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 +1,79 @@
+---
+license: apache-2.0
+base_model: google/mt5-small
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: mt5-small-sport
+  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-small-sport
+
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2444
+- Rouge1: 22.6291
+- Rouge2: 9.9519
+- Rougel: 18.0362
+- Rougelsum: 19.4768
+- 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 16
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 2.3085        | 1.0   | 2897  | 1.6680          | 21.9624 | 8.3028  | 16.8626 | 18.4892   | 19.0    |
+| 1.9601        | 2.0   | 5794  | 1.5129          | 22.355  | 8.0976  | 17.1001 | 18.4518   | 19.0    |
+| 1.8149        | 3.0   | 8691  | 1.4461          | 21.7553 | 8.2693  | 16.8813 | 18.1753   | 19.0    |
+| 1.6939        | 4.0   | 11588 | 1.3859          | 22.1485 | 8.5444  | 17.1957 | 18.5641   | 19.0    |
+| 1.6661        | 5.0   | 14485 | 1.3600          | 22.1464 | 8.5701  | 17.1911 | 18.5834   | 19.0    |
+| 1.5776        | 6.0   | 17382 | 1.3366          | 22.188  | 8.6102  | 17.2114 | 18.6171   | 19.0    |
+| 1.5635        | 7.0   | 20279 | 1.3036          | 22.2216 | 8.8053  | 17.3255 | 18.7127   | 19.0    |
+| 1.5286        | 8.0   | 23176 | 1.2969          | 22.6098 | 9.4618  | 17.7417 | 19.2344   | 19.0    |
+| 1.5034        | 9.0   | 26073 | 1.2774          | 22.7211 | 9.8323  | 17.9709 | 19.456    | 19.0    |
+| 1.4808        | 10.0  | 28970 | 1.2697          | 22.6057 | 9.778   | 17.9176 | 19.3593   | 19.0    |
+| 1.468         | 11.0  | 31867 | 1.2612          | 22.6437 | 9.8167  | 17.9253 | 19.3505   | 19.0    |
+| 1.458         | 12.0  | 34764 | 1.2527          | 22.744  | 10.0172 | 18.0459 | 19.5324   | 19.0    |
+| 1.4494        | 13.0  | 37661 | 1.2491          | 22.687  | 9.9128  | 17.9941 | 19.4752   | 19.0    |
+| 1.4286        | 14.0  | 40558 | 1.2490          | 22.6855 | 9.9731  | 18.0414 | 19.5128   | 19.0    |
+| 1.4448        | 15.0  | 43455 | 1.2436          | 22.6476 | 9.9704  | 18.0385 | 19.498    | 19.0    |
+| 1.4324        | 16.0  | 46352 | 1.2444          | 22.6291 | 9.9519  | 18.0362 | 19.4768   | 19.0    |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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": "4.38.1",
+  "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": "4.38.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708e841d2912cb316e4c4e4246394f471b161477c3a51a48d7a44a441e99a1e2
+size 1200729512

runs/Mar12_01-05-47_d5f8b6fd30a3/events.out.tfevents.1710205559.d5f8b6fd30a3.1294.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c36114d4b08940e55f2273d554bd5b7ae58345828e2dbab3b34dbb22a7d24df
+size 33364

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:a0910f648726ceada34086ae80066cd253863e183cbb52ae566659a2d37716f0
+size 16330660

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_prefix_space": true,
+  "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 sha256:3af6d6353c95828db6fe7ce633093188f532373c04cad5f5d282a0fce35462f3
+size 5048