End of training

README.md

@@ -40,7 +40,7 @@ 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
-- training_steps: 200
+- training_steps: 500
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -8,18 +8,21 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
+  "loftq_config": {},
   "lora_alpha": 16,
   "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_h_to_4h",
     "dense_4h_to_h",
+    "dense",
     "query_key_value",
-    "dense"
+    "dense_h_to_4h"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71258ca8225ab6a8bf33458edcea76007452e847dc3b5bbeee2bcbbe75d4d13c
+oid sha256:eab1a2aa95059e6cd002735f0882f6b7de9e08b5c69e9639218b1ecea2446bc5
 size 522227376

runs/Dec08_15-24-00_fbcc3b6d014c/events.out.tfevents.1702049080.fbcc3b6d014c.312.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5efef46e3c787fda477a2b46a1cdfada20be2e3cbab70b333691a6c250236d5d
+size 12911

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f202f832e860fb8231cfbeed1715946106baf5585b24946b0a35f38ec5997762
+oid sha256:fd10f2615a3e6c518153fc4c55ad3cac280631bf86eaf5d63367a4eb73780d2e
 size 4600