Track the model files

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "UBC-NLP/MARBERT",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "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": "4.26.1",
+  "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:f2059e171b8ca906f726d479158ee4f07b65da57fdc9c29aaf26100d1d2ae122
+size 1298159621

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91bf355a8399a307cd076db691b31d1a372fc086273e419228901f1c397f683a
+size 649093613

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f113467ba153437377d3cca21247a1bf13d5ec4199ee15a4ce0dbae7ce2c1608
+size 17641

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a0fbb9478949421cddae7297acf773062e367b83de55aa1d3cf8ac35dd5ed9
+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 +1,78 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 795,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.38,
+      "eval_loss": 0.2512435019016266,
+      "eval_runtime": 8.34,
+      "eval_samples_per_second": 133.813,
+      "eval_steps_per_second": 4.197,
+      "step": 100
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.2268657237291336,
+      "eval_runtime": 8.3466,
+      "eval_samples_per_second": 133.707,
+      "eval_steps_per_second": 4.193,
+      "step": 200
+    },
+    {
+      "epoch": 1.13,
+      "eval_loss": 0.23051245510578156,
+      "eval_runtime": 8.3417,
+      "eval_samples_per_second": 133.786,
+      "eval_steps_per_second": 4.196,
+      "step": 300
+    },
+    {
+      "epoch": 1.51,
+      "eval_loss": 0.2245202660560608,
+      "eval_runtime": 8.337,
+      "eval_samples_per_second": 133.862,
+      "eval_steps_per_second": 4.198,
+      "step": 400
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.8553459119496856e-05,
+      "loss": 0.2119,
+      "step": 500
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 0.22478941082954407,
+      "eval_runtime": 8.3391,
+      "eval_samples_per_second": 133.828,
+      "eval_steps_per_second": 4.197,
+      "step": 500
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 0.2384825348854065,
+      "eval_runtime": 8.3396,
+      "eval_samples_per_second": 133.819,
+      "eval_steps_per_second": 4.197,
+      "step": 600
+    },
+    {
+      "epoch": 2.64,
+      "eval_loss": 0.23830106854438782,
+      "eval_runtime": 8.3367,
+      "eval_samples_per_second": 133.866,
+      "eval_steps_per_second": 4.198,
+      "step": 700
+    }
+  ],
+  "max_steps": 795,
+  "num_train_epochs": 3,
+  "total_flos": 6635087188033536.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:016e178b54b4499d7401b710ae361f0d803cad1f54a717ede8cfa3bf9199ee13
+size 3515