ninagroot commited on
Commit
c2b65a9
·
verified ·
1 Parent(s): 5bfc8f4

ninagroot/Llama-360Mtest

Browse files
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: 8.2764
17
 
18
  ## Model description
19
 
@@ -41,17 +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: 300
44
- - num_epochs: 4
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | No log | 0.89 | 2 | 8.5545 |
52
- | No log | 1.78 | 4 | 8.5018 |
53
- | No log | 2.67 | 6 | 8.4091 |
54
- | No log | 3.56 | 8 | 8.2764 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### 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: 5.9655
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: 300
44
+ - num_epochs: 20
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | No log | 0.89 | 2 | 8.5679 |
52
+ | No log | 1.78 | 4 | 8.5182 |
53
+ | No log | 2.67 | 6 | 8.4304 |
54
+ | No log | 4.0 | 9 | 8.2278 |
55
+ | No log | 4.89 | 11 | 8.0473 |
56
+ | No log | 5.78 | 13 | 7.8459 |
57
+ | No log | 6.67 | 15 | 7.6372 |
58
+ | No log | 8.0 | 18 | 7.3787 |
59
+ | 7.9918 | 8.89 | 20 | 7.1956 |
60
+ | 7.9918 | 9.78 | 22 | 7.0644 |
61
+ | 7.9918 | 10.67 | 24 | 6.9150 |
62
+ | 7.9918 | 12.0 | 27 | 6.7280 |
63
+ | 7.9918 | 12.89 | 29 | 6.5960 |
64
+ | 7.9918 | 13.78 | 31 | 6.4792 |
65
+ | 7.9918 | 14.67 | 33 | 6.3487 |
66
+ | 7.9918 | 16.0 | 36 | 6.1616 |
67
+ | 7.9918 | 16.89 | 38 | 6.0606 |
68
+ | 6.3677 | 17.78 | 40 | 5.9655 |
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8177d7dce9ccc7fe15c2f39e9889ac0b5a28059453f66da83d3a4ec1f938d295
3
  size 1344172280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd7d3b9032857420cb3030328c76375a6bb5f32b36c42f25f16f07a6eccf4255
3
  size 1344172280
runs/Mar20_14-33-09_gcn44.local.snellius.surf.nl/events.out.tfevents.1710941597.gcn44.local.snellius.surf.nl.624542.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef01474436e95c41e6f9a334f4e2e8bfd5beb5031218b65bf7e74bf851b18fe
3
+ size 9764
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1eac06fa6a81dfd6cee717c8e16104728e75f8a169ec4c91b67bba4b5245c90
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:854943628158b4953c8db55688afec58f9d4beac612540e46ff06bd58dd3e71c
3
  size 4728