Upload 9 files

.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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5447be03a51cb03d8cc0e6f49907ddd864c122c3b81422989bba9b08940aea
+size 1112252785

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23756a57676af0efddbbfc4b250ebcedbe7e94044eee24902b983356b5a51bf
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e855be1a91a6dd07b0fe78203051f0b1c1a0271dc8e04743d097a9ed6d79b69d
+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 sha256:4c08c80d1df11b82ada2fd707562f86a9ebd5b7de04f51ebd2b49f2cd5906d00
+size 17082925

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "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,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,132 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.9220672682526665,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8372436423297786e-05,
+      "loss": 0.4396,
+      "step": 500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.673502871205907e-05,
+      "loss": 0.3623,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7705605028810896,
+      "eval_f1": 0.7981601731601731,
+      "eval_loss": 0.3199549615383148,
+      "eval_roc_auc": 0.8454688318491356,
+      "eval_runtime": 4.9345,
+      "eval_samples_per_second": 386.871,
+      "eval_steps_per_second": 48.435,
+      "step": 1219
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.5097621000820346e-05,
+      "loss": 0.3118,
+      "step": 1500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.345693191140279e-05,
+      "loss": 0.3084,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.787323205866946,
+      "eval_f1": 0.8144357662267707,
+      "eval_loss": 0.3036384880542755,
+      "eval_roc_auc": 0.857778941854374,
+      "eval_runtime": 5.4523,
+      "eval_samples_per_second": 350.13,
+      "eval_steps_per_second": 43.835,
+      "step": 2438
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.1816242821985235e-05,
+      "loss": 0.2862,
+      "step": 2500
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.017555373256768e-05,
+      "loss": 0.2544,
+      "step": 3000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 8.534864643150123e-06,
+      "loss": 0.2555,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7946568884232582,
+      "eval_f1": 0.8135683760683762,
+      "eval_loss": 0.34248924255371094,
+      "eval_roc_auc": 0.858040859088528,
+      "eval_runtime": 4.9485,
+      "eval_samples_per_second": 385.776,
+      "eval_steps_per_second": 48.298,
+      "step": 3657
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 6.894175553732568e-06,
+      "loss": 0.2306,
+      "step": 4000
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 5.253486464315013e-06,
+      "loss": 0.2173,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8114195914091147,
+      "eval_f1": 0.8226875165650676,
+      "eval_loss": 0.35695233941078186,
+      "eval_roc_auc": 0.8656364588789941,
+      "eval_runtime": 4.8414,
+      "eval_samples_per_second": 394.309,
+      "eval_steps_per_second": 49.366,
+      "step": 4876
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 3.612797374897457e-06,
+      "loss": 0.2049,
+      "step": 5000
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 1.9753896636587367e-06,
+      "loss": 0.1896,
+      "step": 5500
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 3.347005742411813e-07,
+      "loss": 0.1873,
+      "step": 6000
+    }
+  ],
+  "max_steps": 6095,
+  "num_train_epochs": 5,
+  "total_flos": 3156308559065088.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5287093bc0630ad949f861ebf54ec278543f54605ab43193520197c4b86a9b5d
+size 3963