Mert
commited on
End of training
Browse files- README.md +4 -2
- config.json +1 -0
- model.safetensors +1 -1
- tokenizer.json +1 -6
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -4,6 +4,8 @@ tags:
|
|
4 |
- trl
|
5 |
- sft
|
6 |
- generated_from_trainer
|
|
|
|
|
7 |
model-index:
|
8 |
- name: mistral-supervised
|
9 |
results: []
|
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# mistral-supervised
|
16 |
|
17 |
-
This model is a fine-tuned version of [gulmert89/mistral-pretraining](https://huggingface.co/gulmert89/mistral-pretraining) on
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -39,7 +41,7 @@ The following hyperparameters were used during training:
|
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
-
- num_epochs:
|
43 |
|
44 |
### Training results
|
45 |
|
|
|
4 |
- trl
|
5 |
- sft
|
6 |
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- generator
|
9 |
model-index:
|
10 |
- name: mistral-supervised
|
11 |
results: []
|
|
|
16 |
|
17 |
# mistral-supervised
|
18 |
|
19 |
+
This model is a fine-tuned version of [gulmert89/mistral-pretraining](https://huggingface.co/gulmert89/mistral-pretraining) on the generator dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 3
|
45 |
|
46 |
### Training results
|
47 |
|
config.json
CHANGED
@@ -16,6 +16,7 @@
|
|
16 |
"num_attention_heads": 16,
|
17 |
"num_hidden_layers": 4,
|
18 |
"num_key_value_heads": 8,
|
|
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_theta": 10000.0,
|
21 |
"sliding_window": 768,
|
|
|
16 |
"num_attention_heads": 16,
|
17 |
"num_hidden_layers": 4,
|
18 |
"num_key_value_heads": 8,
|
19 |
+
"pad_token_id": 2,
|
20 |
"rms_norm_eps": 1e-06,
|
21 |
"rope_theta": 10000.0,
|
22 |
"sliding_window": 768,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 338197712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:917edbb6ce453ce0076c8b23aaa79b4e71ae0440b013bcc195dd3db4414e0d6d
|
3 |
size 338197712
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 512,
|
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
@@ -38,7 +38,7 @@
|
|
38 |
"pad_to_multiple_of": null,
|
39 |
"pad_token": "</s>",
|
40 |
"pad_token_type_id": 0,
|
41 |
-
"padding_side": "
|
42 |
"sp_model_kwargs": {},
|
43 |
"spaces_between_special_tokens": false,
|
44 |
"stride": 0,
|
|
|
38 |
"pad_to_multiple_of": null,
|
39 |
"pad_token": "</s>",
|
40 |
"pad_token_type_id": 0,
|
41 |
+
"padding_side": "right",
|
42 |
"sp_model_kwargs": {},
|
43 |
"spaces_between_special_tokens": false,
|
44 |
"stride": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8209e8a32ef804268b5e35de8fe38030f954cef6085aad72f9139a472a46c2c
|
3 |
size 5432
|