JsteReubsSoftware/en_af_sql_trained_model

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: t5-small
+tags:
+- generated_from_trainer
+model-index:
+- name: en-af-sql-training-1727527893
+  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. -->
+
+# en-af-sql-training-1727527893
+
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0210
+
+## 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: 0.005
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0573        | 0.1348 | 500  | 0.0452          |
+| 0.0424        | 0.2695 | 1000 | 0.0364          |
+| 0.037         | 0.4043 | 1500 | 0.0323          |
+| 0.0356        | 0.5391 | 2000 | 0.0287          |
+| 0.0328        | 0.6739 | 2500 | 0.0269          |
+| 0.0281        | 0.8086 | 3000 | 0.0255          |
+| 0.0286        | 0.9434 | 3500 | 0.0238          |
+| 0.0269        | 1.0782 | 4000 | 0.0233          |
+| 0.0247        | 1.2129 | 4500 | 0.0225          |
+| 0.0245        | 1.3477 | 5000 | 0.0217          |
+| 0.0226        | 1.4825 | 5500 | 0.0214          |
+| 0.0245        | 1.6173 | 6000 | 0.0211          |
+| 0.024         | 1.7520 | 6500 | 0.0210          |
+| 0.0249        | 1.8868 | 7000 | 0.0210          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "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: "
+    }
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a6c87fdeb0da89aacabd73e160dae77e87d4ffd289c444d85c4a9b0e5f1716
+size 121028656

runs/Sep28_12-51-33_000fa0f9cb72/events.out.tfevents.1727527920.000fa0f9cb72.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b6cf82cebad7c32c9a3639106e9447c41268b803e7c9b369aa0a270db87202b
+size 41189

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3ab186886fb2df1a7d41d819ff58b82c393891da5e99949b64a37f2b23c0c8
+size 5176