model improvement

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -1,19 +1,108 @@
 ---
-license: mit
-datasets:
-- allocine
 language:
 - fr
+license: mit
 tags:
-- camembert
+- generated_from_trainer
+datasets:
+- allocine
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: distilcamembert-allocine
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: allocine
+      type: allocine
+      config: allocine
+      split: validation
+      args: allocine
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9714
+    - name: F1
+      type: f1
+      value: 0.9709909727152854
+    - name: Precision
+      type: precision
+      value: 0.9648256399919372
+    - name: Recall
+      type: recall
+      value: 0.9772356063699469
 ---
-## TextAttack Model Card
 
-This `cmarkea/distilcamembert-base` model was fine-tuned using TextAttackand the `allocine` dataset loaded using the `datasets` library. The model was fine-tuned
-for 3 epochs with a batch size of 64,
-    a maximum sequence length of 512, and an initial learning rate of 5e-05.
-Since this was a classification task, the model was trained with a cross-entropy loss function.
-The best score the model achieved on this task was 0.9707, as measured by the
-eval set accuracy, found after 3 epochs.
+<!-- 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. -->
+
+# distilcamembert-allocine
+
+This model is a fine-tuned version of [cmarkea/distilcamembert-base](https://huggingface.co/cmarkea/distilcamembert-base) on the allocine dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1066
+- Accuracy: 0.9714
+- F1: 0.9710
+- Precision: 0.9648
+- Recall: 0.9772
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.1504        | 0.2   | 500  | 0.1290          | 0.9555   | 0.9542 | 0.9614    | 0.9470 |
+| 0.1334        | 0.4   | 1000 | 0.1049          | 0.9624   | 0.9619 | 0.9536    | 0.9703 |
+| 0.1158        | 0.6   | 1500 | 0.1052          | 0.963    | 0.9627 | 0.9498    | 0.9760 |
+| 0.1153        | 0.8   | 2000 | 0.0949          | 0.9661   | 0.9653 | 0.9686    | 0.9620 |
+| 0.1053        | 1.0   | 2500 | 0.0936          | 0.9666   | 0.9663 | 0.9542    | 0.9788 |
+| 0.0755        | 1.2   | 3000 | 0.0987          | 0.97     | 0.9695 | 0.9644    | 0.9748 |
+| 0.0716        | 1.4   | 3500 | 0.1078          | 0.9688   | 0.9684 | 0.9598    | 0.9772 |
+| 0.0688        | 1.6   | 4000 | 0.1051          | 0.9673   | 0.9670 | 0.9552    | 0.9792 |
+| 0.0691        | 1.8   | 4500 | 0.0940          | 0.9709   | 0.9704 | 0.9688    | 0.9720 |
+| 0.0733        | 2.0   | 5000 | 0.1038          | 0.9686   | 0.9683 | 0.9558    | 0.9812 |
+| 0.0476        | 2.2   | 5500 | 0.1066          | 0.9714   | 0.9710 | 0.9648    | 0.9772 |
+| 0.047         | 2.4   | 6000 | 0.1098          | 0.9689   | 0.9686 | 0.9587    | 0.9788 |
+| 0.0431        | 2.6   | 6500 | 0.1110          | 0.9711   | 0.9706 | 0.9666    | 0.9747 |
+| 0.0464        | 2.8   | 7000 | 0.1149          | 0.9697   | 0.9694 | 0.9592    | 0.9798 |
+| 0.0342        | 3.0   | 7500 | 0.1122          | 0.9703   | 0.9699 | 0.9621    | 0.9778 |
+
+
+### Framework versions
 
-For more information, check out [TextAttack on Github](https://github.com/QData/TextAttack).
+- Transformers 4.26.1
+- Pytorch 1.13.1+cu117
+- Datasets 2.10.1
+- Tokenizers 0.13.2

config.json

@@ -28,6 +28,7 @@
   "num_hidden_layers": 6,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.26.1",
   "type_vocab_size": 1,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf75746015301662f1a8677d6e45d6c0efba735b927358db3cf1c57975d0875
+oid sha256:599dd962ba50e977558a4120f60d5b9fc06fb04a4237ab1e2f22015a59c76a92
 size 272425205

results/all_results.json

@@ -0,0 +1,27 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9714,
+    "eval_f1": 0.9709909727152854,
+    "eval_loss": 0.10657692700624466,
+    "eval_precision": 0.9648256399919372,
+    "eval_recall": 0.9772356063699469,
+    "eval_runtime": 52.9584,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 377.655,
+    "eval_steps_per_second": 23.603,
+    "test_accuracy": 0.97035,
+    "test_f1": 0.9691900036369305,
+    "test_loss": 0.10945655405521393,
+    "test_precision": 0.9660279647850855,
+    "test_recall": 0.9723728106755629,
+    "test_runtime": 54.5698,
+    "test_samples": 20000,
+    "test_samples_per_second": 366.503,
+    "test_steps_per_second": 22.906,
+    "total_flos": 4.553211650587354e+16,
+    "train_loss": 0.08937127710183461,
+    "train_runtime": 4426.0374,
+    "train_samples": 160000,
+    "train_samples_per_second": 108.449,
+    "train_steps_per_second": 1.695
+}

results/eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.9714,
+    "eval_f1": 0.9709909727152854,
+    "eval_loss": 0.10657692700624466,
+    "eval_precision": 0.9648256399919372,
+    "eval_recall": 0.9772356063699469,
+    "eval_runtime": 52.9584,
+    "eval_samples": 20000,
+    "eval_samples_per_second": 377.655,
+    "eval_steps_per_second": 23.603
+}

results/test_results.json

@@ -0,0 +1,11 @@
+{
+    "test_accuracy": 0.97035,
+    "test_f1": 0.9691900036369305,
+    "test_loss": 0.10945655405521393,
+    "test_precision": 0.9660279647850855,
+    "test_recall": 0.9723728106755629,
+    "test_runtime": 54.5698,
+    "test_samples": 20000,
+    "test_samples_per_second": 366.503,
+    "test_steps_per_second": 22.906
+}

results/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 4.553211650587354e+16,
+    "train_loss": 0.08937127710183461,
+    "train_runtime": 4426.0374,
+    "train_samples": 160000,
+    "train_samples_per_second": 108.449,
+    "train_steps_per_second": 1.695
+}

results/trainer_state.json

@@ -0,0 +1,583 @@
+{
+  "best_metric": 0.9714,
+  "best_model_checkpoint": "models/distilcamembert-allocine\\checkpoint-5500",
+  "epoch": 3.0,
+  "global_step": 7500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 0.7377,
+      "step": 1
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.25e-05,
+      "loss": 0.5782,
+      "step": 125
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.5e-05,
+      "loss": 0.1837,
+      "step": 250
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.1665,
+      "step": 375
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 5e-05,
+      "loss": 0.1504,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.95545,
+      "eval_f1": 0.9541784520442272,
+      "eval_loss": 0.1289823055267334,
+      "eval_precision": 0.9614467820499534,
+      "eval_recall": 0.9470191915067374,
+      "eval_runtime": 51.8793,
+      "eval_samples_per_second": 385.51,
+      "eval_steps_per_second": 24.094,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.910714285714286e-05,
+      "loss": 0.1469,
+      "step": 625
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.8214285714285716e-05,
+      "loss": 0.1363,
+      "step": 750
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.732142857142857e-05,
+      "loss": 0.1332,
+      "step": 875
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.642857142857143e-05,
+      "loss": 0.1334,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.96235,
+      "eval_f1": 0.9618984971917219,
+      "eval_loss": 0.10494959354400635,
+      "eval_precision": 0.9536470352162135,
+      "eval_recall": 0.9702939975500204,
+      "eval_runtime": 52.9168,
+      "eval_samples_per_second": 377.951,
+      "eval_steps_per_second": 23.622,
+      "step": 1000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.5535714285714286e-05,
+      "loss": 0.1286,
+      "step": 1125
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.464285714285715e-05,
+      "loss": 0.1322,
+      "step": 1250
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.375e-05,
+      "loss": 0.1214,
+      "step": 1375
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.1158,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.963,
+      "eval_f1": 0.962742926190716,
+      "eval_loss": 0.10521914064884186,
+      "eval_precision": 0.9498311146433539,
+      "eval_recall": 0.9760106165781952,
+      "eval_runtime": 52.1412,
+      "eval_samples_per_second": 383.574,
+      "eval_steps_per_second": 23.973,
+      "step": 1500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.196428571428572e-05,
+      "loss": 0.1146,
+      "step": 1625
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.107142857142857e-05,
+      "loss": 0.1154,
+      "step": 1750
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.017857142857143e-05,
+      "loss": 0.1246,
+      "step": 1875
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.928571428571429e-05,
+      "loss": 0.1153,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.9661,
+      "eval_f1": 0.9652770664754685,
+      "eval_loss": 0.09492386132478714,
+      "eval_precision": 0.9685508735868448,
+      "eval_recall": 0.9620253164556962,
+      "eval_runtime": 53.0859,
+      "eval_samples_per_second": 376.748,
+      "eval_steps_per_second": 23.547,
+      "step": 2000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.839285714285715e-05,
+      "loss": 0.1064,
+      "step": 2125
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.112,
+      "step": 2250
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.6607142857142853e-05,
+      "loss": 0.1062,
+      "step": 2375
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.1053,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9666,
+      "eval_f1": 0.9663374319693611,
+      "eval_loss": 0.09356806427240372,
+      "eval_precision": 0.95421974522293,
+      "eval_recall": 0.9787668436096366,
+      "eval_runtime": 52.3106,
+      "eval_samples_per_second": 382.331,
+      "eval_steps_per_second": 23.896,
+      "step": 2500
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.4821428571428574e-05,
+      "loss": 0.0797,
+      "step": 2625
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.392857142857143e-05,
+      "loss": 0.0684,
+      "step": 2750
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 3.303571428571429e-05,
+      "loss": 0.0745,
+      "step": 2875
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.2142857142857144e-05,
+      "loss": 0.0755,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2,
+      "eval_accuracy": 0.97,
+      "eval_f1": 0.9695400548279013,
+      "eval_loss": 0.09874136000871658,
+      "eval_precision": 0.964350636235104,
+      "eval_recall": 0.9747856267864434,
+      "eval_runtime": 52.4682,
+      "eval_samples_per_second": 381.183,
+      "eval_steps_per_second": 23.824,
+      "step": 3000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.125e-05,
+      "loss": 0.0771,
+      "step": 3125
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.0357142857142857e-05,
+      "loss": 0.0733,
+      "step": 3250
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.9464285714285718e-05,
+      "loss": 0.069,
+      "step": 3375
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.0716,
+      "step": 3500
+    },
+    {
+      "epoch": 1.4,
+      "eval_accuracy": 0.9688,
+      "eval_f1": 0.9684370257966616,
+      "eval_loss": 0.10781414806842804,
+      "eval_precision": 0.9597954682173652,
+      "eval_recall": 0.9772356063699469,
+      "eval_runtime": 52.2793,
+      "eval_samples_per_second": 382.561,
+      "eval_steps_per_second": 23.91,
+      "step": 3500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.767857142857143e-05,
+      "loss": 0.0781,
+      "step": 3625
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.6785714285714288e-05,
+      "loss": 0.0725,
+      "step": 3750
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.5892857142857148e-05,
+      "loss": 0.0755,
+      "step": 3875
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0688,
+      "step": 4000
+    },
+    {
+      "epoch": 1.6,
+      "eval_accuracy": 0.9673,
+      "eval_f1": 0.967032967032967,
+      "eval_loss": 0.10506118088960648,
+      "eval_precision": 0.9551882095200159,
+      "eval_recall": 0.9791751735402205,
+      "eval_runtime": 52.2828,
+      "eval_samples_per_second": 382.535,
+      "eval_steps_per_second": 23.908,
+      "step": 4000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.4107142857142858e-05,
+      "loss": 0.07,
+      "step": 4125
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.3214285714285715e-05,
+      "loss": 0.0735,
+      "step": 4250
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.2321428571428575e-05,
+      "loss": 0.0748,
+      "step": 4375
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.0691,
+      "step": 4500
+    },
+    {
+      "epoch": 1.8,
+      "eval_accuracy": 0.97095,
+      "eval_f1": 0.9703949044585987,
+      "eval_loss": 0.09402387589216232,
+      "eval_precision": 0.9687658968358938,
+      "eval_recall": 0.972029399755002,
+      "eval_runtime": 52.5632,
+      "eval_samples_per_second": 380.494,
+      "eval_steps_per_second": 23.781,
+      "step": 4500
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 2.0535714285714285e-05,
+      "loss": 0.0655,
+      "step": 4625
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.9642857142857145e-05,
+      "loss": 0.0714,
+      "step": 4750
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.0783,
+      "step": 4875
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 0.0733,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.96855,
+      "eval_f1": 0.9683171309122047,
+      "eval_loss": 0.10380826145410538,
+      "eval_precision": 0.9557522123893806,
+      "eval_recall": 0.9812168231931401,
+      "eval_runtime": 52.269,
+      "eval_samples_per_second": 382.636,
+      "eval_steps_per_second": 23.915,
+      "step": 5000
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.6964285714285715e-05,
+      "loss": 0.0461,
+      "step": 5125
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.6071428571428572e-05,
+      "loss": 0.0451,
+      "step": 5250
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.5178571428571429e-05,
+      "loss": 0.0502,
+      "step": 5375
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.0476,
+      "step": 5500
+    },
+    {
+      "epoch": 2.2,
+      "eval_accuracy": 0.9714,
+      "eval_f1": 0.9709909727152854,
+      "eval_loss": 0.10657692700624466,
+      "eval_precision": 0.9648256399919372,
+      "eval_recall": 0.9772356063699469,
+      "eval_runtime": 51.6788,
+      "eval_samples_per_second": 387.006,
+      "eval_steps_per_second": 24.188,
+      "step": 5500
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.3392857142857144e-05,
+      "loss": 0.0522,
+      "step": 5625
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.25e-05,
+      "loss": 0.0476,
+      "step": 5750
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.1607142857142857e-05,
+      "loss": 0.0404,
+      "step": 5875
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.047,
+      "step": 6000
+    },
+    {
+      "epoch": 2.4,
+      "eval_accuracy": 0.96895,
+      "eval_f1": 0.9686316108501288,
+      "eval_loss": 0.10983184725046158,
+      "eval_precision": 0.9587041295870413,
+      "eval_recall": 0.9787668436096366,
+      "eval_runtime": 52.0939,
+      "eval_samples_per_second": 383.922,
+      "eval_steps_per_second": 23.995,
+      "step": 6000
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 9.821428571428573e-06,
+      "loss": 0.0426,
+      "step": 6125
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.92857142857143e-06,
+      "loss": 0.0396,
+      "step": 6250
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 8.035714285714286e-06,
+      "loss": 0.0481,
+      "step": 6375
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.0431,
+      "step": 6500
+    },
+    {
+      "epoch": 2.6,
+      "eval_accuracy": 0.9711,
+      "eval_f1": 0.9706211243265224,
+      "eval_loss": 0.11103978008031845,
+      "eval_precision": 0.9665924276169265,
+      "eval_recall": 0.9746835443037974,
+      "eval_runtime": 54.7325,
+      "eval_samples_per_second": 365.413,
+      "eval_steps_per_second": 22.838,
+      "step": 6500
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.25e-06,
+      "loss": 0.0396,
+      "step": 6625
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.0446,
+      "step": 6750
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.464285714285715e-06,
+      "loss": 0.0362,
+      "step": 6875
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.5714285714285714e-06,
+      "loss": 0.0464,
+      "step": 7000
+    },
+    {
+      "epoch": 2.8,
+      "eval_accuracy": 0.9697,
+      "eval_f1": 0.9693970306029694,
+      "eval_loss": 0.11486733704805374,
+      "eval_precision": 0.9592244653208075,
+      "eval_recall": 0.9797876684360963,
+      "eval_runtime": 52.2973,
+      "eval_samples_per_second": 382.429,
+      "eval_steps_per_second": 23.902,
+      "step": 7000
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.6785714285714285e-06,
+      "loss": 0.0431,
+      "step": 7125
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.7857142857142857e-06,
+      "loss": 0.0343,
+      "step": 7250
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.928571428571428e-07,
+      "loss": 0.0467,
+      "step": 7375
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.0342,
+      "step": 7500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9703,
+      "eval_f1": 0.9699270959902794,
+      "eval_loss": 0.11218974739313126,
+      "eval_precision": 0.9621333869023704,
+      "eval_recall": 0.9778481012658228,
+      "eval_runtime": 52.6026,
+      "eval_samples_per_second": 380.209,
+      "eval_steps_per_second": 23.763,
+      "step": 7500
+    },
+    {
+      "epoch": 3.0,
+      "step": 7500,
+      "total_flos": 4.553211650587354e+16,
+      "train_loss": 0.08937127710183461,
+      "train_runtime": 4426.0374,
+      "train_samples_per_second": 108.449,
+      "train_steps_per_second": 1.695
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9714,
+      "eval_f1": 0.9709909727152854,
+      "eval_loss": 0.10657692700624466,
+      "eval_precision": 0.9648256399919372,
+      "eval_recall": 0.9772356063699469,
+      "eval_runtime": 52.9584,
+      "eval_samples_per_second": 377.655,
+      "eval_steps_per_second": 23.603,
+      "step": 7500
+    }
+  ],
+  "max_steps": 7500,
+  "num_train_epochs": 3,
+  "total_flos": 4.553211650587354e+16,
+  "trial_name": null,
+  "trial_params": null
+}

runs/Mar14_20-34-07_AROZYM/1678822455.5490243/events.out.tfevents.1678822455.AROZYM.16852.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e49c3016098df08fcf83bb49cea9a857c5593a89f2e9b9b3cd1784d323f6bb84
+size 5710

runs/Mar14_20-34-07_AROZYM/events.out.tfevents.1678822455.AROZYM.16852.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db08e1b90c90067776c1e15d37cc7a8d26a54bc05fb7fc5d9613ed2f30e41b6
+size 21036

runs/Mar14_20-34-07_AROZYM/events.out.tfevents.1678826935.AROZYM.16852.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1594f661d83b602890f5bf87ce4c11486081cd819d02ce577ae50386c0e40b33
+size 512

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3343c132ab69ea1d603a332bf27f2e9c2a72d227f7194ec4d73ebfc0b0f09d4
+size 272534616

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 1,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

train_log.txt

@@ -1,29 +0,0 @@
-Writing logs to ./outputs/2023-02-12-23-30-37-265125/train_log.txt.
-Wrote original training args to ./outputs/2023-02-12-23-30-37-265125/training_args.json.
-***** Running training *****
-  Num examples = 160000
-  Num epochs = 3
-  Num clean epochs = 3
-  Instantaneous batch size per device = 64
-  Total train batch size (w. parallel, distributed & accumulation) = 64
-  Gradient accumulation steps = 1
-  Total optimization steps = 7500
-==========================================================
-Epoch 1
-Running clean epoch 1/3
-Train accuracy: 94.11%
-Eval accuracy: 96.77%
-Best score found. Saved model to ./outputs/2023-02-12-23-30-37-265125/best_model/
-==========================================================
-Epoch 2
-Running clean epoch 2/3
-Train accuracy: 97.52%
-Eval accuracy: 96.95%
-Best score found. Saved model to ./outputs/2023-02-12-23-30-37-265125/best_model/
-==========================================================
-Epoch 3
-Running clean epoch 3/3
-Train accuracy: 98.70%
-Eval accuracy: 97.07%
-Best score found. Saved model to ./outputs/2023-02-12-23-30-37-265125/best_model/
-Wrote README to ./outputs/2023-02-12-23-30-37-265125/README.md.

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3e252df7bb1c760edf828ca28397c7d4e9cca53a7f15ee0bea8c2efbfb54af
+size 3515

training_args.json

@@ -1,38 +0,0 @@
-{
-    "model_name_or_path": "cmarkea/distilcamembert-base",
-    "attack": null,
-    "dataset": "allocine",
-    "task_type": "classification",
-    "model_max_length": null,
-    "model_num_labels": null,
-    "dataset_train_split": "train",
-    "dataset_eval_split": "validation",
-    "filter_train_by_labels": null,
-    "filter_eval_by_labels": null,
-    "num_epochs": 3,
-    "num_clean_epochs": 1,
-    "attack_epoch_interval": 1,
-    "early_stopping_epochs": null,
-    "learning_rate": 5e-05,
-    "num_warmup_steps": 500,
-    "weight_decay": 0.01,
-    "per_device_train_batch_size": 64,
-    "per_device_eval_batch_size": 32,
-    "gradient_accumulation_steps": 1,
-    "random_seed": 786,
-    "parallel": false,
-    "load_best_model_at_end": false,
-    "alpha": 1.0,
-    "num_train_adv_examples": -1,
-    "query_budget_train": null,
-    "attack_num_workers_per_device": 1,
-    "output_dir": "./outputs/2023-02-12-23-30-37-265125",
-    "checkpoint_interval_steps": null,
-    "checkpoint_interval_epochs": null,
-    "save_last": true,
-    "log_to_tb": false,
-    "tb_log_dir": null,
-    "log_to_wandb": false,
-    "wandb_project": "textattack",
-    "logging_interval_step": 1
-}