Upload 12 files

added_tokens.json

@@ -0,0 +1 @@
+{"[TGT]": 30000}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "emanjavacas/MacBERTh",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30001
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303d966ae523b7ce5bc505a2bdfb8325e5d9db8d9ebdaf211bac45e610050892
+size 872804125

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d8fb4618d2809f192a969e29c2cfd3888784325a163e5512d2e9c7471b45ff
+size 436427949

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8428d03558b10006b981876d2b12cff1bc8d7b34472b3934ceaf92364ec70dc8
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b918da4fc3cbae9fddacc2c9f670190e23bf5af81a10ace564c01ef0a89855
+size 623

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "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, "name_or_path": "emanjavacas/MacBERTh", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": 0.04861336573958397,
+  "best_model_checkpoint": "/home/manjavacasema/data1/ing-forms/results-ing-single/checkpoint-1266",
+  "epoch": 5.0,
+  "global_step": 3165,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.907582938388626e-05,
+      "loss": 0.2536,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.08746412396430969,
+      "eval_runtime": 2.5343,
+      "eval_samples_per_second": 221.758,
+      "eval_steps_per_second": 28.016,
+      "step": 633
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 3.315165876777251e-05,
+      "loss": 0.0895,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.04861336573958397,
+      "eval_runtime": 2.5502,
+      "eval_samples_per_second": 220.371,
+      "eval_steps_per_second": 27.84,
+      "step": 1266
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.722748815165877e-05,
+      "loss": 0.0324,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.06070622429251671,
+      "eval_runtime": 2.5516,
+      "eval_samples_per_second": 220.251,
+      "eval_steps_per_second": 27.825,
+      "step": 1899
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 2.1303317535545027e-05,
+      "loss": 0.0173,
+      "step": 2000
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 1.537914691943128e-05,
+      "loss": 0.0076,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.09658198803663254,
+      "eval_runtime": 2.5515,
+      "eval_samples_per_second": 220.262,
+      "eval_steps_per_second": 27.827,
+      "step": 2532
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 9.454976303317536e-06,
+      "loss": 0.0044,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.05032559856772423,
+      "eval_runtime": 2.5533,
+      "eval_samples_per_second": 220.103,
+      "eval_steps_per_second": 27.807,
+      "step": 3165
+    }
+  ],
+  "max_steps": 3798,
+  "num_train_epochs": 6,
+  "total_flos": 2464245296909520.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb2a4ce1f581f374f17e3a4631e9341e82901a09274f6bbdabb9bc9cdd5d8fb
+size 3119