KushwanthK/mistral-7b-instruct-tune-500s

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- generator
+model-index:
+- name: mistral7b_instruct_generation
+  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. -->
+
+# mistral7b_instruct_generation
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8140
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 0.03
+- training_steps: 500
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.8937        | 0.0028 | 20   | 1.8344          |
+| 1.8442        | 0.0056 | 40   | 1.8027          |
+| 1.887         | 0.0084 | 60   | 1.7948          |
+| 1.7711        | 0.0112 | 80   | 1.7884          |
+| 1.7809        | 0.0140 | 100  | 1.7881          |
+| 1.8632        | 0.0168 | 120  | 1.7957          |
+| 1.8436        | 0.0196 | 140  | 1.8012          |
+| 1.8959        | 0.0224 | 160  | 1.7860          |
+| 1.8644        | 0.0252 | 180  | 1.7912          |
+| 1.8285        | 0.0280 | 200  | 1.7884          |
+| 1.8769        | 0.0307 | 220  | 1.7982          |
+| 1.8726        | 0.0335 | 240  | 1.8046          |
+| 1.8227        | 0.0363 | 260  | 1.7954          |
+| 1.8554        | 0.0391 | 280  | 1.7927          |
+| 1.9006        | 0.0419 | 300  | 1.7952          |
+| 1.769         | 0.0447 | 320  | 1.8006          |
+| 1.8014        | 0.0475 | 340  | 1.7895          |
+| 1.8772        | 0.0503 | 360  | 1.7966          |
+| 1.7403        | 0.0531 | 380  | 1.7988          |
+| 1.8945        | 0.0559 | 400  | 1.7979          |
+| 1.8937        | 0.0587 | 420  | 1.7987          |
+| 1.9235        | 0.0615 | 440  | 1.8044          |
+| 1.8496        | 0.0643 | 460  | 1.7951          |
+| 1.8778        | 0.0671 | 480  | 1.7974          |
+| 1.8681        | 0.0699 | 500  | 1.8140          |
+
+
+### 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 +1,29 @@
+{
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "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:a17fdbd7df778419e6fffa9b07f6537ee15296fde0b3f1ffcd3332cfd994772b
+size 109069176

runs/May25_06-57-49_e164cc202637/events.out.tfevents.1716620316.e164cc202637.2817.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df9ce9eb1d0af57a9dfe3835f2aa4523849cd11dba77e65c8766ff03297fde6
+size 22932

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59aa77a454c7679704bc51722c5fe2ebfcbcc005ebb7f006dbc500bacd24f2b3
+size 5112