Upload folder using huggingface_hub

Generalize/UD_English-EWT-UD_North_Sami-Giella/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "total_flos": 8.698923198185472e+16,
+    "train_loss": 267.11919642857146,
+    "train_runtime": 7699.2593,
+    "train_samples_per_second": 65.17,
+    "train_steps_per_second": 1.018
+}

Generalize/UD_English-EWT-UD_North_Sami-Giella/config.json

@@ -0,0 +1,187 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "adapters": {
+    "adapters": {},
+    "config_map": {},
+    "fusion_config_map": {},
+    "fusion_name_map": {},
+    "fusions": {}
+  },
+  "architectures": [
+    "BertAdapterGeneralizeModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "_",
+    "1": "acl",
+    "2": "advcl",
+    "3": "advmod",
+    "4": "amod",
+    "5": "appos",
+    "6": "aux",
+    "7": "case",
+    "8": "cc",
+    "9": "ccomp",
+    "10": "clf",
+    "11": "compound",
+    "12": "conj",
+    "13": "cop",
+    "14": "csubj",
+    "15": "dep",
+    "16": "det",
+    "17": "discourse",
+    "18": "dislocated",
+    "19": "expl",
+    "20": "fixed",
+    "21": "flat",
+    "22": "goeswith",
+    "23": "iobj",
+    "24": "list",
+    "25": "mark",
+    "26": "nmod",
+    "27": "nsubj",
+    "28": "nummod",
+    "29": "obj",
+    "30": "obl",
+    "31": "orphan",
+    "32": "parataxis",
+    "33": "punct",
+    "34": "reparandum",
+    "35": "root",
+    "36": "vocative",
+    "37": "xcomp",
+    "38": "dup",
+    "39": "mwe",
+    "40": "name",
+    "41": "remnant"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "_": 0,
+    "acl": 1,
+    "advcl": 2,
+    "advmod": 3,
+    "amod": 4,
+    "appos": 5,
+    "aux": 6,
+    "case": 7,
+    "cc": 8,
+    "ccomp": 9,
+    "clf": 10,
+    "compound": 11,
+    "conj": 12,
+    "cop": 13,
+    "csubj": 14,
+    "dep": 15,
+    "det": 16,
+    "discourse": 17,
+    "dislocated": 18,
+    "dup": 38,
+    "expl": 19,
+    "fixed": 20,
+    "flat": 21,
+    "goeswith": 22,
+    "iobj": 23,
+    "list": 24,
+    "mark": 25,
+    "mwe": 39,
+    "name": 40,
+    "nmod": 26,
+    "nsubj": 27,
+    "nummod": 28,
+    "obj": 29,
+    "obl": 30,
+    "orphan": 31,
+    "parataxis": 32,
+    "punct": 33,
+    "remnant": 41,
+    "reparandum": 34,
+    "root": 35,
+    "vocative": 36,
+    "xcomp": 37
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "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": {
+      "activation_function": "gelu",
+      "bias": true,
+      "embedding_size": 768,
+      "head_type": "masked_lm",
+      "label2id": null,
+      "layer_norm": true,
+      "layers": 2,
+      "shift_labels": false,
+      "vocab_size": 119547
+    },
+    "ud_North_Sami-Giella": {
+      "head_type": "dependency_parsing",
+      "label2id": {
+        "_": 0,
+        "acl": 1,
+        "advcl": 2,
+        "advmod": 3,
+        "amod": 4,
+        "appos": 5,
+        "aux": 6,
+        "case": 7,
+        "cc": 8,
+        "ccomp": 9,
+        "clf": 10,
+        "compound": 11,
+        "conj": 12,
+        "cop": 13,
+        "csubj": 14,
+        "dep": 15,
+        "det": 16,
+        "discourse": 17,
+        "dislocated": 18,
+        "dup": 38,
+        "expl": 19,
+        "fixed": 20,
+        "flat": 21,
+        "goeswith": 22,
+        "iobj": 23,
+        "list": 24,
+        "mark": 25,
+        "mwe": 39,
+        "name": 40,
+        "nmod": 26,
+        "nsubj": 27,
+        "nummod": 28,
+        "obj": 29,
+        "obl": 30,
+        "orphan": 31,
+        "parataxis": 32,
+        "punct": 33,
+        "remnant": 41,
+        "reparandum": 34,
+        "root": 35,
+        "vocative": 36,
+        "xcomp": 37
+      },
+      "num_labels": 42
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

Generalize/UD_English-EWT-UD_North_Sami-Giella/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d214bc600ef35e8abf7f02f18dc2f032c410db107787d267945400e1c45794f
+size 820332780

Generalize/UD_English-EWT-UD_North_Sami-Giella/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "total_flos": 8.698923198185472e+16,
+    "train_loss": 267.11919642857146,
+    "train_runtime": 7699.2593,
+    "train_samples_per_second": 65.17,
+    "train_steps_per_second": 1.018
+}

Generalize/UD_English-EWT-UD_North_Sami-Giella/trainer_state.json

@@ -0,0 +1,287 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 500,
+  "global_step": 7840,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.0891998464908075,
+      "las": 54.8824494259158,
+      "step": 392,
+      "uas": 66.30945872061235
+    },
+    {
+      "epoch": 1.2755102040816326,
+      "grad_norm": 13.828027725219727,
+      "learning_rate": 0.00018724489795918367,
+      "loss": 274.3555,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.269648735676337,
+      "las": 60.42646254784035,
+      "step": 784,
+      "uas": 69.72115910333515
+    },
+    {
+      "epoch": 2.5510204081632653,
+      "grad_norm": 5.014928817749023,
+      "learning_rate": 0.00017448979591836735,
+      "loss": 270.0787,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.225621202670106,
+      "las": 61.979223619464186,
+      "step": 1176,
+      "uas": 70.06014215418261
+    },
+    {
+      "epoch": 3.826530612244898,
+      "grad_norm": 4.364072322845459,
+      "learning_rate": 0.00016173469387755103,
+      "loss": 267.9641,
+      "step": 1500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.3704753406004073,
+      "las": 63.31328594860579,
+      "step": 1568,
+      "uas": 70.91306724986332
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.739554310063703,
+      "las": 64.27556041552761,
+      "step": 1960,
+      "uas": 72.5095680699836
+    },
+    {
+      "epoch": 5.1020408163265305,
+      "grad_norm": 3.1612472534179688,
+      "learning_rate": 0.00014897959183673472,
+      "loss": 267.1271,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.6826005914342512,
+      "las": 65.18316019682887,
+      "step": 2352,
+      "uas": 72.64078731547293
+    },
+    {
+      "epoch": 6.377551020408164,
+      "grad_norm": 4.340851783752441,
+      "learning_rate": 0.00013622448979591837,
+      "loss": 266.02,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.6943095577966183,
+      "las": 64.78950246036085,
+      "step": 2744,
+      "uas": 72.5205030071077
+    },
+    {
+      "epoch": 7.653061224489796,
+      "grad_norm": 2.736152172088623,
+      "learning_rate": 0.00012346938775510203,
+      "loss": 265.9112,
+      "step": 3000
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.8967232832668026,
+      "las": 65.3143794423182,
+      "step": 3136,
+      "uas": 72.53143794423183
+    },
+    {
+      "epoch": 8.928571428571429,
+      "grad_norm": 2.274150848388672,
+      "learning_rate": 0.00011071428571428572,
+      "loss": 267.0213,
+      "step": 3500
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.8108423364545225,
+      "las": 64.99726626571896,
+      "step": 3528,
+      "uas": 72.69546200109349
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 3.0773769026502555,
+      "las": 65.87206123564789,
+      "step": 3920,
+      "uas": 73.19846910880263
+    },
+    {
+      "epoch": 10.204081632653061,
+      "grad_norm": 1.2913435697555542,
+      "learning_rate": 9.79591836734694e-05,
+      "loss": 266.0448,
+      "step": 4000
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 3.4559491924736476,
+      "las": 66.10169491525424,
+      "step": 4312,
+      "uas": 73.47184253690541
+    },
+    {
+      "epoch": 11.479591836734693,
+      "grad_norm": 1.8192548751831055,
+      "learning_rate": 8.520408163265306e-05,
+      "loss": 265.7753,
+      "step": 4500
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 3.5783781436605193,
+      "las": 66.22197922361947,
+      "step": 4704,
+      "uas": 73.25314379442318
+    },
+    {
+      "epoch": 12.755102040816327,
+      "grad_norm": 2.150754451751709,
+      "learning_rate": 7.244897959183675e-05,
+      "loss": 265.7788,
+      "step": 5000
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 3.742621369318131,
+      "las": 66.76872607982503,
+      "step": 5096,
+      "uas": 73.69054127938765
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 3.6111698169773874,
+      "las": 67.07490431930016,
+      "step": 5488,
+      "uas": 73.98578458173866
+    },
+    {
+      "epoch": 14.03061224489796,
+      "grad_norm": 2.424419641494751,
+      "learning_rate": 5.9693877551020416e-05,
+      "loss": 266.4652,
+      "step": 5500
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 3.558833001950465,
+      "las": 67.08583925642428,
+      "step": 5880,
+      "uas": 74.07326407873155
+    },
+    {
+      "epoch": 15.306122448979592,
+      "grad_norm": 1.3744462728500366,
+      "learning_rate": 4.6938775510204086e-05,
+      "loss": 267.6873,
+      "step": 6000
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 3.7869238930011013,
+      "las": 67.72006560962275,
+      "step": 6272,
+      "uas": 74.46692181519956
+    },
+    {
+      "epoch": 16.581632653061224,
+      "grad_norm": 1.3328207731246948,
+      "learning_rate": 3.4183673469387755e-05,
+      "loss": 265.5007,
+      "step": 6500
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 4.237295362380666,
+      "las": 67.74193548387096,
+      "step": 6664,
+      "uas": 74.72936030617824
+    },
+    {
+      "epoch": 17.857142857142858,
+      "grad_norm": 0.5128316879272461,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 265.6779,
+      "step": 7000
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 4.247772007360371,
+      "las": 68.0590486604702,
+      "step": 7056,
+      "uas": 74.83870967741936
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 4.358184982877259,
+      "las": 68.37616183706943,
+      "step": 7448,
+      "uas": 74.99179879715692
+    },
+    {
+      "epoch": 19.132653061224488,
+      "grad_norm": 0.30317503213882446,
+      "learning_rate": 8.673469387755103e-06,
+      "loss": 266.1403,
+      "step": 7500
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 4.434211952423831,
+      "las": 68.40896664844178,
+      "step": 7840,
+      "uas": 75.0683433570257
+    },
+    {
+      "epoch": 20.0,
+      "step": 7840,
+      "total_flos": 8.698923198185472e+16,
+      "train_loss": 267.11919642857146,
+      "train_runtime": 7699.2593,
+      "train_samples_per_second": 65.17,
+      "train_steps_per_second": 1.018
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.698923198185472e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

Generalize/UD_English-EWT-UD_North_Sami-Giella/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344a0f3cc8c7f95e92e9f1dc19081eab7849a26d31dcd1df5bef804eddd6cbfe
+size 5432