Upload 11 files

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "bert-base-multilingual-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Description",
+    "1": "Immediate Correction",
+    "2": "Root Cause",
+    "3": "Action Plan",
+    "4": "Impacted Elements"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Action Plan": 3,
+    "Description": 0,
+    "Immediate Correction": 1,
+    "Impacted Elements": 4,
+    "Root Cause": 2
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db1af060840b95665333f30940ee208d514a4f19c3fc1b96398f2c223fea8dc
+size 669464588

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ca26c08eece585cd728cbfebd4cd49b8db96143654cc4f1c179ddec76e40cd1
+size 1339044602

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3652934cda515cb3e43dc51083a5b8b2fc854e79a1f7ebe753080ac19f5664b0
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d29115f2a720b98298e75a5cef464fbbdf33676214194ab640f943a6eb2704
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": 0.5764515399932861,
+  "best_model_checkpoint": "my_awesome_model/checkpoint-510",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 918,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6685082872928176,
+      "eval_loss": 0.8615816235542297,
+      "eval_runtime": 1.994,
+      "eval_samples_per_second": 90.773,
+      "eval_steps_per_second": 6.018,
+      "step": 102
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8066298342541437,
+      "eval_loss": 0.6153411269187927,
+      "eval_runtime": 1.8412,
+      "eval_samples_per_second": 98.303,
+      "eval_steps_per_second": 6.517,
+      "step": 204
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8287292817679558,
+      "eval_loss": 0.6224671006202698,
+      "eval_runtime": 2.4099,
+      "eval_samples_per_second": 75.105,
+      "eval_steps_per_second": 4.979,
+      "step": 306
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8342541436464088,
+      "eval_loss": 0.6203207969665527,
+      "eval_runtime": 2.2713,
+      "eval_samples_per_second": 79.691,
+      "eval_steps_per_second": 5.283,
+      "step": 408
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 2.156015634536743,
+      "learning_rate": 1.5098039215686276e-05,
+      "loss": 0.5475,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.850828729281768,
+      "eval_loss": 0.5764515399932861,
+      "eval_runtime": 2.1191,
+      "eval_samples_per_second": 85.413,
+      "eval_steps_per_second": 5.663,
+      "step": 510
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.861878453038674,
+      "eval_loss": 0.5947481393814087,
+      "eval_runtime": 2.0161,
+      "eval_samples_per_second": 89.776,
+      "eval_steps_per_second": 5.952,
+      "step": 612
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8674033149171271,
+      "eval_loss": 0.6233269572257996,
+      "eval_runtime": 2.2366,
+      "eval_samples_per_second": 80.928,
+      "eval_steps_per_second": 5.365,
+      "step": 714
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8729281767955801,
+      "eval_loss": 0.6563280820846558,
+      "eval_runtime": 2.1333,
+      "eval_samples_per_second": 84.846,
+      "eval_steps_per_second": 5.625,
+      "step": 816
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8784530386740331,
+      "eval_loss": 0.7191643714904785,
+      "eval_runtime": 2.1691,
+      "eval_samples_per_second": 83.444,
+      "eval_steps_per_second": 5.532,
+      "step": 918
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2040,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1548260124430500.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978506d8c5ea6a3d9a490ed6436c56800ffae0a55401f5e2273c1491471af00a
+size 5176