Training in progress epoch 8

README.md

@@ -138,6 +138,30 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_use_double_quant: False
 - bnb_4bit_compute_dtype: float32
 
+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
+
+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
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: True
@@ -175,6 +199,8 @@ The following `bitsandbytes` quantization config was used during training:
 - PEFT 0.5.0
 - PEFT 0.5.0
 - PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
 
 - PEFT 0.5.0.dev0
  `bitsandbytes` quantization config was used during training:

Whisper PEFT Fine-Tuning/events.out.tfevents.1696436338.MLbox.300106.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94bdcd96fa14cea6a0aa01b078c2b2b8c61be16b5b284676d11b3b1d69f4e6fa
-size 5704
+oid sha256:b9bd6b09d4942c038d660dff2cb242e14ed9dee1a1f4721a0b34777fb0445a0d
+size 5863

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2aef5cc5861aa4178fadf6aec45ec69bb0ede0dd24faa5f79f5e0acd0d39cfb
+oid sha256:6af3df148b3ebd99b3b055a4741c5bb191ebece2eff08728b401ca84e4f8c422
 size 38697637

best_checkpoint/README.md

@@ -424,6 +424,18 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_use_double_quant: False
 - bnb_4bit_compute_dtype: float32
 
+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
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: True
@@ -472,5 +484,6 @@ The following `bitsandbytes` quantization config was used during training:
 - PEFT 0.5.0
 - PEFT 0.5.0
 - PEFT 0.5.0
+- PEFT 0.5.0
 
 - PEFT 0.5.0

best_checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:945fb9287c8252170548a62c8b31f0e2bac3a2123e2c7771498ff4b0ed86667f
+oid sha256:1a230cceee43a69525dbd7c377779c007f5c895483ddcb17f4df8654dd5c3efb
 size 38697637

best_checkpoint/random_states_1.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97eef37a8daf39b503800acd6b12dacc4632d876f40eebb2435196bbc25f883d
+oid sha256:4e6e978f9942ec103bb5784eec46f3cc88230ee85fad0ef1c8dce41f5e45a225
 size 15755