End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google-t5/t5-large
+base_model: t5-base
 tags:
 - generated_from_trainer
 metrics:
@@ -15,13 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # olonok_billsum_model
 
-This model is a fine-tuned version of [google-t5/t5-large](https://huggingface.co/google-t5/t5-large) on an unknown dataset.
+This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
-- Rouge1: 0.1317
-- Rouge2: 0.049
-- Rougel: 0.1073
-- Rougelsum: 0.1075
+- Loss: 1.8641
+- Rouge1: 0.2024
+- Rouge2: 0.1156
+- Rougel: 0.177
+- Rougelsum: 0.177
 - Gen Len: 19.0
 
 ## Model description
@@ -41,29 +41,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 4
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- 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   | 248  | nan             | 0.1317 | 0.049  | 0.1073 | 0.1075    | 19.0    |
-| No log        | 2.0   | 496  | nan             | 0.1317 | 0.049  | 0.1073 | 0.1075    | 19.0    |
-| 0.0           | 3.0   | 744  | nan             | 0.1317 | 0.049  | 0.1073 | 0.1075    | 19.0    |
-| 0.0           | 4.0   | 992  | nan             | 0.1317 | 0.049  | 0.1073 | 0.1075    | 19.0    |
-| 0.0           | 5.0   | 1240 | nan             | 0.1317 | 0.049  | 0.1073 | 0.1075    | 19.0    |
-| 0.0           | 6.0   | 1488 | nan             | 0.1317 | 0.049  | 0.1073 | 0.1075    | 19.0    |
-| 0.0           | 7.0   | 1736 | nan             | 0.1317 | 0.049  | 0.1073 | 0.1075    | 19.0    |
-| 0.0           | 8.0   | 1984 | nan             | 0.1317 | 0.049  | 0.1073 | 0.1075    | 19.0    |
-| 0.0           | 9.0   | 2232 | nan             | 0.1317 | 0.049  | 0.1073 | 0.1075    | 19.0    |
-| 0.0           | 10.0  | 2480 | nan             | 0.1317 | 0.049  | 0.1073 | 0.1075    | 19.0    |
+| No log        | 1.0   | 62   | 2.0236          | 0.1683 | 0.0807 | 0.1445 | 0.1449    | 19.0    |
+| No log        | 2.0   | 124  | 1.9080          | 0.2041 | 0.1158 | 0.1778 | 0.1779    | 19.0    |
+| No log        | 3.0   | 186  | 1.8728          | 0.2024 | 0.1165 | 0.1778 | 0.1776    | 19.0    |
+| No log        | 4.0   | 248  | 1.8641          | 0.2024 | 0.1156 | 0.177  | 0.177     | 19.0    |
 
 
 ### Framework versions

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308e6503652e293f0746f3257c9b3bcdcbf2c31b06cfa7781d33a79c39fe1714
+size 891644712

runs/Feb20_20-20-18_314b927582c5/events.out.tfevents.1708460419.314b927582c5.3177.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8f85643499cc5df8023320c4da3b19fb3673a8eac460c63ce5386f70c22df7
+size 7653

tokenizer_config.json

@@ -930,7 +930,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 1024,
   "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 sha256:13dbb9926a30dfad6ba95eb7e1c7078b53f06e86e1912bd92828a8166eb06f29
+oid sha256:1a08f050456a751e92b91c29608ef81d0f86356fac277ab7cff3c986bbac5dfa
 size 4728