jmeneu/Fine-tuning-Mistral

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- generated_from_trainer
+datasets:
+- imdb
+metrics:
+- accuracy
+model-index:
+- name: Mistral-7B-v0.1-lora-text-classification
+  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-7B-v0.1-lora-text-classification
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the imdb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0108
+- Accuracy: {'accuracy': 0.52024}
+
+## 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: 0.005
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy              |
+|:-------------:|:-----:|:-----:|:---------------:|:---------------------:|
+| 1.0658        | 1.0   | 12500 | 1.0108          | {'accuracy': 0.52024} |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "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,
+  "lora_alpha": 32,
+  "lora_dropout": 0.01,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 2,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "SEQ_CLS"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc1809aa56f860eb0909d3df4edf552279c3db4b61ae711b9d3b40773f0690c
+size 3441168

runs/Dec03_10-39-47_910116764b25/events.out.tfevents.1701599988.910116764b25.1605.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7baf7510c96d2fa66324100b9654fc79fed478841adeff3a4e352f709f44e25
+size 4792

runs/Dec03_10-39-47_910116764b25/events.out.tfevents.1701600214.910116764b25.1605.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10014e6601bba65cebda01d0d15ccb551c07f46ec1a636f49fdc1a771e9c890
+size 4184

runs/Dec03_10-47-08_910116764b25/events.out.tfevents.1701600428.910116764b25.3826.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0245f216201b295c641920d553351c6615937a1c928bec312a2fd8d55cf42b83
+size 5597

runs/Dec03_11-05-39_910116764b25/events.out.tfevents.1701601539.910116764b25.8971.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6484afc0bc2501f1749ce237a0a0b0ce709a73b69d16d83dc9f33624bb819423
+size 4812

runs/Dec03_11-05-39_910116764b25/events.out.tfevents.1701601593.910116764b25.8971.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4bb452474d9747e839c2c1d404078b6e17bde825179e1f0aa6c9748bd8d6b2
+size 4184

runs/Dec03_11-07-38_910116764b25/events.out.tfevents.1701601667.910116764b25.8971.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8202feedf9b0fbb4e977cc0be20c0a2d43e56c6278876000fe08152c57d443c
+size 4184

runs/Dec03_11-09-33_910116764b25/events.out.tfevents.1701601774.910116764b25.10171.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3f44546ccf951f52bcbd1c48bd492085a5fca999f699a009a410054fc37647
+size 8737

runs/Dec03_11-09-33_910116764b25/events.out.tfevents.1701606176.910116764b25.10171.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272af6abab1f534c4c0a0e84d1bec4a11b16442725fa0d798d2103c7dccc9187
+size 9411

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": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "batched": true,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47dff75f0666d513d32182eea798cc5328bd27076404acc6d2d4537a31f96ec3
+size 4664