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": "mistralai/Mistral-7B-v0.1",
+  "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 sha256:818f965b38527ec090710488f2ed539eb29a308e9a6e978084d2799726d0b761
+size 27309386

checkpoint-20/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-20/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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-20/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818f965b38527ec090710488f2ed539eb29a308e9a6e978084d2799726d0b761
+size 27309386

checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b092ab42c6c0c0871cbdadfdac9aa848de4830e5a4346bf786bbc540de53047
+size 54633978

checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552f477bc0da287482f92f8b95ec9881fdef2d97597b91da7d42d068a8681bd1
+size 14244

checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4c18cd380d4d2c0ee2aa76d8e22b68a563fc85f1cea7dbf7872a16aaf8dd2d
+size 1064

checkpoint-20/special_tokens_map.json

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

checkpoint-20/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-20/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-20/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.5,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 5e-05,
+      "loss": 1.7498,
+      "step": 1
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.0001,
+      "loss": 1.7498,
+      "step": 2
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.7179,
+      "step": 3
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.0002,
+      "loss": 1.6526,
+      "step": 4
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 0.00019444444444444446,
+      "loss": 1.5549,
+      "step": 5
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 0.00018888888888888888,
+      "loss": 1.4428,
+      "step": 6
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 0.00018333333333333334,
+      "loss": 1.3413,
+      "step": 7
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 1.2458,
+      "step": 8
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 0.00017222222222222224,
+      "loss": 1.1408,
+      "step": 9
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 1.0299,
+      "step": 10
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 0.0001611111111111111,
+      "loss": 0.9223,
+      "step": 11
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.8215,
+      "step": 12
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.7281,
+      "step": 13
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 0.00014444444444444444,
+      "loss": 0.6339,
+      "step": 14
+    },
+    {
+      "epoch": 14.5,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 0.5883,
+      "step": 15
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.4937,
+      "step": 16
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 0.00012777777777777776,
+      "loss": 0.4356,
+      "step": 17
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 0.00012222222222222224,
+      "loss": 0.3726,
+      "step": 18
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 0.00011666666666666668,
+      "loss": 0.319,
+      "step": 19
+    },
+    {
+      "epoch": 19.5,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.2746,
+      "step": 20
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 40,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 1749190862438400.0,
+  "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:e352f5102aa074e2fa31d00ee7ee152a0cf64d79c772f18405817be11c3ae30a
+size 4536

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "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:e352f5102aa074e2fa31d00ee7ee152a0cf64d79c772f18405817be11c3ae30a
+size 4536

training_params.json

@@ -0,0 +1 @@
+{"model": "mistralai/Mistral-7B-v0.1", "data_path": ".", "project_name": "mistral-7b-sapiens-2", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 20, "batch_size": 12, "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": 1024, "repo_id": "ranonrat/mistral-7b-sapiens-3", "use_int4": true, "trainer": "sft", "target_modules": "q_proj,v_proj", "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"}