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": "TinyPixel/Llama-2-7B-bf16-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 sha256:86e1dc9dc058e68c53d1b1248d03f207a022c9be725a23f230fb96759fc5cf57
+size 33600461

checkpoint-264/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.dev0
+
+- PEFT 0.5.0.dev0

checkpoint-264/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-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-264/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86e1dc9dc058e68c53d1b1248d03f207a022c9be725a23f230fb96759fc5cf57
+size 33600461

checkpoint-264/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0af33773013b6d0185d34d66502435c22ac3411c8f5f48f6c3ed8c62397bcc
+size 67216581

checkpoint-264/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28e5d25a032d09c4a3d6718b3173abf845c1cb0042c567f3f4f76ad7e2d2ff2
+size 14575

checkpoint-264/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a41ab85c58558fee6dcd0228f4fae0e20458d44f07c60df8063fa029dff7c7
+size 627

checkpoint-264/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-264/tokenizer.model

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

checkpoint-264/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-264/trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8181818181818183,
+  "eval_steps": 500,
+  "global_step": 264,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00012592592592592592,
+      "loss": 1.7865,
+      "step": 17
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00019409282700421943,
+      "loss": 1.5839,
+      "step": 34
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.000179746835443038,
+      "loss": 1.3442,
+      "step": 51
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00016540084388185655,
+      "loss": 1.2967,
+      "step": 68
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0001510548523206751,
+      "loss": 1.2723,
+      "step": 85
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00013670886075949366,
+      "loss": 1.2075,
+      "step": 102
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00012236286919831225,
+      "loss": 1.1807,
+      "step": 119
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00010801687763713079,
+      "loss": 1.0787,
+      "step": 136
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.367088607594936e-05,
+      "loss": 1.0961,
+      "step": 153
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.932489451476794e-05,
+      "loss": 1.0747,
+      "step": 170
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 6.49789029535865e-05,
+      "loss": 1.0936,
+      "step": 187
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 5.0632911392405066e-05,
+      "loss": 1.0467,
+      "step": 204
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 3.628691983122363e-05,
+      "loss": 0.9777,
+      "step": 221
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 2.1940928270042196e-05,
+      "loss": 1.0002,
+      "step": 238
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 7.5949367088607605e-06,
+      "loss": 0.948,
+      "step": 255
+    }
+  ],
+  "logging_steps": 17,
+  "max_steps": 264,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.1873419863719936e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-264/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02dffcfd2d7df20620d35ee2def64a55115ff4f48f64180e213ba26e8f941c07
+size 4027

runs/Aug17_11-16-46_7a99b650c2d1/events.out.tfevents.1692271007.7a99b650c2d1.3718.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb213892dffd7667c7215f191e35ae5acb1e94e6140f77f9e7cec7a8db5ee58
+size 4465

runs/Aug17_11-33-03_7a99b650c2d1/events.out.tfevents.1692271983.7a99b650c2d1.8265.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475b6a3549bfb5e721d5c32f1e27eee703d39fa8188d0903d5faee43c12457d6
+size 7153

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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02dffcfd2d7df20620d35ee2def64a55115ff4f48f64180e213ba26e8f941c07
+size 4027

training_params.json

@@ -0,0 +1 @@
+{"model": "TinyPixel/Llama-2-7B-bf16-sharded", "data_path": "dataset", "project_name": "llama2-test", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 3, "batch_size": 4, "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": "Sameera827/try111", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false}