Model save

README.md

@@ -1,3 +1,72 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: apache-2.0
+base_model: answerdotai/ModernBERT-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- 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. -->
+
+# 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
+
+## 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: 6e-05
+- train_batch_size: 1024
+- eval_batch_size: 1024
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 2048
+- total_eval_batch_size: 2048
+- 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
+- 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 |
+
+
+### Framework versions
+
+- Transformers 4.48.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

all_results.json

@@ -1,5 +1,5 @@
 {
-    "epoch": 5.0,
+    "epoch": 2.0,
     "eval_f1": 0.5005918962125724,
     "eval_loss": 0.916015625,
     "eval_precision": 0.5713280704919877,
@@ -14,8 +14,8 @@
     "test_runtime": 0.2719,
     "test_samples_per_second": 7355.241,
     "test_steps_per_second": 3.678,
-    "train_loss": 1.565679931640625,
-    "train_runtime": 80.5078,
-    "train_samples_per_second": 993.693,
-    "train_steps_per_second": 0.497
+    "train_loss": 1.836273193359375,
+    "train_runtime": 55.5777,
+    "train_samples_per_second": 575.77,
+    "train_steps_per_second": 0.288
 }

runs/Dec31_23-40-45_hn-fornix-testing-gpu-platform-2/events.out.tfevents.1735688460.hn-fornix-testing-gpu-platform-2.1028595.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:287d08406c1997c6520f7cf436397cbb03265b773d3bbbaeb4210f850067a7d0
-size 6644
+oid sha256:dad1fffc7ba82d9a265fbef176283a5ba7e5c45c1c7c0790d7a059195ce79e46
+size 7818

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 5.0,
-    "train_loss": 1.565679931640625,
-    "train_runtime": 80.5078,
-    "train_samples_per_second": 993.693,
-    "train_steps_per_second": 0.497
+    "epoch": 2.0,
+    "train_loss": 1.836273193359375,
+    "train_runtime": 55.5777,
+    "train_samples_per_second": 575.77,
+    "train_steps_per_second": 0.288
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5005918962125724,
-  "best_model_checkpoint": "./output/modernBERT-base-sentiment-v2/checkpoint-40",
-  "epoch": 5.0,
+  "best_metric": 0.12910686958067819,
+  "best_model_checkpoint": "./output/modernBERT-base-sentiment-v2/checkpoint-8",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 40,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,9 +21,9 @@
       "eval_loss": 1.8330078125,
       "eval_precision": 0.16504066117321736,
       "eval_recall": 0.1890018282051825,
-      "eval_runtime": 8.9078,
-      "eval_samples_per_second": 224.523,
-      "eval_steps_per_second": 0.112,
+      "eval_runtime": 8.3613,
+      "eval_samples_per_second": 239.198,
+      "eval_steps_per_second": 0.12,
       "step": 8
     },
     {
@@ -46,93 +46,25 @@
       "eval_loss": 1.8330078125,
       "eval_precision": 0.16504066117321736,
       "eval_recall": 0.1890018282051825,
-      "eval_runtime": 0.2841,
-      "eval_samples_per_second": 7040.66,
-      "eval_steps_per_second": 3.52,
+      "eval_runtime": 0.2784,
+      "eval_samples_per_second": 7185.079,
+      "eval_steps_per_second": 3.593,
       "step": 16
     },
     {
-      "epoch": 2.5,
-      "grad_norm": 5.113753318786621,
-      "learning_rate": 5.961150787913738e-05,
-      "loss": 1.7937,
-      "step": 20
-    },
-    {
-      "epoch": 3.0,
-      "eval_f1": 0.17970771787293252,
-      "eval_loss": 1.53515625,
-      "eval_precision": 0.22861304458868634,
-      "eval_recall": 0.23211174242424246,
-      "eval_runtime": 0.2207,
-      "eval_samples_per_second": 9062.407,
-      "eval_steps_per_second": 4.531,
-      "step": 24
-    },
-    {
-      "epoch": 3.125,
-      "grad_norm": 1.7188981771469116,
-      "learning_rate": 5.535570256631384e-05,
-      "loss": 1.5896,
-      "step": 25
-    },
-    {
-      "epoch": 3.75,
-      "grad_norm": 1.9793833494186401,
-      "learning_rate": 4.704194240193467e-05,
-      "loss": 1.4145,
-      "step": 30
-    },
-    {
-      "epoch": 4.0,
-      "eval_f1": 0.31283295562034524,
-      "eval_loss": 1.15625,
-      "eval_precision": 0.5734842356008,
-      "eval_recall": 0.33733943473317013,
-      "eval_runtime": 0.1992,
-      "eval_samples_per_second": 10041.198,
-      "eval_steps_per_second": 5.021,
-      "step": 32
-    },
-    {
-      "epoch": 4.375,
-      "grad_norm": 11.112994194030762,
-      "learning_rate": 3.6000770813281334e-05,
-      "loss": 1.2037,
-      "step": 35
-    },
-    {
-      "epoch": 5.0,
-      "grad_norm": 2.136584758758545,
-      "learning_rate": 2.399922918671867e-05,
-      "loss": 1.0167,
-      "step": 40
-    },
-    {
-      "epoch": 5.0,
-      "eval_f1": 0.5005918962125724,
-      "eval_loss": 0.916015625,
-      "eval_precision": 0.5713280704919877,
-      "eval_recall": 0.49814126531372666,
-      "eval_runtime": 0.2727,
-      "eval_samples_per_second": 7333.058,
-      "eval_steps_per_second": 3.667,
-      "step": 40
-    },
-    {
-      "epoch": 5.0,
-      "step": 40,
-      "total_flos": 3738898811322368.0,
-      "train_loss": 1.565679931640625,
-      "train_runtime": 80.5078,
-      "train_samples_per_second": 993.693,
-      "train_steps_per_second": 0.497
+      "epoch": 2.0,
+      "step": 16,
+      "total_flos": 1489153141243904.0,
+      "train_loss": 1.836273193359375,
+      "train_runtime": 55.5777,
+      "train_samples_per_second": 575.77,
+      "train_steps_per_second": 0.288
     }
   ],
   "logging_steps": 5,
-  "max_steps": 40,
+  "max_steps": 16,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 5.0,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -146,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3738898811322368.0,
+  "total_flos": 1489153141243904.0,
   "train_batch_size": 1024,
   "trial_name": null,
   "trial_params": null