End of training

README.md

@@ -18,12 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 2.4819
-- Rouge1: 0.1435
-- Rouge2: 0.0508
-- Rougel: 0.1179
-- Rougelsum: 0.1179
-- Gen Len: 19.0
+- Loss: 2.5385
+- Rouge1: 0.141
+- Rouge2: 0.0479
+- Rougel: 0.1172
+- Rougelsum: 0.1172
+- Gen Len: 20.0
 
 ## Model description
 
@@ -49,21 +49,20 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 4
-- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 62   | 2.7787          | 0.125  | 0.0331 | 0.1038 | 0.1038    | 19.0    |
-| No log        | 2.0   | 124  | 2.5635          | 0.1388 | 0.0491 | 0.1151 | 0.115     | 19.0    |
-| No log        | 3.0   | 186  | 2.4988          | 0.1432 | 0.0501 | 0.1167 | 0.1168    | 19.0    |
-| No log        | 4.0   | 248  | 2.4819          | 0.1435 | 0.0508 | 0.1179 | 0.1179    | 19.0    |
+| No log        | 1.0   | 62   | 2.8323          | 0.1328 | 0.0383 | 0.1112 | 0.111     | 20.0    |
+| No log        | 2.0   | 124  | 2.6200          | 0.1408 | 0.0475 | 0.117  | 0.117     | 20.0    |
+| No log        | 3.0   | 186  | 2.5557          | 0.1406 | 0.0472 | 0.1161 | 0.1161    | 20.0    |
+| No log        | 4.0   | 248  | 2.5385          | 0.141  | 0.0479 | 0.1172 | 0.1172    | 20.0    |
 
 
 ### Framework versions
 
-- Transformers 4.46.2
-- Pytorch 2.5.1+cu124
+- Transformers 4.47.0
+- Pytorch 2.5.1
 - Datasets 3.1.0
-- Tokenizers 0.20.1
+- Tokenizers 0.21.0

config.json

@@ -55,7 +55,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.46.2",
+  "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.46.2"
+  "transformers_version": "4.47.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:323a3087e95bec2b817f261652dd376189a0736e2fd6980fa2c71daf9d99956d
+oid sha256:ab27ec6f806c818da0dc913f1f5df82dd65ce62705040dd2564554b4a43de2d0
 size 242041896

runs/Dec09_14-44-37_bogon/events.out.tfevents.1733726678.bogon.89513.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeeffdbe583643a2f210bf2961490c143fe8acc08b8ba269a4e1e32ebc69782e
+size 8496

tokenizer_config.json

@@ -930,6 +930,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
+  "extra_special_tokens": {},
   "model_max_length": 512,
   "pad_token": "<pad>",
   "tokenizer_class": "T5Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9af873a04eea9088dffdb6431163dc98b0bb8e76c77c91e075212cfa6a14cb7
-size 5432
+oid sha256:dd222a68140c324f706901732cb544e673b7ecf7a0e64dacf7f686d54b20b7d0
+size 5496