pmrster/test-mistral-7b-fine-tune-1

README.md

@@ -0,0 +1,79 @@
+---
+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 the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3365
+
+## 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
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 1.9309        | 2.0833  | 25   | 1.6414          |
+| 0.5146        | 4.1667  | 50   | 1.8892          |
+| 0.2481        | 6.25    | 75   | 1.9643          |
+| 0.1804        | 8.3333  | 100  | 1.9184          |
+| 0.1683        | 10.4167 | 125  | 1.9770          |
+| 0.1582        | 12.5    | 150  | 2.1538          |
+| 0.1591        | 14.5833 | 175  | 2.1592          |
+| 0.1509        | 16.6667 | 200  | 2.1474          |
+| 0.1478        | 18.75   | 225  | 2.1839          |
+| 0.1465        | 20.8333 | 250  | 2.2255          |
+| 0.1465        | 22.9167 | 275  | 2.2356          |
+| 0.1427        | 25.0    | 300  | 2.2581          |
+| 0.144         | 27.0833 | 325  | 2.2707          |
+| 0.139         | 29.1667 | 350  | 2.2694          |
+| 0.1437        | 31.25   | 375  | 2.2956          |
+| 0.141         | 33.3333 | 400  | 2.3087          |
+| 0.1359        | 35.4167 | 425  | 2.3056          |
+| 0.1385        | 37.5    | 450  | 2.3213          |
+| 0.1363        | 39.5833 | 475  | 2.3332          |
+| 0.1359        | 41.6667 | 500  | 2.3365          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "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,
+  "layer_replication": null,
+  "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": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "lm_head",
+    "down_proj"
+  ],
+  "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 sha256:87666f31de4cf217f723b83891edad9ef2a9d6eae789b2ee9b66451abce714ad
+size 864513616

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0b867866ae7aff9894222d7c90340e7dad0c3d1ed3c3d254b57ea312cbc009
+size 5112