SmolLM-1.7B-Instruct_fsdp_qlora_nf4_adapter
Browse files- README.md +23 -23
- adapter_config.json +6 -6
- adapter_model.safetensors +1 -1
- runs/Sep04_14-46-19_algo-2/events.out.tfevents.1725461208.algo-2.69.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -9,18 +9,18 @@ base_model: HuggingFaceTB/SmolLM-1.7B-Instruct
|
|
9 |
datasets:
|
10 |
- generator
|
11 |
model-index:
|
12 |
-
- name:
|
13 |
results: []
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
-
#
|
20 |
|
21 |
This model is a fine-tuned version of [HuggingFaceTB/SmolLM-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-Instruct) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 1.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -57,26 +57,26 @@ The following hyperparameters were used during training:
|
|
57 |
|
58 |
| Training Loss | Epoch | Step | Validation Loss |
|
59 |
|:-------------:|:-------:|:----:|:---------------:|
|
60 |
-
| 2.
|
61 |
-
| 1.
|
62 |
-
| 1.
|
63 |
-
| 1.
|
64 |
-
| 1.
|
65 |
-
| 1.
|
66 |
-
| 1.
|
67 |
-
| 1.
|
68 |
-
| 1.
|
69 |
-
| 1.
|
70 |
-
| 1.
|
71 |
-
| 1.
|
72 |
-
| 1.
|
73 |
-
| 1.
|
74 |
-
| 1.
|
75 |
-
| 1.
|
76 |
-
| 1.
|
77 |
-
| 1.
|
78 |
-
| 1.
|
79 |
-
| 1.
|
80 |
|
81 |
|
82 |
### Framework versions
|
|
|
9 |
datasets:
|
10 |
- generator
|
11 |
model-index:
|
12 |
+
- name: SmolLM_1_7B_Instruct_qlora_nf4
|
13 |
results: []
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
+
# SmolLM_1_7B_Instruct_qlora_nf4
|
20 |
|
21 |
This model is a fine-tuned version of [HuggingFaceTB/SmolLM-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-1.7B-Instruct) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.6111
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
57 |
|
58 |
| Training Loss | Epoch | Step | Validation Loss |
|
59 |
|:-------------:|:-------:|:----:|:---------------:|
|
60 |
+
| 2.0769 | 0.9524 | 10 | 1.9176 |
|
61 |
+
| 1.8602 | 2.0 | 21 | 1.7910 |
|
62 |
+
| 1.7729 | 2.9524 | 31 | 1.7320 |
|
63 |
+
| 1.7147 | 4.0 | 42 | 1.6913 |
|
64 |
+
| 1.6753 | 4.9524 | 52 | 1.6662 |
|
65 |
+
| 1.6518 | 6.0 | 63 | 1.6477 |
|
66 |
+
| 1.6228 | 6.9524 | 73 | 1.6361 |
|
67 |
+
| 1.6118 | 8.0 | 84 | 1.6274 |
|
68 |
+
| 1.5843 | 8.9524 | 94 | 1.6214 |
|
69 |
+
| 1.5805 | 10.0 | 105 | 1.6173 |
|
70 |
+
| 1.5712 | 10.9524 | 115 | 1.6151 |
|
71 |
+
| 1.5524 | 12.0 | 126 | 1.6133 |
|
72 |
+
| 1.5491 | 12.9524 | 136 | 1.6121 |
|
73 |
+
| 1.5445 | 14.0 | 147 | 1.6113 |
|
74 |
+
| 1.5397 | 14.9524 | 157 | 1.6113 |
|
75 |
+
| 1.5392 | 16.0 | 168 | 1.6114 |
|
76 |
+
| 1.5337 | 16.9524 | 178 | 1.6111 |
|
77 |
+
| 1.5347 | 18.0 | 189 | 1.6111 |
|
78 |
+
| 1.5337 | 18.9524 | 199 | 1.6111 |
|
79 |
+
| 1.5351 | 19.0476 | 200 | 1.6111 |
|
80 |
|
81 |
|
82 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
-
"down_proj",
|
25 |
-
"up_proj",
|
26 |
-
"o_proj",
|
27 |
-
"v_proj",
|
28 |
"k_proj",
|
29 |
-
"
|
|
|
|
|
|
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
23 |
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"o_proj",
|
27 |
+
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"down_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 36220744
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3a4c40f6a10d6fc3272a401bd4d0f52278f41ae12d179f9cadc4402d40e0279
|
3 |
size 36220744
|
runs/Sep04_14-46-19_algo-2/events.out.tfevents.1725461208.algo-2.69.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:116ce818c01ba78a5ff0c099c7b051a4b6418b19f3bf8d60d9717135513417dc
|
3 |
+
size 15367
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cdd7102f1042f158c2abca7f8429922f42b01b3ea7573c0aea6cd2d44ac80de
|
3 |
size 5240
|