End of training

README.md

@@ -0,0 +1,84 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- reward-trainer
+- generated_from_trainer
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+metrics:
+- accuracy
+model-index:
+- name: layer-project
+  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. -->
+
+# layer-project
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0064
+- Accuracy: 1.0
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.0365        | 1.0   | 5    | 0.0393          | 1.0      |
+| 0.0142        | 2.0   | 10   | 0.0349          | 1.0      |
+| 0.0228        | 3.0   | 15   | 0.0295          | 1.0      |
+| 0.0157        | 4.0   | 20   | 0.0249          | 1.0      |
+| 0.0153        | 5.0   | 25   | 0.0211          | 1.0      |
+| 0.0117        | 6.0   | 30   | 0.0181          | 1.0      |
+| 0.0072        | 7.0   | 35   | 0.0155          | 1.0      |
+| 0.0121        | 8.0   | 40   | 0.0135          | 1.0      |
+| 0.0097        | 9.0   | 45   | 0.0119          | 1.0      |
+| 0.008         | 10.0  | 50   | 0.0106          | 1.0      |
+| 0.0055        | 11.0  | 55   | 0.0095          | 1.0      |
+| 0.0046        | 12.0  | 60   | 0.0087          | 1.0      |
+| 0.0085        | 13.0  | 65   | 0.0081          | 1.0      |
+| 0.0046        | 14.0  | 70   | 0.0076          | 1.0      |
+| 0.0059        | 15.0  | 75   | 0.0072          | 1.0      |
+| 0.0044        | 16.0  | 80   | 0.0069          | 1.0      |
+| 0.0021        | 17.0  | 85   | 0.0067          | 1.0      |
+| 0.0039        | 18.0  | 90   | 0.0066          | 1.0      |
+| 0.0027        | 19.0  | 95   | 0.0065          | 1.0      |
+| 0.0039        | 20.0  | 100  | 0.0064          | 1.0      |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "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": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b1ef1bc8690e97e22a23d6f4e789bcf364b042d42ae194ed61236f8270905a
+size 4525440

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 +1,41 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "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 sha256:4d4c1dda4a68896bc0cdcd3f7b8478380314ae12fe2f0f3a2985f6146f064aed
+size 4984