Training in progress, step 150

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "BioMistral/BioMistral-DARE-NS",
+  "base_model_name_or_path": "BioMistral/BioMistral-7B-DARE",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 1024,
+  "lora_alpha": 2048,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 512,
+  "r": 1024,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
     "o_proj",
-    "q_proj",
     "gate_proj",
     "k_proj",
-    "v_proj"
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270d708c97a46296284f422448ccce5611a11cc286ba7f72ce14f4ab947a8a09
-size 5368770952
+oid sha256:c3e613a6c6444409f23c43c3b9347fe1096f3050cef84f253661a57e4ba91865
+size 10737480672

runs/Sep17_13-30-22_524427e95e1b/events.out.tfevents.1726579836.524427e95e1b.511.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5795d00e43ce41a66ba589a8a05f750a6eacfa05e5df9fb8dcead98ba3154749
+size 11452

special_tokens_map.json

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

tokenizer_config.json

@@ -30,6 +30,7 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbe2503616bfbd271c086110c48c2b4ebc9ce4a5a77b58f4cfcd54e3a6bab336
+oid sha256:67b5e0816e534be7763cb62bdba0122e6978559ef83027680998287cc7f72524
 size 5432