Hugging Face's logo

ninagroot
/
Llama-360M-RUN1

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
ninagroot commited on
Commit
82315ad
·
verified ·
1 Parent(s): dae006d

ninagroot/Llama-360Mtest

Browse files
Files changed (4) hide show
  1. README.md +9 -25
  2. model.safetensors +1 -1
  3. runs/Apr16_13-55-22_gcn38.local.snellius.surf.nl/events.out.tfevents.1713268532.gcn38.local.snellius.surf.nl.410094.0 +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: 5.4940
17
 
18
  ## Model description
19
 
@@ -33,41 +33,25 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.0003
36
- - train_batch_size: 8
37
  - eval_batch_size: 8
38
  - seed: 42
39
- - gradient_accumulation_steps: 4
40
- - total_train_batch_size: 32
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
- | 9.479 | 1.0 | 7 | 8.7145 |
52
- | 8.0855 | 2.0 | 14 | 7.4514 |
53
- | 6.1163 | 3.0 | 21 | 6.7073 |
54
- | 5.6369 | 4.0 | 28 | 6.1912 |
55
- | 4.5226 | 5.0 | 35 | 5.6228 |
56
- | 3.9429 | 6.0 | 42 | 5.2825 |
57
- | 3.6281 | 7.0 | 49 | 5.1522 |
58
- | 2.9972 | 8.0 | 56 | 5.1116 |
59
- | 2.6381 | 9.0 | 63 | 5.1819 |
60
- | 2.086 | 10.0 | 70 | 5.1975 |
61
- | 1.6887 | 11.0 | 77 | 5.2503 |
62
- | 1.4587 | 12.0 | 84 | 5.2902 |
63
- | 0.8906 | 13.0 | 91 | 5.3147 |
64
- | 0.6621 | 14.0 | 98 | 5.3620 |
65
- | 0.438 | 15.0 | 105 | 5.4429 |
66
- | 0.3238 | 16.0 | 112 | 5.4327 |
67
- | 0.2746 | 17.0 | 119 | 5.4741 |
68
- | 0.1768 | 18.0 | 126 | 5.4815 |
69
- | 0.158 | 19.0 | 133 | 5.4927 |
70
- | 0.1372 | 20.0 | 140 | 5.4940 |
71
 
72
 
73
  ### 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: 8.4754
17
 
18
  ## Model description
19
 
 
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.0003
36
+ - train_batch_size: 16
37
  - eval_batch_size: 8
38
  - seed: 42
39
+ - gradient_accumulation_steps: 8
40
+ - total_train_batch_size: 128
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: 7
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | No log | 0.57 | 1 | 9.6252 |
52
+ | No log | 1.71 | 3 | 9.4433 |
53
+ | 9.3421 | 2.86 | 5 | 9.0516 |
54
+ | 9.3421 | 4.0 | 7 | 8.4754 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec56ecee6ae3aaa98718619dbeb72270907a12d38795c0e946d91b16353bbafa
3
  size 1408774432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3375e53d7102dd3a275e1e4156ab7cbd98639869ac79a0b7425f36fabe7b518a
3
  size 1408774432
runs/Apr16_13-55-22_gcn38.local.snellius.surf.nl/events.out.tfevents.1713268532.gcn38.local.snellius.surf.nl.410094.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ea982d8ff8adda5e161530ee3d1e55d459ac51402dcacca808babdbff3ba72
3
+ size 6180
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93f56e97aea497cdde58cfc833feb9c2066279a2e9f2526583aca3325b8ace05
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3a4fed7955d1ec15847dd659018f1c7ef290604c2366c696a3092f87e5f84c
3
  size 4984