Track the model's files

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "UBC-NLP/MARBERT",
+  "architectures": [
+    "CustomBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761f633a0302b31bd7d13ec3751a886f2b77890bb5a57e37c1fab5b1cb2ec13f
+size 1302959429

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3989e47242497fe72ed4d7d4eb3e4e844748ffa0503f55aaec70c641ad29142
+size 651489137

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48da22cc15fdfee75f9603ad88fee44d89afeb069a4d2ac2b8c88eeb682b3093
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa988053a6c5e04bc00463df8c22cd4c1df63ae90765804239310631a7df05c
+size 627

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/project/6007993/elmadany/Models/MARBERT_17M/pytorch_verison/"}

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 2.2883481979370117,
+  "best_model_checkpoint": "models/basic_NADI2023/checkpoint-1689",
+  "epoch": 3.0,
+  "global_step": 1689,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.5198342214328006e-05,
+      "loss": 2.425,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_NADI2023_dev_loss": 2.349003314971924,
+      "eval_NADI2023_dev_runtime": 3.2106,
+      "eval_NADI2023_dev_samples_per_second": 560.648,
+      "eval_NADI2023_dev_steps_per_second": 70.081,
+      "step": 563
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.039668442865601e-05,
+      "loss": 2.2599,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_NADI2023_dev_loss": 2.310096502304077,
+      "eval_NADI2023_dev_runtime": 3.2198,
+      "eval_NADI2023_dev_samples_per_second": 559.041,
+      "eval_NADI2023_dev_steps_per_second": 69.88,
+      "step": 1126
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 5.595026642984015e-06,
+      "loss": 2.1854,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_NADI2023_dev_loss": 2.2883481979370117,
+      "eval_NADI2023_dev_runtime": 3.2189,
+      "eval_NADI2023_dev_samples_per_second": 559.191,
+      "eval_NADI2023_dev_steps_per_second": 69.899,
+      "step": 1689
+    }
+  ],
+  "max_steps": 1689,
+  "num_train_epochs": 3,
+  "total_flos": 2275826410512000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8ee8eb527f8e50690e8f36729b9ebbabc25849d3854b447a40efbe2f77f24a
+size 4027