End of training

README.md

@@ -4,6 +4,17 @@ library_name: peft
 ## 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
+
 The following `bitsandbytes` quantization config was used during training:
 - load_in_8bit: False
 - load_in_4bit: True
@@ -16,5 +27,6 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: bfloat16
 ### Framework versions
 
+- PEFT 0.5.0.dev0
 
 - PEFT 0.5.0.dev0

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e67d7745d3aeca35ff3b1c6478fffa90ede3bf05c782597b3761b48c46666b7d
+oid sha256:72430327e78de59be454a580331181e8890a36181da2b084c9534c4fe570c7bc
 size 160069389

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.0,
     "total_flos": 232910960836608.0,
-    "train_loss": 1.4102739254633585,
-    "train_runtime": 116.3917,
-    "train_samples_per_second": 0.516,
-    "train_steps_per_second": 0.129
+    "train_loss": 1.4252451022466024,
+    "train_runtime": 119.4569,
+    "train_samples_per_second": 0.502,
+    "train_steps_per_second": 0.126
 }

runs/Jul25_12-44-09_a96f9d5e146d/events.out.tfevents.1690289053.a96f9d5e146d.548.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f39c5ee5b0075bb15a7fb07d879f5f3dbb9e46af3b1551827bd1ac6e1fe9260
+size 7043

runs/Jul25_13-13-45_a96f9d5e146d/events.out.tfevents.1690290829.a96f9d5e146d.548.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f93248b75582710c0fc31bc883e563d1484693b1d8335815c75721035c0d6e
+size 4693

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.0,
     "total_flos": 232910960836608.0,
-    "train_loss": 1.4102739254633585,
-    "train_runtime": 116.3917,
-    "train_samples_per_second": 0.516,
-    "train_steps_per_second": 0.129
+    "train_loss": 1.4252451022466024,
+    "train_runtime": 119.4569,
+    "train_samples_per_second": 0.502,
+    "train_steps_per_second": 0.126
 }

trainer_state.json

@@ -22,89 +22,89 @@
     {
       "epoch": 0.0,
       "learning_rate": 0.00018461538461538463,
-      "loss": 1.6373,
+      "loss": 1.638,
       "step": 3
     },
     {
       "epoch": 0.0,
       "learning_rate": 0.00016923076923076923,
-      "loss": 1.5748,
+      "loss": 1.5763,
       "step": 4
     },
     {
       "epoch": 0.0,
       "learning_rate": 0.00015384615384615385,
-      "loss": 1.5775,
+      "loss": 1.5843,
       "step": 5
     },
     {
       "epoch": 0.0,
       "learning_rate": 0.00013846153846153847,
-      "loss": 1.2566,
+      "loss": 1.2616,
       "step": 6
     },
     {
       "epoch": 0.0,
       "learning_rate": 0.0001230769230769231,
-      "loss": 1.3078,
+      "loss": 1.3111,
       "step": 7
     },
     {
       "epoch": 0.0,
       "learning_rate": 0.0001076923076923077,
-      "loss": 1.3014,
+      "loss": 1.3044,
       "step": 8
     },
     {
       "epoch": 0.0,
-      "learning_rate": 9.230769230769232e-05,
-      "loss": 1.2879,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 1.299,
       "step": 9
     },
     {
       "epoch": 0.0,
-      "learning_rate": 7.692307692307693e-05,
-      "loss": 1.2206,
+      "learning_rate": 9.230769230769232e-05,
+      "loss": 1.2492,
       "step": 10
     },
     {
       "epoch": 0.0,
-      "learning_rate": 6.153846153846155e-05,
-      "loss": 1.083,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 1.1069,
       "step": 11
     },
     {
       "epoch": 0.0,
-      "learning_rate": 4.615384615384616e-05,
-      "loss": 0.7552,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 0.7699,
       "step": 12
     },
     {
       "epoch": 0.0,
-      "learning_rate": 3.0769230769230774e-05,
-      "loss": 1.1158,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 1.1393,
       "step": 13
     },
     {
       "epoch": 0.0,
-      "learning_rate": 1.5384615384615387e-05,
-      "loss": 1.3777,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 1.4198,
       "step": 14
     },
     {
       "epoch": 0.0,
-      "learning_rate": 0.0,
-      "loss": 1.1955,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 1.2558,
       "step": 15
     },
     {
       "epoch": 0.0,
       "step": 15,
       "total_flos": 232910960836608.0,
-      "train_loss": 1.4102739254633585,
-      "train_runtime": 116.3917,
-      "train_samples_per_second": 0.516,
-      "train_steps_per_second": 0.129
+      "train_loss": 1.4252451022466024,
+      "train_runtime": 119.4569,
+      "train_samples_per_second": 0.502,
+      "train_steps_per_second": 0.126
     }
   ],
   "max_steps": 15,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e7ca42ee048951bf6929c30c03619fb336d7b3f80bbfeacde887d223d12e670
+oid sha256:dc5ffe380d413e602923828d5dc8c1040fadc1541eda8020df9c5efb964a8927
 size 3963