Training in progress, epoch 0
Browse files- .amlignore +6 -0
- .amlignore.amltmp +6 -0
- README.md +4 -4
- adapter_config.json +6 -7
- adapter_model.safetensors +1 -1
- runs/Apr07_14-59-32_krishnan-srinivas-nc40/.amlignore +6 -0
- runs/Apr07_14-59-32_krishnan-srinivas-nc40/.amlignore.amltmp +6 -0
- runs/Apr08_08-52-32_krishnan-srinivas-nc40/events.out.tfevents.1744102378.krishnan-srinivas-nc40.4023.0 +3 -0
- training_args.bin +2 -2
.amlignore
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## This file was auto generated by the Azure Machine Learning Studio. Please do not remove.
|
2 |
+
## Read more about the .amlignore file here: https://docs.microsoft.com/azure/machine-learning/how-to-save-write-experiment-files#storage-limits-of-experiment-snapshots
|
3 |
+
|
4 |
+
.ipynb_aml_checkpoints/
|
5 |
+
*.amltmp
|
6 |
+
*.amltemp
|
.amlignore.amltmp
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## This file was auto generated by the Azure Machine Learning Studio. Please do not remove.
|
2 |
+
## Read more about the .amlignore file here: https://docs.microsoft.com/azure/machine-learning/how-to-save-write-experiment-files#storage-limits-of-experiment-snapshots
|
3 |
+
|
4 |
+
.ipynb_aml_checkpoints/
|
5 |
+
*.amltmp
|
6 |
+
*.amltemp
|
README.md
CHANGED
@@ -34,10 +34,10 @@ This model was trained with SFT.
|
|
34 |
|
35 |
### Framework versions
|
36 |
|
37 |
-
- TRL: 0.
|
38 |
-
- Transformers: 4.
|
39 |
-
- Pytorch: 2.
|
40 |
-
- Datasets: 3.
|
41 |
- Tokenizers: 0.21.1
|
42 |
|
43 |
## Citations
|
|
|
34 |
|
35 |
### Framework versions
|
36 |
|
37 |
+
- TRL: 0.15.2
|
38 |
+
- Transformers: 4.51.0
|
39 |
+
- Pytorch: 2.6.0
|
40 |
+
- Datasets: 3.3.2
|
41 |
- Tokenizers: 0.21.1
|
42 |
|
43 |
## Citations
|
adapter_config.json
CHANGED
@@ -3,7 +3,6 @@
|
|
3 |
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "google/gemma-3-4b-pt",
|
5 |
"bias": "none",
|
6 |
-
"corda_config": null,
|
7 |
"eva_config": null,
|
8 |
"exclude_modules": null,
|
9 |
"fan_in_fan_out": false,
|
@@ -27,19 +26,19 @@
|
|
27 |
"rank_pattern": {},
|
28 |
"revision": null,
|
29 |
"target_modules": [
|
|
|
|
|
30 |
"gate_proj",
|
|
|
31 |
"v_proj",
|
32 |
-
"out_proj",
|
33 |
"q_proj",
|
|
|
|
|
34 |
"up_proj",
|
35 |
-
"fc2",
|
36 |
"k_proj",
|
37 |
-
"
|
38 |
-
"o_proj",
|
39 |
-
"down_proj"
|
40 |
],
|
41 |
"task_type": "CAUSAL_LM",
|
42 |
-
"trainable_token_indices": null,
|
43 |
"use_dora": false,
|
44 |
"use_rslora": false
|
45 |
}
|
|
|
3 |
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "google/gemma-3-4b-pt",
|
5 |
"bias": "none",
|
|
|
6 |
"eva_config": null,
|
7 |
"exclude_modules": null,
|
8 |
"fan_in_fan_out": false,
|
|
|
26 |
"rank_pattern": {},
|
27 |
"revision": null,
|
28 |
"target_modules": [
|
29 |
+
"down_proj",
|
30 |
+
"fc1",
|
31 |
"gate_proj",
|
32 |
+
"lm_head",
|
33 |
"v_proj",
|
|
|
34 |
"q_proj",
|
35 |
+
"o_proj",
|
36 |
+
"out_proj",
|
37 |
"up_proj",
|
|
|
38 |
"k_proj",
|
39 |
+
"fc2"
|
|
|
|
|
40 |
],
|
41 |
"task_type": "CAUSAL_LM",
|
|
|
42 |
"use_dora": false,
|
43 |
"use_rslora": false
|
44 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2839124552
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ed0f1cbcdb1a9800411e6f156484db47f1c04871e8b72662471eaaf24832deb
|
3 |
size 2839124552
|
runs/Apr07_14-59-32_krishnan-srinivas-nc40/.amlignore
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## This file was auto generated by the Azure Machine Learning Studio. Please do not remove.
|
2 |
+
## Read more about the .amlignore file here: https://docs.microsoft.com/azure/machine-learning/how-to-save-write-experiment-files#storage-limits-of-experiment-snapshots
|
3 |
+
|
4 |
+
.ipynb_aml_checkpoints/
|
5 |
+
*.amltmp
|
6 |
+
*.amltemp
|
runs/Apr07_14-59-32_krishnan-srinivas-nc40/.amlignore.amltmp
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## This file was auto generated by the Azure Machine Learning Studio. Please do not remove.
|
2 |
+
## Read more about the .amlignore file here: https://docs.microsoft.com/azure/machine-learning/how-to-save-write-experiment-files#storage-limits-of-experiment-snapshots
|
3 |
+
|
4 |
+
.ipynb_aml_checkpoints/
|
5 |
+
*.amltmp
|
6 |
+
*.amltemp
|
runs/Apr08_08-52-32_krishnan-srinivas-nc40/events.out.tfevents.1744102378.krishnan-srinivas-nc40.4023.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8731184db1bf88eeb5238041b9a1fd6579b5eacbdc2ce8e749d283f9d80ed370
|
3 |
+
size 25504
|
training_args.bin
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 sha256:67bb03ad9de8799da734261d37374eb331bb04961734047106c169a3f18e4ebe
|
3 |
+
size 5624
|