End of training

README.md

@@ -4,9 +4,24 @@ license: apache-2.0
 base_model: google-t5/t5-small
 tags:
 - generated_from_trainer
+datasets:
+- cnn_dailymail
+metrics:
+- rouge
 model-index:
 - name: finetuned-t5-cnn_dailymail
-  results: []
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: cnn_dailymail 3.0.0
+      type: cnn_dailymail
+      args: 3.0.0
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 34.6768
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +29,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # finetuned-t5-cnn_dailymail
 
-This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
+This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the cnn_dailymail 3.0.0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9668
+- Rouge1: 34.6768
+- Rouge2: 13.9858
+- Rougel: 24.7762
+- Rougelsum: 32.0487
+- Gen Len: 57.9425
 
 ## Model description
 

all_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 57.9425,
+    "eval_loss": 1.9668134450912476,
+    "eval_rouge1": 34.6768,
+    "eval_rouge2": 13.9858,
+    "eval_rougeL": 24.7762,
+    "eval_rougeLsum": 32.0487,
+    "eval_runtime": 298.1386,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 6.708,
+    "eval_steps_per_second": 0.839,
+    "total_flos": 1619815089045504.0,
+    "train_loss": 1.9870933024088542,
+    "train_runtime": 328.7104,
+    "train_samples": 2000,
+    "train_samples_per_second": 18.253,
+    "train_steps_per_second": 2.282
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 57.9425,
+    "eval_loss": 1.9668134450912476,
+    "eval_rouge1": 34.6768,
+    "eval_rouge2": 13.9858,
+    "eval_rougeL": 24.7762,
+    "eval_rougeLsum": 32.0487,
+    "eval_runtime": 298.1386,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 6.708,
+    "eval_steps_per_second": 0.839
+}

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/Sep19_08-53-52_4fa5516cabac/events.out.tfevents.1726736693.4fa5516cabac.40491.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd14176b3b96ee23f451d17287f9362f7ecb79c007ead5b2c25a65b8c558330
+size 613

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1619815089045504.0,
+    "train_loss": 1.9870933024088542,
+    "train_runtime": 328.7104,
+    "train_samples": 2000,
+    "train_samples_per_second": 18.253,
+    "train_steps_per_second": 2.282
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.001534938812256,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 2.0135,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 750,
+      "total_flos": 1619815089045504.0,
+      "train_loss": 1.9870933024088542,
+      "train_runtime": 328.7104,
+      "train_samples_per_second": 18.253,
+      "train_steps_per_second": 2.282
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1619815089045504.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}