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
b309ad9
•
1 Parent(s): bf55255

Training in progress, step 500

Browse files
Files changed (15) hide show
  1. last-checkpoint/config.json +54 -0
  2. last-checkpoint/optimizer.pt +3 -0
  3. last-checkpoint/pytorch_model.bin +3 -0
  4. last-checkpoint/rng_state.pth +3 -0
  5. last-checkpoint/scaler.pt +3 -0
  6. last-checkpoint/scheduler.pt +3 -0
  7. last-checkpoint/trainer_state.json +22 -0
  8. last-checkpoint/training_args.bin +3 -0
  9. pytorch_model.bin +1 -1
  10. runs/Oct06_20-08-52_36e54443a43e/1665087168.9900694/events.out.tfevents.1665087168.36e54443a43e.68.1 +3 -0
  11. runs/Oct06_20-08-52_36e54443a43e/1665087185.0690587/events.out.tfevents.1665087185.36e54443a43e.68.2 +3 -0
  12. runs/Oct06_20-08-52_36e54443a43e/1665087185.664654/events.out.tfevents.1665087185.36e54443a43e.68.3 +3 -0
  13. runs/Oct06_20-08-52_36e54443a43e/1665087186.2224376/events.out.tfevents.1665087186.36e54443a43e.68.4 +3 -0
  14. runs/Oct06_20-08-52_36e54443a43e/events.out.tfevents.1665087168.36e54443a43e.68.0 +3 -0
  15. training_args.bin +1 -1
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 sha256:3be554315ba8e9132bf819988f66580e5e44364b1f1effd3f324d53cc04d53de
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:fa5d56c37dc8d80dd5ebc25ea117c30ce5dd4652f47f8533f9a3801ecc6d13bf
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:f62196fb1b113eee81e8d3d881e7700e032897a91d6c3590f3456d6916ed8474
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": 4.722222222222222e-05,
13
+ "loss": 0.066,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 9000,
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:c2d8413e357dd2abb04f91d2a5d6f1a1409824d2aef432f001542fe21d09714c
3
+ size 3567
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7eaca1c65253d8d954b56da32f5d0edd3b3d5f18d2bfbf76ec399a4718910206
3
  size 551185105
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa5d56c37dc8d80dd5ebc25ea117c30ce5dd4652f47f8533f9a3801ecc6d13bf
3
  size 551185105
runs/Oct06_20-08-52_36e54443a43e/1665087168.9900694/events.out.tfevents.1665087168.36e54443a43e.68.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4614b19ea91b1af184b29256fceaf4730704059ddd708b0b73ca29a33405138a
3
+ size 5679
runs/Oct06_20-08-52_36e54443a43e/1665087185.0690587/events.out.tfevents.1665087185.36e54443a43e.68.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f509fee46fccc408d40548e11a2ba91420fcaccd706194aaa5cb00cbca75bb92
3
+ size 5679
runs/Oct06_20-08-52_36e54443a43e/1665087185.664654/events.out.tfevents.1665087185.36e54443a43e.68.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fde67c34826c2bd3a77537c39f6223ca9cc4e41558e263a1856d792a0623ff3e
3
+ size 5679
runs/Oct06_20-08-52_36e54443a43e/1665087186.2224376/events.out.tfevents.1665087186.36e54443a43e.68.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4172f427ebacc59ad0e81b4b3478194d7d9084d6e4ad0dacb1acf53cc0c10981
3
+ size 5679
runs/Oct06_20-08-52_36e54443a43e/events.out.tfevents.1665087168.36e54443a43e.68.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2361d89e007d300df4c896029d852a5fac7a1ab173bf9ae7ac99a4867c3ce722
3
+ size 17401
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ad5bcc910f15fcfe415e4694b734bd32b2375fcdc79ffc4921d2b1cd12cbf7c
3
  size 3567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2d8413e357dd2abb04f91d2a5d6f1a1409824d2aef432f001542fe21d09714c
3
  size 3567