Model save

README.md

@@ -34,14 +34,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 4
-- eval_batch_size: 8
+- train_batch_size: 8
+- eval_batch_size: 16
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 2
-- gradient_accumulation_steps: 128
-- total_train_batch_size: 1024
-- total_eval_batch_size: 16
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - num_epochs: 1

adapter_config.json

@@ -17,8 +17,8 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "o_proj",
     "k_proj",
+    "o_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM"

runs/Feb01_23-43-05_r2d2-devbox-l74gc/events.out.tfevents.1738453396.r2d2-devbox-l74gc.1257.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf942c518dd1b5e9a21affc6f681ba4d2a69423a5e423e5cd10a09d929bbdc9
+size 4619

step_0/README.md

@@ -203,60 +203,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ### Framework versions
 
 
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
 - PEFT 0.6.1

step_0/adapter_config.json

@@ -16,9 +16,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "k_proj",
     "o_proj",
-    "q_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM"

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:474709a6006c3092e509b34915c981e6f121c05a99366513abb5f1339867c2c0
+oid sha256:ba6015c2dd85cc13191835636419dbe31d742db4f1d045f1538497665918b6d1
 size 5816

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a452bfaf833a0e1a022c8aa6d5cbbfcd12ed965b49a5d3e2bdb03a64568a5d
+oid sha256:ba6015c2dd85cc13191835636419dbe31d742db4f1d045f1538497665918b6d1
 size 5816