Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/esm2_t30_150M_UR50D",
+  "_name_or_path": "facebook/esm2_t12_35M_UR50D",
   "architectures": [
     "EsmForSequenceClassification"
   ],
@@ -9,7 +9,7 @@
   "esmfold_config": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 640,
+  "hidden_size": 480,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -17,7 +17,7 @@
     "3": "LABEL_3"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 2560,
+  "intermediate_size": 1920,
   "is_folding_model": false,
   "label2id": {
     "LABEL_0": 0,
@@ -30,13 +30,13 @@
   "max_position_embeddings": 1026,
   "model_type": "esm",
   "num_attention_heads": 20,
-  "num_hidden_layers": 30,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "rotary",
   "problem_type": "single_label_classification",
   "token_dropout": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2",
+  "transformers_version": "4.33.3",
   "use_cache": true,
   "vocab_list": null,
   "vocab_size": 33

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889c14d72153bf35a803bfbb7cf7c7f360036f55f331cd107b634cfd45f3bbce
-size 595371117
+oid sha256:ffe46ef89b6113c431e1902b06454efd423bf79ead57bb91ff74f3c5d4ced849
+size 136051621

tokenizer_config.json

@@ -1,5 +1,5 @@
 {
   "clean_up_tokenization_spaces": true,
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 1024,
   "tokenizer_class": "EsmTokenizer"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1bfb665cdb09d36d5f63d351420f8d4c27e472c8120f4515dface8f9208b28
+oid sha256:55b056cd591b7d7685a6cae8251485327650139936b6d6594177e5ed61cd133d
 size 4091