ninagroot commited on
Commit
f7009af
·
verified ·
1 Parent(s): 9dc88e6

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: 3.5144
17
 
18
  ## Model description
19
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 5.4376 | 0.99 | 45 | 4.6269 |
52
- | 3.5916 | 2.0 | 91 | 3.7375 |
53
- | 2.7508 | 2.97 | 135 | 3.5144 |
54
 
55
 
56
  ### 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: 3.3102
17
 
18
  ## Model description
19
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 5.418 | 0.99 | 49 | 4.3687 |
52
+ | 3.5953 | 2.0 | 99 | 3.6199 |
53
+ | 2.516 | 2.97 | 147 | 3.3102 |
54
 
55
 
56
  ### Framework versions
config.json CHANGED
@@ -15,7 +15,7 @@
15
  "n_inner": null,
16
  "n_layer": 24,
17
  "n_positions": 256,
18
- "pad_token_id": 50256,
19
  "reorder_and_upcast_attn": false,
20
  "resid_pdrop": 0.0,
21
  "scale_attn_by_inverse_layer_idx": false,
@@ -28,5 +28,5 @@
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.39.1",
30
  "use_cache": true,
31
- "vocab_size": 50257
32
  }
 
15
  "n_inner": null,
16
  "n_layer": 24,
17
  "n_positions": 256,
18
+ "pad_token_id": 0,
19
  "reorder_and_upcast_attn": false,
20
  "resid_pdrop": 0.0,
21
  "scale_attn_by_inverse_layer_idx": false,
 
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.39.1",
30
  "use_cache": true,
31
+ "vocab_size": 32000
32
  }
generation_config.json CHANGED
@@ -2,6 +2,6 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
- "pad_token_id": 50256,
6
  "transformers_version": "4.39.1"
7
  }
 
2
  "_from_model_config": true,
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:edcdc2e8b934d6e5f57aec20c8665204d854e298d6bf9963a83ebea2ce4d8417
3
- size 3030220576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43fc797fdeafe2a712b7042be287a3bfccaa8333d2040b7905a200a1f33955b7
3
+ size 2918049568
runs/Apr10_10-47-27_gcn10.local.snellius.surf.nl/events.out.tfevents.1712738857.gcn10.local.snellius.surf.nl.241513.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5d027284527755fa9e1a8f26e6adeb836f5401804979b1ac9ce7d7907b38b3d
3
+ size 7289
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67652905ed07950025ae0f17f985e23ba59ec1ae0e4cf668a1d90b4c0fa93ff3
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d537fb716c983e38cc2bd8d5326c5cac4a21efff3a0a19129c0cf7eb13cf3f
3
  size 4984