End of training

README.md

@@ -5,4 +5,21 @@ datasets:
 language:
 - en
 - fr
----
+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: False
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

runs/Aug07_11-57-10_a4471ca964ab/events.out.tfevents.1691410340.a4471ca964ab.222.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c11c27fe0bf46e597230f1ba808606556681d24773891e2941532b6095b36d38
-size 7753
+oid sha256:ecd1e92b5f3603a57ad4e53b13290f5bd4a0b5ddae7614ed7361a43fb97496a3
+size 8107