joy2000/mistral-brev

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: mistral-journal-finetune
+  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. -->
+
+# mistral-journal-finetune
+
+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.
+It achieves the following results on the evaluation set:
+- Loss: 0.6324
+
+## 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: 2.5e-05
+- train_batch_size: 2
+- 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: 1
+- training_steps: 500
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.9438        | 0.03  | 25   | 1.2268          |
+| 1.1449        | 0.06  | 50   | 1.1088          |
+| 1.1742        | 0.09  | 75   | 1.0455          |
+| 1.0987        | 0.12  | 100  | 0.9922          |
+| 1.0298        | 0.15  | 125  | 0.9476          |
+| 0.9422        | 0.18  | 150  | 0.9082          |
+| 0.934         | 0.21  | 175  | 0.8789          |
+| 0.8254        | 0.24  | 200  | 0.8560          |
+| 1.045         | 0.27  | 225  | 0.8217          |
+| 0.9614        | 0.3   | 250  | 0.7783          |
+| 0.8001        | 0.33  | 275  | 0.7525          |
+| 0.8299        | 0.36  | 300  | 0.7238          |
+| 0.7427        | 0.39  | 325  | 0.7087          |
+| 0.7323        | 0.42  | 350  | 0.6973          |
+| 0.7501        | 0.45  | 375  | 0.6794          |
+| 0.819         | 0.48  | 400  | 0.6692          |
+| 0.7871        | 0.51  | 425  | 0.6544          |
+| 0.7604        | 0.54  | 450  | 0.6431          |
+| 0.6955        | 0.57  | 475  | 0.6356          |
+| 0.6919        | 0.6   | 500  | 0.6324          |
+
+
+### Framework versions
+
+- PEFT 0.7.2.dev0
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "lm_head"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6211a4fab6bb6a261bb32fbd028c4430ba5fd3b246ec554ccda582fc4e81c4e
+size 864513616

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf6c8f2f40116a86dce40032b15ec423ef4c208c787c771c93e091660bcbb97
+size 4728