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
23757c7
•
1 Parent(s): 66a22af

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/Oct07_19-39-13_407225e3d50d/1665171765.3632407/events.out.tfevents.1665171765.407225e3d50d.67.1 +3 -0
  11. runs/Oct07_19-39-13_407225e3d50d/1665171781.0398965/events.out.tfevents.1665171781.407225e3d50d.67.2 +3 -0
  12. runs/Oct07_19-39-13_407225e3d50d/1665171781.649494/events.out.tfevents.1665171781.407225e3d50d.67.3 +3 -0
  13. runs/Oct07_19-39-13_407225e3d50d/1665171782.2305255/events.out.tfevents.1665171782.407225e3d50d.67.4 +3 -0
  14. runs/Oct07_19-39-13_407225e3d50d/events.out.tfevents.1665171765.407225e3d50d.67.0 +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 sha256:72f5a3de6c75b5389ce665da1b8bf2bd240b58c31836447a0ad633114dfdf87d
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:b405faeee731dfc124b7fec279f7c32062c6c7d52218cd6f56fe5b3e8a69f14b
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 sha256:9bba0534880ddf6cf8901153e43087f30df53e956d861cda03d12ae77a09ee10
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": 4.8333333333333334e-05,
13
+ "loss": 0.066,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 15000,
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 sha256:6048d6353a005842408f284124d4e0a00f4c965367ff7017b3effe58208b36fb
3
+ size 3567
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da2e60e1321538e8dcabc8897ef99dbf7b9410c3b8f8749c22d66eaa42769e65
3
  size 551185105
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b405faeee731dfc124b7fec279f7c32062c6c7d52218cd6f56fe5b3e8a69f14b
3
  size 551185105
runs/Oct07_19-39-13_407225e3d50d/1665171765.3632407/events.out.tfevents.1665171765.407225e3d50d.67.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1228de901e610d53ef53ca32bfe25f36cfa7eca2eda3800201d6458f935bb22
3
+ size 5679
runs/Oct07_19-39-13_407225e3d50d/1665171781.0398965/events.out.tfevents.1665171781.407225e3d50d.67.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91fbe3e4519f8cd45143ed75d3054225dc9069e12f26dffd7960e028af7c1b6f
3
+ size 5679
runs/Oct07_19-39-13_407225e3d50d/1665171781.649494/events.out.tfevents.1665171781.407225e3d50d.67.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:042ab48267a26cb790798e0dd8b8e4fcc61d2bfa17269f48e8e284ad04121d96
3
+ size 5679
runs/Oct07_19-39-13_407225e3d50d/1665171782.2305255/events.out.tfevents.1665171782.407225e3d50d.67.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f82ebb2826b3089032b5ce4a41c5ae4d72c4cff995aeae647a217e59a14344f5
3
+ size 5679
runs/Oct07_19-39-13_407225e3d50d/events.out.tfevents.1665171765.407225e3d50d.67.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:050fd71744592ce05c815b579af89222b2a1b7ce0b8924d0b563c327e083946e
3
+ size 17405
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18598edc94a8846299e3dbe81cbd09d538beedc0c8a3af0c13ba691e27344d05
3
  size 3567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6048d6353a005842408f284124d4e0a00f4c965367ff7017b3effe58208b36fb
3
  size 3567