Upload 8 files

README.md

@@ -1,3 +1,21 @@
 ---
-license: wtfpl
+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: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": {
+    "base_model_class": "Blip2ForConditionalGeneration",
+    "parent_library": "transformers.models.blip_2.modeling_blip_2"
+  },
+  "base_model_name_or_path": "/disk1/data/users/yanyang/models/Salesforce/blip2-opt-6.7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q",
+    "v",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": null
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558b00e040aff3fb4a90d2d071f0ad336c0966aefa3afb8f6abb17b21357091e
+size 33603405

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b734631a831e26910376f384538d89d170f00f914fff3910ddb9e683755d12a
+size 67216581

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e498c87e9cb50866756a08f51cba0a1c14784bc72a91e7b45a928406ac0015e
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5019856136180e834579d7f445ade1ce1eb1d251d0596259f73dc9e416fd7596
+size 627

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6188118811881188,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.948432343234324e-05,
+      "loss": 3.6134,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.8968646864686466e-05,
+      "loss": 1.7076,
+      "step": 100
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.8452970297029704e-05,
+      "loss": 1.6069,
+      "step": 150
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.793729372937294e-05,
+      "loss": 1.5834,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.7421617161716174e-05,
+      "loss": 1.5641,
+      "step": 250
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.6905940594059406e-05,
+      "loss": 1.5434,
+      "step": 300
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.6390264026402644e-05,
+      "loss": 1.533,
+      "step": 350
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.5874587458745876e-05,
+      "loss": 1.5326,
+      "step": 400
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.5358910891089114e-05,
+      "loss": 1.5294,
+      "step": 450
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.4843234323432346e-05,
+      "loss": 1.525,
+      "step": 500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.432755775577558e-05,
+      "loss": 1.5229,
+      "step": 550
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.3811881188118816e-05,
+      "loss": 1.5178,
+      "step": 600
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.329620462046205e-05,
+      "loss": 1.5181,
+      "step": 650
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.278052805280528e-05,
+      "loss": 1.5179,
+      "step": 700
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.226485148514852e-05,
+      "loss": 1.5022,
+      "step": 750
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.174917491749175e-05,
+      "loss": 1.5108,
+      "step": 800
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.123349834983499e-05,
+      "loss": 1.5075,
+      "step": 850
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.071782178217822e-05,
+      "loss": 1.5011,
+      "step": 900
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.020214521452145e-05,
+      "loss": 1.5023,
+      "step": 950
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.968646864686469e-05,
+      "loss": 1.4978,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4848,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 8.738647348755825e+20,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21db4ab0b81b3d96bd8307b7f2bb94ccb97ab7af924f610afa2e086c7b860217
+size 4155