Commit
•
5f87f70
1
Parent(s):
cbf661b
End of training
Browse files- README.md +13 -12
- all_results.json +23 -16
- eval_results.json +9 -8
- predict_results.json +8 -8
- predictions.txt +0 -0
- tb/events.out.tfevents.1715786919.61af03e56d14.5022.1 +3 -0
- train.log +48 -0
- train_results.json +9 -0
- trainer_state.json +388 -0
README.md
CHANGED
@@ -2,9 +2,10 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
-
- drugtemist-ner
|
8 |
metrics:
|
9 |
- precision
|
10 |
- recall
|
@@ -17,24 +18,24 @@ model-index:
|
|
17 |
name: Token Classification
|
18 |
type: token-classification
|
19 |
dataset:
|
20 |
-
name: drugtemist-ner
|
21 |
-
type: drugtemist-ner
|
22 |
config: DrugTEMIST NER
|
23 |
split: validation
|
24 |
args: DrugTEMIST NER
|
25 |
metrics:
|
26 |
- name: Precision
|
27 |
type: precision
|
28 |
-
value: 0.
|
29 |
- name: Recall
|
30 |
type: recall
|
31 |
-
value: 0.
|
32 |
- name: F1
|
33 |
type: f1
|
34 |
-
value: 0.
|
35 |
- name: Accuracy
|
36 |
type: accuracy
|
37 |
-
value: 0.
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -42,12 +43,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
42 |
|
43 |
# output
|
44 |
|
45 |
-
This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the drugtemist-ner dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
-
- Loss: 0.
|
48 |
-
- Precision: 0.
|
49 |
-
- Recall: 0.
|
50 |
-
- F1: 0.
|
51 |
- Accuracy: 0.9990
|
52 |
|
53 |
## Model description
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: PlanTL-GOB-ES/bsc-bio-ehr-es
|
4 |
tags:
|
5 |
+
- token-classification
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
+
- Rodrigo1771/drugtemist-ner
|
9 |
metrics:
|
10 |
- precision
|
11 |
- recall
|
|
|
18 |
name: Token Classification
|
19 |
type: token-classification
|
20 |
dataset:
|
21 |
+
name: Rodrigo1771/drugtemist-ner
|
22 |
+
type: Rodrigo1771/drugtemist-ner
|
23 |
config: DrugTEMIST NER
|
24 |
split: validation
|
25 |
args: DrugTEMIST NER
|
26 |
metrics:
|
27 |
- name: Precision
|
28 |
type: precision
|
29 |
+
value: 0.9430379746835443
|
30 |
- name: Recall
|
31 |
type: recall
|
32 |
+
value: 0.9586397058823529
|
33 |
- name: F1
|
34 |
type: f1
|
35 |
+
value: 0.95077484047402
|
36 |
- name: Accuracy
|
37 |
type: accuracy
|
38 |
+
value: 0.9990319324961724
|
39 |
---
|
40 |
|
41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
43 |
|
44 |
# output
|
45 |
|
46 |
+
This model is a fine-tuned version of [PlanTL-GOB-ES/bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es) on the Rodrigo1771/drugtemist-ner dataset.
|
47 |
It achieves the following results on the evaluation set:
|
48 |
+
- Loss: 0.0058
|
49 |
+
- Precision: 0.9430
|
50 |
+
- Recall: 0.9586
|
51 |
+
- F1: 0.9508
|
52 |
- Accuracy: 0.9990
|
53 |
|
54 |
## Model description
|
all_results.json
CHANGED
@@ -1,19 +1,26 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
|
|
8 |
"eval_samples": 6807,
|
9 |
-
"eval_samples_per_second":
|
10 |
-
"eval_steps_per_second":
|
11 |
-
"predict_accuracy": 0.
|
12 |
-
"predict_f1": 0.
|
13 |
-
"predict_loss":
|
14 |
-
"predict_precision": 0.
|
15 |
-
"predict_recall": 0.
|
16 |
-
"predict_runtime": 15.
|
17 |
-
"predict_samples_per_second":
|
18 |
-
"predict_steps_per_second":
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 9.997061416397296,
|
3 |
+
"eval_accuracy": 0.9990319324961724,
|
4 |
+
"eval_f1": 0.95077484047402,
|
5 |
+
"eval_loss": 0.0058256350457668304,
|
6 |
+
"eval_precision": 0.9430379746835443,
|
7 |
+
"eval_recall": 0.9586397058823529,
|
8 |
+
"eval_runtime": 15.6142,
|
9 |
"eval_samples": 6807,
|
10 |
+
"eval_samples_per_second": 435.949,
|
11 |
+
"eval_steps_per_second": 54.502,
|
12 |
+
"predict_accuracy": 0.9990319324961724,
|
13 |
+
"predict_f1": 0.95077484047402,
|
14 |
+
"predict_loss": 0.0058256350457668304,
|
15 |
+
"predict_precision": 0.9430379746835443,
|
16 |
+
"predict_recall": 0.9586397058823529,
|
17 |
+
"predict_runtime": 15.6972,
|
18 |
+
"predict_samples_per_second": 433.645,
|
19 |
+
"predict_steps_per_second": 54.214,
|
20 |
+
"total_flos": 6700358578825584.0,
|
21 |
+
"train_loss": 0.0023016003105682196,
|
22 |
+
"train_runtime": 3387.0101,
|
23 |
+
"train_samples": 27224,
|
24 |
+
"train_samples_per_second": 80.378,
|
25 |
+
"train_steps_per_second": 5.022
|
26 |
}
|
eval_results.json
CHANGED
@@ -1,11 +1,12 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
|
|
8 |
"eval_samples": 6807,
|
9 |
-
"eval_samples_per_second":
|
10 |
-
"eval_steps_per_second":
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 9.997061416397296,
|
3 |
+
"eval_accuracy": 0.9990319324961724,
|
4 |
+
"eval_f1": 0.95077484047402,
|
5 |
+
"eval_loss": 0.0058256350457668304,
|
6 |
+
"eval_precision": 0.9430379746835443,
|
7 |
+
"eval_recall": 0.9586397058823529,
|
8 |
+
"eval_runtime": 15.6142,
|
9 |
"eval_samples": 6807,
|
10 |
+
"eval_samples_per_second": 435.949,
|
11 |
+
"eval_steps_per_second": 54.502
|
12 |
}
|
predict_results.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
-
"predict_accuracy": 0.
|
3 |
-
"predict_f1": 0.
|
4 |
-
"predict_loss":
|
5 |
-
"predict_precision": 0.
|
6 |
-
"predict_recall": 0.
|
7 |
-
"predict_runtime": 15.
|
8 |
-
"predict_samples_per_second":
|
9 |
-
"predict_steps_per_second":
|
10 |
}
|
|
|
1 |
{
|
2 |
+
"predict_accuracy": 0.9990319324961724,
|
3 |
+
"predict_f1": 0.95077484047402,
|
4 |
+
"predict_loss": 0.0058256350457668304,
|
5 |
+
"predict_precision": 0.9430379746835443,
|
6 |
+
"predict_recall": 0.9586397058823529,
|
7 |
+
"predict_runtime": 15.6972,
|
8 |
+
"predict_samples_per_second": 433.645,
|
9 |
+
"predict_steps_per_second": 54.214
|
10 |
}
|
predictions.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tb/events.out.tfevents.1715786919.61af03e56d14.5022.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a27f137b8259d61cfd2526684bc8f5a7589382dd45db907e2e5fc45dc56b2e14
|
3 |
+
size 569
|
train.log
CHANGED
@@ -1590,3 +1590,51 @@ Training completed. Do not forget to share your model on huggingface.co/models =
|
|
1590 |
[INFO|modeling_utils.py:2590] 2024-05-15 15:28:19,154 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
|
1591 |
[INFO|tokenization_utils_base.py:2488] 2024-05-15 15:28:19,155 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
|
1592 |
[INFO|tokenization_utils_base.py:2497] 2024-05-15 15:28:19,156 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1593 |
0%| | 0/851 [00:00<?, ?it/s]
|
1594 |
1%| | 10/851 [00:00<00:09, 90.51it/s]
|
1595 |
2%|▏ | 20/851 [00:00<00:10, 77.83it/s]
|
1596 |
3%|▎ | 28/851 [00:00<00:11, 74.40it/s]
|
1597 |
4%|▍ | 36/851 [00:00<00:11, 73.24it/s]
|
1598 |
5%|▌ | 44/851 [00:00<00:10, 73.71it/s]
|
1599 |
6%|▌ | 52/851 [00:00<00:10, 74.57it/s]
|
1600 |
7%|▋ | 60/851 [00:00<00:10, 75.32it/s]
|
1601 |
8%|▊ | 68/851 [00:00<00:11, 69.52it/s]
|
1602 |
9%|▉ | 76/851 [00:01<00:11, 69.83it/s]
|
1603 |
10%|▉ | 84/851 [00:01<00:10, 70.07it/s]
|
1604 |
11%|█ | 92/851 [00:01<00:10, 69.97it/s]
|
1605 |
12%|█▏ | 100/851 [00:01<00:10, 69.61it/s]
|
1606 |
13%|█▎ | 107/851 [00:01<00:10, 68.65it/s]
|
1607 |
14%|█▎ | 115/851 [00:01<00:10, 68.72it/s]
|
1608 |
15%|█▍ | 124/851 [00:01<00:10, 72.49it/s]
|
1609 |
16%|█▌ | 132/851 [00:01<00:10, 65.39it/s]
|
1610 |
16%|█▋ | 139/851 [00:01<00:10, 65.90it/s]
|
1611 |
17%|█▋ | 147/851 [00:02<00:10, 67.50it/s]
|
1612 |
18%|█▊ | 154/851 [00:02<00:10, 67.04it/s]
|
1613 |
19%|█▉ | 161/851 [00:02<00:10, 66.91it/s]
|
1614 |
20%|█▉ | 169/851 [00:02<00:10, 67.78it/s]
|
1615 |
21%|██ | 177/851 [00:02<00:09, 69.96it/s]
|
1616 |
22%|██▏ | 185/851 [00:02<00:09, 71.55it/s]
|
1617 |
23%|██▎ | 193/851 [00:02<00:09, 72.55it/s]
|
1618 |
24%|██▎ | 201/851 [00:02<00:08, 74.28it/s]
|
1619 |
25%|██▍ | 209/851 [00:02<00:09, 70.56it/s]
|
1620 |
25%|██▌ | 217/851 [00:03<00:09, 68.99it/s]
|
1621 |
26%|██▋ | 224/851 [00:03<00:09, 69.14it/s]
|
1622 |
27%|██▋ | 232/851 [00:03<00:08, 71.37it/s]
|
1623 |
28%|██▊ | 240/851 [00:03<00:08, 68.79it/s]
|
1624 |
29%|██▉ | 247/851 [00:03<00:09, 66.73it/s]
|
1625 |
30%|██▉ | 255/851 [00:03<00:08, 69.91it/s]
|
1626 |
31%|███ | 263/851 [00:03<00:08, 72.69it/s]
|
1627 |
32%|███▏ | 271/851 [00:03<00:08, 71.09it/s]
|
1628 |
33%|███▎ | 279/851 [00:03<00:07, 73.46it/s]
|
1629 |
34%|███▎ | 287/851 [00:04<00:07, 72.07it/s]
|
1630 |
35%|███▍ | 295/851 [00:04<00:07, 72.11it/s]
|
1631 |
36%|███▌ | 303/851 [00:04<00:07, 73.81it/s]
|
1632 |
37%|███▋ | 311/851 [00:04<00:07, 68.28it/s]
|
1633 |
38%|███▊ | 320/851 [00:04<00:07, 71.75it/s]
|
1634 |
39%|███▊ | 328/851 [00:04<00:07, 72.02it/s]
|
1635 |
39%|███▉ | 336/851 [00:04<00:07, 71.36it/s]
|
1636 |
40%|████ | 344/851 [00:04<00:06, 73.18it/s]
|
1637 |
41%|████▏ | 352/851 [00:04<00:06, 72.55it/s]
|
1638 |
42%|████▏ | 360/851 [00:05<00:07, 66.67it/s]
|
1639 |
43%|████▎ | 368/851 [00:05<00:07, 68.29it/s]
|
1640 |
44%|████▍ | 375/851 [00:05<00:06, 68.41it/s]
|
1641 |
45%|████▍ | 382/851 [00:05<00:07, 66.01it/s]
|
1642 |
46%|████▌ | 390/851 [00:05<00:06, 69.04it/s]
|
1643 |
47%|████▋ | 398/851 [00:05<00:06, 70.03it/s]
|
1644 |
48%|████▊ | 406/851 [00:05<00:06, 65.84it/s]
|
1645 |
49%|████▊ | 414/851 [00:05<00:06, 66.93it/s]
|
1646 |
50%|████▉ | 422/851 [00:06<00:06, 69.24it/s]
|
1647 |
50%|█████ | 429/851 [00:06<00:06, 67.99it/s]
|
1648 |
51%|█████▏ | 437/851 [00:06<00:05, 70.32it/s]
|
1649 |
52%|█████▏ | 445/851 [00:06<00:05, 71.78it/s]
|
1650 |
53%|█████▎ | 453/851 [00:06<00:05, 71.61it/s]
|
1651 |
54%|█████▍ | 461/851 [00:06<00:05, 69.59it/s]
|
1652 |
55%|█████▍ | 468/851 [00:06<00:05, 67.35it/s]
|
1653 |
56%|█████▌ | 475/851 [00:06<00:06, 62.52it/s]
|
1654 |
57%|█████▋ | 482/851 [00:06<00:05, 63.14it/s]
|
1655 |
57%|█████▋ | 489/851 [00:07<00:05, 63.97it/s]
|
1656 |
59%|█████▊ | 498/851 [00:07<00:05, 69.11it/s]
|
1657 |
59%|█████▉ | 506/851 [00:07<00:04, 71.64it/s]
|
1658 |
60%|██████ | 514/851 [00:07<00:04, 70.85it/s]
|
1659 |
61%|██████▏ | 522/851 [00:07<00:04, 66.68it/s]
|
1660 |
62%|██████▏ | 529/851 [00:07<00:04, 65.77it/s]
|
1661 |
63%|██████▎ | 537/851 [00:07<00:04, 68.38it/s]
|
1662 |
64%|██████▍ | 545/851 [00:07<00:04, 69.93it/s]
|
1663 |
65%|██████▍ | 553/851 [00:07<00:04, 67.90it/s]
|
1664 |
66%|██████▌ | 561/851 [00:08<00:04, 70.98it/s]
|
1665 |
67%|██████▋ | 569/851 [00:08<00:03, 73.27it/s]
|
1666 |
68%|██████▊ | 577/851 [00:08<00:03, 73.20it/s]
|
1667 |
69%|██████▊ | 585/851 [00:08<00:03, 68.88it/s]
|
1668 |
70%|██████▉ | 592/851 [00:08<00:03, 67.31it/s]
|
1669 |
70%|███████ | 599/851 [00:08<00:03, 67.73it/s]
|
1670 |
71%|███████▏ | 607/851 [00:08<00:03, 68.80it/s]
|
1671 |
72%|███████▏ | 614/851 [00:08<00:03, 66.33it/s]
|
1672 |
73%|███████▎ | 622/851 [00:08<00:03, 67.71it/s]
|
1673 |
74%|███████▍ | 629/851 [00:09<00:03, 63.90it/s]
|
1674 |
75%|███████▍ | 637/851 [00:09<00:03, 66.80it/s]
|
1675 |
76%|███████▌ | 644/851 [00:09<00:03, 62.23it/s]
|
1676 |
77%|███████▋ | 652/851 [00:09<00:03, 65.75it/s]
|
1677 |
78%|███████▊ | 660/851 [00:09<00:02, 68.73it/s]
|
1678 |
78%|███████▊ | 668/851 [00:09<00:02, 70.08it/s]
|
1679 |
79%|███████▉ | 676/851 [00:09<00:02, 69.11it/s]
|
1680 |
80%|████████ | 684/851 [00:09<00:02, 70.02it/s]
|
1681 |
81%|████████▏ | 693/851 [00:09<00:02, 73.25it/s]
|
1682 |
82%|████████▏ | 701/851 [00:10<00:02, 73.96it/s]
|
1683 |
83%|████████▎ | 710/851 [00:10<00:01, 75.96it/s]
|
1684 |
84%|████████▍ | 718/851 [00:10<00:01, 73.07it/s]
|
1685 |
85%|████████▌ | 726/851 [00:10<00:01, 74.63it/s]
|
1686 |
86%|████████▋ | 734/851 [00:10<00:01, 75.56it/s]
|
1687 |
87%|████████▋ | 742/851 [00:10<00:01, 75.66it/s]
|
1688 |
88%|████████▊ | 750/851 [00:10<00:01, 74.81it/s]
|
1689 |
89%|████████▉ | 758/851 [00:10<00:01, 75.25it/s]
|
1690 |
90%|█████████ | 766/851 [00:10<00:01, 71.07it/s]
|
1691 |
91%|█████████ | 774/851 [00:11<00:01, 71.24it/s]
|
1692 |
92%|█████████▏| 782/851 [00:11<00:00, 69.20it/s]
|
1693 |
93%|█████████▎| 790/851 [00:11<00:00, 70.20it/s]
|
1694 |
94%|█████████▍| 798/851 [00:11<00:00, 70.94it/s]
|
1695 |
95%|█████████▍| 806/851 [00:11<00:00, 72.86it/s]
|
1696 |
96%|█████████▌| 814/851 [00:11<00:00, 69.90it/s]
|
1697 |
97%|█████████▋| 822/851 [00:11<00:00, 70.42it/s]
|
1698 |
98%|█████████▊| 830/851 [00:11<00:00, 70.64it/s]
|
1699 |
98%|█████████▊| 838/851 [00:11<00:00, 71.14it/s]
|
1700 |
99%|█████████▉| 846/851 [00:12<00:00, 67.21it/s]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1701 |
0%| | 0/851 [00:00<?, ?it/s]
|
1702 |
1%| | 9/851 [00:00<00:09, 89.28it/s]
|
1703 |
2%|▏ | 18/851 [00:00<00:10, 76.32it/s]
|
1704 |
3%|▎ | 26/851 [00:00<00:11, 74.84it/s]
|
1705 |
4%|▍ | 34/851 [00:00<00:11, 73.37it/s]
|
1706 |
5%|▍ | 42/851 [00:00<00:11, 72.40it/s]
|
1707 |
6%|▌ | 50/851 [00:00<00:10, 73.86it/s]
|
1708 |
7%|▋ | 58/851 [00:00<00:10, 73.78it/s]
|
1709 |
8%|▊ | 66/851 [00:00<00:10, 71.71it/s]
|
1710 |
9%|▊ | 74/851 [00:01<00:11, 67.99it/s]
|
1711 |
10%|▉ | 82/851 [00:01<00:11, 69.81it/s]
|
1712 |
11%|█ | 90/851 [00:01<00:10, 71.29it/s]
|
1713 |
12%|█▏ | 98/851 [00:01<00:10, 69.84it/s]
|
1714 |
12%|█▏ | 106/851 [00:01<00:10, 70.25it/s]
|
1715 |
13%|█▎ | 114/851 [00:01<00:10, 67.45it/s]
|
1716 |
14%|█▍ | 122/851 [00:01<00:10, 70.51it/s]
|
1717 |
15%|█▌ | 130/851 [00:01<00:11, 65.54it/s]
|
1718 |
16%|█▌ | 137/851 [00:01<00:11, 64.79it/s]
|
1719 |
17%|█▋ | 145/851 [00:02<00:10, 66.82it/s]
|
1720 |
18%|█▊ | 152/851 [00:02<00:10, 65.49it/s]
|
1721 |
19%|█▉ | 160/851 [00:02<00:09, 69.23it/s]
|
1722 |
20%|█▉ | 168/851 [00:02<00:09, 70.13it/s]
|
1723 |
21%|██ | 176/851 [00:02<00:09, 71.41it/s]
|
1724 |
22%|██▏ | 184/851 [00:02<00:09, 71.13it/s]
|
1725 |
23%|██▎ | 192/851 [00:02<00:09, 71.88it/s]
|
1726 |
24%|██▎ | 200/851 [00:02<00:08, 73.17it/s]
|
1727 |
24%|██▍ | 208/851 [00:02<00:09, 69.02it/s]
|
1728 |
25%|██▌ | 215/851 [00:03<00:09, 67.30it/s]
|
1729 |
26%|██▌ | 223/851 [00:03<00:09, 68.83it/s]
|
1730 |
27%|██▋ | 231/851 [00:03<00:08, 69.85it/s]
|
1731 |
28%|██▊ | 239/851 [00:03<00:09, 67.99it/s]
|
1732 |
29%|██▉ | 246/851 [00:03<00:09, 65.91it/s]
|
1733 |
30%|██▉ | 254/851 [00:03<00:08, 69.57it/s]
|
1734 |
31%|███ | 262/851 [00:03<00:08, 71.81it/s]
|
1735 |
32%|███▏ | 270/851 [00:03<00:08, 70.28it/s]
|
1736 |
33%|███▎ | 278/851 [00:03<00:07, 72.94it/s]
|
1737 |
34%|███▎ | 286/851 [00:04<00:07, 73.83it/s]
|
1738 |
35%|███▍ | 294/851 [00:04<00:07, 70.51it/s]
|
1739 |
36%|███▌ | 303/851 [00:04<00:07, 73.46it/s]
|
1740 |
37%|███▋ | 311/851 [00:04<00:07, 70.10it/s]
|
1741 |
37%|███▋ | 319/851 [00:04<00:07, 72.11it/s]
|
1742 |
38%|███▊ | 327/851 [00:04<00:07, 71.11it/s]
|
1743 |
39%|███▉ | 335/851 [00:04<00:07, 70.55it/s]
|
1744 |
40%|████ | 343/851 [00:04<00:07, 72.12it/s]
|
1745 |
41%|████ | 351/851 [00:04<00:06, 72.42it/s]
|
1746 |
42%|████▏ | 359/851 [00:05<00:07, 66.81it/s]
|
1747 |
43%|████▎ | 367/851 [00:05<00:07, 68.19it/s]
|
1748 |
44%|████▍ | 374/851 [00:05<00:07, 67.00it/s]
|
1749 |
45%|████▍ | 381/851 [00:05<00:07, 64.83it/s]
|
1750 |
46%|████▌ | 389/851 [00:05<00:06, 68.13it/s]
|
1751 |
47%|████▋ | 397/851 [00:05<00:06, 69.09it/s]
|
1752 |
47%|████▋ | 404/851 [00:05<00:06, 64.36it/s]
|
1753 |
48%|████▊ | 412/851 [00:05<00:06, 65.60it/s]
|
1754 |
49%|████▉ | 420/851 [00:06<00:06, 68.49it/s]
|
1755 |
50%|█████ | 427/851 [00:06<00:06, 65.71it/s]
|
1756 |
51%|█████ | 435/851 [00:06<00:06, 68.37it/s]
|
1757 |
52%|█████▏ | 443/851 [00:06<00:05, 70.54it/s]
|
1758 |
53%|█████▎ | 451/851 [00:06<00:05, 71.45it/s]
|
1759 |
54%|█████▍ | 459/851 [00:06<00:05, 72.02it/s]
|
1760 |
55%|█████▍ | 467/851 [00:06<00:05, 66.48it/s]
|
1761 |
56%|█████▌ | 474/851 [00:06<00:06, 62.19it/s]
|
1762 |
57%|█████▋ | 481/851 [00:06<00:05, 63.17it/s]
|
1763 |
57%|█████▋ | 488/851 [00:07<00:05, 64.90it/s]
|
1764 |
58%|█████▊ | 496/851 [00:07<00:05, 67.97it/s]
|
1765 |
59%|█████▉ | 504/851 [00:07<00:04, 71.24it/s]
|
1766 |
60%|██████ | 512/851 [00:07<00:04, 70.23it/s]
|
1767 |
61%|██████ | 520/851 [00:07<00:04, 71.31it/s]
|
1768 |
62%|██████▏ | 528/851 [00:07<00:04, 65.51it/s]
|
1769 |
63%|██████▎ | 536/851 [00:07<00:04, 67.75it/s]
|
1770 |
64%|██████▍ | 544/851 [00:07<00:04, 69.64it/s]
|
1771 |
65%|██████▍ | 552/851 [00:07<00:04, 67.32it/s]
|
1772 |
66%|██████▌ | 560/851 [00:08<00:04, 69.83it/s]
|
1773 |
67%|██████▋ | 568/851 [00:08<00:03, 72.10it/s]
|
1774 |
68%|██████▊ | 576/851 [00:08<00:03, 72.39it/s]
|
1775 |
69%|██████▊ | 584/851 [00:08<00:03, 68.89it/s]
|
1776 |
69%|██████▉ | 591/851 [00:08<00:03, 66.82it/s]
|
1777 |
70%|███████ | 598/851 [00:08<00:03, 67.43it/s]
|
1778 |
71%|███████ | 605/851 [00:08<00:03, 67.25it/s]
|
1779 |
72%|███████▏ | 612/851 [00:08<00:03, 65.87it/s]
|
1780 |
73%|███████▎ | 619/851 [00:08<00:03, 65.34it/s]
|
1781 |
74%|███████▎ | 626/851 [00:09<00:03, 64.84it/s]
|
1782 |
74%|███████▍ | 633/851 [00:09<00:03, 65.27it/s]
|
1783 |
75%|███████▌ | 640/851 [00:09<00:03, 64.95it/s]
|
1784 |
76%|███████▌ | 647/851 [00:09<00:03, 63.18it/s]
|
1785 |
77%|███████▋ | 655/851 [00:09<00:02, 66.34it/s]
|
1786 |
78%|███████▊ | 663/851 [00:09<00:02, 67.96it/s]
|
1787 |
79%|███████▊ | 670/851 [00:09<00:02, 68.44it/s]
|
1788 |
80%|███████▉ | 677/851 [00:09<00:02, 68.31it/s]
|
1789 |
80%|████████ | 685/851 [00:09<00:02, 69.35it/s]
|
1790 |
81%|████████▏ | 693/851 [00:10<00:02, 72.25it/s]
|
1791 |
82%|████████▏ | 701/851 [00:10<00:02, 72.73it/s]
|
1792 |
83%|████████▎ | 709/851 [00:10<00:01, 74.24it/s]
|
1793 |
84%|████████▍ | 717/851 [00:10<00:01, 73.24it/s]
|
1794 |
85%|████████▌ | 725/851 [00:10<00:01, 73.55it/s]
|
1795 |
86%|████████▌ | 733/851 [00:10<00:01, 74.45it/s]
|
1796 |
87%|████████▋ | 741/851 [00:10<00:01, 75.51it/s]
|
1797 |
88%|████████▊ | 749/851 [00:10<00:01, 74.86it/s]
|
1798 |
89%|████████▉ | 757/851 [00:10<00:01, 74.62it/s]
|
1799 |
90%|████████▉ | 765/851 [00:11<00:01, 73.45it/s]
|
1800 |
91%|█████████ | 773/851 [00:11<00:01, 70.77it/s]
|
1801 |
92%|█████████▏| 781/851 [00:11<00:01, 67.45it/s]
|
1802 |
93%|█████████▎| 789/851 [00:11<00:00, 69.14it/s]
|
1803 |
94%|█████████▎| 797/851 [00:11<00:00, 70.53it/s]
|
1804 |
95%|█████████▍| 805/851 [00:11<00:00, 73.00it/s]
|
1805 |
96%|█████████▌| 813/851 [00:11<00:00, 69.66it/s]
|
1806 |
96%|█████████▋| 821/851 [00:11<00:00, 70.69it/s]
|
1807 |
97%|█████████▋| 829/851 [00:11<00:00, 71.60it/s]
|
1808 |
98%|█████████▊| 837/851 [00:12<00:00, 72.30it/s]
|
1809 |
99%|█████████▉| 845/851 [00:12<00:00, 66.40it/s]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1590 |
[INFO|modeling_utils.py:2590] 2024-05-15 15:28:19,154 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
|
1591 |
[INFO|tokenization_utils_base.py:2488] 2024-05-15 15:28:19,155 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
|
1592 |
[INFO|tokenization_utils_base.py:2497] 2024-05-15 15:28:19,156 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
|
1593 |
+
{'eval_loss': 0.006454338785260916, 'eval_precision': 0.9437386569872959, 'eval_recall': 0.9558823529411765, 'eval_f1': 0.949771689497717, 'eval_accuracy': 0.9990250667691949, 'eval_runtime': 15.7656, 'eval_samples_per_second': 431.764, 'eval_steps_per_second': 53.978, 'epoch': 10.0}
|
1594 |
+
{'train_runtime': 3387.0101, 'train_samples_per_second': 80.378, 'train_steps_per_second': 5.022, 'train_loss': 0.0023016003105682196, 'epoch': 10.0}
|
1595 |
+
***** train metrics *****
|
1596 |
+
epoch = 9.9971
|
1597 |
+
total_flos = 6240195GF
|
1598 |
+
train_loss = 0.0023
|
1599 |
+
train_runtime = 0:56:27.01
|
1600 |
+
train_samples = 27224
|
1601 |
+
train_samples_per_second = 80.378
|
1602 |
+
train_steps_per_second = 5.022
|
1603 |
+
05/15/2024 15:28:23 - INFO - __main__ - *** Evaluate ***
|
1604 |
+
[INFO|trainer.py:786] 2024-05-15 15:28:23,892 >> The following columns in the evaluation set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, tokens, id. If ner_tags, tokens, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message.
|
1605 |
+
[INFO|trainer.py:3614] 2024-05-15 15:28:23,895 >> ***** Running Evaluation *****
|
1606 |
+
[INFO|trainer.py:3616] 2024-05-15 15:28:23,895 >> Num examples = 6807
|
1607 |
+
[INFO|trainer.py:3619] 2024-05-15 15:28:23,895 >> Batch size = 8
|
1608 |
+
|
1609 |
0%| | 0/851 [00:00<?, ?it/s]
|
1610 |
1%| | 10/851 [00:00<00:09, 90.51it/s]
|
1611 |
2%|▏ | 20/851 [00:00<00:10, 77.83it/s]
|
1612 |
3%|▎ | 28/851 [00:00<00:11, 74.40it/s]
|
1613 |
4%|▍ | 36/851 [00:00<00:11, 73.24it/s]
|
1614 |
5%|▌ | 44/851 [00:00<00:10, 73.71it/s]
|
1615 |
6%|▌ | 52/851 [00:00<00:10, 74.57it/s]
|
1616 |
7%|▋ | 60/851 [00:00<00:10, 75.32it/s]
|
1617 |
8%|▊ | 68/851 [00:00<00:11, 69.52it/s]
|
1618 |
9%|▉ | 76/851 [00:01<00:11, 69.83it/s]
|
1619 |
10%|▉ | 84/851 [00:01<00:10, 70.07it/s]
|
1620 |
11%|█ | 92/851 [00:01<00:10, 69.97it/s]
|
1621 |
12%|█▏ | 100/851 [00:01<00:10, 69.61it/s]
|
1622 |
13%|█▎ | 107/851 [00:01<00:10, 68.65it/s]
|
1623 |
14%|█▎ | 115/851 [00:01<00:10, 68.72it/s]
|
1624 |
15%|█▍ | 124/851 [00:01<00:10, 72.49it/s]
|
1625 |
16%|█▌ | 132/851 [00:01<00:10, 65.39it/s]
|
1626 |
16%|█▋ | 139/851 [00:01<00:10, 65.90it/s]
|
1627 |
17%|█▋ | 147/851 [00:02<00:10, 67.50it/s]
|
1628 |
18%|█▊ | 154/851 [00:02<00:10, 67.04it/s]
|
1629 |
19%|█▉ | 161/851 [00:02<00:10, 66.91it/s]
|
1630 |
20%|█▉ | 169/851 [00:02<00:10, 67.78it/s]
|
1631 |
21%|██ | 177/851 [00:02<00:09, 69.96it/s]
|
1632 |
22%|██▏ | 185/851 [00:02<00:09, 71.55it/s]
|
1633 |
23%|██▎ | 193/851 [00:02<00:09, 72.55it/s]
|
1634 |
24%|██▎ | 201/851 [00:02<00:08, 74.28it/s]
|
1635 |
25%|██▍ | 209/851 [00:02<00:09, 70.56it/s]
|
1636 |
25%|██▌ | 217/851 [00:03<00:09, 68.99it/s]
|
1637 |
26%|██▋ | 224/851 [00:03<00:09, 69.14it/s]
|
1638 |
27%|██▋ | 232/851 [00:03<00:08, 71.37it/s]
|
1639 |
28%|██▊ | 240/851 [00:03<00:08, 68.79it/s]
|
1640 |
29%|██▉ | 247/851 [00:03<00:09, 66.73it/s]
|
1641 |
30%|██▉ | 255/851 [00:03<00:08, 69.91it/s]
|
1642 |
31%|███ | 263/851 [00:03<00:08, 72.69it/s]
|
1643 |
32%|███▏ | 271/851 [00:03<00:08, 71.09it/s]
|
1644 |
33%|███▎ | 279/851 [00:03<00:07, 73.46it/s]
|
1645 |
34%|███▎ | 287/851 [00:04<00:07, 72.07it/s]
|
1646 |
35%|███▍ | 295/851 [00:04<00:07, 72.11it/s]
|
1647 |
36%|███▌ | 303/851 [00:04<00:07, 73.81it/s]
|
1648 |
37%|███▋ | 311/851 [00:04<00:07, 68.28it/s]
|
1649 |
38%|███▊ | 320/851 [00:04<00:07, 71.75it/s]
|
1650 |
39%|███▊ | 328/851 [00:04<00:07, 72.02it/s]
|
1651 |
39%|███▉ | 336/851 [00:04<00:07, 71.36it/s]
|
1652 |
40%|████ | 344/851 [00:04<00:06, 73.18it/s]
|
1653 |
41%|████▏ | 352/851 [00:04<00:06, 72.55it/s]
|
1654 |
42%|████▏ | 360/851 [00:05<00:07, 66.67it/s]
|
1655 |
43%|████▎ | 368/851 [00:05<00:07, 68.29it/s]
|
1656 |
44%|████▍ | 375/851 [00:05<00:06, 68.41it/s]
|
1657 |
45%|████▍ | 382/851 [00:05<00:07, 66.01it/s]
|
1658 |
46%|████▌ | 390/851 [00:05<00:06, 69.04it/s]
|
1659 |
47%|████▋ | 398/851 [00:05<00:06, 70.03it/s]
|
1660 |
48%|████▊ | 406/851 [00:05<00:06, 65.84it/s]
|
1661 |
49%|████▊ | 414/851 [00:05<00:06, 66.93it/s]
|
1662 |
50%|████▉ | 422/851 [00:06<00:06, 69.24it/s]
|
1663 |
50%|█████ | 429/851 [00:06<00:06, 67.99it/s]
|
1664 |
51%|█████▏ | 437/851 [00:06<00:05, 70.32it/s]
|
1665 |
52%|█████▏ | 445/851 [00:06<00:05, 71.78it/s]
|
1666 |
53%|█████▎ | 453/851 [00:06<00:05, 71.61it/s]
|
1667 |
54%|█████▍ | 461/851 [00:06<00:05, 69.59it/s]
|
1668 |
55%|█████▍ | 468/851 [00:06<00:05, 67.35it/s]
|
1669 |
56%|█████▌ | 475/851 [00:06<00:06, 62.52it/s]
|
1670 |
57%|█████▋ | 482/851 [00:06<00:05, 63.14it/s]
|
1671 |
57%|█████▋ | 489/851 [00:07<00:05, 63.97it/s]
|
1672 |
59%|█████▊ | 498/851 [00:07<00:05, 69.11it/s]
|
1673 |
59%|█████▉ | 506/851 [00:07<00:04, 71.64it/s]
|
1674 |
60%|██████ | 514/851 [00:07<00:04, 70.85it/s]
|
1675 |
61%|██████▏ | 522/851 [00:07<00:04, 66.68it/s]
|
1676 |
62%|██████▏ | 529/851 [00:07<00:04, 65.77it/s]
|
1677 |
63%|██████▎ | 537/851 [00:07<00:04, 68.38it/s]
|
1678 |
64%|██████▍ | 545/851 [00:07<00:04, 69.93it/s]
|
1679 |
65%|██████▍ | 553/851 [00:07<00:04, 67.90it/s]
|
1680 |
66%|██████▌ | 561/851 [00:08<00:04, 70.98it/s]
|
1681 |
67%|██████▋ | 569/851 [00:08<00:03, 73.27it/s]
|
1682 |
68%|██████▊ | 577/851 [00:08<00:03, 73.20it/s]
|
1683 |
69%|██████▊ | 585/851 [00:08<00:03, 68.88it/s]
|
1684 |
70%|██████▉ | 592/851 [00:08<00:03, 67.31it/s]
|
1685 |
70%|███████ | 599/851 [00:08<00:03, 67.73it/s]
|
1686 |
71%|███████▏ | 607/851 [00:08<00:03, 68.80it/s]
|
1687 |
72%|███████▏ | 614/851 [00:08<00:03, 66.33it/s]
|
1688 |
73%|███████▎ | 622/851 [00:08<00:03, 67.71it/s]
|
1689 |
74%|███████▍ | 629/851 [00:09<00:03, 63.90it/s]
|
1690 |
75%|███████▍ | 637/851 [00:09<00:03, 66.80it/s]
|
1691 |
76%|███████▌ | 644/851 [00:09<00:03, 62.23it/s]
|
1692 |
77%|███████▋ | 652/851 [00:09<00:03, 65.75it/s]
|
1693 |
78%|███████▊ | 660/851 [00:09<00:02, 68.73it/s]
|
1694 |
78%|███████▊ | 668/851 [00:09<00:02, 70.08it/s]
|
1695 |
79%|███████▉ | 676/851 [00:09<00:02, 69.11it/s]
|
1696 |
80%|████████ | 684/851 [00:09<00:02, 70.02it/s]
|
1697 |
81%|████████▏ | 693/851 [00:09<00:02, 73.25it/s]
|
1698 |
82%|████████▏ | 701/851 [00:10<00:02, 73.96it/s]
|
1699 |
83%|████████▎ | 710/851 [00:10<00:01, 75.96it/s]
|
1700 |
84%|████████▍ | 718/851 [00:10<00:01, 73.07it/s]
|
1701 |
85%|████████▌ | 726/851 [00:10<00:01, 74.63it/s]
|
1702 |
86%|████████▋ | 734/851 [00:10<00:01, 75.56it/s]
|
1703 |
87%|████████▋ | 742/851 [00:10<00:01, 75.66it/s]
|
1704 |
88%|████████▊ | 750/851 [00:10<00:01, 74.81it/s]
|
1705 |
89%|████████▉ | 758/851 [00:10<00:01, 75.25it/s]
|
1706 |
90%|█████████ | 766/851 [00:10<00:01, 71.07it/s]
|
1707 |
91%|█████████ | 774/851 [00:11<00:01, 71.24it/s]
|
1708 |
92%|█████████▏| 782/851 [00:11<00:00, 69.20it/s]
|
1709 |
93%|█████████▎| 790/851 [00:11<00:00, 70.20it/s]
|
1710 |
94%|█████████▍| 798/851 [00:11<00:00, 70.94it/s]
|
1711 |
95%|█████████▍| 806/851 [00:11<00:00, 72.86it/s]
|
1712 |
96%|█████████▌| 814/851 [00:11<00:00, 69.90it/s]
|
1713 |
97%|█████████▋| 822/851 [00:11<00:00, 70.42it/s]
|
1714 |
98%|█████████▊| 830/851 [00:11<00:00, 70.64it/s]
|
1715 |
98%|█████████▊| 838/851 [00:11<00:00, 71.14it/s]
|
1716 |
99%|█████████▉| 846/851 [00:12<00:00, 67.21it/s]
|
1717 |
+
***** eval metrics *****
|
1718 |
+
epoch = 9.9971
|
1719 |
+
eval_accuracy = 0.999
|
1720 |
+
eval_f1 = 0.9508
|
1721 |
+
eval_loss = 0.0058
|
1722 |
+
eval_precision = 0.943
|
1723 |
+
eval_recall = 0.9586
|
1724 |
+
eval_runtime = 0:00:15.61
|
1725 |
+
eval_samples = 6807
|
1726 |
+
eval_samples_per_second = 435.949
|
1727 |
+
eval_steps_per_second = 54.502
|
1728 |
+
05/15/2024 15:28:39 - INFO - __main__ - *** Predict ***
|
1729 |
+
[INFO|trainer.py:786] 2024-05-15 15:28:39,512 >> The following columns in the test set don't have a corresponding argument in `RobertaForTokenClassification.forward` and have been ignored: ner_tags, tokens, id. If ner_tags, tokens, id are not expected by `RobertaForTokenClassification.forward`, you can safely ignore this message.
|
1730 |
+
[INFO|trainer.py:3614] 2024-05-15 15:28:39,514 >> ***** Running Prediction *****
|
1731 |
+
[INFO|trainer.py:3616] 2024-05-15 15:28:39,514 >> Num examples = 6807
|
1732 |
+
[INFO|trainer.py:3619] 2024-05-15 15:28:39,514 >> Batch size = 8
|
1733 |
+
|
1734 |
0%| | 0/851 [00:00<?, ?it/s]
|
1735 |
1%| | 9/851 [00:00<00:09, 89.28it/s]
|
1736 |
2%|▏ | 18/851 [00:00<00:10, 76.32it/s]
|
1737 |
3%|▎ | 26/851 [00:00<00:11, 74.84it/s]
|
1738 |
4%|▍ | 34/851 [00:00<00:11, 73.37it/s]
|
1739 |
5%|▍ | 42/851 [00:00<00:11, 72.40it/s]
|
1740 |
6%|▌ | 50/851 [00:00<00:10, 73.86it/s]
|
1741 |
7%|▋ | 58/851 [00:00<00:10, 73.78it/s]
|
1742 |
8%|▊ | 66/851 [00:00<00:10, 71.71it/s]
|
1743 |
9%|▊ | 74/851 [00:01<00:11, 67.99it/s]
|
1744 |
10%|▉ | 82/851 [00:01<00:11, 69.81it/s]
|
1745 |
11%|█ | 90/851 [00:01<00:10, 71.29it/s]
|
1746 |
12%|█▏ | 98/851 [00:01<00:10, 69.84it/s]
|
1747 |
12%|█▏ | 106/851 [00:01<00:10, 70.25it/s]
|
1748 |
13%|█▎ | 114/851 [00:01<00:10, 67.45it/s]
|
1749 |
14%|█▍ | 122/851 [00:01<00:10, 70.51it/s]
|
1750 |
15%|█▌ | 130/851 [00:01<00:11, 65.54it/s]
|
1751 |
16%|█▌ | 137/851 [00:01<00:11, 64.79it/s]
|
1752 |
17%|█▋ | 145/851 [00:02<00:10, 66.82it/s]
|
1753 |
18%|█▊ | 152/851 [00:02<00:10, 65.49it/s]
|
1754 |
19%|█▉ | 160/851 [00:02<00:09, 69.23it/s]
|
1755 |
20%|█▉ | 168/851 [00:02<00:09, 70.13it/s]
|
1756 |
21%|██ | 176/851 [00:02<00:09, 71.41it/s]
|
1757 |
22%|██▏ | 184/851 [00:02<00:09, 71.13it/s]
|
1758 |
23%|██▎ | 192/851 [00:02<00:09, 71.88it/s]
|
1759 |
24%|██▎ | 200/851 [00:02<00:08, 73.17it/s]
|
1760 |
24%|██▍ | 208/851 [00:02<00:09, 69.02it/s]
|
1761 |
25%|██▌ | 215/851 [00:03<00:09, 67.30it/s]
|
1762 |
26%|██▌ | 223/851 [00:03<00:09, 68.83it/s]
|
1763 |
27%|██▋ | 231/851 [00:03<00:08, 69.85it/s]
|
1764 |
28%|██▊ | 239/851 [00:03<00:09, 67.99it/s]
|
1765 |
29%|██▉ | 246/851 [00:03<00:09, 65.91it/s]
|
1766 |
30%|██▉ | 254/851 [00:03<00:08, 69.57it/s]
|
1767 |
31%|███ | 262/851 [00:03<00:08, 71.81it/s]
|
1768 |
32%|███▏ | 270/851 [00:03<00:08, 70.28it/s]
|
1769 |
33%|███▎ | 278/851 [00:03<00:07, 72.94it/s]
|
1770 |
34%|███▎ | 286/851 [00:04<00:07, 73.83it/s]
|
1771 |
35%|███▍ | 294/851 [00:04<00:07, 70.51it/s]
|
1772 |
36%|███▌ | 303/851 [00:04<00:07, 73.46it/s]
|
1773 |
37%|███▋ | 311/851 [00:04<00:07, 70.10it/s]
|
1774 |
37%|███▋ | 319/851 [00:04<00:07, 72.11it/s]
|
1775 |
38%|███▊ | 327/851 [00:04<00:07, 71.11it/s]
|
1776 |
39%|███▉ | 335/851 [00:04<00:07, 70.55it/s]
|
1777 |
40%|████ | 343/851 [00:04<00:07, 72.12it/s]
|
1778 |
41%|████ | 351/851 [00:04<00:06, 72.42it/s]
|
1779 |
42%|████▏ | 359/851 [00:05<00:07, 66.81it/s]
|
1780 |
43%|████▎ | 367/851 [00:05<00:07, 68.19it/s]
|
1781 |
44%|████▍ | 374/851 [00:05<00:07, 67.00it/s]
|
1782 |
45%|████▍ | 381/851 [00:05<00:07, 64.83it/s]
|
1783 |
46%|████▌ | 389/851 [00:05<00:06, 68.13it/s]
|
1784 |
47%|████▋ | 397/851 [00:05<00:06, 69.09it/s]
|
1785 |
47%|████▋ | 404/851 [00:05<00:06, 64.36it/s]
|
1786 |
48%|████▊ | 412/851 [00:05<00:06, 65.60it/s]
|
1787 |
49%|████▉ | 420/851 [00:06<00:06, 68.49it/s]
|
1788 |
50%|█████ | 427/851 [00:06<00:06, 65.71it/s]
|
1789 |
51%|█████ | 435/851 [00:06<00:06, 68.37it/s]
|
1790 |
52%|█████▏ | 443/851 [00:06<00:05, 70.54it/s]
|
1791 |
53%|█████▎ | 451/851 [00:06<00:05, 71.45it/s]
|
1792 |
54%|█████▍ | 459/851 [00:06<00:05, 72.02it/s]
|
1793 |
55%|█████▍ | 467/851 [00:06<00:05, 66.48it/s]
|
1794 |
56%|█████▌ | 474/851 [00:06<00:06, 62.19it/s]
|
1795 |
57%|█████▋ | 481/851 [00:06<00:05, 63.17it/s]
|
1796 |
57%|█████▋ | 488/851 [00:07<00:05, 64.90it/s]
|
1797 |
58%|█████▊ | 496/851 [00:07<00:05, 67.97it/s]
|
1798 |
59%|█████▉ | 504/851 [00:07<00:04, 71.24it/s]
|
1799 |
60%|██████ | 512/851 [00:07<00:04, 70.23it/s]
|
1800 |
61%|██████ | 520/851 [00:07<00:04, 71.31it/s]
|
1801 |
62%|██████▏ | 528/851 [00:07<00:04, 65.51it/s]
|
1802 |
63%|██████▎ | 536/851 [00:07<00:04, 67.75it/s]
|
1803 |
64%|██████▍ | 544/851 [00:07<00:04, 69.64it/s]
|
1804 |
65%|██████▍ | 552/851 [00:07<00:04, 67.32it/s]
|
1805 |
66%|██████▌ | 560/851 [00:08<00:04, 69.83it/s]
|
1806 |
67%|██████▋ | 568/851 [00:08<00:03, 72.10it/s]
|
1807 |
68%|██████▊ | 576/851 [00:08<00:03, 72.39it/s]
|
1808 |
69%|██████▊ | 584/851 [00:08<00:03, 68.89it/s]
|
1809 |
69%|██████▉ | 591/851 [00:08<00:03, 66.82it/s]
|
1810 |
70%|███████ | 598/851 [00:08<00:03, 67.43it/s]
|
1811 |
71%|███████ | 605/851 [00:08<00:03, 67.25it/s]
|
1812 |
72%|███████▏ | 612/851 [00:08<00:03, 65.87it/s]
|
1813 |
73%|███████▎ | 619/851 [00:08<00:03, 65.34it/s]
|
1814 |
74%|███████▎ | 626/851 [00:09<00:03, 64.84it/s]
|
1815 |
74%|███████▍ | 633/851 [00:09<00:03, 65.27it/s]
|
1816 |
75%|███████▌ | 640/851 [00:09<00:03, 64.95it/s]
|
1817 |
76%|███████▌ | 647/851 [00:09<00:03, 63.18it/s]
|
1818 |
77%|███████▋ | 655/851 [00:09<00:02, 66.34it/s]
|
1819 |
78%|███████▊ | 663/851 [00:09<00:02, 67.96it/s]
|
1820 |
79%|███████▊ | 670/851 [00:09<00:02, 68.44it/s]
|
1821 |
80%|███████▉ | 677/851 [00:09<00:02, 68.31it/s]
|
1822 |
80%|████████ | 685/851 [00:09<00:02, 69.35it/s]
|
1823 |
81%|████████▏ | 693/851 [00:10<00:02, 72.25it/s]
|
1824 |
82%|████████▏ | 701/851 [00:10<00:02, 72.73it/s]
|
1825 |
83%|████████▎ | 709/851 [00:10<00:01, 74.24it/s]
|
1826 |
84%|████████▍ | 717/851 [00:10<00:01, 73.24it/s]
|
1827 |
85%|████████▌ | 725/851 [00:10<00:01, 73.55it/s]
|
1828 |
86%|████████▌ | 733/851 [00:10<00:01, 74.45it/s]
|
1829 |
87%|████████▋ | 741/851 [00:10<00:01, 75.51it/s]
|
1830 |
88%|████████▊ | 749/851 [00:10<00:01, 74.86it/s]
|
1831 |
89%|████████▉ | 757/851 [00:10<00:01, 74.62it/s]
|
1832 |
90%|████████▉ | 765/851 [00:11<00:01, 73.45it/s]
|
1833 |
91%|█████████ | 773/851 [00:11<00:01, 70.77it/s]
|
1834 |
92%|█████████▏| 781/851 [00:11<00:01, 67.45it/s]
|
1835 |
93%|█████████▎| 789/851 [00:11<00:00, 69.14it/s]
|
1836 |
94%|█████████▎| 797/851 [00:11<00:00, 70.53it/s]
|
1837 |
95%|█████████▍| 805/851 [00:11<00:00, 73.00it/s]
|
1838 |
96%|█████████▌| 813/851 [00:11<00:00, 69.66it/s]
|
1839 |
96%|█████████▋| 821/851 [00:11<00:00, 70.69it/s]
|
1840 |
97%|█████████▋| 829/851 [00:11<00:00, 71.60it/s]
|
1841 |
98%|█████████▊| 837/851 [00:12<00:00, 72.30it/s]
|
1842 |
99%|█████████▉| 845/851 [00:12<00:00, 66.40it/s]
|
1843 |
+
[INFO|trainer.py:3305] 2024-05-15 15:28:55,509 >> Saving model checkpoint to /content/dissertation/scripts/ner/output
|
1844 |
+
[INFO|configuration_utils.py:471] 2024-05-15 15:28:55,510 >> Configuration saved in /content/dissertation/scripts/ner/output/config.json
|
1845 |
+
[INFO|modeling_utils.py:2590] 2024-05-15 15:28:56,772 >> Model weights saved in /content/dissertation/scripts/ner/output/model.safetensors
|
1846 |
+
[INFO|tokenization_utils_base.py:2488] 2024-05-15 15:28:56,773 >> tokenizer config file saved in /content/dissertation/scripts/ner/output/tokenizer_config.json
|
1847 |
+
[INFO|tokenization_utils_base.py:2497] 2024-05-15 15:28:56,774 >> Special tokens file saved in /content/dissertation/scripts/ner/output/special_tokens_map.json
|
1848 |
+
***** predict metrics *****
|
1849 |
+
predict_accuracy = 0.999
|
1850 |
+
predict_f1 = 0.9508
|
1851 |
+
predict_loss = 0.0058
|
1852 |
+
predict_precision = 0.943
|
1853 |
+
predict_recall = 0.9586
|
1854 |
+
predict_runtime = 0:00:15.69
|
1855 |
+
predict_samples_per_second = 433.645
|
1856 |
+
predict_steps_per_second = 54.214
|
1857 |
+
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 9.997061416397296,
|
3 |
+
"total_flos": 6700358578825584.0,
|
4 |
+
"train_loss": 0.0023016003105682196,
|
5 |
+
"train_runtime": 3387.0101,
|
6 |
+
"train_samples": 27224,
|
7 |
+
"train_samples_per_second": 80.378,
|
8 |
+
"train_steps_per_second": 5.022
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,388 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.95077484047402,
|
3 |
+
"best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-13612",
|
4 |
+
"epoch": 9.997061416397296,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 17010,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.29385836027034967,
|
13 |
+
"grad_norm": 0.008281867019832134,
|
14 |
+
"learning_rate": 4.853027630805409e-05,
|
15 |
+
"loss": 0.0278,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.5877167205406993,
|
20 |
+
"grad_norm": 0.7454735040664673,
|
21 |
+
"learning_rate": 4.7060552616108174e-05,
|
22 |
+
"loss": 0.0082,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.8815750808110491,
|
27 |
+
"grad_norm": 0.028717944398522377,
|
28 |
+
"learning_rate": 4.559082892416226e-05,
|
29 |
+
"loss": 0.0055,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.9997061416397296,
|
34 |
+
"eval_accuracy": 0.9984002856142422,
|
35 |
+
"eval_f1": 0.9022907900888265,
|
36 |
+
"eval_loss": 0.003938445821404457,
|
37 |
+
"eval_precision": 0.9181731684110371,
|
38 |
+
"eval_recall": 0.8869485294117647,
|
39 |
+
"eval_runtime": 15.693,
|
40 |
+
"eval_samples_per_second": 433.761,
|
41 |
+
"eval_steps_per_second": 54.228,
|
42 |
+
"step": 1701
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.1754334410813987,
|
46 |
+
"grad_norm": 0.007521205581724644,
|
47 |
+
"learning_rate": 4.4121105232216346e-05,
|
48 |
+
"loss": 0.0042,
|
49 |
+
"step": 2000
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 1.4692918013517484,
|
53 |
+
"grad_norm": 0.0010779600124806166,
|
54 |
+
"learning_rate": 4.265138154027043e-05,
|
55 |
+
"loss": 0.0036,
|
56 |
+
"step": 2500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.7631501616220981,
|
60 |
+
"grad_norm": 0.0016530421562492847,
|
61 |
+
"learning_rate": 4.118165784832452e-05,
|
62 |
+
"loss": 0.0037,
|
63 |
+
"step": 3000
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.0,
|
67 |
+
"eval_accuracy": 0.9981599851700297,
|
68 |
+
"eval_f1": 0.9000469263256687,
|
69 |
+
"eval_loss": 0.005709913093596697,
|
70 |
+
"eval_precision": 0.9194630872483222,
|
71 |
+
"eval_recall": 0.8814338235294118,
|
72 |
+
"eval_runtime": 15.7138,
|
73 |
+
"eval_samples_per_second": 433.187,
|
74 |
+
"eval_steps_per_second": 54.156,
|
75 |
+
"step": 3403
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.0570085218924477,
|
79 |
+
"grad_norm": 0.7208561897277832,
|
80 |
+
"learning_rate": 3.971193415637861e-05,
|
81 |
+
"loss": 0.0032,
|
82 |
+
"step": 3500
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 2.3508668821627974,
|
86 |
+
"grad_norm": 0.010068068280816078,
|
87 |
+
"learning_rate": 3.824221046443269e-05,
|
88 |
+
"loss": 0.0023,
|
89 |
+
"step": 4000
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 2.644725242433147,
|
93 |
+
"grad_norm": 0.017267288640141487,
|
94 |
+
"learning_rate": 3.677248677248677e-05,
|
95 |
+
"loss": 0.0029,
|
96 |
+
"step": 4500
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 2.938583602703497,
|
100 |
+
"grad_norm": 0.14932678639888763,
|
101 |
+
"learning_rate": 3.530276308054086e-05,
|
102 |
+
"loss": 0.0024,
|
103 |
+
"step": 5000
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 2.9997061416397295,
|
107 |
+
"eval_accuracy": 0.9990113353152399,
|
108 |
+
"eval_f1": 0.9414965986394559,
|
109 |
+
"eval_loss": 0.0036316141486167908,
|
110 |
+
"eval_precision": 0.9292748433303492,
|
111 |
+
"eval_recall": 0.9540441176470589,
|
112 |
+
"eval_runtime": 15.718,
|
113 |
+
"eval_samples_per_second": 433.069,
|
114 |
+
"eval_steps_per_second": 54.142,
|
115 |
+
"step": 5104
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 3.2324419629738466,
|
119 |
+
"grad_norm": 0.0006910681258887053,
|
120 |
+
"learning_rate": 3.3833039388594945e-05,
|
121 |
+
"loss": 0.0019,
|
122 |
+
"step": 5500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 3.5263003232441963,
|
126 |
+
"grad_norm": 0.07551395893096924,
|
127 |
+
"learning_rate": 3.2363315696649034e-05,
|
128 |
+
"loss": 0.0017,
|
129 |
+
"step": 6000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 3.820158683514546,
|
133 |
+
"grad_norm": 0.035475652664899826,
|
134 |
+
"learning_rate": 3.0893592004703116e-05,
|
135 |
+
"loss": 0.0013,
|
136 |
+
"step": 6500
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 4.0,
|
140 |
+
"eval_accuracy": 0.9989358123184874,
|
141 |
+
"eval_f1": 0.9402501157943493,
|
142 |
+
"eval_loss": 0.005335611291229725,
|
143 |
+
"eval_precision": 0.9477124183006536,
|
144 |
+
"eval_recall": 0.9329044117647058,
|
145 |
+
"eval_runtime": 15.7659,
|
146 |
+
"eval_samples_per_second": 431.754,
|
147 |
+
"eval_steps_per_second": 53.977,
|
148 |
+
"step": 6806
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 4.114017043784895,
|
152 |
+
"grad_norm": 0.0003611127322074026,
|
153 |
+
"learning_rate": 2.9423868312757202e-05,
|
154 |
+
"loss": 0.0011,
|
155 |
+
"step": 7000
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 4.407875404055245,
|
159 |
+
"grad_norm": 0.000422955141402781,
|
160 |
+
"learning_rate": 2.795414462081129e-05,
|
161 |
+
"loss": 0.0007,
|
162 |
+
"step": 7500
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 4.701733764325595,
|
166 |
+
"grad_norm": 0.00019804929615929723,
|
167 |
+
"learning_rate": 2.648442092886537e-05,
|
168 |
+
"loss": 0.0009,
|
169 |
+
"step": 8000
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 4.9955921245959445,
|
173 |
+
"grad_norm": 0.00024289640714414418,
|
174 |
+
"learning_rate": 2.501469723691946e-05,
|
175 |
+
"loss": 0.0012,
|
176 |
+
"step": 8500
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 4.99970614163973,
|
180 |
+
"eval_accuracy": 0.9988808865026674,
|
181 |
+
"eval_f1": 0.9406350667280257,
|
182 |
+
"eval_loss": 0.006314857862889767,
|
183 |
+
"eval_precision": 0.9419354838709677,
|
184 |
+
"eval_recall": 0.9393382352941176,
|
185 |
+
"eval_runtime": 15.9896,
|
186 |
+
"eval_samples_per_second": 425.713,
|
187 |
+
"eval_steps_per_second": 53.222,
|
188 |
+
"step": 8507
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 5.289450484866294,
|
192 |
+
"grad_norm": 0.0022946298122406006,
|
193 |
+
"learning_rate": 2.3544973544973546e-05,
|
194 |
+
"loss": 0.0014,
|
195 |
+
"step": 9000
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 5.583308845136644,
|
199 |
+
"grad_norm": 0.0001970727025764063,
|
200 |
+
"learning_rate": 2.2075249853027632e-05,
|
201 |
+
"loss": 0.0008,
|
202 |
+
"step": 9500
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 5.877167205406994,
|
206 |
+
"grad_norm": 1.1225332021713257,
|
207 |
+
"learning_rate": 2.0605526161081718e-05,
|
208 |
+
"loss": 0.0007,
|
209 |
+
"step": 10000
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 6.0,
|
213 |
+
"eval_accuracy": 0.9989426780454649,
|
214 |
+
"eval_f1": 0.9480401093892434,
|
215 |
+
"eval_loss": 0.0047547053545713425,
|
216 |
+
"eval_precision": 0.9403254972875226,
|
217 |
+
"eval_recall": 0.9558823529411765,
|
218 |
+
"eval_runtime": 15.7168,
|
219 |
+
"eval_samples_per_second": 433.104,
|
220 |
+
"eval_steps_per_second": 54.146,
|
221 |
+
"step": 10209
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 6.171025565677343,
|
225 |
+
"grad_norm": 0.0004107556596864015,
|
226 |
+
"learning_rate": 1.91358024691358e-05,
|
227 |
+
"loss": 0.0005,
|
228 |
+
"step": 10500
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 6.464883925947693,
|
232 |
+
"grad_norm": 1.6069244146347046,
|
233 |
+
"learning_rate": 1.766607877718989e-05,
|
234 |
+
"loss": 0.0005,
|
235 |
+
"step": 11000
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 6.758742286218043,
|
239 |
+
"grad_norm": 0.00012789235915988684,
|
240 |
+
"learning_rate": 1.6196355085243976e-05,
|
241 |
+
"loss": 0.0005,
|
242 |
+
"step": 11500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 6.99970614163973,
|
246 |
+
"eval_accuracy": 0.9989220808645324,
|
247 |
+
"eval_f1": 0.9445983379501385,
|
248 |
+
"eval_loss": 0.00655418960377574,
|
249 |
+
"eval_precision": 0.9489795918367347,
|
250 |
+
"eval_recall": 0.9402573529411765,
|
251 |
+
"eval_runtime": 15.8136,
|
252 |
+
"eval_samples_per_second": 430.452,
|
253 |
+
"eval_steps_per_second": 53.814,
|
254 |
+
"step": 11910
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 7.052600646488393,
|
258 |
+
"grad_norm": 0.00015387983876280487,
|
259 |
+
"learning_rate": 1.472663139329806e-05,
|
260 |
+
"loss": 0.0002,
|
261 |
+
"step": 12000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 7.346459006758742,
|
265 |
+
"grad_norm": 0.00010029759141616523,
|
266 |
+
"learning_rate": 1.3256907701352148e-05,
|
267 |
+
"loss": 0.0002,
|
268 |
+
"step": 12500
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 7.640317367029092,
|
272 |
+
"grad_norm": 9.027074702316895e-05,
|
273 |
+
"learning_rate": 1.1787184009406232e-05,
|
274 |
+
"loss": 0.0002,
|
275 |
+
"step": 13000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 7.934175727299442,
|
279 |
+
"grad_norm": 8.488987077726051e-05,
|
280 |
+
"learning_rate": 1.0317460317460318e-05,
|
281 |
+
"loss": 0.0002,
|
282 |
+
"step": 13500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 8.0,
|
286 |
+
"eval_accuracy": 0.9990319324961724,
|
287 |
+
"eval_f1": 0.95077484047402,
|
288 |
+
"eval_loss": 0.0058256350457668304,
|
289 |
+
"eval_precision": 0.9430379746835443,
|
290 |
+
"eval_recall": 0.9586397058823529,
|
291 |
+
"eval_runtime": 15.7444,
|
292 |
+
"eval_samples_per_second": 432.344,
|
293 |
+
"eval_steps_per_second": 54.051,
|
294 |
+
"step": 13612
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 8.22803408756979,
|
298 |
+
"grad_norm": 0.0003942732000723481,
|
299 |
+
"learning_rate": 8.847736625514404e-06,
|
300 |
+
"loss": 0.0002,
|
301 |
+
"step": 14000
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 8.521892447840141,
|
305 |
+
"grad_norm": 0.006602809764444828,
|
306 |
+
"learning_rate": 7.37801293356849e-06,
|
307 |
+
"loss": 0.0001,
|
308 |
+
"step": 14500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 8.81575080811049,
|
312 |
+
"grad_norm": 8.021829853532836e-05,
|
313 |
+
"learning_rate": 5.908289241622575e-06,
|
314 |
+
"loss": 0.0001,
|
315 |
+
"step": 15000
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 8.999706141639729,
|
319 |
+
"eval_accuracy": 0.9990250667691949,
|
320 |
+
"eval_f1": 0.9494305239179955,
|
321 |
+
"eval_loss": 0.006341648753732443,
|
322 |
+
"eval_precision": 0.941282746160795,
|
323 |
+
"eval_recall": 0.9577205882352942,
|
324 |
+
"eval_runtime": 16.0762,
|
325 |
+
"eval_samples_per_second": 423.422,
|
326 |
+
"eval_steps_per_second": 52.936,
|
327 |
+
"step": 15313
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 9.10960916838084,
|
331 |
+
"grad_norm": 6.85813938616775e-05,
|
332 |
+
"learning_rate": 4.438565549676661e-06,
|
333 |
+
"loss": 0.0001,
|
334 |
+
"step": 15500
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 9.40346752865119,
|
338 |
+
"grad_norm": 0.0018187027890235186,
|
339 |
+
"learning_rate": 2.9688418577307467e-06,
|
340 |
+
"loss": 0.0001,
|
341 |
+
"step": 16000
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 9.69732588892154,
|
345 |
+
"grad_norm": 0.000292234995868057,
|
346 |
+
"learning_rate": 1.4991181657848325e-06,
|
347 |
+
"loss": 0.0,
|
348 |
+
"step": 16500
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 9.991184249191889,
|
352 |
+
"grad_norm": 6.29909336566925e-05,
|
353 |
+
"learning_rate": 2.9394473838918286e-08,
|
354 |
+
"loss": 0.0,
|
355 |
+
"step": 17000
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 9.997061416397296,
|
359 |
+
"eval_accuracy": 0.9990250667691949,
|
360 |
+
"eval_f1": 0.949771689497717,
|
361 |
+
"eval_loss": 0.006454338785260916,
|
362 |
+
"eval_precision": 0.9437386569872959,
|
363 |
+
"eval_recall": 0.9558823529411765,
|
364 |
+
"eval_runtime": 15.7656,
|
365 |
+
"eval_samples_per_second": 431.764,
|
366 |
+
"eval_steps_per_second": 53.978,
|
367 |
+
"step": 17010
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 9.997061416397296,
|
371 |
+
"step": 17010,
|
372 |
+
"total_flos": 6700358578825584.0,
|
373 |
+
"train_loss": 0.0023016003105682196,
|
374 |
+
"train_runtime": 3387.0101,
|
375 |
+
"train_samples_per_second": 80.378,
|
376 |
+
"train_steps_per_second": 5.022
|
377 |
+
}
|
378 |
+
],
|
379 |
+
"logging_steps": 500,
|
380 |
+
"max_steps": 17010,
|
381 |
+
"num_input_tokens_seen": 0,
|
382 |
+
"num_train_epochs": 10,
|
383 |
+
"save_steps": 500,
|
384 |
+
"total_flos": 6700358578825584.0,
|
385 |
+
"train_batch_size": 4,
|
386 |
+
"trial_name": null,
|
387 |
+
"trial_params": null
|
388 |
+
}
|