Trained for four epochs on enron

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,29 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.25.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772f485bfa964ceaca9eee3c04b706c7b8b5d39e1fafd80158a71abaf7a6baf6
+size 2224479365

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5509373af07c4424e18f6b39d6b12d7e56aaa5503a38e512c637dc4c14f6b1a
+size 1112254133

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95ae9913bfca7218ab97cf3ed92e4ae1f29264d5a024c50a79c12b3e954c9d63
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81ea28dd40bbb06af618449b6fdda1ed03b36b8df7b59f262b727d237b849af
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50da2f84fc792838940acca98873197c2795d8678983a21238a931caf0457dab
+size 627

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:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
+size 17082758

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "xlm-roberta-base",
+  "num_labels": 2,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": 0.996,
+  "best_model_checkpoint": "xlm-roberta-base-finetuned-enron/checkpoint-7932",
+  "epoch": 4.0,
+  "global_step": 7932,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.8999495713565305e-05,
+      "loss": 0.1679,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.799293998991427e-05,
+      "loss": 0.0773,
+      "step": 1000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.698436712052446e-05,
+      "loss": 0.0504,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.995,
+      "eval_loss": 0.022810379043221474,
+      "eval_runtime": 7.2177,
+      "eval_samples_per_second": 277.095,
+      "eval_steps_per_second": 17.318,
+      "step": 1983
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5977811396873426e-05,
+      "loss": 0.0436,
+      "step": 2000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.4969238527483611e-05,
+      "loss": 0.0377,
+      "step": 2500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.39606656580938e-05,
+      "loss": 0.0283,
+      "step": 3000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.2952092788703986e-05,
+      "loss": 0.0211,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.991,
+      "eval_loss": 0.05412155017256737,
+      "eval_runtime": 8.3181,
+      "eval_samples_per_second": 240.441,
+      "eval_steps_per_second": 15.028,
+      "step": 3966
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.194351991931417e-05,
+      "loss": 0.0201,
+      "step": 4000
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.0936964195663137e-05,
+      "loss": 0.0073,
+      "step": 4500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 9.928391326273324e-06,
+      "loss": 0.0094,
+      "step": 5000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 8.919818456883512e-06,
+      "loss": 0.0118,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.993,
+      "eval_loss": 0.0558784045279026,
+      "eval_runtime": 7.2776,
+      "eval_samples_per_second": 274.815,
+      "eval_steps_per_second": 17.176,
+      "step": 5949
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 7.911245587493697e-06,
+      "loss": 0.0122,
+      "step": 6000
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 6.902672718103883e-06,
+      "loss": 0.0034,
+      "step": 6500
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 5.89409984871407e-06,
+      "loss": 0.0091,
+      "step": 7000
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 4.885526979324257e-06,
+      "loss": 0.0027,
+      "step": 7500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.996,
+      "eval_loss": 0.031464751809835434,
+      "eval_runtime": 7.3051,
+      "eval_samples_per_second": 273.782,
+      "eval_steps_per_second": 17.111,
+      "step": 7932
+    }
+  ],
+  "max_steps": 9915,
+  "num_train_epochs": 5,
+  "total_flos": 3.326409472938432e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c026923163f5548ac526d3f042090ebebc98b002256cf06abd1ea0b97ccefc
+size 3451