/content/eu_ai_model_mistral7b

README.md

@@ -0,0 +1,96 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: peft
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+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: 1.4476
+
+## 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: 0.001
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- 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: 17
+- training_steps: 1792
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.8156        | 0.1115 | 50   | 1.7682          |
+| 1.6754        | 0.2230 | 100  | 1.6347          |
+| 1.5257        | 0.3344 | 150  | 1.5543          |
+| 1.5435        | 0.4459 | 200  | 1.5301          |
+| 1.613         | 0.5574 | 250  | 1.5579          |
+| 1.6178        | 0.6689 | 300  | 1.6006          |
+| 1.675         | 0.7804 | 350  | 1.5209          |
+| 1.5046        | 0.8919 | 400  | 1.5203          |
+| 1.5977        | 1.0033 | 450  | 1.5253          |
+| 1.5303        | 1.1148 | 500  | 1.4984          |
+| 1.4748        | 1.2263 | 550  | 1.5073          |
+| 1.4955        | 1.3378 | 600  | 1.4998          |
+| 1.5737        | 1.4493 | 650  | 1.5405          |
+| 1.5662        | 1.5608 | 700  | 1.5147          |
+| 1.417         | 1.6722 | 750  | 1.5047          |
+| 1.5732        | 1.7837 | 800  | 1.4768          |
+| 1.5077        | 1.8952 | 850  | 1.4948          |
+| 1.5634        | 2.0067 | 900  | 1.4768          |
+| 1.5219        | 2.1182 | 950  | 1.4752          |
+| 1.4073        | 2.2297 | 1000 | 1.4776          |
+| 1.4915        | 2.3411 | 1050 | 1.4799          |
+| 1.4585        | 2.4526 | 1100 | 1.4868          |
+| 1.4979        | 2.5641 | 1150 | 1.4703          |
+| 1.4755        | 2.6756 | 1200 | 1.4617          |
+| 1.4167        | 2.7871 | 1250 | 1.4576          |
+| 1.5095        | 2.8986 | 1300 | 1.4651          |
+| 1.477         | 3.0100 | 1350 | 1.4526          |
+| 1.4495        | 3.1215 | 1400 | 1.4660          |
+| 1.5609        | 3.2330 | 1450 | 1.4547          |
+| 1.4319        | 3.3445 | 1500 | 1.4478          |
+| 1.3469        | 3.4560 | 1550 | 1.4597          |
+| 1.4454        | 3.5674 | 1600 | 1.4478          |
+| 1.4071        | 3.6789 | 1650 | 1.4506          |
+| 1.3686        | 3.7904 | 1700 | 1.4485          |
+| 1.4958        | 3.9019 | 1750 | 1.4476          |
+
+
+### Framework versions
+
+- PEFT 0.13.0
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "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": 8,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_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 sha256:16c860b38dc1d1c3700a6a81e657c3e944b0694c895d6eb1ae4d457b10107e15
+size 13648432

runs/Sep27_14-06-12_e43ae22af8f2/events.out.tfevents.1727445979.e43ae22af8f2.1867.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff6915fde08b951651c835f060a29e97e34c7d6da23b5ce490d9a911be29740
+size 4905

runs/Sep27_14-12-04_e43ae22af8f2/events.out.tfevents.1727446396.e43ae22af8f2.1867.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20ad35c496b2f8a9a83fc52f5934651330c0fcbbada04f30503bed71450d3605
+size 4184

runs/Sep27_14-14-46_e43ae22af8f2/events.out.tfevents.1727446490.e43ae22af8f2.8258.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effcb09806bebaa2abbf1ed2dbab3435d3659c7cac3a58dadbd9b6f9cfa2883d
+size 7171

runs/Sep27_14-40-16_e43ae22af8f2/events.out.tfevents.1727448033.e43ae22af8f2.14823.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45b9d2c406d563238bc33b94669d90856f9abd61bdac15c61909434fdd80570
+size 4184

runs/Sep27_14-40-50_e43ae22af8f2/events.out.tfevents.1727448054.e43ae22af8f2.14823.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:266665bd2542d8dd4d129a6d2e713c8a64bf8bf38f3c092e21e627932709fb94
+size 4184

runs/Sep27_14-41-57_e43ae22af8f2/events.out.tfevents.1727448121.e43ae22af8f2.15440.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c2a75b468746baeb44c0429444f2062fd1569dbf9670841ee9ed712f2597a5
+size 22113

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ff26e167a9478789c2d262a782aec148f9e28a5297d2e0c67c1dde92e20dda
+size 5176