breadlicker45 commited on
Commit
1dfdfab
·
1 Parent(s): 18964c0

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +27 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scaler.pt +3 -0
  6. scheduler.pt +3 -0
  7. trainer_state.json +0 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-70m-deduped",
3
+ "architectures": [
4
+ "GPTNeoXForSequenceClassification"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": 0.1,
8
+ "eos_token_id": 0,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 512,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2048,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "gpt_neox",
16
+ "num_attention_heads": 8,
17
+ "num_hidden_layers": 6,
18
+ "pad_token_id": 50278,
19
+ "rotary_emb_base": 10000,
20
+ "rotary_pct": 0.25,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.29.2",
24
+ "use_cache": true,
25
+ "use_parallel_residual": true,
26
+ "vocab_size": 50279
27
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfbea48ee125cf583cb4787f9e8e0800324b1332f7c6549fdf4413b4a73c8a5c
3
+ size 819
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5283fdd81ffd1e2e6f8124726bc82cd1c2e1308ca149e396492cc4d27174c486
3
+ size 203833995
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
3
+ size 14575
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa181fa360d46feed4180ea17c8b6a4a879a9b4231c2e91aff2be20be9076cc
3
+ size 557
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd962cfcecec67841abeb990001e78b5eca24487a69228bb356e033e5c74e15f
3
+ size 627
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d83f45d8599c42eb99699532982a4da788a47d0733d7fd36af302345552c5aa
3
+ size 3899