tiagoblima commited on
Commit
7585707
1 Parent(s): 50b77b5

Training in progress, step 500

Browse files
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unicamp-dl/ptt5-large-t5-vocab",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.1,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": [
17
+ "lm_head"
18
+ ],
19
+ "peft_type": "LORA",
20
+ "r": 16,
21
+ "rank_pattern": {},
22
+ "revision": null,
23
+ "target_modules": [
24
+ "v",
25
+ "q"
26
+ ],
27
+ "task_type": "SEQ_2_SEQ_LM"
28
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f242cb09606095ec2a21c1f77c5123be5c65cca91e00278ff5014badfcfc15a9
3
+ size 150511720
tokenizer.json CHANGED
@@ -1,7 +1,21 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 30,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 30
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "<pad>"
18
+ },
19
  "added_tokens": [
20
  {
21
  "id": 0,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e28a73318dd04c95c1e1feecdb57e7914ffc1ea6df372abcf4c3369b0d15ff72
3
- size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147b2df6f46d9de7cfda46969ce87d4b9c259fda1d673ca46ec0b77d19af9aa2
3
+ size 4856