Training in progress, epoch 0

adapter_config.json

@@ -6,24 +6,18 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
-  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "loftq_config": {},
   "lora_alpha": 16,
   "lora_dropout": 0.05,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
+  "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1278aa7425dace5a76fbf3d0bcbbaf84be546ff9d2690393fcfbaf5453eec5f
+oid sha256:25a2710e0d4284fad1ce9dbe15095b84a272ff38140547a82daadb6c8ac9097f
 size 9022864

runs/May26_14-31-28_nc383ar3my/events.out.tfevents.1716733889.nc383ar3my.76.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a837162abded76c3d745f7b7b54236221f820e955bf7305987dcb6bc192b28dd
+size 5294

tokenizer.json

@@ -139,7 +139,6 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
-    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json

@@ -1,6 +1,4 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -31,6 +29,7 @@
   "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "legacy": false,
   "model_max_length": 2048,
   "pad_token": "</s>",
   "padding_side": "right",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c609729bd926dda2886652557084b8373c1f85e2d84ea5010caafd277179b105
-size 5112
+oid sha256:a0b2d6d7a74acb20027b4245ba06849210082b9a1965ffec1a8c7af3d1ca78aa
+size 4600