Training in progress, step 500

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "google-t5/t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
@@ -10,6 +9,7 @@
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
+  "dtype": "float32",
   "eos_token_id": 1,
   "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
@@ -29,7 +29,7 @@
     "summarization": {
       "early_stopping": true,
       "length_penalty": 2.0,
-      "max_length": 300,
+      "max_length": 200,
       "min_length": 30,
       "no_repeat_ngram_size": 3,
       "num_beams": 4,
@@ -54,8 +54,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "torch_dtype": "float32",
-  "transformers_version": "4.48.3",
+  "transformers_version": "4.57.1",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -1,6 +1,9 @@
 {
+  "_from_model_config": true,
   "decoder_start_token_id": 0,
-  "eos_token_id": 1,
+  "eos_token_id": [
+    1
+  ],
   "pad_token_id": 0,
-  "transformers_version": "4.48.3"
+  "transformers_version": "4.57.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a254735985e7afa51e5d2db00697731ef400ec8627c5f479cc02094365e215a9
+oid sha256:9494edf26bac0c76ff814cf3e3e44495497f04df027074f8cd6e9ff4aaebe534
 size 242041896

runs/Nov18_16-57-19_dd086913b758/events.out.tfevents.1763485194.dd086913b758.631.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd22ab96f4bf01b85386f5572de0617c1c53e1ae7f19ffe4c45242539112df0
+size 6345

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4c16e403ae7b8f8346a70978da69b81c3734c4c64a33cb2de2b9bdc847e5f2
-size 5624
+oid sha256:ec74ee33007a4fc0d401e9662ed9697395fd22d7eeb816d59ed002ee4fd28ffa
+size 6097