Training in progress, step 500

adapter_config.json

@@ -3,37 +3,29 @@
   "auto_mapping": null,
   "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "bias": "none",
-  "corda_config": null,
-  "eva_config": null,
-  "exclude_modules": null,
   "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": 64,
-  "lora_bias": false,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
-    "down_proj",
     "v_proj",
-    "up_proj",
+    "gate_proj",
+    "down_proj",
     "o_proj",
-    "gate_proj"
+    "k_proj",
+    "q_proj",
+    "up_proj"
   ],
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "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 sha256:0f41f87cf74c110e9e1193011267a840e015a98ec11aaa41114f03de36218605
-size 335604696
+oid sha256:0125633087172414d3bfe773c60ec2f28414659891b9a2443eabaaf840f781b5
+size 335605144

runs/Jun14_14-08-15_nio2xbg6s6/events.out.tfevents.1749910096.nio2xbg6s6.292.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85c58fd4a9104c73114d77ab2d45c5b07208f2d792b69f410d998c118f95df50
+size 4773

tokenizer_config.json

@@ -30,13 +30,12 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
-  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1f8acc6fee1da9104e6417d454e3c4ab03f3899c67dd6b65d8c131cc31909e
-size 5368
+oid sha256:756d407ae9c6d98508652ed40b389920d9a93b3751c9f3b448070a24f0e90620
+size 5048