E13 deploy checkpoints (seeds 42, 43) + test metrics

deploy_metrics.json

@@ -0,0 +1,24 @@
+{
+  "seeds": [
+    42,
+    43
+  ],
+  "test_per_seed": [
+    {
+      "spearman": 0.6429902736103762,
+      "accuracy": 0.7623655913978494
+    },
+    {
+      "spearman": 0.6907304832649427,
+      "accuracy": 0.7989247311827957
+    }
+  ],
+  "test_mean": {
+    "spearman": 0.6809442748753467,
+    "accuracy": 0.7795698924731183
+  },
+  "test_mean_rank_blend": {
+    "spearman": 0.7022199696692332,
+    "accuracy": 0.8010752688172043
+  }
+}

model_seed42/config.json

@@ -0,0 +1,35 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "dtype": "float16",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0.0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model_seed42/e13_config.json

@@ -0,0 +1,10 @@
+{
+  "head": "ordinal",
+  "max_len": 256,
+  "mark": true,
+  "example": true,
+  "rank_blend_w": 0.15,
+  "seed": 42,
+  "epochs": 6,
+  "inner_val_rho": 0.6927909344955228
+}

model_seed42/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61ac7177aecf2fc3e45159e56cc9e3e90033c81acae67669487b054177e2e128
+size 868075352

model_seed42/test_pred.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ae9213196ff51a25316ea425bb37868c05a63c328103ba906f04d05b9cd6a3
+size 3848

model_seed42/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": [
+    "[PAD]",
+    "[CLS]",
+    "[SEP]"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_id": 3,
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

model_seed43/config.json

@@ -0,0 +1,35 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "dtype": "float16",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0.0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model_seed43/e13_config.json

@@ -0,0 +1,10 @@
+{
+  "head": "ordinal",
+  "max_len": 256,
+  "mark": true,
+  "example": true,
+  "rank_blend_w": 0.15,
+  "seed": 43,
+  "epochs": 6,
+  "inner_val_rho": 0.6259052696435157
+}

model_seed43/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b221d125fdf748af1fb0501138ae0f1ff47ac2bc9c1bdc03b421b10ac41ae56
+size 868075352

model_seed43/test_pred.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14a7bd841d623d93d927a1945d7809c4b7244084ed85a8dbf2d24fec6b53d91
+size 3848

model_seed43/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": [
+    "[PAD]",
+    "[CLS]",
+    "[SEP]"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_id": 3,
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}