End of training
Browse files- README.md +3 -3
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- runs/Jan30_16-15-07_1c9b503a0ca8/events.out.tfevents.1738253710.1c9b503a0ca8.345.0 +3 -0
- runs/Jan30_16-17-11_1c9b503a0ca8/events.out.tfevents.1738253842.1c9b503a0ca8.345.1 +3 -0
- runs/Jan30_16-30-00_1c9b503a0ca8/events.out.tfevents.1738254600.1c9b503a0ca8.345.2 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -34,14 +34,14 @@ More information needed
|
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
- learning_rate: 0.0001
|
| 37 |
-
- train_batch_size:
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
- gradient_accumulation_steps: 2
|
| 41 |
-
- total_train_batch_size:
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
-
- num_epochs:
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
|
|
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
- learning_rate: 0.0001
|
| 37 |
+
- train_batch_size: 2
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
- gradient_accumulation_steps: 2
|
| 41 |
+
- total_train_batch_size: 4
|
| 42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 20
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"gate_proj",
|
| 27 |
"k_proj",
|
| 28 |
"q_proj",
|
| 29 |
-
"
|
|
|
|
| 30 |
"o_proj",
|
| 31 |
"up_proj",
|
| 32 |
-
"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
| 26 |
"k_proj",
|
| 27 |
"q_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
"o_proj",
|
| 31 |
"up_proj",
|
| 32 |
+
"down_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"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 75012288
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afcb60863fc2172e7b72b7cf95ce542343f16da3ed273074168547fd75011294
|
| 3 |
size 75012288
|
runs/Jan30_16-15-07_1c9b503a0ca8/events.out.tfevents.1738253710.1c9b503a0ca8.345.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3cf662bbf70586541dc0dc0bfc4e7a6abb3058156451b07ee210923cbd7103d
|
| 3 |
+
size 5165
|
runs/Jan30_16-17-11_1c9b503a0ca8/events.out.tfevents.1738253842.1c9b503a0ca8.345.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4c2b4e74905c4f2b5da074b8686d8a514da06c02a9034637299f393342f373e
|
| 3 |
+
size 10799
|
runs/Jan30_16-30-00_1c9b503a0ca8/events.out.tfevents.1738254600.1c9b503a0ca8.345.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ab9bcc1cf628035abd8eb0cdd686c47a6c85b8e773d7498eafdb7d373a6e7c6
|
| 3 |
+
size 5928
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5a0f430e52f5d04e0c2c40836dea750d58d508074b1116ce739af8e50eca6ca
|
| 3 |
size 5368
|