Model save

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- training_steps: 250
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60330201cb5b0a820f8ba3f627888bcf8d8aaec45c1e2ace7e486fcc24b4dadf
+oid sha256:e81b2125abd427e6bc280c704230f9d9477819a8752efa3c65a9bff668a6193d
 size 7382336

runs/Feb23_12-48-05_6a55cc4830ee/events.out.tfevents.1708692653.6a55cc4830ee.936.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d87984458a5ad5b3ce1072c504144c12e3ff4998b4e576f5bdceb9fcd4fb17aa
+size 5045

runs/Feb23_13-03-08_6a55cc4830ee/events.out.tfevents.1708693571.6a55cc4830ee.936.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90467d273f3e666c344ca5b1bf6211de32266f9fb59e7426de78c30c4417bdab
+size 5046

runs/Feb23_13-08-20_6a55cc4830ee/events.out.tfevents.1708693867.6a55cc4830ee.936.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6d2ade0943b9b15c6409229906f39df21f478f47353ac93320ac8bef6cdd05
+size 5046

runs/Feb23_13-16-44_6a55cc4830ee/events.out.tfevents.1708694372.6a55cc4830ee.8321.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c479207d0e381106ac648b0bdd20092a5e9c6bc29df0751969884f248b4e0f02
+size 5046

runs/Feb23_13-21-04_6a55cc4830ee/events.out.tfevents.1708694651.6a55cc4830ee.8321.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b234d9a724618bebb57425764f57f96e45e39f1cf6ce6a942b8f894754a8364d
+size 7506

tokenizer_config.json

@@ -56,7 +56,7 @@
     "<end_of_turn>"
   ],
   "bos_token": "<bos>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% 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'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% 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'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
   "legacy": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b47d3383f9e27458088194ec7f5ca55cb3eea6e20090f2c1b369b6015a1b046
+oid sha256:dc5838e39b8e011372fbaa449e528877905e3f9902b2aa8c4028641a2c295567
 size 4920