End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,89 @@
+---
+license: apache-2.0
+base_model: google/mt5-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: deed_summarization_mt5_version_1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# deed_summarization_mt5_version_1
+
+This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5863
+- Rouge1: 1.0138
+- Rouge2: 0.6875
+- Rougel: 1.0233
+- Rougelsum: 1.0941
+- Gen Len: 288.1509
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5000
+- num_epochs: 25
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len  |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:--------:|
+| 25.5422       | 1.0   | 375  | 16.6467         | 0.6477 | 0.0    | 0.6383 | 0.6639    | 25.0     |
+| 11.9626       | 2.0   | 750  | 13.5214         | 0.6633 | 0.0    | 0.6553 | 0.6745    | 38.5912  |
+| 10.1002       | 3.0   | 1125 | 7.4294          | 0.7257 | 0.0    | 0.7163 | 0.7264    | 386.6164 |
+| 2.8844        | 4.0   | 1500 | 2.8574          | 0.7257 | 0.0    | 0.7163 | 0.7264    | 499.0    |
+| 4.1183        | 5.0   | 1875 | 9.6893          | 0.7257 | 0.0    | 0.7163 | 0.7264    | 499.0    |
+| 1.4443        | 6.0   | 2250 | 2.4224          | 0.7257 | 0.0    | 0.7163 | 0.7264    | 466.7673 |
+| 3.8512        | 7.0   | 2625 | 1.5813          | 0.7257 | 0.0    | 0.7163 | 0.7264    | 432.4717 |
+| 8.6527        | 8.0   | 3000 | 1.4532          | 0.7257 | 0.0    | 0.7163 | 0.7264    | 480.6164 |
+| 0.5302        | 9.0   | 3375 | 1.1597          | 0.7257 | 0.0    | 0.7163 | 0.7264    | 419.239  |
+| 1.2311        | 10.0  | 3750 | 0.9806          | 0.9895 | 0.1006 | 0.9135 | 0.9189    | 383.6855 |
+| 0.8903        | 11.0  | 4125 | 0.8961          | 0.9609 | 0.1578 | 0.8871 | 0.8934    | 376.6038 |
+| 0.8742        | 12.0  | 4500 | 0.8109          | 1.1104 | 0.2243 | 1.0038 | 1.007     | 388.3648 |
+| 0.5934        | 13.0  | 4875 | 0.7588          | 0.3145 | 0.2287 | 0.3145 | 0.3145    | 341.717  |
+| 0.1715        | 14.0  | 5250 | 0.7073          | 0.2795 | 0.2013 | 0.2795 | 0.2795    | 333.434  |
+| 0.4363        | 15.0  | 5625 | 0.6780          | 0.4368 | 0.2287 | 0.4368 | 0.4368    | 326.7044 |
+| 1.0736        | 16.0  | 6000 | 0.6647          | 0.7163 | 0.5169 | 0.7512 | 0.7512    | 299.4151 |
+| 0.1069        | 17.0  | 6375 | 0.6294          | 0.856  | 0.6038 | 0.863  | 0.8595    | 312.434  |
+| 0.1434        | 18.0  | 6750 | 0.6358          | 0.7512 | 0.5222 | 0.7862 | 0.808     | 291.4403 |
+| 0.4344        | 19.0  | 7125 | 0.6164          | 1.1082 | 0.7576 | 1.1305 | 1.1574    | 304.7484 |
+| 0.1038        | 20.0  | 7500 | 0.6066          | 0.8572 | 0.6108 | 0.8758 | 0.9085    | 297.3145 |
+| 0.5519        | 21.0  | 7875 | 0.5972          | 0.4354 | 0.2935 | 0.5382 | 0.5382    | 281.5786 |
+| 0.0804        | 22.0  | 8250 | 0.5994          | 0.6464 | 0.5583 | 0.7741 | 0.7794    | 305.805  |
+| 0.3696        | 23.0  | 8625 | 0.5884          | 0.6362 | 0.3246 | 0.6362 | 0.6362    | 291.434  |
+| 0.3966        | 24.0  | 9000 | 0.5852          | 0.7133 | 0.408  | 0.7311 | 0.8082    | 281.9119 |
+| 0.3484        | 25.0  | 9375 | 0.5863          | 1.0138 | 0.6875 | 1.0233 | 1.0941    | 288.1509 |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0.dev20230811+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "max_length": 500,
+  "model_type": "mt5",
+  "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,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "max_length": 500,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d64469afe7e273c69e7dac0049de913a30674a798435a34ce9db32975cd9b38
+size 2329638768

runs/Feb21_21-12-17_WIN-F8FVB99PGRI/events.out.tfevents.1708578743.WIN-F8FVB99PGRI.17568.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e56062b510fd276386369de2134130ca395480c075c098eb7e70ab0e6c85d9a
+size 1489718

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6512ef2b02777ef782756927e24139ce5b24fcfe947abf5cd8fb7a7b1a44f7f4
+size 16330827

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0881a2217d7897fe0c0714e209c8178ccbae1b85b6c2f322fba23c4c0dab3917
+size 4920