daljeetsingh/sql_ft_t5small_kag

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+base_model: t5-small
+tags:
+- generated_from_trainer
+model-index:
+- name: sql-training-1725691627
+  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. -->
+
+# sql-training-1725691627
+
+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: 0.0117
+
+## 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: 16
+- eval_batch_size: 16
+- 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 |
+|:-------------:|:------:|:-----:|:---------------:|
+| 0.0561        | 0.0674 | 500   | 0.0401          |
+| 0.0398        | 0.1348 | 1000  | 0.0298          |
+| 0.035         | 0.2022 | 1500  | 0.0259          |
+| 0.0312        | 0.2696 | 2000  | 0.0231          |
+| 0.0244        | 0.3370 | 2500  | 0.0204          |
+| 0.0264        | 0.4044 | 3000  | 0.0191          |
+| 0.0295        | 0.4718 | 3500  | 0.0181          |
+| 0.0227        | 0.5392 | 4000  | 0.0171          |
+| 0.0245        | 0.6066 | 4500  | 0.0162          |
+| 0.02          | 0.6739 | 5000  | 0.0153          |
+| 0.0193        | 0.7413 | 5500  | 0.0148          |
+| 0.0198        | 0.8087 | 6000  | 0.0142          |
+| 0.0231        | 0.8761 | 6500  | 0.0139          |
+| 0.0224        | 0.9435 | 7000  | 0.0134          |
+| 0.0133        | 1.0109 | 7500  | 0.0131          |
+| 0.0166        | 1.0783 | 8000  | 0.0129          |
+| 0.0173        | 1.1457 | 8500  | 0.0126          |
+| 0.0143        | 1.2131 | 9000  | 0.0124          |
+| 0.0105        | 1.2805 | 9500  | 0.0123          |
+| 0.0193        | 1.3479 | 10000 | 0.0122          |
+| 0.0183        | 1.4153 | 10500 | 0.0120          |
+| 0.0142        | 1.4827 | 11000 | 0.0119          |
+| 0.0128        | 1.5501 | 11500 | 0.0118          |
+| 0.0132        | 1.6175 | 12000 | 0.0118          |
+| 0.0143        | 1.6849 | 12500 | 0.0117          |
+| 0.015         | 1.7523 | 13000 | 0.0117          |
+| 0.0161        | 1.8197 | 13500 | 0.0117          |
+| 0.0132        | 1.8870 | 14000 | 0.0117          |
+| 0.0119        | 1.9544 | 14500 | 0.0117          |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.4.0
+- Datasets 2.21.0
+- 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": "4.44.0",
+  "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": "4.44.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fadf32460b5ba3640df41ab31c22ef25190818ef0bd0b76280658873b27f4f0
+size 121028656

runs/Sep07_06-47-07_3a62b5bc08b8/events.out.tfevents.1725691629.3a62b5bc08b8.36.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3200a5cb903a374ddcd912bf70c12f701437ccd3b543daa0d46dc4a6cd94eb
+size 76464

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73fbfb50508f46fe4856f92aa4f2ee778e3061b132819c17bf6bc7a24be1d1b
+size 5176