End of training

README.md

@@ -36,8 +36,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 3
-- eval_batch_size: 3
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.9.0
-- Transformers 4.38.2
-- Pytorch 2.1.0+cu121
+- PEFT 0.10.0
+- Transformers 4.39.1
+- Pytorch 2.2.1+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

adapter_config.json

@@ -6,6 +6,7 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
@@ -19,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "o_proj",
     "v_proj",
+    "q_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf67056181301cceb3944b2f70cad9102c91430891c60ffbd33c413b1935913
+oid sha256:c13f081f213b196b7f3e8688d19886615d834d8f71eb6175bd53a277f3ccfdb4
 size 54560368

runs/Mar23_09-20-55_6a9aee56c5e9/events.out.tfevents.1711186532.6a9aee56c5e9.3111.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d76cb8ef61163c24f30dd0594861b2d53517090a85319befa86c28a5e60ec6
+size 5647

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 16000,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ec84d813dd91765ca3ee23df4018dd0961da74e740217aa2fc7b6246bcb04c0
+oid sha256:f7030e151a7cb221aeccd9565fdf8d25e95904a92612cf92e4f31d0e13459988
 size 4984