Training in progress, step 1000

README.md

@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+base_model: t5-base
+tags:
+- generated_from_trainer
+model-index:
+- name: Question_Generation_ComQ_onT5base_withDataGen10
+  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. -->
+
+# Question_Generation_ComQ_onT5base_withDataGen10
+
+This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3923
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 7
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.7546        | 0.23  | 1000  | 0.5504          |
+| 0.6013        | 0.47  | 2000  | 0.5134          |
+| 0.557         | 0.7   | 3000  | 0.4834          |
+| 0.5217        | 0.94  | 4000  | 0.4513          |
+| 0.449         | 1.17  | 5000  | 0.4519          |
+| 0.4441        | 1.41  | 6000  | 0.4389          |
+| 0.439         | 1.64  | 7000  | 0.4322          |
+| 0.4355        | 1.88  | 8000  | 0.4153          |
+| 0.3996        | 2.11  | 9000  | 0.4263          |
+| 0.388         | 2.35  | 10000 | 0.4183          |
+| 0.3856        | 2.58  | 11000 | 0.4129          |
+| 0.3782        | 2.82  | 12000 | 0.4101          |
+| 0.3719        | 3.05  | 13000 | 0.4091          |
+| 0.3395        | 3.29  | 14000 | 0.4091          |
+| 0.3453        | 3.52  | 15000 | 0.4053          |
+| 0.3538        | 3.76  | 16000 | 0.3933          |
+| 0.3468        | 3.99  | 17000 | 0.3897          |
+| 0.3128        | 4.22  | 18000 | 0.4035          |
+| 0.3191        | 4.46  | 19000 | 0.4005          |
+| 0.322         | 4.69  | 20000 | 0.3944          |
+| 0.3204        | 4.93  | 21000 | 0.3881          |
+| 0.302         | 5.16  | 22000 | 0.3951          |
+| 0.2947        | 5.4   | 23000 | 0.3948          |
+| 0.3011        | 5.63  | 24000 | 0.3932          |
+| 0.303         | 5.87  | 25000 | 0.3873          |
+| 0.2902        | 6.1   | 26000 | 0.3916          |
+| 0.2777        | 6.34  | 27000 | 0.3940          |
+| 0.2811        | 6.57  | 28000 | 0.3937          |
+| 0.2815        | 6.81  | 29000 | 0.3923          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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,
+  "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": "4.36.2",
+  "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": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597c7b28fe4ad3ef4af24e393ac417da8247ee63c79d45a4ebad8a13a7d9ca8f
+size 891644712

tmp-checkpoint-10600/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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,
+  "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": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

tmp-checkpoint-10600/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": "4.36.2"
+}

tmp-checkpoint-10600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd499fa5b39c0c2f11a6aa9d8ec8d0314973d5f1b7b2ed410c19806a827d94aa
+size 891644712

tmp-checkpoint-10600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29c20946110430c54df7ddb3dfb5a71fb4bcde3f7cb62f4b4131be345a6e1d4
+size 896512256

tmp-checkpoint-10600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9772c3657161a71b023db8412d5c74f76b1355672f520a3a78ff17e8b3122786
+size 4792

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c896b6854524d25e317d5e16791949cdcdb5330cb1425b74f68d305c511d8bf9
+size 4856