e47b399abbce37250a4a77a02505055f541
3
+ size 14308
run-0/checkpoint-4/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec8328a101ecfb9328a192aa4c891b28e4011a7c3d865d47f696e29975c79888
3
+ size 1064
run-0/checkpoint-4/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-4/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-4/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-4/trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.70751953125,
3
+ "best_model_checkpoint": "test_trainer\\run-0\\checkpoint-3",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4,
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
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.0,
24
+ "eval_f1": 0.0,
25
+ "eval_loss": 0.7080078125,
26
+ "eval_runtime": 0.1514,
27
+ "eval_samples_per_second": 6.605,
28
+ "eval_steps_per_second": 6.605,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 3.0,
33
+ "eval_accuracy": 0.0,
34
+ "eval_f1": 0.0,
35
+ "eval_loss": 0.70751953125,
36
+ "eval_runtime": 0.1497,
37
+ "eval_samples_per_second": 6.681,
38
+ "eval_steps_per_second": 6.681,
39
+ "step": 3
40
+ },
41
+ {
42
+ "epoch": 4.0,
43
+ "eval_accuracy": 0.0,
44
+ "eval_f1": 0.0,
45
+ "eval_loss": 0.70751953125,
46
+ "eval_runtime": 0.1815,
47
+ "eval_samples_per_second": 5.51,
48
+ "eval_steps_per_second": 5.51,
49
+ "step": 4
50
+ }
51
+ ],
52
+ "logging_steps": 500,
53
+ "max_steps": 5,
54
+ "num_input_tokens_seen": 0,
55
+ "num_train_epochs": 5,
56
+ "save_steps": 500,
57
+ "total_flos": 0,
58
+ "train_batch_size": 8,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "gradient_accumulation_steps": 8,
62
+ "learning_rate": 7.543213106016258e-06,
63
+ "num_train_epochs": 5,
64
+ "optimizer": "AdamW",
65
+ "seed": 48,
66
+ "warmup_ratio": 0.2668631355210866,
67
+ "warmup_steps": 204,
68
+ "weight_decay": 0.4761015845296048
69
+ }
70
+ }
run-0/checkpoint-4/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75d07f95613d82874f5c1c1a8ba5956eb7a8647edfa0d0ba7a2261402aaea793
3
+ size 4856
run-0/checkpoint-4/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-5/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-5/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-5/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c08b633e2e0f6b02d1ab59de7788a7aac7322d65152ec4bc4ad8d62e38587716
3
+ size 1738480904
run-0/checkpoint-5/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7bd8ac540ea34a9d47bdfa1abe15c96f9fd1963f4fe25b5c62c74747cc29a84
3
+ size 4554273
run-0/checkpoint-5/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18308430d4d6058308cc7aa38b35086c7b54b6b3ddbb9b70089a8a7c83e0fa85
3
+ size 14308
run-0/checkpoint-5/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f1afa49e5045bdde66f8b816a340ff2540385d98345ad4c7207da0793c008c
3
+ size 1064
run-0/checkpoint-5/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-5/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff