new

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: meta-llama/Llama-2-7b-hf
+base_model: togethercomputer/LLaMA-2-7B-32K
 ---
 
 # Model Card for Model ID
@@ -205,4 +205,25 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ### Framework versions
 
 
+- PEFT 0.6.2
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2
+## Training procedure
+
+
+### Framework versions
+
+
 - PEFT 0.6.2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "base_model_name_or_path": "togethercomputer/LLaMA-2-7B-32K",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -16,8 +16,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa6add37cf960e5a9f2d2643de77e104b808daf257b26470d4499517c8c2edae
+oid sha256:19985c498c50e1eeba26d00b9fe10e5c08ea9c9eb6c8f6442310cca560ab3d9d
 size 8405600

all_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 2.0,
-    "max_memory_allocated (GB)": 91.67,
-    "memory_allocated (GB)": 36.81,
+    "max_memory_allocated (GB)": 30.34,
+    "memory_allocated (GB)": 19.36,
     "total_memory_available (GB)": 94.62,
-    "train_loss": 2.199738980594434,
-    "train_runtime": 396.1043,
-    "train_samples_per_second": 154.112,
-    "train_steps_per_second": 0.603
+    "train_loss": 2.0642123500715774,
+    "train_runtime": 549.193,
+    "train_samples_per_second": 97.186,
+    "train_steps_per_second": 1.517
 }

special_tokens_map.json

@@ -5,7 +5,7 @@
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -9,7 +14,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -18,7 +23,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     },
     {
@@ -27,7 +32,7 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
+      "normalized": true,
       "special": true
     }
   ],
@@ -51,12 +56,6 @@
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
@@ -65,24 +64,12 @@
       }
     ],
     "pair": [
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 0
-        }
-      },
       {
         "Sequence": {
           "id": "A",
           "type_id": 0
         }
       },
-      {
-        "SpecialToken": {
-          "id": "<s>",
-          "type_id": 1
-        }
-      },
       {
         "Sequence": {
           "id": "B",
@@ -90,17 +77,7 @@
         }
       }
     ],
-    "special_tokens": {
-      "<s>": {
-        "id": "<s>",
-        "ids": [
-          1
-        ],
-        "tokens": [
-          "<s>"
-        ]
-      }
-    }
+    "special_tokens": {}
   },
   "decoder": {
     "type": "Sequence",

tokenizer_config.json

@@ -1,11 +1,11 @@
 {
-  "add_bos_token": true,
+  "add_bos_token": false,
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -13,7 +13,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -21,21 +21,22 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 32768,
   "pad_token": "<unk>",
-  "padding_side": "right",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": true
 }

train_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 2.0,
-    "max_memory_allocated (GB)": 91.67,
-    "memory_allocated (GB)": 36.81,
+    "max_memory_allocated (GB)": 30.34,
+    "memory_allocated (GB)": 19.36,
     "total_memory_available (GB)": 94.62,
-    "train_loss": 2.199738980594434,
-    "train_runtime": 396.1043,
-    "train_samples_per_second": 154.112,
-    "train_steps_per_second": 0.603
+    "train_loss": 2.0642123500715774,
+    "train_runtime": 549.193,
+    "train_samples_per_second": 97.186,
+    "train_steps_per_second": 1.517
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc06ad8fc135210b6ce0c44e44393666a7ddfe4b7098aed18864648c7c05a0f8
+oid sha256:ccad0ba6423a129eb8ea87982afec4e9165bc87b1828e9b4852ba11f0b3610bc
 size 5240