Hugging Face's logo

cedpsam
/
EleutherAI_gpt-neo-125M-stablediffionprompts

Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
gpt_neo
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
2
cedpsam commited on
Commit
5e318c2
•
1 Parent(s): 95c491c

Model save

Browse files
Files changed (10) hide show
  1. last-checkpoint/config.json +0 -54
  2. last-checkpoint/optimizer.pt +0 -3
  3. last-checkpoint/pytorch_model.bin +0 -3
  4. last-checkpoint/rng_state.pth +0 -3
  5. last-checkpoint/scaler.pt +0 -3
  6. last-checkpoint/scheduler.pt +0 -3
  7. last-checkpoint/trainer_state.json +0 -46
  8. last-checkpoint/training_args.bin +0 -3
  9. pytorch_model.bin +1 -1
  10. runs/Oct20_17-51-04_5425517b47a3/events.out.tfevents.1666288481.5425517b47a3.23.0 +2 -2
last-checkpoint/config.json DELETED
@@ -1,54 +0,0 @@
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": "4.20.1",
51
- "use_cache": true,
52
- "vocab_size": 50257,
53
- "window_size": 256
54
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c62acbc7881602ea0f4db49faa36f1d8f14d31b8a746c89b0ff6357b4b3b489a
3
- size 1001681601
 
 
 
last-checkpoint/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a228789c61b1e2ff247caa4ab6b8e11add9d34f6ab4900a597f2f49d5b48d0a
3
- size 551185105
 
 
 
last-checkpoint/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:62851f63d26f31f0098aaf22bfc590da9d5dd492f2a149b0c502c13be7100a3d
3
- size 14503
 
 
 
last-checkpoint/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9450f60642b7670a16793d57df57c7e8137dd41cb122c592e7c3a2a581d5e5db
3
- size 559
 
 
 
last-checkpoint/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f7152e2336509512ccf0b5b6d81eb65f7bcfddb028a0a3b52eb739d4a34a93a
3
- size 623
 
 
 
last-checkpoint/trainer_state.json DELETED
@@ -1,46 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.03391301988659486,
5
- "global_step": 2500,
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": 9.886136363636363e-08,
13
- "loss": 0.0253,
14
- "step": 500
15
- },
16
- {
17
- "epoch": 0.01,
18
- "learning_rate": 9.7725e-08,
19
- "loss": 0.0256,
20
- "step": 1000
21
- },
22
- {
23
- "epoch": 0.02,
24
- "learning_rate": 9.658863636363636e-08,
25
- "loss": 0.0296,
26
- "step": 1500
27
- },
28
- {
29
- "epoch": 0.03,
30
- "learning_rate": 9.545227272727273e-08,
31
- "loss": 0.0246,
32
- "step": 2000
33
- },
34
- {
35
- "epoch": 0.03,
36
- "learning_rate": 9.431590909090909e-08,
37
- "loss": 0.0248,
38
- "step": 2500
39
- }
40
- ],
41
- "max_steps": 44000,
42
- "num_train_epochs": 1,
43
- "total_flos": 2614160630218752.0,
44
- "trial_name": null,
45
- "trial_params": null
46
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
last-checkpoint/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a991bd9fa9f78a109c37f34127e236c70674b999767dd09c9c452dae8fb567ad
3
- size 3439
 
 
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a228789c61b1e2ff247caa4ab6b8e11add9d34f6ab4900a597f2f49d5b48d0a
3
  size 551185105
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8000569242cedfaf9b7ae03492a445867bea9e20a464cb019bc9166be1cba14
3
  size 551185105
runs/Oct20_17-51-04_5425517b47a3/events.out.tfevents.1666288481.5425517b47a3.23.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1d56c6640324ffe66ced1201282dc43b5f23cff09a8d864593cb496886d5117
3
- size 46431
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3b9196b30d47bb1082878ef8be624138049524d7dc2464c6e5d57a5b281066
3
+ size 59990