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": "XLMRobertaForQuestionAnswering",
+  "model_name": "xlm-roberta-base",
+  "model_type": "xlm-roberta",
+  "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": "XLMRobertaForQuestionAnswering",
+  "model_name": "xlm-roberta-base",
+  "model_type": "xlm-roberta",
+  "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 sha256:4b17a46ba80383402c76f13963a4358b31a3414685dab86f67855c1526fe5229
+size 29571214

en/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe856d97bfbd4c99cd6cd98c002c551ac99bf42809129422582ef2bc299dfc4
+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": "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": "XLMRobertaForQuestionAnswering",
+  "model_name": "xlm-roberta-base",
+  "model_type": "xlm-roberta",
+  "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": "XLMRobertaForQuestionAnswering",
+  "model_name": "xlm-roberta-base",
+  "model_type": "xlm-roberta",
+  "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 sha256:5660cec9f38fd65854266b43f2f03e854a232f55bb1ed63d5f5b5dac2157eee0
+size 29571214

id/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe856d97bfbd4c99cd6cd98c002c551ac99bf42809129422582ef2bc299dfc4
+size 7706

runs/Nov10_01-59-05_4bb77c5415eb/events.out.tfevents.1699581553.4bb77c5415eb.2998.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30c444b256ede53f7020bbc3876efb88e7aa7806246d33bb5707149f9383f6e8
-size 30233
+oid sha256:f8e90a56ed843b24e9e762e765f9e55c1cf059426eb904985ff6cb2488a415e0
+size 30901

xlmr_squadv2/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": "XLMRobertaForQuestionAnswering",
+  "model_name": "xlm-roberta-base",
+  "model_type": "xlm-roberta",
+  "name": "xlmr_squadv2",
+  "version": "3.2.1"
+}

xlmr_squadv2/head_config.json

@@ -0,0 +1,14 @@
+{
+  "config": null,
+  "hidden_size": 768,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "model_class": "XLMRobertaForQuestionAnswering",
+  "model_name": "xlm-roberta-base",
+  "model_type": "xlm-roberta",
+  "name": null,
+  "num_labels": 2,
+  "version": "3.2.1"
+}

xlmr_squadv2/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647b53593cf642ea3e3da9ff02da2060f2f021b42f8ea3ef2b5d0dbd8d0727b5
+size 3595942

xlmr_squadv2/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe856d97bfbd4c99cd6cd98c002c551ac99bf42809129422582ef2bc299dfc4
+size 7706