End of training

README.md

@@ -1,4 +1,6 @@
 ---
+language:
+- id
 license: apache-2.0
 base_model: LazarusNLP/IndoNanoT5-base
 tags:
@@ -18,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4876
-- Rouge1: 73.194
-- Rouge2: 66.308
-- Rougel: 70.335
-- Rougelsum: 72.3629
-- Gen Len: 102.86
+- Rouge1: 73.5772
+- Rouge2: 66.7059
+- Rougel: 70.6615
+- Rougelsum: 72.7397
+- Gen Len: 102.9213
 
 ## Model description
 

all_results.json

@@ -1,29 +1,29 @@
 {
     "epoch": 5.0,
-    "eval_gen_len": 103.516,
-    "eval_loss": 0.4996706545352936,
-    "eval_rouge1": 73.7275,
-    "eval_rouge2": 66.7471,
-    "eval_rougeL": 70.8087,
-    "eval_rougeLsum": 72.8058,
-    "eval_runtime": 986.8474,
+    "eval_gen_len": 102.92133333333334,
+    "eval_loss": 0.4875640571117401,
+    "eval_rouge1": 73.5772,
+    "eval_rouge2": 66.7059,
+    "eval_rougeL": 70.6615,
+    "eval_rougeLsum": 72.7397,
+    "eval_runtime": 993.2105,
     "eval_samples": 750,
-    "eval_samples_per_second": 0.76,
+    "eval_samples_per_second": 0.755,
     "eval_steps_per_second": 0.024,
-    "predict_gen_len": 102.5544922913344,
-    "predict_loss": 0.5238111019134521,
-    "predict_rouge1": 72.4368,
-    "predict_rouge2": 65.4622,
-    "predict_rougeL": 69.4545,
-    "predict_rougeLsum": 71.556,
-    "predict_runtime": 4955.5742,
+    "predict_gen_len": 102.38011695906432,
+    "predict_loss": 0.5111322999000549,
+    "predict_rouge1": 72.6295,
+    "predict_rouge2": 65.6923,
+    "predict_rougeL": 69.5969,
+    "predict_rougeLsum": 71.7822,
+    "predict_runtime": 4951.9631,
     "predict_samples": 3762,
-    "predict_samples_per_second": 0.759,
+    "predict_samples_per_second": 0.76,
     "predict_steps_per_second": 0.024,
-    "total_flos": 4.90238608932864e+16,
-    "train_loss": 0.6246773758276696,
-    "train_runtime": 4840.7009,
+    "total_flos": 4.921767498350592e+16,
+    "train_loss": 0.5898041729435258,
+    "train_runtime": 4899.3175,
     "train_samples": 14262,
-    "train_samples_per_second": 14.731,
-    "train_steps_per_second": 0.921
+    "train_samples_per_second": 14.555,
+    "train_steps_per_second": 0.91
 }

eval_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 5.0,
-    "eval_gen_len": 103.516,
-    "eval_loss": 0.4996706545352936,
-    "eval_rouge1": 73.7275,
-    "eval_rouge2": 66.7471,
-    "eval_rougeL": 70.8087,
-    "eval_rougeLsum": 72.8058,
-    "eval_runtime": 986.8474,
+    "eval_gen_len": 102.92133333333334,
+    "eval_loss": 0.4875640571117401,
+    "eval_rouge1": 73.5772,
+    "eval_rouge2": 66.7059,
+    "eval_rougeL": 70.6615,
+    "eval_rougeLsum": 72.7397,
+    "eval_runtime": 993.2105,
     "eval_samples": 750,
-    "eval_samples_per_second": 0.76,
+    "eval_samples_per_second": 0.755,
     "eval_steps_per_second": 0.024
 }

predict_results.json

@@ -1,12 +1,12 @@
 {
-    "predict_gen_len": 102.5544922913344,
-    "predict_loss": 0.5238111019134521,
-    "predict_rouge1": 72.4368,
-    "predict_rouge2": 65.4622,
-    "predict_rougeL": 69.4545,
-    "predict_rougeLsum": 71.556,
-    "predict_runtime": 4955.5742,
+    "predict_gen_len": 102.38011695906432,
+    "predict_loss": 0.5111322999000549,
+    "predict_rouge1": 72.6295,
+    "predict_rouge2": 65.6923,
+    "predict_rougeL": 69.5969,
+    "predict_rougeLsum": 71.7822,
+    "predict_runtime": 4951.9631,
     "predict_samples": 3762,
-    "predict_samples_per_second": 0.759,
+    "predict_samples_per_second": 0.76,
     "predict_steps_per_second": 0.024
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 5.0,
-    "total_flos": 4.90238608932864e+16,
-    "train_loss": 0.6246773758276696,
-    "train_runtime": 4840.7009,
+    "total_flos": 4.921767498350592e+16,
+    "train_loss": 0.5898041729435258,
+    "train_runtime": 4899.3175,
     "train_samples": 14262,
-    "train_samples_per_second": 14.731,
-    "train_steps_per_second": 0.921
+    "train_samples_per_second": 14.555,
+    "train_steps_per_second": 0.91
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 73.3085,
+  "best_metric": 73.194,
   "best_model_checkpoint": "bin/indosum-lora-0/checkpoint-4460",
   "epoch": 5.0,
   "eval_steps": 500,
@@ -10,112 +10,112 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.5802992582321167,
+      "grad_norm": 0.6674928665161133,
       "learning_rate": 0.0008,
-      "loss": 0.8234,
+      "loss": 0.7749,
       "step": 892
     },
     {
       "epoch": 1.0,
-      "eval_gen_len": 100.72533333333334,
-      "eval_loss": 0.5383104681968689,
-      "eval_rouge1": 70.3236,
-      "eval_rouge2": 62.968,
-      "eval_rougeL": 67.3562,
-      "eval_rougeLsum": 69.3577,
-      "eval_runtime": 218.3908,
-      "eval_samples_per_second": 3.434,
-      "eval_steps_per_second": 0.11,
+      "eval_gen_len": 103.084,
+      "eval_loss": 0.5290482640266418,
+      "eval_rouge1": 71.3679,
+      "eval_rouge2": 64.0441,
+      "eval_rougeL": 68.2584,
+      "eval_rougeLsum": 70.462,
+      "eval_runtime": 221.5809,
+      "eval_samples_per_second": 3.385,
+      "eval_steps_per_second": 0.108,
       "step": 892
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.8689345717430115,
+      "grad_norm": 0.8049286603927612,
       "learning_rate": 0.0006,
-      "loss": 0.6236,
+      "loss": 0.5963,
       "step": 1784
     },
     {
       "epoch": 2.0,
-      "eval_gen_len": 106.88,
-      "eval_loss": 0.5276467800140381,
-      "eval_rouge1": 70.7232,
-      "eval_rouge2": 63.3489,
-      "eval_rougeL": 67.5777,
-      "eval_rougeLsum": 69.7735,
-      "eval_runtime": 220.8428,
-      "eval_samples_per_second": 3.396,
-      "eval_steps_per_second": 0.109,
+      "eval_gen_len": 105.98266666666666,
+      "eval_loss": 0.5043113827705383,
+      "eval_rouge1": 71.9204,
+      "eval_rouge2": 64.8766,
+      "eval_rougeL": 68.9265,
+      "eval_rougeLsum": 71.053,
+      "eval_runtime": 223.3788,
+      "eval_samples_per_second": 3.358,
+      "eval_steps_per_second": 0.107,
       "step": 1784
     },
     {
       "epoch": 3.0,
-      "grad_norm": 0.7641115784645081,
+      "grad_norm": 0.7607690691947937,
       "learning_rate": 0.0004,
-      "loss": 0.5819,
+      "loss": 0.5524,
       "step": 2676
     },
     {
       "epoch": 3.0,
-      "eval_gen_len": 103.876,
-      "eval_loss": 0.501513659954071,
-      "eval_rouge1": 72.5246,
-      "eval_rouge2": 65.3573,
-      "eval_rougeL": 69.5275,
-      "eval_rougeLsum": 71.631,
-      "eval_runtime": 219.8404,
-      "eval_samples_per_second": 3.412,
-      "eval_steps_per_second": 0.109,
+      "eval_gen_len": 103.22266666666667,
+      "eval_loss": 0.4928290545940399,
+      "eval_rouge1": 72.0196,
+      "eval_rouge2": 65.0022,
+      "eval_rougeL": 69.1173,
+      "eval_rougeLsum": 71.1808,
+      "eval_runtime": 222.1187,
+      "eval_samples_per_second": 3.377,
+      "eval_steps_per_second": 0.108,
       "step": 2676
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.5158720016479492,
+      "grad_norm": 0.6080348491668701,
       "learning_rate": 0.0002,
-      "loss": 0.5563,
+      "loss": 0.5236,
       "step": 3568
     },
     {
       "epoch": 4.0,
-      "eval_gen_len": 104.65333333333334,
-      "eval_loss": 0.5031823515892029,
-      "eval_rouge1": 72.7472,
-      "eval_rouge2": 65.6552,
-      "eval_rougeL": 69.7436,
-      "eval_rougeLsum": 71.8704,
-      "eval_runtime": 218.7145,
-      "eval_samples_per_second": 3.429,
-      "eval_steps_per_second": 0.11,
+      "eval_gen_len": 105.364,
+      "eval_loss": 0.494816392660141,
+      "eval_rouge1": 72.454,
+      "eval_rouge2": 65.5465,
+      "eval_rougeL": 69.6508,
+      "eval_rougeLsum": 71.6454,
+      "eval_runtime": 224.5973,
+      "eval_samples_per_second": 3.339,
+      "eval_steps_per_second": 0.107,
       "step": 3568
     },
     {
       "epoch": 5.0,
-      "grad_norm": 0.7064367532730103,
+      "grad_norm": 0.6512352824211121,
       "learning_rate": 0.0,
-      "loss": 0.5381,
+      "loss": 0.5017,
       "step": 4460
     },
     {
       "epoch": 5.0,
-      "eval_gen_len": 103.344,
-      "eval_loss": 0.4996706545352936,
-      "eval_rouge1": 73.3085,
-      "eval_rouge2": 66.3297,
-      "eval_rougeL": 70.3711,
-      "eval_rougeLsum": 72.4621,
-      "eval_runtime": 218.4594,
-      "eval_samples_per_second": 3.433,
-      "eval_steps_per_second": 0.11,
+      "eval_gen_len": 102.86,
+      "eval_loss": 0.4875640571117401,
+      "eval_rouge1": 73.194,
+      "eval_rouge2": 66.308,
+      "eval_rougeL": 70.335,
+      "eval_rougeLsum": 72.3629,
+      "eval_runtime": 226.5596,
+      "eval_samples_per_second": 3.31,
+      "eval_steps_per_second": 0.106,
       "step": 4460
     },
     {
       "epoch": 5.0,
       "step": 4460,
-      "total_flos": 4.90238608932864e+16,
-      "train_loss": 0.6246773758276696,
-      "train_runtime": 4840.7009,
-      "train_samples_per_second": 14.731,
-      "train_steps_per_second": 0.921
+      "total_flos": 4.921767498350592e+16,
+      "train_loss": 0.5898041729435258,
+      "train_runtime": 4899.3175,
+      "train_samples_per_second": 14.555,
+      "train_steps_per_second": 0.91
     }
   ],
   "logging_steps": 500,
@@ -123,7 +123,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 4.90238608932864e+16,
+  "total_flos": 4.921767498350592e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null