Model save

README.md

@@ -9,21 +9,21 @@ metrics:
 - precision
 - recall
 model-index:
-- name: clapAI/modernBERT-base-multilingual-sentiment
+- name: modernBERT-base-multilingual-sentiment
   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. -->
 
-# clapAI/modernBERT-base-multilingual-sentiment
+# modernBERT-base-multilingual-sentiment
 
 This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8330
-- F1: 0.1291
-- Precision: 0.1650
-- Recall: 0.1890
+- Loss: 0.5464
+- F1: 0.7944
+- Precision: 0.7945
+- Recall: 0.7944
 
 ## Model description
 
@@ -42,26 +42,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 6e-05
-- train_batch_size: 1024
-- eval_batch_size: 1024
+- learning_rate: 5e-05
+- train_batch_size: 512
+- eval_batch_size: 512
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 2
+- gradient_accumulation_steps: 2
 - total_train_batch_size: 2048
-- total_eval_batch_size: 2048
+- total_eval_batch_size: 1024
 - optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.01
-- num_epochs: 2.0
+- num_epochs: 5.0
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|
-| 1.8373        | 1.0   | 8    | 1.8330          | 0.1291 | 0.1650    | 0.1890 |
-| 1.8364        | 2.0   | 16   | 1.8330          | 0.1291 | 0.1650    | 0.1890 |
+| 0.9287        | 1.0   | 1537 | 0.4626          | 0.7910 | 0.7940    | 0.7897 |
+| 0.8356        | 2.0   | 3074 | 0.4441          | 0.8011 | 0.8009    | 0.8015 |
+| 0.7488        | 3.0   | 4611 | 0.4517          | 0.8012 | 0.8020    | 0.8007 |
+| 0.6177        | 4.0   | 6148 | 0.4915          | 0.7990 | 0.7989    | 0.7991 |
+| 0.5174        | 5.0   | 7685 | 0.5464          | 0.7944 | 0.7945    | 0.7944 |
 
 
 ### Framework versions

all_results.json

@@ -1,21 +1,7 @@
 {
-    "epoch": 2.0,
-    "eval_f1": 0.12910686958067819,
-    "eval_loss": 1.8330078125,
-    "eval_precision": 0.16504066117321736,
-    "eval_recall": 0.1890018282051825,
-    "eval_runtime": 0.2271,
-    "eval_samples_per_second": 8807.622,
-    "eval_steps_per_second": 4.404,
-    "test_f1": 0.12457335796698589,
-    "test_loss": 1.833984375,
-    "test_precision": 0.16755594823291797,
-    "test_recall": 0.1749254997504109,
-    "test_runtime": 0.3221,
-    "test_samples_per_second": 6208.711,
-    "test_steps_per_second": 3.104,
-    "train_loss": 1.836273193359375,
-    "train_runtime": 55.8529,
-    "train_samples_per_second": 572.934,
-    "train_steps_per_second": 0.286
+    "epoch": 5.0,
+    "train_loss": 0.7729351929743412,
+    "train_runtime": 35402.7725,
+    "train_samples_per_second": 444.524,
+    "train_steps_per_second": 0.217
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a54a318fd1bb50cb88a677bf2ff027f4de21277d4ec560034f5043ee00b5c474
+oid sha256:f152c2ee66c141d5e3c8db7cb2e5f370cdd43111bd53550090a854bd26ff1a04
 size 299228486

runs/Jan01_01-03-55_hn-fornix-testing-gpu-platform-2/events.out.tfevents.1735693897.hn-fornix-testing-gpu-platform-2.1050019.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19bf24c9129f79411bdf64da387be27e16721b61fb93731ca2320dfa393100cf
-size 331926
+oid sha256:3f637f923a9e8194e170c3f0a35eb85270b3448100dd12145be613bdeb655932
+size 332700

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 2.0,
-    "train_loss": 1.836273193359375,
-    "train_runtime": 55.8529,
-    "train_samples_per_second": 572.934,
-    "train_steps_per_second": 0.286
+    "epoch": 5.0,
+    "train_loss": 0.7729351929743412,
+    "train_runtime": 35402.7725,
+    "train_samples_per_second": 444.524,
+    "train_steps_per_second": 0.217
 }