End of training

README.md

@@ -0,0 +1,53 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: baichuan-inc/Baichuan2-7B-Chat
+model-index:
+- name: output
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# output
+
+This model is a fine-tuned version of [baichuan-inc/Baichuan2-7B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
+- lr_scheduler_type: constant
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.39.3
+- Pytorch 2.1.1+cu118
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "baichuan-inc/Baichuan2-7B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 1,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "W_pack"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8435702d85eb957e709a271cf67f94bb155fd1e16bd7091f2a3fb23f7fef3a
+size 1057000

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:79452955be6b419a65984273a9f08af86042e1c2a75ee3ba989cbf620a133cc2
+size 2001107

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "baichuan-inc/Baichuan2-7B-Chat--tokenization_baichuan.BaichuanTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BaichuanTokenizer",
+  "unk_token": "<unk>",
+  "use_fast": false
+}

trainer_state.json

@@ -0,0 +1,205 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.7118462980814906,
+      "learning_rate": 2e-05,
+      "loss": 3.2188,
+      "step": 1
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.243513187461372,
+      "learning_rate": 2e-05,
+      "loss": 3.2031,
+      "step": 2
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.255141780135075,
+      "learning_rate": 2e-05,
+      "loss": 3.4062,
+      "step": 3
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.9969165185367705,
+      "learning_rate": 2e-05,
+      "loss": 3.3906,
+      "step": 4
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.438489764211926,
+      "learning_rate": 2e-05,
+      "loss": 3.0156,
+      "step": 5
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.766192546154473,
+      "learning_rate": 2e-05,
+      "loss": 3.4844,
+      "step": 6
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 3.9558834203135564,
+      "learning_rate": 2e-05,
+      "loss": 3.3438,
+      "step": 7
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.674429472944892,
+      "learning_rate": 2e-05,
+      "loss": 3.2812,
+      "step": 8
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.397569304216886,
+      "learning_rate": 2e-05,
+      "loss": 3.5625,
+      "step": 9
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.711305621777796,
+      "learning_rate": 2e-05,
+      "loss": 3.3906,
+      "step": 10
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.522398149101374,
+      "learning_rate": 2e-05,
+      "loss": 3.5156,
+      "step": 11
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.720634885278218,
+      "learning_rate": 2e-05,
+      "loss": 3.0469,
+      "step": 12
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.785757297998787,
+      "learning_rate": 2e-05,
+      "loss": 3.2031,
+      "step": 13
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.048262973601319,
+      "learning_rate": 2e-05,
+      "loss": 3.1875,
+      "step": 14
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.7511911027906355,
+      "learning_rate": 2e-05,
+      "loss": 3.3906,
+      "step": 15
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.0425470439337685,
+      "learning_rate": 2e-05,
+      "loss": 3.2656,
+      "step": 16
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.98478458099974,
+      "learning_rate": 2e-05,
+      "loss": 3.0781,
+      "step": 17
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.799674032749701,
+      "learning_rate": 2e-05,
+      "loss": 3.3906,
+      "step": 18
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.29152733822888,
+      "learning_rate": 2e-05,
+      "loss": 3.0469,
+      "step": 19
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.129518256677459,
+      "learning_rate": 2e-05,
+      "loss": 3.1875,
+      "step": 20
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 5.376728680507069,
+      "learning_rate": 2e-05,
+      "loss": 3.5156,
+      "step": 21
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.486180337502593,
+      "learning_rate": 2e-05,
+      "loss": 3.0469,
+      "step": 22
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.325703260677074,
+      "learning_rate": 2e-05,
+      "loss": 3.0469,
+      "step": 23
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.997299669613812,
+      "learning_rate": 2e-05,
+      "loss": 3.2344,
+      "step": 24
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.358892642300858,
+      "learning_rate": 2e-05,
+      "loss": 3.1562,
+      "step": 25
+    },
+    {
+      "epoch": 1.0,
+      "step": 25,
+      "total_flos": 478414897152.0,
+      "train_loss": 3.264375,
+      "train_runtime": 89.414,
+      "train_samples_per_second": 2.203,
+      "train_steps_per_second": 0.28
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 478414897152.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9777306178442ab094924e72fec92f58a7ad5317283e4a958fd2571c8a19eafe
+size 6200