Hugging Face's logo

timaeus
/
gpt-2-small

Safetensors
Model card Files Community
svwingerden georgeyw commited on
Commit
6ed6502
·
verified ·
0 Parent(s):

Duplicate from georgeyw/gpt-2-small

Browse files

Co-authored-by: George Wang <[email protected]>

This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +35 -0
  2. checkpoint-100/config.json +31 -0
  3. checkpoint-100/model.safetensors +3 -0
  4. checkpoint-100/training_args.bin +3 -0
  5. checkpoint-1000/config.json +31 -0
  6. checkpoint-1000/model.safetensors +3 -0
  7. checkpoint-1000/training_args.bin +3 -0
  8. checkpoint-10000/config.json +31 -0
  9. checkpoint-10000/model.safetensors +3 -0
  10. checkpoint-10000/training_args.bin +3 -0
  11. checkpoint-10100/config.json +31 -0
  12. checkpoint-10100/model.safetensors +3 -0
  13. checkpoint-10100/training_args.bin +3 -0
  14. checkpoint-10200/config.json +31 -0
  15. checkpoint-10200/model.safetensors +3 -0
  16. checkpoint-10200/training_args.bin +3 -0
  17. checkpoint-10300/config.json +31 -0
  18. checkpoint-10300/model.safetensors +3 -0
  19. checkpoint-10300/training_args.bin +3 -0
  20. checkpoint-10400/config.json +31 -0
  21. checkpoint-10400/model.safetensors +3 -0
  22. checkpoint-10400/training_args.bin +3 -0
  23. checkpoint-10500/config.json +31 -0
  24. checkpoint-10500/model.safetensors +3 -0
  25. checkpoint-10500/training_args.bin +3 -0
  26. checkpoint-10600/config.json +31 -0
  27. checkpoint-10600/model.safetensors +3 -0
  28. checkpoint-10600/training_args.bin +3 -0
  29. checkpoint-10700/config.json +31 -0
  30. checkpoint-10700/model.safetensors +3 -0
  31. checkpoint-10700/training_args.bin +3 -0
  32. checkpoint-10800/config.json +31 -0
  33. checkpoint-10800/model.safetensors +3 -0
  34. checkpoint-10800/training_args.bin +3 -0
  35. checkpoint-10900/config.json +31 -0
  36. checkpoint-10900/model.safetensors +3 -0
  37. checkpoint-10900/training_args.bin +3 -0
  38. checkpoint-1100/config.json +31 -0
  39. checkpoint-1100/model.safetensors +3 -0
  40. checkpoint-1100/training_args.bin +3 -0
  41. checkpoint-11000/config.json +31 -0
  42. checkpoint-11000/model.safetensors +3 -0
  43. checkpoint-11000/training_args.bin +3 -0
  44. checkpoint-11100/config.json +31 -0
  45. checkpoint-11100/model.safetensors +3 -0
  46. checkpoint-11100/training_args.bin +3 -0
  47. checkpoint-11200/config.json +31 -0
  48. checkpoint-11200/model.safetensors +3 -0
  49. checkpoint-11200/training_args.bin +3 -0
  50. checkpoint-11300/config.json +31 -0
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
checkpoint-100/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e56f5b3dd4afc21190625e190827309ea556064666d746669af2409569127a
3
+ size 324662984
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-1000/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a56aaeb73fd5a850495c644f8711e0fd2770f3e773c4f808af9f7d9b344fd53f
3
+ size 324662984
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-10000/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-10000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:601eb51db6fa707eba37f9f216c6ffc9ef4e32ec527c68a765795e43bc8fb8d3
3
+ size 324662984
checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-10100/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-10100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27a558976d50677b7e1442ead7e2855bff7b5b876d504ec9b153a3109d85e196
3
+ size 324662984
checkpoint-10100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-10200/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-10200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2d9e0280973fece6e5e52c31bebb9e5f505e3445f4e067cffe0770508672937
3
+ size 324662984
checkpoint-10200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-10300/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-10300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b2881cddcf530c4f56798b9d9f54ebd1c448c3c3a19ecbe5fabe76f0be128c
3
+ size 324662984
checkpoint-10300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-10400/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-10400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0afbf78250eeb4ad3b4f622ea40aeac0e6cd63d06d234cbd22308fb29b9f8c
3
+ size 324662984
checkpoint-10400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-10500/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-10500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed06b43dd3d7554cc68e351367ce5eead72a165a405ed21daa98a55d0de06463
3
+ size 324662984
checkpoint-10500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-10600/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-10600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf1409774fbd0059a81253e6a1783a2666f1794181fd01ed2a923cdf762b951
3
+ size 324662984
checkpoint-10600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-10700/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-10700/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c0d6f0f34b0e72b1f398d5350a1418d32daa962eada990b846d3d3aba240342
3
+ size 324662984
checkpoint-10700/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-10800/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-10800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:241a4ebaaafe542b303716ff632a8e2009aaa45efa2db89340bef14f7e92670f
3
+ size 324662984
checkpoint-10800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-10900/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-10900/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:842701f4fbad38879acacd251e3aee93cc1f8967942effddfa9a5ebf7576a45e
3
+ size 324662984
checkpoint-10900/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-1100/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-1100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0f0e5d1fdece8c968bb138920e72a81d0166e2538ade4d8d74175b147ae605
3
+ size 324662984
checkpoint-1100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-11000/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-11000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b62d3a64f76e93d93111b2c51de044e3aee7043289749e9c1cdcd31ac0ff37ee
3
+ size 324662984
checkpoint-11000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-11100/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-11100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29764862ba130e00fbec38ec91af863d3b1b57f42f29df49e93536cfd3a7ce37
3
+ size 324662984
checkpoint-11100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-11200/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }
checkpoint-11200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e08e950a505b355d9602f3c47d9eea94807466658b5a615ea3491faeb966a1f
3
+ size 324662984
checkpoint-11200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520
checkpoint-11300/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "georgeyw/gpt-2-small-init-seed-5",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "layer_norm_epsilon": 1e-05,
18
+ "max_position_embeddings": 1024,
19
+ "model_type": "gpt_neox",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "rope_scaling": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.38.2",
28
+ "use_cache": true,
29
+ "use_parallel_residual": true,
30
+ "vocab_size": 50304
31
+ }