End of training

README.md

@@ -2,8 +2,6 @@
 license: mit
 library_name: peft
 tags:
-- trl
-- sft
 - generated_from_trainer
 base_model: microsoft/phi-2
 model-index:
@@ -53,7 +51,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.9.0
-- Transformers 4.39.0.dev0
+- Transformers 4.38.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc2",
     "fc1",
+    "fc2",
     "Wqkv"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4449348d0e04f39d07eed7efa35cea5a9fc737a7c66c0e7c7dfa50d433d9d0c7
-size 146825352
+oid sha256:d0f60efaad8b661df40a8fa7c5bb78716d1daf4c343f4fc79cad226f4527ea3d
+size 73424880

model/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "embd_pdrop": 0.0,
+  "flash_attn": true,
+  "flash_rotary": true,
+  "fused_dense": true,
+  "img_processor": null,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "phi-msft",
+  "n_embd": 2560,
+  "n_head": 32,
+  "n_head_kv": null,
+  "n_inner": null,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_type": "nf4",
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "resid_pdrop": 0.1,
+  "rotary_dim": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 51200
+}

model/generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.39.0.dev0"
+}

model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a89ba86cfb46480f56097de51cf8f72562ef3db7bf6311380114c3de890b619
+size 2614912216

runs/Mar12_01-52-21_6fa9c9ac5280/events.out.tfevents.1710208343.6fa9c9ac5280.277.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608d9e164ed7b191ff2585732eff84c8a841d2327acbaadf5373b0e7939f9d5b
+size 5573

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4c3a9053c66c46a31bde368eb854da066acfc250aff3d291b049fb6e6a7dee
+oid sha256:c4a73ab7288fcae90c89cac3697c96bc039bc8d8ac33b6c0cc54edb601b328bf
 size 4920