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: mt5_deed_sum
+  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. -->
+
+# mt5_deed_sum
+
+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: 0.5590
+- Rouge1: 0.0
+- Rouge2: 0.0
+- Rougel: 0.0
+- Rougelsum: 0.0
+- Gen Len: 19.0
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 19.6644       | 1.0   | 188  | 13.7553         | 0.7175 | 0.0    | 0.7387 | 0.7032    | 12.283  |
+| 10.6133       | 2.0   | 376  | 11.3168         | 0.7175 | 0.0    | 0.7387 | 0.7032    | 13.4654 |
+| 10.1742       | 3.0   | 564  | 7.7772          | 0.7175 | 0.0    | 0.7387 | 0.7032    | 15.9874 |
+| 2.8326        | 4.0   | 752  | 4.6011          | 0.7498 | 0.0    | 0.7731 | 0.7387    | 19.0    |
+| 4.2099        | 5.0   | 940  | 5.8284          | 0.7498 | 0.0    | 0.7731 | 0.7387    | 15.8805 |
+| 1.7867        | 6.0   | 1128 | 2.0588          | 0.7498 | 0.0    | 0.7731 | 0.7387    | 15.761  |
+| 3.6568        | 7.0   | 1316 | 1.7242          | 0.7498 | 0.0    | 0.7731 | 0.7387    | 12.9371 |
+| 4.1534        | 8.0   | 1504 | 1.4302          | 0.7498 | 0.0    | 0.7731 | 0.7387    | 15.1761 |
+| 0.9298        | 9.0   | 1692 | 1.3871          | 0.7498 | 0.0    | 0.7731 | 0.7387    | 14.3711 |
+| 1.5429        | 10.0  | 1880 | 1.1574          | 0.7498 | 0.0    | 0.7731 | 0.7387    | 18.4969 |
+| 1.1307        | 11.0  | 2068 | 1.0076          | 0.8804 | 0.1144 | 0.8573 | 0.8336    | 19.0    |
+| 0.9566        | 12.0  | 2256 | 0.9130          | 0.7498 | 0.0    | 0.7731 | 0.7387    | 19.0    |
+| 0.6761        | 13.0  | 2444 | 0.8454          | 0.8804 | 0.1144 | 0.8573 | 0.8336    | 19.0    |
+| 0.1983        | 14.0  | 2632 | 0.7835          | 0.0    | 0.0    | 0.0    | 0.0       | 19.0    |
+| 0.5771        | 15.0  | 2820 | 0.7411          | 0.0    | 0.0    | 0.0    | 0.0       | 19.0    |
+| 1.1574        | 16.0  | 3008 | 0.7099          | 0.3594 | 0.2648 | 0.3594 | 0.3594    | 19.0    |
+| 0.1504        | 17.0  | 3196 | 0.6689          | 0.0    | 0.0    | 0.0    | 0.0       | 19.0    |
+| 0.1265        | 18.0  | 3384 | 0.6576          | 0.3594 | 0.2648 | 0.3594 | 0.3594    | 19.0    |
+| 0.6688        | 19.0  | 3572 | 0.6355          | 0.3594 | 0.2648 | 0.3594 | 0.3594    | 19.0    |
+| 0.1103        | 20.0  | 3760 | 0.6101          | 0.5391 | 0.3972 | 0.5391 | 0.5391    | 19.0    |
+| 0.4472        | 21.0  | 3948 | 0.6018          | 0.0    | 0.0    | 0.0    | 0.0       | 19.0    |
+| 0.0696        | 22.0  | 4136 | 0.5804          | 0.2459 | 0.1324 | 0.2459 | 0.2223    | 19.0    |
+| 0.2857        | 23.0  | 4324 | 0.5685          | 0.0    | 0.0    | 0.0    | 0.0       | 19.0    |
+| 0.4744        | 24.0  | 4512 | 0.5475          | 0.2459 | 0.1324 | 0.2459 | 0.2223    | 19.0    |
+| 0.2841        | 25.0  | 4700 | 0.5590          | 0.0    | 0.0    | 0.0    | 0.0       | 19.0    |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0.dev20230811+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,33 @@
+{
+  "_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,
+  "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 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98da4a9b94072a624f9b4323fe34d0d9b3fc7a280ad6d18721e759b25caced59
+size 2329638768

runs/Feb27_05-17-59_WIN-F8FVB99PGRI/events.out.tfevents.1709039898.WIN-F8FVB99PGRI.8304.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3d580fbbb8ea764ce1128ed8a7165181e191b1c281cfe5cd70a83927e661ea
+size 755662

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:ede3830ad5fc8aa7fa2d611309b0f8aa2bc067c1c1522ea155ef65f3f89b49bc
+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 sha256:99719cf83aeaaeb70e3f76af67515ed0ab3fe2a33f8087d8f15ec1521034c825
+size 4856