HuggingFaceTB/SmolLM-360M-Instruct
Browse files- README.md +25 -11
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- runs/Aug28_13-15-09_algo-1/events.out.tfevents.1724850924.algo-1.67.0 +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 [HuggingFaceTB/SmolLM-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss:
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -39,7 +39,7 @@ More information needed
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
-
- learning_rate: 0.
|
43 |
- train_batch_size: 8
|
44 |
- eval_batch_size: 8
|
45 |
- seed: 42
|
@@ -51,18 +51,32 @@ The following hyperparameters were used during training:
|
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: constant
|
53 |
- lr_scheduler_warmup_ratio: 0.03
|
54 |
-
- num_epochs:
|
55 |
|
56 |
### Training results
|
57 |
|
58 |
-
| Training Loss | Epoch
|
59 |
-
|
60 |
-
| 2.
|
61 |
-
| 2.
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
|
68 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [HuggingFaceTB/SmolLM-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.7710
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.001
|
43 |
- train_batch_size: 8
|
44 |
- eval_batch_size: 8
|
45 |
- seed: 42
|
|
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: constant
|
53 |
- lr_scheduler_warmup_ratio: 0.03
|
54 |
+
- num_epochs: 20
|
55 |
|
56 |
### Training results
|
57 |
|
58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
59 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
60 |
+
| 2.2354 | 0.9524 | 10 | 2.1179 |
|
61 |
+
| 2.0715 | 2.0 | 21 | 2.0075 |
|
62 |
+
| 1.9885 | 2.9524 | 31 | 1.9518 |
|
63 |
+
| 1.9385 | 4.0 | 42 | 1.9090 |
|
64 |
+
| 1.8925 | 4.9524 | 52 | 1.8811 |
|
65 |
+
| 1.867 | 6.0 | 63 | 1.8578 |
|
66 |
+
| 1.8507 | 6.9524 | 73 | 1.8416 |
|
67 |
+
| 1.8314 | 8.0 | 84 | 1.8279 |
|
68 |
+
| 1.8086 | 8.9524 | 94 | 1.8177 |
|
69 |
+
| 1.7969 | 10.0 | 105 | 1.8085 |
|
70 |
+
| 1.7858 | 10.9524 | 115 | 1.8016 |
|
71 |
+
| 1.7711 | 12.0 | 126 | 1.7957 |
|
72 |
+
| 1.7616 | 12.9524 | 136 | 1.7904 |
|
73 |
+
| 1.7504 | 14.0 | 147 | 1.7854 |
|
74 |
+
| 1.7399 | 14.9524 | 157 | 1.7821 |
|
75 |
+
| 1.732 | 16.0 | 168 | 1.7791 |
|
76 |
+
| 1.7218 | 16.9524 | 178 | 1.7755 |
|
77 |
+
| 1.7142 | 18.0 | 189 | 1.7735 |
|
78 |
+
| 1.6992 | 18.9524 | 199 | 1.7708 |
|
79 |
+
| 1.6993 | 19.0476 | 200 | 1.7710 |
|
80 |
|
81 |
|
82 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"up_proj",
|
25 |
"o_proj",
|
26 |
"q_proj",
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"k_proj",
|
|
|
24 |
"o_proj",
|
25 |
"q_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"v_proj",
|
28 |
+
"up_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 17426248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31c655e84ff620beca55c5028fc8e5f810800373205f1a8dab2d4379558b1bef
|
3 |
size 17426248
|
runs/Aug28_13-15-09_algo-1/events.out.tfevents.1724850924.algo-1.67.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f93a6bb2ccc83a4cd3e3ac02d6438a63a93a6aa05d9ae451b70af47e501e78c
|
3 |
+
size 15294
|
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 sha256:4fef496847ab2924b511e4f67bfdd2b7f90755757b282a49c79c06fd4b763a1a
|
3 |
size 5240
|