Upload folder using huggingface_hub

README.md

@@ -4,6 +4,18 @@ library_name: peft
 ## Training procedure
 
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- 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: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: False
@@ -17,5 +29,6 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float16
 ### Framework versions
 
+- PEFT 0.4.0
 
 - PEFT 0.4.0

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441ed8437ef696fca88f87327b562c9340116b1441f6c8d2c8d50fc293f0f392
+size 63564410

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875acd07fbaa252f994f5aa2f25ef1f4bdd0643009b8c06c5b0ae9b034919328
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b9a4abb47b1f7cc1dfd2e4035b39611a01db8ddaa04fd2cde539012db4dec1
+size 1064

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019375130200295878,
+      "loss": 0.4073,
+      "step": 500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0001757861325449997,
+      "loss": 0.4069,
+      "step": 1000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00014834966999429178,
+      "loss": 0.4009,
+      "step": 1500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00011487075772256517,
+      "loss": 0.3973,
+      "step": 2000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.953338797092902e-05,
+      "loss": 0.3955,
+      "step": 2500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.6753811771138364e-05,
+      "loss": 0.3905,
+      "step": 3000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.062862256606306e-05,
+      "loss": 0.3881,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.422788704864633e-06,
+      "loss": 0.3841,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4420,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 3.644311294921707e+17,
+  "trial_name": null,
+  "trial_params": null
+}