Training in progress, epoch 1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "base_model_name_or_path": "Upstage/SOLAR-10.7B-Instruct-v1.0",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,12 +20,12 @@
   "revision": null,
   "target_modules": [
     "down_proj",
-    "lm_head",
     "q_proj",
+    "lm_head",
     "o_proj",
+    "up_proj",
     "gate_proj",
     "k_proj",
-    "up_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93d3a77eb6848ddf0d5e68293b91ec0c2c5e188e05ce355c0125faf54040246
-size 609389712
+oid sha256:a2e5f3d328b1aa5a250555d56ef8e2c76f2d6c8c47a86565b7a29b8eef7572ae
+size 651362912

runs/Dec14_21-55-39_e9f4ff0213cb/events.out.tfevents.1702590953.e9f4ff0213cb.540.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1984adaf4eab2425d431c232e98e73d67929941d1c0cce2d6c1d5ea55bcdb310
+size 6549

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 2048,
+    "max_length": 4096,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -29,15 +29,15 @@
   },
   "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 %}",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "model_max_length": 2048,
+  "model_max_length": 4096,
   "pad_token": "</s>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4236fa3e64a5d0348766df96696fd6ec7830dbf15a1ab898aff916eea7f0d1f
+oid sha256:4afa890dcddb41365b4343e28704035b60d83312f7c66e1583fd822688cdce8f
 size 4728