Training in progress, step 100

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
-    "gate_proj",
-    "up_proj",
     "down_proj",
+    "up_proj",
     "q_proj",
     "o_proj",
-    "v_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72d92ea60154f7be85c721556b2f6e30aa243be84b80d01b626f9658cba8d51
-size 83946192
+oid sha256:a4af8aa1e7cd698009bb2c6c47ce7e3388059c964dace1843bdb30b95e6eb0e5
+size 167832240

runs/May04_03-53-22_p3-16xlarge-us-east-2-dy-p3-16xlarge-us-east-2-3/events.out.tfevents.1714796450.p3-16xlarge-us-east-2-dy-p3-16xlarge-us-east-2-3.91325.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc2744e4a798ccb56512ae44c377e3b3e4295489df2fd5438addb8419b0e6b28
+size 5296

runs/May04_04-21-58_p3-16xlarge-us-east-2-dy-p3-16xlarge-us-east-2-3/events.out.tfevents.1714796552.p3-16xlarge-us-east-2-dy-p3-16xlarge-us-east-2-3.104358.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91783f54679bd429470bdb716d6e396061d5698ac7d72590e4c1f8e54e678f20
+size 5296

runs/May14_18-33-49_training-queue-st-p4d-24xlarge-6/events.out.tfevents.1715711686.training-queue-st-p4d-24xlarge-6.5976.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53527a62e7a3647942ad07162d079721ccb964b4d6780cc620ccd952dfb4540c
+size 5280

runs/May14_18-35-03_training-queue-st-p4d-24xlarge-6/events.out.tfevents.1715711731.training-queue-st-p4d-24xlarge-6.6870.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e70d209ff7199f90465e0f28e557e54dc3cfa04d98911cbd6f31f6e27482f3
+size 5280

runs/May14_18-39-15_training-queue-st-p4d-24xlarge-6/events.out.tfevents.1715711983.training-queue-st-p4d-24xlarge-6.10103.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae3606e43487d305eb3f04e92cc40db8d850f132f0e26c658db04428dde1e5b
+size 9627

tokenizer_config.json

@@ -32,6 +32,7 @@
   "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "legacy": true,
   "model_max_length": 2048,
   "pad_token": "</s>",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7363d8866f508cbd41a5146a67dbf35d0166e0b8deac6c64e21e8fc6cdab8f8
-size 5176
+oid sha256:e07b802ae9915472e1e390561bcd6af54050e097dedea4bf7c8d260c9a38aecb
+size 5112