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": "bn22/Mistral-7B-Instruct-v0.1-sharded",
+  "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:b85bd3763814d5326eb042e24e59326c6ffb9c47fab45fb41f6ede65c966da13
+size 27309386

checkpoint-30/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-30/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "bn22/Mistral-7B-Instruct-v0.1-sharded",
+  "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-30/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85bd3763814d5326eb042e24e59326c6ffb9c47fab45fb41f6ede65c966da13
+size 27309386

checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8ae01fee7651756cd1be8ea1d4c47982c84a69bf636b8503dd98a61751d3de
+size 54633978

checkpoint-30/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5afbaefc7bbcf91d724da172800c23bd0cd36e740462c6101df4d59a886b9c
+size 14244

checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a1a7cdc19350a0569e07fbb035c5e22179f5ede97216a49ff2b8fe9cd50e89
+size 1064

checkpoint-30/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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-30/tokenizer.model

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

checkpoint-30/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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
+    }
+  },
+  "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-30/trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 29.333333333333332,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 1.4717,
+      "step": 1
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.4717,
+      "step": 2
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.4497,
+      "step": 3
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 1.4049,
+      "step": 4
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 1.3354,
+      "step": 5
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.2413,
+      "step": 6
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 1.1378,
+      "step": 7
+    },
+    {
+      "epoch": 7.33,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 1.0309,
+      "step": 8
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 0.0002,
+      "loss": 0.9263,
+      "step": 9
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 0.00019753086419753085,
+      "loss": 0.8314,
+      "step": 10
+    },
+    {
+      "epoch": 10.33,
+      "learning_rate": 0.00019506172839506175,
+      "loss": 0.7409,
+      "step": 11
+    },
+    {
+      "epoch": 11.33,
+      "learning_rate": 0.0001925925925925926,
+      "loss": 0.6599,
+      "step": 12
+    },
+    {
+      "epoch": 12.33,
+      "learning_rate": 0.00019012345679012346,
+      "loss": 0.581,
+      "step": 13
+    },
+    {
+      "epoch": 13.33,
+      "learning_rate": 0.00018765432098765433,
+      "loss": 0.4985,
+      "step": 14
+    },
+    {
+      "epoch": 14.33,
+      "learning_rate": 0.0001851851851851852,
+      "loss": 0.4184,
+      "step": 15
+    },
+    {
+      "epoch": 15.33,
+      "learning_rate": 0.00018271604938271605,
+      "loss": 0.3421,
+      "step": 16
+    },
+    {
+      "epoch": 16.33,
+      "learning_rate": 0.00018024691358024692,
+      "loss": 0.271,
+      "step": 17
+    },
+    {
+      "epoch": 17.33,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.2084,
+      "step": 18
+    },
+    {
+      "epoch": 18.33,
+      "learning_rate": 0.00017530864197530866,
+      "loss": 0.1555,
+      "step": 19
+    },
+    {
+      "epoch": 19.33,
+      "learning_rate": 0.0001728395061728395,
+      "loss": 0.1131,
+      "step": 20
+    },
+    {
+      "epoch": 20.33,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.0872,
+      "step": 21
+    },
+    {
+      "epoch": 21.33,
+      "learning_rate": 0.00016790123456790124,
+      "loss": 0.0698,
+      "step": 22
+    },
+    {
+      "epoch": 22.33,
+      "learning_rate": 0.0001654320987654321,
+      "loss": 0.0578,
+      "step": 23
+    },
+    {
+      "epoch": 23.33,
+      "learning_rate": 0.00016296296296296295,
+      "loss": 0.0485,
+      "step": 24
+    },
+    {
+      "epoch": 24.33,
+      "learning_rate": 0.00016049382716049385,
+      "loss": 0.0412,
+      "step": 25
+    },
+    {
+      "epoch": 25.33,
+      "learning_rate": 0.0001580246913580247,
+      "loss": 0.0327,
+      "step": 26
+    },
+    {
+      "epoch": 26.33,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.0264,
+      "step": 27
+    },
+    {
+      "epoch": 27.33,
+      "learning_rate": 0.0001530864197530864,
+      "loss": 0.0202,
+      "step": 28
+    },
+    {
+      "epoch": 28.33,
+      "learning_rate": 0.0001506172839506173,
+      "loss": 0.0155,
+      "step": 29
+    },
+    {
+      "epoch": 29.33,
+      "learning_rate": 0.00014814814814814815,
+      "loss": 0.0137,
+      "step": 30
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 90,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 2623786293657600.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c783e34488731103d3604a4441576eb6189bac86bc7813b128541b0afe8bdd
+size 4536

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": "</s>",
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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
+    }
+  },
+  "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 sha256:92c783e34488731103d3604a4441576eb6189bac86bc7813b128541b0afe8bdd
+size 4536

training_params.json

@@ -0,0 +1 @@
+{"model": "bn22/Mistral-7B-Instruct-v0.1-sharded", "data_path": ".", "project_name": "mistral-7b-taelor-finetuned", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 30, "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": "persival-cogtive/taelor-setup", "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"}