Hugging Face's logo

georgeyw
/
gpt-2-small

Safetensors
Model card Files Community
georgeyw commited on
Commit
743a576
·
verified ·
1 Parent(s): 3e6365b

Training in progress, step 62000, checkpoint

Browse files
Files changed (30) hide show
  1. checkpoint-61100/config.json +31 -0
  2. checkpoint-61100/model.safetensors +3 -0
  3. checkpoint-61100/training_args.bin +3 -0
  4. checkpoint-61200/config.json +31 -0
  5. checkpoint-61200/model.safetensors +3 -0
  6. checkpoint-61200/training_args.bin +3 -0
  7. checkpoint-61300/config.json +31 -0
  8. checkpoint-61300/model.safetensors +3 -0
  9. checkpoint-61300/training_args.bin +3 -0
  10. checkpoint-61400/config.json +31 -0
  11. checkpoint-61400/model.safetensors +3 -0
  12. checkpoint-61400/training_args.bin +3 -0
  13. checkpoint-61500/config.json +31 -0
  14. checkpoint-61500/model.safetensors +3 -0
  15. checkpoint-61500/training_args.bin +3 -0
  16. checkpoint-61600/config.json +31 -0
  17. checkpoint-61600/model.safetensors +3 -0
  18. checkpoint-61600/training_args.bin +3 -0
  19. checkpoint-61700/config.json +31 -0
  20. checkpoint-61700/model.safetensors +3 -0
  21. checkpoint-61700/training_args.bin +3 -0
  22. checkpoint-61800/config.json +31 -0
  23. checkpoint-61800/model.safetensors +3 -0
  24. checkpoint-61800/training_args.bin +3 -0
  25. checkpoint-61900/config.json +31 -0
  26. checkpoint-61900/model.safetensors +3 -0
  27. checkpoint-61900/training_args.bin +3 -0
  28. checkpoint-62000/config.json +31 -0
  29. checkpoint-62000/model.safetensors +3 -0
  30. checkpoint-62000/training_args.bin +3 -0
checkpoint-61100/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-61100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:342fe41e9417a7ab74d99ce274fbdf85a843c084d87ae246936f33eea870d493
3
+ size 324662984
checkpoint-61100/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-61200/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-61200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00395e3db3a514c10bf2525a69a4062b7a161101b8416774dd7ca48fbc743022
3
+ size 324662984
checkpoint-61200/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-61300/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-61300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372ef5633f0282baf296c7476eaf59cff26656a343c32ab1ae30102ba49b79d9
3
+ size 324662984
checkpoint-61300/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-61400/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-61400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9543ccbb118a2d0d7bd1f0f66bb02d53f544d85edd6cee9cb12f5fde4ecbebaa
3
+ size 324662984
checkpoint-61400/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-61500/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-61500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7203b09741192de73184d653e52eaf6e997c22ce892d99fd93e4436a135afa9
3
+ size 324662984
checkpoint-61500/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-61600/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-61600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a77a5f2c71fc3fce2dc0ec58c72090d51fe8ca7f516f03bb67f2f5fddb06d6ae
3
+ size 324662984
checkpoint-61600/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-61700/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-61700/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9657e987f27b818370545e4d71bc16749940026f9b8ab38b2f789b078dd1eb
3
+ size 324662984
checkpoint-61700/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-61800/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-61800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:728a97406b9d639b80419d1f970a6583f885b3720c8b0705c0044354b2e8b44e
3
+ size 324662984
checkpoint-61800/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-61900/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-61900/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7befbe582ee93cc3391f82280df65603a84bdad1bac30357fc4a1874d230a2e
3
+ size 324662984
checkpoint-61900/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-62000/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-62000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0990b41b6b2e15ffd481af42406ef2cd237f3370aa6a2f78c5631be262b8697
3
+ size 324662984
checkpoint-62000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520