Upload folder using huggingface_hub

checkpoint-40/README.md

@@ -0,0 +1,21 @@
+---
+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 0.6.0.dev0

checkpoint-40/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-40/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9d6598f557d2e5393069a41e87400c97f10aee85c14335115341831c818dc2
+size 31494413

checkpoint-40/adapter_model/README.md

@@ -0,0 +1,21 @@
+---
+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 0.6.0.dev0

checkpoint-40/adapter_model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-40/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9d6598f557d2e5393069a41e87400c97f10aee85c14335115341831c818dc2
+size 31494413

checkpoint-40/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6930a4cb7d96e3e3ae1dc9c5866caa23f969b7d0e718f116a79a4ef01e9bcd1
+size 125504317

checkpoint-40/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67bcfa0ab14857a82a44ffa02d3cf39b82d87e2c22e546b87fa2df244368933a
+size 14575

checkpoint-40/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d048c63c660c9f2cb6345c4f756c8abee0e570482b06bf9c08827d79b257394
+size 627

checkpoint-40/trainer_state.json

@@ -0,0 +1,259 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9182209469153515,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 5e-05,
+      "loss": 1.7667,
+      "step": 1
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5e-05,
+      "loss": 1.7274,
+      "step": 2
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5e-05,
+      "loss": 1.656,
+      "step": 3
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5e-05,
+      "loss": 1.7964,
+      "step": 4
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 5e-05,
+      "loss": 1.6153,
+      "step": 5
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 5e-05,
+      "loss": 1.7931,
+      "step": 6
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 5e-05,
+      "loss": 1.7548,
+      "step": 7
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 5e-05,
+      "loss": 1.7054,
+      "step": 8
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 5e-05,
+      "loss": 1.7311,
+      "step": 9
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 5e-05,
+      "loss": 1.6827,
+      "step": 10
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 5e-05,
+      "loss": 1.7158,
+      "step": 11
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5e-05,
+      "loss": 1.6599,
+      "step": 12
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5e-05,
+      "loss": 1.6991,
+      "step": 13
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 5e-05,
+      "loss": 1.6628,
+      "step": 14
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 5e-05,
+      "loss": 1.6188,
+      "step": 15
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 5e-05,
+      "loss": 1.6868,
+      "step": 16
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 5e-05,
+      "loss": 1.6854,
+      "step": 17
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 5e-05,
+      "loss": 1.5938,
+      "step": 18
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 5e-05,
+      "loss": 1.6603,
+      "step": 19
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 5e-05,
+      "loss": 1.561,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5e-05,
+      "loss": 1.6162,
+      "step": 21
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 5e-05,
+      "loss": 1.6159,
+      "step": 22
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 5e-05,
+      "loss": 1.6414,
+      "step": 23
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5e-05,
+      "loss": 1.6915,
+      "step": 24
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5e-05,
+      "loss": 1.6853,
+      "step": 25
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 5e-05,
+      "loss": 1.6563,
+      "step": 26
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 5e-05,
+      "loss": 1.6622,
+      "step": 27
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5e-05,
+      "loss": 1.638,
+      "step": 28
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5e-05,
+      "loss": 1.66,
+      "step": 29
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5e-05,
+      "loss": 1.6565,
+      "step": 30
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 5e-05,
+      "loss": 1.6076,
+      "step": 31
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5e-05,
+      "loss": 1.6971,
+      "step": 32
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5e-05,
+      "loss": 1.6836,
+      "step": 33
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5e-05,
+      "loss": 1.587,
+      "step": 34
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5e-05,
+      "loss": 1.7034,
+      "step": 35
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5e-05,
+      "loss": 1.705,
+      "step": 36
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5e-05,
+      "loss": 1.5491,
+      "step": 37
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5e-05,
+      "loss": 1.611,
+      "step": 38
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5e-05,
+      "loss": 1.6795,
+      "step": 39
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5e-05,
+      "loss": 1.5823,
+      "step": 40
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 129,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "total_flos": 1.77300992065536e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-40/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056b2d35a8edd0b4c4e1fa596b4bfb9c414a316aae917663d8deeb089d445a4e
+size 4219