Upload folder using huggingface_hub

UD_English-EWT/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "bert-base-multilingual-cased",
+  "_name_or_path": "xlm-roberta-base",
   "adapters": {
     "adapters": {},
     "config_map": {},
@@ -8,11 +8,12 @@
     "fusions": {}
   },
   "architectures": [
-    "BertAdapterModel"
+    "XLMRobertaAdapterModel"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "directionality": "bidi",
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -106,17 +107,13 @@
     "vocative": 36,
     "xcomp": 37
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
+  "output_past": true,
   "pad_token_id": -1,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "prediction_heads": {
     "default": {
@@ -128,7 +125,7 @@
       "layer_norm": true,
       "layers": 2,
       "shift_labels": false,
-      "vocab_size": 119547
+      "vocab_size": 250002
     },
     "ud_UD_English-EWT": {
       "head_type": "dependency_parsing",
@@ -181,7 +178,7 @@
   },
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 119547
+  "vocab_size": 250002
 }

UD_English-EWT/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72ec06c21166f029da5b02c649c27bfc33cb757d3191ce240434bcf663afd350
-size 815995556
+oid sha256:4f19b14ce7a3371db8bb3bfb107904d19c83374b3f6b7e02a10a1774968485d6
+size 1217279040

UD_English-EWT/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddfe22ad1fdf8c284588a548048b8dcfae9fefd285e1d2149c648f5f0e71595d
-size 1632115130
+oid sha256:fd638c5dcd3d84d0357114b75398d0c563543286e672d9143d2e7401b104d93f
+size 2434680506

UD_English-EWT/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318e9c3d0f08aee56211408354272de367b86cfa59039ef95f34a2492203921e
+oid sha256:158cac9ee55d327b0b16f27e590bb67852f21d1bbb6885543a4bf8b0525f54cb
 size 14244

UD_English-EWT/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff13e8b65c0e6da1ed6e58b28e262db591ac75fc1eb083dac3a0bf96640bbb3a
+oid sha256:b5d476c12da381846e3dd23747ce593bb7d9068ba7200583b801a8ee542adb9c
 size 1064

UD_English-EWT/trainer_state.json

@@ -1,33 +1,47 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5510204081632653,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 980,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.559650621761287,
-      "las": 86.17440057258739,
+      "eval_loss": 0.6601235683238695,
+      "las": 84.1703447453179,
       "step": 196,
-      "uas": 89.10095828859994
+      "uas": 87.77684997415403
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5288873102464196,
-      "las": 87.89216271024692,
+      "eval_loss": 0.6943420922708889,
+      "las": 85.18430156268639,
       "step": 392,
-      "uas": 90.58014235158456
+      "uas": 88.57608652431507
     },
     {
       "epoch": 2.5510204081632653,
-      "grad_norm": 4.740634441375732,
+      "grad_norm": 10.005887031555176,
       "learning_rate": 9.79591836734694e-05,
-      "loss": 0.6275,
+      "loss": 0.8481,
       "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.542496694828428,
+      "las": 88.15459859238935,
+      "step": 588,
+      "uas": 91.02151178973318
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5330029517589581,
+      "las": 88.73513857409837,
+      "step": 784,
+      "uas": 91.52650204779515
     }
   ],
   "logging_steps": 500,
@@ -42,12 +56,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5494506504192000.0,
+  "total_flos": 1.078180051156992e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null

UD_English-EWT/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4e83cf0cfb6fc9ab8de20143e6c6325b21f1ea7c67e92a0a9c44f68e5e18cc7
+oid sha256:7bbfa0b662d2f2a575d8e0fe7d3a40efcea245c8cd2a4bd8807e3916cd3d86ea
 size 5432