eyalmazuz commited on
Commit
239b83e
1 Parent(s): 2a2de59

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +28 -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 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "d_ff": 2048,
6
+ "d_kv": 64,
7
+ "d_model": 512,
8
+ "decoder_start_token_id": 3,
9
+ "dense_act_fn": "relu",
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "is_gated_act": false,
16
+ "layer_norm_epsilon": 1e-06,
17
+ "model_type": "t5",
18
+ "num_decoder_layers": 6,
19
+ "num_heads": 8,
20
+ "num_layers": 6,
21
+ "pad_token_id": 0,
22
+ "relative_attention_max_distance": 128,
23
+ "relative_attention_num_buckets": 32,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.25.1",
26
+ "use_cache": true,
27
+ "vocab_size": 37000
28
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da499b430b1a6f4ce0c6278a653503613b76d11fef4430a85b6ff78d521980bf
3
+ size 504085429
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd5167d80de1c683478c39a84fd1f11442cb00a03466b936247259c78be298af
3
+ size 252048123
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:629a7e6696e1dffb77363086aabfda125f9858db97a59f19bb32e8e474b303b1
3
+ size 14503
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4ed84309e9de32c7a5b660324bcc4b5f8952fd6c48c4e11687280f2a3687b7
3
+ size 559
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4953833922a6bd5b035cd9f760221f0b9caae7b6a9500c5be480eeee36736eb2
3
+ size 623
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:ce0f0e493fa5023727e587f7f9be8dfaed676c84230fca15a4aee4e2512a8153
3
+ size 3439