Training in progress, epoch 0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Open-Orca/Mistral-7B-OpenOrca",
+  "base_model_name_or_path": "ai-forever/mGPT",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
-    "k_proj",
-    "o_proj",
-    "gate_proj",
-    "q_proj",
-    "down_proj"
+    "c_fc",
+    "c_proj",
+    "c_attn"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c080a65f73d94577b5eeae381f5b725cf6f6620f6bcb8f0bf04f77fc38b0f4f3
-size 167832240
+oid sha256:bc37db4145117ddae06ee852a185d64c9672fcc2b13fac6e4dc6cccfe8a5ff10
+size 50356480

runs/Dec15_20-34-10_4d38b0951ba7/events.out.tfevents.1734295265.4d38b0951ba7.228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ef1a1012ab75f1bc53f9df08e2766c03f33b03c652f464b41faa78e7e30cfed
+size 5599

runs/Dec15_20-46-50_4d38b0951ba7/events.out.tfevents.1734295621.4d38b0951ba7.4136.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3cd16b65b94cdc4f109ecce898e348ae4a2599ae75ed5d7910c7bbc9c9d37cf
+size 6080

runs/Dec15_20-50-08_4d38b0951ba7/events.out.tfevents.1734295829.4d38b0951ba7.4136.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48fbf89c912d8f7ff22a648cbcbdfb10f251fe80640feb6829b9265c00f1ee6c
+size 6079

special_tokens_map.json

@@ -1,24 +1,44 @@
 {
   "bos_token": {
     "content": "<s>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|im_end|>",
   "unk_token": {
     "content": "<unk>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": true,
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
     "single_word": false
   }
 }

tokenizer_config.json

@@ -1,21 +1,20 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_bos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "<s>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     },
@@ -27,36 +26,42 @@
       "single_word": false,
       "special": true
     },
-    "32000": {
-      "content": "<|im_end|>",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32001": {
-      "content": "<|im_start|>",
-      "lstrip": true,
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
       "normalized": false,
-      "rstrip": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": false,
-  "eos_token": "<|im_end|>",
-  "legacy": true,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|im_end|>",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sep_token": "</s>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "left",
   "trust_remote_code": false,
-  "unk_token": "<unk>",
-  "use_default_system_prompt": true,
-  "use_fast": true
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b9a1cf0404ce6c011f321d4d2f393f4b9fa744f8db33df3f167d5a9f30a88bb
+oid sha256:8a459bf4d215f65a9e2eb1918db43aac5fcd723e6c0ff9758d31125ebcbc2686
 size 5560