End of training

README.md

@@ -5,6 +5,7 @@ tags:
 model-index:
 - name: outputs
   results: []
+library_name: peft
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,6 +29,17 @@ More information needed
 
 ## Training procedure
 
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- 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: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -44,6 +56,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
+- PEFT 0.5.0.dev0
 - Transformers 4.32.0.dev0
 - Pytorch 2.0.1+cu118
 - Datasets 2.13.1

all_results.json

@@ -2,7 +2,7 @@
     "epoch": 0.0,
     "total_flos": 232910960836608.0,
     "train_loss": 1.4252451022466024,
-    "train_runtime": 119.4569,
-    "train_samples_per_second": 0.502,
-    "train_steps_per_second": 0.126
+    "train_runtime": 116.0587,
+    "train_samples_per_second": 0.517,
+    "train_steps_per_second": 0.129
 }

runs/Jul25_13-14-25_a96f9d5e146d/events.out.tfevents.1690290908.a96f9d5e146d.548.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33d1b64b6d824dd58b73e34215a3aaabf4c4856c6e5918146fffc9a16fd5ca0
+size 7043

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 0.0,
     "total_flos": 232910960836608.0,
     "train_loss": 1.4252451022466024,
-    "train_runtime": 119.4569,
-    "train_samples_per_second": 0.502,
-    "train_steps_per_second": 0.126
+    "train_runtime": 116.0587,
+    "train_samples_per_second": 0.517,
+    "train_steps_per_second": 0.129
 }

trainer_state.json

@@ -102,9 +102,9 @@
       "step": 15,
       "total_flos": 232910960836608.0,
       "train_loss": 1.4252451022466024,
-      "train_runtime": 119.4569,
-      "train_samples_per_second": 0.502,
-      "train_steps_per_second": 0.126
+      "train_runtime": 116.0587,
+      "train_samples_per_second": 0.517,
+      "train_steps_per_second": 0.129
     }
   ],
   "max_steps": 15,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc5ffe380d413e602923828d5dc8c1040fadc1541eda8020df9c5efb964a8927
+oid sha256:661ac85967701cd97f641328d09e6d3e56c94e50385170e34cf7f5e2f45655a8
 size 3963