End of training

README.md

@@ -3,9 +3,23 @@ license: apache-2.0
 base_model: google/mt5-small
 tags:
 - generated_from_trainer
+datasets:
+- cwchang/tw_address_medium
+metrics:
+- rouge
 model-index:
 - name: formatted_addr
-  results: []
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: cwchang/tw_address_medium
+      type: cwchang/tw_address_medium
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 99.0667
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +27,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # formatted_addr
 
-This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the cwchang/tw_address_medium dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1763
+- Rouge1: 99.0667
+- Rouge2: 39.6667
+- Rougel: 99.1333
+- Rougelsum: 99.1333
+- Gen Len: 13.375
 
 ## Model description
 

all_results.json

@@ -1,8 +1,18 @@
 {
     "epoch": 3.0,
-    "train_loss": 6.107138163248698,
-    "train_runtime": 143.5946,
-    "train_samples": 800,
-    "train_samples_per_second": 16.714,
-    "train_steps_per_second": 4.178
+    "eval_gen_len": 13.375,
+    "eval_loss": 0.17634712159633636,
+    "eval_rouge1": 99.0667,
+    "eval_rouge2": 39.6667,
+    "eval_rougeL": 99.1333,
+    "eval_rougeLsum": 99.1333,
+    "eval_runtime": 16.2949,
+    "eval_samples": 200,
+    "eval_samples_per_second": 12.274,
+    "eval_steps_per_second": 3.068,
+    "train_loss": 2.2646766764322916,
+    "train_runtime": 282.894,
+    "train_samples": 2000,
+    "train_samples_per_second": 21.209,
+    "train_steps_per_second": 5.302
 }

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 13.375,
+    "eval_loss": 0.17634712159633636,
+    "eval_rouge1": 99.0667,
+    "eval_rouge2": 39.6667,
+    "eval_rougeL": 99.1333,
+    "eval_rougeLsum": 99.1333,
+    "eval_runtime": 16.2949,
+    "eval_samples": 200,
+    "eval_samples_per_second": 12.274,
+    "eval_steps_per_second": 3.068
+}

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

runs/Dec12_06-16-38_e168a4df8b39/events.out.tfevents.1702362181.e168a4df8b39.5272.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3142bbb691760bd6cc67b1a818bc6ee0ac726de8387d4486ccd2ab8f9dd1f2e
+size 613

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 6.107138163248698,
-    "train_runtime": 143.5946,
-    "train_samples": 800,
-    "train_samples_per_second": 16.714,
-    "train_steps_per_second": 4.178
+    "train_loss": 2.2646766764322916,
+    "train_runtime": 282.894,
+    "train_samples": 2000,
+    "train_samples_per_second": 21.209,
+    "train_steps_per_second": 5.302
 }

trainer_state.json

@@ -3,33 +3,45 @@
   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 600,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 2.5,
-      "learning_rate": 8.333333333333334e-06,
-      "loss": 6.9234,
+      "epoch": 1.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 5.4127,
       "step": 500
     },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.8232,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.5581,
+      "step": 1500
+    },
     {
       "epoch": 3.0,
-      "step": 600,
-      "total_flos": 52647771955200.0,
-      "train_loss": 6.107138163248698,
-      "train_runtime": 143.5946,
-      "train_samples_per_second": 16.714,
-      "train_steps_per_second": 4.178
+      "step": 1500,
+      "total_flos": 143865355345920.0,
+      "train_loss": 2.2646766764322916,
+      "train_runtime": 282.894,
+      "train_samples_per_second": 21.209,
+      "train_steps_per_second": 5.302
     }
   ],
   "logging_steps": 500,
-  "max_steps": 600,
+  "max_steps": 1500,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
-  "save_steps": 500,
-  "total_flos": 52647771955200.0,
+  "save_steps": 5000,
+  "total_flos": 143865355345920.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null