End of training

en/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": "nice",
+    "inv_adapter_reduction_factor": 2,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 2,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "config_id": "16eaa0b5fae9ed68",
+  "hidden_size": 768,
+  "model_class": "BertForQuestionAnswering",
+  "model_name": "bert-base-multilingual-cased",
+  "model_type": "bert",
+  "name": "en",
+  "version": "3.2.1"
+}

en/head_config.json

@@ -0,0 +1,14 @@
+{
+  "config": null,
+  "hidden_size": 768,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "model_class": "BertForQuestionAnswering",
+  "model_name": "bert-base-multilingual-cased",
+  "model_type": "bert",
+  "name": null,
+  "num_labels": 2,
+  "version": "3.2.1"
+}

en/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:844f0eaa1560cc431be598082ffa0c49b0728a9aabaae40430ee2546371c6891
+size 29571086

en/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62b15e2414187a2fafaaca38a551b2c55a7ac4c820223b9bb6c708380b972b1
+size 7706

id/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": "nice",
+    "inv_adapter_reduction_factor": 2,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "gelu_new",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 2,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "config_id": "c4d39032a237a0ba",
+  "hidden_size": 768,
+  "model_class": "BertForQuestionAnswering",
+  "model_name": "bert-base-multilingual-cased",
+  "model_type": "bert",
+  "name": "id",
+  "version": "3.2.1"
+}

id/head_config.json

@@ -0,0 +1,14 @@
+{
+  "config": null,
+  "hidden_size": 768,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "model_class": "BertForQuestionAnswering",
+  "model_name": "bert-base-multilingual-cased",
+  "model_type": "bert",
+  "name": null,
+  "num_labels": 2,
+  "version": "3.2.1"
+}

id/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:559c41fb8f85892c6bc12a7c18a4d6a8ed95c84cc730a8dfe51e5f630e7d82ba
+size 29571086

id/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62b15e2414187a2fafaaca38a551b2c55a7ac4c820223b9bb6c708380b972b1
+size 7706

mbert_idkmrc/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 16,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "config_id": "9076f36a74755ac4",
+  "hidden_size": 768,
+  "model_class": "BertForQuestionAnswering",
+  "model_name": "bert-base-multilingual-cased",
+  "model_type": "bert",
+  "name": "mbert_idkmrc",
+  "version": "3.2.1"
+}

mbert_idkmrc/head_config.json

@@ -0,0 +1,14 @@
+{
+  "config": null,
+  "hidden_size": 768,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "model_class": "BertForQuestionAnswering",
+  "model_name": "bert-base-multilingual-cased",
+  "model_type": "bert",
+  "name": null,
+  "num_labels": 2,
+  "version": "3.2.1"
+}

mbert_idkmrc/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b240429e5c2ba4aba3b3573a8a6319b5f32e38e605b81a83dc98389556626eb
+size 3595750

mbert_idkmrc/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62b15e2414187a2fafaaca38a551b2c55a7ac4c820223b9bb6c708380b972b1
+size 7706

runs/Nov10_04-23-55_bff0ace4099d/events.out.tfevents.1699590239.bff0ace4099d.305.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44642889ea38c992c30592f268e4f1e811de7f265470dfaa762173228e91b7e3
-size 14875
+oid sha256:3383d37ca06cedd231e801982ca84be791f11336817466eee812312528d2c2e3
+size 15700