End of training

README.md

@@ -1,3 +1,53 @@
 ---
 license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+model-index:
+- name: Lora-add-paramter
+  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. -->
+
+# Lora-add-paramter
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral"
+  },
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "embed_tokens",
+    "lm_head",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": null,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d19d0bf27fd8801cf728ec9a1e6fc072c444f5c3014cfbc57463cf29f2e40ae4
+size 1177026136

runs/Feb10_14-10-45_89e0ea32bb02/events.out.tfevents.1707574246.89e0ea32bb02.249.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c533cee0afdb11d6c3ff2b0746f9593ecff259b1ddfd1ace7d4b4a8bbc21904
+size 6462

runs/Feb10_14-17-15_89e0ea32bb02/events.out.tfevents.1707574635.89e0ea32bb02.249.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c2e3dd953a508ece53fd813caad801b6fba60de03f9766cccc73db990cf0d6
+size 4247

runs/Feb10_14-24-25_89e0ea32bb02/events.out.tfevents.1707575074.89e0ea32bb02.13522.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:499be7b83b9a019c6070932d41ec63f9aa58b93098ca67f6ad7917d5d1170959
+size 6443

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ed01f8b16cca5107778fb6486243708f5fb6f9e853b603a6e36470f44bbd04
+size 4600