End of training
Browse files- README.md +3 -3
- adapter_config.json +5 -6
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -3,9 +3,9 @@ license: apache-2.0
|
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
datasets:
|
7 |
- generator
|
8 |
-
base_model: mistralai/Mistral-7B-v0.1
|
9 |
model-index:
|
10 |
- name: mistral-journal-finetune
|
11 |
results: []
|
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
### Framework versions
|
52 |
|
53 |
-
- PEFT 0.9.
|
54 |
-
- Transformers 4.
|
55 |
- Pytorch 2.2.1+cu121
|
56 |
- Datasets 2.18.0
|
57 |
- Tokenizers 0.15.2
|
|
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
base_model: mistralai/Mistral-7B-v0.1
|
7 |
datasets:
|
8 |
- generator
|
|
|
9 |
model-index:
|
10 |
- name: mistral-journal-finetune
|
11 |
results: []
|
|
|
50 |
|
51 |
### Framework versions
|
52 |
|
53 |
+
- PEFT 0.9.0
|
54 |
+
- Transformers 4.38.2
|
55 |
- Pytorch 2.2.1+cu121
|
56 |
- Datasets 2.18.0
|
57 |
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
@@ -6,7 +6,6 @@
|
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
8 |
"init_lora_weights": true,
|
9 |
-
"layer_replication": null,
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
@@ -20,14 +19,14 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"up_proj",
|
24 |
-
"v_proj",
|
25 |
"down_proj",
|
|
|
26 |
"lm_head",
|
27 |
-
"
|
28 |
-
"k_proj",
|
29 |
"gate_proj",
|
30 |
-
"
|
|
|
|
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM",
|
33 |
"use_dora": false,
|
|
|
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": {},
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
22 |
"down_proj",
|
23 |
+
"up_proj",
|
24 |
"lm_head",
|
25 |
+
"o_proj",
|
|
|
26 |
"gate_proj",
|
27 |
+
"k_proj",
|
28 |
+
"v_proj",
|
29 |
+
"q_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"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 864513616
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9cde7be54ce6334c0bf239c9e687db55a2c180806a4a95ba9ad043fe8ce8cc4
|
3 |
size 864513616
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f64ca798924db3a0282eefe19a1bb196ad8ed712f8b477f1c5cfa4ceaea0ebf
|
3 |
size 4920
|