feat: update to better 70b dpo tune

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "../lhopelr",
+  "_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -22,8 +22,8 @@
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 128262
 }

generation_config.json

@@ -6,7 +6,7 @@
     128009
   ],
   "max_length": 4096,
-  "temperature": 0.5,
-  "top_p": 0.65,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.41.2"
 }

model-00001-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f7e037ffca87c43bd6c33921cb003f97b2c5522050e28528748bca522ba44e
-size 4584507096
+oid sha256:89c0cf12c018c38cf7c8b391c163150bf9b7ed0cc6d9ef39dea1a8cb05ccc6c3
+size 1667887104

model-00002-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152060fe040e9b5998e6dd2b5b13b40c915f863cc9a6284d295396a1284f0b40
-size 4664167352
+oid sha256:b773c80ad2a40b3874b5e7e27bae3435a0c7b46b548960f21474641392fd1f01
+size 2271522816

model-00003-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a061687519af8d5a7fc1264d3d34fe0e697cd5155950daff906e176970b7c4ce
-size 4999711672
+oid sha256:e8f2dfa59ce691f77e9f9c61fd5c430f6a6fd05f0e8c7af261dcab451347b9dc
+size 2902474752

model-00004-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de50ab3a14e90f393e74e6f343a01340c0b1ed133d137396b78e0557e061479c
-size 4966157008
+oid sha256:684654854a05cf480fd6078dad5fdc30dc3150abdd0e473a1e8a77ee4a8f7e09
+size 1926475776

model-00005-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e180c7e17bf15e8597f5cdaa8516da90195c8e639439420a1ec27367a38c6cdd
-size 4664134384
+oid sha256:d24b87bb35ccfa24148e645511011a0a606b7104f63cffaa18ce62ddb2027acd
+size 2115403776

model-00006-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155b37117038fb13769cb4b202f1555e50300b7d46c0a1bee131930e447c5f5e
-size 4664167384
+oid sha256:5e4d22a5c2587e7201e580e30b33983672512c61cf360c9c52f167831ed5fca3
+size 2085535744

model-00007-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e54b4a54fe8734c639482f9f826bb6d231341b3718e7fac85deba693511b2f0
-size 4664167376
+oid sha256:4a16256256708582ebb192d49321a2fb587f7e26b4cf34b3aef7b320871ecf49
+size 3320299520

model-00008-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6b26e3ef15b68704c39dcf8b87946a59a73c5255f9deac0ec8a14e3ba1d2f0
-size 4999711704
+oid sha256:3893f5ee9b0aeed6f38412cdff44d1f9a9acc972188d889c46961ae6743303dc
+size 2075869184

model-00009-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed02a5de74f8d2afe1e98ccb07536765bed767cf791b97365fd40bf9edc2157
-size 4966157032
+oid sha256:ac3300128ce519ca18bec75cc818270a33f02b21dff51bc139862896fdd49cc7
+size 2178609152

model-00010-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e1ee49eb39a0276adc97cf4370607b83de0f8dc909af9af5248b09fe0201a6
-size 4664134384
+oid sha256:86db844cd3f365fd1f45fb907beff98f0081813f71d8356a820684a88731437c
+size 2317238272

model-00011-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad7eea3d8f9a8e69a61f6e99309bedcf130c761765448d622aa0ebb1ed7daf6
-size 4664167384
+oid sha256:54caa3ed702ad418e81d669b4d4b6e5e09eb2c8f18d22264b2b59a75edb93929
+size 2744877056

model-00012-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f3690df426707ff7c362175542f58ff46306d431437610ccee9e5233a788c9c
-size 4664167376
+oid sha256:b9d7e17c168fa1255949fbfe076a48e9f2275946afef00db8a4deab2c9029932
+size 1326813184

model-00013-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e2f654d6e9b4f18b4c63dc6590b1228c40cff8667ee8da1b246e9a76dc4277
-size 4999711704
+oid sha256:09397e734de2662b3769f2aed6775f3a3dc4d970a8c3bdad41319e828f41ee3a
+size 1561567232

model-00014-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d03359a52d3b0ef5ad8b6603b59dac8e77b842cc654cda989a990d4fcc197ec
-size 4966157032
+oid sha256:9326ddb10d7590df13bac3090d7bf48bf86ff32d64f1e462dd1e19491a0b63fa
+size 1665040384

model-00015-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad9f84260eb8fc91eb7b43ed0bbffdb85418de4439c08e33f51624af21c49f4c
-size 4664134384
+oid sha256:6ae0863d919bcaaacdbe4d96226aaf2a15c3bec7a145a9baaa18f0a172d06a1a
+size 2390306816

model-00016-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67321ffc4ab419157094ce482bf96c45dcb8393595c90516b3848dbd737e07db
-size 4664167384
+oid sha256:6697f8a014e85835d44b83b402dd91b6712b203d1a2cb7708083d9e533550115
+size 2289614848

model-00017-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cfe9a8a8aa69d43ea72a1c66b939da7017a02f507f77c0a3bad036663c4380f
-size 4664167376
+oid sha256:e2558e7fc3dc3fdfde2892167f1ccb2c14847f7321f3814d0db5b41c88fe2ec6
+size 2891030528

model-00018-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9d61cf88ccd2f621110b2b5e459fa24573a41d6aa60f9ecebf8c965c4a1dc3
-size 4999711704
+oid sha256:dee78cab4bd9e87394346a01e1bea9327dc7b5f3755a85dc49fe89cef48b2ea3
+size 2341629952

model-00019-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa01ec81e85ff5d89a70c3a3432fe1f5f9be6acc1afcb5622d223d1d68adec4
-size 4966157032
+oid sha256:92a1d92ae627b31b4ab238023bda6eb2a250a6fcc9ad1638d45e5ce100ed9712
+size 2105212928

model-00020-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9271368ec7cd322562f984a72ea668a8bc5ed28772b172a2ee6cb9a93b0e8881
-size 4664134384
+oid sha256:1b896da817bee7d9ed78115ddc8e040390ee0530829fef1ede2e76d34a28606a
+size 2810728448

model-00021-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b328c000ced927882a4807940f74d455f808bc8a15c84beed7a23877b2821a
-size 4664167384
+oid sha256:8a2c8b57bc56b79abb1912fa03e49c89ecf8fb7e915bf42f7b15824d37ec7a54
+size 3029651456

model-00022-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acbb3fce214e0d2c8a25871f8b0e503a59dd3796b2fda8c55fa1dd046fba5e00
-size 4664167376
+oid sha256:74f4cc5b8bfcf45af3e350e1e017995d4b537d06fb9f746074e5c34027243678
+size 2894012416

model-00023-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0353539a790745edcff64de400774e029a3ea141586a0ad5d148af6a74956c34
-size 4999711704
+oid sha256:5b06e19f02ab4cbf03c5c5c76ab2881b2c54cd10cd18b84f14d9ef94c9db6286
+size 3130228736

model-00024-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407acbfce4999fe8a0c63db56154e0f54238b0cde6575275e4c75119ff541a3d
-size 4966157032
+oid sha256:3cfb5fc51d3d63ccd00156687760a316c39bb658eb522aad546f8538f7ce8354
+size 2198028288

model-00025-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b8485f8f15e1aa3bbef696c04b7d818be04a79d1c793529cfa6825a1d5733e3
-size 4664134384
+oid sha256:c15a0be5c7422bdbb8cb6821223c9784986149a688222df17a7517e6b7a653b7
+size 1973522432

model-00026-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c75e3ff116cd6e7a26790b8d74be671d1c2f0e3ae4938bb8bdb6bc4732dfadd
-size 4664167384
+oid sha256:75edb61f8380b8538c97e2836193ac0ebc69709581e3e07eb7de7ae20e583ab8
+size 2898800640

model-00027-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:039b0e5b995cbe78816e29c400e8f06d1b68b53f446334ea52ef33844e71e8b8
-size 4664167376
+oid sha256:dce82bb4cd6b6d85a4777610c56bd2e4e641f9184d837586b4150314cfff5d55
+size 3183329280

model-00028-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1c9146b6ecc41a93d95c0192c08b66c7905bd58cf3f328a2f1fe0426f914db
-size 4999711704
+oid sha256:092b657556324213f842104f7a6323c96f19240be6fd59bcad858b388599c3bc
+size 2281537536

model-00029-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ab5484612af6bd508774d552f18082a2908f1232a18d199a8e3b615042aa352
-size 4966173512
+oid sha256:d0ac27bb6c9fcd4e6aaf102900ec9febe1ef499bc39eeab9306395e5d3207a53
+size 1924145152

model-00030-of-00030.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21bb67ee79bbfbcb678de20af10fe999cb2cf66474b7d8c22aad5e18b7a1d092
-size 2101444736
+oid sha256:61042debc22650145088384224e4ea399eb746ac8a92b63af5f334b573a85c40
+size 1739042816

special_tokens_map.json

@@ -1,11 +1,47 @@
 {
   "additional_special_tokens": [
-    "<tool_call>",
-    "</tool_call>",
-    "<tools>",
-    "</tools>",
-    "<tool_response>",
-    "</tool_response>"
+    {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
   ],
   "bos_token": {
     "content": "<|begin_of_text|>",
@@ -21,11 +57,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|eot_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<|eot_id|>"
 }