Upload folder using huggingface_hub

Aligned-Lambda_0.5/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": [
+    "BertAdapterAlignModel"
+  ],
+  "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_singlish": {
+      "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
+}

Aligned-Lambda_0.5/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad49aa0e4f9b3cfd7515038c0e0ffd5a6c2c0b1c6386650c04769a669f358fda
+size 816784440

Aligned-Lambda_0.5/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a71e83987c19d9e1cdd96069db239845522e0c987021fdf3cc074312867270
+size 1633695418

Aligned-Lambda_0.5/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e7dbbfe8d2173d3434488d16ebec4dd47b0dc1e96c0309f7c7d32572833ad83
+size 14244

Aligned-Lambda_0.5/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d1adeb5a474175a1cb9c0c1efabaa9fd87343414b2349dd1c68b0a5ef6eb54
+size 1064

Aligned-Lambda_0.5/trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1960,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.4080712099870045,
+      "las": 70.92972501091226,
+      "step": 196,
+      "uas": 80.57616761239633
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.741866283946567,
+      "las": 73.1121780881711,
+      "step": 392,
+      "uas": 82.58402444347446
+    },
+    {
+      "epoch": 2.5510204081632653,
+      "grad_norm": 2.2205545902252197,
+      "learning_rate": 0.00014897959183673472,
+      "loss": 0.6053,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.9176928202311199,
+      "las": 75.07638585770407,
+      "step": 588,
+      "uas": 83.45700567437801
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.9914132754007976,
+      "las": 73.02487996508074,
+      "step": 784,
+      "uas": 82.45307725883893
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.1381421354081898,
+      "las": 73.72326494980358,
+      "step": 980,
+      "uas": 82.49672632038411
+    },
+    {
+      "epoch": 5.1020408163265305,
+      "grad_norm": 1.395138144493103,
+      "learning_rate": 9.79591836734694e-05,
+      "loss": 0.1184,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.532452874713474,
+      "las": 73.41772151898735,
+      "step": 1176,
+      "uas": 81.79834133566129
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.5041761729452343,
+      "las": 74.81449148843299,
+      "step": 1372,
+      "uas": 83.41335661283283
+    },
+    {
+      "epoch": 7.653061224489796,
+      "grad_norm": 1.2384448051452637,
+      "learning_rate": 4.6938775510204086e-05,
+      "loss": 0.042,
+      "step": 1500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.593573318587409,
+      "las": 74.2470536883457,
+      "step": 1568,
+      "uas": 82.58402444347446
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.78382584783766,
+      "las": 74.50894805761676,
+      "step": 1764,
+      "uas": 82.97686599738105
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1960,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 4.315289190137856e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

Aligned-Lambda_0.5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e28ef3b7e513ac93187fd82c8f888f75e4a57edff0be39c8465f1da02a2f2f8
+size 5432