End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: google/flan-t5-small
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: flan-t5-small-20-epochs-fine-tune
+  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. -->
+
+# flan-t5-small-20-epochs-fine-tune
+
+This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1136
+- Accuracy: 1
+- F1 Micro: 1
+- F1 Macro: 1
+- F1 Weighted: 1
+
+## 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: 5e-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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1 Micro | F1 Macro | F1 Weighted |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:--------:|:-----------:|
+| 2.0193        | 1.0   | 643   | 1.3910          | 1        | 1        | 1        | 1           |
+| 1.3609        | 2.0   | 1286  | 0.9353          | 1        | 1        | 1        | 1           |
+| 1.0198        | 3.0   | 1929  | 0.8408          | 1        | 1        | 1        | 1           |
+| 0.7264        | 4.0   | 2572  | 0.7945          | 1        | 1        | 1        | 1           |
+| 0.6595        | 5.0   | 3215  | 0.7847          | 1        | 1        | 1        | 1           |
+| 0.5689        | 6.0   | 3858  | 0.7898          | 1        | 1        | 1        | 1           |
+| 0.4745        | 7.0   | 4501  | 0.7969          | 1        | 1        | 1        | 1           |
+| 0.4204        | 8.0   | 5144  | 0.8213          | 1        | 1        | 1        | 1           |
+| 0.403         | 9.0   | 5787  | 0.8726          | 1        | 1        | 1        | 1           |
+| 0.3578        | 10.0  | 6430  | 0.8777          | 1        | 1        | 1        | 1           |
+| 0.3238        | 11.0  | 7073  | 0.9143          | 1        | 1        | 1        | 1           |
+| 0.287         | 12.0  | 7716  | 0.9656          | 1        | 1        | 1        | 1           |
+| 0.2903        | 13.0  | 8359  | 0.9580          | 1        | 1        | 1        | 1           |
+| 0.2463        | 14.0  | 9002  | 1.0306          | 1        | 1        | 1        | 1           |
+| 0.2318        | 15.0  | 9645  | 1.0428          | 1        | 1        | 1        | 1           |
+| 0.2265        | 16.0  | 10288 | 1.0483          | 1        | 1        | 1        | 1           |
+| 0.1954        | 17.0  | 10931 | 1.0825          | 1        | 1        | 1        | 1           |
+| 0.191         | 18.0  | 11574 | 1.0972          | 1        | 1        | 1        | 1           |
+| 0.1774        | 19.0  | 12217 | 1.1163          | 1        | 1        | 1        | 1           |
+| 0.1847        | 20.0  | 12860 | 1.1136          | 1        | 1        | 1        | 1           |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,97 @@
+{
+  "_name_or_path": "google/flan-t5-small",
+  "architectures": [
+    "T5ForSequenceClassification"
+  ],
+  "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",
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14"
+  },
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a327801b6d09083d06c396aa309748558e1a220791cfbd285204f296027db7a7
+size 243152884

runs/Apr07_12-10-23_6b1da69729bf/events.out.tfevents.1712491854.6b1da69729bf.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1b611263388bd144afbcd38d3050025ebc61581ef015d3e45713594ae61c15c
+size 21407

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd1b3d5beca7a74bc163e0ef81d85c68f551c2091cd791eb78e150a1350fa3fb
+size 4920