ManojAlexender commited on
Commit
7047bc2
·
verified ·
1 Parent(s): e3d6650

End of training

Browse files
Files changed (2) hide show
  1. README.md +88 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - accuracy
6
+ - f1
7
+ - precision
8
+ - recall
9
+ model-index:
10
+ - name: Finetuned_Final_LM_200k_v2
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Finetuned_Final_LM_200k_v2
18
+
19
+ This model was trained from scratch on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.5769
22
+ - Accuracy: 0.8410
23
+ - F1: 0.8392
24
+ - Precision: 0.8573
25
+ - Recall: 0.8410
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 5e-05
45
+ - train_batch_size: 16
46
+ - eval_batch_size: 64
47
+ - seed: 42
48
+ - gradient_accumulation_steps: 2
49
+ - total_train_batch_size: 32
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_steps: 50
53
+ - num_epochs: 2
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
59
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
60
+ | 0.0074 | 0.08 | 500 | 1.2669 | 0.8482 | 0.8460 | 0.8695 | 0.8482 |
61
+ | 0.1731 | 0.16 | 1000 | 1.5018 | 0.8433 | 0.8411 | 0.8636 | 0.8433 |
62
+ | 0.2369 | 0.24 | 1500 | 2.0563 | 0.8486 | 0.8461 | 0.8721 | 0.8486 |
63
+ | 0.449 | 0.32 | 2000 | 2.4474 | 0.8323 | 0.8301 | 0.8511 | 0.8323 |
64
+ | 0.225 | 0.4 | 2500 | 2.1554 | 0.8471 | 0.8450 | 0.8662 | 0.8471 |
65
+ | 0.2479 | 0.48 | 3000 | 2.3559 | 0.8455 | 0.8438 | 0.8618 | 0.8455 |
66
+ | 0.2345 | 0.56 | 3500 | 2.3197 | 0.8440 | 0.8419 | 0.8639 | 0.8440 |
67
+ | 0.2424 | 0.64 | 4000 | 2.2472 | 0.8414 | 0.8396 | 0.8571 | 0.8414 |
68
+ | 0.1264 | 0.72 | 4500 | 2.3584 | 0.8418 | 0.8398 | 0.8599 | 0.8418 |
69
+ | 0.2699 | 0.8 | 5000 | 2.3153 | 0.8437 | 0.8419 | 0.8600 | 0.8437 |
70
+ | 0.1399 | 0.88 | 5500 | 2.3416 | 0.8471 | 0.8450 | 0.8665 | 0.8471 |
71
+ | 0.3039 | 0.96 | 6000 | 2.4308 | 0.8448 | 0.8429 | 0.8620 | 0.8448 |
72
+ | 0.0499 | 1.04 | 6500 | 2.5017 | 0.8448 | 0.8428 | 0.8628 | 0.8448 |
73
+ | 0.1455 | 1.12 | 7000 | 2.5024 | 0.8444 | 0.8425 | 0.8618 | 0.8444 |
74
+ | 0.3358 | 1.2 | 7500 | 2.3806 | 0.8425 | 0.8405 | 0.8609 | 0.8425 |
75
+ | 0.1951 | 1.28 | 8000 | 2.5782 | 0.8433 | 0.8415 | 0.8592 | 0.8433 |
76
+ | 0.2118 | 1.36 | 8500 | 2.5075 | 0.8429 | 0.8410 | 0.8597 | 0.8429 |
77
+ | 0.3137 | 1.44 | 9000 | 2.5662 | 0.8421 | 0.8403 | 0.8584 | 0.8421 |
78
+ | 0.1125 | 1.52 | 9500 | 2.5881 | 0.8425 | 0.8406 | 0.8602 | 0.8425 |
79
+ | 0.1198 | 1.6 | 10000 | 2.5321 | 0.8418 | 0.8400 | 0.8576 | 0.8418 |
80
+ | 0.2385 | 1.68 | 10500 | 2.5769 | 0.8410 | 0.8392 | 0.8573 | 0.8410 |
81
+
82
+
83
+ ### Framework versions
84
+
85
+ - Transformers 4.37.0
86
+ - Pytorch 2.1.0+cu121
87
+ - Datasets 2.16.1
88
+ - Tokenizers 0.15.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d43bc1cc4272a08f575bebd7f991337c14cd434270243569ec7fafa3f19bc159
3
  size 498615900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:373e947e5b7fe50e52477baff544adffbbb18f8c676247b149a30a543045188e
3
  size 498615900