End of training

README.md

@@ -0,0 +1,68 @@
+---
+license: llama2
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: meta-llama/Llama-2-7b-hf
+model-index:
+- name: Llama2-7b-BoolQ-layers-0-9-train-A-0
+  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. -->
+
+# Llama2-7b-BoolQ-layers-0-9-train-A-0
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 10.6188
+
+## 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: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.6997        | 0.9996 | 1178 | 0.8920          |
+| 12.3189       | 2.0    | 2357 | 14.1257         |
+| 10.6997       | 2.9996 | 3535 | 10.7032         |
+| 10.6097       | 3.9983 | 4712 | 10.6188         |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.1
+- Pytorch 2.3.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,67 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.7.self_attn.k_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.3.self_attn.k_proj",
+    "model.layers.7.self_attn.o_proj",
+    "model.layers.5.self_attn.o_proj",
+    "model.layers.1.self_attn.o_proj",
+    "model.layers.5.self_attn.k_proj",
+    "model.layers.6.self_attn.k_proj",
+    "model.layers.0.self_attn.o_proj",
+    "model.layers.9.self_attn.o_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.8.self_attn.k_proj",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.2.self_attn.k_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.4.self_attn.o_proj",
+    "model.layers.3.self_attn.v_proj",
+    "model.layers.9.self_attn.k_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.4.self_attn.k_proj",
+    "model.layers.2.self_attn.o_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.8.self_attn.o_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.3.self_attn.o_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.6.self_attn.o_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.1.self_attn.k_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 sha256:3c95b41ddcdf9c2b497d551a21dfd334cc3881c224ae37471d04f90661ffc393
+size 10496272

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_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 sha256:2cc2c07c786daeeb0bdd832fcac286129ce1540dc0257b07842fe9f093c1a95b
+size 5112