Updated model

README.md

@@ -0,0 +1,54 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: BizConsultant
+  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. -->
+
+# BizConsultant
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- training_steps: 6
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.32.0.dev0
+- Pytorch 2.0.0
+- Datasets 2.14.4
+- Tokenizers 0.13.3

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2fc323a0408cee7d756cfb402c31c80a8dcd3e782dc114de20c42a63ed16a2
+size 160077005

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "total_flos": 42650566778880.0,
+    "train_loss": 2.389628251393636,
+    "train_runtime": 39.2629,
+    "train_samples_per_second": 0.611,
+    "train_steps_per_second": 0.153
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "total_flos": 42650566778880.0,
+    "train_loss": 2.389628251393636,
+    "train_runtime": 39.2629,
+    "train_samples_per_second": 0.611,
+    "train_steps_per_second": 0.153
+}

trainer_state.json

@@ -0,0 +1,28 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0013729977116704805,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "step": 6,
+      "total_flos": 42650566778880.0,
+      "train_loss": 2.389628251393636,
+      "train_runtime": 39.2629,
+      "train_samples_per_second": 0.611,
+      "train_steps_per_second": 0.153
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 42650566778880.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ac0db2deb2139cb448a023a3dc53a82c952d78c89d126c7a619268f1a86d61
+size 4091