Hugging Face's logo

georgeyw
/
gpt-2-small

Safetensors
Model card Files Community
georgeyw commited on
Commit
bce786b
·
verified ·
1 Parent(s): 430d19a

Training in progress, step 9000, checkpoint

Browse files
Files changed (30) hide show
  1. checkpoint-8100/config.json +31 -0
  2. checkpoint-8100/model.safetensors +3 -0
  3. checkpoint-8100/training_args.bin +3 -0
  4. checkpoint-8200/config.json +31 -0
  5. checkpoint-8200/model.safetensors +3 -0
  6. checkpoint-8200/training_args.bin +3 -0
  7. checkpoint-8300/config.json +31 -0
  8. checkpoint-8300/model.safetensors +3 -0
  9. checkpoint-8300/training_args.bin +3 -0
  10. checkpoint-8400/config.json +31 -0
  11. checkpoint-8400/model.safetensors +3 -0
  12. checkpoint-8400/training_args.bin +3 -0
  13. checkpoint-8500/config.json +31 -0
  14. checkpoint-8500/model.safetensors +3 -0
  15. checkpoint-8500/training_args.bin +3 -0
  16. checkpoint-8600/config.json +31 -0
  17. checkpoint-8600/model.safetensors +3 -0
  18. checkpoint-8600/training_args.bin +3 -0
  19. checkpoint-8700/config.json +31 -0
  20. checkpoint-8700/model.safetensors +3 -0
  21. checkpoint-8700/training_args.bin +3 -0
  22. checkpoint-8800/config.json +31 -0
  23. checkpoint-8800/model.safetensors +3 -0
  24. checkpoint-8800/training_args.bin +3 -0
  25. checkpoint-8900/config.json +31 -0
  26. checkpoint-8900/model.safetensors +3 -0
  27. checkpoint-8900/training_args.bin +3 -0
  28. checkpoint-9000/config.json +31 -0
  29. checkpoint-9000/model.safetensors +3 -0
  30. checkpoint-9000/training_args.bin +3 -0
checkpoint-8100/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-8100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f87200d4f5fc6fb8aa1c477ed0af2eec66bd290fb088098b0a1bebeb3920ac0e
3
+ size 324662984
checkpoint-8100/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-8200/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-8200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f669b5851234a7b9bae603d87d6f04dd55cd988ea452f77110146f4d5d9cb846
3
+ size 324662984
checkpoint-8200/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-8300/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-8300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62f2b00b9ab27bbb9dca9f661c702869fef069621e979a4d3971e8c19061b8b0
3
+ size 324662984
checkpoint-8300/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-8400/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-8400/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54cc59179d546cd497868862c468637e3f6d52de755c3e5d7d7df1456283cb97
3
+ size 324662984
checkpoint-8400/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-8500/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-8500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca0c5726343c42606559214afda2201196ec99878cf2a3a01833e2fd780a8a2e
3
+ size 324662984
checkpoint-8500/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-8600/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-8600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:414b4c14ac16d2fb5a88fc4e8973c3c88ea9e5ce08db335174b15eb15b04de1c
3
+ size 324662984
checkpoint-8600/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-8700/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-8700/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:563400599d449a325f839ca444577e391414ff0d13948fcb720e2ed05a513c13
3
+ size 324662984
checkpoint-8700/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-8800/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-8800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998d027e222fa8fd3135f9a1b69c094f52c2b7814f3e82cfb0cdf2b02c1d7b3e
3
+ size 324662984
checkpoint-8800/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-8900/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-8900/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7391feb0a3adf74968b22c39d92e956dc064486397997699eec3d9061e5bb03e
3
+ size 324662984
checkpoint-8900/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-9000/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-9000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6c744f4e9ce44ae52384a846204a735fc943b613ffcf69e27ca36ec7b66fa6
3
+ size 324662984
checkpoint-9000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3f522b6b895157d4ae37816ea2b39e4b24555bc3782f9f18492c6709abd779
3
+ size 6520