End of training

README.md

@@ -3,11 +3,23 @@ license: apache-2.0
 base_model: google-t5/t5-small
 tags:
 - generated_from_trainer
+datasets:
+- lilferrit/xsum_t5_distillation
 metrics:
 - rouge
 model-index:
 - name: xsum_aligned_smallT5_full
-  results: []
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: lilferrit/xsum_t5_distillation
+      type: lilferrit/xsum_t5_distillation
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 22.8498
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +27,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # xsum_aligned_smallT5_full
 
-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 lilferrit/xsum_t5_distillation dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.4093
 - Rouge1: 22.8498

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 0.0,
+    "eval_gen_len": 33.63662046437715,
+    "eval_loss": 2.4093151092529297,
+    "eval_rouge1": 22.8498,
+    "eval_rouge2": 4.7818,
+    "eval_rougeL": 17.2861,
+    "eval_rougeLsum": 18.0665,
+    "eval_runtime": 846.5353,
+    "eval_samples": 11327,
+    "eval_samples_per_second": 13.38,
+    "eval_steps_per_second": 1.673,
+    "train_loss": 3.090506744384766,
+    "train_runtime": 1864.227,
+    "train_samples": 204017,
+    "train_samples_per_second": 0.086,
+    "train_steps_per_second": 0.005
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.0,
+    "eval_gen_len": 33.63662046437715,
+    "eval_loss": 2.4093151092529297,
+    "eval_rouge1": 22.8498,
+    "eval_rouge2": 4.7818,
+    "eval_rougeL": 17.2861,
+    "eval_rougeLsum": 18.0665,
+    "eval_runtime": 846.5353,
+    "eval_samples": 11327,
+    "eval_samples_per_second": 13.38,
+    "eval_steps_per_second": 1.673
+}

runs/Apr28_12-43-27_nlpg00.cs.washington.edu/events.out.tfevents.1714336454.nlpg00.cs.washington.edu.783855.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ceb5233677f757e67e99505ca6c0b15f6b89f1f2338c0dc55038dad061e1a7b
+size 603

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "train_loss": 3.090506744384766,
+    "train_runtime": 1864.227,
+    "train_samples": 204017,
+    "train_samples_per_second": 0.086,
+    "train_steps_per_second": 0.005
+}

trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 17.2861,
+  "best_model_checkpoint": "./out/finetuned_models/xsum_aligned_smallT5_full/checkpoint-10",
+  "epoch": 0.0007842214641414735,
+  "eval_steps": 5,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "eval_gen_len": 46.2436655778229,
+      "eval_loss": 2.6444404125213623,
+      "eval_rouge1": 22.3341,
+      "eval_rouge2": 4.3395,
+      "eval_rougeL": 16.2507,
+      "eval_rougeLsum": 17.8303,
+      "eval_runtime": 1003.3723,
+      "eval_samples_per_second": 11.289,
+      "eval_steps_per_second": 1.411,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "eval_gen_len": 33.63662046437715,
+      "eval_loss": 2.4093151092529297,
+      "eval_rouge1": 22.8498,
+      "eval_rouge2": 4.7818,
+      "eval_rougeL": 17.2861,
+      "eval_rougeLsum": 18.0665,
+      "eval_runtime": 845.1794,
+      "eval_samples_per_second": 13.402,
+      "eval_steps_per_second": 1.675,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "step": 10,
+      "total_flos": 41941155446784.0,
+      "train_loss": 3.090506744384766,
+      "train_runtime": 1864.227,
+      "train_samples_per_second": 0.086,
+      "train_steps_per_second": 0.005
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 10,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "total_flos": 41941155446784.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}