Training in progress, epoch 1

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e3472fdd5c6da114424c4a57548ac3cf9bc7393391fde06d2e3772049e07b5f
+oid sha256:cf5deb378c9129bce6f7de7f25860c2cb5111c7d9e389a574de9a32d75b1109a
 size 2772497632

runs/Jul25_08-15-17_merlin.doc.ic.ac.uk/events.out.tfevents.1721891729.merlin.doc.ic.ac.uk

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1582c97957b2cc09264ffc115b79b615f0e953fcfa56f80d9e16cd02a3b6fa91
+size 22415

tokenizer_config.json

@@ -2053,15 +2053,11 @@
   "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|>",
-  "stride": 0,
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a4f6f55b916a7df7f57cd6aa6786955f4e36220806ed57bb1ac09a1fbf0176
+oid sha256:f250493a7505a9f8d7921a54e8e00cc2259ea51a4a6595131855703ceb91dc71
 size 5048