End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,20 @@
+---
+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
+### Framework versions
+
+
+- PEFT 0.5.0.dev0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e67d7745d3aeca35ff3b1c6478fffa90ede3bf05c782597b3761b48c46666b7d
+size 160069389

all_results.json

@@ -0,0 +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
+}

runs/Jul25_12-36-43_a96f9d5e146d/events.out.tfevents.1690288609.a96f9d5e146d.548.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88189de163fb0f72a476002b0582d2e00b622ca2cfc7644676402829b66d39f9
+size 7043

train_results.json

@@ -0,0 +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
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.00400026668444563,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 2.5444,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 1.9186,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 1.6373,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 1.5748,
+      "step": 4
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00015384615384615385,
+      "loss": 1.5775,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00013846153846153847,
+      "loss": 1.2566,
+      "step": 6
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 1.3078,
+      "step": 7
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 1.3014,
+      "step": 8
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.230769230769232e-05,
+      "loss": 1.2879,
+      "step": 9
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 1.2206,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 1.083,
+      "step": 11
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.7552,
+      "step": 12
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 1.1158,
+      "step": 13
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 1.3777,
+      "step": 14
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0,
+      "loss": 1.1955,
+      "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
+    }
+  ],
+  "max_steps": 15,
+  "num_train_epochs": 1,
+  "total_flos": 232910960836608.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e7ca42ee048951bf6929c30c03619fb336d7b3f80bbfeacde887d223d12e670
+size 3963