Training in progress, epoch 1

README.md

@@ -0,0 +1,52 @@
+---
+license: bigscience-bloom-rail-1.0
+base_model: vlsp-2023-vllm/hoa-7b
+tags:
+- generated_from_trainer
+model-index:
+- name: model
+  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. -->
+
+# model
+
+This model is a fine-tuned version of [vlsp-2023-vllm/hoa-7b](https://huggingface.co/vlsp-2023-vllm/hoa-7b) on the None dataset.
+
+## 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: 1
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu117
+- Datasets 2.13.1
+- Tokenizers 0.14.0

adapter_config.json

@@ -0,0 +1,16 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "vlsp-2023-vllm/hoa-7b",
+  "inference_mode": true,
+  "num_attention_heads": 32,
+  "num_layers": 30,
+  "num_transformer_submodules": 1,
+  "num_virtual_tokens": 8,
+  "peft_type": "PROMPT_TUNING",
+  "prompt_tuning_init": "RANDOM",
+  "prompt_tuning_init_text": null,
+  "revision": null,
+  "task_type": "CAUSAL_LM",
+  "token_dim": 4096,
+  "tokenizer_name_or_path": "vlsp-2023-vllm/hoa-7b"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf15cec3cde1d4c50f75a680c910339cf1198e6da2f764f864a524f895993c00
+size 131837

added_tokens.json

@@ -0,0 +1,8 @@
+{
+  "</s>": 2,
+  "<mask>": 4,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3,
+  "<|endoftext|>": 5
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e62e3b3ec9ad7a9e41f071a7ae113486f0034596835cd60bbac77217f50564
+size 4091