Upload 6 files

README.md

@@ -0,0 +1,43 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+- polyglot-ko
+- gpt-neox
+- KoAlpaca
+model-index:
+- name: KoAlpaca-Polyglot-5.8B
+  results: []
+language:
+- ko
+datasets:
+- KoAlpaca-v1.1b
+pipeline_tag: text-generation
+---
+
+
+# KoAlpaca-Polyglot-5.8B (v1.1b)
+
+This model is a fine-tuned version of [EleutherAI/polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-5.8b) on a KoAlpaca Dataset v1.1b
+
+Detail Codes are available at [KoAlpaca Github Repository](https://github.com/Beomi/KoAlpaca)
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.29.0.dev0
+- Pytorch 2.0.0+cu117
+- Datasets 2.10.1
+- Tokenizers 0.13.2

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.2509765625,
+  "best_model_checkpoint": "./models/2023-03-16_1edc4008-e54e/checkpoint-2534",
+  "epoch": 3.0,
+  "global_step": 7602,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9997369113391214e-05,
+      "loss": 9.8984,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.2605,
+      "step": 2534
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2509765625,
+      "eval_runtime": 191.3685,
+      "eval_samples_per_second": 23.536,
+      "eval_steps_per_second": 2.942,
+      "step": 2534
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1598,
+      "step": 5068
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.258544921875,
+      "eval_runtime": 159.499,
+      "eval_samples_per_second": 28.238,
+      "eval_steps_per_second": 3.53,
+      "step": 5068
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.0753,
+      "step": 7602
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.3056640625,
+      "eval_runtime": 159.3863,
+      "eval_samples_per_second": 28.258,
+      "eval_steps_per_second": 3.532,
+      "step": 7602
+    }
+  ],
+  "max_steps": 7602,
+  "num_train_epochs": 3,
+  "total_flos": 2.1525111523686482e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4872b8314368e34757a8c3791ebfcf77a89ff4d439e81f25e5640f42c35bec74
+size 3323