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 +1,86 @@
+---
+license: apache-2.0
+base_model: google/mt5-small
+tags:
+- summarization
+- generated_from_trainer
+datasets:
+- xsum
+metrics:
+- rouge
+model-index:
+- name: mt5-small-finetuned-amazon-en-es
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: xsum
+      type: xsum
+      config: default
+      split: validation
+      args: default
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 0.0706
+---
+
+<!-- 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 xsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.4800
+- Rouge1: 0.0706
+- Rouge2: 0.0067
+- Rougel: 0.058
+- Rougelsum: 0.0654
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
+| No log        | 1.0   | 13   | 7.7221          | 0.0369 | 0.0    | 0.0369 | 0.0366    |
+| No log        | 2.0   | 26   | 7.1952          | 0.0448 | 0.0    | 0.0452 | 0.0449    |
+| No log        | 3.0   | 39   | 6.5146          | 0.0442 | 0.0    | 0.0443 | 0.044     |
+| 12.6754       | 4.0   | 52   | 6.2530          | 0.0745 | 0.008  | 0.0636 | 0.0679    |
+| 12.6754       | 5.0   | 65   | 6.0200          | 0.0745 | 0.0069 | 0.0642 | 0.0693    |
+| 12.6754       | 6.0   | 78   | 5.7336          | 0.0706 | 0.0067 | 0.058  | 0.0654    |
+| 12.6754       | 7.0   | 91   | 5.5400          | 0.0706 | 0.0067 | 0.058  | 0.0654    |
+| 9.1744        | 8.0   | 104  | 5.4800          | 0.0706 | 0.0067 | 0.058  | 0.0654    |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu118
+- Datasets 2.17.1
+- 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": "4.38.2",
+  "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": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:226370d261c4e2df76d679ba4b9f50dc1a8e35787b19173baf80151e0d71aa94
+size 1200729512

runs/Mar01_00-41-17_ip-172-16-70-104.us-gov-west-1.compute.internal/events.out.tfevents.1709253754.ip-172-16-70-104.us-gov-west-1.compute.internal.35342.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d38da999ad5d54a75f5e55229f811b47efbbbbf4bae39d94191d6fe0e36f2884
+size 4930

runs/Mar01_00-47-47_ip-172-16-70-104.us-gov-west-1.compute.internal/events.out.tfevents.1709254081.ip-172-16-70-104.us-gov-west-1.compute.internal.41557.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d44387c08249747b615526bb37ea657da903840ca078be2252d67b873049b0f
+size 4931

runs/Mar01_12-49-31_ip-172-16-66-103.us-gov-west-1.compute.internal/events.out.tfevents.1709297387.ip-172-16-66-103.us-gov-west-1.compute.internal.16137.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e44961980dda0c3cad2f944014b447866d6206c9e4d966ec63ea4a29847d9c1
+size 9766

runs/Mar01_12-49-31_ip-172-16-66-103.us-gov-west-1.compute.internal/events.out.tfevents.1709297581.ip-172-16-66-103.us-gov-west-1.compute.internal.16137.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2329ef36dec9b4ce60cf47b2098023caec49f7bd0f0e6cc8f23b5600952f4ff4
+size 9409

runs/Mar01_12-49-31_ip-172-16-66-103.us-gov-west-1.compute.internal/events.out.tfevents.1709297742.ip-172-16-66-103.us-gov-west-1.compute.internal.16137.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:befcb13f4b66be28a4d5761209120335214bf4219ed08a5003536a3a205795b7
+size 553

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 sha256:92dc1abb6dba9540c85a5e2b57077a602c295f3fffc068e3d95438b3c076ab81
+size 16330659

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": false,
+  "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:e8802a48416e68ce1a0a631d609448c55c0fef046e53774f205cdbb298a84875
+size 5112