Training in progress, step 200
Browse files- README.md +5 -5
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- runs/May20_21-22-34_c07e70359ae1/events.out.tfevents.1716240216.c07e70359ae1.13468.0 +2 -2
- step_0/adapter_config.json +3 -3
- step_0/training_args.bin +1 -1
- step_400/adapter_config.json +2 -2
- step_400/adapter_model.safetensors +1 -1
- step_400/training_args.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/
|
20 |
# llama2-7b-sft-lora
|
21 |
|
22 |
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
|
@@ -38,15 +38,15 @@ More information needed
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
-
- learning_rate:
|
42 |
- train_batch_size: 4
|
43 |
- eval_batch_size: 8
|
44 |
- seed: 4
|
45 |
- distributed_type: multi-GPU
|
46 |
-
- num_devices:
|
47 |
- gradient_accumulation_steps: 4
|
48 |
-
- total_train_batch_size:
|
49 |
-
- total_eval_batch_size:
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: cosine
|
52 |
- training_steps: 2000
|
|
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/quirky_lats_at_mats/harmbench_adv_training/runs/4u15rhza)
|
20 |
# llama2-7b-sft-lora
|
21 |
|
22 |
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
|
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
- train_batch_size: 4
|
43 |
- eval_batch_size: 8
|
44 |
- seed: 4
|
45 |
- distributed_type: multi-GPU
|
46 |
+
- num_devices: 4
|
47 |
- gradient_accumulation_steps: 4
|
48 |
+
- total_train_batch_size: 64
|
49 |
+
- total_eval_batch_size: 32
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: cosine
|
52 |
- training_steps: 2000
|
adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"k_proj",
|
|
|
20 |
"up_proj",
|
21 |
-
"down_proj",
|
22 |
"o_proj",
|
23 |
-
"
|
24 |
-
"q_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"v_proj",
|
20 |
"k_proj",
|
21 |
+
"q_proj",
|
22 |
"up_proj",
|
|
|
23 |
"o_proj",
|
24 |
+
"down_proj"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 258001832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c891e8033ec5889b3efe65331a4ed6be13c023e34b298adecfbceea43f1bd2f3
|
3 |
size 258001832
|
runs/May20_21-22-34_c07e70359ae1/events.out.tfevents.1716240216.c07e70359ae1.13468.0
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 sha256:3e5507cf6157f547a01011e9dddf7bd84c92010d995222b86e45f00585d3ab76
|
3 |
+
size 11416
|
step_0/adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"k_proj",
|
|
|
20 |
"up_proj",
|
21 |
-
"down_proj",
|
22 |
"o_proj",
|
23 |
-
"
|
24 |
-
"q_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"v_proj",
|
20 |
"k_proj",
|
21 |
+
"q_proj",
|
22 |
"up_proj",
|
|
|
23 |
"o_proj",
|
24 |
+
"down_proj"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
step_0/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d5a2bc4755dd43d7d40ba9e853eb1528b6f82c1de5eaf623707ae7753c17001
|
3 |
size 6200
|
step_400/adapter_config.json
CHANGED
@@ -16,10 +16,10 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"k_proj",
|
20 |
"v_proj",
|
21 |
-
"
|
22 |
"q_proj",
|
|
|
23 |
"o_proj",
|
24 |
"down_proj"
|
25 |
],
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"v_proj",
|
20 |
+
"k_proj",
|
21 |
"q_proj",
|
22 |
+
"up_proj",
|
23 |
"o_proj",
|
24 |
"down_proj"
|
25 |
],
|
step_400/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 258001832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4654ba892d076143ec5687141d3afb7b697a533f01f788e060d51bb4b2daf0d3
|
3 |
size 258001832
|
step_400/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d5a2bc4755dd43d7d40ba9e853eb1528b6f82c1de5eaf623707ae7753c17001
|
3 |
size 6200
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d5a2bc4755dd43d7d40ba9e853eb1528b6f82c1de5eaf623707ae7753c17001
|
3 |
size 6200
|