HuggingFaceTB/SmolLM-360M-Instruct
Browse files
README.md
CHANGED
@@ -58,24 +58,24 @@ The following hyperparameters were used during training:
|
|
58 |
| Training Loss | Epoch | Step | Validation Loss |
|
59 |
|:-------------:|:-------:|:----:|:---------------:|
|
60 |
| 2.3024 | 0.9524 | 10 | 2.1503 |
|
61 |
-
| 2.1107 | 2.0 | 21 | 2.
|
62 |
| 2.0147 | 2.9524 | 31 | 1.9716 |
|
63 |
| 1.9577 | 4.0 | 42 | 1.9243 |
|
64 |
-
| 1.
|
65 |
| 1.8825 | 6.0 | 63 | 1.8716 |
|
66 |
| 1.8667 | 6.9524 | 73 | 1.8558 |
|
67 |
| 1.8488 | 8.0 | 84 | 1.8429 |
|
68 |
| 1.8284 | 8.9524 | 94 | 1.8343 |
|
69 |
| 1.8201 | 10.0 | 105 | 1.8270 |
|
70 |
-
| 1.8129 | 10.9524 | 115 | 1.
|
71 |
| 1.8028 | 12.0 | 126 | 1.8179 |
|
72 |
| 1.7987 | 12.9524 | 136 | 1.8155 |
|
73 |
| 1.7938 | 14.0 | 147 | 1.8137 |
|
74 |
-
| 1.79 | 14.9524 | 157 | 1.
|
75 |
-
| 1.
|
76 |
| 1.7884 | 16.9524 | 178 | 1.8125 |
|
77 |
| 1.7892 | 18.0 | 189 | 1.8125 |
|
78 |
-
| 1.7825 | 18.9524 | 199 | 1.
|
79 |
| 1.7906 | 19.0476 | 200 | 1.8125 |
|
80 |
|
81 |
|
|
|
58 |
| Training Loss | Epoch | Step | Validation Loss |
|
59 |
|:-------------:|:-------:|:----:|:---------------:|
|
60 |
| 2.3024 | 0.9524 | 10 | 2.1503 |
|
61 |
+
| 2.1107 | 2.0 | 21 | 2.0370 |
|
62 |
| 2.0147 | 2.9524 | 31 | 1.9716 |
|
63 |
| 1.9577 | 4.0 | 42 | 1.9243 |
|
64 |
+
| 1.9087 | 4.9524 | 52 | 1.8953 |
|
65 |
| 1.8825 | 6.0 | 63 | 1.8716 |
|
66 |
| 1.8667 | 6.9524 | 73 | 1.8558 |
|
67 |
| 1.8488 | 8.0 | 84 | 1.8429 |
|
68 |
| 1.8284 | 8.9524 | 94 | 1.8343 |
|
69 |
| 1.8201 | 10.0 | 105 | 1.8270 |
|
70 |
+
| 1.8129 | 10.9524 | 115 | 1.8219 |
|
71 |
| 1.8028 | 12.0 | 126 | 1.8179 |
|
72 |
| 1.7987 | 12.9524 | 136 | 1.8155 |
|
73 |
| 1.7938 | 14.0 | 147 | 1.8137 |
|
74 |
+
| 1.79 | 14.9524 | 157 | 1.8129 |
|
75 |
+
| 1.7902 | 16.0 | 168 | 1.8126 |
|
76 |
| 1.7884 | 16.9524 | 178 | 1.8125 |
|
77 |
| 1.7892 | 18.0 | 189 | 1.8125 |
|
78 |
+
| 1.7825 | 18.9524 | 199 | 1.8125 |
|
79 |
| 1.7906 | 19.0476 | 200 | 1.8125 |
|
80 |
|
81 |
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
-
"k_proj",
|
25 |
"v_proj",
|
26 |
"gate_proj",
|
27 |
-
"
|
28 |
"down_proj",
|
29 |
-
"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"v_proj",
|
24 |
"gate_proj",
|
25 |
+
"up_proj",
|
26 |
"down_proj",
|
27 |
+
"q_proj",
|
28 |
+
"k_proj",
|
29 |
+
"o_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 17426248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c587df1586ec935d93f9952356b438517b40f5c4ad9e0ae8f99ed5a144a94d35
|
3 |
size 17426248
|
runs/Aug29_07-58-46_algo-2/events.out.tfevents.1724918357.algo-2.67.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92241d60b0720b8c28aa4ca92c54f8ba8d22d187ff2e341efa6605ae3862590d
|
3 |
+
size 15293
|
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 sha256:900cba946f024ad97f4f693140e395ca5de6858bec1ae80b49a41cd0c161e551
|
3 |
size 5240
|