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": "4.52.2",
+  "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 sha256:68c6e2f6df1d7bd8aacd39000f8e2badff34b5445f02bd552b601f3d5ba493cd
+size 2239618672

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10e11e407fa86a6ab1ce02196171e5b2b4613d79c187e48ba0f0300f3b92512c
+size 4479472785

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ac76eb81992fdf43ff2672a0c31b111fd43bda056b9b508a675ed32cbaf6bb
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03ba69f1d5a7a4294ea82c8e2270b75d5aaf1b36a41c9836ae96231be3be454
+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 +1,51 @@
+{
+  "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": false,
+    "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 sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_global_step": 3222,
+  "best_metric": 0.9287502085766728,
+  "best_model_checkpoint": "./results/checkpoint-3222",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4296,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4655493482309125,
+      "grad_norm": 27.341506958007812,
+      "learning_rate": 9.535381750465549e-07,
+      "loss": 0.5434,
+      "step": 500
+    },
+    {
+      "epoch": 0.931098696461825,
+      "grad_norm": 20.316381454467773,
+      "learning_rate": 9.069832402234636e-07,
+      "loss": 0.32,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.900884365092608,
+      "eval_loss": 0.270067423582077,
+      "eval_runtime": 119.0728,
+      "eval_samples_per_second": 50.331,
+      "eval_steps_per_second": 3.149,
+      "step": 1074
+    },
+    {
+      "epoch": 1.3966480446927374,
+      "grad_norm": 59.5791015625,
+      "learning_rate": 8.604283054003724e-07,
+      "loss": 0.2702,
+      "step": 1500
+    },
+    {
+      "epoch": 1.86219739292365,
+      "grad_norm": 35.37834548950195,
+      "learning_rate": 8.138733705772811e-07,
+      "loss": 0.2547,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9229100617386952,
+      "eval_loss": 0.21657520532608032,
+      "eval_runtime": 118.9079,
+      "eval_samples_per_second": 50.4,
+      "eval_steps_per_second": 3.154,
+      "step": 2148
+    },
+    {
+      "epoch": 2.3277467411545625,
+      "grad_norm": 51.73606491088867,
+      "learning_rate": 7.673184357541899e-07,
+      "loss": 0.2446,
+      "step": 2500
+    },
+    {
+      "epoch": 2.793296089385475,
+      "grad_norm": 39.03384017944336,
+      "learning_rate": 7.207635009310986e-07,
+      "loss": 0.2238,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9287502085766728,
+      "eval_loss": 0.21104617416858673,
+      "eval_runtime": 118.9557,
+      "eval_samples_per_second": 50.38,
+      "eval_steps_per_second": 3.152,
+      "step": 3222
+    },
+    {
+      "epoch": 3.2588454376163876,
+      "grad_norm": 18.250083923339844,
+      "learning_rate": 6.742085661080075e-07,
+      "loss": 0.226,
+      "step": 3500
+    },
+    {
+      "epoch": 3.7243947858473,
+      "grad_norm": 14.896623611450195,
+      "learning_rate": 6.276536312849162e-07,
+      "loss": 0.2153,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9237443684298348,
+      "eval_loss": 0.23883432149887085,
+      "eval_runtime": 118.9658,
+      "eval_samples_per_second": 50.376,
+      "eval_steps_per_second": 3.152,
+      "step": 4296
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10740,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.401995693518029e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1124fc6417b5794aea354210b6acea4acef2ffd51a8ecf1189260ccb906088e8
+size 5304