Training in progress, step 500

README.md

@@ -3,26 +3,11 @@ license: apache-2.0
 base_model: t5-small
 tags:
 - generated_from_trainer
-datasets:
-- opus_books
 metrics:
 - bleu
 model-index:
 - name: my_awesome_opus_books_model
-  results:
-  - task:
-      name: Sequence-to-sequence Language Modeling
-      type: text2text-generation
-    dataset:
-      name: opus_books
-      type: opus_books
-      config: en-es
-      split: train
-      args: en-es
-    metrics:
-    - name: Bleu
-      type: bleu
-      value: 0.8718
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my_awesome_opus_books_model
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus_books dataset.
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1549
-- Bleu: 0.8718
-- Gen Len: 18.1062
+- Loss: 2.2384
+- Bleu: 0.4736
+- Gen Len: 18.0826
 
 ## Model description
 
@@ -59,26 +44,23 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 8
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
-| 2.9712        | 1.0   | 4674  | 2.6344          | 0.3403 | 18.2053 |
-| 2.7554        | 2.0   | 9348  | 2.4373          | 0.4973 | 18.1724 |
-| 2.6295        | 3.0   | 14022 | 2.3271          | 0.638  | 18.1463 |
-| 2.5452        | 4.0   | 18696 | 2.2553          | 0.7342 | 18.1319 |
-| 2.4968        | 5.0   | 23370 | 2.2089          | 0.7964 | 18.1238 |
-| 2.4531        | 6.0   | 28044 | 2.1771          | 0.8458 | 18.1048 |
-| 2.4441        | 7.0   | 32718 | 2.1605          | 0.8637 | 18.1065 |
-| 2.42          | 8.0   | 37392 | 2.1549          | 0.8718 | 18.1062 |
+| 2.9148        | 1.0   | 4674  | 2.5719          | 0.2155 | 18.2619 |
+| 2.7067        | 2.0   | 9348  | 2.3872          | 0.3419 | 18.1173 |
+| 2.5969        | 3.0   | 14022 | 2.2973          | 0.4065 | 18.101  |
+| 2.5413        | 4.0   | 18696 | 2.2518          | 0.4603 | 18.0815 |
+| 2.5223        | 5.0   | 23370 | 2.2384          | 0.4736 | 18.0826 |
 
 
 ### Framework versions
 
-- Transformers 4.36.2
-- Pytorch 2.1.2
+- Transformers 4.35.2
+- Pytorch 2.1.1
 - Datasets 2.15.0
 - Tokenizers 0.15.0

config.json

@@ -55,7 +55,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.35.2",
   "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": "4.36.2"
+  "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd3620aea053651e236661a9f9c1bdc02f4c394f3eb5ba7130c2102225680c0
+oid sha256:7eb546d53b4cd5a535bc16e1dda74f157bd93aabed8ecf85f7d1cff5d2c7b738
 size 242041896

runs/Dec21_08-03-30_WJHF67-129/events.out.tfevents.1703117012.WJHF67-129.3916.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:987cd951e5331032b8bd279acb7442f07d64f2e1a3ff540771d34229202208b4
+size 5380

special_tokens_map.json

@@ -101,25 +101,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "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
-  }
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4186122426cd9077379a3ee8074cf02939f121a2230cd91887ce80ec7bfbfd1d
-size 4856
+oid sha256:9b28647bbad4adf2887f44fd5a88c9c012cc315473350a058131fe0e1bbc7c06
+size 4728