Training in progress, step 100

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "MohamedAhmedAE/Llama3-8B-Medical-Finetune-V2-pad-unk-token",
+  "base_model_name_or_path": "MohamedAhmedAE/Llama3-8B-Medical-Finetune-V3-Merged-unk-token",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 256,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
-    "k_proj",
-    "down_proj",
-    "gate_proj",
     "v_proj",
-    "q_proj"
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_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 sha256:57f529300eeb0957bd99f77b268696e0ca8e391e5fdad16ad0fd8857763df262
+oid sha256:8c06156259b7b487a0160a0853ce60dca62895b5ad1fad5c64ef7c7097d61d8f
 size 1342238560

special_tokens_map.json

@@ -1,21 +1,25 @@
 {
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "bos_token": {
-    "content": "<|begin_of_text|>",
+    "content": "<|im_start|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|eot_id|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|unk|>",
+  "pad_token": "<unk>",
   "unk_token": {
-    "content": "<|unk|>",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 4096,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -2309,7 +2314,7 @@
     },
     {
       "id": 128256,
-      "content": "<|pad|>",
+      "content": "<|im_start|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -2318,7 +2323,16 @@
     },
     {
       "id": 128257,
-      "content": "<|unk|>",
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 128258,
+      "content": "<unk>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json

@@ -2049,7 +2049,7 @@
       "special": true
     },
     "128256": {
-      "content": "<|pad|>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2057,7 +2057,15 @@
       "special": true
     },
     "128257": {
-      "content": "<|unk|>",
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128258": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -2065,17 +2073,26 @@
       "special": true
     }
   },
-  "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 %}",
+  "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": "<|eot_id|>",
+  "device_map": "auto",
+  "eos_token": "<|im_end|>",
+  "max_length": 4096,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 2024,
-  "pad_token": "<|unk|>",
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
   "padding_side": "right",
+  "stride": 0,
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "<|unk|>"
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1739cd9c2bb0672980a28b26f47683a8b80b522d2f06b0b740331e7e294e3edf
-size 5496
+oid sha256:bb149e35d0f0ee3e9bffe7360518648bd13f48a4d5bcea2c3c065dcd78579484
+size 5624