Training in progress, epoch 1

config.json

@@ -1,35 +1,55 @@
 {
-  "_name_or_path": "google-bert/bert-base-uncased",
+  "_name_or_path": "answerdotai/ModernBERT-base",
   "architectures": [
-    "BertForSequenceClassification"
+    "ModernBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_activation": "gelu",
   "hidden_size": 768,
   "id2label": {
     "0": "small_llm",
     "1": "large_llm"
   },
+  "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1152,
   "label2id": {
     "large_llm": "1",
     "small_llm": "0"
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "reference_compile": true,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
   "torch_dtype": "float32",
   "transformers_version": "4.48.0.dev0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 50368
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d3528a3b74cbc73f8babcccaa6db84cfe6b8a59b11ba24a427365207d85843d
-size 437958648
+oid sha256:446cb91f9ec552d72c46a0f13ec9e4c918b247bf6e41f02108511c590479f0c6
+size 598439784

runs/Dec25_08-20-14_ip-172-31-34-75/events.out.tfevents.1735114818.ip-172-31-34-75.12605.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67802a0f1aed3c63baf54336532da088104a2c09786392f65e2d672c8bda74a7
+size 5820

runs/Dec25_08-23-03_ip-172-31-34-75/events.out.tfevents.1735114984.ip-172-31-34-75.14321.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8a58533d3a4e71a91e9071dad6c8b48aec1eb510fb619a9caa43e1eb382f40
+size 5820

runs/Dec25_08-28-22_ip-172-31-34-75/events.out.tfevents.1735115312.ip-172-31-34-75.14616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a7587412e620d3800a4aafa3dff2fa8c860e9f20eaccfd46afd3d62850efb75
+size 6969

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a64e53f28915c2132d46140cb7854d311cdf2e60f59818255c1b166bd80b4ebe
-size 5432
+oid sha256:215b240a700dda3533f8d4b572ab599fb9ebab1126ec87ec3389c5b3058f64d7
+size 5368