jamiehudson/roberta-best-finetuned-hopes-fears

README.md

@@ -0,0 +1,81 @@
+---
+license: mit
+base_model: FacebookAI/roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: roberta-best-finetuned-hopes-fears
+  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-best-finetuned-hopes-fears
+
+This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5676
+- Accuracy: 0.9534
+- F1 Weighted: 0.9543
+- Precision Hopes: 0.7022
+- Recall Hopes: 0.7622
+- F1 Hopes: 0.7310
+- Precision Fears: 0.8740
+- Recall Fears: 0.9328
+- F1 Fears: 0.9024
+- Precision Neither: 0.9804
+- Recall Neither: 0.9699
+- F1 Neither: 0.9751
+
+## 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: 1e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 600
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Weighted | Precision Hopes | Recall Hopes | F1 Hopes | Precision Fears | Recall Fears | F1 Fears | Precision Neither | Recall Neither | F1 Neither |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:-----------------:|:--------------:|:----------:|
+| No log        | 1.0   | 171  | 1.0349          | 0.8791   | 0.8226      | 0.0             | 0.0          | 0.0      | 0.0             | 0.0          | 0.0      | 0.8791            | 1.0            | 0.9357     |
+| 0.9414        | 2.0   | 342  | 0.3255          | 0.9218   | 0.9264      | 0.5810          | 0.7439       | 0.6524   | 0.6792          | 0.9076       | 0.7770   | 0.9777            | 0.9368         | 0.9568     |
+| 0.9414        | 3.0   | 513  | 0.2678          | 0.8697   | 0.8897      | 0.3817          | 0.9146       | 0.5386   | 0.6886          | 0.9664       | 0.8042   | 0.9944            | 0.8605         | 0.9226     |
+| 0.2918        | 4.0   | 684  | 0.2523          | 0.9124   | 0.9238      | 0.4608          | 0.8963       | 0.6087   | 0.8740          | 0.9328       | 0.9024   | 0.9910            | 0.9125         | 0.9502     |
+| 0.2918        | 5.0   | 855  | 0.2868          | 0.9368   | 0.9413      | 0.5787          | 0.8293       | 0.6817   | 0.8485          | 0.9412       | 0.8924   | 0.9853            | 0.9451         | 0.9648     |
+| 0.1436        | 6.0   | 1026 | 0.3765          | 0.9475   | 0.9501      | 0.6415          | 0.8293       | 0.7234   | 0.8672          | 0.9328       | 0.8988   | 0.9850            | 0.9577         | 0.9712     |
+| 0.1436        | 7.0   | 1197 | 0.3750          | 0.9308   | 0.9372      | 0.5492          | 0.8841       | 0.6776   | 0.8129          | 0.9496       | 0.8760   | 0.9912            | 0.9334         | 0.9615     |
+| 0.0673        | 8.0   | 1368 | 0.5053          | 0.9517   | 0.9532      | 0.6825          | 0.7866       | 0.7309   | 0.8626          | 0.9496       | 0.904    | 0.9827            | 0.9650         | 0.9738     |
+| 0.0345        | 9.0   | 1539 | 0.5717          | 0.9539   | 0.9546      | 0.7168          | 0.7561       | 0.7359   | 0.8496          | 0.9496       | 0.8968   | 0.9808            | 0.9699         | 0.9753     |
+| 0.0345        | 10.0  | 1710 | 0.5676          | 0.9534   | 0.9543      | 0.7022          | 0.7622       | 0.7310   | 0.8740          | 0.9328       | 0.9024   | 0.9804            | 0.9699         | 0.9751     |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "fears",
+    "1": "hopes",
+    "2": "neither"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "fears": 0,
+    "hopes": 1,
+    "neither": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "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 sha256:290e7a2d92a13e6e195dd2b693eefe6fc60c33d76670379761558ddd5a89e14b
+size 498615900

runs/May31_19-28-30_68d233ee17d4/events.out.tfevents.1717183717.68d233ee17d4.2835.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2625bf865c5a237c711afe83065fbc36964363e7d28747cdd29941913a62a9ca
+size 5116

runs/May31_19-29-14_68d233ee17d4/events.out.tfevents.1717183763.68d233ee17d4.2835.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa1637659d83866d25a2e2a56e1fd147a25da542b8fb78d859ffb38936201cd3
+size 15284

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 +1,57 @@
+{
+  "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": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "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 sha256:2d1c55d45a1d9a2e5221c3ef0af3febd87977a1184543b19888ac1a79cb7fbd4
+size 5176