initial commit

README.md

@@ -1,3 +1,86 @@
 ---
 license: cc-by-nc-nd-4.0
+metrics:
+- accuracy
+tags:
+- generated_from_trainer
+- Text Generation
+- Primary Sequence Prediction
+model-index:
+- name: protgpt2-finetuned-sarscov2-rbd
+  results: []
 ---
+
+# Model Card for `protgpt2-finetuned-sarscov2-rbd`
+
+This model is a fine-tuned version of [nferruz/ProtGPT2](https://huggingface.co/nferruz/ProtGPT2) on sequences from the NCBI Virus Data Portal.
+
+It achieves the following results on the evaluation set:
+- Loss: 1.1674
+- Accuracy: 0.8883
+
+## Model description
+
+This model is a fine-tuned checkpoint of
+[ProtGPT2](https://huggingface.co/nferruz/ProtGPT2), which was originally
+trained on the UniRef50 (version 2021_04) database. For a detailed overview
+of the original model configuration and architecture, please see the linked
+model card, or refer to the ProtGPT2 publication.
+
+The model was finetuned on data from the SARS-CoV-2 Spike (surface glycoprotein)
+receptor binding domain (RBD).
+
+A repository with the training scripts, train and test data partitions, as well
+as evaluation code is available on GitHub at
+(https://github.com/rahuldhodapkar/PredictSARSVariants).
+
+## Intended uses & limitations
+
+This model is intended to generate synthetic SARS-CoV-2 surface glycoprotein
+(a.k.a. spike protein) sequences for the purpose of identifying meaningful
+variants for characterization either experimentally or through other
+*in silico* tools.  These variants may be used to drive vaccine develop to
+protect against never-before-seen point mutants that are probable in the future.
+
+As this model is based on the original ProtGPT2 model, it is subject to many
+of the same limitations as the base model.  Any biases present in the UniRef50
+dataset will also be present in the model, which may include nonuniform skew
+of peptides sampled across different taxonomic clades.  These limitations
+should be considered when interpreting the output of this model.
+
+## Training and evaluation data
+
+SARS-CoV-2 spike protein sequences were obtained from the NIH Sars-CoV-2 Data Hub
+accessible at 
+
+    https://www.ncbi.nlm.nih.gov/labs/virus/vssi/
+
+Note that the reference sequence for the surface glycoprotein can be found at:
+
+    https://www.ncbi.nlm.nih.gov/protein/1791269090
+
+As the loaded ProtGPT2 model was pretrained on the
+UniRef50 (version 2021_04) dataset, it cannot have contained sequencing
+data that was generated after that date.  Evaluations will be conducted using
+SARS-CoV-2 sequences generated on or after May 2021.
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- 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: 3.0
+
+### Framework versions
+
+- Transformers 4.26.0.dev0
+- Pytorch 1.11.0
+- Datasets 2.8.0
+- Tokenizers 0.13.2
+

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.88832083168838,
+    "eval_loss": 1.1674294471740723,
+    "eval_runtime": 2701.99,
+    "eval_samples": 17880,
+    "eval_samples_per_second": 6.617,
+    "eval_steps_per_second": 0.414,
+    "perplexity": 3.2137209721788196,
+    "train_loss": 0.6325470058006347,
+    "train_runtime": 19128.0107,
+    "train_samples": 35882,
+    "train_samples_per_second": 5.628,
+    "train_steps_per_second": 0.352
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "nferruz/ProtGPT2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.88832083168838,
+    "eval_loss": 1.1674294471740723,
+    "eval_runtime": 2701.99,
+    "eval_samples": 17880,
+    "eval_samples_per_second": 6.617,
+    "eval_steps_per_second": 0.414,
+    "perplexity": 3.2137209721788196
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c63729d4a9f5aa4a5b4a913f28958e6b98b75b68dcdf52f17328f1a742ab7eb
+size 3134031497

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "nferruz/ProtGPT2",
+  "special_tokens_map_file": "/home/rd389/.cache/huggingface/hub/models--nferruz--ProtGPT2/snapshots/24c0e18bf98bb165c8c745c5d179af1aec2ed0c1/special_tokens_map.json",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.6325470058006347,
+    "train_runtime": 19128.0107,
+    "train_samples": 35882,
+    "train_samples_per_second": 5.628,
+    "train_steps_per_second": 0.352
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 6729,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.25694754049636e-06,
+      "loss": 2.6361,
+      "step": 500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.513895080992719e-06,
+      "loss": 1.8094,
+      "step": 1000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.770842621489078e-06,
+      "loss": 1.1517,
+      "step": 1500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.027790161985437e-06,
+      "loss": 0.6839,
+      "step": 2000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 6.284737702481796e-06,
+      "loss": 0.4235,
+      "step": 2500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.541685242978154e-06,
+      "loss": 0.3156,
+      "step": 3000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.798632783474514e-06,
+      "loss": 0.2609,
+      "step": 3500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.055580323970872e-06,
+      "loss": 0.2301,
+      "step": 4000
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 3.3125278644672313e-06,
+      "loss": 0.2043,
+      "step": 4500
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 2.5694754049635905e-06,
+      "loss": 0.1912,
+      "step": 5000
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.8264229454599496e-06,
+      "loss": 0.1811,
+      "step": 5500
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 1.0833704859563087e-06,
+      "loss": 0.1756,
+      "step": 6000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 3.403180264526676e-07,
+      "loss": 0.1709,
+      "step": 6500
+    },
+    {
+      "epoch": 3.0,
+      "step": 6729,
+      "total_flos": 1.171282836455424e+17,
+      "train_loss": 0.6325470058006347,
+      "train_runtime": 19128.0107,
+      "train_samples_per_second": 5.628,
+      "train_steps_per_second": 0.352
+    }
+  ],
+  "max_steps": 6729,
+  "num_train_epochs": 3,
+  "total_flos": 1.171282836455424e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82b7bc7acc27b5a9e6cfbe5b41cd08a0822f87cd2da530f0cc4beda359278ba
+size 3439