upload

README.md

@@ -1,3 +1,41 @@
 ---
 license: apache-2.0
+base_model: meta-llama/Llama-2-7b-hf
+datasets:
+- b-mc2/sql-create-context
+language:
+- en
+pipeline_tag: text2text-generation
+tags:
+- punica
+- llama-factory
+- lora
+- generated_from_trainer
 ---
+
+* Base Model: [Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf)
+* LoRA target: `q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj`
+* LoRA rank: 16
+
+See <https://github.com/punica-ai/punica/tree/master/examples/finetune>
+
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 4.0
+
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.2.0.dev20230911+cu121
+- Datasets 2.14.4
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "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,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c6b1ffd5d9dc567b0014a251fbac14d83d9d01b7d1fb1322a0c9627ee4f139
+size 160069834

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.01796033810001285,
+    "train_runtime": 18572.7384,
+    "train_samples_per_second": 16.923,
+    "train_steps_per_second": 0.529
+}

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
+  }
+}

sqlctx-r16.punica.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e321a0ff1fc10a4244d9549357eb40e0729fe8c1cbfb7f5dcff1288a43ee93
+size 159912672

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.01796033810001285,
+    "train_runtime": 18572.7384,
+    "train_samples_per_second": 16.923,
+    "train_steps_per_second": 0.529
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3848f4caaf8f90ffa05a58fb5d63cf874b8aa053b5e44103a147f7f6a660c2de
+size 4664