add model

README.md

@@ -16,7 +16,7 @@ model_index:
     metric:
       name: Accuracy
       type: accuracy
-      value: 0.9860828488372093
+      value: 0.991500810518732
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -26,11 +26,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on an unkown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0503
-- Precision: 0.9333
-- Recall: 0.9275
-- F1: 0.9304
-- Accuracy: 0.9861
+- Loss: 0.0301
+- Precision: 0.9601
+- Recall: 0.9527
+- F1: 0.9564
+- Accuracy: 0.9915
 
 ## Model description
 

all_results.json

@@ -1,25 +1,25 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.9860828488372093,
-    "eval_f1": 0.9304015991277484,
-    "eval_loss": 0.05031319707632065,
-    "eval_precision": 0.9332847247539191,
-    "eval_recall": 0.927536231884058,
-    "eval_runtime": 3.16,
-    "eval_samples": 430,
-    "eval_samples_per_second": 136.078,
-    "eval_steps_per_second": 17.089,
-    "predict_accuracy": 0.9901502991390632,
-    "predict_f1": 0.952212389380531,
-    "predict_loss": 0.03813100978732109,
-    "predict_precision": 0.9662356321839081,
-    "predict_recall": 0.9385903698534543,
-    "predict_runtime": 3.1212,
-    "predict_samples_per_second": 137.449,
-    "predict_steps_per_second": 17.301,
-    "train_loss": 0.059730371578719264,
-    "train_runtime": 194.0601,
-    "train_samples": 3434,
-    "train_samples_per_second": 53.087,
-    "train_steps_per_second": 3.324
+    "eval_accuracy": 0.991500810518732,
+    "eval_f1": 0.9564196794489446,
+    "eval_loss": 0.03012062981724739,
+    "eval_precision": 0.9601328903654485,
+    "eval_recall": 0.9527350787748687,
+    "eval_runtime": 30.7406,
+    "eval_samples": 4164,
+    "eval_samples_per_second": 135.456,
+    "eval_steps_per_second": 16.948,
+    "predict_accuracy": 0.9907505424296343,
+    "predict_f1": 0.952959144711722,
+    "predict_loss": 0.03142160549759865,
+    "predict_precision": 0.9562085743841232,
+    "predict_recall": 0.9497317249514822,
+    "predict_runtime": 31.6681,
+    "predict_samples_per_second": 131.457,
+    "predict_steps_per_second": 16.452,
+    "train_loss": 0.02315408722391657,
+    "train_runtime": 2017.0522,
+    "train_samples": 33304,
+    "train_samples_per_second": 49.534,
+    "train_steps_per_second": 3.097
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 0.9860828488372093,
-    "eval_f1": 0.9304015991277484,
-    "eval_loss": 0.05031319707632065,
-    "eval_precision": 0.9332847247539191,
-    "eval_recall": 0.927536231884058,
-    "eval_runtime": 3.16,
-    "eval_samples": 430,
-    "eval_samples_per_second": 136.078,
-    "eval_steps_per_second": 17.089
+    "eval_accuracy": 0.991500810518732,
+    "eval_f1": 0.9564196794489446,
+    "eval_loss": 0.03012062981724739,
+    "eval_precision": 0.9601328903654485,
+    "eval_recall": 0.9527350787748687,
+    "eval_runtime": 30.7406,
+    "eval_samples": 4164,
+    "eval_samples_per_second": 135.456,
+    "eval_steps_per_second": 16.948
 }

predict_results.json

@@ -1,10 +1,10 @@
 {
-    "predict_accuracy": 0.9901502991390632,
-    "predict_f1": 0.952212389380531,
-    "predict_loss": 0.03813100978732109,
-    "predict_precision": 0.9662356321839081,
-    "predict_recall": 0.9385903698534543,
-    "predict_runtime": 3.1212,
-    "predict_samples_per_second": 137.449,
-    "predict_steps_per_second": 17.301
+    "predict_accuracy": 0.9907505424296343,
+    "predict_f1": 0.952959144711722,
+    "predict_loss": 0.03142160549759865,
+    "predict_precision": 0.9562085743841232,
+    "predict_recall": 0.9497317249514822,
+    "predict_runtime": 31.6681,
+    "predict_samples_per_second": 131.457,
+    "predict_steps_per_second": 16.452
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c841421b4991274dd8f2e12a18211934ea8b410a43b579a231ceaac23e3e5745
+oid sha256:799b6c8692bf8a5e41950b41508032b2c1a06cffe87aa6d980d208ade3975d39
 size 440216305

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 0.059730371578719264,
-    "train_runtime": 194.0601,
-    "train_samples": 3434,
-    "train_samples_per_second": 53.087,
-    "train_steps_per_second": 3.324
+    "train_loss": 0.02315408722391657,
+    "train_runtime": 2017.0522,
+    "train_samples": 33304,
+    "train_samples_per_second": 49.534,
+    "train_steps_per_second": 3.097
 }

trainer_state.json

@@ -2,30 +2,96 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 3.0,
-  "global_step": 645,
+  "global_step": 6246,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 2.33,
-      "learning_rate": 1.1240310077519382e-05,
-      "loss": 0.0692,
+      "epoch": 0.24,
+      "learning_rate": 4.599743836055075e-05,
+      "loss": 0.0731,
       "step": 500
     },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.1994876721101504e-05,
+      "loss": 0.0345,
+      "step": 1000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7992315081652255e-05,
+      "loss": 0.0299,
+      "step": 1500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.398975344220301e-05,
+      "loss": 0.027,
+      "step": 2000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.998719180275376e-05,
+      "loss": 0.0199,
+      "step": 2500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.5984630163304517e-05,
+      "loss": 0.0183,
+      "step": 3000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.1982068523855268e-05,
+      "loss": 0.018,
+      "step": 3500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.797950688440602e-05,
+      "loss": 0.0175,
+      "step": 4000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.3976945244956775e-05,
+      "loss": 0.0132,
+      "step": 4500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 9.974383605507526e-06,
+      "loss": 0.0114,
+      "step": 5000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 5.971821966058277e-06,
+      "loss": 0.0108,
+      "step": 5500
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.96926032660903e-06,
+      "loss": 0.0105,
+      "step": 6000
+    },
     {
       "epoch": 3.0,
-      "step": 645,
-      "total_flos": 675153499627752.0,
-      "train_loss": 0.059730371578719264,
-      "train_runtime": 194.0601,
-      "train_samples_per_second": 53.087,
-      "train_steps_per_second": 3.324
+      "step": 6246,
+      "total_flos": 6623681170117440.0,
+      "train_loss": 0.02315408722391657,
+      "train_runtime": 2017.0522,
+      "train_samples_per_second": 49.534,
+      "train_steps_per_second": 3.097
     }
   ],
-  "max_steps": 645,
+  "max_steps": 6246,
   "num_train_epochs": 3,
-  "total_flos": 675153499627752.0,
+  "total_flos": 6623681170117440.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82e501ebaafb54fa08b9cc6a6a337a7ed61a65191081ddd5bda8581472f0a7c2
+oid sha256:aa1fa9ff04e58841c66e7e501162366a8cc278043ea6c602d8e2d809df1e4268
 size 2607