End of training
Browse files- .gitattributes +1 -0
- README.md +5 -2
- adapter_config.json +5 -5
- nipsllm_13350.1733587985088903357.pt.trace.json +3 -0
- training_args.bin +1 -1
.gitattributes
CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
nipsllm_3601.1733584591283538056.pt.trace.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
nipsllm_3601.1733584591283538056.pt.trace.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
nipsllm_13350.1733587985088903357.pt.trace.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: cosine
|
47 |
- lr_scheduler_warmup_ratio: 0.02
|
48 |
-
- num_epochs: 0.
|
49 |
|
50 |
### Training results
|
51 |
|
@@ -79,6 +79,9 @@ The following hyperparameters were used during training:
|
|
79 |
| 1.2469 | 0.3368 | 52 | 1.2331 |
|
80 |
| 1.1653 | 0.3498 | 54 | 1.2330 |
|
81 |
| 1.2752 | 0.3628 | 56 | 1.2332 |
|
|
|
|
|
|
|
82 |
|
83 |
|
84 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.2331
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: cosine
|
47 |
- lr_scheduler_warmup_ratio: 0.02
|
48 |
+
- num_epochs: 0.4
|
49 |
|
50 |
### Training results
|
51 |
|
|
|
79 |
| 1.2469 | 0.3368 | 52 | 1.2331 |
|
80 |
| 1.1653 | 0.3498 | 54 | 1.2330 |
|
81 |
| 1.2752 | 0.3628 | 56 | 1.2332 |
|
82 |
+
| 1.2077 | 0.3757 | 58 | 1.2331 |
|
83 |
+
| 1.1729 | 0.3887 | 60 | 1.2330 |
|
84 |
+
| 1.2643 | 0.4016 | 62 | 1.2331 |
|
85 |
|
86 |
|
87 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"down_proj",
|
24 |
"up_proj",
|
25 |
-
"gate_proj",
|
26 |
-
"o_proj",
|
27 |
-
"k_proj",
|
28 |
"q_proj",
|
29 |
-
"
|
|
|
|
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"up_proj",
|
|
|
|
|
|
|
24 |
"q_proj",
|
25 |
+
"k_proj",
|
26 |
+
"v_proj",
|
27 |
+
"o_proj",
|
28 |
+
"down_proj",
|
29 |
+
"gate_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
nipsllm_13350.1733587985088903357.pt.trace.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a49e55b6fc8b50e7db83fc03202259c26e51bff767c1c57b8612b194e4eb244
|
3 |
+
size 9843112280
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4acdf5d9d14749a7ba943f69011cd34aabbb367437fc76cd520d695b4617adad
|
3 |
size 5304
|