talazz/falcon

README.md

@@ -13,12 +13,7 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<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/team2001/falcon/runs/awqj4mrk)
-[<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/team2001/falcon/runs/awqj4mrk)
-[<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/team2001/falcon/runs/lq1v9kx5)
-[<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/team2001/falcon/runs/lq1v9kx5)
-[<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/team2001/falcon/runs/lq1v9kx5)
-[<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/team2001/falcon/runs/lq1v9kx5)
+[<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/team2001/falcon/runs/g89n84q2)
 # results
 
 This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on an unknown dataset.
@@ -49,7 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 2
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
-    "dense_h_to_4h",
     "dense",
-    "dense_4h_to_h"
+    "dense_4h_to_h",
+    "dense_h_to_4h",
+    "query_key_value"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4724b2e8238c5839864e6fd5c887d6b01d57a2b987dc96ba109afc00986f2e
+oid sha256:7c199d8563d2475ada86114386192ba9d6addf3af7a9bd49d15215bac0cf7452
 size 130583912

runs/May18_21-08-26_50c731965516/events.out.tfevents.1716066584.50c731965516.851.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e354e7ccff1b7d0c7cc9a669db92243046ce7e0343ea787f32779d7c8393df9
+size 16816

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e6dc1265cda0347e7adeec07916f41c4bcb1cb01405dae1d6aa6a77dfc24569
+oid sha256:1311408a6959dd88543c60097d041cb07fac4a54a00bc9e684287e00039940d3
 size 5112