subha-roy/legal-ps-defence-mistral-v3-7b

README.md

@@ -1,3 +1,61 @@
----
-license: mit
----
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+library_name: peft
+license: apache-2.0
+tags:
+- trl
+- sft
+- unsloth
+- generated_from_trainer
+model-index:
+- name: legal-ps-defence-mistral-v3-7b
+  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. -->
+
+# legal-ps-defence-mistral-v3-7b
+
+This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-instruct-v0.3-bnb-4bit) 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: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 3407
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- training_steps: 60
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "k_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:e5d730ac95a598ded51fcb39fbbb7d1805086cb883511530afdbd17bda121ba1
+size 167832240

runs/Oct07_03-26-07_a7b604bd1a54/events.out.tfevents.1728271639.a7b604bd1a54.267.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d42572dca0231580a14af7860c56d4ddb30a19396ab7e389811c909775cfa8
+size 18546

runs/Oct14_05-44-56_750dcd2031df/events.out.tfevents.1728884769.750dcd2031df.250.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778f770850e2589359731fdf141dc92d0b8242b927ede8283a95170c3b9f4b1a
+size 18546

runs/Oct16_08-14-21_b01a39543d4b/events.out.tfevents.1729066534.b01a39543d4b.484.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e34cb7da9b76333efe2f4de8753dcce95d72bf23fc5852cd49128c3e7a3f4591
+size 18543

runs/Oct17_02-32-37_b4ee09d34f31/events.out.tfevents.1729132432.b4ee09d34f31.1098.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e77d8275e261e1ef441d506b1faa556da66ffae1873f6e279234c70dc1bfb1f
+size 18543

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[control_768]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c314e6c4c8046ff21e08f4324ee1b2e8a13236e54c2a182c9ed6534cc7b57518
+size 5496