Training in progress, step 500

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,
@@ -16,17 +16,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "down_proj",
+    "gate_proj",
     "q_proj",
     "up_proj",
+    "v_proj",
     "o_proj",
-    "down_proj",
-    "gate_proj",
-    "v_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:a7c1d57ef1af02622d9229ce7a326907af8b91303b85bade0c79b9fe5773faf6
-size 167832240
+oid sha256:ac9fe8124dab0a7b6cbefd18116896f74607adc3059aa9292828dd90fb3803cc
+size 5544997664

runs/Jul14_17-00-25_ml-cluster/events.out.tfevents.1720976433.ml-cluster

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e569eea8199281c2dfe7bda04b7445f9a51d75a33d7d28099c7df517d282e5
+size 6302

special_tokens_map.json

@@ -1,23 +1,21 @@
 {
-  "bos_token": {
-    "content": "<|begin_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|end_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>"
 }

tokenizer.json

@@ -2314,7 +2314,16 @@
     },
     {
       "id": 128256,
-      "content": "[PAD]",
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 128257,
+      "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json

@@ -2049,7 +2049,15 @@
       "special": true
     },
     "128256": {
-      "content": "[PAD]",
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128257": {
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2057,14 +2065,19 @@
       "special": true
     }
   },
-  "bos_token": "<|begin_of_text|>",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
+  "eos_token": "<|im_end|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
+  "pad_token": "<|im_end|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e2008df619968f860bea0ef68062b4745c3ab9910343223e27015d96b4ec03d
+oid sha256:0f0e6f3c363821084a6d606990254d5b42965195600b3d1b40c019958ae101be
 size 5432