Model save
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [google/codegemma-7b](https://huggingface.co/google/codegemma-7b) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -128,7 +128,45 @@ The following hyperparameters were used during training:
|
|
| 128 |
| 0.0655 | 3.8202 | 3600 | 0.0684 |
|
| 129 |
| 0.0671 | 3.8732 | 3650 | 0.0679 |
|
| 130 |
| 0.0642 | 3.9263 | 3700 | 0.0676 |
|
| 131 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 132 |
|
| 133 |
|
| 134 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [google/codegemma-7b](https://huggingface.co/google/codegemma-7b) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0558
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 128 |
| 0.0655 | 3.8202 | 3600 | 0.0684 |
|
| 129 |
| 0.0671 | 3.8732 | 3650 | 0.0679 |
|
| 130 |
| 0.0642 | 3.9263 | 3700 | 0.0676 |
|
| 131 |
+
| 0.0676 | 3.9801 | 3750 | 0.0670 |
|
| 132 |
+
| 0.0756 | 4.0331 | 3800 | 0.0669 |
|
| 133 |
+
| 0.0691 | 4.0862 | 3850 | 0.0667 |
|
| 134 |
+
| 0.0699 | 4.1392 | 3900 | 0.0659 |
|
| 135 |
+
| 0.0633 | 4.1923 | 3950 | 0.0658 |
|
| 136 |
+
| 0.0673 | 4.2453 | 4000 | 0.0655 |
|
| 137 |
+
| 0.0656 | 4.2983 | 4050 | 0.0653 |
|
| 138 |
+
| 0.0595 | 4.3514 | 4100 | 0.0648 |
|
| 139 |
+
| 0.0685 | 4.4044 | 4150 | 0.0644 |
|
| 140 |
+
| 0.0635 | 4.4574 | 4200 | 0.0641 |
|
| 141 |
+
| 0.0742 | 4.5105 | 4250 | 0.0637 |
|
| 142 |
+
| 0.0617 | 4.5635 | 4300 | 0.0634 |
|
| 143 |
+
| 0.0628 | 4.6165 | 4350 | 0.0629 |
|
| 144 |
+
| 0.0635 | 4.6696 | 4400 | 0.0629 |
|
| 145 |
+
| 0.0595 | 4.7226 | 4450 | 0.0623 |
|
| 146 |
+
| 0.0621 | 4.7757 | 4500 | 0.0624 |
|
| 147 |
+
| 0.0635 | 4.8287 | 4550 | 0.0621 |
|
| 148 |
+
| 0.0671 | 4.8817 | 4600 | 0.0615 |
|
| 149 |
+
| 0.0618 | 4.9348 | 4650 | 0.0613 |
|
| 150 |
+
| 0.0623 | 4.9878 | 4700 | 0.0606 |
|
| 151 |
+
| 0.057 | 5.0408 | 4750 | 0.0609 |
|
| 152 |
+
| 0.0529 | 5.0939 | 4800 | 0.0603 |
|
| 153 |
+
| 0.0582 | 5.1469 | 4850 | 0.0607 |
|
| 154 |
+
| 0.0577 | 5.1999 | 4900 | 0.0599 |
|
| 155 |
+
| 0.0561 | 5.2530 | 4950 | 0.0600 |
|
| 156 |
+
| 0.0591 | 5.3060 | 5000 | 0.0592 |
|
| 157 |
+
| 0.054 | 5.3591 | 5050 | 0.0596 |
|
| 158 |
+
| 0.0628 | 5.4121 | 5100 | 0.0590 |
|
| 159 |
+
| 0.0545 | 5.4651 | 5150 | 0.0586 |
|
| 160 |
+
| 0.0545 | 5.5182 | 5200 | 0.0582 |
|
| 161 |
+
| 0.0527 | 5.5712 | 5250 | 0.0581 |
|
| 162 |
+
| 0.0522 | 5.6242 | 5300 | 0.0581 |
|
| 163 |
+
| 0.0525 | 5.6773 | 5350 | 0.0575 |
|
| 164 |
+
| 0.0535 | 5.7303 | 5400 | 0.0574 |
|
| 165 |
+
| 0.0541 | 5.7833 | 5450 | 0.0579 |
|
| 166 |
+
| 0.0482 | 5.8364 | 5500 | 0.0566 |
|
| 167 |
+
| 0.0506 | 5.8894 | 5550 | 0.0562 |
|
| 168 |
+
| 0.0572 | 5.9425 | 5600 | 0.0558 |
|
| 169 |
+
| 0.0497 | 5.9955 | 5650 | 0.0558 |
|
| 170 |
|
| 171 |
|
| 172 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 23 |
"q_proj",
|
| 24 |
"k_proj",
|
| 25 |
-
"o_proj",
|
| 26 |
-
"gate_proj",
|
| 27 |
"up_proj",
|
| 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 |
"q_proj",
|
| 25 |
"k_proj",
|
|
|
|
|
|
|
| 26 |
"up_proj",
|
| 27 |
"down_proj",
|
| 28 |
+
"gate_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 1600180696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e2f635b99931890c1d838b560eaa0cca7bba66fc748339db6fb17c7e799fd3f
|
| 3 |
size 1600180696
|
runs/Sep19_17-16-33_m3h111/events.out.tfevents.1758266889.m3h111.863562.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9692a1f48516532133b3e83a0d18622797cc90cbec658beaaab6ca02830d1ea
|
| 3 |
+
size 57491
|
runs/Sep19_22-54-52_m3h111/events.out.tfevents.1758287146.m3h111.2294041.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f494797c8b23fed081821b488309aa8a00d64cc21d0043797c12a74285ee285a
|
| 3 |
+
size 5777
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a16b815f53bd4513c2b4f07bc95d454eb203dbe028b2a1c071040d5bdd8f77f
|
| 3 |
size 6904
|