Training complete

.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 +1,82 @@
+---
+license: apache-2.0
+base_model: google/mt5-small
+tags:
+- summarization
+- generated_from_trainer
+datasets:
+- scientific_papers
+metrics:
+- rouge
+model-index:
+- name: mt5-small-finetuned-amazon-en-es
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: scientific_papers
+      type: scientific_papers
+      config: pubmed
+      split: validation
+      args: pubmed
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 7.0145
+---
+
+<!-- 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-finetuned-amazon-en-es
+
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the scientific_papers dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5188
+- Rouge1: 7.0145
+- Rouge2: 1.8214
+- Rougel: 5.8355
+- Rougelsum: 6.2468
+
+## 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: 5.6e-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
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
+| 17.5935       | 1.0   | 50   | 8.3763          | 1.0909 | 0.7547 | 1.0909 | 1.0909    |
+| 10.9464       | 2.0   | 100  | 4.7599          | 3.5415 | 0.0    | 2.927  | 2.547     |
+| 6.5498        | 3.0   | 150  | 3.6772          | 6.7136 | 1.8214 | 5.2193 | 5.925     |
+| 6.0161        | 4.0   | 200  | 3.5188          | 7.0145 | 1.8214 | 5.8355 | 6.2468    |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.2.1+cpu
+- Datasets 2.17.0
+- 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": "4.37.2",
+  "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:f2aac15ae5bf1f0d43faab6cf37f227b5a8d1d4eaa00768cf3dd476f9b461ed9
+size 1200729512

runs/Feb29_21-33-52_LAPTOP-JGR2QN7D/events.out.tfevents.1709260453.LAPTOP-JGR2QN7D.22696.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eae25cd82f5ce9ca53623a0e256fd1444e42d5925f64dded064e9e95b8b1ce8
+size 4689

runs/Feb29_21-52-26_LAPTOP-JGR2QN7D/events.out.tfevents.1709261564.LAPTOP-JGR2QN7D.21708.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d79c890c5b5d4753e27c55ff82ee652d0cef1268252f88e41b24e6b2839684f
+size 4689

runs/Feb29_22-13-12_LAPTOP-JGR2QN7D/events.out.tfevents.1709262806.LAPTOP-JGR2QN7D.21832.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:297dbca6641d3efd40c2395e817172a89e447c8a8d013d7e73cb850b0a41c508
+size 4687

runs/Feb29_22-43-22_LAPTOP-JGR2QN7D/events.out.tfevents.1709264629.LAPTOP-JGR2QN7D.23044.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea18efc702ac389b7040935e3272fbe8d9b63e3cf725d9b2ce52570270995c0
+size 4687

runs/Feb29_23-02-36_LAPTOP-JGR2QN7D/events.out.tfevents.1709265774.LAPTOP-JGR2QN7D.12256.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c107f1499065e57adace569b41f55d655be774d4be999ac82b1afc1df6de2323
+size 4687

runs/Feb29_23-05-14_LAPTOP-JGR2QN7D/events.out.tfevents.1709265931.LAPTOP-JGR2QN7D.12256.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ad8574f8043125d10f39803178de32f62754d715e8076bb8606827c0aee77b
+size 4686

runs/Feb29_23-28-11_LAPTOP-JGR2QN7D/events.out.tfevents.1709267323.LAPTOP-JGR2QN7D.22468.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a04bf74a25a44030f22ee3bec819fd91c0ec6c2653c91e8e2a90aeb22f2b34
+size 4686

runs/Mar01_11-51-45_LAPTOP-JGR2QN7D/events.out.tfevents.1709311963.LAPTOP-JGR2QN7D.21596.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6127d977826026d97314458adced03dd414232420bed49c0ced9de174b25c9ed
+size 4687

runs/Mar01_11-53-56_LAPTOP-JGR2QN7D/events.out.tfevents.1709312067.LAPTOP-JGR2QN7D.21596.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a73709e28f3a8f5b7841f50e39c826cf2ec8830867644ac8edce8a7a9a8e62b
+size 4687

runs/Mar01_11-56-38_LAPTOP-JGR2QN7D/events.out.tfevents.1709312213.LAPTOP-JGR2QN7D.16536.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f7e65852800494e0eef19e393854f16f2c8010c8e854e9e3ed8162b1319e4d
+size 4840

runs/Mar01_12-08-50_LAPTOP-JGR2QN7D/events.out.tfevents.1709312941.LAPTOP-JGR2QN7D.16536.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750e70430da5f9f73c08efad01ecc01e5b08217ecde889c8dab262794c93d846
+size 9592

runs/Mar01_12-43-02_LAPTOP-JGR2QN7D/events.out.tfevents.1709314993.LAPTOP-JGR2QN7D.19780.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf640b6097bf747e7546a675f2017869494fc02ad0147cc8b55e04df5b9f52e
+size 7540

runs/Mar01_12-43-02_LAPTOP-JGR2QN7D/events.out.tfevents.1709316768.LAPTOP-JGR2QN7D.19780.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffde1a0db842d45f32a9b1c266f96df3a7fc0217d270895dd96e19d8ad8dea67
+size 562

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 sha256:1e61a9218fac8f1c425496db9e52d35cacb7978912db376cb6f8029daa45d1c1
+size 16330660

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 sha256:13a8cdfc6b6ffdf0a721751eedff9ef06dfeeecac233a626f5823eae3ef80d04
+size 4856