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-pt-pl5
-  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: 18.3412
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,14 +32,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # liputan6-pt-pl5
 
-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: 3.8205
-- Rouge1: 18.6328
-- Rouge2: 4.2703
-- Rougel: 15.6625
-- Rougelsum: 16.9103
-- Gen Len: 30.177
+- Rouge1: 18.3412
+- Rouge2: 4.7361
+- Rougel: 15.5136
+- Rougelsum: 16.6913
+- Gen Len: 35.5
 
 ## Model description
 

all_results.json

@@ -0,0 +1,29 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 35.5,
+    "eval_loss": 3.820514440536499,
+    "eval_rouge1": 18.3412,
+    "eval_rouge2": 4.7361,
+    "eval_rougeL": 15.5136,
+    "eval_rougeLsum": 16.6913,
+    "eval_runtime": 1715.0696,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 0.583,
+    "eval_steps_per_second": 0.019,
+    "predict_gen_len": 35.234,
+    "predict_loss": 3.543308973312378,
+    "predict_rouge1": 21.9696,
+    "predict_rouge2": 6.2524,
+    "predict_rougeL": 18.1263,
+    "predict_rougeLsum": 20.1408,
+    "predict_runtime": 1735.6386,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 0.576,
+    "predict_steps_per_second": 0.018,
+    "total_flos": 3877644533760000.0,
+    "train_loss": 4.081830463712177,
+    "train_runtime": 1435.3865,
+    "train_samples": 1000,
+    "train_samples_per_second": 3.483,
+    "train_steps_per_second": 0.219
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 35.5,
+    "eval_loss": 3.820514440536499,
+    "eval_rouge1": 18.3412,
+    "eval_rouge2": 4.7361,
+    "eval_rougeL": 15.5136,
+    "eval_rougeLsum": 16.6913,
+    "eval_runtime": 1715.0696,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 0.583,
+    "eval_steps_per_second": 0.019
+}

predict_results.json

@@ -0,0 +1,12 @@
+{
+    "predict_gen_len": 35.234,
+    "predict_loss": 3.543308973312378,
+    "predict_rouge1": 21.9696,
+    "predict_rouge2": 6.2524,
+    "predict_rougeL": 18.1263,
+    "predict_rougeLsum": 20.1408,
+    "predict_runtime": 1735.6386,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 0.576,
+    "predict_steps_per_second": 0.018
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3877644533760000.0,
+    "train_loss": 4.081830463712177,
+    "train_runtime": 1435.3865,
+    "train_samples": 1000,
+    "train_samples_per_second": 3.483,
+    "train_steps_per_second": 0.219
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 18.6328,
+  "best_model_checkpoint": "bin/liputan6-pt-pl5/checkpoint-315",
+  "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": 0.9840264320373535,
+      "learning_rate": 0.0008,
+      "loss": 4.799,
+      "step": 63
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 40.873,
+      "eval_loss": 4.114248275756836,
+      "eval_rouge1": 13.0788,
+      "eval_rouge2": 2.2394,
+      "eval_rougeL": 10.8409,
+      "eval_rougeLsum": 11.8062,
+      "eval_runtime": 296.6779,
+      "eval_samples_per_second": 3.371,
+      "eval_steps_per_second": 0.108,
+      "step": 63
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9562803506851196,
+      "learning_rate": 0.0006,
+      "loss": 4.179,
+      "step": 126
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 32.962,
+      "eval_loss": 3.9927873611450195,
+      "eval_rouge1": 16.7604,
+      "eval_rouge2": 3.2541,
+      "eval_rougeL": 13.8889,
+      "eval_rougeLsum": 15.1654,
+      "eval_runtime": 249.03,
+      "eval_samples_per_second": 4.016,
+      "eval_steps_per_second": 0.128,
+      "step": 126
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.9820513725280762,
+      "learning_rate": 0.0004,
+      "loss": 3.9656,
+      "step": 189
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 30.549,
+      "eval_loss": 3.883206367492676,
+      "eval_rouge1": 18.1366,
+      "eval_rouge2": 3.9918,
+      "eval_rougeL": 15.2392,
+      "eval_rougeLsum": 16.4266,
+      "eval_runtime": 192.373,
+      "eval_samples_per_second": 5.198,
+      "eval_steps_per_second": 0.166,
+      "step": 189
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.9895921945571899,
+      "learning_rate": 0.0002,
+      "loss": 3.8038,
+      "step": 252
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 28.411,
+      "eval_loss": 3.855151414871216,
+      "eval_rouge1": 18.2504,
+      "eval_rouge2": 4.0948,
+      "eval_rougeL": 15.4777,
+      "eval_rougeLsum": 16.7374,
+      "eval_runtime": 138.9665,
+      "eval_samples_per_second": 7.196,
+      "eval_steps_per_second": 0.23,
+      "step": 252
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.030814290046692,
+      "learning_rate": 0.0,
+      "loss": 3.6617,
+      "step": 315
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 30.177,
+      "eval_loss": 3.820514440536499,
+      "eval_rouge1": 18.6328,
+      "eval_rouge2": 4.2703,
+      "eval_rougeL": 15.6625,
+      "eval_rougeLsum": 16.9103,
+      "eval_runtime": 173.6125,
+      "eval_samples_per_second": 5.76,
+      "eval_steps_per_second": 0.184,
+      "step": 315
+    },
+    {
+      "epoch": 5.0,
+      "step": 315,
+      "total_flos": 3877644533760000.0,
+      "train_loss": 4.081830463712177,
+      "train_runtime": 1435.3865,
+      "train_samples_per_second": 3.483,
+      "train_steps_per_second": 0.219
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3877644533760000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}