Training in progress epoch 0

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+base_model: t5-small
+tags:
+- generated_from_keras_callback
+model-index:
+- name: MelioAI/machine-translation
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# MelioAI/machine-translation
+
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 2.0902
+- Validation Loss: 1.8618
+- Epoch: 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:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 2.0902     | 1.8618          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- TensorFlow 2.16.1
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -54,7 +54,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.2",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.40.2"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be8918b3e4ed56b4c3f790fbf5abaf89421f2af3d20a0af109316ef0bfae7f15
+oid sha256:73652b24f1d3f86914424b747c230e518d5cfa1e90bd2b86827483f7694fe019
 size 373902664

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -944,8 +949,8 @@
       {
         "type": "Metaspace",
         "replacement": "▁",
-        "add_prefix_space": true,
-        "prepend_scheme": "always"
+        "prepend_scheme": "always",
+        "split": true
       }
     ]
   },
@@ -1006,8 +1011,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true,
-    "prepend_scheme": "always"
+    "prepend_scheme": "always",
+    "split": true
   },
   "model": {
     "type": "Unigram",

tokenizer_config.json

@@ -930,12 +930,8 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "max_length": 128,
   "model_max_length": 512,
   "pad_token": "<pad>",
-  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }