Upload 8 files

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "paust/pko-t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50358
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ddae68a05c9c43809a148e35736311e35f4ee3130863a5d97ce249d5613fc10
+size 1102350184

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffb714bb6de2850cc6b88ae603d6c7a923819e5e4a59b4f21d2bcaf4d8e6b7bf
+size 2204870650

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a77bd69234016228ec9ebf99497a0ea574087b712e15db1557f33fb48092239e
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337d6ae372b376365d9a318f2e56ce0db29afd63d67df5aef7cc5e4d3baecd7f
+size 1064

trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1870,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.703195333480835,
+      "eval_runtime": 211.7753,
+      "eval_samples_per_second": 3.532,
+      "eval_steps_per_second": 0.444,
+      "step": 374
+    },
+    {
+      "epoch": 1.3368983957219251,
+      "grad_norm": 0.5129834413528442,
+      "learning_rate": 1.4652406417112302e-05,
+      "loss": 2.9329,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6699346303939819,
+      "eval_runtime": 210.8953,
+      "eval_samples_per_second": 3.547,
+      "eval_steps_per_second": 0.446,
+      "step": 748
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 0.537359356880188,
+      "learning_rate": 9.3048128342246e-06,
+      "loss": 0.6964,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.655941903591156,
+      "eval_runtime": 210.9443,
+      "eval_samples_per_second": 3.546,
+      "eval_steps_per_second": 0.446,
+      "step": 1122
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6526938676834106,
+      "eval_runtime": 211.2934,
+      "eval_samples_per_second": 3.54,
+      "eval_steps_per_second": 0.445,
+      "step": 1496
+    },
+    {
+      "epoch": 4.010695187165775,
+      "grad_norm": 0.4965839087963104,
+      "learning_rate": 3.957219251336899e-06,
+      "loss": 0.6599,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.087284373880832e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76fa0804427b39eb374b1e3b5ed0385732a5efe248c77a39860274997e5af57c
+size 5240