Hugging Face's logo

ninagroot
/
Llama-360M-ORIGINAL

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
ninagroot commited on
Commit
9866095
·
verified ·
1 Parent(s): e7a740c

ninagroot/Llama-360M

Browse files
Files changed (4) hide show
  1. README.md +20 -38
  2. model.safetensors +1 -1
  3. runs/Apr22_21-01-14_gcn12.local.snellius.surf.nl/events.out.tfevents.1713812489.gcn12.local.snellius.surf.nl.3550372.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 4.9792
17
 
18
  ## Model description
19
 
@@ -41,49 +41,31 @@ The following hyperparameters were used during training:
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 50
44
- - num_epochs: 40
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 8.5497 | 0.89 | 2 | 8.5052 |
52
- | 8.1931 | 1.78 | 4 | 8.1997 |
53
- | 7.6129 | 2.67 | 6 | 7.7377 |
54
- | 6.8911 | 4.0 | 9 | 7.1268 |
55
- | 6.5051 | 4.89 | 11 | 6.8545 |
56
- | 6.2169 | 5.78 | 13 | 6.6684 |
57
- | 5.9195 | 6.67 | 15 | 6.4750 |
58
- | 5.5126 | 8.0 | 18 | 6.1687 |
59
- | 5.3062 | 8.89 | 20 | 6.0107 |
60
- | 4.9111 | 9.78 | 22 | 5.8687 |
61
- | 4.7431 | 10.67 | 24 | 5.6626 |
62
- | 4.2334 | 12.0 | 27 | 5.4330 |
63
- | 4.0508 | 12.89 | 29 | 5.1847 |
64
- | 3.7627 | 13.78 | 31 | 5.0201 |
65
- | 3.4304 | 14.67 | 33 | 4.9383 |
66
- | 3.101 | 16.0 | 36 | 4.9051 |
67
- | 2.889 | 16.89 | 38 | 4.8583 |
68
- | 2.5785 | 17.78 | 40 | 4.8899 |
69
- | 2.2328 | 18.67 | 42 | 4.8363 |
70
- | 1.875 | 20.0 | 45 | 4.8183 |
71
- | 1.5514 | 20.89 | 47 | 4.8539 |
72
- | 1.1894 | 21.78 | 49 | 4.9134 |
73
- | 0.9224 | 22.67 | 51 | 4.8557 |
74
- | 0.6526 | 24.0 | 54 | 4.9283 |
75
- | 0.49 | 24.89 | 56 | 5.0074 |
76
- | 0.3634 | 25.78 | 58 | 4.9522 |
77
- | 0.2674 | 26.67 | 60 | 5.0044 |
78
- | 0.2052 | 28.0 | 63 | 4.9431 |
79
- | 0.166 | 28.89 | 65 | 4.9770 |
80
- | 0.1323 | 29.78 | 67 | 4.9768 |
81
- | 0.1059 | 30.67 | 69 | 4.9760 |
82
- | 0.0858 | 32.0 | 72 | 4.9849 |
83
- | 0.079 | 32.89 | 74 | 4.9828 |
84
- | 0.0687 | 33.78 | 76 | 4.9798 |
85
- | 0.0636 | 34.67 | 78 | 4.9792 |
86
- | 0.061 | 35.56 | 80 | 4.9792 |
87
 
88
 
89
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 4.8426
17
 
18
  ## Model description
19
 
 
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 50
44
+ - num_epochs: 20
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 8.5997 | 0.89 | 2 | 8.5409 |
52
+ | 8.2818 | 1.78 | 4 | 8.2523 |
53
+ | 7.6582 | 2.67 | 6 | 7.8134 |
54
+ | 6.881 | 4.0 | 9 | 7.1270 |
55
+ | 6.4599 | 4.89 | 11 | 6.8434 |
56
+ | 6.1818 | 5.78 | 13 | 6.6395 |
57
+ | 5.8836 | 6.67 | 15 | 6.4502 |
58
+ | 5.5042 | 8.0 | 18 | 6.1589 |
59
+ | 5.2565 | 8.89 | 20 | 5.9815 |
60
+ | 4.8638 | 9.78 | 22 | 5.8434 |
61
+ | 4.6811 | 10.67 | 24 | 5.6290 |
62
+ | 4.162 | 12.0 | 27 | 5.3371 |
63
+ | 3.9392 | 12.89 | 29 | 5.1585 |
64
+ | 3.6738 | 13.78 | 31 | 5.0040 |
65
+ | 3.3264 | 14.67 | 33 | 4.9210 |
66
+ | 2.9917 | 16.0 | 36 | 4.8846 |
67
+ | 2.7623 | 16.89 | 38 | 4.8758 |
68
+ | 2.478 | 17.78 | 40 | 4.8426 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:218c35ebb9d82f55932847541e4948912e899accf4fb246b2ee81d3d446c15c4
3
  size 1344213240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11db9296555813830fcd05a0b6549211fa3a57ce1671fdbf1e01cc612e245a51
3
  size 1344213240
runs/Apr22_21-01-14_gcn12.local.snellius.surf.nl/events.out.tfevents.1713812489.gcn12.local.snellius.surf.nl.3550372.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e797e87a2ec2ae43df99a86d787baf80cac35b12b8467f5ab1200b43c710f342
3
+ size 17977
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e3362fa68c5ab8d42f5ff87b9d3459feb3cbd9664fec82296692784cc7b67c7
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f85b83857ad58d44e98a7d2bf3c2e0558f37a2fdf1a6147d234cce95d1982e17
3
  size 4984