diallomama commited on
Commit
cc5a2da
1 Parent(s): 04177cd

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "_name_or_path": "t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
- "d_ff": 2048,
7
  "d_kv": 64,
8
- "d_model": 512,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "relu",
11
  "dropout_rate": 0.1,
@@ -17,9 +17,9 @@
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
  "n_positions": 512,
20
- "num_decoder_layers": 6,
21
- "num_heads": 8,
22
- "num_layers": 6,
23
  "output_past": true,
24
  "pad_token_id": 0,
25
  "relative_attention_max_distance": 128,
 
1
  {
2
+ "_name_or_path": "t5-large",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
+ "d_ff": 4096,
7
  "d_kv": 64,
8
+ "d_model": 1024,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "relu",
11
  "dropout_rate": 0.1,
 
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
  "n_positions": 512,
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 16,
22
+ "num_layers": 24,
23
  "output_past": true,
24
  "pad_token_id": 0,
25
  "relative_attention_max_distance": 128,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e48b3847454d4c27ed0c1bde4922d3712c53b7846ff4232f892b14f0cd3f1b4c
3
- size 242069785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ab40a3638b252be0b880b0b396a7718adab0b01a047681613be38945bffe36
3
+ size 2950841345
runs/Jun12_09-19-57_5f07fe1612f6/events.out.tfevents.1686561806.5f07fe1612f6.5756.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab8aa415cb4a691dcbbfbbcc5edde0168bae24d798e7d3185474ab98926efcd5
3
- size 7025
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649bd8181421285b2dd144c5d656e9346ac4089ccb9317d5279bf589684b8422
3
+ size 7182
runs/Jun12_10-08-26_5f07fe1612f6/events.out.tfevents.1686564553.5f07fe1612f6.20935.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55df3228e483dfe893d8e5c336c75a4beca7fcbd72c7c7da9da7c9262b82e17
3
+ size 5146
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c62ce46bdb8434e536fd47a9b27d7dbb28c9f2aaf40156959c64f0491931fae2
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e1e78b7151160719a7d2ace2cdaa84d2548b2d363cdac26ef5ebfe4e1120be
3
  size 4091