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": "FlagAlpha/Llama2-Chinese-7b-Chat",
+  "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 sha256:77ade734c60389e2ff174a45147dcb7b847c3fb6924e6d939838e9bb0b2058a5
+size 33600461

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

checkpoint-696/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-696/adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "FlagAlpha/Llama2-Chinese-7b-Chat",
+  "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-696/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ade734c60389e2ff174a45147dcb7b847c3fb6924e6d939838e9bb0b2058a5
+size 33600461

checkpoint-696/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

checkpoint-696/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53f2a4cf87f874f7028ae8c81122b35a2ff3c8e9d42372fd6adaad54f4056a6
+size 67216581

checkpoint-696/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
+size 443

checkpoint-696/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc72fb193ed5d5e9ef927f6726d8b99d4cea09392f79bdd99fae32d08fd464a5
+size 14575

checkpoint-696/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db50f1bedfa24345193fed1ca3721b897e83491227f777f7f448726281af8dd
+size 627

checkpoint-696/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-696/tokenizer.model

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

checkpoint-696/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": false
+}

checkpoint-696/trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 696,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00013142857142857143,
+      "loss": 1.5363,
+      "step": 46
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019297124600638977,
+      "loss": 1.1994,
+      "step": 92
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001782747603833866,
+      "loss": 1.0903,
+      "step": 138
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0001635782747603834,
+      "loss": 0.9799,
+      "step": 184
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0001488817891373802,
+      "loss": 0.9738,
+      "step": 230
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.000134185303514377,
+      "loss": 0.8681,
+      "step": 276
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0001194888178913738,
+      "loss": 0.8991,
+      "step": 322
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00010479233226837062,
+      "loss": 0.9033,
+      "step": 368
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 9.009584664536742e-05,
+      "loss": 0.9134,
+      "step": 414
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 7.539936102236423e-05,
+      "loss": 0.8864,
+      "step": 460
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 6.070287539936103e-05,
+      "loss": 0.7979,
+      "step": 506
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 4.600638977635783e-05,
+      "loss": 0.8006,
+      "step": 552
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 3.130990415335464e-05,
+      "loss": 0.7841,
+      "step": 598
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.6613418530351437e-05,
+      "loss": 0.8221,
+      "step": 644
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 1.9169329073482426e-06,
+      "loss": 0.803,
+      "step": 690
+    }
+  ],
+  "logging_steps": 46,
+  "max_steps": 696,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 5.645876465133158e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-696/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221defbff5b6d6d8f74a178cf6e936125d84f9aaa1eee964e7504cff02ebf691
+size 4091

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "FlagAlpha/Llama2-Chinese-7b-Chat",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95378d8855e6ac585e8f235a2db59c53a511614883cda4d15b7fb683f14c457
+size 5362811008

runs/Oct12_01-04-52_33f7c2a40506/events.out.tfevents.1697072692.33f7c2a40506.475.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e87b56dca05815da584a551f056e10ed10c4e3afb9b3f414b7545a682d26011
+size 7273

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221defbff5b6d6d8f74a178cf6e936125d84f9aaa1eee964e7504cff02ebf691
+size 4091

training_params.json

@@ -0,0 +1 @@
+{"model": "FlagAlpha/Llama2-Chinese-7b-Chat", "data_path": "wangzhang/sdb", "project_name": "nlp_sdb_model", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 3, "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": "wangzhang/nlp-sdb", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": true, "username": null, "use_flash_attention_2": false}