Training in progress, epoch 0

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
+    "o_proj",
     "gate_proj",
     "down_proj",
+    "v_proj",
     "up_proj",
-    "k_proj",
-    "o_proj"
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768cf83bc9afd144d587ca13d2816431c89798366d93d6c1a5974b6ae6b8905b
+oid sha256:8e3472fdd5c6da114424c4a57548ac3cf9bc7393391fde06d2e3772049e07b5f
 size 2772497632

runs/Jul24_08-57-18_merlin.doc.ic.ac.uk/events.out.tfevents.1721807921.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85bff7eae7bb40a0c10b49d4b5c6faaed749d6e76033f1589ccff8d6626f2caa
+size 8420

tokenizer_config.json

@@ -2053,11 +2053,15 @@
   "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
+  "max_length": 2048,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|eot_id|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc36a475354e472599c026be6dffa9bdec341e38b233ccebd4465d336c543c9
+oid sha256:47a4f6f55b916a7df7f57cd6aa6786955f4e36220806ed57bb1ac09a1fbf0176
 size 5048