/content/eu_ai_model_mistral7b

README.md

@@ -0,0 +1,57 @@
+---
+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.
+
+## 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: 3e-05
+- 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: 8
+- training_steps: 896
+
+### Training results
+
+
+
+### 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 +1,33 @@
+{
+  "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,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "out_proj",
+    "ffn.down_proj",
+    "q_proj",
+    "v_proj",
+    "ffn.up_proj",
+    "k_proj"
+  ],
+  "task_type": "causal",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:662c1b6f8bb63a63b20de1be93e86b220296ea9aaebebde22f1feaeb3c089c69
+size 37774528

runs/Oct04_14-46-23_946e4b288798/events.out.tfevents.1728053184.946e4b288798.4607.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af6d0e22cc5ca9a4c25d388631ba7b5b983f64ab6c2a7943174b2f4a5b1b414
+size 5331

runs/Oct04_14-52-45_946e4b288798/events.out.tfevents.1728053566.946e4b288798.6964.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33db17a148921d7b9be8c194837af2741313b1975abc68e1ce073a3fe847c91
+size 6625

runs/Oct04_15-17-31_946e4b288798/events.out.tfevents.1728055052.946e4b288798.13749.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5e05cc2f5e5b648fee47929dfa5605b54590ebf42b4041f9b74622aec44f73
+size 8828

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9433ae31d2a32f8177943b19eefe0a70c2dc6ffa83afcf6655117c1b6d2a6a
+size 5176