End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: t5-base
+base_model: t5-small
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tmp_test
 
-This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
 
 ## Model description
 
@@ -49,5 +49,4 @@ The following hyperparameters were used during training:
 
 - Transformers 4.48.3
 - Pytorch 2.5.1+cu124
-- Datasets 3.3.2
 - Tokenizers 0.21.0

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-base",
+  "_name_or_path": "t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 3072,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 512,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6c61ba918d54f6e8236dd1d3959f028639a08df803ed8cfe096fe1e161f5b67
-size 891644712
+oid sha256:4aecf7e71fec15552e380056131e48a2039358338af772afdd796764d96406c1
+size 242041896

runs/Mar03_20-40-57_a9d196f7c806/events.out.tfevents.1741034464.a9d196f7c806.421.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfc0f64810f5d925de2feabafa86529fce3f5e5986d21250991bb7a7c20c6a7
+size 6361

special_tokens_map.json

@@ -101,7 +101,25 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -928,11 +928,11 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "pad_token": "<pad>",
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf672a9f77b2d035bec7412af2fa989a56b759cf903b61d32921a9ffb402039
+oid sha256:de1ac5595ddbea0fb26bf8d39bb6441926485be18f1121b28351e0e753106017
 size 5432