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_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. -->
+
+# mt5_deed_sum_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: 0.5951
+- Rouge1: 0.0572
+- Rouge2: 0.0
+- Rougel: 0.0572
+- Rougelsum: 0.0572
+- 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: 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 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 24.1526       | 1.0   | 375  | 15.7524         | 0.7082 | 0.0    | 0.6842 | 0.6883    | 12.0881 |
+| 11.2879       | 2.0   | 750  | 13.1581         | 0.7082 | 0.0    | 0.6842 | 0.6883    | 12.3208 |
+| 10.5585       | 3.0   | 1125 | 7.4334          | 0.7082 | 0.0    | 0.6842 | 0.6883    | 17.1384 |
+| 2.9668        | 4.0   | 1500 | 6.5357          | 0.7487 | 0.0    | 0.7176 | 0.7257    | 19.0    |
+| 3.7198        | 5.0   | 1875 | 2.1303          | 0.7487 | 0.0    | 0.7176 | 0.7257    | 19.0    |
+| 1.3383        | 6.0   | 2250 | 1.8675          | 0.7487 | 0.0    | 0.7176 | 0.7257    | 19.0    |
+| 3.4973        | 7.0   | 2625 | 1.6299          | 0.7487 | 0.0    | 0.7176 | 0.7257    | 18.8994 |
+| 11.7006       | 8.0   | 3000 | 4.6990          | 0.7487 | 0.0    | 0.7176 | 0.7257    | 19.0    |
+| 0.4529        | 9.0   | 3375 | 1.0729          | 0.7487 | 0.0    | 0.7176 | 0.7257    | 19.0    |
+| 1.2783        | 10.0  | 3750 | 0.9424          | 0.7487 | 0.0    | 0.7176 | 0.7257    | 19.0    |
+| 0.7953        | 11.0  | 4125 | 0.8889          | 1.0108 | 0.2013 | 0.892  | 0.9014    | 19.0    |
+| 0.9359        | 12.0  | 4500 | 0.7996          | 1.1489 | 0.3019 | 0.9952 | 0.9877    | 19.0    |
+| 0.5759        | 13.0  | 4875 | 0.7622          | 0.1572 | 0.1144 | 0.1572 | 0.1572    | 19.0    |
+| 0.1533        | 14.0  | 5250 | 0.7068          | 0.2144 | 0.1144 | 0.1715 | 0.1715    | 19.0    |
+| 0.4524        | 15.0  | 5625 | 0.6760          | 0.3145 | 0.2287 | 0.3145 | 0.3145    | 19.0    |
+| 1.0126        | 16.0  | 6000 | 0.6627          | 0.0    | 0.0    | 0.0    | 0.0       | 19.0    |
+| 0.1065        | 17.0  | 6375 | 0.6391          | 0.3145 | 0.2287 | 0.3145 | 0.3145    | 19.0    |
+| 0.2096        | 18.0  | 6750 | 0.6419          | 0.2144 | 0.1144 | 0.2144 | 0.2144    | 19.0    |
+| 0.5649        | 19.0  | 7125 | 0.6261          | 0.1572 | 0.1144 | 0.1572 | 0.1572    | 19.0    |
+| 0.125         | 20.0  | 7500 | 0.6139          | 0.1572 | 0.1144 | 0.1572 | 0.1572    | 19.0    |
+| 0.5511        | 21.0  | 7875 | 0.6057          | 0.3145 | 0.2287 | 0.3145 | 0.3145    | 19.0    |
+| 0.0759        | 22.0  | 8250 | 0.6029          | 0.3145 | 0.2287 | 0.3145 | 0.3145    | 19.0    |
+| 0.3491        | 23.0  | 8625 | 0.5995          | 0.3145 | 0.2287 | 0.3145 | 0.3145    | 19.0    |
+| 0.3735        | 24.0  | 9000 | 0.5936          | 0.1572 | 0.1144 | 0.1572 | 0.1572    | 19.0    |
+| 0.3451        | 25.0  | 9375 | 0.5951          | 0.0572 | 0.0    | 0.0572 | 0.0572    | 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 sha256:22efc3db7c3cfb263afa06c0b7650aa0950e96b87e9a25d1b4b8add9c0a9ea3e
+size 2329638768

runs/Feb28_19-04-28_WIN-F8FVB99PGRI/events.out.tfevents.1709175886.WIN-F8FVB99PGRI.11136.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:170271793ad135a94cea05799db65aeb6b2808725273f6c9b6beb7ad71398450
+size 1489643

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:b5918f100395a1a0b3cb2cdbe13e6d49293a7228cbecd2fb8f7ccc1ce3f34207
+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:afcd8d090bce9034eb64e79fa3142d371dac5eede187eafd390e7f3315b21fc3
+size 4856