Merge branch 'main' of https://huggingface.co/pszemraj/t5-v1_1-base-finetuned-lfqa into main

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- t5
+- qa
+- askscience
+- lfqa
+- information retrieval
+datasets:
+- vblagoje/lfqa
+metrics:
+- rouge
+widget:
+- text: "why aren't there more planets in our solar system?"
+  example_title: "solar system"
+- text: "question: what is a probability distribution? context: I am just learning about statistics."
+  example_title: "probability distribution"
+- text: "question: how does exercise help us lose weight? context: I started working out two weeks ago and already feel a lot better, and started to think about it and became deeply confused."
+  example_title: "pumpen"
+- text: "what is a neural network?"
+  example_title: "deep learning"
+- text: "How can computers understand human language?"
+  example_title: "NLP"
+  
+inference:
+  parameters:
+    max_length: 64
+    no_repeat_ngram_size: 2
+    encoder_no_repeat_ngram_size: 4
+    repetition_penalty: 3.51
+    length_penalty: 0.8
+    num_beams: 4
+    early_stopping: True
+    
+---
+
+<!-- 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. -->
+
+# checkpoints
+
+This model is a fine-tuned version of [google/t5-v1_1-base](https://huggingface.co/google/t5-v1_1-base) on the `vblagoje/lfqa` dataset, with training duration of 2 epochs. For a (_somewhat_) apples-to-apples comparison with [t5-base](https://huggingface.co/pszemraj/t5-base-askscience) on the standard eli5 dataset.
+
+## 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: 4e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.16.2
+- Pytorch 1.10.0+cu113
+- Datasets 1.18.3
+- Tokenizers 0.11.0

t5-v1_1-base-finetuned-lfqa_training_metadata.json

@@ -0,0 +1 @@
+{"output_dir": "/content/checkpoints/", "overwrite_output_dir": true, "do_train": false, "do_eval": false, "do_predict": false, "evaluation_strategy": "no", "prediction_loss_only": false, "per_device_train_batch_size": 8, "per_device_eval_batch_size": 8, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 2, "eval_accumulation_steps": 2, "learning_rate": 4e-05, "weight_decay": 0.01, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1, "num_train_epochs": 2, "max_steps": -1, "lr_scheduler_type": "cosine", "warmup_ratio": 0, "warmup_steps": 0, "log_level": -1, "log_level_replica": -1, "log_on_each_node": true, "logging_dir": "/content/logs", "logging_strategy": "steps", "logging_first_step": false, "logging_steps": 15, "logging_nan_inf_filter": true, "save_strategy": "epoch", "save_steps": 500, "save_total_limit": 1, "save_on_each_node": false, "no_cuda": false, "seed": 42, "bf16": false, "fp16": true, "fp16_opt_level": "O1", "half_precision_backend": "amp", "bf16_full_eval": false, "fp16_full_eval": true, "tf32": "None", "local_rank": 0, "xpu_backend": "None", "tpu_num_cores": "None", "tpu_metrics_debug": false, "debug": "[]", "dataloader_drop_last": false, "eval_steps": "None", "dataloader_num_workers": 0, "past_index": -1, "run_name": "/content/checkpoints/", "disable_tqdm": false, "remove_unused_columns": true, "label_names": "None", "load_best_model_at_end": false, "metric_for_best_model": "None", "greater_is_better": "None", "ignore_data_skip": false, "sharded_ddp": "[]", "deepspeed": "/content/ds_config_zero2.json", "label_smoothing_factor": 0.0, "optim": "adamw_hf", "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": "['tensorboard']", "ddp_find_unused_parameters": "None", "ddp_bucket_cap_mb": "None", "dataloader_pin_memory": false, "skip_memory_metrics": false, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": "None", "hub_model_id": "t5-v1_1-base-finetuned-lfqa", "hub_strategy": "end", "hub_token": "<HUB_TOKEN>", "gradient_checkpointing": true, "fp16_backend": "auto", "push_to_hub_model_id": "None", "push_to_hub_organization": "None", "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", "_n_gpu": 1, "mp_parameters": "", "sortish_sampler": false, "predict_with_generate": false, "generation_max_length": "None", "generation_num_beams": "None", "train_batch_size": 8, "eval_batch_size": 8, "configs_src": "t5-v1_1-base-finetuned-lfqa", "data_tag": "vblagoje/lfqa"}