End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google-t5/t5-small
 tags:
 - generated_from_trainer
+metrics:
+- bleu
 model-index:
 - name: t5-big-scratch-iwslt3008
   results: []
@@ -14,6 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 # t5-big-scratch-iwslt3008
 
 This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3140
+- Bleu: 0.2623
+- Gen Len: 26.3604
 
 ## Model description
 

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 50.0,
+    "eval_bleu": 0.2623,
+    "eval_gen_len": 26.3604,
+    "eval_loss": 2.3139915466308594,
+    "eval_runtime": 10.8629,
+    "eval_samples": 888,
+    "eval_samples_per_second": 81.746,
+    "eval_steps_per_second": 1.289,
+    "predict_bleu": 0.2694,
+    "predict_gen_len": 21.9933,
+    "predict_loss": 2.3295047283172607,
+    "predict_runtime": 86.6486,
+    "predict_samples": 8079,
+    "predict_samples_per_second": 93.239,
+    "predict_steps_per_second": 1.466,
+    "total_flos": 9.94521893679661e+17,
+    "train_loss": 1.8893472661618176,
+    "train_runtime": 93675.3384,
+    "train_samples": 206112,
+    "train_samples_per_second": 110.014,
+    "train_steps_per_second": 3.438
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 50.0,
+    "eval_bleu": 0.2623,
+    "eval_gen_len": 26.3604,
+    "eval_loss": 2.3139915466308594,
+    "eval_runtime": 10.8629,
+    "eval_samples": 888,
+    "eval_samples_per_second": 81.746,
+    "eval_steps_per_second": 1.289
+}

generation_config.json

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

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 0.2694,
+    "predict_gen_len": 21.9933,
+    "predict_loss": 2.3295047283172607,
+    "predict_runtime": 86.6486,
+    "predict_samples": 8079,
+    "predict_samples_per_second": 93.239,
+    "predict_steps_per_second": 1.466
+}

runs/May25_13-37-31_0d573eeffc83/events.out.tfevents.1716737990.0d573eeffc83.1345596.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b217d1268ed9258889dc5b343ea4612b89400c4d4a0f9719827944f1bd7c6c
+size 465

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 50.0,
+    "total_flos": 9.94521893679661e+17,
+    "train_loss": 1.8893472661618176,
+    "train_runtime": 93675.3384,
+    "train_samples": 206112,
+    "train_samples_per_second": 110.014,
+    "train_steps_per_second": 3.438
+}