End of training

README.md

@@ -0,0 +1,117 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- unsloth
+- generated_from_trainer
+base_model: unsloth/tinyllama-bnb-4bit
+datasets:
+- generator
+model-index:
+- name: MunicipalPredictionModel-TinyLlama
+  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. -->
+
+# MunicipalPredictionModel-TinyLlama
+
+This model is a fine-tuned version of [unsloth/tinyllama-bnb-4bit](https://huggingface.co/unsloth/tinyllama-bnb-4bit) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2394
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.788         | 0.0578 | 10   | 1.4309          |
+| 1.3849        | 0.1156 | 20   | 1.3661          |
+| 1.3425        | 0.1734 | 30   | 1.3366          |
+| 1.3263        | 0.2312 | 40   | 1.3180          |
+| 1.3223        | 0.2890 | 50   | 1.3034          |
+| 1.293         | 0.3468 | 60   | 1.2890          |
+| 1.2815        | 0.4046 | 70   | 1.2816          |
+| 1.275         | 0.4624 | 80   | 1.2763          |
+| 1.2765        | 0.5202 | 90   | 1.2676          |
+| 1.2786        | 0.5780 | 100  | 1.2635          |
+| 1.25          | 0.6358 | 110  | 1.2576          |
+| 1.2476        | 0.6936 | 120  | 1.2524          |
+| 1.2479        | 0.7514 | 130  | 1.2491          |
+| 1.2497        | 0.8092 | 140  | 1.2437          |
+| 1.2362        | 0.8671 | 150  | 1.2409          |
+| 1.2511        | 0.9249 | 160  | 1.2363          |
+| 1.2368        | 0.9827 | 170  | 1.2335          |
+| 1.1279        | 1.0405 | 180  | 1.2404          |
+| 1.0929        | 1.0983 | 190  | 1.2408          |
+| 1.0803        | 1.1561 | 200  | 1.2426          |
+| 1.0939        | 1.2139 | 210  | 1.2391          |
+| 1.0869        | 1.2717 | 220  | 1.2364          |
+| 1.084         | 1.3295 | 230  | 1.2337          |
+| 1.0967        | 1.3873 | 240  | 1.2314          |
+| 1.0922        | 1.4451 | 250  | 1.2287          |
+| 1.0774        | 1.5029 | 260  | 1.2264          |
+| 1.0825        | 1.5607 | 270  | 1.2247          |
+| 1.08          | 1.6185 | 280  | 1.2217          |
+| 1.0828        | 1.6763 | 290  | 1.2174          |
+| 1.0791        | 1.7341 | 300  | 1.2169          |
+| 1.0907        | 1.7919 | 310  | 1.2148          |
+| 1.0748        | 1.8497 | 320  | 1.2137          |
+| 1.082         | 1.9075 | 330  | 1.2104          |
+| 1.0753        | 1.9653 | 340  | 1.2081          |
+| 1.0165        | 2.0231 | 350  | 1.2490          |
+| 0.9266        | 2.0809 | 360  | 1.2431          |
+| 0.9239        | 2.1387 | 370  | 1.2440          |
+| 0.9207        | 2.1965 | 380  | 1.2443          |
+| 0.9218        | 2.2543 | 390  | 1.2485          |
+| 0.9262        | 2.3121 | 400  | 1.2447          |
+| 0.9246        | 2.3699 | 410  | 1.2463          |
+| 0.9145        | 2.4277 | 420  | 1.2422          |
+| 0.9178        | 2.4855 | 430  | 1.2457          |
+| 0.9229        | 2.5434 | 440  | 1.2421          |
+| 0.9205        | 2.6012 | 450  | 1.2429          |
+| 0.9184        | 2.6590 | 460  | 1.2436          |
+| 0.93          | 2.7168 | 470  | 1.2395          |
+| 0.9111        | 2.7746 | 480  | 1.2418          |
+| 0.9125        | 2.8324 | 490  | 1.2396          |
+| 0.9268        | 2.8902 | 500  | 1.2389          |
+| 0.9148        | 2.9480 | 510  | 1.2394          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.43.4
+- Pytorch 2.2.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.0

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/tinyllama-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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "mlp.gate_up_proj",
+    "self_attn.qkv_proj.weight",
+    "self_attn.o_proj.weight",
+    "mlp.down_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:f80b9db16e5fed0bf6ecae0adbad111753a18767096b07670e575d400522b07e
+size 403743472

runs/Sep23_10-07-52_sammie/events.out.tfevents.1727108974.sammie.1130.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891e814e65ad449c904aed97cf4d53b507c4146eb988b5ed3070905dccf9a2b5
+size 30783

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": "</s>",
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "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:d5c8d4ca54c402a351b455c5aa2a1c419b359bb8071d4496b4ab4bdb1d95dda2
+size 5560