Training in progress, epoch 0

adapter_config.json

@@ -1,4 +1,5 @@
 {
+  "alpha_pattern": {},
   "auto_mapping": {
     "base_model_class": "MistralForCausalLM",
     "parent_library": "transformers.models.mistral.modeling_mistral"
@@ -8,17 +9,24 @@
   "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": 32,
   "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 64,
+  "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
     "v_proj"
   ],
-  "task_type": null
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8148dd8adea1327f39cb0de1c15698f7f5105dbd7c4ec2fe90f0354ebb3e55bd
+oid sha256:7189708c7e729ed8056bc769b02116a2616e96fdb75d18571a6e8b6738dc7c1d
 size 109069176

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -134,6 +139,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a717807a1d9e858fcd9add1a628eac101343f1e7aeace20949eed0a8f4315b
-size 4920
+oid sha256:2a712b5bef0955a52b4f98e5e92e74d7e37465da135ff4a6e01695d5297c2dd0
+size 4984