Training in progress, step 500

README.md

@@ -38,10 +38,11 @@ The following hyperparameters were used during training:
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
+- lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 2.0
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
 
 ### Training results
 
@@ -49,7 +50,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.34.1
+- Transformers 4.35.0
 - Pytorch 2.1.0+cu118
 - Datasets 2.14.6
 - Tokenizers 0.14.1

adapter_config.json

@@ -16,14 +16,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "lm_head",
-    "down_proj",
     "v_proj",
     "gate_proj",
-    "k_proj",
     "up_proj",
-    "q_proj"
+    "lm_head",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6db25a3cb8b1b46a974c9ab041f5ce60acaef0ab07ffd7db1dea43c855c9601
+oid sha256:65d13c2845ccc57375ac09ab86f7a208daec0227a864806d622fbef18c78a207
 size 170244818

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ec6e9d3f977022ac2b9955b3b9402097fd7d7b2426ecf50e5f7c8baaa88435d
+oid sha256:06e599f303eabb49ad2fc5299d033e5e9ef3bde53a4384640576fb7ce6d0fa36
 size 170142632

runs/Nov09_03-08-41_0d7ebc02c5c5/events.out.tfevents.1699499321.0d7ebc02c5c5.824.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785f68b1f0eba349ff228cb36fa4677ba15b10e749391b8e0f571d67f0066552
+size 8574

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e9a037cb6a22f46a1a596ebf5e042d64ac5cefb0edc157309873d2f68758b05
+oid sha256:c86f4cbb16abaca98ff384da542ad81d5d7cea536194f4c093956a2ee40123a6
 size 4728