Training in progress, step 625

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
+  "base_model_name_or_path": "ahxt/LiteLlama-460M-1T",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_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:d877c44144a8bacc5e3dafc9d5cfc32d8169a72526921e1b72acc9a291e22f8e
-size 134235048
+oid sha256:6ebac840943abfc4e22bff536a5597a0f698f9e6165c51d18d0417f3d9adf38b
+size 19673632

runs/Aug01_10-47-52_fastgpuserv/events.out.tfevents.1722491274.fastgpuserv.2113260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea32443cb43711c1a8f3b9a7c6fbfc180424cf50862b663ddfcd0468dd88a28
+size 5752

runs/Aug01_10-51-09_fastgpuserv/events.out.tfevents.1722491470.fastgpuserv.2113260.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89db4b1d7228307280aa3594178c3b17922ad3e04d1b2446a8e2ec2aebc66615
+size 5753

runs/Aug01_10-55-04_fastgpuserv/events.out.tfevents.1722491706.fastgpuserv.2113260.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:034df33b3f1320467f8fc105405fffe445e701405a84ac31a39ad367bebcad98
+size 5752

runs/Aug01_11-01-02_fastgpuserv/events.out.tfevents.1722492064.fastgpuserv.2134733.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f63a830d193f53344febcc33dfa34ab61f00285032e3878af71b493ddde937
+size 5753

runs/Aug01_11-02-42_fastgpuserv/events.out.tfevents.1722492163.fastgpuserv.2134733.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb01cadc06f59c43c9f071f8a399a5ffb04867d74ead76ccb43c6ca702eb777
+size 12697

runs/Aug01_14-05-55_fastgpuserv/events.out.tfevents.1722503158.fastgpuserv.6531.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210ecb64a0f7832fb67fe3c9c5b4bb675f3820b2fc78ab7939d5fbbe5c6f8617
+size 4184

runs/Aug01_14-08-57_fastgpuserv/events.out.tfevents.1722503340.fastgpuserv.7077.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca9054c067e0196ed042b95af7a47122046e9703ad44707d016c515df877980
+size 11399

special_tokens_map.json

@@ -1,27 +1,21 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "</s>",
+    "content": "#",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "#",
   "unk_token": {
-    "content": "<unk>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": true,
     "rstrip": false,

tokenizer_config.json

@@ -1,26 +1,25 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
+  "add_bos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "1": {
+      "content": "\"",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "2": {
+      "content": "#",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "50256": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -28,18 +27,12 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": false,
-  "max_length": 512,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "sp_model_kwargs": {},
-  "stride": 0,
-  "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "#",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "#",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e319b39897641377afbe6098aec71383e9563fd47d322772c14245fe379794
+oid sha256:8d4b657ec66cb9698ba6f4bfb8dfdca966a93c2f6574c2d7b7c148d2ae8d40cb
 size 5432