Upload 13 files

README.md

@@ -1,3 +1,22 @@
 ---
-license: cc-by-sa-4.0
+library_name: peft
 ---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+### Framework versions
+
+- PEFT 0.5.0.dev0
+
+- PEFT 0.5.0.dev0

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "../llama/Llama-2-13b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
+size 443

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd252023ad377ab471696a0353253ad4f3c6446c45bafbbafd2171307ba620d8
+size 52562757

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:356ded462a5c026117412149a3c38fa2a19d3ada9a86225c129661b4a2d90cf2
+size 26271757

checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819bbebd4638bc94da4de230bc6ce2f470d518a082e944aedd33a78f501377f9
+size 17655

checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb1711896b18fae6b3b01415cfe8630f68197edc43417b873cad79e315270bd
+size 17655

checkpoint-200/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87213c71bd5423f9e0ce464f07994f133bfb98c7344d36f4951e6665a01e0435
+size 17655

checkpoint-200/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152127eb111c9847a65aeef6260b412925df7be5584ebe72e4c3f5f0ab72570d
+size 17655

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fccf0f9be1bb8f24861e4393745b3e09cc2687125a69e3757955fb0f0925ea5
+size 557

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aadae1c1fe293674b5a6ac7680b50aac3799a07d912e3567ecc67f1214efb1b
+size 627

checkpoint-200/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 0.7962789535522461,
+  "best_model_checkpoint": "../outputs/13b_chat_lora_0/checkpoint-200",
+  "epoch": 0.6825938566552902,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.591,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.5586,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.3909,
+      "step": 30
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.1395,
+      "step": 40
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00015,
+      "loss": 0.9936,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.939,
+      "step": 60
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.9151,
+      "step": 70
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.8975,
+      "step": 80
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00027,
+      "loss": 0.8636,
+      "step": 90
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0003,
+      "loss": 0.8319,
+      "step": 100
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00028445595854922277,
+      "loss": 0.8163,
+      "step": 110
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00026891191709844557,
+      "loss": 0.814,
+      "step": 120
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00025336787564766836,
+      "loss": 0.8116,
+      "step": 130
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0002378238341968912,
+      "loss": 0.8058,
+      "step": 140
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00022227979274611396,
+      "loss": 0.8039,
+      "step": 150
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00020673575129533678,
+      "loss": 0.8035,
+      "step": 160
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00019119170984455958,
+      "loss": 0.7976,
+      "step": 170
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00017564766839378237,
+      "loss": 0.7947,
+      "step": 180
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00016010362694300517,
+      "loss": 0.7911,
+      "step": 190
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00014455958549222797,
+      "loss": 0.7928,
+      "step": 200
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.7962789535522461,
+      "eval_runtime": 39.6388,
+      "eval_samples_per_second": 50.456,
+      "eval_steps_per_second": 1.589,
+      "step": 200
+    }
+  ],
+  "max_steps": 293,
+  "num_train_epochs": 1,
+  "total_flos": 6.32024838701056e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3edcce272f33c7ece5a84e4ff5374199ab781df059da624092e0bb97918b44d
+size 3899