Training in progress, step 10

config.json

@@ -1,20 +1,20 @@
 {
-  "_name_or_path": "facebook/esm2_t6_8M_UR50D",
+  "_name_or_path": "mgh6/TCS_MLM",
   "architectures": [
     "EsmForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.0,
-  "classifier_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.01,
+  "classifier_dropout": 0.1,
   "emb_layer_norm_before": false,
   "esmfold_config": null,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 320,
+  "hidden_dropout_prob": 0.01,
+  "hidden_size": 480,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1280,
+  "intermediate_size": 1920,
   "is_folding_model": false,
   "label2id": {
     "LABEL_0": 0
@@ -24,7 +24,7 @@
   "max_position_embeddings": 1026,
   "model_type": "esm",
   "num_attention_heads": 20,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "rotary",
   "problem_type": "regression",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67afb08fa3fa42d52d1e501b87386dc7a8d586c77c53b999d1197f3c9c312eec
-size 31374504
+oid sha256:6d539ebb152a9de4cebfc6ee975fc55f34e811c4e37b5439f4bd3ef7add29015
+size 135998360

runs/Oct15_05-26-00_torch-flash-large-0-2/events.out.tfevents.1728969962.torch-flash-large-0-2.9099.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0aec7d5ec24634098794ce4e5dea181845f040d27a08eaa86211c22053c6095
+size 5565

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f29bf9205718973acbf377cbfa261e70052b9ce01e722c91d3ab928c4f8167b
+oid sha256:817f147e7811e03bf49492ad2d0a235905c796ad46b255e92f7cb610efc94f8c
 size 5240