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: 0.7478
-- Rouge1: 72.0587
-- Rouge2: 64.7973
-- Rougel: 68.9279
-- Rougelsum: 71.3028
-- Gen Len: 99.3765
+- Rouge1: 72.3325
+- Rouge2: 65.1065
+- Rougel: 69.2256
+- Rougelsum: 71.5325
+- Gen Len: 99.4045
 
 ## Model description
 

all_results.json

@@ -0,0 +1,29 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 99.4045393858478,
+    "eval_loss": 0.7477750778198242,
+    "eval_rouge1": 72.3325,
+    "eval_rouge2": 65.1065,
+    "eval_rougeL": 69.2256,
+    "eval_rougeLsum": 71.5325,
+    "eval_runtime": 870.3123,
+    "eval_samples": 749,
+    "eval_samples_per_second": 0.861,
+    "eval_steps_per_second": 0.028,
+    "predict_gen_len": 98.35964912280701,
+    "predict_loss": 0.7349855899810791,
+    "predict_rouge1": 71.9235,
+    "predict_rouge2": 64.9283,
+    "predict_rougeL": 68.9356,
+    "predict_rougeLsum": 71.0817,
+    "predict_runtime": 4349.2967,
+    "predict_samples": 3762,
+    "predict_samples_per_second": 0.865,
+    "predict_steps_per_second": 0.027,
+    "total_flos": 4.883347058982912e+16,
+    "train_loss": 0.5788277185551254,
+    "train_runtime": 5011.2822,
+    "train_samples": 14263,
+    "train_samples_per_second": 14.231,
+    "train_steps_per_second": 0.89
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 99.4045393858478,
+    "eval_loss": 0.7477750778198242,
+    "eval_rouge1": 72.3325,
+    "eval_rouge2": 65.1065,
+    "eval_rougeL": 69.2256,
+    "eval_rougeLsum": 71.5325,
+    "eval_runtime": 870.3123,
+    "eval_samples": 749,
+    "eval_samples_per_second": 0.861,
+    "eval_steps_per_second": 0.028
+}

predict_results.json

@@ -0,0 +1,12 @@
+{
+    "predict_gen_len": 98.35964912280701,
+    "predict_loss": 0.7349855899810791,
+    "predict_rouge1": 71.9235,
+    "predict_rouge2": 64.9283,
+    "predict_rougeL": 68.9356,
+    "predict_rougeLsum": 71.0817,
+    "predict_runtime": 4349.2967,
+    "predict_samples": 3762,
+    "predict_samples_per_second": 0.865,
+    "predict_steps_per_second": 0.027
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 4.883347058982912e+16,
+    "train_loss": 0.5788277185551254,
+    "train_runtime": 5011.2822,
+    "train_samples": 14263,
+    "train_samples_per_second": 14.231,
+    "train_steps_per_second": 0.89
+}

trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 72.0587,
+  "best_model_checkpoint": "bin/indosum-base-1/checkpoint-4460",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 4460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9205507636070251,
+      "learning_rate": 0.0008,
+      "loss": 1.1904,
+      "step": 892
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 95.85981308411215,
+      "eval_loss": 0.8053300976753235,
+      "eval_rouge1": 65.8257,
+      "eval_rouge2": 57.6167,
+      "eval_rougeL": 62.6222,
+      "eval_rougeLsum": 65.0027,
+      "eval_runtime": 190.0984,
+      "eval_samples_per_second": 3.94,
+      "eval_steps_per_second": 0.126,
+      "step": 892
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9236537218093872,
+      "learning_rate": 0.0006,
+      "loss": 0.6851,
+      "step": 1784
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 96.29105473965286,
+      "eval_loss": 0.6778599619865417,
+      "eval_rouge1": 67.8889,
+      "eval_rouge2": 60.0878,
+      "eval_rougeL": 64.5868,
+      "eval_rougeLsum": 66.9914,
+      "eval_runtime": 191.4753,
+      "eval_samples_per_second": 3.912,
+      "eval_steps_per_second": 0.125,
+      "step": 1784
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7036951184272766,
+      "learning_rate": 0.0004,
+      "loss": 0.4856,
+      "step": 2676
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 96.92122830440587,
+      "eval_loss": 0.6460219621658325,
+      "eval_rouge1": 70.9241,
+      "eval_rouge2": 63.6363,
+      "eval_rougeL": 67.8555,
+      "eval_rougeLsum": 70.153,
+      "eval_runtime": 191.9289,
+      "eval_samples_per_second": 3.902,
+      "eval_steps_per_second": 0.125,
+      "step": 2676
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.5336605906486511,
+      "learning_rate": 0.0002,
+      "loss": 0.3358,
+      "step": 3568
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 101.87449933244326,
+      "eval_loss": 0.6564512848854065,
+      "eval_rouge1": 69.9002,
+      "eval_rouge2": 62.4,
+      "eval_rougeL": 66.5928,
+      "eval_rougeLsum": 69.0347,
+      "eval_runtime": 192.0018,
+      "eval_samples_per_second": 3.901,
+      "eval_steps_per_second": 0.125,
+      "step": 3568
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.46569395065307617,
+      "learning_rate": 0.0,
+      "loss": 0.1973,
+      "step": 4460
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 99.37650200267022,
+      "eval_loss": 0.7477750778198242,
+      "eval_rouge1": 72.0587,
+      "eval_rouge2": 64.7973,
+      "eval_rougeL": 68.9279,
+      "eval_rougeLsum": 71.3028,
+      "eval_runtime": 192.0514,
+      "eval_samples_per_second": 3.9,
+      "eval_steps_per_second": 0.125,
+      "step": 4460
+    },
+    {
+      "epoch": 5.0,
+      "step": 4460,
+      "total_flos": 4.883347058982912e+16,
+      "train_loss": 0.5788277185551254,
+      "train_runtime": 5011.2822,
+      "train_samples_per_second": 14.231,
+      "train_steps_per_second": 0.89
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 4.883347058982912e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}