Hugging Face's logo

cedpsam
/
cedpsam_EleutherAI_gpt-neo-125M-stablediffionprompts-stablediffionprompts

Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
gpt_neo
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
3
cedpsam commited on
Commit
613f2b3
·
1 Parent(s): 91d38de

Training in progress, step 500

Browse files
Files changed (17) hide show
  1. .gitignore +1 -0
  2. config.json +54 -0
  3. last-checkpoint/config.json +54 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/pytorch_model.bin +3 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scaler.pt +3 -0
  8. last-checkpoint/scheduler.pt +3 -0
  9. last-checkpoint/trainer_state.json +22 -0
  10. last-checkpoint/training_args.bin +3 -0
  11. pytorch_model.bin +3 -0
  12. runs/Oct06_09-31-30_e00e77eee234/1665048700.6992056/events.out.tfevents.1665048700.e00e77eee234.68.1 +3 -0
  13. runs/Oct06_09-31-30_e00e77eee234/1665048712.441633/events.out.tfevents.1665048712.e00e77eee234.68.2 +3 -0
  14. runs/Oct06_09-31-30_e00e77eee234/1665048713.0094912/events.out.tfevents.1665048713.e00e77eee234.68.3 +3 -0
  15. runs/Oct06_09-31-30_e00e77eee234/1665048713.5420418/events.out.tfevents.1665048713.e00e77eee234.68.4 +3 -0
  16. runs/Oct06_09-31-30_e00e77eee234/events.out.tfevents.1665048700.e00e77eee234.68.0 +3 -0
  17. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cedpsam/EleutherAI_gpt-neo-125M-stablediffionprompts",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.22.2",
51
+ "use_cache": true,
52
+ "vocab_size": 50257,
53
+ "window_size": 256
54
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cedpsam/EleutherAI_gpt-neo-125M-stablediffionprompts",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.22.2",
51
+ "use_cache": true,
52
+ "vocab_size": 50257,
53
+ "window_size": 256
54
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a5a898497ac34ef91059e94cb8c3b2676b5a3ef592072ebb12928e1c9c4d811
3
+ size 1001681601
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f49da5c416f98bbb66d3aeed807e34fc7759177c306c14acdb96a3a1c9fe4d
3
+ size 551185105
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84838ccd45951bbe1e5f964cffc9f60572ee4f5e111f59de86b1a56f3d7a6bd8
3
+ size 14503
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa4c7be44c959599b8b43bb9bc3371e9e4e5bbc5758b3ab5afcccfda3e72e67
3
+ size 559
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e87ba192c742c7c7c8f8563ad074e60cd4f741a14b12398af9a9008c512ad42
3
+ size 623
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.006782603977318972,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 4.5e-05,
13
+ "loss": 0.0673,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 5000,
18
+ "num_train_epochs": 1,
19
+ "total_flos": 522414194688000.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a4735e64071787e2288521b2318ebc0a4172be47ab15e2affd44b484047498f
3
+ size 3567
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f49da5c416f98bbb66d3aeed807e34fc7759177c306c14acdb96a3a1c9fe4d
3
+ size 551185105
runs/Oct06_09-31-30_e00e77eee234/1665048700.6992056/events.out.tfevents.1665048700.e00e77eee234.68.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ce533c076020d6bb31f09e45490b3a46df4b4b18a02e605ee41d70fb9bdf63
3
+ size 5679
runs/Oct06_09-31-30_e00e77eee234/1665048712.441633/events.out.tfevents.1665048712.e00e77eee234.68.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21d3d4af3d9abe79ffe87d9ffad477cb8d10d0bd85ebb3d25e66db12024f324
3
+ size 5679
runs/Oct06_09-31-30_e00e77eee234/1665048713.0094912/events.out.tfevents.1665048713.e00e77eee234.68.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75bf8cc043cb1a0a7b51384b21df71b395bb05ec8b3b628992247c6e31324530
3
+ size 5679
runs/Oct06_09-31-30_e00e77eee234/1665048713.5420418/events.out.tfevents.1665048713.e00e77eee234.68.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08228631a9e1affd233461ed168efb5ed63f3fbd218b0e943ef8193d45f08a90
3
+ size 5679
runs/Oct06_09-31-30_e00e77eee234/events.out.tfevents.1665048700.e00e77eee234.68.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72af4f1645c614497221e641391bb1e20791aa3eff3b030d5764d0e1f63d9dc2
3
+ size 17401
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a4735e64071787e2288521b2318ebc0a4172be47ab15e2affd44b484047498f
3
+ size 3567