Track the model files

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "UBC-NLP/MARBERT",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "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 sha256:54c8f56c27e48fce875735c93c58c1a7d55cc84f80fba6896d1fba3c658e0944
+size 1302854789

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ddff6c9680382a79805f6943edcf72e4d4396132b043845acf1eef4b5874c46
+size 651441269

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fec9362fc57cf2dcfee210342521ec4fed1decbc9f9d913f8a721fc61e88bd4
+size 14639

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf501303f049f96d13ee57ddac5410f72a079229358bfc0084c90a64ba044efe
+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 +1,211 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 9648,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.740878938640133e-05,
+      "loss": 0.044,
+      "step": 500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.4817578772802655e-05,
+      "loss": 0.0377,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "eval_dev_RMSE": 0.18756112476090767,
+      "eval_dev_loss": 0.035179175436496735,
+      "eval_dev_runtime": 132.887,
+      "eval_dev_samples_per_second": 92.259,
+      "eval_dev_steps_per_second": 11.536,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.222636815920398e-05,
+      "loss": 0.0376,
+      "step": 1500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.9635157545605314e-05,
+      "loss": 0.0356,
+      "step": 2000
+    },
+    {
+      "epoch": 0.62,
+      "eval_dev_RMSE": 0.19046555146164063,
+      "eval_dev_loss": 0.03627712279558182,
+      "eval_dev_runtime": 133.0324,
+      "eval_dev_samples_per_second": 92.158,
+      "eval_dev_steps_per_second": 11.524,
+      "step": 2000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.7043946932006634e-05,
+      "loss": 0.0344,
+      "step": 2500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.445273631840796e-05,
+      "loss": 0.0334,
+      "step": 3000
+    },
+    {
+      "epoch": 0.93,
+      "eval_dev_RMSE": 0.1837653706986114,
+      "eval_dev_loss": 0.03376971185207367,
+      "eval_dev_runtime": 133.0551,
+      "eval_dev_samples_per_second": 92.142,
+      "eval_dev_steps_per_second": 11.522,
+      "step": 3000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.1861525704809286e-05,
+      "loss": 0.0263,
+      "step": 3500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 2.9270315091210616e-05,
+      "loss": 0.0201,
+      "step": 4000
+    },
+    {
+      "epoch": 1.24,
+      "eval_dev_RMSE": 0.18422561995605843,
+      "eval_dev_loss": 0.03393908217549324,
+      "eval_dev_runtime": 133.012,
+      "eval_dev_samples_per_second": 92.172,
+      "eval_dev_steps_per_second": 11.525,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.6679104477611942e-05,
+      "loss": 0.0206,
+      "step": 4500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.408789386401327e-05,
+      "loss": 0.0207,
+      "step": 5000
+    },
+    {
+      "epoch": 1.55,
+      "eval_dev_RMSE": 0.17716465270016277,
+      "eval_dev_loss": 0.031387314200401306,
+      "eval_dev_runtime": 132.975,
+      "eval_dev_samples_per_second": 92.198,
+      "eval_dev_steps_per_second": 11.528,
+      "step": 5000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.1496683250414595e-05,
+      "loss": 0.0216,
+      "step": 5500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.890547263681592e-05,
+      "loss": 0.0209,
+      "step": 6000
+    },
+    {
+      "epoch": 1.87,
+      "eval_dev_RMSE": 0.174460176191386,
+      "eval_dev_loss": 0.030436350032687187,
+      "eval_dev_runtime": 132.9619,
+      "eval_dev_samples_per_second": 92.207,
+      "eval_dev_steps_per_second": 11.53,
+      "step": 6000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.6314262023217248e-05,
+      "loss": 0.0188,
+      "step": 6500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.3723051409618576e-05,
+      "loss": 0.0111,
+      "step": 7000
+    },
+    {
+      "epoch": 2.18,
+      "eval_dev_RMSE": 0.18001000469726128,
+      "eval_dev_loss": 0.032403603196144104,
+      "eval_dev_runtime": 133.072,
+      "eval_dev_samples_per_second": 92.131,
+      "eval_dev_steps_per_second": 11.52,
+      "step": 7000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.1131840796019902e-05,
+      "loss": 0.0117,
+      "step": 7500
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 8.540630182421228e-06,
+      "loss": 0.0113,
+      "step": 8000
+    },
+    {
+      "epoch": 2.49,
+      "eval_dev_RMSE": 0.18047865859291073,
+      "eval_dev_loss": 0.03257254138588905,
+      "eval_dev_runtime": 132.9865,
+      "eval_dev_samples_per_second": 92.19,
+      "eval_dev_steps_per_second": 11.527,
+      "step": 8000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 5.9494195688225545e-06,
+      "loss": 0.0104,
+      "step": 8500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.358208955223881e-06,
+      "loss": 0.0109,
+      "step": 9000
+    },
+    {
+      "epoch": 2.8,
+      "eval_dev_RMSE": 0.177416393937498,
+      "eval_dev_loss": 0.03147657588124275,
+      "eval_dev_runtime": 133.0425,
+      "eval_dev_samples_per_second": 92.151,
+      "eval_dev_steps_per_second": 11.523,
+      "step": 9000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 7.669983416252073e-07,
+      "loss": 0.0111,
+      "step": 9500
+    }
+  ],
+  "max_steps": 9648,
+  "num_train_epochs": 3,
+  "total_flos": 8.121060296152474e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40cfd843c416ec9c00e520d86ae666cba0a4f454166084558a0fdafafc46857
+size 3515