Full fine-tuned masakhane/afri-mt5-base on sentiment task

.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 +1,77 @@
+---
+library_name: transformers
+license: afl-3.0
+base_model: masakhane/afri-mt5-base
+tags:
+- full-finetuning
+- amharic
+- sentiment-classification
+- single-task
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: MTL-FullFT-afri-mt5-base-sentiment
+  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. -->
+
+# MTL-FullFT-afri-mt5-base-sentiment
+
+This model is a fine-tuned version of [masakhane/afri-mt5-base](https://huggingface.co/masakhane/afri-mt5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9457
+- Accuracy: 0.6783
+- Macro F1: 0.6676
+- Exact Match: 0.6783
+
+## 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: 0.0003
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 300
+- num_epochs: 10
+- label_smoothing_factor: 0.1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Exact Match |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|
+| 9.3722        | 1.0   | 189  | 2.1564          | 0.3566   | 0.1953   | 0.3566      |
+| 4.0864        | 2.0   | 378  | 1.8879          | 0.6646   | 0.6569   | 0.6646      |
+| 3.8180        | 3.0   | 567  | 1.8513          | 0.6658   | 0.6519   | 0.6658      |
+| 3.6847        | 4.0   | 756  | 1.8845          | 0.6796   | 0.6771   | 0.6796      |
+| 3.5788        | 5.0   | 945  | 1.8890          | 0.6671   | 0.6509   | 0.6671      |
+| 3.4913        | 6.0   | 1134 | 1.9142          | 0.6808   | 0.6728   | 0.6808      |
+| 3.4349        | 7.0   | 1323 | 1.9457          | 0.6783   | 0.6676   | 0.6783      |
+
+
+### Framework versions
+
+- Transformers 5.0.0
+- Pytorch 2.10.0+cu128
+- Datasets 5.0.0
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": null,
+  "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,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_decoder": false,
+  "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": true,
+  "tokenizer_class": "T5Tokenizer",
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,35 @@
+{
+  "_from_model_config": false,
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "decoder_start_token_id": 0,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": 1,
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "pad_token_id": 0,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "target_lookbehind": 10,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.0.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1833689bdbe1c93020111f84f62f64d8014b0a0d7b118775e2a8ea4279b666b
+size 2008678272

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f863ac4ba16e5c05a534f69aeccb624f9177f940cac50650f42b8f67515aeae
+size 16013692

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": [],
+  "is_local": 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:f4479e147dc482feefb5134d83e6b3611e1a57cdc077d61874ddcdad1d3b8c5f
+size 5393