Upload folder using huggingface_hub

.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 +1,28 @@
+{
+  "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": "4.53.3",
+  "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 sha256:594d196fe2e89e725ec3d0b4ad198033a041b7bafdc63fad3547124426ab6986
+size 2239618672

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca7288a9c93a66b361598690410a81f95e6be8c1c8cb7be17733a0ecb9c850fc
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046b700ec3dc788162e9ad1143180111779056a1837172279ab8fb86760d39b7
+size 1383

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 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34fea3cc01b92a71db3482ab7d2e472fdc9bafc4d1e832bda9b2576d4b23dbd0
+size 17082896

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.06772813200950623,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.2229,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 70.07539367675781,
+      "learning_rate": 1.8791111111111113e-05,
+      "loss": 0.0587,
+      "step": 200
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.027119344100356102,
+      "learning_rate": 1.7013333333333335e-05,
+      "loss": 0.0501,
+      "step": 300
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.03452509641647339,
+      "learning_rate": 1.5253333333333335e-05,
+      "loss": 0.0785,
+      "step": 400
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.03838394209742546,
+      "learning_rate": 1.3475555555555558e-05,
+      "loss": 0.0402,
+      "step": 500
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.019694995135068893,
+      "learning_rate": 1.1697777777777779e-05,
+      "loss": 0.022,
+      "step": 600
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.022513490170240402,
+      "learning_rate": 9.920000000000002e-06,
+      "loss": 0.0003,
+      "step": 700
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.00941507425159216,
+      "learning_rate": 8.142222222222223e-06,
+      "loss": 0.0002,
+      "step": 800
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.002056879224255681,
+      "learning_rate": 6.364444444444445e-06,
+      "loss": 0.0012,
+      "step": 900
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.007224950939416885,
+      "learning_rate": 4.586666666666667e-06,
+      "loss": 0.0088,
+      "step": 1000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.011511213146150112,
+      "learning_rate": 2.8088888888888893e-06,
+      "loss": 0.0001,
+      "step": 1100
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.01675555668771267,
+      "learning_rate": 1.0311111111111112e-06,
+      "loss": 0.0112,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 364035688800000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b890a980fb55367869b697d841efca2faffe6b058338ef43d7eaa8abaa56594
+size 5777