End of training

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+mnist_test.csv filter=lfs diff=lfs merge=lfs -text
+mnist_train_small.csv filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,64 @@
+---
+license: apache-2.0
+base_model: google/flan-t5-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: sample_data
+  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. -->
+
+# sample_data
+
+This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9981
+- Rouge1: 11.7326
+- Rouge2: 5.4413
+- Rougel: 10.8133
+- Rougelsum: 11.3071
+- Gen Len: 19.0
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| 2.7628        | 5.0   | 500  | 1.9981          | 11.7326 | 5.4413 | 10.8133 | 11.3071   | 19.0    |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

anscombe.json

@@ -0,0 +1,49 @@
+[
+  {"Series":"I", "X":10.0, "Y":8.04},
+  {"Series":"I", "X":8.0, "Y":6.95},
+  {"Series":"I", "X":13.0, "Y":7.58},
+  {"Series":"I", "X":9.0, "Y":8.81},
+  {"Series":"I", "X":11.0, "Y":8.33},
+  {"Series":"I", "X":14.0, "Y":9.96},
+  {"Series":"I", "X":6.0, "Y":7.24},
+  {"Series":"I", "X":4.0, "Y":4.26},
+  {"Series":"I", "X":12.0, "Y":10.84},
+  {"Series":"I", "X":7.0, "Y":4.81},
+  {"Series":"I", "X":5.0, "Y":5.68},
+
+  {"Series":"II", "X":10.0, "Y":9.14},
+  {"Series":"II", "X":8.0, "Y":8.14},
+  {"Series":"II", "X":13.0, "Y":8.74},
+  {"Series":"II", "X":9.0, "Y":8.77},
+  {"Series":"II", "X":11.0, "Y":9.26},
+  {"Series":"II", "X":14.0, "Y":8.10},
+  {"Series":"II", "X":6.0, "Y":6.13},
+  {"Series":"II", "X":4.0, "Y":3.10},
+  {"Series":"II", "X":12.0, "Y":9.13},
+  {"Series":"II", "X":7.0, "Y":7.26},
+  {"Series":"II", "X":5.0, "Y":4.74},
+
+  {"Series":"III", "X":10.0, "Y":7.46},
+  {"Series":"III", "X":8.0, "Y":6.77},
+  {"Series":"III", "X":13.0, "Y":12.74},
+  {"Series":"III", "X":9.0, "Y":7.11},
+  {"Series":"III", "X":11.0, "Y":7.81},
+  {"Series":"III", "X":14.0, "Y":8.84},
+  {"Series":"III", "X":6.0, "Y":6.08},
+  {"Series":"III", "X":4.0, "Y":5.39},
+  {"Series":"III", "X":12.0, "Y":8.15},
+  {"Series":"III", "X":7.0, "Y":6.42},
+  {"Series":"III", "X":5.0, "Y":5.73},
+
+  {"Series":"IV", "X":8.0, "Y":6.58},
+  {"Series":"IV", "X":8.0, "Y":5.76},
+  {"Series":"IV", "X":8.0, "Y":7.71},
+  {"Series":"IV", "X":8.0, "Y":8.84},
+  {"Series":"IV", "X":8.0, "Y":8.47},
+  {"Series":"IV", "X":8.0, "Y":7.04},
+  {"Series":"IV", "X":8.0, "Y":5.25},
+  {"Series":"IV", "X":19.0, "Y":12.50},
+  {"Series":"IV", "X":8.0, "Y":5.56},
+  {"Series":"IV", "X":8.0, "Y":7.91},
+  {"Series":"IV", "X":8.0, "Y":6.89}
+]

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "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",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

events.out.tfevents.1698207096.458000d8fda0.16021.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed34b5814161fc4f333762adf763907fa1e88e7c5406c7b170b428875315c85d
+size 6138

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.1"
+}

mnist_test.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c292478d94ec3a01461bdfa82eb0885d262eb09e615679b2d69dedb6ad09e7
+size 18289443

mnist_train_small.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef64781aa03180f4f5ce504314f058f5d0227277df86060473d973cf43b033e
+size 36523880

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6374028aa4e7023cecc63463220b1f2fa2df2fc40490fda28e8c824f97d3e934
+size 990405362

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5a0a04958fc68851b347aedcd51a4f4349a11cca970a86ea4dc6ae8a295cb2
+size 4600