kogpt2_small_simple_qa

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+base_model: MrBananaHuman/kogpt2_small
+tags:
+- generated_from_trainer
+model-index:
+- name: test_v5
+  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. -->
+
+# test_v5
+
+This model is a fine-tuned version of [MrBananaHuman/kogpt2_small](https://huggingface.co/MrBananaHuman/kogpt2_small) 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 1.13.1+cu116
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "MrBananaHuman/kogpt2_small",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 52000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed60a859cf3daa4b7ddc316e0db01895b042257f9038607852dbb7dd72126bc
+size 503128704

runs/Nov22_03-35-19_75d5a95252af/events.out.tfevents.1700624122.75d5a95252af.24844.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e7d29da3e7481b2299ccad9c718176cb4f28b8c21277b15ecbfe12f47fa51fd
+size 7507

trainer_state.json

@@ -0,0 +1,136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 3,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.7248471372984996e-05,
+      "loss": 3.6424,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.4469149527515285e-05,
+      "loss": 3.4737,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.168982768204558e-05,
+      "loss": 3.4762,
+      "step": 1500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.891050583657588e-05,
+      "loss": 3.3944,
+      "step": 2000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.613118399110617e-05,
+      "loss": 3.3814,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.3351862145636464e-05,
+      "loss": 3.3406,
+      "step": 3000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.057254030016676e-05,
+      "loss": 2.7112,
+      "step": 3500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.7793218454697057e-05,
+      "loss": 2.7357,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.501389660922735e-05,
+      "loss": 2.7325,
+      "step": 4500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2.2234574763757643e-05,
+      "loss": 2.6802,
+      "step": 5000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.945525291828794e-05,
+      "loss": 2.7204,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6675931072818232e-05,
+      "loss": 2.6908,
+      "step": 6000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.3896609227348528e-05,
+      "loss": 2.259,
+      "step": 6500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.1117287381878821e-05,
+      "loss": 2.2829,
+      "step": 7000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.337965536409116e-06,
+      "loss": 2.2751,
+      "step": 7500
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.558643690939411e-06,
+      "loss": 2.2862,
+      "step": 8000
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 2.7793218454697053e-06,
+      "loss": 2.2833,
+      "step": 8500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 2.2729,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "step": 9000,
+      "total_flos": 2160942262272000.0,
+      "train_loss": 2.813265679253472,
+      "train_runtime": 715.4534,
+      "train_samples_per_second": 50.318,
+      "train_steps_per_second": 12.579
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9000,
+  "num_train_epochs": 3,
+  "save_steps": 5000,
+  "total_flos": 2160942262272000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc7d72ea92cc6e5b894c0ad164b1252000911661ce87a735049a25e9f2651f5
+size 4091