thisishadis commited on
Commit
b943f3e
1 Parent(s): 0517c79

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,11 +1,11 @@
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,
@@ -17,9 +17,9 @@
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,
 
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
  "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,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f57995ad781ab482844f8a340368a83010d743c5e045046fe97213b6aed40283
3
- size 2950848513
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7453889cc8fcccaf44b643c12d289adc81fdaa87d928484935daef5b60f964ca
3
+ size 242071641
runs/Aug14_07-40-57_d460946fe585/events.out.tfevents.1691999580.d460946fe585.430.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a899c0a03f006ad0d8966382255a7f2773e195b869397d66e182e4b42ebc0f7b
3
+ size 7392
runs/Aug14_08-12-55_d460946fe585/events.out.tfevents.1692000794.d460946fe585.430.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9135e3a257eeec7b157fb5a2b5ff20b2c7e19989b48631b7e7622fdffc32eb61
3
+ size 7392
runs/Aug14_08-14-04_d460946fe585/events.out.tfevents.1692000850.d460946fe585.430.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fdc447ff9df093ae7ac51099da37f6e86ce249e511422cbbd39c88f06d1715a
3
+ size 9880
runs/Aug14_08-20-18_d460946fe585/events.out.tfevents.1692001231.d460946fe585.19542.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7962a7323f346d1e67e334234e50d8463d75036fed3b7fd4023535802ccdc78
3
+ size 5141
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 128,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2791ff57504365dfafb9d92619d2bac4c8e79654dfbd234f905fa8f331e305c8
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06eb8b65c27393663b5ceaf631eb22e73724fd3e523d67c567b5a65a4467e775
3
  size 4091