Training in progress, step 500

README.md

@@ -38,11 +38,10 @@ 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: cosine
+- lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.05
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 3.0
-- mixed_precision_training: Native AMP
+- num_epochs: 2.0
 
 ### Training results
 
@@ -50,7 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.0
+- Transformers 4.34.1
 - 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": [
-    "down_proj",
-    "q_proj",
+    "o_proj",
     "lm_head",
+    "down_proj",
+    "v_proj",
     "gate_proj",
     "k_proj",
     "up_proj",
-    "v_proj",
-    "o_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d13c2845ccc57375ac09ab86f7a208daec0227a864806d622fbef18c78a207
+oid sha256:2c649c6af991909d31c0865df8a7420648ce47ac1af2a21727f094da14c7f31f
 size 170244818

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d67db2fe097039e7e121d5e518b0780b8071f6455e481f9de237920ee2df858
+oid sha256:2c960cb8679ac9980bbb8ae67fe2e9a6523414b956985dceccb0036a245dfe03
 size 170142632

runs/Nov08_23-33-54_af85daa2b52f/events.out.tfevents.1699486434.af85daa2b52f.1074.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ecfdcb901e54152b7710ad2750b491c437daeb1f2ac8148ad8da206eb4b6f4
+size 8574

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b5edcdf0a098a183caa61eb62ae740ef5fafa6286c25b57b828f4cf4d9d16c9
+oid sha256:6e9a037cb6a22f46a1a596ebf5e042d64ac5cefb0edc157309873d2f68758b05
 size 4728