Training in progress, step 200

adapter_config.json

@@ -3,7 +3,7 @@
   "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
   "bias": "none",
   "fan_in_fan_out": null,
-  "inference_mode": false,
+  "inference_mode": true,
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
     "k_proj",
     "down_proj",
     "o_proj",
-    "v_proj",
-    "gate_proj",
-    "up_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e3346b176d6fcd29f1030224d15a9659a7886dfde431254b0c2c482f7f12ee
+size 500897101

checkpoint-200/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

checkpoint-200/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "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": 32,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-200/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e3346b176d6fcd29f1030224d15a9659a7886dfde431254b0c2c482f7f12ee
+size 500897101

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7279df0ba6a87a3f75b7d314713b3e2ad235ea556deace54c5ed88731053c8e
+size 1001736445

checkpoint-200/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da64efc9dde53926f928c894617fbf0d3cb2ae763b94af40d50272f40390946d
+size 27772

checkpoint-200/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db417e21e6b6d1ae789628c94b5f1ed08d62047fc09f30b693fcd005bebda36
+size 27772

checkpoint-200/rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf26229b77cf29a765bf52ae8a7c1da17f8f3f15fc5f78763162e594fa63670b
+size 27789

checkpoint-200/rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db97f6b3f80c0bc222d155530394c9cde17cdd394f4271b4f329eae8a9fce649
+size 27789

checkpoint-200/rng_state_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8136f8788ad62a1b95fc461ab5c54ebfc79c5c3147e5496579a03d3b2c4a073
+size 27789

checkpoint-200/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ee750ae3cf6051a5897d7940e410cb3e8326ebf95634e2106ede6d0f1a164f
+size 27789

checkpoint-200/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff35143fc37295c6bb931e10ada59cb846c3becb29a8c330c4bcb2e2d7dbf1c
+size 27772

checkpoint-200/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4618a675e687e5c0fb8f6418051239a91b2cdaf24246d5cedb509956f23ec5f
+size 27772

checkpoint-200/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f92bb724819a9b37f50673a2ef764c216893ce38d47800c4d1247ca27567b0e
+size 27772

checkpoint-200/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f65da5c3fd524d57e1e393855ca2e460e1ca1e0e63675872313d79b6fda74be
+size 27772

checkpoint-200/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab194c2a0e0b5f9bfccfa318cc6a981f235da2b7d08e65be576e723aac19c318
+size 27772

checkpoint-200/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4046dacc20fadf115d03161f72d3531c63569d4b39f03bfc1090911d6e1e9f93
+size 27772

checkpoint-200/rng_state_8.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21fea850cb0c10a02794ed024b9d4248ecf9bd626138e47995dba6aa8502927a
+size 27772

checkpoint-200/rng_state_9.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a308f6513afeac6867267883a39bd0a3c95a2bea71b416b4390e0023b46dae
+size 27772

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024d4cf2a426f07c2e2ce03edd6538c1ac6fcaded49d4ec29b7b8a390c1fd54c
+size 627

checkpoint-200/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07754943776657619,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001999867761371633,
+      "loss": 1.0435,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019993306018843102,
+      "loss": 0.8918,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019983804784290833,
+      "loss": 0.8874,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019970177836355307,
+      "loss": 0.8839,
+      "step": 200
+    }
+  ],
+  "max_steps": 7737,
+  "num_train_epochs": 3,
+  "total_flos": 8.600712554731274e+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:e7d8e6ca3ee52d610ea6af580762703958acb68894884ff8627b9a467240686f
+size 4027

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7d8e6ca3ee52d610ea6af580762703958acb68894884ff8627b9a467240686f
+size 4027