Training in progress, step 500

adapter_config.json

@@ -1,8 +1,13 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama"
+  },
   "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -10,20 +15,21 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
-  "task_type": "CAUSAL_LM",
+  "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 sha256:7bc979d8f45d3a68b1fb596defd32fa57a9350e5cc1c3cd5638c1b0a347b6a54
-size 33571624
+oid sha256:1a6a7db52feb0622cd0c0879c56a47d3b77955e9f74b5c261452aa39e1665f22
+size 16794200

runs/Feb07_11-24-11_autodl-container-ae2d4d944b-64da26b0/events.out.tfevents.1738898662.autodl-container-ae2d4d944b-64da26b0.1665.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ba8ce926ea590888567b341fa611027b129cd0603f043e84d56ff6e2f05e78
+size 5161

runs/Feb07_11-25-04_autodl-container-ae2d4d944b-64da26b0/events.out.tfevents.1738898716.autodl-container-ae2d4d944b-64da26b0.1833.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ab01abe2c0af56ac4a52760304eefb303524c30580b8330afb3b8ca7bcb4eb
+size 286549

runs/Feb07_11-31-54_autodl-container-ae2d4d944b-64da26b0/events.out.tfevents.1738899123.autodl-container-ae2d4d944b-64da26b0.2083.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb27deab953c0942970635d74cea290e43e2c92f22f974a4eadf2ed5edb0ee34
+size 14476

runs/Feb07_11-32-52_autodl-container-ae2d4d944b-64da26b0/events.out.tfevents.1738899183.autodl-container-ae2d4d944b-64da26b0.2219.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce452010389b0069f332b74f6df9d5eaaf9d6f3b73722f2af9a1f0f2e1b129c8
+size 9508

runs/Feb07_11-37-42_autodl-container-ae2d4d944b-64da26b0/events.out.tfevents.1738899472.autodl-container-ae2d4d944b-64da26b0.2403.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc9bba4d21289b482f671d5527c937ffad82e947d5bc67ca607c07a73f632aec
+size 73439

runs/Feb07_11-46-37_autodl-container-ae2d4d944b-64da26b0/events.out.tfevents.1738900006.autodl-container-ae2d4d944b-64da26b0.2668.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf0b06eed5895eb1a9478ba2a7838652d337b23d7311d7e15e9922bb514a7c8a
+size 136145

runs/Feb07_12-02-54_autodl-container-ae2d4d944b-64da26b0/events.out.tfevents.1738900984.autodl-container-ae2d4d944b-64da26b0.3043.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5ec6fba81aac983c95bccabd9e9e36c09c87e4677730bbc4b5222740d87346
+size 110192

special_tokens_map.json

@@ -13,7 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -34,7 +34,7 @@
   "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": null,
   "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c475dd4b8c9f09f7d2e2020d9060e7404ece41105bbfcad9d9739bd67c7b37a4
-size 5816
+oid sha256:f781d828578bf6b12bdd9b91a328bf105f029202a0ff7eaf0c08d29afede3b7e
+size 5496