Hugging Face's logo

ninagroot
/
Llama-450M

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
ninagroot commited on
Commit
43b2483
·
verified ·
1 Parent(s): 24b277c

ninagroot/Llama-450M

Browse files
Files changed (4) hide show
  1. README.md +16 -38
  2. model.safetensors +1 -1
  3. runs/Apr22_12-29-10_gcn59.local.snellius.surf.nl/events.out.tfevents.1713781762.gcn59.local.snellius.surf.nl.2259150.0 +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: 5.3640
17
 
18
  ## Model description
19
 
@@ -41,49 +41,27 @@ 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
- | 8.6361 | 0.89 | 2 | 8.5417 |
52
- | 8.0877 | 1.78 | 4 | 8.1311 |
53
- | 7.2872 | 2.67 | 6 | 7.5663 |
54
- | 6.4202 | 4.0 | 9 | 6.9344 |
55
- | 5.9503 | 4.89 | 11 | 6.6943 |
56
- | 5.5025 | 5.78 | 13 | 6.4322 |
57
- | 5.1215 | 6.67 | 15 | 6.2306 |
58
- | 4.637 | 8.0 | 18 | 6.0048 |
59
- | 4.1326 | 8.89 | 20 | 5.8295 |
60
- | 3.7514 | 9.78 | 22 | 5.7679 |
61
- | 3.296 | 10.67 | 24 | 5.5661 |
62
- | 2.716 | 12.0 | 27 | 5.5157 |
63
- | 2.3207 | 12.89 | 29 | 5.3937 |
64
- | 1.8748 | 13.78 | 31 | 5.4251 |
65
- | 1.4214 | 14.67 | 33 | 5.3836 |
66
- | 1.0506 | 16.0 | 36 | 5.3606 |
67
- | 0.6948 | 16.89 | 38 | 5.4011 |
68
- | 0.4323 | 17.78 | 40 | 5.4518 |
69
- | 0.283 | 18.67 | 42 | 5.4008 |
70
- | 0.2449 | 20.0 | 45 | 5.3915 |
71
- | 0.1604 | 20.89 | 47 | 5.4076 |
72
- | 0.1215 | 21.78 | 49 | 5.4089 |
73
- | 0.1578 | 22.67 | 51 | 5.4804 |
74
- | 0.1656 | 24.0 | 54 | 5.3938 |
75
- | 0.159 | 24.89 | 56 | 5.3649 |
76
- | 0.094 | 25.78 | 58 | 5.3596 |
77
- | 0.0781 | 26.67 | 60 | 5.3267 |
78
- | 0.0772 | 28.0 | 63 | 5.3841 |
79
- | 0.0836 | 28.89 | 65 | 5.4028 |
80
- | 0.0616 | 29.78 | 67 | 5.3790 |
81
- | 0.0371 | 30.67 | 69 | 5.3636 |
82
- | 0.037 | 32.0 | 72 | 5.3607 |
83
- | 0.037 | 32.89 | 74 | 5.3625 |
84
- | 0.0342 | 33.78 | 76 | 5.3636 |
85
- | 0.0303 | 34.67 | 78 | 5.3640 |
86
- | 0.0287 | 35.56 | 80 | 5.3640 |
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: 5.3758
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: 15
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 8.6181 | 0.89 | 2 | 8.5302 |
52
+ | 8.1094 | 1.78 | 4 | 8.1630 |
53
+ | 7.3294 | 2.67 | 6 | 7.6121 |
54
+ | 6.3925 | 4.0 | 9 | 6.9573 |
55
+ | 5.9558 | 4.89 | 11 | 6.7168 |
56
+ | 5.5426 | 5.78 | 13 | 6.4826 |
57
+ | 5.16 | 6.67 | 15 | 6.2638 |
58
+ | 4.6423 | 8.0 | 18 | 6.0366 |
59
+ | 4.1416 | 8.89 | 20 | 5.7887 |
60
+ | 3.7696 | 9.78 | 22 | 5.6999 |
61
+ | 3.254 | 10.67 | 24 | 5.5623 |
62
+ | 2.6811 | 12.0 | 27 | 5.4521 |
63
+ | 2.2384 | 12.89 | 29 | 5.3798 |
64
+ | 1.9875 | 13.33 | 30 | 5.3758 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ae413f342aca44ebbc0f61078f97fdf828b7c850a0c2ae00ade540af60df766
3
  size 2875619784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5896153eace3ec70c419036cde870446ca935c3466f9c6f0e51b703cbc5c64b1
3
  size 2875619784
runs/Apr22_12-29-10_gcn59.local.snellius.surf.nl/events.out.tfevents.1713781762.gcn59.local.snellius.surf.nl.2259150.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a18724a1f6c76aef7f96d7e9151c249c11aec020e788618f25f61e30f0fa74
3
+ size 14845
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6e9d6cbdc34d70c6de96be3de548f534380541bdc3d82dcce3a4882538518b8
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4de35aa34987d37e77f9bcbe2c87a87d76e449c367565bbe69a24a7b36e05b2
3
  size 4984