Training in progress, step 100

adapter_config.json

@@ -16,12 +16,12 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 2,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b455760216b0089c76f223174053d8427baf82a6a024f322fe739aafb7c2df51
-size 3424688
+oid sha256:7425dc27e44d063f9dc71b7ee53c376347837a85607a0fdcd10e516ba3f01ee0
+size 6832600

runs/May02_22-27-57_ip-10-192-12-6/events.out.tfevents.1714688882.ip-10-192-12-6.4963.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7fa0fdf02a598adfcfb5f6c537b0452c6c95f9ec6dc54214d113bf067a36cb
+size 5291

runs/May02_22-29-26_ip-10-192-12-6/events.out.tfevents.1714688971.ip-10-192-12-6.6363.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193a2a89aefaaf16262e814bd2abef72c77b9341a2bf8327a841e79e02c21222
+size 5291

runs/May02_22-30-35_ip-10-192-12-6/events.out.tfevents.1714689046.ip-10-192-12-6.6363.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2965f37c0d63f6fef4430280a8f13817c29495232bc1a36b66e8ffd88f6ed101
+size 5291

runs/May02_22-32-02_ip-10-192-12-6/events.out.tfevents.1714689133.ip-10-192-12-6.8741.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba655e01275b91f7db5c5bcc422e6c89e97ac336ad63051992c2fc44abc4502
+size 5498

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 280,
+    "max_length": 285,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -2052,6 +2052,7 @@
   "bos_token": "<|begin_of_text|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
+  "max_length": 280,
   "model_input_names": [
     "input_ids",
     "attention_mask"
@@ -2059,5 +2060,8 @@
   "model_max_length": 8192,
   "pad_token": "<|end_of_text|>",
   "padding_side": "right",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173f7b953d068616de371e5278125998c60b01a753ac546253522d04793ac376
+oid sha256:2b6e1f707a8c05a8eca0bc9e165f6ca86a0f960f70760ac382c3978a71609e91
 size 5048