End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- id
 license: apache-2.0
 base_model: LazarusNLP/IndoNanoT5-base
 tags:
@@ -9,7 +11,20 @@ metrics:
 - rouge
 model-index:
 - name: liputan6-unipelt
-  results: []
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: id_liputan6 canonical
+      type: id_liputan6
+      config: canonical
+      split: validation
+      args: canonical
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 6.2596
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,13 +32,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # liputan6-unipelt
 
-This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on the id_liputan6 dataset.
+This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on the id_liputan6 canonical dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6316
-- Rouge1: 1.8166
-- Rouge2: 0.0438
-- Rougel: 1.7867
-- Rougelsum: 1.8115
+- Loss: 3.9181
+- Rouge1: 6.2596
+- Rouge2: 1.3631
+- Rougel: 5.5527
+- Rougelsum: 5.702
 - Gen Len: 127.0
 
 ## Model description

all_results.json

@@ -0,0 +1,29 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 127.0,
+    "eval_loss": 3.9181036949157715,
+    "eval_rouge1": 6.2596,
+    "eval_rouge2": 1.3631,
+    "eval_rougeL": 5.5527,
+    "eval_rougeLsum": 5.702,
+    "eval_runtime": 3038.3287,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 0.329,
+    "eval_steps_per_second": 0.011,
+    "predict_gen_len": 127.0,
+    "predict_loss": 3.675906181335449,
+    "predict_rouge1": 8.1435,
+    "predict_rouge2": 1.7586,
+    "predict_rougeL": 6.9904,
+    "predict_rougeLsum": 7.4145,
+    "predict_runtime": 3068.2499,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 0.326,
+    "predict_steps_per_second": 0.01,
+    "total_flos": 3920273141760000.0,
+    "train_loss": 3.429138425796751,
+    "train_runtime": 4104.3672,
+    "train_samples": 1000,
+    "train_samples_per_second": 1.218,
+    "train_steps_per_second": 0.077
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 127.0,
+    "eval_loss": 3.9181036949157715,
+    "eval_rouge1": 6.2596,
+    "eval_rouge2": 1.3631,
+    "eval_rougeL": 5.5527,
+    "eval_rougeLsum": 5.702,
+    "eval_runtime": 3038.3287,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 0.329,
+    "eval_steps_per_second": 0.011
+}

predict_results.json

@@ -0,0 +1,12 @@
+{
+    "predict_gen_len": 127.0,
+    "predict_loss": 3.675906181335449,
+    "predict_rouge1": 8.1435,
+    "predict_rouge2": 1.7586,
+    "predict_rougeL": 6.9904,
+    "predict_rougeLsum": 7.4145,
+    "predict_runtime": 3068.2499,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 0.326,
+    "predict_steps_per_second": 0.01
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3920273141760000.0,
+    "train_loss": 3.429138425796751,
+    "train_runtime": 4104.3672,
+    "train_samples": 1000,
+    "train_samples_per_second": 1.218,
+    "train_steps_per_second": 0.077
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 6.5087,
+  "best_model_checkpoint": "bin/liputan6-unipelt/checkpoint-63",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 315,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6662813425064087,
+      "learning_rate": 0.0008,
+      "loss": 4.4282,
+      "step": 63
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 127.0,
+      "eval_loss": 3.9181036949157715,
+      "eval_rouge1": 6.5087,
+      "eval_rouge2": 1.1507,
+      "eval_rougeL": 5.6509,
+      "eval_rougeLsum": 5.8646,
+      "eval_runtime": 719.7468,
+      "eval_samples_per_second": 1.389,
+      "eval_steps_per_second": 0.044,
+      "step": 63
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9859250783920288,
+      "learning_rate": 0.0006,
+      "loss": 3.5887,
+      "step": 126
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 127.0,
+      "eval_loss": 3.7177910804748535,
+      "eval_rouge1": 2.446,
+      "eval_rouge2": 0.2311,
+      "eval_rougeL": 2.2699,
+      "eval_rougeLsum": 2.3165,
+      "eval_runtime": 730.7553,
+      "eval_samples_per_second": 1.368,
+      "eval_steps_per_second": 0.044,
+      "step": 126
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.097254991531372,
+      "learning_rate": 0.0004,
+      "loss": 3.2648,
+      "step": 189
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 127.0,
+      "eval_loss": 3.648098945617676,
+      "eval_rouge1": 2.5164,
+      "eval_rouge2": 0.1545,
+      "eval_rougeL": 2.3984,
+      "eval_rougeLsum": 2.4483,
+      "eval_runtime": 742.5951,
+      "eval_samples_per_second": 1.347,
+      "eval_steps_per_second": 0.043,
+      "step": 189
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.1174938678741455,
+      "learning_rate": 0.0002,
+      "loss": 3.0219,
+      "step": 252
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 127.0,
+      "eval_loss": 3.6383612155914307,
+      "eval_rouge1": 1.8155,
+      "eval_rouge2": 0.0676,
+      "eval_rougeL": 1.7586,
+      "eval_rougeLsum": 1.7921,
+      "eval_runtime": 741.1853,
+      "eval_samples_per_second": 1.349,
+      "eval_steps_per_second": 0.043,
+      "step": 252
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.148689031600952,
+      "learning_rate": 0.0,
+      "loss": 2.8422,
+      "step": 315
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 127.0,
+      "eval_loss": 3.6315574645996094,
+      "eval_rouge1": 1.8166,
+      "eval_rouge2": 0.0438,
+      "eval_rougeL": 1.7867,
+      "eval_rougeLsum": 1.8115,
+      "eval_runtime": 723.9069,
+      "eval_samples_per_second": 1.381,
+      "eval_steps_per_second": 0.044,
+      "step": 315
+    },
+    {
+      "epoch": 5.0,
+      "step": 315,
+      "total_flos": 3920273141760000.0,
+      "train_loss": 3.429138425796751,
+      "train_runtime": 4104.3672,
+      "train_samples_per_second": 1.218,
+      "train_steps_per_second": 0.077
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3920273141760000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}