Model save
Browse files- README.md +5 -5
- adapter_config.json +2 -2
- adapter_model.safetensors +2 -2
- runs/Jan26_08-38-47_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706258573.pedro-morel-rosa-workspace-cuda-0.1047.1 +3 -0
- runs/Jan26_10-08-57_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706263757.pedro-morel-rosa-workspace-cuda-0.1735.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -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-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 1.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -54,10 +54,10 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
-
| 1.
|
58 |
-
| 1.
|
59 |
-
| 1.
|
60 |
-
| 1.
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.6641
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 1.8895 | 0.97 | 18 | 1.8383 |
|
58 |
+
| 1.749 | 1.99 | 37 | 1.7245 |
|
59 |
+
| 1.6948 | 2.96 | 55 | 1.6720 |
|
60 |
+
| 1.6684 | 3.88 | 72 | 1.6641 |
|
61 |
|
62 |
|
63 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -9,13 +9,13 @@
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
-
"lora_alpha":
|
13 |
"lora_dropout": 0.1,
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
-
"r":
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
"lora_dropout": 0.1,
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
+
"r": 64,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74ccd31679e07065274ccad7c12a8f69a4b3fefa72a411964a7a4e8a455b1d0a
|
3 |
+
size 218138576
|
runs/Jan26_08-38-47_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706258573.pedro-morel-rosa-workspace-cuda-0.1047.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f2aae107d2c7ff75e416e29dc627091849e810de76e553182ea53c35d273e4f
|
3 |
+
size 5405
|
runs/Jan26_10-08-57_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706263757.pedro-morel-rosa-workspace-cuda-0.1735.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e50134e6384b8f1b7440b9518833c5d19a5c1635bf55dcbf0d59c3b17e07947a
|
3 |
+
size 9127
|
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 sha256:4c3895989c66e37b62a0af070fdab10058c70081ca593c278e61da71cd3e9e94
|
3 |
size 4856
|