Upload folder using huggingface_hub

.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 +1,73 @@
+---
+language:
+- en
+- bgc
+license: apache-2.0
+base_model: google/mt5-base
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: tst-translation
+  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. -->
+
+# tst-translation
+
+This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.8421
+- Bleu: 13.1948
+- Gen Len: 49.9179
+
+## 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: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20.0
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
+| 3.4257        | 1.9900  | 400  | 2.1087          | 4.1008  | 77.8284 |
+| 1.8571        | 3.9801  | 800  | 1.9292          | 8.6198  | 61.1418 |
+| 1.2467        | 5.9701  | 1200 | 1.9779          | 10.7074 | 48.3184 |
+| 0.8749        | 7.9602  | 1600 | 2.0539          | 11.8538 | 49.3483 |
+| 0.6141        | 9.9502  | 2000 | 2.1948          | 12.4452 | 51.1269 |
+| 0.4446        | 11.9403 | 2400 | 2.3902          | 12.3052 | 48.0995 |
+| 0.3251        | 13.9303 | 2800 | 2.5698          | 12.5824 | 49.1244 |
+| 0.2501        | 15.9204 | 3200 | 2.6631          | 13.0619 | 50.6095 |
+| 0.1986        | 17.9104 | 3600 | 2.7877          | 13.0557 | 51.1443 |
+| 0.1692        | 19.9005 | 4000 | 2.8421          | 13.1948 | 49.9179 |
+
+
+### Framework versions
+
+- Transformers 4.43.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 20.0,
+    "eval_bleu": 13.1948,
+    "eval_gen_len": 49.9179,
+    "eval_loss": 2.8421177864074707,
+    "eval_runtime": 82.86,
+    "eval_samples": 402,
+    "eval_samples_per_second": 4.852,
+    "eval_steps_per_second": 0.314,
+    "total_flos": 4364211764689920.0,
+    "train_loss": 0.9366569099141591,
+    "train_runtime": 4542.9296,
+    "train_samples": 1607,
+    "train_samples_per_second": 7.075,
+    "train_steps_per_second": 0.885
+}

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": "4.43.0.dev0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 20.0,
+    "eval_bleu": 13.1948,
+    "eval_gen_len": 49.9179,
+    "eval_loss": 2.8421177864074707,
+    "eval_runtime": 82.86,
+    "eval_samples": 402,
+    "eval_samples_per_second": 4.852,
+    "eval_steps_per_second": 0.314
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.43.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:826d8270f3ef5c20774e6b122f5cd8667645329c6d77efa3cb4a0654ad02fb03
+size 2329638768

runs/Jul09_14-45-13_015fb6e6cd9b/events.out.tfevents.1720536323.015fb6e6cd9b.53266.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f65b96360cdd6409d863465baefaef8957ce6b54726c16a85bbb24191baae3cd
+size 11412

runs/Jul09_14-45-13_015fb6e6cd9b/events.out.tfevents.1720541097.015fb6e6cd9b.53266.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8403c3c87cdaa60d181966da216d3fe77d374e9295e37a6b2b5982470071f90
+size 458

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 sha256:5f47eb5c71090da540a205198ab25536a203255a5d4500e51f861050302a22c1
+size 16350028

tokenizer_config.json

@@ -0,0 +1,839 @@
+{
+  "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
+    },
+    "250000": {
+      "content": "▁<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250001": {
+      "content": "▁<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250002": {
+      "content": "▁<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250003": {
+      "content": "▁<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250004": {
+      "content": "▁<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250005": {
+      "content": "▁<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250006": {
+      "content": "▁<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250007": {
+      "content": "▁<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250008": {
+      "content": "▁<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250009": {
+      "content": "▁<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250010": {
+      "content": "▁<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250011": {
+      "content": "▁<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250012": {
+      "content": "▁<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250013": {
+      "content": "▁<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250014": {
+      "content": "▁<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250015": {
+      "content": "▁<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250016": {
+      "content": "▁<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250017": {
+      "content": "▁<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250018": {
+      "content": "▁<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250019": {
+      "content": "▁<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250020": {
+      "content": "▁<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250021": {
+      "content": "▁<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250022": {
+      "content": "▁<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250023": {
+      "content": "▁<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250024": {
+      "content": "▁<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250025": {
+      "content": "▁<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250026": {
+      "content": "▁<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250027": {
+      "content": "▁<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250028": {
+      "content": "▁<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250029": {
+      "content": "▁<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250030": {
+      "content": "▁<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250031": {
+      "content": "▁<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250032": {
+      "content": "▁<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250033": {
+      "content": "▁<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250034": {
+      "content": "▁<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250035": {
+      "content": "▁<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250036": {
+      "content": "▁<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250037": {
+      "content": "▁<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250038": {
+      "content": "▁<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250039": {
+      "content": "▁<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250040": {
+      "content": "▁<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250041": {
+      "content": "▁<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250042": {
+      "content": "▁<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250043": {
+      "content": "▁<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250044": {
+      "content": "▁<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250045": {
+      "content": "▁<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250046": {
+      "content": "▁<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250047": {
+      "content": "▁<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250048": {
+      "content": "▁<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250049": {
+      "content": "▁<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250050": {
+      "content": "���<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250051": {
+      "content": "▁<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250052": {
+      "content": "▁<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250053": {
+      "content": "▁<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250054": {
+      "content": "▁<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250055": {
+      "content": "▁<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250056": {
+      "content": "▁<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250057": {
+      "content": "▁<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250058": {
+      "content": "▁<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250059": {
+      "content": "▁<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250060": {
+      "content": "▁<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250061": {
+      "content": "▁<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250062": {
+      "content": "▁<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250063": {
+      "content": "▁<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250064": {
+      "content": "▁<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250065": {
+      "content": "▁<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250066": {
+      "content": "▁<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250067": {
+      "content": "▁<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250068": {
+      "content": "▁<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250069": {
+      "content": "▁<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250070": {
+      "content": "▁<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250071": {
+      "content": "▁<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250072": {
+      "content": "▁<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250073": {
+      "content": "▁<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250074": {
+      "content": "▁<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250075": {
+      "content": "▁<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250076": {
+      "content": "▁<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250077": {
+      "content": "▁<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250078": {
+      "content": "▁<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250079": {
+      "content": "▁<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250080": {
+      "content": "▁<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250081": {
+      "content": "▁<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250082": {
+      "content": "▁<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250083": {
+      "content": "▁<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250084": {
+      "content": "▁<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250085": {
+      "content": "▁<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250086": {
+      "content": "▁<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250087": {
+      "content": "▁<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250088": {
+      "content": "▁<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250089": {
+      "content": "▁<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250090": {
+      "content": "▁<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250091": {
+      "content": "▁<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250092": {
+      "content": "▁<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250093": {
+      "content": "▁<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250094": {
+      "content": "▁<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250095": {
+      "content": "▁<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250096": {
+      "content": "▁<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250097": {
+      "content": "▁<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250098": {
+      "content": "▁<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250099": {
+      "content": "▁<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "total_flos": 4364211764689920.0,
+    "train_loss": 0.9366569099141591,
+    "train_runtime": 4542.9296,
+    "train_samples": 1607,
+    "train_samples_per_second": 7.075,
+    "train_steps_per_second": 0.885
+}

trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_metric": 13.1948,
+  "best_model_checkpoint": "/content/tst-translation/checkpoint-4000",
+  "epoch": 20.0,
+  "eval_steps": 400,
+  "global_step": 4020,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.9900497512437811,
+      "grad_norm": 2.333070993423462,
+      "learning_rate": 0.00045024875621890546,
+      "loss": 3.4257,
+      "step": 400
+    },
+    {
+      "epoch": 1.9900497512437811,
+      "eval_bleu": 4.1008,
+      "eval_gen_len": 77.8284,
+      "eval_loss": 2.1086840629577637,
+      "eval_runtime": 201.8226,
+      "eval_samples_per_second": 1.992,
+      "eval_steps_per_second": 0.129,
+      "step": 400
+    },
+    {
+      "epoch": 3.9800995024875623,
+      "grad_norm": 2.2885234355926514,
+      "learning_rate": 0.00040049751243781097,
+      "loss": 1.8571,
+      "step": 800
+    },
+    {
+      "epoch": 3.9800995024875623,
+      "eval_bleu": 8.6198,
+      "eval_gen_len": 61.1418,
+      "eval_loss": 1.9292024374008179,
+      "eval_runtime": 149.5469,
+      "eval_samples_per_second": 2.688,
+      "eval_steps_per_second": 0.174,
+      "step": 800
+    },
+    {
+      "epoch": 5.970149253731344,
+      "grad_norm": 1.9040518999099731,
+      "learning_rate": 0.0003507462686567164,
+      "loss": 1.2467,
+      "step": 1200
+    },
+    {
+      "epoch": 5.970149253731344,
+      "eval_bleu": 10.7074,
+      "eval_gen_len": 48.3184,
+      "eval_loss": 1.9778931140899658,
+      "eval_runtime": 82.3257,
+      "eval_samples_per_second": 4.883,
+      "eval_steps_per_second": 0.316,
+      "step": 1200
+    },
+    {
+      "epoch": 7.960199004975125,
+      "grad_norm": 1.6420375108718872,
+      "learning_rate": 0.00030099502487562194,
+      "loss": 0.8749,
+      "step": 1600
+    },
+    {
+      "epoch": 7.960199004975125,
+      "eval_bleu": 11.8538,
+      "eval_gen_len": 49.3483,
+      "eval_loss": 2.0539379119873047,
+      "eval_runtime": 80.462,
+      "eval_samples_per_second": 4.996,
+      "eval_steps_per_second": 0.323,
+      "step": 1600
+    },
+    {
+      "epoch": 9.950248756218905,
+      "grad_norm": 1.6268000602722168,
+      "learning_rate": 0.0002512437810945274,
+      "loss": 0.6141,
+      "step": 2000
+    },
+    {
+      "epoch": 9.950248756218905,
+      "eval_bleu": 12.4452,
+      "eval_gen_len": 51.1269,
+      "eval_loss": 2.1948225498199463,
+      "eval_runtime": 88.7102,
+      "eval_samples_per_second": 4.532,
+      "eval_steps_per_second": 0.293,
+      "step": 2000
+    },
+    {
+      "epoch": 11.940298507462687,
+      "grad_norm": 1.412307858467102,
+      "learning_rate": 0.00020149253731343284,
+      "loss": 0.4446,
+      "step": 2400
+    },
+    {
+      "epoch": 11.940298507462687,
+      "eval_bleu": 12.3052,
+      "eval_gen_len": 48.0995,
+      "eval_loss": 2.3901803493499756,
+      "eval_runtime": 67.4373,
+      "eval_samples_per_second": 5.961,
+      "eval_steps_per_second": 0.386,
+      "step": 2400
+    },
+    {
+      "epoch": 13.930348258706468,
+      "grad_norm": 1.7401809692382812,
+      "learning_rate": 0.00015174129353233832,
+      "loss": 0.3251,
+      "step": 2800
+    },
+    {
+      "epoch": 13.930348258706468,
+      "eval_bleu": 12.5824,
+      "eval_gen_len": 49.1244,
+      "eval_loss": 2.5697591304779053,
+      "eval_runtime": 74.1886,
+      "eval_samples_per_second": 5.419,
+      "eval_steps_per_second": 0.35,
+      "step": 2800
+    },
+    {
+      "epoch": 15.92039800995025,
+      "grad_norm": 1.2750484943389893,
+      "learning_rate": 0.00010199004975124378,
+      "loss": 0.2501,
+      "step": 3200
+    },
+    {
+      "epoch": 15.92039800995025,
+      "eval_bleu": 13.0619,
+      "eval_gen_len": 50.6095,
+      "eval_loss": 2.663144588470459,
+      "eval_runtime": 80.5868,
+      "eval_samples_per_second": 4.988,
+      "eval_steps_per_second": 0.323,
+      "step": 3200
+    },
+    {
+      "epoch": 17.91044776119403,
+      "grad_norm": 0.941927433013916,
+      "learning_rate": 5.223880597014925e-05,
+      "loss": 0.1986,
+      "step": 3600
+    },
+    {
+      "epoch": 17.91044776119403,
+      "eval_bleu": 13.0557,
+      "eval_gen_len": 51.1443,
+      "eval_loss": 2.787724494934082,
+      "eval_runtime": 83.6803,
+      "eval_samples_per_second": 4.804,
+      "eval_steps_per_second": 0.311,
+      "step": 3600
+    },
+    {
+      "epoch": 19.90049751243781,
+      "grad_norm": 1.0183725357055664,
+      "learning_rate": 2.4875621890547264e-06,
+      "loss": 0.1692,
+      "step": 4000
+    },
+    {
+      "epoch": 19.90049751243781,
+      "eval_bleu": 13.1948,
+      "eval_gen_len": 49.9179,
+      "eval_loss": 2.8421177864074707,
+      "eval_runtime": 82.7516,
+      "eval_samples_per_second": 4.858,
+      "eval_steps_per_second": 0.314,
+      "step": 4000
+    },
+    {
+      "epoch": 20.0,
+      "step": 4020,
+      "total_flos": 4364211764689920.0,
+      "train_loss": 0.9366569099141591,
+      "train_runtime": 4542.9296,
+      "train_samples_per_second": 7.075,
+      "train_steps_per_second": 0.885
+    }
+  ],
+  "logging_steps": 400,
+  "max_steps": 4020,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4364211764689920.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:195e6ee3a6f8fee17f85303741e2fd95897667f915f800df04603d859f6b5d15
+size 5368