End of training

README.md

@@ -0,0 +1,89 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.6
+tags:
+- generated_from_trainer
+model-index:
+- name: TinyLlama-1.1B-Chat-v0.6-BALLUFF
+  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. -->
+
+# TinyLlama-1.1B-Chat-v0.6-BALLUFF
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.6](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.6) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2857
+
+## 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: 0.001
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.4974        | 1.0   | 1334  | 0.4325          |
+| 0.4279        | 2.0   | 2668  | 0.4047          |
+| 0.304         | 3.0   | 4002  | 0.3933          |
+| 0.2024        | 4.0   | 5336  | 0.3896          |
+| 0.298         | 5.0   | 6670  | 0.3859          |
+| 0.4684        | 6.0   | 8004  | 0.4056          |
+| 0.3579        | 7.0   | 9338  | 0.3844          |
+| 0.3633        | 8.0   | 10672 | 0.3963          |
+| 0.8385        | 9.0   | 12006 | 0.3809          |
+| 0.4261        | 10.0  | 13340 | 0.3974          |
+| 0.6172        | 11.0  | 14674 | 0.3797          |
+| 0.4697        | 12.0  | 16008 | 0.3747          |
+| 0.3488        | 13.0  | 17342 | 0.3687          |
+| 0.5322        | 14.0  | 18676 | 0.3583          |
+| 0.3615        | 15.0  | 20010 | 0.3571          |
+| 0.4629        | 16.0  | 21344 | 0.3501          |
+| 0.2742        | 17.0  | 22678 | 0.3425          |
+| 0.2556        | 18.0  | 24012 | 0.3340          |
+| 0.1484        | 19.0  | 25346 | 0.3287          |
+| 0.3551        | 20.0  | 26680 | 0.3227          |
+| 0.2442        | 21.0  | 28014 | 0.3129          |
+| 0.2195        | 22.0  | 29348 | 0.3087          |
+| 0.1966        | 23.0  | 30682 | 0.3024          |
+| 0.5957        | 24.0  | 32016 | 0.2962          |
+| 0.2548        | 25.0  | 33350 | 0.2926          |
+| 0.2288        | 26.0  | 34684 | 0.2896          |
+| 0.1871        | 27.0  | 36018 | 0.2872          |
+| 0.4647        | 28.0  | 37352 | 0.2862          |
+| 0.1915        | 29.0  | 38686 | 0.2858          |
+| 0.4057        | 30.0  | 40020 | 0.2857          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "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:b1627a69183e36b802aa7a945e8cade6ee5e6f778a927f5f276249830beda311
+size 4518648

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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "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 sha256:4f3e572933bf504f598ba8b5bf062f5f08d71a0ce5f5419526c85526b3707905
+size 5240