rafaeloc15
commited on
Commit
•
82329a4
1
Parent(s):
4e27acc
rafaeloc15/mistral-small-v4
Browse files- README.md +5 -5
- adapter_config.json +1 -0
- adapter_model.safetensors +1 -1
- runs/Apr19_22-31-37_9503fe95efd9/events.out.tfevents.1713565928.9503fe95efd9.237.0 +3 -0
- runs/Apr19_22-31-37_9503fe95efd9/events.out.tfevents.1713566894.9503fe95efd9.237.1 +3 -0
- runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713568718.9503fe95efd9.237.2 +3 -0
- runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713569825.9503fe95efd9.237.3 +3 -0
- runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570268.9503fe95efd9.237.4 +3 -0
- runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570357.9503fe95efd9.237.5 +3 -0
- runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570505.9503fe95efd9.237.6 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -5,9 +5,9 @@ tags:
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
|
|
8 |
datasets:
|
9 |
- generator
|
10 |
-
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
11 |
model-index:
|
12 |
- name: mistral_instruct_generation_v2
|
13 |
results: []
|
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
|
58 |
|
59 |
### Framework versions
|
@@ -61,5 +61,5 @@ The following hyperparameters were used during training:
|
|
61 |
- PEFT 0.10.0
|
62 |
- Transformers 4.38.2
|
63 |
- Pytorch 2.2.1+cu121
|
64 |
-
- Datasets 2.
|
65 |
- Tokenizers 0.15.2
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
9 |
datasets:
|
10 |
- generator
|
|
|
11 |
model-index:
|
12 |
- name: mistral_instruct_generation_v2
|
13 |
results: []
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0237
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 0.0373 | 1.0 | 110 | 0.0274 |
|
56 |
+
| 0.0302 | 2.0 | 220 | 0.0237 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
61 |
- PEFT 0.10.0
|
62 |
- Transformers 4.38.2
|
63 |
- Pytorch 2.2.1+cu121
|
64 |
+
- Datasets 2.19.0
|
65 |
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
@@ -6,6 +6,7 @@
|
|
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": {},
|
|
|
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": {},
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109069176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96b67927fcb00c931555dd243722108043295fc73678578097ae65fe6e7ecdcf
|
3 |
size 109069176
|
runs/Apr19_22-31-37_9503fe95efd9/events.out.tfevents.1713565928.9503fe95efd9.237.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ed5002c0236ba86390971afa1b38b25c56dda75f8d6e29d9f625b435eb939f9
|
3 |
+
size 7338
|
runs/Apr19_22-31-37_9503fe95efd9/events.out.tfevents.1713566894.9503fe95efd9.237.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18b513623342282493ff47c89e230645624e761a706c254a5109f792a909156b
|
3 |
+
size 7338
|
runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713568718.9503fe95efd9.237.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:202a26a3a98db39330dc405c22122b24566a39440d6a5ba3947c3c48d3c7d831
|
3 |
+
size 7338
|
runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713569825.9503fe95efd9.237.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d21e38cf569bf89a82292b5fa563a88bfc8852efb26f7d3bab2e735062f3db2f
|
3 |
+
size 5061
|
runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570268.9503fe95efd9.237.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bad150580d97258780b28ce04002a774bb76c4128f115f143d56c06efe962b63
|
3 |
+
size 5061
|
runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570357.9503fe95efd9.237.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dfd8cb04cfa3bd4204d3c0b7166226cabc3bbb042e352e039e45544462b8db4
|
3 |
+
size 6148
|
runs/Apr19_23-17-55_9503fe95efd9/events.out.tfevents.1713570505.9503fe95efd9.237.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8a8fe31521a812528bdccb5f9672cd5d88fa897d3ce374eb8ce9ce8d5f2c531
|
3 |
+
size 10546
|
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:e8c798461c57d7010b041a17a668493a8d2410e8526dd949bcb3fb2d86ac4ae4
|
3 |
size 4920
|