Upload folder using huggingface_hub

checkpoint-10/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-10/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-10/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67fd4a3a3418bbc0ed846603065e64b8116be3bfc992eb04d83bbdfcebefa231
+size 31494413

checkpoint-10/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-10/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-10/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67fd4a3a3418bbc0ed846603065e64b8116be3bfc992eb04d83bbdfcebefa231
+size 31494413

checkpoint-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74d55409badc9e2d12f64f46f090ffaa0fcded60f955f648fbd1b5c02de722a7
+size 125504317

checkpoint-10/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a11170ab4940450fb911eaec901717176e7513c69be23bd75c6f2b5954750bb
+size 14575

checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f23bc239cbe3e7a4f862f2448a71aa49fc3b361c6c5866cc00242a779c0be4
+size 627

checkpoint-10/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.22955523672883787,
+  "eval_steps": 500,
+  "global_step": 10,
+  "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
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 129,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "total_flos": 4.37897752215552e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10/training_args.bin

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

checkpoint-20/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-20/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-20/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6da7406b42629dec08fbd4d226f0436a51dc43ae4efe506e97b0ea4a9e8488
+size 31494413

checkpoint-20/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-20/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-20/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6da7406b42629dec08fbd4d226f0436a51dc43ae4efe506e97b0ea4a9e8488
+size 31494413

checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71a08457863ca2cb623ca115f24e2b74d5a686747d1aec9706089c364cb19e41
+size 125504317

checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f834ad020c1324fb2c966581df1ae2046dc51e5a909aa761e65b75922dd2efb2
+size 14575

checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64bd2871a807ae2da11c5073d611b4d4223c336499ef21e9e856aaa448a1a35
+size 627

checkpoint-20/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.45911047345767575,
+  "eval_steps": 500,
+  "global_step": 20,
+  "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
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 129,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "total_flos": 8.884714919952384e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-20/training_args.bin

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

checkpoint-30/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-30/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-30/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fcc63edc1ffcda424b4eeea79da75a17e8f27a3b5534b154d7687ffd6931e1
+size 31494413

checkpoint-30/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-30/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-30/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fcc63edc1ffcda424b4eeea79da75a17e8f27a3b5534b154d7687ffd6931e1
+size 31494413

checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5de6d5c52c3d24089ca51dc0452c99b5461d213b610a7a1de7130b47a33c2a
+size 125504317

checkpoint-30/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63c98d5bc0c13cbc2260248b7a3f1a7a407a627d11d527ecc7f53e37782b0b9
+size 14575

checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:298c19c2d0215ea63da7419132c9dac6c9c75fdd531e32dfc1cb87dbb0aa8259
+size 627

checkpoint-30/trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6886657101865137,
+  "eval_steps": 500,
+  "global_step": 30,
+  "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
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 129,
+  "num_train_epochs": 3,
+  "save_steps": 10,
+  "total_flos": 1.3296259208577024e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-30/training_args.bin

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