Hugging Face's logo

georgeyw
/
gpt-2-small

Safetensors
Model card Files Community
georgeyw commited on
Commit
c02e950
·
verified ·
1 Parent(s): 47e28cc

Training in progress, step 14000, checkpoint

Browse files
Files changed (30) hide show
  1. checkpoint-13100/config.json +31 -0
  2. checkpoint-13100/model.safetensors +3 -0
  3. checkpoint-13100/training_args.bin +3 -0
  4. checkpoint-13200/config.json +31 -0
  5. checkpoint-13200/model.safetensors +3 -0
  6. checkpoint-13200/training_args.bin +3 -0
  7. checkpoint-13300/config.json +31 -0
  8. checkpoint-13300/model.safetensors +3 -0
  9. checkpoint-13300/training_args.bin +3 -0
  10. checkpoint-13400/config.json +31 -0
  11. checkpoint-13400/model.safetensors +3 -0
  12. checkpoint-13400/training_args.bin +3 -0
  13. checkpoint-13500/config.json +31 -0
  14. checkpoint-13500/model.safetensors +3 -0
  15. checkpoint-13500/training_args.bin +3 -0
  16. checkpoint-13600/config.json +31 -0
  17. checkpoint-13600/model.safetensors +3 -0
  18. checkpoint-13600/training_args.bin +3 -0
  19. checkpoint-13700/config.json +31 -0
  20. checkpoint-13700/model.safetensors +3 -0
  21. checkpoint-13700/training_args.bin +3 -0
  22. checkpoint-13800/config.json +31 -0
  23. checkpoint-13800/model.safetensors +3 -0
  24. checkpoint-13800/training_args.bin +3 -0
  25. checkpoint-13900/config.json +31 -0
  26. checkpoint-13900/model.safetensors +3 -0
  27. checkpoint-13900/training_args.bin +3 -0
  28. checkpoint-14000/config.json +31 -0
  29. checkpoint-14000/model.safetensors +3 -0
  30. checkpoint-14000/training_args.bin +3 -0
checkpoint-13100/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-13100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab134cc7d59feeddd0b7305dcf51e6eb6a0ca2b06812f5bb4e71d8450d26af24
3
+ size 324662984
checkpoint-13100/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-13200/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-13200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a63ef113fb8b2456632589376cf0bb652e35c6506e143c3af1df28769e11e51
3
+ size 324662984
checkpoint-13200/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-13300/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-13300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fe2952ea6b548ccd45635efbba5d2c97e7830013b09c91b6a351d23e793b3f7
3
+ size 324662984
checkpoint-13300/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-13400/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-13400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f608ec53530441d49d3169a68bd734192c72742ddb944d6b605b509139f10e01
3
+ size 324662984
checkpoint-13400/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-13500/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-13500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748c13a00e6f44758f9756023b746ba3a3d94c21a9a919e3e580fe00c872c5e3
3
+ size 324662984
checkpoint-13500/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-13600/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-13600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e84c7158de425286a4f5d86486a87a28b65d678561ff38b84b12f766ae6a6d
3
+ size 324662984
checkpoint-13600/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-13700/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-13700/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee973e21e1df0fa6b321b83a21975a00bd53fbd8766fd4da6b33aa44c074db81
3
+ size 324662984
checkpoint-13700/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-13800/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-13800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a2a0449a2a9c089c5d377a7b8df808be37ff2296d51435d519d602600178af0
3
+ size 324662984
checkpoint-13800/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-13900/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-13900/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af2b6fbb9bf5f09c347fedaaf26b1cac9acacf0a047dc2f61c0f6cf8f32728d
3
+ size 324662984
checkpoint-13900/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-14000/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-14000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37090f18a5b1f2af061ef7c30907642afed2bdc411fef40c2a620a7549f78ddb
3
+ size 324662984
checkpoint-14000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520