Training in progress, step 2499

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "dtype": "float32",
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ebe17550ed43a1465e14a3c17e0dee3086816e6ae0a64ac30f8e84e495a0b4
+size 46743904

runs/Mar01_07-23-37_b7cf2e31f5e8/events.out.tfevents.1772349817.b7cf2e31f5e8.632.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7df58338f5c3abd6f8b12f843ee4bfd5978530d9eb895398aa852b8b47c33c73
+size 58116

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66ad8e1a578bc9c42ace4755ee4748b11d113be415be57724804ef5b5ae9d0d0
+size 5201