hiranmai49/llama-2_totto_instructions

README.md

@@ -41,6 +41,7 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
 - training_steps: 500
+- mixed_precision_training: Native AMP
 
 ### Training results
 
@@ -48,7 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.33.2
+- Transformers 4.35.2
 - Pytorch 2.0.0
 - Datasets 2.1.0
-- Tokenizers 0.13.3
+- Tokenizers 0.15.0

adapter_config.json

@@ -8,16 +8,19 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
+  "loftq_config": {},
   "lora_alpha": 16,
   "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549812a016e194282c7dd96822d57093e7319358443c9117b3ebdc1cf60873d6
+size 134235048

runs/Dec02_10-23-16_a88a7964f57c/events.out.tfevents.1701512646.a88a7964f57c.80.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01737a65b79db48e88bd2ecf86220d0bd2763db9c04b31a2182634d629951d0
+size 4613

runs/Dec02_10-30-25_a88a7964f57c/events.out.tfevents.1701513035.a88a7964f57c.391.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce6956ef5b679f90fe83054146aaff480560907cbdfab420a91210d3834f1a3
+size 6531

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -1,34 +1,40 @@
 {
-  "bos_token": {
-    "__type": "AddedToken",
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
   },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": {
-    "__type": "AddedToken",
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "eos_token": "</s>",
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": "</s>",
   "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
-  "unk_token": {
-    "__type": "AddedToken",
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "use_default_system_prompt": true
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42b254bfb1cab8007ed7e5f3d53ea1ae197fde91458cd33b42a57427a8718849
-size 4027
+oid sha256:e2e63e93839eaa998b5e16cb20ee9e106c022ebcf9dce5f477a2fe77e595fea7
+size 4155