End of training

README.md

@@ -34,7 +34,7 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.15.1
+- TRL: 0.15.2
 - Transformers: 4.48.3
 - Pytorch: 2.5.1+cu124
 - Datasets: 3.3.2

adapter_config.json

@@ -5,7 +5,7 @@
   "bias": "lora_only",
   "eva_config": null,
   "exclude_modules": null,
-  "fan_in_fan_out": true,
+  "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
@@ -23,9 +23,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "c_fc",
     "c_proj",
-    "c_attn",
-    "c_fc"
+    "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 sha256:5a985c949388a45893d301d366e100fb9422b24a62cd6d5cd8084759f27012ed
-size 397959576
+oid sha256:8e69dd0819ff9b5022a5c890d9fb44c2b10ee605bc39bcff1533232a58547332
+size 4730632

special_tokens_map.json

@@ -1,22 +1,6 @@
 {
-  "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|>",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
   "unk_token": "<|endoftext|>"
 }

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 256,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -38,24 +43,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 64000,
-      "content": "<|im_start|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 64001,
-      "content": "<|im_end|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -32,36 +32,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "64000": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "64001": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "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 %}",
+  "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|im_end|>",
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
-  "trust_remote_model": true,
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44329eba918abad06f64871058cbe7feec8541eb6a0cd805c7aca3a98a599272
+oid sha256:9907bdf5c44b343a9fb589f61e65b0b7b8baff0d5edff6054e6ed0f0ae46acfc
 size 5560