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
c72e4b5
·
verified ·
1 Parent(s): e0212c7

ninagroot/Llama-360Mtest

Browse files
Files changed (8) hide show
  1. README.md +12 -17
  2. merges.txt +0 -0
  3. model.safetensors +1 -1
  4. runs/Mar21_14-29-49_gcn49.local.snellius.surf.nl/events.out.tfevents.1711027802.gcn49.local.snellius.surf.nl.4179046.0 +3 -0
  5. special_tokens_map.json +1 -7
  6. tokenizer_config.json +26 -4
  7. training_args.bin +1 -1
  8. vocab.json +0 -0
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: 4.4066
17
 
18
  ## Model description
19
 
@@ -41,28 +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: 300
44
- - num_epochs: 15
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 7.1842 | 0.99 | 44 | 6.6664 |
52
- | 5.6972 | 1.99 | 88 | 5.4155 |
53
- | 4.8124 | 2.98 | 132 | 4.6722 |
54
- | 4.1773 | 4.0 | 177 | 4.4451 |
55
- | 3.6907 | 4.99 | 221 | 4.3309 |
56
- | 3.5861 | 5.99 | 265 | 4.2794 |
57
- | 3.3727 | 6.98 | 309 | 4.2343 |
58
- | 3.1369 | 8.0 | 354 | 4.2810 |
59
- | 2.7116 | 8.99 | 398 | 4.2828 |
60
- | 2.3491 | 9.99 | 442 | 4.3183 |
61
- | 2.0411 | 10.98 | 486 | 4.3084 |
62
- | 1.5302 | 12.0 | 531 | 4.3548 |
63
- | 1.1022 | 12.99 | 575 | 4.3852 |
64
- | 0.8591 | 13.99 | 619 | 4.4058 |
65
- | 0.7952 | 14.92 | 660 | 4.4066 |
66
 
67
 
68
  ### 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: 4.1915
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: 10
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 7.042 | 0.99 | 44 | 6.5393 |
52
+ | 5.6951 | 1.99 | 88 | 5.4631 |
53
+ | 4.7481 | 2.98 | 132 | 4.6474 |
54
+ | 4.1761 | 4.0 | 177 | 4.4405 |
55
+ | 3.6565 | 4.99 | 221 | 4.3291 |
56
+ | 3.5648 | 5.99 | 265 | 4.2850 |
57
+ | 3.3644 | 6.98 | 309 | 4.2276 |
58
+ | 3.1299 | 8.0 | 354 | 4.2050 |
59
+ | 2.5705 | 8.99 | 398 | 4.2062 |
60
+ | 2.1843 | 9.94 | 440 | 4.1915 |
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78c1fe6f7d2437c2bafc14f73fde089a7b787a9de39c6d9b251e0f45d3dad955
3
  size 1344172280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75005945ce406a49db1b8b4b9aef520f33dd864987fe79a782192a532bf8d76b
3
  size 1344172280
runs/Mar21_14-29-49_gcn49.local.snellius.surf.nl/events.out.tfevents.1711027802.gcn49.local.snellius.surf.nl.4179046.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0225f2bacaf411f636f8bdd210858899d173f444539fe2aec26d8e2c0b05ae85
3
+ size 10809
special_tokens_map.json CHANGED
@@ -2,11 +2,5 @@
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
  "pad_token": "<pad>",
5
- "unk_token": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
- }
12
  }
 
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
  "pad_token": "<pad>",
5
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
6
  }
tokenizer_config.json CHANGED
@@ -1,11 +1,34 @@
1
  {
2
- "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
- "50256": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "content": "<|endoftext|>",
7
  "lstrip": false,
8
- "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
@@ -14,7 +37,6 @@
14
  "bos_token": "<s>",
15
  "clean_up_tokenization_spaces": true,
16
  "eos_token": "</s>",
17
- "errors": "replace",
18
  "model_max_length": 100,
19
  "pad_token": "<pad>",
20
  "tokenizer_class": "GPT2Tokenizer",
 
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "4312": {
29
  "content": "<|endoftext|>",
30
  "lstrip": false,
31
+ "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
 
37
  "bos_token": "<s>",
38
  "clean_up_tokenization_spaces": true,
39
  "eos_token": "</s>",
 
40
  "model_max_length": 100,
41
  "pad_token": "<pad>",
42
  "tokenizer_class": "GPT2Tokenizer",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f13366bfb195d096cd3184a397ce800d616db058f4a3641146de48e5a915eec0
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8087606d28ebab0c1abebab447a0ae1e9c17fda4ef368b96a83e8f2e6950e66
3
  size 4728
vocab.json CHANGED
The diff for this file is too large to render. See raw diff