Upload trained RoBERTa model

README.md

@@ -0,0 +1,71 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/roberta-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: roberta-Questions-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-Questions-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: 0.3192
+- Accuracy: 0.7805
+- Precision: 0.6813
+- Recall: 0.8185
+- F1: 0.7436
+
+## 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: 3.0384066791847988e-05
+- 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: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.5249        | 1.0   | 165  | 0.2628          | 0.6110   | 0.0       | 0.0    | 0.0    |
+| 0.4371        | 2.0   | 330  | 0.3133          | 0.7843   | 0.6517    | 0.9571 | 0.7754 |
+| 0.3969        | 3.0   | 495  | 0.2745          | 0.6226   | 0.6364    | 0.0693 | 0.125  |
+| 0.3765        | 4.0   | 660  | 0.3192          | 0.7805   | 0.6813    | 0.8185 | 0.7436 |
+
+
+### Framework versions
+
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.21.0

checkpoint-330/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": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-330/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d24c367a53538d015985e0d840fbfa8a906a07d6e9eb2d13831aa0e8129bd92
+size 1421495416

checkpoint-330/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056acf15d90bafa9478b0ff2b41d4b9661c6f1a7bca8cc45bc3c03b4000bb378
+size 2843228717

checkpoint-330/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528bf3e014a0e5c7addd06a81fa142adcf48ccf5674f356b0c8c67d42e077000
+size 14244

checkpoint-330/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366c0bd82d4ff4a4666a4b8b9583fcbf8a5c6f31a37ca20ab83bbf0426666746
+size 1064

checkpoint-330/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-330/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-330/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.7754010695187166,
+  "best_model_checkpoint": "roberta-Questions-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-330",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 330,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.699333667755127,
+      "learning_rate": 2.5320055659873325e-05,
+      "loss": 0.5249,
+      "step": 165
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6110397946084724,
+      "eval_f1": 0.0,
+      "eval_loss": 0.26281124353408813,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 2.97,
+      "eval_samples_per_second": 262.286,
+      "eval_steps_per_second": 16.498,
+      "step": 165
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.26629114151001,
+      "learning_rate": 1.6880037106582216e-05,
+      "loss": 0.4371,
+      "step": 330
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7843388960205392,
+      "eval_f1": 0.7754010695187166,
+      "eval_loss": 0.3132757842540741,
+      "eval_precision": 0.651685393258427,
+      "eval_recall": 0.9570957095709571,
+      "eval_runtime": 3.447,
+      "eval_samples_per_second": 225.994,
+      "eval_steps_per_second": 14.215,
+      "step": 330
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 660,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 1161477707257728.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-330/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86e294efc509f7567830f1623069a82773ad637137ae3232308a6a42802341c
+size 5496

checkpoint-844/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": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-844/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:240bd8f100b35e11988e0aa3ab54977ea1bed67eed59332e0f795474219954f5
+size 1421495416

checkpoint-844/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d97b759afd9f5565e81ca72505a63f7b5dcfc905f57b1a557b3c3def10a1b2d9
+size 2843228717

checkpoint-844/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c480f193ef4f43396b61c85a57a504c3363631118a770917017caef7b0da9420
+size 14244

checkpoint-844/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05710f58acb3383f2b72b3057f742e9c3a7f629080e64cb5dea590b0c8745d9a
+size 1064

checkpoint-844/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-844/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-844/trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": 0.41818181818181815,
+  "best_model_checkpoint": "roberta-Questions-goodareas-eval_FeedbackESConv5pp_CARE10pp-sweeps-current/checkpoint-422",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 844,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 475.60015869140625,
+      "learning_rate": 2.0872026879361993e-05,
+      "loss": 0.5219,
+      "step": 211
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6110397946084724,
+      "eval_f1": 0.0,
+      "eval_loss": 0.4811629056930542,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 6.4472,
+      "eval_samples_per_second": 120.828,
+      "eval_steps_per_second": 7.6,
+      "step": 211
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.935336589813232,
+      "learning_rate": 1.3914684586241329e-05,
+      "loss": 0.5152,
+      "step": 422
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6713735558408216,
+      "eval_f1": 0.41818181818181815,
+      "eval_loss": 0.5361036062240601,
+      "eval_precision": 0.6715328467153284,
+      "eval_recall": 0.30363036303630364,
+      "eval_runtime": 6.0743,
+      "eval_samples_per_second": 128.246,
+      "eval_steps_per_second": 8.067,
+      "step": 422
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 7.51805305480957,
+      "learning_rate": 6.957342293120664e-06,
+      "loss": 0.4977,
+      "step": 633
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6097560975609756,
+      "eval_f1": 0.0,
+      "eval_loss": 0.4554288983345032,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 5.9395,
+      "eval_samples_per_second": 131.156,
+      "eval_steps_per_second": 8.25,
+      "step": 633
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.534423828125,
+      "learning_rate": 0.0,
+      "loss": 0.4749,
+      "step": 844
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6161745827984596,
+      "eval_f1": 0.032362459546925564,
+      "eval_loss": 0.47242072224617004,
+      "eval_precision": 0.8333333333333334,
+      "eval_recall": 0.0165016501650165,
+      "eval_runtime": 6.1591,
+      "eval_samples_per_second": 126.48,
+      "eval_steps_per_second": 7.956,
+      "step": 844
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 844,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 1.114287760918584e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-844/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce38847542d95fbd971a2c16c1dd756d266e913c269d7a7697792594b0cbace
+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": "4.48.3",
+  "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 sha256:5d24c367a53538d015985e0d840fbfa8a906a07d6e9eb2d13831aa0e8129bd92
+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:b86e294efc509f7567830f1623069a82773ad637137ae3232308a6a42802341c
+size 5496