Add augmented BERT

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2a92240bad1c7fb9befbf021a62fad5feb1e2a3990d53a28d160a39bb1cac7b
+size 1112208084

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10419e94a765ca488575093ca0e4f7c4deb4dd1e16e0b9abb34f9ffe4ce896e
+size 2224535738

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c65c8debb1ebe2735825b8fe600f5c48a6b955c168b67c3324ddca054a6efc6
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:709e48b007a54c8e682d10b10c4e5282922aee30a9e7dc3f9c878f0e56436182
+size 1064

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.9109132885932922,
+  "best_model_checkpoint": "bert-combined/checkpoint-1500",
+  "epoch": 1.1029411764705883,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36764705882352944,
+      "grad_norm": 3.704710006713867,
+      "learning_rate": 9.080882352941177e-06,
+      "loss": 0.9954,
+      "step": 500
+    },
+    {
+      "epoch": 0.36764705882352944,
+      "eval_accuracy": 0.5526893523600439,
+      "eval_loss": 0.9458832144737244,
+      "eval_runtime": 39.4256,
+      "eval_samples_per_second": 92.427,
+      "eval_steps_per_second": 2.892,
+      "step": 500
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "grad_norm": 5.2961835861206055,
+      "learning_rate": 8.161764705882354e-06,
+      "loss": 0.9644,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "eval_accuracy": 0.5760153677277717,
+      "eval_loss": 0.9222443699836731,
+      "eval_runtime": 39.4362,
+      "eval_samples_per_second": 92.402,
+      "eval_steps_per_second": 2.891,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1029411764705883,
+      "grad_norm": 7.299610614776611,
+      "learning_rate": 7.24264705882353e-06,
+      "loss": 0.951,
+      "step": 1500
+    },
+    {
+      "epoch": 1.1029411764705883,
+      "eval_accuracy": 0.5927552140504939,
+      "eval_loss": 0.9109132885932922,
+      "eval_runtime": 40.7062,
+      "eval_samples_per_second": 89.519,
+      "eval_steps_per_second": 2.801,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5440,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1.1886933874968432e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cec2760b2c92b3f867e3b123b32141b736c60fd4df2722a6c0aa2c9780a182fb
+size 4984