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 sha256:16fde90a97c60aed5065e57c6d165d685f7dc99e92d998adf544e8c71d31e689
+size 33600906

added_tokens.json

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

checkpoint-77/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-77/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-77/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fde90a97c60aed5065e57c6d165d685f7dc99e92d998adf544e8c71d31e689
+size 33600906

checkpoint-77/added_tokens.json

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

checkpoint-77/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc17f4b34bafc58908da8144bad9de2ed10dcf9945201a09d00e1befa7f5ba8
+size 67217018

checkpoint-77/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de2fc6d2b4ade0448d2d7e3ef5fb50372de0f446fd4bcd2f3834db8fb9bd674
+size 14244

checkpoint-77/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d18109ad90dc69eb6ec757ed437dd3e26425370d3a2e3e4404b2c1b253096b
+size 1064

checkpoint-77/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-77/tokenizer.model

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

checkpoint-77/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-77/trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.38888888888889,
+  "eval_steps": 500,
+  "global_step": 77,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 3e-05,
+      "loss": 1.7262,
+      "step": 3
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 6e-05,
+      "loss": 1.9459,
+      "step": 6
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 9e-05,
+      "loss": 1.8076,
+      "step": 9
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00012,
+      "loss": 1.4458,
+      "step": 12
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.6202,
+      "step": 15
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.00018,
+      "loss": 1.1957,
+      "step": 18
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 0.00019887640449438204,
+      "loss": 1.4084,
+      "step": 21
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 0.0001955056179775281,
+      "loss": 1.2387,
+      "step": 24
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.00019213483146067416,
+      "loss": 1.0168,
+      "step": 27
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 0.00018876404494382024,
+      "loss": 1.1336,
+      "step": 30
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 0.0001853932584269663,
+      "loss": 0.9109,
+      "step": 33
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 0.00018202247191011236,
+      "loss": 0.6177,
+      "step": 36
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 0.00017865168539325842,
+      "loss": 0.6269,
+      "step": 39
+    },
+    {
+      "epoch": 5.39,
+      "learning_rate": 0.0001752808988764045,
+      "loss": 0.6662,
+      "step": 42
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 0.00017191011235955056,
+      "loss": 0.5579,
+      "step": 45
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 0.00016853932584269662,
+      "loss": 0.4686,
+      "step": 48
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 0.0001651685393258427,
+      "loss": 0.3634,
+      "step": 51
+    },
+    {
+      "epoch": 7.28,
+      "learning_rate": 0.00016179775280898877,
+      "loss": 0.4219,
+      "step": 54
+    },
+    {
+      "epoch": 8.06,
+      "learning_rate": 0.00015842696629213485,
+      "loss": 0.3465,
+      "step": 57
+    },
+    {
+      "epoch": 8.22,
+      "learning_rate": 0.0001550561797752809,
+      "loss": 0.2471,
+      "step": 60
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 0.00015168539325842697,
+      "loss": 0.2689,
+      "step": 63
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 0.00014831460674157306,
+      "loss": 0.2027,
+      "step": 66
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 0.00014494382022471912,
+      "loss": 0.2501,
+      "step": 69
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 0.00014157303370786517,
+      "loss": 0.1825,
+      "step": 72
+    },
+    {
+      "epoch": 10.28,
+      "learning_rate": 0.00013820224719101123,
+      "loss": 0.1805,
+      "step": 75
+    }
+  ],
+  "logging_steps": 3,
+  "max_steps": 198,
+  "num_train_epochs": 11,
+  "save_steps": 500,
+  "total_flos": 6259650928312320.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-77/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ad6742aa4c595ab92aa22fda1a67c7ee13e354506f7462857dcbe28ea14607
+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 sha256:80ad6742aa4c595ab92aa22fda1a67c7ee13e354506f7462857dcbe28ea14607
+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": 0.0002, "epochs": 11, "batch_size": 2, "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-testv5", "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"}