End of training

README.md

@@ -3,9 +3,23 @@ license: mit
 base_model: facebook/bart-large-xsum
 tags:
 - generated_from_trainer
+datasets:
+- Andyrasika/TweetSumm-tuned
+metrics:
+- rouge
 model-index:
 - name: bart-large-xsum-tweetsum
-  results: []
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: Andyrasika/TweetSumm-tuned
+      type: Andyrasika/TweetSumm-tuned
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 46.1359
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -14,7 +28,14 @@ should probably proofread and complete it, then remove this comment. -->
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/samuel-lima-tech4humans/peft-tweetsum/runs/8kw429vm)
 # bart-large-xsum-tweetsum
 
-This model is a fine-tuned version of [facebook/bart-large-xsum](https://huggingface.co/facebook/bart-large-xsum) on an unknown dataset.
+This model is a fine-tuned version of [facebook/bart-large-xsum](https://huggingface.co/facebook/bart-large-xsum) on the Andyrasika/TweetSumm-tuned dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9921
+- Rouge1: 46.1359
+- Rouge2: 20.5196
+- Rougel: 38.6353
+- Rougelsum: 41.9642
+- Gen Len: 45.1
 
 ## Model description
 

all_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 45.1,
+    "eval_loss": 1.9920917749404907,
+    "eval_rouge1": 46.1359,
+    "eval_rouge2": 20.5196,
+    "eval_rougeL": 38.6353,
+    "eval_rougeLsum": 41.9642,
+    "eval_runtime": 32.1818,
+    "eval_samples": 110,
+    "eval_samples_per_second": 3.418,
+    "eval_steps_per_second": 0.87,
+    "total_flos": 1975694664867840.0,
+    "train_loss": 1.4291834513346353,
+    "train_runtime": 580.4464,
+    "train_samples": 879,
+    "train_samples_per_second": 4.543,
+    "train_steps_per_second": 1.137
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 45.1,
+    "eval_loss": 1.9920917749404907,
+    "eval_rouge1": 46.1359,
+    "eval_rouge2": 20.5196,
+    "eval_rougeL": 38.6353,
+    "eval_rougeLsum": 41.9642,
+    "eval_runtime": 32.1818,
+    "eval_samples": 110,
+    "eval_samples_per_second": 3.418,
+    "eval_steps_per_second": 0.87
+}

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
   "early_stopping": true,

runs/Aug27_18-03-09_4ce6981ec145/events.out.tfevents.1724782549.4ce6981ec145.1438.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245eeb97aac4281eb82d99b019d85b443ce02bbd86bb0965923908dc7273db99
+size 613

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1975694664867840.0,
+    "train_loss": 1.4291834513346353,
+    "train_runtime": 580.4464,
+    "train_samples": 879,
+    "train_samples_per_second": 4.543,
+    "train_steps_per_second": 1.137
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 660,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 8.485174179077148,
+      "learning_rate": 1.2121212121212122e-05,
+      "loss": 1.6089,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 660,
+      "total_flos": 1975694664867840.0,
+      "train_loss": 1.4291834513346353,
+      "train_runtime": 580.4464,
+      "train_samples_per_second": 4.543,
+      "train_steps_per_second": 1.137
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 660,
+  "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": 1975694664867840.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}