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
47e1241
·
verified ·
1 Parent(s): e4e5318

ninagroot/Llama-360Mtest

Browse files
Files changed (4) hide show
  1. README.md +43 -26
  2. model.safetensors +1 -1
  3. runs/Apr17_11-29-46_gcn21.local.snellius.surf.nl/events.out.tfevents.1713346199.gcn21.local.snellius.surf.nl.35160.0 +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: 5.3116
17
 
18
  ## Model description
19
 
@@ -33,11 +33,11 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.0003
36
- - train_batch_size: 32
37
  - eval_batch_size: 8
38
  - seed: 42
39
  - gradient_accumulation_steps: 4
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
@@ -48,29 +48,46 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 9.6413 | 0.57 | 1 | 9.6052 |
52
- | 9.4769 | 1.71 | 3 | 9.4099 |
53
- | 8.7439 | 2.86 | 5 | 8.9775 |
54
- | 7.8497 | 4.0 | 7 | 8.3771 |
55
- | 7.4766 | 4.57 | 8 | 8.1367 |
56
- | 6.9952 | 5.71 | 10 | 7.7250 |
57
- | 6.6416 | 6.86 | 12 | 7.4427 |
58
- | 6.2883 | 8.0 | 14 | 7.1768 |
59
- | 6.1005 | 8.57 | 15 | 7.0533 |
60
- | 5.7404 | 9.71 | 17 | 6.8339 |
61
- | 5.4256 | 10.86 | 19 | 6.5861 |
62
- | 5.1676 | 12.0 | 21 | 6.4346 |
63
- | 5.0194 | 12.57 | 22 | 6.3089 |
64
- | 4.664 | 13.71 | 24 | 6.1123 |
65
- | 4.2274 | 14.86 | 26 | 5.9158 |
66
- | 3.9322 | 16.0 | 28 | 5.7166 |
67
- | 3.6973 | 16.57 | 29 | 5.6338 |
68
- | 3.4695 | 17.71 | 31 | 5.5249 |
69
- | 3.2858 | 18.86 | 33 | 5.4034 |
70
- | 2.9602 | 20.0 | 35 | 5.4233 |
71
- | 2.819 | 20.57 | 36 | 5.3921 |
72
- | 2.5548 | 21.71 | 38 | 5.4247 |
73
- | 2.2437 | 22.86 | 40 | 5.3116 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74
 
75
 
76
  ### 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: 5.8024
17
 
18
  ## Model description
19
 
 
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
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 8.5041 | 1.0 | 7 | 8.6380 |
52
+ | 6.6883 | 2.0 | 14 | 7.4371 |
53
+ | 5.9557 | 3.0 | 21 | 6.6954 |
54
+ | 4.8588 | 4.0 | 28 | 6.1892 |
55
+ | 4.4731 | 5.0 | 35 | 5.5921 |
56
+ | 3.6281 | 6.0 | 42 | 5.3513 |
57
+ | 2.9612 | 7.0 | 49 | 5.2090 |
58
+ | 2.802 | 8.0 | 56 | 5.1107 |
59
+ | 2.4916 | 9.0 | 63 | 5.1980 |
60
+ | 2.1409 | 10.0 | 70 | 5.1957 |
61
+ | 1.6778 | 11.0 | 77 | 5.2886 |
62
+ | 1.2634 | 12.0 | 84 | 5.3171 |
63
+ | 0.886 | 13.0 | 91 | 5.3896 |
64
+ | 0.6634 | 14.0 | 98 | 5.4225 |
65
+ | 0.4751 | 15.0 | 105 | 5.4527 |
66
+ | 0.3235 | 16.0 | 112 | 5.4897 |
67
+ | 0.2209 | 17.0 | 119 | 5.5317 |
68
+ | 0.179 | 18.0 | 126 | 5.5994 |
69
+ | 0.1267 | 19.0 | 133 | 5.5412 |
70
+ | 0.0678 | 20.0 | 140 | 5.6162 |
71
+ | 0.059 | 21.0 | 147 | 5.6587 |
72
+ | 0.0312 | 22.0 | 154 | 5.6621 |
73
+ | 0.0289 | 23.0 | 161 | 5.6768 |
74
+ | 0.0238 | 24.0 | 168 | 5.6965 |
75
+ | 0.0148 | 25.0 | 175 | 5.7041 |
76
+ | 0.0133 | 26.0 | 182 | 5.7436 |
77
+ | 0.0122 | 27.0 | 189 | 5.7582 |
78
+ | 0.0111 | 28.0 | 196 | 5.7673 |
79
+ | 0.0099 | 29.0 | 203 | 5.7776 |
80
+ | 0.0103 | 30.0 | 210 | 5.7868 |
81
+ | 0.0119 | 31.0 | 217 | 5.7928 |
82
+ | 0.0091 | 32.0 | 224 | 5.7955 |
83
+ | 0.0081 | 33.0 | 231 | 5.7970 |
84
+ | 0.0093 | 34.0 | 238 | 5.7987 |
85
+ | 0.0096 | 35.0 | 245 | 5.8000 |
86
+ | 0.0085 | 36.0 | 252 | 5.8012 |
87
+ | 0.0088 | 37.0 | 259 | 5.8019 |
88
+ | 0.0065 | 38.0 | 266 | 5.8023 |
89
+ | 0.0107 | 39.0 | 273 | 5.8024 |
90
+ | 0.0066 | 40.0 | 280 | 5.8024 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4d06ab39d612ccc08778ac3b8c56c398fe4432b0f11f78efb11f18ac3fe43d7
3
  size 1408774432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74228c349164d80ee62af7c29b63be54d60266aec8f44c532549eefe6da737dd
3
  size 1408774432
runs/Apr17_11-29-46_gcn21.local.snellius.surf.nl/events.out.tfevents.1713346199.gcn21.local.snellius.surf.nl.35160.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5058967043a9cebb432331cd299b84ca4a8520504f8817dc3063e0bfb3bce3ac
3
+ size 74237
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a82cbbba3d018e3891de5927be97d78b317b2d057b9154e10aba47406af05ced
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b31b00a75e81265b81970f32b5ebd7e524ba0b5a165a9ed33f3baada7f115907
3
  size 4984