End of training

README.md

@@ -0,0 +1,53 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: EleutherAI/polyglot-ko-1.3b
+tags:
+- generated_from_trainer
+model-index:
+- name: arstyle
+  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. -->
+
+# arstyle
+
+This model is a fine-tuned version of [EleutherAI/polyglot-ko-1.3b](https://huggingface.co/EleutherAI/polyglot-ko-1.3b) 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.48.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "EleutherAI/polyglot-ko-1.3b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "partial_rotary_factor": 0.5,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.5,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 30080
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.48.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e336bb4a06d0a02c2d4455fb7bebab8c37acbdc51e1cadc339db7b48a999193
+size 2663655160

runs/Jan30_06-58-02_2fd698e94d8e/events.out.tfevents.1738220305.2fd698e94d8e.1548.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d3fa0b961cbf5f20b58c7d95b395006b38348eab1f87a85a12158a3abc0e994
+size 5188

runs/Jan30_07-03-11_2fd698e94d8e/events.out.tfevents.1738220602.2fd698e94d8e.1864.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2de8c05a04190852f94c996a4d7f38ac59233c14f7ebf60feffb0cb46c61250
+size 5188

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72319de5ed9faf23d35f300df1a8c6a4effcaaedd9122617b330d3189bf3961
+size 5304