Training in progress, epoch 1
Browse files- README.md +4 -4
- adapter_config.json +8 -9
- adapter_model.safetensors +1 -1
- runs/Apr08_08-52-32_krishnan-srinivas-nc40/events.out.tfevents.1744108008.krishnan-srinivas-nc40.4023.1 +3 -0
- runs/Apr08_10-27-18_krishnan-srinivas-nc40/events.out.tfevents.1744108046.krishnan-srinivas-nc40.4023.2 +3 -0
- training_args.bin +2 -2
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 |
-
"k_proj",
|
| 31 |
-
"o_proj",
|
| 32 |
-
"up_proj",
|
| 33 |
"down_proj",
|
| 34 |
-
"
|
| 35 |
-
"
|
|
|
|
| 36 |
"v_proj",
|
|
|
|
|
|
|
| 37 |
"out_proj",
|
| 38 |
-
"
|
| 39 |
-
"
|
|
|
|
| 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 sha256:10a0983125ec85332be9a20afe7bea354a20e1c91fe76a8b79fc75e4717deeb9
|
| 3 |
size 2839124552
|
runs/Apr08_08-52-32_krishnan-srinivas-nc40/events.out.tfevents.1744108008.krishnan-srinivas-nc40.4023.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f6d884688e6a5d25e173c90476bf1e2701e22ede66b814f1265385636788e84
|
| 3 |
+
size 6786
|
runs/Apr08_10-27-18_krishnan-srinivas-nc40/events.out.tfevents.1744108046.krishnan-srinivas-nc40.4023.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09c8d384cfeb08c1ff7516945ac631bdf96ac9ed7add6a0ee0ac14c48da05dd0
|
| 3 |
+
size 7197
|
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:ebd1f8bb9b9e95ed8e54d12109eb1983e52ba023c81787751513b2ae39d2cdc6
|
| 3 |
+
size 5624
|