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
e0212c7
·
verified ·
1 Parent(s): 13c128c

ninagroot/Llama-360Mtest

Browse files
Files changed (10) hide show
  1. README.md +17 -17
  2. config.json +2 -2
  3. generation_config.json +1 -1
  4. merges.txt +0 -0
  5. model.safetensors +2 -2
  6. runs/Mar21_14-19-37_gcn7.local.snellius.surf.nl/events.out.tfevents.1711027186.gcn7.local.snellius.surf.nl.2387174.0 +3 -0
  7. special_tokens_map.json +7 -1
  8. tokenizer_config.json +4 -26
  9. training_args.bin +1 -1
  10. 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: 4.7211
17
 
18
  ## Model description
19
 
@@ -32,7 +32,7 @@ More information needed
32
  ### Training hyperparameters
33
 
34
  The following hyperparameters were used during training:
35
- - learning_rate: 3e-05
36
  - train_batch_size: 1
37
  - eval_batch_size: 8
38
  - seed: 42
@@ -48,21 +48,21 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 10.8127 | 0.98 | 41 | 10.5984 |
52
- | 9.6409 | 1.98 | 83 | 9.0771 |
53
- | 8.3725 | 2.99 | 125 | 8.0192 |
54
- | 7.2983 | 3.99 | 167 | 7.0163 |
55
- | 6.408 | 4.99 | 209 | 6.2115 |
56
- | 5.4886 | 5.99 | 251 | 5.4663 |
57
- | 4.8987 | 7.0 | 293 | 5.1240 |
58
- | 4.4918 | 8.0 | 335 | 4.9146 |
59
- | 4.2381 | 8.98 | 376 | 4.8076 |
60
- | 4.0984 | 9.98 | 418 | 4.7645 |
61
- | 3.9135 | 10.99 | 460 | 4.7195 |
62
- | 3.6736 | 11.99 | 502 | 4.7150 |
63
- | 3.467 | 12.99 | 544 | 4.7175 |
64
- | 3.4323 | 13.99 | 586 | 4.7194 |
65
- | 3.443 | 14.69 | 615 | 4.7211 |
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: 4.4066
17
 
18
  ## Model description
19
 
 
32
  ### Training hyperparameters
33
 
34
  The following hyperparameters were used during training:
35
+ - learning_rate: 0.0003
36
  - train_batch_size: 1
37
  - eval_batch_size: 8
38
  - seed: 42
 
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
config.json CHANGED
@@ -15,7 +15,7 @@
15
  "num_attention_heads": 8,
16
  "num_hidden_layers": 24,
17
  "num_key_value_heads": 8,
18
- "pad_token_id": 50256,
19
  "pretraining_tp": 1,
20
  "rms_norm_eps": 1e-06,
21
  "rope_scaling": null,
@@ -24,5 +24,5 @@
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.37.2",
26
  "use_cache": true,
27
- "vocab_size": 50257
28
  }
 
15
  "num_attention_heads": 8,
16
  "num_hidden_layers": 24,
17
  "num_key_value_heads": 8,
18
+ "pad_token_id": 0,
19
  "pretraining_tp": 1,
20
  "rms_norm_eps": 1e-06,
21
  "rope_scaling": null,
 
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.37.2",
26
  "use_cache": true,
27
+ "vocab_size": 4312
28
  }
generation_config.json CHANGED
@@ -2,6 +2,6 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "pad_token_id": 50256,
6
  "transformers_version": "4.37.2"
7
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
  "transformers_version": "4.37.2"
7
  }
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 sha256:52c8d6589ac866b90c44e5b803d259a7ee96f9f9029f707aa7db6e82b4515797
3
- size 1720553864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c1fe6f7d2437c2bafc14f73fde089a7b787a9de39c6d9b251e0f45d3dad955
3
+ size 1344172280
runs/Mar21_14-19-37_gcn7.local.snellius.surf.nl/events.out.tfevents.1711027186.gcn7.local.snellius.surf.nl.2387174.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e98aa76f66cf91ee9f810b47e7b86d7e7453e0a328b397f5b569aecf19ea7277
3
+ size 13890
special_tokens_map.json CHANGED
@@ -2,5 +2,11 @@
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
  "pad_token": "<pad>",
5
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
6
  }
 
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
  }
tokenizer_config.json CHANGED
@@ -1,34 +1,11 @@
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
@@ -37,6 +14,7 @@
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",
 
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
  "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",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6930c0ab087b6ba724e4cf9b2bcb7b1cd8afe2a296b2b6ad30397ad33891d6cf
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13366bfb195d096cd3184a397ce800d616db058f4a3641146de48e5a915eec0
3
  size 4728
vocab.json CHANGED
The diff for this file is too large to render. See raw diff