Dohahemdann commited on
Commit
bb1667f
·
verified ·
1 Parent(s): 1bb0835

End of training

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.3677
20
 
21
  ## Model description
22
 
@@ -35,7 +35,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.001
39
  - train_batch_size: 2
40
  - eval_batch_size: 2
41
  - seed: 42
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 1.3935 | 0.3458 | 500 | 1.4429 |
54
- | 1.8791 | 0.6917 | 1000 | 1.3677 |
55
 
56
 
57
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.4735
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
  - train_batch_size: 2
40
  - eval_batch_size: 2
41
  - seed: 42
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
+ | 1.1782 | 0.3458 | 500 | 1.5188 |
54
+ | 1.9895 | 0.6917 | 1000 | 1.4735 |
55
 
56
 
57
  ### Framework versions
adapter_config.json CHANGED
@@ -25,9 +25,9 @@
25
  "revision": null,
26
  "target_modules": [
27
  "q",
28
- "k",
29
  "o",
30
- "v"
 
31
  ],
32
  "task_type": "SEQ_2_SEQ_LM",
33
  "trainable_token_indices": null,
 
25
  "revision": null,
26
  "target_modules": [
27
  "q",
 
28
  "o",
29
+ "v",
30
+ "k"
31
  ],
32
  "task_type": "SEQ_2_SEQ_LM",
33
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2613675b20d31af750791a2d1405af3f81d7ffe8eeb0b317607adb1176d04a7a
3
  size 75579856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:834b1dd283913ebfc2d18316445a639ee023e4440db9f48c163a6c165e4649e2
3
  size 75579856
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 192,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
tokenizer_config.json CHANGED
@@ -932,13 +932,9 @@
932
  "eos_token": "</s>",
933
  "extra_ids": 100,
934
  "extra_special_tokens": {},
935
- "max_length": 192,
936
  "model_max_length": 512,
937
  "pad_token": "</s>",
938
  "sp_model_kwargs": {},
939
- "stride": 0,
940
  "tokenizer_class": "T5Tokenizer",
941
- "truncation_side": "right",
942
- "truncation_strategy": "longest_first",
943
  "unk_token": "<unk>"
944
  }
 
932
  "eos_token": "</s>",
933
  "extra_ids": 100,
934
  "extra_special_tokens": {},
 
935
  "model_max_length": 512,
936
  "pad_token": "</s>",
937
  "sp_model_kwargs": {},
 
938
  "tokenizer_class": "T5Tokenizer",
 
 
939
  "unk_token": "<unk>"
940
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d5b430e5b2a85d276116ac9933ef719131551fbe484625f902d0afbd6a1d469
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dfb19e2122f69c32b93027a61ec66def9d3f89fd327fe5664e5d30fce5d166a
3
  size 5432