End of training
Browse files- README.md +2 -6
- adapter_config.json +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [obrmmk/tinycodellama-jp-1.3b-1k](https://huggingface.co/obrmmk/tinycodellama-jp-1.3b-1k) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -43,15 +43,11 @@ The following hyperparameters were used during training:
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 50
|
46 |
-
- training_steps:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
-
| 0.7064 | 0.16 | 100 | 1.0144 |
|
54 |
-
| 0.6659 | 0.33 | 200 | 0.9164 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [obrmmk/tinycodellama-jp-1.3b-1k](https://huggingface.co/obrmmk/tinycodellama-jp-1.3b-1k) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 1.3754
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 50
|
46 |
+
- training_steps: 50
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
|
|
|
|
|
|
|
|
51 |
|
52 |
|
53 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -19,10 +19,10 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
22 |
"q_proj",
|
23 |
"k_proj",
|
24 |
-
"o_proj"
|
25 |
-
"v_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_dora": false,
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
"q_proj",
|
24 |
"k_proj",
|
25 |
+
"o_proj"
|
|
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_dora": false,
|
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:ffed5f8ea0860d188317af6c76611724acdd5e3d277fffefaead7c24524f57f4
|
3 |
size 4920
|