Training in progress, epoch 3

config.json

@@ -1,40 +1,55 @@
 {
-  "_name_or_path": "google-bert/bert-base-multilingual-uncased",
+  "_name_or_path": "answerdotai/ModernBERT-large",
   "architectures": [
-    "BertForSequenceClassification"
+    "ModernBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "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_activation": "gelu",
+  "hidden_size": 1024,
   "id2label": {
     "0": "bad",
     "1": "good"
   },
+  "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 2624,
   "label2id": {
     "bad": "0",
     "good": "1"
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
+  "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": 16,
+  "num_hidden_layers": 28,
+  "pad_token_id": 50283,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
+  "reference_compile": true,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.48.0.dev0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 105879
+  "vocab_size": 50368
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40ad276dc4b01243e18ae1e8327684fd0fd5f26a0b9979ed8845900aca0a50b3
-size 669455360
+oid sha256:95cea7d34180b340ce05f1e3b1dabc9d679d55bd8f319ffb83fabe480ba94000
+size 791684972

runs/Dec31_09-07-31_ai4d-Lambda-Vector/events.out.tfevents.1735625254.ai4d-Lambda-Vector.979901.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14b21d01dbf008485ae32c17c6268fc95f17e6544e39ebd13de530c03107c571
-size 7184
+oid sha256:f65dd2110d970c4b44e3950e2fe31c14534dbad9e4b2b4f7b9c750befa195c67
+size 9400

runs/Dec31_09-17-15_ai4d-Lambda-Vector/events.out.tfevents.1735625838.ai4d-Lambda-Vector.1007012.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f84cb1e9dc7f794cb8318149536060564105e508ed086abd8e17cda24f986689
+size 5812

runs/Dec31_09-19-23_ai4d-Lambda-Vector/events.out.tfevents.1735625964.ai4d-Lambda-Vector.1012242.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dcda7a2a59ddd39b368d6abdb15e9917bc9ec306f46b938b1ba4c8912347ccb
+size 11643

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:586aa086ac31eeb9250177bbf91ba4ab24f8e4a91958c5edb3d8ac41e761872a
+oid sha256:9a4eb7939a836581b014e47ee49ab28fa0fff75265be891193136662e142887a
 size 5432