marmolpen3/lexglue-unfair-tos

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: seed_1
+  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. -->
+
+# seed_1
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0251
+- Macro-f1: 0.7620
+- Micro-f1: 0.9517
+
+## 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 1
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Macro-f1 | Micro-f1 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
+| 0.0965        | 1.0   | 692  | 0.0395          | 0.3257   | 0.9201   |
+| 0.0428        | 2.0   | 1384 | 0.0300          | 0.5948   | 0.9260   |
+| 0.0202        | 3.0   | 2076 | 0.0251          | 0.7620   | 0.9517   |
+| 0.0136        | 4.0   | 2768 | 0.0285          | 0.7234   | 0.9372   |
+| 0.01          | 5.0   | 3460 | 0.0300          | 0.7252   | 0.9452   |
+| 0.0068        | 6.0   | 4152 | 0.0286          | 0.7559   | 0.9501   |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 1.13.1
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.025112023577094078,
+    "eval_macro-f1": 0.7620096966057794,
+    "eval_micro-f1": 0.9517181383210092,
+    "eval_runtime": 2.8738,
+    "eval_samples": 2275,
+    "eval_samples_per_second": 791.624,
+    "eval_steps_per_second": 99.171,
+    "total_flos": 2183413154955264.0,
+    "train_loss": 0.027697743765421227,
+    "train_runtime": 253.8343,
+    "train_samples": 5532,
+    "train_samples_per_second": 435.875,
+    "train_steps_per_second": 54.524
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "unfair_toc",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 6.0,
+    "eval_loss": 0.025112023577094078,
+    "eval_macro-f1": 0.7620096966057794,
+    "eval_micro-f1": 0.9517181383210092,
+    "eval_runtime": 2.8738,
+    "eval_samples": 2275,
+    "eval_samples_per_second": 791.624,
+    "eval_steps_per_second": 99.171
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07278187d1b84fc740771ac28b546b10041a394bcd3ce49ea20c923eb45f4ebd
+size 219000200

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 2183413154955264.0,
+    "train_loss": 0.027697743765421227,
+    "train_runtime": 253.8343,
+    "train_samples": 5532,
+    "train_samples_per_second": 435.875,
+    "train_steps_per_second": 54.524
+}

trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_metric": 0.9517181383210092,
+  "best_model_checkpoint": "logs/unfair_tos/bert-base-uncased/seed_1/checkpoint-2076",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 4152,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7225433526011561,
+      "grad_norm": 0.4137115776538849,
+      "learning_rate": 2.8916184971098265e-05,
+      "loss": 0.0965,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.03946217894554138,
+      "eval_macro-f1": 0.3257253069723768,
+      "eval_micro-f1": 0.9201138104618078,
+      "eval_runtime": 3.109,
+      "eval_samples_per_second": 731.749,
+      "eval_steps_per_second": 91.67,
+      "step": 692
+    },
+    {
+      "epoch": 1.4450867052023122,
+      "grad_norm": 0.5951205492019653,
+      "learning_rate": 2.7832369942196533e-05,
+      "loss": 0.0428,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.030047794803977013,
+      "eval_macro-f1": 0.5948063101905734,
+      "eval_micro-f1": 0.926039387308534,
+      "eval_runtime": 3.1251,
+      "eval_samples_per_second": 727.972,
+      "eval_steps_per_second": 91.196,
+      "step": 1384
+    },
+    {
+      "epoch": 2.167630057803468,
+      "grad_norm": 0.040406469255685806,
+      "learning_rate": 2.6748554913294797e-05,
+      "loss": 0.0294,
+      "step": 1500
+    },
+    {
+      "epoch": 2.8901734104046244,
+      "grad_norm": 0.47717490792274475,
+      "learning_rate": 2.5664739884393065e-05,
+      "loss": 0.0202,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.025113314390182495,
+      "eval_macro-f1": 0.7620096966057794,
+      "eval_micro-f1": 0.9517181383210092,
+      "eval_runtime": 3.0811,
+      "eval_samples_per_second": 738.38,
+      "eval_steps_per_second": 92.5,
+      "step": 2076
+    },
+    {
+      "epoch": 3.61271676300578,
+      "grad_norm": 0.00729083176702261,
+      "learning_rate": 2.458092485549133e-05,
+      "loss": 0.0136,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.028495851904153824,
+      "eval_macro-f1": 0.7233574363382008,
+      "eval_micro-f1": 0.937227550130776,
+      "eval_runtime": 3.1146,
+      "eval_samples_per_second": 730.425,
+      "eval_steps_per_second": 91.504,
+      "step": 2768
+    },
+    {
+      "epoch": 4.335260115606936,
+      "grad_norm": 0.01607728749513626,
+      "learning_rate": 2.3497109826589597e-05,
+      "loss": 0.01,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.030019745230674744,
+      "eval_macro-f1": 0.7251725230841095,
+      "eval_micro-f1": 0.9452084697664266,
+      "eval_runtime": 3.0696,
+      "eval_samples_per_second": 741.132,
+      "eval_steps_per_second": 92.845,
+      "step": 3460
+    },
+    {
+      "epoch": 5.057803468208093,
+      "grad_norm": 0.006081081461161375,
+      "learning_rate": 2.2413294797687862e-05,
+      "loss": 0.0087,
+      "step": 3500
+    },
+    {
+      "epoch": 5.780346820809249,
+      "grad_norm": 4.081294536590576,
+      "learning_rate": 2.132947976878613e-05,
+      "loss": 0.0068,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.02861410565674305,
+      "eval_macro-f1": 0.7558502112595478,
+      "eval_micro-f1": 0.9500763025942882,
+      "eval_runtime": 3.0792,
+      "eval_samples_per_second": 738.833,
+      "eval_steps_per_second": 92.557,
+      "step": 4152
+    },
+    {
+      "epoch": 6.0,
+      "step": 4152,
+      "total_flos": 2183413154955264.0,
+      "train_loss": 0.027697743765421227,
+      "train_runtime": 253.8343,
+      "train_samples_per_second": 435.875,
+      "train_steps_per_second": 54.524
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 13840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 2183413154955264.0,
+  "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 sha256:1db0c70fffaf91741e6abd5690e6a2fecb4890b3688ab1c1f901c806aed4c804
+size 4603