ninagroot commited on
Commit
1989038
·
verified ·
1 Parent(s): 5d8801b

ninagroot/Llama-360Mtest

Browse files
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: 3.8269
17
 
18
  ## Model description
19
 
@@ -41,21 +41,15 @@ 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: 100
44
- - num_epochs: 8
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 2.9655 | 1.0 | 254 | 3.7658 |
52
- | 1.7363 | 2.0 | 509 | 3.5948 |
53
- | 0.9884 | 3.0 | 763 | 3.6899 |
54
- | 0.6078 | 4.0 | 1018 | 3.7297 |
55
- | 0.3566 | 5.0 | 1272 | 3.7598 |
56
- | 0.2182 | 6.0 | 1527 | 3.8006 |
57
- | 0.1633 | 7.0 | 1781 | 3.8219 |
58
- | 0.1284 | 7.98 | 2032 | 3.8269 |
59
 
60
 
61
  ### 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: 3.5128
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: 100
44
+ - num_epochs: 2
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 2.9191 | 1.0 | 254 | 3.7445 |
52
+ | 1.828 | 2.0 | 508 | 3.5128 |
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd82abd3133a184ba4773b3c6a75792665145cf367d5308fd529d07d7da1e95c
3
  size 1570992472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c31e469dafc14f5b44973fff506cb6b58c7e9a29212eca1a94b10698acd27e
3
  size 1570992472
runs/Apr02_16-38-15_gcn36.local.snellius.surf.nl/events.out.tfevents.1712068707.gcn36.local.snellius.surf.nl.1729376.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380d8369928ff546700ce9feb6f12afd293429b4318c79a7d98fb385d03bf24d
3
+ size 10709
tokenizer_config.json CHANGED
@@ -32,7 +32,7 @@
32
  "clean_up_tokenization_spaces": false,
33
  "eos_token": "</s>",
34
  "legacy": true,
35
- "model_max_length": 128,
36
  "pad_token": "<pad>",
37
  "sp_model_kwargs": {},
38
  "spaces_between_special_tokens": false,
 
32
  "clean_up_tokenization_spaces": false,
33
  "eos_token": "</s>",
34
  "legacy": true,
35
+ "model_max_length": 30,
36
  "pad_token": "<pad>",
37
  "sp_model_kwargs": {},
38
  "spaces_between_special_tokens": false,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e192133b205882b76e8d67aa6c28e4a7aece21d9df363db42b30a69b6cd47b7
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56176203a926a2239766a855e8a4c7e560543261d6afbdedcc1dfba1e0c75197
3
  size 4984