ninagroot commited on
Commit
613aa3c
·
verified ·
1 Parent(s): 2ce4e90

ninagroot/GPT2-705Mtest

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: 4.3277
17
 
18
  ## Model description
19
 
@@ -48,17 +48,17 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 5.8849 | 1.0 | 138 | 5.5972 |
52
- | 5.0533 | 2.0 | 276 | 4.9053 |
53
- | 4.0659 | 3.0 | 414 | 4.5644 |
54
- | 4.0541 | 4.0 | 552 | 4.4225 |
55
- | 3.8361 | 5.0 | 690 | 4.3304 |
56
- | 3.5307 | 6.0 | 828 | 4.3277 |
57
 
58
 
59
  ### Framework versions
60
 
61
- - Transformers 4.37.2
62
  - Pytorch 2.1.2+cu121
63
  - Datasets 2.16.1
64
  - Tokenizers 0.15.0
 
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: 3.6575
17
 
18
  ## Model description
19
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 2.9814 | 1.0 | 786 | 3.7914 |
52
+ | 2.5963 | 2.0 | 1572 | 3.6927 |
53
+ | 2.3478 | 3.0 | 2358 | 3.7172 |
54
+ | 2.0341 | 4.0 | 3144 | 3.6845 |
55
+ | 1.7373 | 5.0 | 3930 | 3.6596 |
56
+ | 1.7065 | 6.0 | 4716 | 3.6575 |
57
 
58
 
59
  ### Framework versions
60
 
61
+ - Transformers 4.39.1
62
  - Pytorch 2.1.2+cu121
63
  - Datasets 2.16.1
64
  - Tokenizers 0.15.0
config.json CHANGED
@@ -26,7 +26,7 @@
26
  "summary_type": "cls_index",
27
  "summary_use_proj": true,
28
  "torch_dtype": "float32",
29
- "transformers_version": "4.37.2",
30
  "use_cache": true,
31
- "vocab_size": 4312
32
  }
 
26
  "summary_type": "cls_index",
27
  "summary_use_proj": true,
28
  "torch_dtype": "float32",
29
+ "transformers_version": "4.39.1",
30
  "use_cache": true,
31
+ "vocab_size": 32000
32
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.37.2"
7
  }
 
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.39.1"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f400724a6e0d3898b884969758b48524c91c76bd4046072ce4e2c350645c075
3
- size 2747934496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c91e31860b19345b05e0f1e9e1ba2de97ffc56b229cb792f4542af9b151e2af
3
+ size 2918049568
runs/Apr05_14-54-56_gcn33.local.snellius.surf.nl/events.out.tfevents.1712321705.gcn33.local.snellius.surf.nl.3713920.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b838993b4bac0f3f173cb6860a746350da5b1faa31a15da1c4b0969863ce6d8e
3
+ size 56220
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf71524b3c83674824e3d16b3d014431c3ea8d8433979f72682c2eefae6d82b6
3
- size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa0847ab599c58a1133dac29dd7ae134718e1285515ee60a80d4d30e0cb92086
3
+ size 4984