Upload trained RoBERTa model

README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/roberta-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: roberta-Validation-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# roberta-Validation-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current
+
+This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7517
+- Accuracy: 0.8331
+- Precision: 0.4610
+- Recall: 0.6017
+- F1: 0.5221
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3.263554762497362e-06
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.533         | 1.0   | 486  | 0.3998          | 0.8485   | 0.0       | 0.0    | 0.0    |
+| 0.4106        | 2.0   | 972  | 0.3184          | 0.8601   | 0.5714    | 0.3051 | 0.3978 |
+| 0.3506        | 3.0   | 1458 | 0.3458          | 0.8665   | 0.5778    | 0.4407 | 0.5    |
+| 0.3103        | 4.0   | 1944 | 0.3449          | 0.8460   | 0.4926    | 0.5678 | 0.5276 |
+| 0.2684        | 5.0   | 2430 | 0.3504          | 0.8472   | 0.4959    | 0.5085 | 0.5021 |
+| 0.2295        | 6.0   | 2916 | 0.4242          | 0.8588   | 0.5299    | 0.6017 | 0.5635 |
+| 0.1905        | 7.0   | 3402 | 0.5236          | 0.8549   | 0.5191    | 0.5763 | 0.5462 |
+| 0.1614        | 8.0   | 3888 | 0.6659          | 0.8434   | 0.4859    | 0.5847 | 0.5308 |
+| 0.1499        | 9.0   | 4374 | 0.7185          | 0.8421   | 0.4825    | 0.5847 | 0.5287 |
+| 0.1347        | 10.0  | 4860 | 0.7517          | 0.8331   | 0.4610    | 0.6017 | 0.5221 |
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.5.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.21.0

checkpoint-2916/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "FacebookAI/roberta-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "not selected",
+    "1": "selected"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "not selected": "0",
+    "selected": "1"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-2916/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300ff926d3597fbd7f719bc0051d5e35ff38aa43fc8a1fb4ca660c252218b9eb
+size 1421495416

checkpoint-2916/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b96046360b29514b2f5f1acdf462bb03a433dd59134e6151e102435c017b3e8
+size 2843228717

checkpoint-2916/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7c361196e62664d87275eef98741dca91e5ee11b9df1b33cfbd6ee4ddf7a1c6
+size 14244

checkpoint-2916/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:253ec4c32a480d59ba15a3f8c0b36c771f3c70c4dc3056b474d960c616a672f6
+size 1064

checkpoint-2916/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>"
+}

checkpoint-2916/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "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>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-2916/trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.5634920634920635,
+  "best_model_checkpoint": "roberta-Validation-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-2916",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 2916,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 32.236263275146484,
+      "learning_rate": 3.263554762497362e-06,
+      "loss": 0.533,
+      "step": 486
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8485237483953787,
+      "eval_f1": 0.0,
+      "eval_loss": 0.39981475472450256,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 5.4841,
+      "eval_samples_per_second": 142.046,
+      "eval_steps_per_second": 8.935,
+      "step": 486
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 27.773176193237305,
+      "learning_rate": 2.9009375666643217e-06,
+      "loss": 0.4106,
+      "step": 972
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8600770218228498,
+      "eval_f1": 0.39779005524861877,
+      "eval_loss": 0.3184129595756531,
+      "eval_precision": 0.5714285714285714,
+      "eval_recall": 0.3050847457627119,
+      "eval_runtime": 5.7415,
+      "eval_samples_per_second": 135.679,
+      "eval_steps_per_second": 8.534,
+      "step": 972
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.45919132232666,
+      "learning_rate": 2.538320370831282e-06,
+      "loss": 0.3506,
+      "step": 1458
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8664955070603337,
+      "eval_f1": 0.5,
+      "eval_loss": 0.3457795977592468,
+      "eval_precision": 0.5777777777777777,
+      "eval_recall": 0.4406779661016949,
+      "eval_runtime": 5.929,
+      "eval_samples_per_second": 131.388,
+      "eval_steps_per_second": 8.264,
+      "step": 1458
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 19.585311889648438,
+      "learning_rate": 2.175703174998241e-06,
+      "loss": 0.3103,
+      "step": 1944
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8459563543003851,
+      "eval_f1": 0.5275590551181102,
+      "eval_loss": 0.3448907732963562,
+      "eval_precision": 0.49264705882352944,
+      "eval_recall": 0.5677966101694916,
+      "eval_runtime": 5.7047,
+      "eval_samples_per_second": 136.555,
+      "eval_steps_per_second": 8.589,
+      "step": 1944
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 14.003765106201172,
+      "learning_rate": 1.8130859791652012e-06,
+      "loss": 0.2684,
+      "step": 2430
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8472400513478819,
+      "eval_f1": 0.502092050209205,
+      "eval_loss": 0.35038354992866516,
+      "eval_precision": 0.49586776859504134,
+      "eval_recall": 0.5084745762711864,
+      "eval_runtime": 6.2487,
+      "eval_samples_per_second": 124.665,
+      "eval_steps_per_second": 7.842,
+      "step": 2430
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 28.96128273010254,
+      "learning_rate": 1.4504687833321609e-06,
+      "loss": 0.2295,
+      "step": 2916
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.858793324775353,
+      "eval_f1": 0.5634920634920635,
+      "eval_loss": 0.4241916835308075,
+      "eval_precision": 0.5298507462686567,
+      "eval_recall": 0.6016949152542372,
+      "eval_runtime": 5.5866,
+      "eval_samples_per_second": 139.442,
+      "eval_steps_per_second": 8.771,
+      "step": 2916
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4860,
+  "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": 2.716439770360932e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2916/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe08e557831ea92136ea7ca84809952426264adcee228b9f5947753a6668044
+size 5496

checkpoint-4860/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "FacebookAI/roberta-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "not selected",
+    "1": "selected"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "not selected": "0",
+    "selected": "1"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-4860/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d894d753c69c83f6d1b96d90046fb19e054bc15f5dcc3f8164d2c1985475c6f
+size 1421495416

checkpoint-4860/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96409a60f8eca34814194b371ba953454d0db76dbe359bcd921971561b4c2265
+size 2843228717

checkpoint-4860/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f949567d55d049fb5ee3cec6978127cc9e73c979c8a9f82ed47b3034cd32f612
+size 14180

checkpoint-4860/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778c3ce2b9fee04a227064b251a05cecafc2ed3ae0fc9943f5a1e9decf4b8c36
+size 1064

checkpoint-4860/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>"
+}

checkpoint-4860/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "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>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

checkpoint-4860/trainer_state.json

@@ -0,0 +1,223 @@
+{
+  "best_metric": 0.5634920634920635,
+  "best_model_checkpoint": "roberta-Validation-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-2916",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 4860,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 32.236263275146484,
+      "learning_rate": 3.263554762497362e-06,
+      "loss": 0.533,
+      "step": 486
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8485237483953787,
+      "eval_f1": 0.0,
+      "eval_loss": 0.39981475472450256,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 5.4841,
+      "eval_samples_per_second": 142.046,
+      "eval_steps_per_second": 8.935,
+      "step": 486
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 27.773176193237305,
+      "learning_rate": 2.9009375666643217e-06,
+      "loss": 0.4106,
+      "step": 972
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8600770218228498,
+      "eval_f1": 0.39779005524861877,
+      "eval_loss": 0.3184129595756531,
+      "eval_precision": 0.5714285714285714,
+      "eval_recall": 0.3050847457627119,
+      "eval_runtime": 5.7415,
+      "eval_samples_per_second": 135.679,
+      "eval_steps_per_second": 8.534,
+      "step": 972
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.45919132232666,
+      "learning_rate": 2.538320370831282e-06,
+      "loss": 0.3506,
+      "step": 1458
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8664955070603337,
+      "eval_f1": 0.5,
+      "eval_loss": 0.3457795977592468,
+      "eval_precision": 0.5777777777777777,
+      "eval_recall": 0.4406779661016949,
+      "eval_runtime": 5.929,
+      "eval_samples_per_second": 131.388,
+      "eval_steps_per_second": 8.264,
+      "step": 1458
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 19.585311889648438,
+      "learning_rate": 2.175703174998241e-06,
+      "loss": 0.3103,
+      "step": 1944
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8459563543003851,
+      "eval_f1": 0.5275590551181102,
+      "eval_loss": 0.3448907732963562,
+      "eval_precision": 0.49264705882352944,
+      "eval_recall": 0.5677966101694916,
+      "eval_runtime": 5.7047,
+      "eval_samples_per_second": 136.555,
+      "eval_steps_per_second": 8.589,
+      "step": 1944
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 14.003765106201172,
+      "learning_rate": 1.8130859791652012e-06,
+      "loss": 0.2684,
+      "step": 2430
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8472400513478819,
+      "eval_f1": 0.502092050209205,
+      "eval_loss": 0.35038354992866516,
+      "eval_precision": 0.49586776859504134,
+      "eval_recall": 0.5084745762711864,
+      "eval_runtime": 6.2487,
+      "eval_samples_per_second": 124.665,
+      "eval_steps_per_second": 7.842,
+      "step": 2430
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 28.96128273010254,
+      "learning_rate": 1.4504687833321609e-06,
+      "loss": 0.2295,
+      "step": 2916
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.858793324775353,
+      "eval_f1": 0.5634920634920635,
+      "eval_loss": 0.4241916835308075,
+      "eval_precision": 0.5298507462686567,
+      "eval_recall": 0.6016949152542372,
+      "eval_runtime": 5.5866,
+      "eval_samples_per_second": 139.442,
+      "eval_steps_per_second": 8.771,
+      "step": 2916
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 38.02456283569336,
+      "learning_rate": 1.0878515874991205e-06,
+      "loss": 0.1905,
+      "step": 3402
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8549422336328626,
+      "eval_f1": 0.5461847389558233,
+      "eval_loss": 0.523625373840332,
+      "eval_precision": 0.5190839694656488,
+      "eval_recall": 0.576271186440678,
+      "eval_runtime": 5.6207,
+      "eval_samples_per_second": 138.595,
+      "eval_steps_per_second": 8.718,
+      "step": 3402
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 43.9564208984375,
+      "learning_rate": 7.252343916660804e-07,
+      "loss": 0.1614,
+      "step": 3888
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8433889602053916,
+      "eval_f1": 0.5307692307692308,
+      "eval_loss": 0.6658771634101868,
+      "eval_precision": 0.4859154929577465,
+      "eval_recall": 0.5847457627118644,
+      "eval_runtime": 6.9799,
+      "eval_samples_per_second": 111.606,
+      "eval_steps_per_second": 7.02,
+      "step": 3888
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 11.728702545166016,
+      "learning_rate": 3.626171958330402e-07,
+      "loss": 0.1499,
+      "step": 4374
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8421052631578947,
+      "eval_f1": 0.5287356321839081,
+      "eval_loss": 0.7185185551643372,
+      "eval_precision": 0.4825174825174825,
+      "eval_recall": 0.5847457627118644,
+      "eval_runtime": 9.1672,
+      "eval_samples_per_second": 84.977,
+      "eval_steps_per_second": 5.345,
+      "step": 4374
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 97.16883087158203,
+      "learning_rate": 0.0,
+      "loss": 0.1347,
+      "step": 4860
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8331193838254172,
+      "eval_f1": 0.5220588235294118,
+      "eval_loss": 0.7517234086990356,
+      "eval_precision": 0.461038961038961,
+      "eval_recall": 0.6016949152542372,
+      "eval_runtime": 5.6382,
+      "eval_samples_per_second": 138.164,
+      "eval_steps_per_second": 8.691,
+      "step": 4860
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4860,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.523602846379266e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4860/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe08e557831ea92136ea7ca84809952426264adcee228b9f5947753a6668044
+size 5496

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "FacebookAI/roberta-large",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "not selected",
+    "1": "selected"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "not selected": "0",
+    "selected": "1"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300ff926d3597fbd7f719bc0051d5e35ff38aa43fc8a1fb4ca660c252218b9eb
+size 1421495416

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_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "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>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe08e557831ea92136ea7ca84809952426264adcee228b9f5947753a6668044
+size 5496