sanduntg/llama_2_dpo_with_reward_1000
Browse files
README.md
CHANGED
|
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
|
|
| 41 |
- total_train_batch_size: 64
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
-
- num_epochs:
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
|
|
|
| 41 |
- total_train_batch_size: 64
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 1
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
adapter_config.json
CHANGED
|
@@ -6,6 +6,7 @@
|
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
| 8 |
"init_lora_weights": true,
|
|
|
|
| 9 |
"layers_pattern": null,
|
| 10 |
"layers_to_transform": null,
|
| 11 |
"loftq_config": {},
|
|
|
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
| 8 |
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
"layers_pattern": null,
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 134235048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b81da75c8efc20cb169e645668a633395dc6cbb114b8a343ddbd7160b51df37a
|
| 3 |
size 134235048
|
runs/Mar20_16-41-22_d12c3011894c/events.out.tfevents.1710952897.d12c3011894c.1141.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b149ebb3e748c46d748529eebcf4be8c38f18f7ea0416aedf0096999a86c46be
|
| 3 |
+
size 7404
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4475
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04e50e81ce114fffd92cc882f3345c51ab5afad372b5e8f0d3c7e7bd0a80f6cf
|
| 3 |
size 4475
|