Upload folder using huggingface_hub

README.md

@@ -1,3 +1,32 @@
 ---
-license: mit
+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: False
+- bnb_4bit_compute_dtype: float16
+
+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: False
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+- PEFT 0.5.0
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "Salesforce/codegen25-7b-mono",
+  "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": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "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 sha256:2e0898b5d529660c366fa51559a5da535e274cd7b245ee0959dd7e7a10d6d6d8
+size 134264202

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2c9c2ab6f7085d33f60f9a87db6ebf80fe693bf39c07447fb2dc1ed65b8c38
+size 268511866

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c71f450a2202eb36cbb6525b8c2095459f5d1fbf9eaabe85505785a807880420
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4fe8e328be6e10e053e14666b2e571c45c73d9a8291556b08910e3da67b3e6
+size 1064

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_eos_token": false,
+  "add_special_tokens": true,
+  "auto_map": {
+    "AutoTokenizer": [
+      "Salesforce/codegen25-7b-mono--tokenization_codegen25.CodeGen25Tokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "tokenizer_class": "CodeGen25Tokenizer"
+}

trainer_state.json

@@ -0,0 +1,316 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5336179295624333,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.000196,
+      "loss": 0.6124,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.000192,
+      "loss": 0.6304,
+      "step": 20
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.000188,
+      "loss": 0.5953,
+      "step": 30
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 0.5826,
+      "step": 40
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00018,
+      "loss": 0.5742,
+      "step": 50
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 0.5814,
+      "step": 60
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000172,
+      "loss": 0.6119,
+      "step": 70
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000168,
+      "loss": 0.6219,
+      "step": 80
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.000164,
+      "loss": 0.5717,
+      "step": 90
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00016,
+      "loss": 0.6244,
+      "step": 100
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 0.5547,
+      "step": 110
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.000152,
+      "loss": 0.5985,
+      "step": 120
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.000148,
+      "loss": 0.605,
+      "step": 130
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.000144,
+      "loss": 0.5856,
+      "step": 140
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00014,
+      "loss": 0.6418,
+      "step": 150
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.6063,
+      "step": 160
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000132,
+      "loss": 0.5929,
+      "step": 170
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 0.5798,
+      "step": 180
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.000124,
+      "loss": 0.5479,
+      "step": 190
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00012,
+      "loss": 0.6223,
+      "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.000116,
+      "loss": 0.5758,
+      "step": 210
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.5971,
+      "step": 220
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00010800000000000001,
+      "loss": 0.6101,
+      "step": 230
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.6146,
+      "step": 240
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0001,
+      "loss": 0.5715,
+      "step": 250
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.6e-05,
+      "loss": 0.6039,
+      "step": 260
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.5445,
+      "step": 270
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.5678,
+      "step": 280
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 8.4e-05,
+      "loss": 0.5321,
+      "step": 290
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 8e-05,
+      "loss": 0.5726,
+      "step": 300
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.6e-05,
+      "loss": 0.5636,
+      "step": 310
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.2e-05,
+      "loss": 0.5964,
+      "step": 320
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.5715,
+      "step": 330
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.5882,
+      "step": 340
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 6e-05,
+      "loss": 0.521,
+      "step": 350
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.5874,
+      "step": 360
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.6203,
+      "step": 370
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.8e-05,
+      "loss": 0.585,
+      "step": 380
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.5754,
+      "step": 390
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4e-05,
+      "loss": 0.6136,
+      "step": 400
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.6e-05,
+      "loss": 0.5735,
+      "step": 410
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.5704,
+      "step": 420
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 0.5559,
+      "step": 430
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.4e-05,
+      "loss": 0.6044,
+      "step": 440
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2e-05,
+      "loss": 0.578,
+      "step": 450
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.563,
+      "step": 460
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.2e-05,
+      "loss": 0.6081,
+      "step": 470
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.5994,
+      "step": 480
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.5802,
+      "step": 490
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0,
+      "loss": 0.5422,
+      "step": 500
+    }
+  ],
+  "max_steps": 500,
+  "num_train_epochs": 1,
+  "total_flos": 1.7111689606397952e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bf2d43f463605daa47b96aadce75d3bee8ec0acbde92899c89553139efffee
+size 4408