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:e07d392e7c1ac87397e850614e8283182290f690d1e194e4dde8dd3e9a2fb2df
+size 33600461

added_tokens.json

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

checkpoint-966/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-966/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-966/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07d392e7c1ac87397e850614e8283182290f690d1e194e4dde8dd3e9a2fb2df
+size 33600461

checkpoint-966/added_tokens.json

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

checkpoint-966/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73691c75f56d098cf7dd63da4eea1cf2d870db0d96bae9a3bfb6651d4a695f16
+size 67216581

checkpoint-966/pytorch_model.bin

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

checkpoint-966/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4ef92777521220f0c48eea3c9a5a155641cafccff2a373ccefd41ec9797820
+size 14575

checkpoint-966/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522ccb241b744758595fafc9b1cbc4d81058f9c8467ab3d4dfc916f5ebdb35e7
+size 627

checkpoint-966/special_tokens_map.json

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

checkpoint-966/tokenizer.model

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

checkpoint-966/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-966/trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 966,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00013195876288659794,
+      "loss": 1.0791,
+      "step": 64
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019286536248561565,
+      "loss": 0.7112,
+      "step": 128
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00017813578826237055,
+      "loss": 0.6255,
+      "step": 192
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00016340621403912543,
+      "loss": 0.6076,
+      "step": 256
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00014867663981588033,
+      "loss": 0.6049,
+      "step": 320
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0001339470655926352,
+      "loss": 0.5394,
+      "step": 384
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00011921749136939012,
+      "loss": 0.5384,
+      "step": 448
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.000104487917146145,
+      "loss": 0.5194,
+      "step": 512
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 8.975834292289989e-05,
+      "loss": 0.5137,
+      "step": 576
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 7.502876869965478e-05,
+      "loss": 0.5329,
+      "step": 640
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 6.0299194476409674e-05,
+      "loss": 0.4623,
+      "step": 704
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 4.556962025316456e-05,
+      "loss": 0.4729,
+      "step": 768
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 3.084004602991945e-05,
+      "loss": 0.4677,
+      "step": 832
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.611047180667434e-05,
+      "loss": 0.4768,
+      "step": 896
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.380897583429229e-06,
+      "loss": 0.4893,
+      "step": 960
+    }
+  ],
+  "logging_steps": 64,
+  "max_steps": 966,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.570602351423652e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-966/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f834eb4447db12f1aa776ef77213abf0dd0c7b790f8bba06a9e8304399678e4
+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:b69850e756fbfae8825c0eaa67f380ea24944a69055d087ca28d89e44ff5bec6
+size 5348786304

runs/Oct13_17-56-35_6518eb10d224/events.out.tfevents.1697219796.6518eb10d224.1291.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd7bcc4a7039e5180f278558f41addaf30f63ad3645311a0da34189bdecb4d9
+size 7284

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 sha256:8f834eb4447db12f1aa776ef77213abf0dd0c7b790f8bba06a9e8304399678e4
+size 4091

training_params.json

@@ -0,0 +1 @@
+{"model": "FlagAlpha/Llama2-Chinese-7b-Chat", "data_path": "wangzhang/sdb", "project_name": "ChatSequioaDB_7b", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "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": 2048, "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/ChatSequioaDB_7b", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": true, "username": null, "use_flash_attention_2": false, "disable_gradient_checkpointing": false}