Model save

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+base_model: t5-base
+tags:
+- generated_from_trainer
+datasets:
+- bigbench
+metrics:
+- accuracy
+model-index:
+- name: bigbench_entailedpolarity-t5-base
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: bigbench
+      type: bigbench
+      config: entailed_polarity
+      split: train
+      args: entailed_polarity
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9583333333333334
+---
+
+<!-- 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. -->
+
+# bigbench_entailedpolarity-t5-base
+
+This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the bigbench dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3881
+- Accuracy: 0.9583
+
+## 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: 4
+- eval_batch_size: 32
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 24   | 0.4860          | 0.875    |
+| No log        | 2.0   | 48   | 0.3200          | 0.875    |
+| No log        | 3.0   | 72   | 0.3107          | 0.9167   |
+| No log        | 4.0   | 96   | 0.3666          | 0.9167   |
+| No log        | 5.0   | 120  | 0.5273          | 0.9167   |
+| No log        | 6.0   | 144  | 0.3190          | 0.9583   |
+| No log        | 7.0   | 168  | 0.3328          | 0.9583   |
+| No log        | 8.0   | 192  | 0.5994          | 0.9167   |
+| No log        | 9.0   | 216  | 0.6515          | 0.9167   |
+| No log        | 10.0  | 240  | 0.6435          | 0.9167   |
+| No log        | 11.0  | 264  | 0.6450          | 0.9167   |
+| No log        | 12.0  | 288  | 0.6565          | 0.9167   |
+| No log        | 13.0  | 312  | 0.6484          | 0.9167   |
+| No log        | 14.0  | 336  | 0.6376          | 0.9167   |
+| No log        | 15.0  | 360  | 0.6808          | 0.9167   |
+| No log        | 16.0  | 384  | 0.6884          | 0.9167   |
+| No log        | 17.0  | 408  | 0.6502          | 0.9167   |
+| No log        | 18.0  | 432  | 0.6781          | 0.9167   |
+| No log        | 19.0  | 456  | 0.3894          | 0.9583   |
+| No log        | 20.0  | 480  | 0.3881          | 0.9583   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 1.10.1+cu102
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForSequenceClassification"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fc2fec27b327606beb1b146fed8e80037f846a771ffc1bc758b0e21d0fc10f
+size 894016712

runs/Mar22_22-15-50_dsail2/events.out.tfevents.1711160155.dsail2.28517.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a929e4b7d17c26df68af52491fbe7a395fd371193dad5d4b0e08ae0fbc8c84c
+size 5069

runs/Mar22_22-16-56_dsail2/events.out.tfevents.1711160219.dsail2.29710.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e10210e05194582f1844d2ef3b7ef3fd4994a3d030645d642b615319ce5156f
+size 11853

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29924a5b3404a58a6b432ec9f30f43385cb968356397ba903ef3d5c0b890cb58
+size 4207