be2be2/et5-typos-maker

README.md

@@ -0,0 +1,85 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: j5ng/et5-typos-corrector
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: make_err_ft_results
+  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. -->
+
+# make_err_ft_results
+
+This model is a fine-tuned version of [j5ng/et5-typos-corrector](https://huggingface.co/j5ng/et5-typos-corrector) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9276
+- Rouge1: 0.0
+- Rouge2: 0.0
+- Rougel: 0.0
+- Rougelsum: 0.0
+- Gen Len: 12.1935
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 2.7078        | 0.1   | 100  | 1.7370          | 0.0    | 0.0    | 0.0    | 0.0       | 11.7045 |
+| 1.7594        | 0.2   | 200  | 1.4867          | 0.0    | 0.0    | 0.0    | 0.0       | 11.7515 |
+| 1.5496        | 0.3   | 300  | 1.3286          | 0.0    | 0.0    | 0.0    | 0.0       | 11.834  |
+| 1.429         | 0.4   | 400  | 1.2470          | 0.0    | 0.0    | 0.0    | 0.0       | 12.003  |
+| 1.3714        | 0.5   | 500  | 1.1811          | 0.0    | 0.0    | 0.0    | 0.0       | 12.0145 |
+| 1.2822        | 0.6   | 600  | 1.1452          | 0.0    | 0.0    | 0.0    | 0.0       | 11.999  |
+| 1.2407        | 0.7   | 700  | 1.0803          | 0.0    | 0.0    | 0.0    | 0.0       | 12.092  |
+| 1.1908        | 0.8   | 800  | 1.0616          | 0.0    | 0.0    | 0.0    | 0.0       | 12.023  |
+| 1.1535        | 0.9   | 900  | 1.0261          | 0.0    | 0.0    | 0.0    | 0.0       | 12.1115 |
+| 1.1341        | 1.0   | 1000 | 1.0039          | 0.0    | 0.0    | 0.0    | 0.0       | 12.1475 |
+| 0.9145        | 1.1   | 1100 | 0.9805          | 0.0    | 0.0    | 0.0    | 0.0       | 12.185  |
+| 0.9111        | 1.2   | 1200 | 0.9741          | 0.0    | 0.0    | 0.0    | 0.0       | 12.3435 |
+| 0.8736        | 1.3   | 1300 | 0.9667          | 0.0    | 0.0    | 0.0    | 0.0       | 12.147  |
+| 0.855         | 1.4   | 1400 | 0.9600          | 0.0    | 0.0    | 0.0    | 0.0       | 12.21   |
+| 0.8754        | 1.5   | 1500 | 0.9506          | 0.0    | 0.0    | 0.0    | 0.0       | 12.1465 |
+| 0.8576        | 1.6   | 1600 | 0.9418          | 0.0    | 0.0    | 0.0    | 0.0       | 12.1645 |
+| 0.8518        | 1.7   | 1700 | 0.9329          | 0.0    | 0.0    | 0.0    | 0.0       | 12.2435 |
+| 0.8322        | 1.8   | 1800 | 0.9321          | 0.0    | 0.0    | 0.0    | 0.0       | 12.1975 |
+| 0.8275        | 1.9   | 1900 | 0.9304          | 0.0    | 0.0    | 0.0    | 0.0       | 12.1885 |
+| 0.8157        | 2.0   | 2000 | 0.9276          | 0.0    | 0.0    | 0.0    | 0.0       | 12.1935 |
+
+
+### Framework versions
+
+- Transformers 4.55.1
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.21.4

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "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": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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": "4.55.1",
+  "use_cache": true,
+  "vocab_size": 45100
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.55.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd5e64fcf29664febf34ed4db70f3278a128b9993d29bb5004fef078f6a7d7c5
+size 1296537480

runs/Aug17_17-00-28_4fbe18cadcab/events.out.tfevents.1755450067.4fbe18cadcab.287.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c69bbc786a0b4f2be2cb8ab5bb7480f6048c3426619988b475d1afd4ff7c38
+size 20339

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 sha256:0ebba0a7b0fadda80677fe980264027fd8c51f822c486201b39dfdfe8804a570
+size 1196021

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "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 sha256:4a678f2d2f76ee1c999dac9c37a8841cfb2e15cd25ddabc5d5a6149c3dc1f3cc
+size 5496