Hugging Face's logo

Reyad-Ahmmed
/
hf-data-timeframe

ONNX
Safetensors
Model card Files
xet
 Community
Reyad-Ahmmed commited on
Commit
136f052
·
1 Parent(s): 5071dc2

initial commit.

Browse files
Files changed (37) hide show
  1. data-timeframe_model/config.json +45 -0
  2. data-timeframe_model/model.safetensors +3 -0
  3. data-timeframe_tokenizer/merges.txt +0 -0
  4. data-timeframe_tokenizer/special_tokens_map.json +51 -0
  5. data-timeframe_tokenizer/tokenizer_config.json +57 -0
  6. data-timeframe_tokenizer/vocab.json +0 -0
  7. logs_data-timeframe/events.out.tfevents.1735047620.DESKTOP-V8OQANU.13272.0 +3 -0
  8. logs_data-timeframe/events.out.tfevents.1735048136.DESKTOP-V8OQANU.13272.1 +3 -0
  9. logs_data-timeframe/events.out.tfevents.1735048599.DESKTOP-V8OQANU.31244.0 +3 -0
  10. logs_data-timeframe/events.out.tfevents.1735049133.DESKTOP-V8OQANU.31244.1 +3 -0
  11. logs_data-timeframe/events.out.tfevents.1735050480.DESKTOP-V8OQANU.19216.0 +3 -0
  12. logs_data-timeframe/events.out.tfevents.1735051069.DESKTOP-V8OQANU.19216.1 +3 -0
  13. logs_data-timeframe/events.out.tfevents.1735051176.DESKTOP-V8OQANU.9580.0 +3 -0
  14. logs_data-timeframe/events.out.tfevents.1735051765.DESKTOP-V8OQANU.9580.1 +3 -0
  15. logs_data-timeframe/events.out.tfevents.1735052065.DESKTOP-V8OQANU.29144.0 +3 -0
  16. logs_data-timeframe/events.out.tfevents.1735052687.DESKTOP-V8OQANU.29144.1 +3 -0
  17. results_data-timeframe/checkpoint-500/config.json +45 -0
  18. results_data-timeframe/checkpoint-500/model.safetensors +3 -0
  19. results_data-timeframe/checkpoint-500/optimizer.pt +3 -0
  20. results_data-timeframe/checkpoint-500/rng_state.pth +3 -0
  21. results_data-timeframe/checkpoint-500/scheduler.pt +3 -0
  22. results_data-timeframe/checkpoint-500/trainer_state.json +543 -0
  23. results_data-timeframe/checkpoint-500/training_args.bin +3 -0
  24. results_data-timeframe/checkpoint-550/config.json +45 -0
  25. results_data-timeframe/checkpoint-550/model.safetensors +3 -0
  26. results_data-timeframe/checkpoint-550/optimizer.pt +3 -0
  27. results_data-timeframe/checkpoint-550/rng_state.pth +3 -0
  28. results_data-timeframe/checkpoint-550/scheduler.pt +3 -0
  29. results_data-timeframe/checkpoint-550/trainer_state.json +610 -0
  30. results_data-timeframe/checkpoint-550/training_args.bin +3 -0
  31. results_data-timeframe/checkpoint-600/config.json +45 -0
  32. results_data-timeframe/checkpoint-600/model.safetensors +3 -0
  33. results_data-timeframe/checkpoint-600/optimizer.pt +3 -0
  34. results_data-timeframe/checkpoint-600/rng_state.pth +3 -0
  35. results_data-timeframe/checkpoint-600/scheduler.pt +3 -0
  36. results_data-timeframe/checkpoint-600/trainer_state.json +645 -0
  37. results_data-timeframe/checkpoint-600/training_args.bin +3 -0
data-timeframe_model/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_attentions": true,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.47.0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 50265
45
+ }
data-timeframe_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:376187c9c95223ab42d3efdcc84b08dce45fc79d83e2f1a299c0686f02b37718
3
+ size 498625128
data-timeframe_tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
data-timeframe_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
data-timeframe_tokenizer/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": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "unk_token": "<unk>"
57
+ }
data-timeframe_tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
logs_data-timeframe/events.out.tfevents.1735047620.DESKTOP-V8OQANU.13272.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1922ad9a5b09899668cdb61888c7f9be5417109c8a48a6fbf4abdb631b2e3c02
3
+ size 22893
logs_data-timeframe/events.out.tfevents.1735048136.DESKTOP-V8OQANU.13272.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a2b45f945739b98fa3c727d8a91855f614d19f99ffa27749cd61718ff38016f
3
+ size 359
logs_data-timeframe/events.out.tfevents.1735048599.DESKTOP-V8OQANU.31244.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c2cf46640d7a8a2ab9fd456e86d44b0e5bf3610487e72420be613373819c50
3
+ size 22931
logs_data-timeframe/events.out.tfevents.1735049133.DESKTOP-V8OQANU.31244.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2986977d381e2cd6c926bec133167622f686f7b04c2638c3f6ba1cd510be939
3
+ size 359
logs_data-timeframe/events.out.tfevents.1735050480.DESKTOP-V8OQANU.19216.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66908ebc1bcf1f017807e3e0b8d549a09af78d88248c9e905b3b543ec3d62a87
3
+ size 23991
logs_data-timeframe/events.out.tfevents.1735051069.DESKTOP-V8OQANU.19216.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e413e2445346ea234ffbf5a58283c0fdd7b5b4409c015ab5d730d9c25ec5b35
3
+ size 359
logs_data-timeframe/events.out.tfevents.1735051176.DESKTOP-V8OQANU.9580.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a98866c696edbc415db425d8d7f8e3c07cd7b6be96e40f3c0af791d8ee502de5
3
+ size 23991
logs_data-timeframe/events.out.tfevents.1735051765.DESKTOP-V8OQANU.9580.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dacdac46f560bf53c6c510cb5560d2ffa41ea20f76e5baf6063d0243e1d00734
3
+ size 359
logs_data-timeframe/events.out.tfevents.1735052065.DESKTOP-V8OQANU.29144.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c1f93a68a3903324a8c9744e512886d5c3d2cb18785bf1cdc9c652dc2f42469
3
+ size 25046
logs_data-timeframe/events.out.tfevents.1735052687.DESKTOP-V8OQANU.29144.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76738ad9f35342be4bba945947c2e8306f397b26461938f2ade6725847c5e434
3
+ size 359
results_data-timeframe/checkpoint-500/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_attentions": true,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.47.0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 50265
45
+ }
results_data-timeframe/checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d6e0766d033e2ff1341352a699cc3654c969044c3c9e8a39244e4a8d994a5e
3
+ size 498625128
results_data-timeframe/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30cfa0941023e5e624984bf59994d75c42bde450550e28d20ec3aca4bca07519
3
+ size 997364474
results_data-timeframe/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1dd74c522de9b2ebf9e3de4f1d7065e4056e29a472dae3b5b3877c163ab7396
3
+ size 13990
results_data-timeframe/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b95887d087ecb9b076f77f879a5bab49b20a51f9528a2ace2fcec20a5769453f
3
+ size 1064
results_data-timeframe/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,543 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 20.833333333333332,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4166666666666667,
13
+ "grad_norm": 6.0618205070495605,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 1.798,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.8333333333333334,
20
+ "grad_norm": 6.417165279388428,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 1.7985,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 1.7860785722732544,
28
+ "eval_runtime": 0.3111,
29
+ "eval_samples_per_second": 41.789,
30
+ "eval_steps_per_second": 22.502,
31
+ "step": 24
32
+ },
33
+ {
34
+ "epoch": 1.25,
35
+ "grad_norm": 4.898193359375,
36
+ "learning_rate": 3e-06,
37
+ "loss": 1.8044,
38
+ "step": 30
39
+ },
40
+ {
41
+ "epoch": 1.6666666666666665,
42
+ "grad_norm": 11.263764381408691,
43
+ "learning_rate": 4.000000000000001e-06,
44
+ "loss": 1.7697,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_loss": 1.7887693643569946,
50
+ "eval_runtime": 0.348,
51
+ "eval_samples_per_second": 37.356,
52
+ "eval_steps_per_second": 20.115,
53
+ "step": 48
54
+ },
55
+ {
56
+ "epoch": 2.0833333333333335,
57
+ "grad_norm": 8.04253101348877,
58
+ "learning_rate": 5e-06,
59
+ "loss": 1.8272,
60
+ "step": 50
61
+ },
62
+ {
63
+ "epoch": 2.5,
64
+ "grad_norm": 8.051115989685059,
65
+ "learning_rate": 6e-06,
66
+ "loss": 1.8026,
67
+ "step": 60
68
+ },
69
+ {
70
+ "epoch": 2.9166666666666665,
71
+ "grad_norm": 5.35995626449585,
72
+ "learning_rate": 7.000000000000001e-06,
73
+ "loss": 1.7747,
74
+ "step": 70
75
+ },
76
+ {
77
+ "epoch": 3.0,
78
+ "eval_loss": 1.7891459465026855,
79
+ "eval_runtime": 0.303,
80
+ "eval_samples_per_second": 42.904,
81
+ "eval_steps_per_second": 23.102,
82
+ "step": 72
83
+ },
84
+ {
85
+ "epoch": 3.3333333333333335,
86
+ "grad_norm": 9.972128868103027,
87
+ "learning_rate": 8.000000000000001e-06,
88
+ "loss": 1.8083,
89
+ "step": 80
90
+ },
91
+ {
92
+ "epoch": 3.75,
93
+ "grad_norm": 8.969843864440918,
94
+ "learning_rate": 9e-06,
95
+ "loss": 1.7868,
96
+ "step": 90
97
+ },
98
+ {
99
+ "epoch": 4.0,
100
+ "eval_loss": 1.7817317247390747,
101
+ "eval_runtime": 0.3946,
102
+ "eval_samples_per_second": 32.949,
103
+ "eval_steps_per_second": 17.742,
104
+ "step": 96
105
+ },
106
+ {
107
+ "epoch": 4.166666666666667,
108
+ "grad_norm": 11.44456958770752,
109
+ "learning_rate": 1e-05,
110
+ "loss": 1.7434,
111
+ "step": 100
112
+ },
113
+ {
114
+ "epoch": 4.583333333333333,
115
+ "grad_norm": 8.22879409790039,
116
+ "learning_rate": 1.1000000000000001e-05,
117
+ "loss": 1.7098,
118
+ "step": 110
119
+ },
120
+ {
121
+ "epoch": 5.0,
122
+ "grad_norm": 16.9021053314209,
123
+ "learning_rate": 1.2e-05,
124
+ "loss": 1.7193,
125
+ "step": 120
126
+ },
127
+ {
128
+ "epoch": 5.0,
129
+ "eval_loss": 1.654787302017212,
130
+ "eval_runtime": 0.3,
131
+ "eval_samples_per_second": 43.332,
132
+ "eval_steps_per_second": 23.333,
133
+ "step": 120
134
+ },
135
+ {
136
+ "epoch": 5.416666666666667,
137
+ "grad_norm": 20.225313186645508,
138
+ "learning_rate": 1.3000000000000001e-05,
139
+ "loss": 1.4464,
140
+ "step": 130
141
+ },
142
+ {
143
+ "epoch": 5.833333333333333,
144
+ "grad_norm": 16.05558204650879,
145
+ "learning_rate": 1.4000000000000001e-05,
146
+ "loss": 1.224,
147
+ "step": 140
148
+ },
149
+ {
150
+ "epoch": 6.0,
151
+ "eval_loss": 0.9721017479896545,
152
+ "eval_runtime": 0.3072,
153
+ "eval_samples_per_second": 42.316,
154
+ "eval_steps_per_second": 22.786,
155
+ "step": 144
156
+ },
157
+ {
158
+ "epoch": 6.25,
159
+ "grad_norm": 25.41301727294922,
160
+ "learning_rate": 1.5e-05,
161
+ "loss": 0.9575,
162
+ "step": 150
163
+ },
164
+ {
165
+ "epoch": 6.666666666666667,
166
+ "grad_norm": 16.681772232055664,
167
+ "learning_rate": 1.6000000000000003e-05,
168
+ "loss": 0.7018,
169
+ "step": 160
170
+ },
171
+ {
172
+ "epoch": 7.0,
173
+ "eval_loss": 0.45807310938835144,
174
+ "eval_runtime": 0.3083,
175
+ "eval_samples_per_second": 42.169,
176
+ "eval_steps_per_second": 22.706,
177
+ "step": 168
178
+ },
179
+ {
180
+ "epoch": 7.083333333333333,
181
+ "grad_norm": 17.640907287597656,
182
+ "learning_rate": 1.7000000000000003e-05,
183
+ "loss": 0.5636,
184
+ "step": 170
185
+ },
186
+ {
187
+ "epoch": 7.5,
188
+ "grad_norm": 27.690807342529297,
189
+ "learning_rate": 1.8e-05,
190
+ "loss": 0.3966,
191
+ "step": 180
192
+ },
193
+ {
194
+ "epoch": 7.916666666666667,
195
+ "grad_norm": 12.304574012756348,
196
+ "learning_rate": 1.9e-05,
197
+ "loss": 0.2749,
198
+ "step": 190
199
+ },
200
+ {
201
+ "epoch": 8.0,
202
+ "eval_loss": 0.21334221959114075,
203
+ "eval_runtime": 0.403,
204
+ "eval_samples_per_second": 32.257,
205
+ "eval_steps_per_second": 17.369,
206
+ "step": 192
207
+ },
208
+ {
209
+ "epoch": 8.333333333333334,
210
+ "grad_norm": 7.840561389923096,
211
+ "learning_rate": 2e-05,
212
+ "loss": 0.2055,
213
+ "step": 200
214
+ },
215
+ {
216
+ "epoch": 8.75,
217
+ "grad_norm": 1.9353489875793457,
218
+ "learning_rate": 2.1e-05,
219
+ "loss": 0.1099,
220
+ "step": 210
221
+ },
222
+ {
223
+ "epoch": 9.0,
224
+ "eval_loss": 0.10991117358207703,
225
+ "eval_runtime": 0.3071,
226
+ "eval_samples_per_second": 42.327,
227
+ "eval_steps_per_second": 22.791,
228
+ "step": 216
229
+ },
230
+ {
231
+ "epoch": 9.166666666666666,
232
+ "grad_norm": 1.330659031867981,
233
+ "learning_rate": 2.2000000000000003e-05,
234
+ "loss": 0.0665,
235
+ "step": 220
236
+ },
237
+ {
238
+ "epoch": 9.583333333333334,
239
+ "grad_norm": 0.8371493816375732,
240
+ "learning_rate": 2.3000000000000003e-05,
241
+ "loss": 0.0411,
242
+ "step": 230
243
+ },
244
+ {
245
+ "epoch": 10.0,
246
+ "grad_norm": 1.259158968925476,
247
+ "learning_rate": 2.4e-05,
248
+ "loss": 0.0448,
249
+ "step": 240
250
+ },
251
+ {
252
+ "epoch": 10.0,
253
+ "eval_loss": 0.3714790344238281,
254
+ "eval_runtime": 0.3101,
255
+ "eval_samples_per_second": 41.924,
256
+ "eval_steps_per_second": 22.574,
257
+ "step": 240
258
+ },
259
+ {
260
+ "epoch": 10.416666666666666,
261
+ "grad_norm": 1.5030195713043213,
262
+ "learning_rate": 2.5e-05,
263
+ "loss": 0.0756,
264
+ "step": 250
265
+ },
266
+ {
267
+ "epoch": 10.833333333333334,
268
+ "grad_norm": 0.26728466153144836,
269
+ "learning_rate": 2.6000000000000002e-05,
270
+ "loss": 0.0142,
271
+ "step": 260
272
+ },
273
+ {
274
+ "epoch": 11.0,
275
+ "eval_loss": 0.028693975880742073,
276
+ "eval_runtime": 0.3216,
277
+ "eval_samples_per_second": 40.417,
278
+ "eval_steps_per_second": 21.763,
279
+ "step": 264
280
+ },
281
+ {
282
+ "epoch": 11.25,
283
+ "grad_norm": 0.18753524124622345,
284
+ "learning_rate": 2.7000000000000002e-05,
285
+ "loss": 0.0093,
286
+ "step": 270
287
+ },
288
+ {
289
+ "epoch": 11.666666666666666,
290
+ "grad_norm": 0.11348039656877518,
291
+ "learning_rate": 2.8000000000000003e-05,
292
+ "loss": 0.0064,
293
+ "step": 280
294
+ },
295
+ {
296
+ "epoch": 12.0,
297
+ "eval_loss": 0.028606100007891655,
298
+ "eval_runtime": 0.3211,
299
+ "eval_samples_per_second": 40.492,
300
+ "eval_steps_per_second": 21.803,
301
+ "step": 288
302
+ },
303
+ {
304
+ "epoch": 12.083333333333334,
305
+ "grad_norm": 0.0765966922044754,
306
+ "learning_rate": 2.9e-05,
307
+ "loss": 0.0058,
308
+ "step": 290
309
+ },
310
+ {
311
+ "epoch": 12.5,
312
+ "grad_norm": 0.08425896614789963,
313
+ "learning_rate": 3e-05,
314
+ "loss": 0.0042,
315
+ "step": 300
316
+ },
317
+ {
318
+ "epoch": 12.916666666666666,
319
+ "grad_norm": 0.14490404725074768,
320
+ "learning_rate": 3.1e-05,
321
+ "loss": 0.0043,
322
+ "step": 310
323
+ },
324
+ {
325
+ "epoch": 13.0,
326
+ "eval_loss": 0.019509978592395782,
327
+ "eval_runtime": 0.3866,
328
+ "eval_samples_per_second": 33.624,
329
+ "eval_steps_per_second": 18.105,
330
+ "step": 312
331
+ },
332
+ {
333
+ "epoch": 13.333333333333334,
334
+ "grad_norm": 0.05439736321568489,
335
+ "learning_rate": 3.2000000000000005e-05,
336
+ "loss": 0.0034,
337
+ "step": 320
338
+ },
339
+ {
340
+ "epoch": 13.75,
341
+ "grad_norm": 0.04903283342719078,
342
+ "learning_rate": 3.3e-05,
343
+ "loss": 0.0028,
344
+ "step": 330
345
+ },
346
+ {
347
+ "epoch": 14.0,
348
+ "eval_loss": 0.010294664651155472,
349
+ "eval_runtime": 0.3059,
350
+ "eval_samples_per_second": 42.501,
351
+ "eval_steps_per_second": 22.885,
352
+ "step": 336
353
+ },
354
+ {
355
+ "epoch": 14.166666666666666,
356
+ "grad_norm": 0.057338546961545944,
357
+ "learning_rate": 3.4000000000000007e-05,
358
+ "loss": 0.0026,
359
+ "step": 340
360
+ },
361
+ {
362
+ "epoch": 14.583333333333334,
363
+ "grad_norm": 0.053346164524555206,
364
+ "learning_rate": 3.5e-05,
365
+ "loss": 0.0026,
366
+ "step": 350
367
+ },
368
+ {
369
+ "epoch": 15.0,
370
+ "grad_norm": 0.05332862585783005,
371
+ "learning_rate": 3.6e-05,
372
+ "loss": 0.0022,
373
+ "step": 360
374
+ },
375
+ {
376
+ "epoch": 15.0,
377
+ "eval_loss": 0.012851966544985771,
378
+ "eval_runtime": 0.3306,
379
+ "eval_samples_per_second": 39.321,
380
+ "eval_steps_per_second": 21.173,
381
+ "step": 360
382
+ },
383
+ {
384
+ "epoch": 15.416666666666666,
385
+ "grad_norm": 0.05147263780236244,
386
+ "learning_rate": 3.7e-05,
387
+ "loss": 0.0022,
388
+ "step": 370
389
+ },
390
+ {
391
+ "epoch": 15.833333333333334,
392
+ "grad_norm": 0.04216151684522629,
393
+ "learning_rate": 3.8e-05,
394
+ "loss": 0.0018,
395
+ "step": 380
396
+ },
397
+ {
398
+ "epoch": 16.0,
399
+ "eval_loss": 0.00792662426829338,
400
+ "eval_runtime": 0.3955,
401
+ "eval_samples_per_second": 32.87,
402
+ "eval_steps_per_second": 17.699,
403
+ "step": 384
404
+ },
405
+ {
406
+ "epoch": 16.25,
407
+ "grad_norm": 0.03432933986186981,
408
+ "learning_rate": 3.9000000000000006e-05,
409
+ "loss": 0.0018,
410
+ "step": 390
411
+ },
412
+ {
413
+ "epoch": 16.666666666666668,
414
+ "grad_norm": 0.0388726145029068,
415
+ "learning_rate": 4e-05,
416
+ "loss": 0.0017,
417
+ "step": 400
418
+ },
419
+ {
420
+ "epoch": 17.0,
421
+ "eval_loss": 0.002699882024899125,
422
+ "eval_runtime": 0.3106,
423
+ "eval_samples_per_second": 41.848,
424
+ "eval_steps_per_second": 22.534,
425
+ "step": 408
426
+ },
427
+ {
428
+ "epoch": 17.083333333333332,
429
+ "grad_norm": 0.030444540083408356,
430
+ "learning_rate": 4.1e-05,
431
+ "loss": 0.0016,
432
+ "step": 410
433
+ },
434
+ {
435
+ "epoch": 17.5,
436
+ "grad_norm": 0.02462877333164215,
437
+ "learning_rate": 4.2e-05,
438
+ "loss": 0.0016,
439
+ "step": 420
440
+ },
441
+ {
442
+ "epoch": 17.916666666666668,
443
+ "grad_norm": 0.022693680599331856,
444
+ "learning_rate": 4.3e-05,
445
+ "loss": 0.0014,
446
+ "step": 430
447
+ },
448
+ {
449
+ "epoch": 18.0,
450
+ "eval_loss": 0.003563512582331896,
451
+ "eval_runtime": 0.3097,
452
+ "eval_samples_per_second": 41.971,
453
+ "eval_steps_per_second": 22.6,
454
+ "step": 432
455
+ },
456
+ {
457
+ "epoch": 18.333333333333332,
458
+ "grad_norm": 0.02234797179698944,
459
+ "learning_rate": 4.4000000000000006e-05,
460
+ "loss": 0.0015,
461
+ "step": 440
462
+ },
463
+ {
464
+ "epoch": 18.75,
465
+ "grad_norm": 0.03259611874818802,
466
+ "learning_rate": 4.5e-05,
467
+ "loss": 0.0013,
468
+ "step": 450
469
+ },
470
+ {
471
+ "epoch": 19.0,
472
+ "eval_loss": 0.004523274954408407,
473
+ "eval_runtime": 0.4017,
474
+ "eval_samples_per_second": 32.362,
475
+ "eval_steps_per_second": 17.426,
476
+ "step": 456
477
+ },
478
+ {
479
+ "epoch": 19.166666666666668,
480
+ "grad_norm": 0.021357201039791107,
481
+ "learning_rate": 4.600000000000001e-05,
482
+ "loss": 0.0011,
483
+ "step": 460
484
+ },
485
+ {
486
+ "epoch": 19.583333333333332,
487
+ "grad_norm": 0.021904248744249344,
488
+ "learning_rate": 4.7e-05,
489
+ "loss": 0.0012,
490
+ "step": 470
491
+ },
492
+ {
493
+ "epoch": 20.0,
494
+ "grad_norm": 0.023305868729948997,
495
+ "learning_rate": 4.8e-05,
496
+ "loss": 0.0012,
497
+ "step": 480
498
+ },
499
+ {
500
+ "epoch": 20.0,
501
+ "eval_loss": 0.00353155261836946,
502
+ "eval_runtime": 0.3179,
503
+ "eval_samples_per_second": 40.893,
504
+ "eval_steps_per_second": 22.019,
505
+ "step": 480
506
+ },
507
+ {
508
+ "epoch": 20.416666666666668,
509
+ "grad_norm": 0.019376859068870544,
510
+ "learning_rate": 4.9e-05,
511
+ "loss": 0.001,
512
+ "step": 490
513
+ },
514
+ {
515
+ "epoch": 20.833333333333332,
516
+ "grad_norm": 0.013724086806178093,
517
+ "learning_rate": 5e-05,
518
+ "loss": 0.001,
519
+ "step": 500
520
+ }
521
+ ],
522
+ "logging_steps": 10,
523
+ "max_steps": 600,
524
+ "num_input_tokens_seen": 0,
525
+ "num_train_epochs": 25,
526
+ "save_steps": 500,
527
+ "stateful_callbacks": {
528
+ "TrainerControl": {
529
+ "args": {
530
+ "should_epoch_stop": false,
531
+ "should_evaluate": false,
532
+ "should_log": false,
533
+ "should_save": true,
534
+ "should_training_stop": false
535
+ },
536
+ "attributes": {}
537
+ }
538
+ },
539
+ "total_flos": 10792051956000.0,
540
+ "train_batch_size": 2,
541
+ "trial_name": null,
542
+ "trial_params": null
543
+ }
results_data-timeframe/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5b127a0fcad90022b910ab6e74e044a789717da0938e142c39fde1fe9ce365
3
+ size 5304
results_data-timeframe/checkpoint-550/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_attentions": true,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.47.0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 50265
45
+ }
results_data-timeframe/checkpoint-550/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc3d3ccf05f56b6c64ab05ec23c702e196482726a2e2246cb81cae61a9f7ac43
3
+ size 498625128
results_data-timeframe/checkpoint-550/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c3671ab51de38c685afebe5f9f3601e6e26f94299f23982b2b0ddddc7c0787
3
+ size 997364474
results_data-timeframe/checkpoint-550/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81887768dd0c9351006e8bf73d8c3a7c0733fc17ca97a29e98c20d492c3d332d
3
+ size 13990
results_data-timeframe/checkpoint-550/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04eb2f5e8d3e50735714e65d0d29701a4ff692f39f71fee44b1906c2c2c9b8cf
3
+ size 1064
results_data-timeframe/checkpoint-550/trainer_state.json ADDED
@@ -0,0 +1,610 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 25.0,
5
+ "eval_steps": 500,
6
+ "global_step": 550,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.45454545454545453,
13
+ "grad_norm": 6.3619704246521,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 1.8722,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.9090909090909091,
20
+ "grad_norm": 6.3357253074646,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 1.7585,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 1.797034502029419,
28
+ "eval_runtime": 0.3138,
29
+ "eval_samples_per_second": 35.055,
30
+ "eval_steps_per_second": 19.121,
31
+ "step": 22
32
+ },
33
+ {
34
+ "epoch": 1.3636363636363638,
35
+ "grad_norm": 5.592566967010498,
36
+ "learning_rate": 3e-06,
37
+ "loss": 1.8594,
38
+ "step": 30
39
+ },
40
+ {
41
+ "epoch": 1.8181818181818183,
42
+ "grad_norm": 12.072809219360352,
43
+ "learning_rate": 4.000000000000001e-06,
44
+ "loss": 1.8278,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_loss": 1.7967263460159302,
50
+ "eval_runtime": 0.2731,
51
+ "eval_samples_per_second": 40.273,
52
+ "eval_steps_per_second": 21.967,
53
+ "step": 44
54
+ },
55
+ {
56
+ "epoch": 2.2727272727272725,
57
+ "grad_norm": 5.9688825607299805,
58
+ "learning_rate": 5e-06,
59
+ "loss": 1.8067,
60
+ "step": 50
61
+ },
62
+ {
63
+ "epoch": 2.7272727272727275,
64
+ "grad_norm": 9.522181510925293,
65
+ "learning_rate": 6e-06,
66
+ "loss": 1.766,
67
+ "step": 60
68
+ },
69
+ {
70
+ "epoch": 3.0,
71
+ "eval_loss": 1.7915326356887817,
72
+ "eval_runtime": 0.3341,
73
+ "eval_samples_per_second": 32.921,
74
+ "eval_steps_per_second": 17.957,
75
+ "step": 66
76
+ },
77
+ {
78
+ "epoch": 3.1818181818181817,
79
+ "grad_norm": 6.273972511291504,
80
+ "learning_rate": 7.000000000000001e-06,
81
+ "loss": 1.7968,
82
+ "step": 70
83
+ },
84
+ {
85
+ "epoch": 3.6363636363636362,
86
+ "grad_norm": 16.80594253540039,
87
+ "learning_rate": 8.000000000000001e-06,
88
+ "loss": 1.8274,
89
+ "step": 80
90
+ },
91
+ {
92
+ "epoch": 4.0,
93
+ "eval_loss": 1.7816592454910278,
94
+ "eval_runtime": 0.2893,
95
+ "eval_samples_per_second": 38.021,
96
+ "eval_steps_per_second": 20.738,
97
+ "step": 88
98
+ },
99
+ {
100
+ "epoch": 4.090909090909091,
101
+ "grad_norm": 8.12016773223877,
102
+ "learning_rate": 9e-06,
103
+ "loss": 1.7927,
104
+ "step": 90
105
+ },
106
+ {
107
+ "epoch": 4.545454545454545,
108
+ "grad_norm": 14.367834091186523,
109
+ "learning_rate": 1e-05,
110
+ "loss": 1.6433,
111
+ "step": 100
112
+ },
113
+ {
114
+ "epoch": 5.0,
115
+ "grad_norm": 33.552955627441406,
116
+ "learning_rate": 1.1000000000000001e-05,
117
+ "loss": 1.5921,
118
+ "step": 110
119
+ },
120
+ {
121
+ "epoch": 5.0,
122
+ "eval_loss": 1.5441871881484985,
123
+ "eval_runtime": 0.3083,
124
+ "eval_samples_per_second": 35.675,
125
+ "eval_steps_per_second": 19.459,
126
+ "step": 110
127
+ },
128
+ {
129
+ "epoch": 5.454545454545454,
130
+ "grad_norm": 21.968534469604492,
131
+ "learning_rate": 1.2e-05,
132
+ "loss": 1.3509,
133
+ "step": 120
134
+ },
135
+ {
136
+ "epoch": 5.909090909090909,
137
+ "grad_norm": 18.8609676361084,
138
+ "learning_rate": 1.3000000000000001e-05,
139
+ "loss": 1.0549,
140
+ "step": 130
141
+ },
142
+ {
143
+ "epoch": 6.0,
144
+ "eval_loss": 1.0241355895996094,
145
+ "eval_runtime": 0.3401,
146
+ "eval_samples_per_second": 32.346,
147
+ "eval_steps_per_second": 17.643,
148
+ "step": 132
149
+ },
150
+ {
151
+ "epoch": 6.363636363636363,
152
+ "grad_norm": 19.167179107666016,
153
+ "learning_rate": 1.4000000000000001e-05,
154
+ "loss": 0.7375,
155
+ "step": 140
156
+ },
157
+ {
158
+ "epoch": 6.818181818181818,
159
+ "grad_norm": 16.344825744628906,
160
+ "learning_rate": 1.5e-05,
161
+ "loss": 0.7427,
162
+ "step": 150
163
+ },
164
+ {
165
+ "epoch": 7.0,
166
+ "eval_loss": 0.8524442315101624,
167
+ "eval_runtime": 0.3202,
168
+ "eval_samples_per_second": 34.355,
169
+ "eval_steps_per_second": 18.739,
170
+ "step": 154
171
+ },
172
+ {
173
+ "epoch": 7.2727272727272725,
174
+ "grad_norm": 10.574152946472168,
175
+ "learning_rate": 1.6000000000000003e-05,
176
+ "loss": 0.7065,
177
+ "step": 160
178
+ },
179
+ {
180
+ "epoch": 7.7272727272727275,
181
+ "grad_norm": 9.10021686553955,
182
+ "learning_rate": 1.7000000000000003e-05,
183
+ "loss": 0.3282,
184
+ "step": 170
185
+ },
186
+ {
187
+ "epoch": 8.0,
188
+ "eval_loss": 0.5009013414382935,
189
+ "eval_runtime": 0.2793,
190
+ "eval_samples_per_second": 39.38,
191
+ "eval_steps_per_second": 21.48,
192
+ "step": 176
193
+ },
194
+ {
195
+ "epoch": 8.181818181818182,
196
+ "grad_norm": 3.470022678375244,
197
+ "learning_rate": 1.8e-05,
198
+ "loss": 0.2607,
199
+ "step": 180
200
+ },
201
+ {
202
+ "epoch": 8.636363636363637,
203
+ "grad_norm": 65.46636962890625,
204
+ "learning_rate": 1.9e-05,
205
+ "loss": 0.3273,
206
+ "step": 190
207
+ },
208
+ {
209
+ "epoch": 9.0,
210
+ "eval_loss": 0.5072993040084839,
211
+ "eval_runtime": 0.2935,
212
+ "eval_samples_per_second": 37.476,
213
+ "eval_steps_per_second": 20.441,
214
+ "step": 198
215
+ },
216
+ {
217
+ "epoch": 9.090909090909092,
218
+ "grad_norm": 4.038318634033203,
219
+ "learning_rate": 2e-05,
220
+ "loss": 0.1661,
221
+ "step": 200
222
+ },
223
+ {
224
+ "epoch": 9.545454545454545,
225
+ "grad_norm": 0.9277220964431763,
226
+ "learning_rate": 2.1e-05,
227
+ "loss": 0.1635,
228
+ "step": 210
229
+ },
230
+ {
231
+ "epoch": 10.0,
232
+ "grad_norm": 0.41654789447784424,
233
+ "learning_rate": 2.2000000000000003e-05,
234
+ "loss": 0.0855,
235
+ "step": 220
236
+ },
237
+ {
238
+ "epoch": 10.0,
239
+ "eval_loss": 0.29970234632492065,
240
+ "eval_runtime": 0.2951,
241
+ "eval_samples_per_second": 37.272,
242
+ "eval_steps_per_second": 20.33,
243
+ "step": 220
244
+ },
245
+ {
246
+ "epoch": 10.454545454545455,
247
+ "grad_norm": 0.25648927688598633,
248
+ "learning_rate": 2.3000000000000003e-05,
249
+ "loss": 0.092,
250
+ "step": 230
251
+ },
252
+ {
253
+ "epoch": 10.909090909090908,
254
+ "grad_norm": 0.23954086005687714,
255
+ "learning_rate": 2.4e-05,
256
+ "loss": 0.0599,
257
+ "step": 240
258
+ },
259
+ {
260
+ "epoch": 11.0,
261
+ "eval_loss": 0.2056308388710022,
262
+ "eval_runtime": 0.3001,
263
+ "eval_samples_per_second": 36.655,
264
+ "eval_steps_per_second": 19.993,
265
+ "step": 242
266
+ },
267
+ {
268
+ "epoch": 11.363636363636363,
269
+ "grad_norm": 0.194340318441391,
270
+ "learning_rate": 2.5e-05,
271
+ "loss": 0.0083,
272
+ "step": 250
273
+ },
274
+ {
275
+ "epoch": 11.818181818181818,
276
+ "grad_norm": 10.558298110961914,
277
+ "learning_rate": 2.6000000000000002e-05,
278
+ "loss": 0.0364,
279
+ "step": 260
280
+ },
281
+ {
282
+ "epoch": 12.0,
283
+ "eval_loss": 0.049530062824487686,
284
+ "eval_runtime": 0.2923,
285
+ "eval_samples_per_second": 37.637,
286
+ "eval_steps_per_second": 20.529,
287
+ "step": 264
288
+ },
289
+ {
290
+ "epoch": 12.272727272727273,
291
+ "grad_norm": 0.09377635270357132,
292
+ "learning_rate": 2.7000000000000002e-05,
293
+ "loss": 0.0212,
294
+ "step": 270
295
+ },
296
+ {
297
+ "epoch": 12.727272727272727,
298
+ "grad_norm": 0.14690159261226654,
299
+ "learning_rate": 2.8000000000000003e-05,
300
+ "loss": 0.0281,
301
+ "step": 280
302
+ },
303
+ {
304
+ "epoch": 13.0,
305
+ "eval_loss": 0.014700615778565407,
306
+ "eval_runtime": 0.4768,
307
+ "eval_samples_per_second": 23.07,
308
+ "eval_steps_per_second": 12.584,
309
+ "step": 286
310
+ },
311
+ {
312
+ "epoch": 13.181818181818182,
313
+ "grad_norm": 0.06858677417039871,
314
+ "learning_rate": 2.9e-05,
315
+ "loss": 0.007,
316
+ "step": 290
317
+ },
318
+ {
319
+ "epoch": 13.636363636363637,
320
+ "grad_norm": 0.06008649244904518,
321
+ "learning_rate": 3e-05,
322
+ "loss": 0.0115,
323
+ "step": 300
324
+ },
325
+ {
326
+ "epoch": 14.0,
327
+ "eval_loss": 0.015877388417720795,
328
+ "eval_runtime": 0.2851,
329
+ "eval_samples_per_second": 38.586,
330
+ "eval_steps_per_second": 21.047,
331
+ "step": 308
332
+ },
333
+ {
334
+ "epoch": 14.090909090909092,
335
+ "grad_norm": 0.08265367895364761,
336
+ "learning_rate": 3.1e-05,
337
+ "loss": 0.0082,
338
+ "step": 310
339
+ },
340
+ {
341
+ "epoch": 14.545454545454545,
342
+ "grad_norm": 0.05378866195678711,
343
+ "learning_rate": 3.2000000000000005e-05,
344
+ "loss": 0.0064,
345
+ "step": 320
346
+ },
347
+ {
348
+ "epoch": 15.0,
349
+ "grad_norm": 0.06609572470188141,
350
+ "learning_rate": 3.3e-05,
351
+ "loss": 0.0049,
352
+ "step": 330
353
+ },
354
+ {
355
+ "epoch": 15.0,
356
+ "eval_loss": 0.0037539436016231775,
357
+ "eval_runtime": 0.2789,
358
+ "eval_samples_per_second": 39.446,
359
+ "eval_steps_per_second": 21.516,
360
+ "step": 330
361
+ },
362
+ {
363
+ "epoch": 15.454545454545455,
364
+ "grad_norm": 0.10500594973564148,
365
+ "learning_rate": 3.4000000000000007e-05,
366
+ "loss": 0.0038,
367
+ "step": 340
368
+ },
369
+ {
370
+ "epoch": 15.909090909090908,
371
+ "grad_norm": 0.038604699075222015,
372
+ "learning_rate": 3.5e-05,
373
+ "loss": 0.0023,
374
+ "step": 350
375
+ },
376
+ {
377
+ "epoch": 16.0,
378
+ "eval_loss": 0.0024555029813200235,
379
+ "eval_runtime": 0.2869,
380
+ "eval_samples_per_second": 38.337,
381
+ "eval_steps_per_second": 20.911,
382
+ "step": 352
383
+ },
384
+ {
385
+ "epoch": 16.363636363636363,
386
+ "grad_norm": 0.041520051658153534,
387
+ "learning_rate": 3.6e-05,
388
+ "loss": 0.0021,
389
+ "step": 360
390
+ },
391
+ {
392
+ "epoch": 16.818181818181817,
393
+ "grad_norm": 0.12043269723653793,
394
+ "learning_rate": 3.7e-05,
395
+ "loss": 0.0026,
396
+ "step": 370
397
+ },
398
+ {
399
+ "epoch": 17.0,
400
+ "eval_loss": 0.0019283693982288241,
401
+ "eval_runtime": 0.2938,
402
+ "eval_samples_per_second": 37.443,
403
+ "eval_steps_per_second": 20.423,
404
+ "step": 374
405
+ },
406
+ {
407
+ "epoch": 17.272727272727273,
408
+ "grad_norm": 0.039373137056827545,
409
+ "learning_rate": 3.8e-05,
410
+ "loss": 0.0023,
411
+ "step": 380
412
+ },
413
+ {
414
+ "epoch": 17.727272727272727,
415
+ "grad_norm": 0.06134188547730446,
416
+ "learning_rate": 3.9000000000000006e-05,
417
+ "loss": 0.002,
418
+ "step": 390
419
+ },
420
+ {
421
+ "epoch": 18.0,
422
+ "eval_loss": 0.0014471285976469517,
423
+ "eval_runtime": 0.299,
424
+ "eval_samples_per_second": 36.789,
425
+ "eval_steps_per_second": 20.067,
426
+ "step": 396
427
+ },
428
+ {
429
+ "epoch": 18.181818181818183,
430
+ "grad_norm": 0.03507056459784508,
431
+ "learning_rate": 4e-05,
432
+ "loss": 0.0016,
433
+ "step": 400
434
+ },
435
+ {
436
+ "epoch": 18.636363636363637,
437
+ "grad_norm": 0.03312617912888527,
438
+ "learning_rate": 4.1e-05,
439
+ "loss": 0.0016,
440
+ "step": 410
441
+ },
442
+ {
443
+ "epoch": 19.0,
444
+ "eval_loss": 0.001228967565111816,
445
+ "eval_runtime": 0.3879,
446
+ "eval_samples_per_second": 28.356,
447
+ "eval_steps_per_second": 15.467,
448
+ "step": 418
449
+ },
450
+ {
451
+ "epoch": 19.09090909090909,
452
+ "grad_norm": 0.03590747341513634,
453
+ "learning_rate": 4.2e-05,
454
+ "loss": 0.0016,
455
+ "step": 420
456
+ },
457
+ {
458
+ "epoch": 19.545454545454547,
459
+ "grad_norm": 0.020240573212504387,
460
+ "learning_rate": 4.3e-05,
461
+ "loss": 0.0015,
462
+ "step": 430
463
+ },
464
+ {
465
+ "epoch": 20.0,
466
+ "grad_norm": 0.012542431242763996,
467
+ "learning_rate": 4.4000000000000006e-05,
468
+ "loss": 0.0013,
469
+ "step": 440
470
+ },
471
+ {
472
+ "epoch": 20.0,
473
+ "eval_loss": 0.0010683450382202864,
474
+ "eval_runtime": 0.2912,
475
+ "eval_samples_per_second": 37.772,
476
+ "eval_steps_per_second": 20.603,
477
+ "step": 440
478
+ },
479
+ {
480
+ "epoch": 20.454545454545453,
481
+ "grad_norm": 0.025147175416350365,
482
+ "learning_rate": 4.5e-05,
483
+ "loss": 0.0013,
484
+ "step": 450
485
+ },
486
+ {
487
+ "epoch": 20.90909090909091,
488
+ "grad_norm": 0.026972901076078415,
489
+ "learning_rate": 4.600000000000001e-05,
490
+ "loss": 0.0013,
491
+ "step": 460
492
+ },
493
+ {
494
+ "epoch": 21.0,
495
+ "eval_loss": 0.0009388752514496446,
496
+ "eval_runtime": 0.2906,
497
+ "eval_samples_per_second": 37.858,
498
+ "eval_steps_per_second": 20.65,
499
+ "step": 462
500
+ },
501
+ {
502
+ "epoch": 21.363636363636363,
503
+ "grad_norm": 0.0228286050260067,
504
+ "learning_rate": 4.7e-05,
505
+ "loss": 0.0012,
506
+ "step": 470
507
+ },
508
+ {
509
+ "epoch": 21.818181818181817,
510
+ "grad_norm": 0.030309300869703293,
511
+ "learning_rate": 4.8e-05,
512
+ "loss": 0.0011,
513
+ "step": 480
514
+ },
515
+ {
516
+ "epoch": 22.0,
517
+ "eval_loss": 0.0008690407848916948,
518
+ "eval_runtime": 0.288,
519
+ "eval_samples_per_second": 38.201,
520
+ "eval_steps_per_second": 20.837,
521
+ "step": 484
522
+ },
523
+ {
524
+ "epoch": 22.272727272727273,
525
+ "grad_norm": 0.016974693164229393,
526
+ "learning_rate": 4.9e-05,
527
+ "loss": 0.001,
528
+ "step": 490
529
+ },
530
+ {
531
+ "epoch": 22.727272727272727,
532
+ "grad_norm": 0.020530015230178833,
533
+ "learning_rate": 5e-05,
534
+ "loss": 0.001,
535
+ "step": 500
536
+ },
537
+ {
538
+ "epoch": 23.0,
539
+ "eval_loss": 0.0007521951338276267,
540
+ "eval_runtime": 0.2932,
541
+ "eval_samples_per_second": 37.517,
542
+ "eval_steps_per_second": 20.464,
543
+ "step": 506
544
+ },
545
+ {
546
+ "epoch": 23.181818181818183,
547
+ "grad_norm": 0.015264404937624931,
548
+ "learning_rate": 4e-05,
549
+ "loss": 0.0009,
550
+ "step": 510
551
+ },
552
+ {
553
+ "epoch": 23.636363636363637,
554
+ "grad_norm": 0.012872988358139992,
555
+ "learning_rate": 3e-05,
556
+ "loss": 0.0009,
557
+ "step": 520
558
+ },
559
+ {
560
+ "epoch": 24.0,
561
+ "eval_loss": 0.0007014179136604071,
562
+ "eval_runtime": 0.3154,
563
+ "eval_samples_per_second": 34.876,
564
+ "eval_steps_per_second": 19.023,
565
+ "step": 528
566
+ },
567
+ {
568
+ "epoch": 24.09090909090909,
569
+ "grad_norm": 0.023056283593177795,
570
+ "learning_rate": 2e-05,
571
+ "loss": 0.0009,
572
+ "step": 530
573
+ },
574
+ {
575
+ "epoch": 24.545454545454547,
576
+ "grad_norm": 0.013329343870282173,
577
+ "learning_rate": 1e-05,
578
+ "loss": 0.0008,
579
+ "step": 540
580
+ },
581
+ {
582
+ "epoch": 25.0,
583
+ "grad_norm": 0.016888407990336418,
584
+ "learning_rate": 0.0,
585
+ "loss": 0.0008,
586
+ "step": 550
587
+ }
588
+ ],
589
+ "logging_steps": 10,
590
+ "max_steps": 550,
591
+ "num_input_tokens_seen": 0,
592
+ "num_train_epochs": 25,
593
+ "save_steps": 500,
594
+ "stateful_callbacks": {
595
+ "TrainerControl": {
596
+ "args": {
597
+ "should_epoch_stop": false,
598
+ "should_evaluate": false,
599
+ "should_log": false,
600
+ "should_save": true,
601
+ "should_training_stop": true
602
+ },
603
+ "attributes": {}
604
+ }
605
+ },
606
+ "total_flos": 11871257151600.0,
607
+ "train_batch_size": 2,
608
+ "trial_name": null,
609
+ "trial_params": null
610
+ }
results_data-timeframe/checkpoint-550/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5b127a0fcad90022b910ab6e74e044a789717da0938e142c39fde1fe9ce365
3
+ size 5304
results_data-timeframe/checkpoint-600/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "output_attentions": true,
37
+ "pad_token_id": 1,
38
+ "position_embedding_type": "absolute",
39
+ "problem_type": "single_label_classification",
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.47.0",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 50265
45
+ }
results_data-timeframe/checkpoint-600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:376187c9c95223ab42d3efdcc84b08dce45fc79d83e2f1a299c0686f02b37718
3
+ size 498625128
results_data-timeframe/checkpoint-600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66a3a8b5b0dfa45c8ac8aa792ab5e4bd0d20eaa80b93e084a0aeadad68e68ba8
3
+ size 997364474
results_data-timeframe/checkpoint-600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd697127039785576c7789a7525c8dd760cee9a1a3b3d28e2ca7c5842e48edc
3
+ size 13990
results_data-timeframe/checkpoint-600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b755b31ac46dd906630f4879ed3ec5277276dc6e61049186e78888b9c8d75b5a
3
+ size 1064
results_data-timeframe/checkpoint-600/trainer_state.json ADDED
@@ -0,0 +1,645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 25.0,
5
+ "eval_steps": 500,
6
+ "global_step": 600,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4166666666666667,
13
+ "grad_norm": 6.0618205070495605,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 1.798,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.8333333333333334,
20
+ "grad_norm": 6.417165279388428,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 1.7985,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 1.7860785722732544,
28
+ "eval_runtime": 0.3111,
29
+ "eval_samples_per_second": 41.789,
30
+ "eval_steps_per_second": 22.502,
31
+ "step": 24
32
+ },
33
+ {
34
+ "epoch": 1.25,
35
+ "grad_norm": 4.898193359375,
36
+ "learning_rate": 3e-06,
37
+ "loss": 1.8044,
38
+ "step": 30
39
+ },
40
+ {
41
+ "epoch": 1.6666666666666665,
42
+ "grad_norm": 11.263764381408691,
43
+ "learning_rate": 4.000000000000001e-06,
44
+ "loss": 1.7697,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 2.0,
49
+ "eval_loss": 1.7887693643569946,
50
+ "eval_runtime": 0.348,
51
+ "eval_samples_per_second": 37.356,
52
+ "eval_steps_per_second": 20.115,
53
+ "step": 48
54
+ },
55
+ {
56
+ "epoch": 2.0833333333333335,
57
+ "grad_norm": 8.04253101348877,
58
+ "learning_rate": 5e-06,
59
+ "loss": 1.8272,
60
+ "step": 50
61
+ },
62
+ {
63
+ "epoch": 2.5,
64
+ "grad_norm": 8.051115989685059,
65
+ "learning_rate": 6e-06,
66
+ "loss": 1.8026,
67
+ "step": 60
68
+ },
69
+ {
70
+ "epoch": 2.9166666666666665,
71
+ "grad_norm": 5.35995626449585,
72
+ "learning_rate": 7.000000000000001e-06,
73
+ "loss": 1.7747,
74
+ "step": 70
75
+ },
76
+ {
77
+ "epoch": 3.0,
78
+ "eval_loss": 1.7891459465026855,
79
+ "eval_runtime": 0.303,
80
+ "eval_samples_per_second": 42.904,
81
+ "eval_steps_per_second": 23.102,
82
+ "step": 72
83
+ },
84
+ {
85
+ "epoch": 3.3333333333333335,
86
+ "grad_norm": 9.972128868103027,
87
+ "learning_rate": 8.000000000000001e-06,
88
+ "loss": 1.8083,
89
+ "step": 80
90
+ },
91
+ {
92
+ "epoch": 3.75,
93
+ "grad_norm": 8.969843864440918,
94
+ "learning_rate": 9e-06,
95
+ "loss": 1.7868,
96
+ "step": 90
97
+ },
98
+ {
99
+ "epoch": 4.0,
100
+ "eval_loss": 1.7817317247390747,
101
+ "eval_runtime": 0.3946,
102
+ "eval_samples_per_second": 32.949,
103
+ "eval_steps_per_second": 17.742,
104
+ "step": 96
105
+ },
106
+ {
107
+ "epoch": 4.166666666666667,
108
+ "grad_norm": 11.44456958770752,
109
+ "learning_rate": 1e-05,
110
+ "loss": 1.7434,
111
+ "step": 100
112
+ },
113
+ {
114
+ "epoch": 4.583333333333333,
115
+ "grad_norm": 8.22879409790039,
116
+ "learning_rate": 1.1000000000000001e-05,
117
+ "loss": 1.7098,
118
+ "step": 110
119
+ },
120
+ {
121
+ "epoch": 5.0,
122
+ "grad_norm": 16.9021053314209,
123
+ "learning_rate": 1.2e-05,
124
+ "loss": 1.7193,
125
+ "step": 120
126
+ },
127
+ {
128
+ "epoch": 5.0,
129
+ "eval_loss": 1.654787302017212,
130
+ "eval_runtime": 0.3,
131
+ "eval_samples_per_second": 43.332,
132
+ "eval_steps_per_second": 23.333,
133
+ "step": 120
134
+ },
135
+ {
136
+ "epoch": 5.416666666666667,
137
+ "grad_norm": 20.225313186645508,
138
+ "learning_rate": 1.3000000000000001e-05,
139
+ "loss": 1.4464,
140
+ "step": 130
141
+ },
142
+ {
143
+ "epoch": 5.833333333333333,
144
+ "grad_norm": 16.05558204650879,
145
+ "learning_rate": 1.4000000000000001e-05,
146
+ "loss": 1.224,
147
+ "step": 140
148
+ },
149
+ {
150
+ "epoch": 6.0,
151
+ "eval_loss": 0.9721017479896545,
152
+ "eval_runtime": 0.3072,
153
+ "eval_samples_per_second": 42.316,
154
+ "eval_steps_per_second": 22.786,
155
+ "step": 144
156
+ },
157
+ {
158
+ "epoch": 6.25,
159
+ "grad_norm": 25.41301727294922,
160
+ "learning_rate": 1.5e-05,
161
+ "loss": 0.9575,
162
+ "step": 150
163
+ },
164
+ {
165
+ "epoch": 6.666666666666667,
166
+ "grad_norm": 16.681772232055664,
167
+ "learning_rate": 1.6000000000000003e-05,
168
+ "loss": 0.7018,
169
+ "step": 160
170
+ },
171
+ {
172
+ "epoch": 7.0,
173
+ "eval_loss": 0.45807310938835144,
174
+ "eval_runtime": 0.3083,
175
+ "eval_samples_per_second": 42.169,
176
+ "eval_steps_per_second": 22.706,
177
+ "step": 168
178
+ },
179
+ {
180
+ "epoch": 7.083333333333333,
181
+ "grad_norm": 17.640907287597656,
182
+ "learning_rate": 1.7000000000000003e-05,
183
+ "loss": 0.5636,
184
+ "step": 170
185
+ },
186
+ {
187
+ "epoch": 7.5,
188
+ "grad_norm": 27.690807342529297,
189
+ "learning_rate": 1.8e-05,
190
+ "loss": 0.3966,
191
+ "step": 180
192
+ },
193
+ {
194
+ "epoch": 7.916666666666667,
195
+ "grad_norm": 12.304574012756348,
196
+ "learning_rate": 1.9e-05,
197
+ "loss": 0.2749,
198
+ "step": 190
199
+ },
200
+ {
201
+ "epoch": 8.0,
202
+ "eval_loss": 0.21334221959114075,
203
+ "eval_runtime": 0.403,
204
+ "eval_samples_per_second": 32.257,
205
+ "eval_steps_per_second": 17.369,
206
+ "step": 192
207
+ },
208
+ {
209
+ "epoch": 8.333333333333334,
210
+ "grad_norm": 7.840561389923096,
211
+ "learning_rate": 2e-05,
212
+ "loss": 0.2055,
213
+ "step": 200
214
+ },
215
+ {
216
+ "epoch": 8.75,
217
+ "grad_norm": 1.9353489875793457,
218
+ "learning_rate": 2.1e-05,
219
+ "loss": 0.1099,
220
+ "step": 210
221
+ },
222
+ {
223
+ "epoch": 9.0,
224
+ "eval_loss": 0.10991117358207703,
225
+ "eval_runtime": 0.3071,
226
+ "eval_samples_per_second": 42.327,
227
+ "eval_steps_per_second": 22.791,
228
+ "step": 216
229
+ },
230
+ {
231
+ "epoch": 9.166666666666666,
232
+ "grad_norm": 1.330659031867981,
233
+ "learning_rate": 2.2000000000000003e-05,
234
+ "loss": 0.0665,
235
+ "step": 220
236
+ },
237
+ {
238
+ "epoch": 9.583333333333334,
239
+ "grad_norm": 0.8371493816375732,
240
+ "learning_rate": 2.3000000000000003e-05,
241
+ "loss": 0.0411,
242
+ "step": 230
243
+ },
244
+ {
245
+ "epoch": 10.0,
246
+ "grad_norm": 1.259158968925476,
247
+ "learning_rate": 2.4e-05,
248
+ "loss": 0.0448,
249
+ "step": 240
250
+ },
251
+ {
252
+ "epoch": 10.0,
253
+ "eval_loss": 0.3714790344238281,
254
+ "eval_runtime": 0.3101,
255
+ "eval_samples_per_second": 41.924,
256
+ "eval_steps_per_second": 22.574,
257
+ "step": 240
258
+ },
259
+ {
260
+ "epoch": 10.416666666666666,
261
+ "grad_norm": 1.5030195713043213,
262
+ "learning_rate": 2.5e-05,
263
+ "loss": 0.0756,
264
+ "step": 250
265
+ },
266
+ {
267
+ "epoch": 10.833333333333334,
268
+ "grad_norm": 0.26728466153144836,
269
+ "learning_rate": 2.6000000000000002e-05,
270
+ "loss": 0.0142,
271
+ "step": 260
272
+ },
273
+ {
274
+ "epoch": 11.0,
275
+ "eval_loss": 0.028693975880742073,
276
+ "eval_runtime": 0.3216,
277
+ "eval_samples_per_second": 40.417,
278
+ "eval_steps_per_second": 21.763,
279
+ "step": 264
280
+ },
281
+ {
282
+ "epoch": 11.25,
283
+ "grad_norm": 0.18753524124622345,
284
+ "learning_rate": 2.7000000000000002e-05,
285
+ "loss": 0.0093,
286
+ "step": 270
287
+ },
288
+ {
289
+ "epoch": 11.666666666666666,
290
+ "grad_norm": 0.11348039656877518,
291
+ "learning_rate": 2.8000000000000003e-05,
292
+ "loss": 0.0064,
293
+ "step": 280
294
+ },
295
+ {
296
+ "epoch": 12.0,
297
+ "eval_loss": 0.028606100007891655,
298
+ "eval_runtime": 0.3211,
299
+ "eval_samples_per_second": 40.492,
300
+ "eval_steps_per_second": 21.803,
301
+ "step": 288
302
+ },
303
+ {
304
+ "epoch": 12.083333333333334,
305
+ "grad_norm": 0.0765966922044754,
306
+ "learning_rate": 2.9e-05,
307
+ "loss": 0.0058,
308
+ "step": 290
309
+ },
310
+ {
311
+ "epoch": 12.5,
312
+ "grad_norm": 0.08425896614789963,
313
+ "learning_rate": 3e-05,
314
+ "loss": 0.0042,
315
+ "step": 300
316
+ },
317
+ {
318
+ "epoch": 12.916666666666666,
319
+ "grad_norm": 0.14490404725074768,
320
+ "learning_rate": 3.1e-05,
321
+ "loss": 0.0043,
322
+ "step": 310
323
+ },
324
+ {
325
+ "epoch": 13.0,
326
+ "eval_loss": 0.019509978592395782,
327
+ "eval_runtime": 0.3866,
328
+ "eval_samples_per_second": 33.624,
329
+ "eval_steps_per_second": 18.105,
330
+ "step": 312
331
+ },
332
+ {
333
+ "epoch": 13.333333333333334,
334
+ "grad_norm": 0.05439736321568489,
335
+ "learning_rate": 3.2000000000000005e-05,
336
+ "loss": 0.0034,
337
+ "step": 320
338
+ },
339
+ {
340
+ "epoch": 13.75,
341
+ "grad_norm": 0.04903283342719078,
342
+ "learning_rate": 3.3e-05,
343
+ "loss": 0.0028,
344
+ "step": 330
345
+ },
346
+ {
347
+ "epoch": 14.0,
348
+ "eval_loss": 0.010294664651155472,
349
+ "eval_runtime": 0.3059,
350
+ "eval_samples_per_second": 42.501,
351
+ "eval_steps_per_second": 22.885,
352
+ "step": 336
353
+ },
354
+ {
355
+ "epoch": 14.166666666666666,
356
+ "grad_norm": 0.057338546961545944,
357
+ "learning_rate": 3.4000000000000007e-05,
358
+ "loss": 0.0026,
359
+ "step": 340
360
+ },
361
+ {
362
+ "epoch": 14.583333333333334,
363
+ "grad_norm": 0.053346164524555206,
364
+ "learning_rate": 3.5e-05,
365
+ "loss": 0.0026,
366
+ "step": 350
367
+ },
368
+ {
369
+ "epoch": 15.0,
370
+ "grad_norm": 0.05332862585783005,
371
+ "learning_rate": 3.6e-05,
372
+ "loss": 0.0022,
373
+ "step": 360
374
+ },
375
+ {
376
+ "epoch": 15.0,
377
+ "eval_loss": 0.012851966544985771,
378
+ "eval_runtime": 0.3306,
379
+ "eval_samples_per_second": 39.321,
380
+ "eval_steps_per_second": 21.173,
381
+ "step": 360
382
+ },
383
+ {
384
+ "epoch": 15.416666666666666,
385
+ "grad_norm": 0.05147263780236244,
386
+ "learning_rate": 3.7e-05,
387
+ "loss": 0.0022,
388
+ "step": 370
389
+ },
390
+ {
391
+ "epoch": 15.833333333333334,
392
+ "grad_norm": 0.04216151684522629,
393
+ "learning_rate": 3.8e-05,
394
+ "loss": 0.0018,
395
+ "step": 380
396
+ },
397
+ {
398
+ "epoch": 16.0,
399
+ "eval_loss": 0.00792662426829338,
400
+ "eval_runtime": 0.3955,
401
+ "eval_samples_per_second": 32.87,
402
+ "eval_steps_per_second": 17.699,
403
+ "step": 384
404
+ },
405
+ {
406
+ "epoch": 16.25,
407
+ "grad_norm": 0.03432933986186981,
408
+ "learning_rate": 3.9000000000000006e-05,
409
+ "loss": 0.0018,
410
+ "step": 390
411
+ },
412
+ {
413
+ "epoch": 16.666666666666668,
414
+ "grad_norm": 0.0388726145029068,
415
+ "learning_rate": 4e-05,
416
+ "loss": 0.0017,
417
+ "step": 400
418
+ },
419
+ {
420
+ "epoch": 17.0,
421
+ "eval_loss": 0.002699882024899125,
422
+ "eval_runtime": 0.3106,
423
+ "eval_samples_per_second": 41.848,
424
+ "eval_steps_per_second": 22.534,
425
+ "step": 408
426
+ },
427
+ {
428
+ "epoch": 17.083333333333332,
429
+ "grad_norm": 0.030444540083408356,
430
+ "learning_rate": 4.1e-05,
431
+ "loss": 0.0016,
432
+ "step": 410
433
+ },
434
+ {
435
+ "epoch": 17.5,
436
+ "grad_norm": 0.02462877333164215,
437
+ "learning_rate": 4.2e-05,
438
+ "loss": 0.0016,
439
+ "step": 420
440
+ },
441
+ {
442
+ "epoch": 17.916666666666668,
443
+ "grad_norm": 0.022693680599331856,
444
+ "learning_rate": 4.3e-05,
445
+ "loss": 0.0014,
446
+ "step": 430
447
+ },
448
+ {
449
+ "epoch": 18.0,
450
+ "eval_loss": 0.003563512582331896,
451
+ "eval_runtime": 0.3097,
452
+ "eval_samples_per_second": 41.971,
453
+ "eval_steps_per_second": 22.6,
454
+ "step": 432
455
+ },
456
+ {
457
+ "epoch": 18.333333333333332,
458
+ "grad_norm": 0.02234797179698944,
459
+ "learning_rate": 4.4000000000000006e-05,
460
+ "loss": 0.0015,
461
+ "step": 440
462
+ },
463
+ {
464
+ "epoch": 18.75,
465
+ "grad_norm": 0.03259611874818802,
466
+ "learning_rate": 4.5e-05,
467
+ "loss": 0.0013,
468
+ "step": 450
469
+ },
470
+ {
471
+ "epoch": 19.0,
472
+ "eval_loss": 0.004523274954408407,
473
+ "eval_runtime": 0.4017,
474
+ "eval_samples_per_second": 32.362,
475
+ "eval_steps_per_second": 17.426,
476
+ "step": 456
477
+ },
478
+ {
479
+ "epoch": 19.166666666666668,
480
+ "grad_norm": 0.021357201039791107,
481
+ "learning_rate": 4.600000000000001e-05,
482
+ "loss": 0.0011,
483
+ "step": 460
484
+ },
485
+ {
486
+ "epoch": 19.583333333333332,
487
+ "grad_norm": 0.021904248744249344,
488
+ "learning_rate": 4.7e-05,
489
+ "loss": 0.0012,
490
+ "step": 470
491
+ },
492
+ {
493
+ "epoch": 20.0,
494
+ "grad_norm": 0.023305868729948997,
495
+ "learning_rate": 4.8e-05,
496
+ "loss": 0.0012,
497
+ "step": 480
498
+ },
499
+ {
500
+ "epoch": 20.0,
501
+ "eval_loss": 0.00353155261836946,
502
+ "eval_runtime": 0.3179,
503
+ "eval_samples_per_second": 40.893,
504
+ "eval_steps_per_second": 22.019,
505
+ "step": 480
506
+ },
507
+ {
508
+ "epoch": 20.416666666666668,
509
+ "grad_norm": 0.019376859068870544,
510
+ "learning_rate": 4.9e-05,
511
+ "loss": 0.001,
512
+ "step": 490
513
+ },
514
+ {
515
+ "epoch": 20.833333333333332,
516
+ "grad_norm": 0.013724086806178093,
517
+ "learning_rate": 5e-05,
518
+ "loss": 0.001,
519
+ "step": 500
520
+ },
521
+ {
522
+ "epoch": 21.0,
523
+ "eval_loss": 0.001900297123938799,
524
+ "eval_runtime": 0.316,
525
+ "eval_samples_per_second": 41.136,
526
+ "eval_steps_per_second": 22.15,
527
+ "step": 504
528
+ },
529
+ {
530
+ "epoch": 21.25,
531
+ "grad_norm": 0.014477409422397614,
532
+ "learning_rate": 4.5e-05,
533
+ "loss": 0.001,
534
+ "step": 510
535
+ },
536
+ {
537
+ "epoch": 21.666666666666668,
538
+ "grad_norm": 0.012809093110263348,
539
+ "learning_rate": 4e-05,
540
+ "loss": 0.0009,
541
+ "step": 520
542
+ },
543
+ {
544
+ "epoch": 22.0,
545
+ "eval_loss": 0.001852882793173194,
546
+ "eval_runtime": 0.3187,
547
+ "eval_samples_per_second": 40.794,
548
+ "eval_steps_per_second": 21.966,
549
+ "step": 528
550
+ },
551
+ {
552
+ "epoch": 22.083333333333332,
553
+ "grad_norm": 0.01569068804383278,
554
+ "learning_rate": 3.5e-05,
555
+ "loss": 0.0009,
556
+ "step": 530
557
+ },
558
+ {
559
+ "epoch": 22.5,
560
+ "grad_norm": 0.016419854015111923,
561
+ "learning_rate": 3e-05,
562
+ "loss": 0.0009,
563
+ "step": 540
564
+ },
565
+ {
566
+ "epoch": 22.916666666666668,
567
+ "grad_norm": 0.01509429793804884,
568
+ "learning_rate": 2.5e-05,
569
+ "loss": 0.0009,
570
+ "step": 550
571
+ },
572
+ {
573
+ "epoch": 23.0,
574
+ "eval_loss": 0.0026340754702687263,
575
+ "eval_runtime": 0.3073,
576
+ "eval_samples_per_second": 42.308,
577
+ "eval_steps_per_second": 22.781,
578
+ "step": 552
579
+ },
580
+ {
581
+ "epoch": 23.333333333333332,
582
+ "grad_norm": 0.016193103045225143,
583
+ "learning_rate": 2e-05,
584
+ "loss": 0.0009,
585
+ "step": 560
586
+ },
587
+ {
588
+ "epoch": 23.75,
589
+ "grad_norm": 0.019486326724290848,
590
+ "learning_rate": 1.5e-05,
591
+ "loss": 0.0008,
592
+ "step": 570
593
+ },
594
+ {
595
+ "epoch": 24.0,
596
+ "eval_loss": 0.002526934025809169,
597
+ "eval_runtime": 0.3324,
598
+ "eval_samples_per_second": 39.113,
599
+ "eval_steps_per_second": 21.061,
600
+ "step": 576
601
+ },
602
+ {
603
+ "epoch": 24.166666666666668,
604
+ "grad_norm": 0.013866975903511047,
605
+ "learning_rate": 1e-05,
606
+ "loss": 0.0008,
607
+ "step": 580
608
+ },
609
+ {
610
+ "epoch": 24.583333333333332,
611
+ "grad_norm": 0.01797279715538025,
612
+ "learning_rate": 5e-06,
613
+ "loss": 0.0008,
614
+ "step": 590
615
+ },
616
+ {
617
+ "epoch": 25.0,
618
+ "grad_norm": 0.013154336251318455,
619
+ "learning_rate": 0.0,
620
+ "loss": 0.0008,
621
+ "step": 600
622
+ }
623
+ ],
624
+ "logging_steps": 10,
625
+ "max_steps": 600,
626
+ "num_input_tokens_seen": 0,
627
+ "num_train_epochs": 25,
628
+ "save_steps": 500,
629
+ "stateful_callbacks": {
630
+ "TrainerControl": {
631
+ "args": {
632
+ "should_epoch_stop": false,
633
+ "should_evaluate": false,
634
+ "should_log": false,
635
+ "should_save": true,
636
+ "should_training_stop": true
637
+ },
638
+ "attributes": {}
639
+ }
640
+ },
641
+ "total_flos": 12950462347200.0,
642
+ "train_batch_size": 2,
643
+ "trial_name": null,
644
+ "trial_params": null
645
+ }
results_data-timeframe/checkpoint-600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5b127a0fcad90022b910ab6e74e044a789717da0938e142c39fde1fe9ce365
3
+ size 5304