Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+---
+
+# Model Trained Using AutoTrain

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "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_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772525c09fdf1d5fe87408ef35fd83a8e589aef41996409d64220e6176523214
+size 33600906

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

checkpoint-280/README.md

@@ -0,0 +1,34 @@
+---
+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: False
+- bnb_4bit_compute_dtype: float16
+
+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: False
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+- PEFT 0.5.0
+
+- PEFT 0.5.0

checkpoint-280/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
+  "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_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-280/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772525c09fdf1d5fe87408ef35fd83a8e589aef41996409d64220e6176523214
+size 33600906

checkpoint-280/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

checkpoint-280/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cab1dc3f60016a6992d38ba08be2731a162ddf28c9c58a2805d8f1f04469978c
+size 67217018

checkpoint-280/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f220dc7f0319c08e3bca888f34b99a2acb6250d2bbaf5a19088926b10242ada6
+size 14244

checkpoint-280/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555dc20376bd6a66dea62a023ec0591857bf60dfd291616dce4019972c45c65b
+size 1064

checkpoint-280/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-280/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-280/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-280/trainer_state.json

@@ -0,0 +1,259 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.4,
+  "eval_steps": 500,
+  "global_step": 280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001,
+      "loss": 1.638,
+      "step": 7
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 1.7376,
+      "step": 14
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0003,
+      "loss": 1.3745,
+      "step": 21
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0004,
+      "loss": 1.0169,
+      "step": 28
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.0005,
+      "loss": 0.7142,
+      "step": 35
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0006,
+      "loss": 0.591,
+      "step": 42
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 0.0007,
+      "loss": 0.3283,
+      "step": 49
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 0.0008,
+      "loss": 0.4281,
+      "step": 56
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 0.0009000000000000001,
+      "loss": 0.2162,
+      "step": 63
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 0.001,
+      "loss": 0.1895,
+      "step": 70
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 0.000988888888888889,
+      "loss": 0.1243,
+      "step": 77
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 0.0009777777777777777,
+      "loss": 0.1904,
+      "step": 84
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 0.0009666666666666667,
+      "loss": 0.1011,
+      "step": 91
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 0.0009555555555555556,
+      "loss": 0.116,
+      "step": 98
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 0.0009444444444444445,
+      "loss": 0.1028,
+      "step": 105
+    },
+    {
+      "epoch": 7.4,
+      "learning_rate": 0.0009333333333333333,
+      "loss": 0.0733,
+      "step": 112
+    },
+    {
+      "epoch": 8.2,
+      "learning_rate": 0.0009238095238095239,
+      "loss": 0.1564,
+      "step": 119
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 0.0009126984126984126,
+      "loss": 0.0727,
+      "step": 126
+    },
+    {
+      "epoch": 9.2,
+      "learning_rate": 0.0009015873015873016,
+      "loss": 0.1515,
+      "step": 133
+    },
+    {
+      "epoch": 9.4,
+      "learning_rate": 0.0008904761904761904,
+      "loss": 0.0682,
+      "step": 140
+    },
+    {
+      "epoch": 10.2,
+      "learning_rate": 0.0008793650793650794,
+      "loss": 0.0594,
+      "step": 147
+    },
+    {
+      "epoch": 10.4,
+      "learning_rate": 0.0008682539682539683,
+      "loss": 0.137,
+      "step": 154
+    },
+    {
+      "epoch": 11.2,
+      "learning_rate": 0.0008571428571428571,
+      "loss": 0.0514,
+      "step": 161
+    },
+    {
+      "epoch": 11.4,
+      "learning_rate": 0.0008460317460317461,
+      "loss": 0.0494,
+      "step": 168
+    },
+    {
+      "epoch": 12.2,
+      "learning_rate": 0.000834920634920635,
+      "loss": 0.0306,
+      "step": 175
+    },
+    {
+      "epoch": 12.4,
+      "learning_rate": 0.0008238095238095238,
+      "loss": 0.041,
+      "step": 182
+    },
+    {
+      "epoch": 13.2,
+      "learning_rate": 0.0008126984126984127,
+      "loss": 0.0286,
+      "step": 189
+    },
+    {
+      "epoch": 13.4,
+      "learning_rate": 0.0008015873015873017,
+      "loss": 0.0283,
+      "step": 196
+    },
+    {
+      "epoch": 14.2,
+      "learning_rate": 0.0007904761904761905,
+      "loss": 0.0153,
+      "step": 203
+    },
+    {
+      "epoch": 14.4,
+      "learning_rate": 0.0007793650793650794,
+      "loss": 0.0194,
+      "step": 210
+    },
+    {
+      "epoch": 15.2,
+      "learning_rate": 0.0007682539682539683,
+      "loss": 0.0115,
+      "step": 217
+    },
+    {
+      "epoch": 15.4,
+      "learning_rate": 0.0007571428571428572,
+      "loss": 0.011,
+      "step": 224
+    },
+    {
+      "epoch": 16.2,
+      "learning_rate": 0.000746031746031746,
+      "loss": 0.0072,
+      "step": 231
+    },
+    {
+      "epoch": 16.4,
+      "learning_rate": 0.000734920634920635,
+      "loss": 0.0132,
+      "step": 238
+    },
+    {
+      "epoch": 17.2,
+      "learning_rate": 0.0007238095238095238,
+      "loss": 0.0065,
+      "step": 245
+    },
+    {
+      "epoch": 17.4,
+      "learning_rate": 0.0007126984126984128,
+      "loss": 0.0109,
+      "step": 252
+    },
+    {
+      "epoch": 18.2,
+      "learning_rate": 0.0007015873015873015,
+      "loss": 0.0064,
+      "step": 259
+    },
+    {
+      "epoch": 18.4,
+      "learning_rate": 0.0006904761904761905,
+      "loss": 0.0076,
+      "step": 266
+    },
+    {
+      "epoch": 19.2,
+      "learning_rate": 0.0006793650793650794,
+      "loss": 0.0028,
+      "step": 273
+    },
+    {
+      "epoch": 19.4,
+      "learning_rate": 0.0006682539682539683,
+      "loss": 0.0065,
+      "step": 280
+    }
+  ],
+  "logging_steps": 7,
+  "max_steps": 700,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 1.13811835060224e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-280/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad528ead7dbae4065a04d62f75623c6cf9fcf4a7316e3ebfc839939bdd9b8cd
+size 4472

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad528ead7dbae4065a04d62f75623c6cf9fcf4a7316e3ebfc839939bdd9b8cd
+size 4472

training_params.json

@@ -0,0 +1 @@
+{"model": "NousResearch/Llama-2-7b-chat-hf", "data_path": "Flyfer/CBDataSetBeta1", "project_name": "TestProject", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.001, "epochs": 20, "batch_size": 1, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 2048, "repo_id": "Flyfer/llama2-testv11", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null, "use_flash_attention_2": false, "log": "none", "disable_gradient_checkpointing": false, "model_ref": null, "dpo_beta": 0.1, "prompt_text_column": "prompt"}