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-lora-8
-  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: 29.078
 ---
 
 <!-- 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-lora-8
 
-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: 2.6385
-- Rouge1: 28.3508
-- Rouge2: 12.5031
-- Rougel: 24.1992
-- Rougelsum: 26.092
-- Gen Len: 32.655
+- Loss: 2.6337
+- Rouge1: 29.078
+- Rouge2: 13.2531
+- Rougel: 24.7383
+- Rougelsum: 26.5396
+- Gen Len: 35.496
 
 ## Model description
 

all_results.json

@@ -0,0 +1,29 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 35.496,
+    "eval_loss": 2.6337075233459473,
+    "eval_rouge1": 29.078,
+    "eval_rouge2": 13.2531,
+    "eval_rougeL": 24.7383,
+    "eval_rougeLsum": 26.5396,
+    "eval_runtime": 810.9249,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 1.233,
+    "eval_steps_per_second": 0.039,
+    "predict_gen_len": 35.069,
+    "predict_loss": 2.1046853065490723,
+    "predict_rouge1": 36.4081,
+    "predict_rouge2": 20.0914,
+    "predict_rougeL": 31.0252,
+    "predict_rougeLsum": 33.8995,
+    "predict_runtime": 888.8681,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 1.125,
+    "predict_steps_per_second": 0.036,
+    "total_flos": 3437376307200000.0,
+    "train_loss": 2.4014356340680805,
+    "train_runtime": 1409.9107,
+    "train_samples": 1000,
+    "train_samples_per_second": 3.546,
+    "train_steps_per_second": 0.223
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 35.496,
+    "eval_loss": 2.6337075233459473,
+    "eval_rouge1": 29.078,
+    "eval_rouge2": 13.2531,
+    "eval_rougeL": 24.7383,
+    "eval_rougeLsum": 26.5396,
+    "eval_runtime": 810.9249,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 1.233,
+    "eval_steps_per_second": 0.039
+}

predict_results.json

@@ -0,0 +1,12 @@
+{
+    "predict_gen_len": 35.069,
+    "predict_loss": 2.1046853065490723,
+    "predict_rouge1": 36.4081,
+    "predict_rouge2": 20.0914,
+    "predict_rougeL": 31.0252,
+    "predict_rougeLsum": 33.8995,
+    "predict_runtime": 888.8681,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 1.125,
+    "predict_steps_per_second": 0.036
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3437376307200000.0,
+    "train_loss": 2.4014356340680805,
+    "train_runtime": 1409.9107,
+    "train_samples": 1000,
+    "train_samples_per_second": 3.546,
+    "train_steps_per_second": 0.223
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 28.8883,
+  "best_model_checkpoint": "bin/liputan6-lora-8/checkpoint-252",
+  "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": 1.1928575038909912,
+      "learning_rate": 0.0008,
+      "loss": 3.1146,
+      "step": 63
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 28.445,
+      "eval_loss": 2.77751088142395,
+      "eval_rouge1": 25.1926,
+      "eval_rouge2": 10.831,
+      "eval_rougeL": 21.8588,
+      "eval_rougeLsum": 23.0603,
+      "eval_runtime": 282.5418,
+      "eval_samples_per_second": 3.539,
+      "eval_steps_per_second": 0.113,
+      "step": 63
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.15657377243042,
+      "learning_rate": 0.0006,
+      "loss": 2.3694,
+      "step": 126
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 35.297,
+      "eval_loss": 2.6682474613189697,
+      "eval_rouge1": 27.3169,
+      "eval_rouge2": 12.0479,
+      "eval_rougeL": 23.5983,
+      "eval_rougeLsum": 25.0305,
+      "eval_runtime": 263.6368,
+      "eval_samples_per_second": 3.793,
+      "eval_steps_per_second": 0.121,
+      "step": 126
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2961732149124146,
+      "learning_rate": 0.0004,
+      "loss": 2.2462,
+      "step": 189
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 31.547,
+      "eval_loss": 2.610564708709717,
+      "eval_rouge1": 27.8939,
+      "eval_rouge2": 12.0631,
+      "eval_rougeL": 23.6765,
+      "eval_rougeLsum": 25.5954,
+      "eval_runtime": 173.0596,
+      "eval_samples_per_second": 5.778,
+      "eval_steps_per_second": 0.185,
+      "step": 189
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.227543830871582,
+      "learning_rate": 0.0002,
+      "loss": 2.1582,
+      "step": 252
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 31.688,
+      "eval_loss": 2.6337075233459473,
+      "eval_rouge1": 28.8883,
+      "eval_rouge2": 12.7056,
+      "eval_rougeL": 24.6102,
+      "eval_rougeLsum": 26.4945,
+      "eval_runtime": 153.1276,
+      "eval_samples_per_second": 6.53,
+      "eval_steps_per_second": 0.209,
+      "step": 252
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2467632293701172,
+      "learning_rate": 0.0,
+      "loss": 2.1188,
+      "step": 315
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 32.655,
+      "eval_loss": 2.638486385345459,
+      "eval_rouge1": 28.3508,
+      "eval_rouge2": 12.5031,
+      "eval_rougeL": 24.1992,
+      "eval_rougeLsum": 26.092,
+      "eval_runtime": 177.4741,
+      "eval_samples_per_second": 5.635,
+      "eval_steps_per_second": 0.18,
+      "step": 315
+    },
+    {
+      "epoch": 5.0,
+      "step": 315,
+      "total_flos": 3437376307200000.0,
+      "train_loss": 2.4014356340680805,
+      "train_runtime": 1409.9107,
+      "train_samples_per_second": 3.546,
+      "train_steps_per_second": 0.223
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3437376307200000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}