Training in progress, epoch 1

README.md

@@ -5,6 +5,7 @@ tags:
 model-index:
 - name: lora-out
   results: []
+library_name: peft
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,6 +30,18 @@ More information needed
 
 ## Training procedure
 
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -52,6 +65,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
+- PEFT 0.6.0.dev0
 - Transformers 4.34.0.dev0
 - Pytorch 2.0.1+cu117
 - Datasets 2.7.1

adapter_config.json

@@ -16,13 +16,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
+    "gate_proj",
     "v_proj",
-    "o_proj",
+    "up_proj",
     "down_proj",
-    "gate_proj",
-    "k_proj"
+    "q_proj",
+    "k_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:967246f51fffdb6114ad2b9080f1d47feac7334865d1a3ef322667e47289beb2
+oid sha256:0007c230ec65d5d38b5df6fe5ad5b5287f2b7ae2a5e3557e34499bf114a8d69e
 size 319977229

config.json

@@ -16,12 +16,24 @@
   "num_key_value_heads": 32,
   "pad_token_id": 0,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.34.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

tokenizer_config.json

@@ -1,26 +1,28 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
     "1": {
       "content": "<s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
     "2": {
       "content": "</s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     }
@@ -33,7 +35,11 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<unk>",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_file": "/N/u/oleykin/BigRed200/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/tokenizer.json",
+  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": true,
+  "use_fast": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ad6007b3cafb42c644da99bc92c29c7845b9ccccc005d1f6ccd837fcdb5308b
+oid sha256:3fbb5692d84707ba0da73df5c8db6584484c9710f3dd89c322d18f3312498cb9
 size 4475