Add finetuned with KoAlpaca v1.1b

README.md

@@ -1,3 +1,55 @@
 ---
 license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: polyglot-12.8b-koalpaca-v1.1b
+  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. -->
+
+# polyglot-12.8b-koalpaca-v1.1b
+
+This model is a fine-tuned version of [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on an unknown 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 4
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.28.1
+- Pytorch 2.0.0+cu117
+- Datasets 2.11.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.1057900991015273,
+    "train_runtime": 20175.6269,
+    "train_samples": 57593,
+    "train_samples_per_second": 2.855,
+    "train_steps_per_second": 0.714
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "EleutherAI/polyglot-ko-12.8b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_steps": "global_step301000",
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.5,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 30003
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62609e6df7ed82684c17b082b397f393363c8bcd6d70e058e77552379acd90ce
+size 25953607721

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"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.1057900991015273,
+    "train_runtime": 20175.6269,
+    "train_samples": 57593,
+    "train_samples_per_second": 2.855,
+    "train_steps_per_second": 0.714
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 14399,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 0,
+      "loss": 2.4746,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-05,
+      "loss": 1.9874,
+      "step": 500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 5e-05,
+      "loss": 1.9445,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 5e-05,
+      "loss": 1.8596,
+      "step": 1500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 5e-05,
+      "loss": 1.7807,
+      "step": 2000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 5e-05,
+      "loss": 1.7298,
+      "step": 2500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 5e-05,
+      "loss": 1.6565,
+      "step": 3000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 5e-05,
+      "loss": 1.5484,
+      "step": 3500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5e-05,
+      "loss": 1.5049,
+      "step": 4000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5e-05,
+      "loss": 1.4478,
+      "step": 4500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 5e-05,
+      "loss": 1.3567,
+      "step": 5000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 5e-05,
+      "loss": 1.2812,
+      "step": 5500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 5e-05,
+      "loss": 1.1882,
+      "step": 6000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 5e-05,
+      "loss": 1.1447,
+      "step": 6500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 5e-05,
+      "loss": 1.0854,
+      "step": 7000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 5e-05,
+      "loss": 1.0182,
+      "step": 7500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5e-05,
+      "loss": 0.9675,
+      "step": 8000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 5e-05,
+      "loss": 0.9076,
+      "step": 8500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5e-05,
+      "loss": 0.8415,
+      "step": 9000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5e-05,
+      "loss": 0.8228,
+      "step": 9500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5e-05,
+      "loss": 0.7656,
+      "step": 10000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5e-05,
+      "loss": 0.7029,
+      "step": 10500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5e-05,
+      "loss": 0.6793,
+      "step": 11000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5e-05,
+      "loss": 0.6369,
+      "step": 11500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5e-05,
+      "loss": 0.5936,
+      "step": 12000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5e-05,
+      "loss": 0.5489,
+      "step": 12500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5e-05,
+      "loss": 0.531,
+      "step": 13000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5e-05,
+      "loss": 0.4948,
+      "step": 13500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5e-05,
+      "loss": 0.4555,
+      "step": 14000
+    },
+    {
+      "epoch": 1.0,
+      "step": 14399,
+      "total_flos": 945700963614720.0,
+      "train_loss": 1.1057900991015273,
+      "train_runtime": 20175.6269,
+      "train_samples_per_second": 2.855,
+      "train_steps_per_second": 0.714
+    }
+  ],
+  "max_steps": 14399,
+  "num_train_epochs": 1,
+  "total_flos": 945700963614720.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6056591c3ad528ed37e907ac6ffb1883ba10604b406d19e94a3ddbe33e4c9d02
+size 4859