ninagroot commited on
Commit
56d4540
·
verified ·
1 Parent(s): 49dd6df

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: 5.1844
17
 
18
  ## Model description
19
 
@@ -41,21 +41,23 @@ 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: 8
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 8.4263 | 0.98 | 7 | 8.5002 |
52
- | 7.2113 | 1.96 | 14 | 7.6702 |
53
- | 6.258 | 2.95 | 21 | 7.0704 |
54
- | 5.4942 | 3.93 | 28 | 6.4329 |
55
- | 4.7105 | 4.91 | 35 | 5.9264 |
56
- | 3.7794 | 5.89 | 42 | 5.5158 |
57
- | 3.18 | 6.88 | 49 | 5.3089 |
58
- | 2.5741 | 7.86 | 56 | 5.1844 |
 
 
59
 
60
 
61
  ### 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: 5.1685
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: 10
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 8.4647 | 0.98 | 7 | 8.5154 |
52
+ | 7.2112 | 1.96 | 14 | 7.6819 |
53
+ | 6.3283 | 2.95 | 21 | 6.9987 |
54
+ | 5.5163 | 3.93 | 28 | 6.4019 |
55
+ | 4.7022 | 4.91 | 35 | 5.8715 |
56
+ | 3.7692 | 5.89 | 42 | 5.4877 |
57
+ | 3.2137 | 6.88 | 49 | 5.2686 |
58
+ | 2.6388 | 8.0 | 57 | 5.1854 |
59
+ | 2.0768 | 8.98 | 64 | 5.1622 |
60
+ | 1.715 | 9.82 | 70 | 5.1685 |
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:637050ce7c3f38a4a41ee4376925419d7bb8b2726bce1be3d21ac305cb5c81e9
3
  size 1408774432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd114647cbb563ea25fbf2c4255d9af4bed9370abedbae25e480835dfdc6e95f
3
  size 1408774432
runs/Apr18_12-07-46_gcn45.local.snellius.surf.nl/events.out.tfevents.1713434874.gcn45.local.snellius.surf.nl.3637688.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb658402c6f01a7d5dad8748d3df89fbe39c94302e5d5a83597869d19f9316e
3
+ size 22060
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:128ff538f545a64a6518eb18a3ebf82610c01b0b910c020382e076d85cffc41e
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ced552914f9b88b0b5e623385178a62392bf44137987e9608078e98983e24d
3
  size 4984