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-16
-  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: 28.4262
 ---
 
 <!-- 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-16
 
-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: 2.6616
-- Rouge1: 28.2024
-- Rouge2: 12.3241
-- Rougel: 23.9228
-- Rougelsum: 25.9287
-- Gen Len: 33.644
+- Loss: 2.6574
+- Rouge1: 28.4262
+- Rouge2: 12.9627
+- Rougel: 24.3479
+- Rougelsum: 26.1183
+- Gen Len: 37.115
 
 ## Model description
 

all_results.json

@@ -0,0 +1,29 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 37.115,
+    "eval_loss": 2.657413959503174,
+    "eval_rouge1": 28.4262,
+    "eval_rouge2": 12.9627,
+    "eval_rougeL": 24.3479,
+    "eval_rougeLsum": 26.1183,
+    "eval_runtime": 1082.3747,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 0.924,
+    "eval_steps_per_second": 0.03,
+    "predict_gen_len": 36.246,
+    "predict_loss": 2.1108694076538086,
+    "predict_rouge1": 36.2324,
+    "predict_rouge2": 20.0427,
+    "predict_rougeL": 31.2369,
+    "predict_rougeLsum": 33.8051,
+    "predict_runtime": 976.7295,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 1.024,
+    "predict_steps_per_second": 0.033,
+    "total_flos": 3450965852160000.0,
+    "train_loss": 2.2952696300688245,
+    "train_runtime": 1511.6568,
+    "train_samples": 1000,
+    "train_samples_per_second": 3.308,
+    "train_steps_per_second": 0.208
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 37.115,
+    "eval_loss": 2.657413959503174,
+    "eval_rouge1": 28.4262,
+    "eval_rouge2": 12.9627,
+    "eval_rougeL": 24.3479,
+    "eval_rougeLsum": 26.1183,
+    "eval_runtime": 1082.3747,
+    "eval_samples": 1000,
+    "eval_samples_per_second": 0.924,
+    "eval_steps_per_second": 0.03
+}

predict_results.json

@@ -0,0 +1,12 @@
+{
+    "predict_gen_len": 36.246,
+    "predict_loss": 2.1108694076538086,
+    "predict_rouge1": 36.2324,
+    "predict_rouge2": 20.0427,
+    "predict_rougeL": 31.2369,
+    "predict_rougeLsum": 33.8051,
+    "predict_runtime": 976.7295,
+    "predict_samples": 1000,
+    "predict_samples_per_second": 1.024,
+    "predict_steps_per_second": 0.033
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3450965852160000.0,
+    "train_loss": 2.2952696300688245,
+    "train_runtime": 1511.6568,
+    "train_samples": 1000,
+    "train_samples_per_second": 3.308,
+    "train_steps_per_second": 0.208
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 28.5562,
+  "best_model_checkpoint": "bin/liputan6-lora-16/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": 1.2158453464508057,
+      "learning_rate": 0.0008,
+      "loss": 2.9434,
+      "step": 63
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 35.404,
+      "eval_loss": 2.6951351165771484,
+      "eval_rouge1": 25.6796,
+      "eval_rouge2": 11.0701,
+      "eval_rougeL": 22.1424,
+      "eval_rougeLsum": 23.2849,
+      "eval_runtime": 342.3214,
+      "eval_samples_per_second": 2.921,
+      "eval_steps_per_second": 0.093,
+      "step": 63
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3100322484970093,
+      "learning_rate": 0.0006,
+      "loss": 2.3008,
+      "step": 126
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 35.768,
+      "eval_loss": 2.654245376586914,
+      "eval_rouge1": 27.4005,
+      "eval_rouge2": 12.0574,
+      "eval_rougeL": 23.6657,
+      "eval_rougeLsum": 25.1251,
+      "eval_runtime": 257.9915,
+      "eval_samples_per_second": 3.876,
+      "eval_steps_per_second": 0.124,
+      "step": 126
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.364740014076233,
+      "learning_rate": 0.0004,
+      "loss": 2.1668,
+      "step": 189
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 32.749,
+      "eval_loss": 2.6101162433624268,
+      "eval_rouge1": 28.0403,
+      "eval_rouge2": 12.2713,
+      "eval_rougeL": 23.9451,
+      "eval_rougeLsum": 25.7556,
+      "eval_runtime": 180.1413,
+      "eval_samples_per_second": 5.551,
+      "eval_steps_per_second": 0.178,
+      "step": 189
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.419220209121704,
+      "learning_rate": 0.0002,
+      "loss": 2.0618,
+      "step": 252
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 32.931,
+      "eval_loss": 2.657413959503174,
+      "eval_rouge1": 28.5562,
+      "eval_rouge2": 12.5992,
+      "eval_rougeL": 24.2399,
+      "eval_rougeLsum": 26.2278,
+      "eval_runtime": 174.5382,
+      "eval_samples_per_second": 5.729,
+      "eval_steps_per_second": 0.183,
+      "step": 252
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2581560611724854,
+      "learning_rate": 0.0,
+      "loss": 2.0036,
+      "step": 315
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 33.644,
+      "eval_loss": 2.661618232727051,
+      "eval_rouge1": 28.2024,
+      "eval_rouge2": 12.3241,
+      "eval_rougeL": 23.9228,
+      "eval_rougeLsum": 25.9287,
+      "eval_runtime": 195.8376,
+      "eval_samples_per_second": 5.106,
+      "eval_steps_per_second": 0.163,
+      "step": 315
+    },
+    {
+      "epoch": 5.0,
+      "step": 315,
+      "total_flos": 3450965852160000.0,
+      "train_loss": 2.2952696300688245,
+      "train_runtime": 1511.6568,
+      "train_samples_per_second": 3.308,
+      "train_steps_per_second": 0.208
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 315,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3450965852160000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}