TheGardener
commited on
vinallama_fine_tune_test
Browse files- README.md +2 -2
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- special_tokens_map.json +1 -7
- tokenizer.json +2 -2
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -35,13 +35,13 @@ More information needed
|
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 2.5e-05
|
37 |
- train_batch_size: 8
|
38 |
-
- eval_batch_size:
|
39 |
- seed: 42
|
40 |
- gradient_accumulation_steps: 4
|
41 |
- total_train_batch_size: 32
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
-
- training_steps:
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
|
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 2.5e-05
|
37 |
- train_batch_size: 8
|
38 |
+
- eval_batch_size: 32
|
39 |
- seed: 42
|
40 |
- gradient_accumulation_steps: 4
|
41 |
- total_train_batch_size: 32
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- training_steps: 100
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
adapter_config.json
CHANGED
@@ -23,8 +23,8 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"
|
27 |
-
"
|
28 |
],
|
29 |
"task_type": null,
|
30 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"v_proj",
|
27 |
+
"q_proj"
|
28 |
],
|
29 |
"task_type": null,
|
30 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10502640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:043d23bf70c3022a9880c507d9f89b134d581ebee7d158fce04f804a6ef106fb
|
3 |
size 10502640
|
special_tokens_map.json
CHANGED
@@ -13,13 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
17 |
-
"content": "<pad>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
"unk_token": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<|im_end|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -12,9 +12,9 @@
|
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
15 |
-
"pad_id":
|
16 |
"pad_type_id": 0,
|
17 |
-
"pad_token": "
|
18 |
},
|
19 |
"added_tokens": [
|
20 |
{
|
|
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 46304,
|
16 |
"pad_type_id": 0,
|
17 |
+
"pad_token": "<|im_end|>"
|
18 |
},
|
19 |
"added_tokens": [
|
20 |
{
|
tokenizer_config.json
CHANGED
@@ -56,7 +56,7 @@
|
|
56 |
"eos_token": "<|im_end|>",
|
57 |
"legacy": false,
|
58 |
"model_max_length": 1000000000000000019884624838656,
|
59 |
-
"pad_token": "
|
60 |
"padding_side": "right",
|
61 |
"sp_model_kwargs": {},
|
62 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
56 |
"eos_token": "<|im_end|>",
|
57 |
"legacy": false,
|
58 |
"model_max_length": 1000000000000000019884624838656,
|
59 |
+
"pad_token": "<|im_end|>",
|
60 |
"padding_side": "right",
|
61 |
"sp_model_kwargs": {},
|
62 |
"tokenizer_class": "LlamaTokenizer",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06efba0e0cd05edac47a4783d151793b8eab3181f8808b37ba0db275e97e19a7
|
3 |
size 4856
|