Training in progress, epoch 1

README.md

@@ -45,7 +45,7 @@ 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: 3
+- num_epochs: 1
 
 ### Training results
 

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
+    "q_proj",
     "o_proj",
-    "gate_proj",
+    "up_proj",
     "v_proj",
+    "gate_proj",
     "k_proj",
-    "q_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccabce0aece80f0b534bb2eefc8f2de883ab10235bb55021fd2e88e14a894adf
+oid sha256:9fc832bdf3ef02697a19f8edef626a4ee203ccecc9765f1d17af731e3569f1a3
 size 2772497632

runs/Jul23_21-54-13_merlin.doc.ic.ac.uk/events.out.tfevents.1721768061.merlin.doc.ic.ac.uk

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:644023fa50c5f98d5077ff6a1d80fc84c110c3680e884da1ae1b468d663a71b2
-size 9957
+oid sha256:e714a35fc675a899bd06f9fc5fc7318945d7db056cc065a00f8a479d36c4900f
+size 15232

runs/Jul23_21-57-03_cloud-vm-47-192.doc.ic.ac.uk/events.out.tfevents.1721768333.cloud-vm-47-192.doc.ic.ac.uk

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f7ea940c13b94d5cd61b4924b3016a576ac7be187e51bef296e385355a1794
-size 6188
+oid sha256:82224e4d5abc8f3b62d2910e83e2a853dc68f3a117ac3131c895583912e4a25e
+size 10109