Upload 10 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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "XLM-roberta-large",
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "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:b0ac2c9ce1dfa0acf2673d7cfbe63b94b8c7a46c01654da207360e59516368c9
+size 4479472785

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4baee7c256492a4f65244acd243467de88ad2446a80f9b4d4113bc1af20535bf
+size 2239705966

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1710306bc77a3578fbfa56aeb19213aa463c4a4fb57e5039dd339bef96ef611
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5256aae9aee46059277254ff8d919fa83741566621cd54f2736e316c806881bb
+size 1064

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:b12c8659905a74a0883d675e55f31cc0dbdcdf1809e04270c95a0542785c54fc
+size 17082826

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": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.188361408882082,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.8468606431852985e-06,
+      "loss": 0.4586,
+      "step": 500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.6937212863705971e-06,
+      "loss": 0.1973,
+      "step": 1000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.5405819295558958e-06,
+      "loss": 0.1644,
+      "step": 1500
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 1.3874425727411944e-06,
+      "loss": 0.1565,
+      "step": 2000
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 1.234303215926493e-06,
+      "loss": 0.1154,
+      "step": 2500
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 1.0811638591117918e-06,
+      "loss": 0.0989,
+      "step": 3000
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 9.280245022970902e-07,
+      "loss": 0.0942,
+      "step": 3500
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 7.74885145482389e-07,
+      "loss": 0.0812,
+      "step": 4000
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 6.217457886676876e-07,
+      "loss": 0.0692,
+      "step": 4500
+    },
+    {
+      "epoch": 7.66,
+      "learning_rate": 4.686064318529862e-07,
+      "loss": 0.0796,
+      "step": 5000
+    },
+    {
+      "epoch": 8.42,
+      "learning_rate": 3.1546707503828487e-07,
+      "loss": 0.0582,
+      "step": 5500
+    },
+    {
+      "epoch": 9.19,
+      "learning_rate": 1.6232771822358346e-07,
+      "loss": 0.0495,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6530,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 5587394488833024.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06462bfd75339f60cb7d7a66e0782a6e75823f1efc59988a6a70c4ce5acb9299
+size 4536