pierreguillou commited on
Commit
27433f3
1 Parent(s): 541b089

Training in progress, step 800

Browse files
Files changed (36) hide show
  1. checkpoint-200/trainer_state.json +0 -40
  2. {checkpoint-200 → checkpoint-600}/config.json +0 -0
  3. {checkpoint-300 → checkpoint-600}/optimizer.pt +1 -1
  4. {checkpoint-300 → checkpoint-600}/pytorch_model.bin +1 -1
  5. {checkpoint-400 → checkpoint-600}/rng_state.pth +1 -1
  6. {checkpoint-400 → checkpoint-600}/scaler.pt +1 -1
  7. {checkpoint-200 → checkpoint-600}/scheduler.pt +1 -1
  8. {checkpoint-200 → checkpoint-600}/special_tokens_map.json +0 -0
  9. {checkpoint-200 → checkpoint-600}/tokenizer.json +0 -0
  10. {checkpoint-200 → checkpoint-600}/tokenizer_config.json +0 -0
  11. {checkpoint-400 → checkpoint-600}/trainer_state.json +35 -5
  12. {checkpoint-200 → checkpoint-600}/training_args.bin +0 -0
  13. {checkpoint-300 → checkpoint-700}/config.json +0 -0
  14. {checkpoint-400 → checkpoint-700}/optimizer.pt +1 -1
  15. {checkpoint-200 → checkpoint-700}/pytorch_model.bin +1 -1
  16. {checkpoint-300 → checkpoint-700}/rng_state.pth +1 -1
  17. {checkpoint-300 → checkpoint-700}/scaler.pt +1 -1
  18. {checkpoint-400 → checkpoint-700}/scheduler.pt +1 -1
  19. {checkpoint-300 → checkpoint-700}/special_tokens_map.json +0 -0
  20. {checkpoint-300 → checkpoint-700}/tokenizer.json +0 -0
  21. {checkpoint-300 → checkpoint-700}/tokenizer_config.json +0 -0
  22. {checkpoint-300 → checkpoint-700}/trainer_state.json +59 -5
  23. {checkpoint-300 → checkpoint-700}/training_args.bin +0 -0
  24. {checkpoint-400 → checkpoint-800}/config.json +0 -0
  25. {checkpoint-200 → checkpoint-800}/optimizer.pt +2 -2
  26. {checkpoint-400 → checkpoint-800}/pytorch_model.bin +1 -1
  27. {checkpoint-200 → checkpoint-800}/rng_state.pth +1 -1
  28. {checkpoint-200 → checkpoint-800}/scaler.pt +1 -1
  29. {checkpoint-300 → checkpoint-800}/scheduler.pt +1 -1
  30. {checkpoint-400 → checkpoint-800}/special_tokens_map.json +0 -0
  31. {checkpoint-400 → checkpoint-800}/tokenizer.json +0 -0
  32. {checkpoint-400 → checkpoint-800}/tokenizer_config.json +0 -0
  33. checkpoint-800/trainer_state.json +118 -0
  34. {checkpoint-400 → checkpoint-800}/training_args.bin +0 -0
  35. pytorch_model.bin +1 -1
  36. runs/Feb15_07-53-26_e220f522c880/events.out.tfevents.1676447621.e220f522c880.495.0 +2 -2
checkpoint-200/trainer_state.json DELETED
@@ -1,40 +0,0 @@
1
- {
2
- "best_metric": 0.7551279108067913,
3
- "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-200",
4
- "epoch": 0.10660980810234541,
5
- "global_step": 200,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.05,
12
- "eval_accuracy": 0.6585185702735884,
13
- "eval_f1": 0.6585185702735884,
14
- "eval_loss": 0.9875321388244629,
15
- "eval_precision": 0.6585185702735884,
16
- "eval_recall": 0.6585185702735884,
17
- "eval_runtime": 47.6616,
18
- "eval_samples_per_second": 33.717,
19
- "eval_steps_per_second": 2.119,
20
- "step": 100
21
- },
22
- {
23
- "epoch": 0.11,
24
- "eval_accuracy": 0.7551279108067913,
25
- "eval_f1": 0.7551279108067913,
26
- "eval_loss": 0.7886354327201843,
27
- "eval_precision": 0.7551279108067913,
28
- "eval_recall": 0.7551279108067913,
29
- "eval_runtime": 48.4163,
30
- "eval_samples_per_second": 33.191,
31
- "eval_steps_per_second": 2.086,
32
- "step": 200
33
- }
34
- ],
35
- "max_steps": 1876,
36
- "num_train_epochs": 1,
37
- "total_flos": 445075582156800.0,
38
- "trial_name": null,
39
- "trial_params": null
40
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
{checkpoint-200 → checkpoint-600}/config.json RENAMED
File without changes
{checkpoint-300 → checkpoint-600}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b57c47892e2c979ead028ed133a8e6310573791bcb0ce4b62a32dc49850683e
3
  size 2265828101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bf81325bd0e7b7920d7e17948dc8fa50b030ce4b352d0169780efcc4860dd37
3
  size 2265828101
{checkpoint-300 → checkpoint-600}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:880a92376813495eb9c614b219a5f3739441875a9dd423f5a5a4c0f194747462
3
  size 1134425553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d412db68cafdb004b544f6d25d7643b5e329556603ad90d82fa1115c4bc0a8c
3
  size 1134425553
{checkpoint-400 → checkpoint-600}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6084e517c898c5f3679c65138c00f6e8c42eb251e79e5c86866ef9d34d8a6959
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc2b7715adb41014862ffc9f81706bab8e34e2a3b27ffab219e62d9e05b4b734
3
  size 14575
{checkpoint-400 → checkpoint-600}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8894add6cf5ff4d4049868d7614fbae0eb98e7ffb617edb8d94b4cd7e15ebd0d
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a320f2c97d42c92479a0b3cc6095c24af378acd4e6f3487e2e940a6cc07c287a
3
  size 557
{checkpoint-200 → checkpoint-600}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f06cf77a584fcbc5eec1e5ddee45214561dae318ae26edcbcc04f742aac3e73b
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0392158b8d45683d14b4e243f1c79ba2f496b8394e6de119418e49df613478c1
3
  size 627
{checkpoint-200 → checkpoint-600}/special_tokens_map.json RENAMED
File without changes
{checkpoint-200 → checkpoint-600}/tokenizer.json RENAMED
File without changes
{checkpoint-200 → checkpoint-600}/tokenizer_config.json RENAMED
File without changes
{checkpoint-400 → checkpoint-600}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.8395799854272509,
3
- "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-400",
4
- "epoch": 0.21321961620469082,
5
- "global_step": 400,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -54,11 +54,41 @@
54
  "eval_samples_per_second": 35.408,
55
  "eval_steps_per_second": 2.225,
56
  "step": 400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
  }
58
  ],
59
  "max_steps": 1876,
60
  "num_train_epochs": 1,
61
- "total_flos": 890151164313600.0,
62
  "trial_name": null,
63
  "trial_params": null
64
  }
 
1
  {
2
+ "best_metric": 0.885723696687195,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-600",
4
+ "epoch": 0.31982942430703626,
5
+ "global_step": 600,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
54
  "eval_samples_per_second": 35.408,
55
  "eval_steps_per_second": 2.225,
56
  "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.27,
60
+ "learning_rate": 1.4712153518123668e-05,
61
+ "loss": 0.7446,
62
+ "step": 500
63
+ },
64
+ {
65
+ "epoch": 0.27,
66
+ "eval_accuracy": 0.870342459600547,
67
+ "eval_f1": 0.8703424596005469,
68
+ "eval_loss": 0.39928165078163147,
69
+ "eval_precision": 0.870342459600547,
70
+ "eval_recall": 0.870342459600547,
71
+ "eval_runtime": 46.3389,
72
+ "eval_samples_per_second": 34.679,
73
+ "eval_steps_per_second": 2.18,
74
+ "step": 500
75
+ },
76
+ {
77
+ "epoch": 0.32,
78
+ "eval_accuracy": 0.885723696687195,
79
+ "eval_f1": 0.885723696687195,
80
+ "eval_loss": 0.36305829882621765,
81
+ "eval_precision": 0.885723696687195,
82
+ "eval_recall": 0.885723696687195,
83
+ "eval_runtime": 46.9181,
84
+ "eval_samples_per_second": 34.251,
85
+ "eval_steps_per_second": 2.153,
86
+ "step": 600
87
  }
88
  ],
89
  "max_steps": 1876,
90
  "num_train_epochs": 1,
91
+ "total_flos": 1335226746470400.0,
92
  "trial_name": null,
93
  "trial_params": null
94
  }
{checkpoint-200 → checkpoint-600}/training_args.bin RENAMED
File without changes
{checkpoint-300 → checkpoint-700}/config.json RENAMED
File without changes
{checkpoint-400 → checkpoint-700}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bea0ae9c91632ba73324243f693237eedfde07c60552f721ae85502620f6663
3
  size 2265828101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3fe13c1ea3aa84e754ff7abe68da7eec60a7e1dc2e5dfc4a93ad1d3f636fa3
3
  size 2265828101
{checkpoint-200 → checkpoint-700}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d22e589804912ea5de135343295f3d1d679cdb01de0862367236991e3a9e8f5b
3
  size 1134425553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe775f2f5e3266c5d9bceb93d7b7d60750dc69b67a1bed6e77aa7d295da49d0
3
  size 1134425553
{checkpoint-300 → checkpoint-700}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2edaa8158eaf8be7cc7f6c6471898dae049ef076acac0f3f1cc542415dc6dfca
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a57174e6d28245887299f8c18770addda0c495bdadadc4f17326f19f3cdd79
3
  size 14575
{checkpoint-300 → checkpoint-700}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35d89833ad47769c3fd687316799e7acd03e729c4180e72e9a36d6ac51bf9656
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55749a54a2c0aac733a45a67ee5b21dbfaa7cb45a667adecbc1609b113af0b09
3
  size 557
{checkpoint-400 → checkpoint-700}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:510282233ecb669cc6a91c195a0954011c19ca6b777845a850e4192cef7447aa
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec7fcec2c61a14f594e0c95f40c28d94feca9810fd5de97d1910aa5fc27619dd
3
  size 627
{checkpoint-300 → checkpoint-700}/special_tokens_map.json RENAMED
File without changes
{checkpoint-300 → checkpoint-700}/tokenizer.json RENAMED
File without changes
{checkpoint-300 → checkpoint-700}/tokenizer_config.json RENAMED
File without changes
{checkpoint-300 → checkpoint-700}/trainer_state.json RENAMED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.8248275724395382,
3
- "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-300",
4
- "epoch": 0.15991471215351813,
5
- "global_step": 300,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -42,11 +42,65 @@
42
  "eval_samples_per_second": 33.804,
43
  "eval_steps_per_second": 2.125,
44
  "step": 300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  }
46
  ],
47
  "max_steps": 1876,
48
  "num_train_epochs": 1,
49
- "total_flos": 667613373235200.0,
50
  "trial_name": null,
51
  "trial_params": null
52
  }
 
1
  {
2
+ "best_metric": 0.885723696687195,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-600",
4
+ "epoch": 0.373134328358209,
5
+ "global_step": 700,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
42
  "eval_samples_per_second": 33.804,
43
  "eval_steps_per_second": 2.125,
44
  "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.21,
48
+ "eval_accuracy": 0.839579985427251,
49
+ "eval_f1": 0.8395799854272509,
50
+ "eval_loss": 0.479428768157959,
51
+ "eval_precision": 0.839579985427251,
52
+ "eval_recall": 0.839579985427251,
53
+ "eval_runtime": 45.3857,
54
+ "eval_samples_per_second": 35.408,
55
+ "eval_steps_per_second": 2.225,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.27,
60
+ "learning_rate": 1.4712153518123668e-05,
61
+ "loss": 0.7446,
62
+ "step": 500
63
+ },
64
+ {
65
+ "epoch": 0.27,
66
+ "eval_accuracy": 0.870342459600547,
67
+ "eval_f1": 0.8703424596005469,
68
+ "eval_loss": 0.39928165078163147,
69
+ "eval_precision": 0.870342459600547,
70
+ "eval_recall": 0.870342459600547,
71
+ "eval_runtime": 46.3389,
72
+ "eval_samples_per_second": 34.679,
73
+ "eval_steps_per_second": 2.18,
74
+ "step": 500
75
+ },
76
+ {
77
+ "epoch": 0.32,
78
+ "eval_accuracy": 0.885723696687195,
79
+ "eval_f1": 0.885723696687195,
80
+ "eval_loss": 0.36305829882621765,
81
+ "eval_precision": 0.885723696687195,
82
+ "eval_recall": 0.885723696687195,
83
+ "eval_runtime": 46.9181,
84
+ "eval_samples_per_second": 34.251,
85
+ "eval_steps_per_second": 2.153,
86
+ "step": 600
87
+ },
88
+ {
89
+ "epoch": 0.37,
90
+ "eval_accuracy": 0.8629662531066905,
91
+ "eval_f1": 0.8629662531066905,
92
+ "eval_loss": 0.4096183180809021,
93
+ "eval_precision": 0.8629662531066905,
94
+ "eval_recall": 0.8629662531066905,
95
+ "eval_runtime": 45.8414,
96
+ "eval_samples_per_second": 35.056,
97
+ "eval_steps_per_second": 2.203,
98
+ "step": 700
99
  }
100
  ],
101
  "max_steps": 1876,
102
  "num_train_epochs": 1,
103
+ "total_flos": 1557764537548800.0,
104
  "trial_name": null,
105
  "trial_params": null
106
  }
{checkpoint-300 → checkpoint-700}/training_args.bin RENAMED
File without changes
{checkpoint-400 → checkpoint-800}/config.json RENAMED
File without changes
{checkpoint-200 → checkpoint-800}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7cdf79d3146238ae659f3724cb61a9f3eef1d94bdc25b29615f00c8f24590c2
3
- size 2265827717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5927a29acc1b827e5e81631185eaee6608e45cc4c08f5547e015207b8c3e1f36
3
+ size 2265828101
{checkpoint-400 → checkpoint-800}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4727566eb4ffd9fac82a769c6b877c66e5ed779dfa933929c682a8e7337e5fa1
3
  size 1134425553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8126932772d64c007aa46752a8678869bff8e31fb1d734f060c2aef68f5b5c3
3
  size 1134425553
{checkpoint-200 → checkpoint-800}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19a5fbfb1d8b3fb183af663f8903b6b2d98760688828d8a5abb54552e6de1d6f
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64c8402a2a8dcf25bb022948010e12c766380abe6897e4ffad7784a45553b860
3
  size 14575
{checkpoint-200 → checkpoint-800}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc28ad4ba690d88b4a64a84b0eb679f0ae2052dd18f66a37a2ec7425463d2024
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d15232b452895e36dc91e0446f6e8ef9af073f8677f732bb005840a10ca7266
3
  size 557
{checkpoint-300 → checkpoint-800}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40904ad5451576d85b4d1b180d481a37f60db63c24eb116a2d70a90d013a25fd
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965edcc2ade2296ca06465ca794bdd6e45524f6fe975b06d7cc6014955adf226
3
  size 627
{checkpoint-400 → checkpoint-800}/special_tokens_map.json RENAMED
File without changes
{checkpoint-400 → checkpoint-800}/tokenizer.json RENAMED
File without changes
{checkpoint-400 → checkpoint-800}/tokenizer_config.json RENAMED
File without changes
checkpoint-800/trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.885723696687195,
3
+ "best_model_checkpoint": "DocLayNet/lilt-xlm-roberta-base-finetuned-DocLayNet-base_paragraphs_ml512-v5/checkpoint-600",
4
+ "epoch": 0.42643923240938164,
5
+ "global_step": 800,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "eval_accuracy": 0.6585185702735884,
13
+ "eval_f1": 0.6585185702735884,
14
+ "eval_loss": 0.9875321388244629,
15
+ "eval_precision": 0.6585185702735884,
16
+ "eval_recall": 0.6585185702735884,
17
+ "eval_runtime": 47.6616,
18
+ "eval_samples_per_second": 33.717,
19
+ "eval_steps_per_second": 2.119,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 0.11,
24
+ "eval_accuracy": 0.7551279108067913,
25
+ "eval_f1": 0.7551279108067913,
26
+ "eval_loss": 0.7886354327201843,
27
+ "eval_precision": 0.7551279108067913,
28
+ "eval_recall": 0.7551279108067913,
29
+ "eval_runtime": 48.4163,
30
+ "eval_samples_per_second": 33.191,
31
+ "eval_steps_per_second": 2.086,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.16,
36
+ "eval_accuracy": 0.8248275724395381,
37
+ "eval_f1": 0.8248275724395382,
38
+ "eval_loss": 0.5894176363945007,
39
+ "eval_precision": 0.8248275724395381,
40
+ "eval_recall": 0.8248275724395381,
41
+ "eval_runtime": 47.5388,
42
+ "eval_samples_per_second": 33.804,
43
+ "eval_steps_per_second": 2.125,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.21,
48
+ "eval_accuracy": 0.839579985427251,
49
+ "eval_f1": 0.8395799854272509,
50
+ "eval_loss": 0.479428768157959,
51
+ "eval_precision": 0.839579985427251,
52
+ "eval_recall": 0.839579985427251,
53
+ "eval_runtime": 45.3857,
54
+ "eval_samples_per_second": 35.408,
55
+ "eval_steps_per_second": 2.225,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.27,
60
+ "learning_rate": 1.4712153518123668e-05,
61
+ "loss": 0.7446,
62
+ "step": 500
63
+ },
64
+ {
65
+ "epoch": 0.27,
66
+ "eval_accuracy": 0.870342459600547,
67
+ "eval_f1": 0.8703424596005469,
68
+ "eval_loss": 0.39928165078163147,
69
+ "eval_precision": 0.870342459600547,
70
+ "eval_recall": 0.870342459600547,
71
+ "eval_runtime": 46.3389,
72
+ "eval_samples_per_second": 34.679,
73
+ "eval_steps_per_second": 2.18,
74
+ "step": 500
75
+ },
76
+ {
77
+ "epoch": 0.32,
78
+ "eval_accuracy": 0.885723696687195,
79
+ "eval_f1": 0.885723696687195,
80
+ "eval_loss": 0.36305829882621765,
81
+ "eval_precision": 0.885723696687195,
82
+ "eval_recall": 0.885723696687195,
83
+ "eval_runtime": 46.9181,
84
+ "eval_samples_per_second": 34.251,
85
+ "eval_steps_per_second": 2.153,
86
+ "step": 600
87
+ },
88
+ {
89
+ "epoch": 0.37,
90
+ "eval_accuracy": 0.8629662531066905,
91
+ "eval_f1": 0.8629662531066905,
92
+ "eval_loss": 0.4096183180809021,
93
+ "eval_precision": 0.8629662531066905,
94
+ "eval_recall": 0.8629662531066905,
95
+ "eval_runtime": 45.8414,
96
+ "eval_samples_per_second": 35.056,
97
+ "eval_steps_per_second": 2.203,
98
+ "step": 700
99
+ },
100
+ {
101
+ "epoch": 0.43,
102
+ "eval_accuracy": 0.8528252168445007,
103
+ "eval_f1": 0.8528252168445007,
104
+ "eval_loss": 0.44917240738868713,
105
+ "eval_precision": 0.8528252168445007,
106
+ "eval_recall": 0.8528252168445007,
107
+ "eval_runtime": 45.6102,
108
+ "eval_samples_per_second": 35.233,
109
+ "eval_steps_per_second": 2.214,
110
+ "step": 800
111
+ }
112
+ ],
113
+ "max_steps": 1876,
114
+ "num_train_epochs": 1,
115
+ "total_flos": 1780302328627200.0,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }
{checkpoint-400 → checkpoint-800}/training_args.bin RENAMED
File without changes
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4727566eb4ffd9fac82a769c6b877c66e5ed779dfa933929c682a8e7337e5fa1
3
  size 1134425553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8126932772d64c007aa46752a8678869bff8e31fb1d734f060c2aef68f5b5c3
3
  size 1134425553
runs/Feb15_07-53-26_e220f522c880/events.out.tfevents.1676447621.e220f522c880.495.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c9463d47ba3115fd44ba28de90fc0000cfcf2825b962b5b23499351a1fc9e21
3
- size 6552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97dbcb650d21eb583ff331584d595df99b7abe792fa93031ec793779393434c8
3
+ size 8597