Training in progress, epoch 1, checkpoint

checkpoint-4/README.md

@@ -28,6 +28,18 @@ 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: 4.0
+- 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
@@ -41,6 +53,7 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: bfloat16
 ### Framework versions
 
+- PEFT 0.5.0
 - PEFT 0.5.0
 - PEFT 0.5.0
 

checkpoint-4/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 1.0,
       "eval_loss": NaN,
-      "eval_runtime": 12.5477,
-      "eval_samples_per_second": 403.819,
-      "eval_steps_per_second": 12.672,
+      "eval_runtime": 12.6379,
+      "eval_samples_per_second": 400.937,
+      "eval_steps_per_second": 12.581,
       "step": 4
     }
   ],

checkpoint-4/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:927c94c7f5204780e4f05fc2c1410aeb6e3f58c905948cab8e90e6c61c6501b4
+oid sha256:168850d057ab63184b4c1532f0b5ac2a09e4bca31d58427d7d43fbd342d5b12c
 size 4219