Training in progress, epoch 2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e463f4d9e16ecaf4a60a3b396702f06ecc551699ed3c9a3594ad25d7980ad52
+oid sha256:461efed3c23271fd56410c7ca7b80996fbd31b52647b85f8638c42a6f040b596
 size 109069176

runs/Jul09_03-41-07_nb-79d9ab29-73f9-44c0-a896-df6270c588fc-6bccdc4c95-d2bzz/events.out.tfevents.1752032493.nb-79d9ab29-73f9-44c0-a896-df6270c588fc-6bccdc4c95-d2bzz.768.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e82c8154b886bbbed3ad39febe48826eb73e534371a47c7628d45bd7e29c1a
+size 25970

runs/Jul09_04-08-59_nb-79d9ab29-73f9-44c0-a896-df6270c588fc-6bccdc4c95-d2bzz/events.out.tfevents.1752034161.nb-79d9ab29-73f9-44c0-a896-df6270c588fc-6bccdc4c95-d2bzz.768.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e177b32048a1bc74a8ac99505e215b86bf711b4d18d3322504203bedee069175
+size 6946

runs/Jul09_04-13-16_nb-79d9ab29-73f9-44c0-a896-df6270c588fc-6bccdc4c95-d2bzz/events.out.tfevents.1752034405.nb-79d9ab29-73f9-44c0-a896-df6270c588fc-6bccdc4c95-d2bzz.768.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a333993d8451cdfcbb4a29cb3ab856df5ac282b6e310f9417c4e9805341a1545
+size 7984

runs/Jul09_04-20-40_nb-79d9ab29-73f9-44c0-a896-df6270c588fc-6bccdc4c95-d2bzz/events.out.tfevents.1752034847.nb-79d9ab29-73f9-44c0-a896-df6270c588fc-6bccdc4c95-d2bzz.768.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01cdae8ad1b34bedee6019888e167ac158c7249840d7b53acffde25ea8eda19b
+size 104195

special_tokens_map.json

@@ -7,11 +7,11 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|end_of_text|>",
+    "content": "<|eot_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|end_of_text|>"
+  "pad_token": "<|eot_id|>"
 }

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 1024,
+    "max_length": 2042,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -2050,13 +2050,14 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
+  "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": "<|end_of_text|>",
+  "eos_token": "<|eot_id|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|end_of_text|>",
+  "pad_token": "<|eot_id|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20941180b276331bf7aa9066d73f944563e4c89a8f3b87363748cd4d2ca3d54d
+oid sha256:a6286358a7fc536d696b60de46cef40fc148ae6d8dce5a985a9af09700228159
 size 5496