ILC-CNR/gs-aristoBERTo

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+base_model: Jacobo/aristoBERTo
+tags:
+- generated_from_trainer
+model-index:
+- name: model-checkpoints
+  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. -->
+
+# model-checkpoints
+
+This model is a fine-tuned version of [Jacobo/aristoBERTo](https://huggingface.co/Jacobo/aristoBERTo) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9964
+
+## 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
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 2.9782        | 1.0   | 5617  | 2.5919          |
+| 2.5711        | 2.0   | 11234 | 2.4118          |
+| 2.4112        | 3.0   | 16851 | 2.3027          |
+| 2.2997        | 4.0   | 22468 | 2.2044          |
+| 2.2077        | 5.0   | 28085 | 2.1578          |
+| 2.1414        | 6.0   | 33702 | 2.1075          |
+| 2.0819        | 7.0   | 39319 | 2.0618          |
+| 2.0388        | 8.0   | 44936 | 2.0305          |
+| 2.0048        | 9.0   | 50553 | 2.0053          |
+| 1.9773        | 10.0  | 56170 | 2.0138          |
+
+
+### Framework versions
+
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

README.md

@@ -4,18 +4,18 @@ base_model: Jacobo/aristoBERTo
 tags:
 - generated_from_trainer
 model-index:
-- name: gs-aristoBERTo
+- name: model-checkpoints
   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. -->
 
-# gs-aristoBERTo
+# model-checkpoints
 
 This model is a fine-tuned version of [Jacobo/aristoBERTo](https://huggingface.co/Jacobo/aristoBERTo) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9964
+- Loss: 2.0134
 
 ## Model description
 

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 10.0,
-    "eval_loss": 1.9963876008987427,
-    "eval_runtime": 19.7328,
-    "eval_samples_per_second": 504.035,
-    "eval_steps_per_second": 31.521,
+    "eval_loss": 2.0134475231170654,
+    "eval_runtime": 19.8825,
+    "eval_samples_per_second": 500.238,
+    "eval_steps_per_second": 31.284,
     "step": 56170,
     "total_flos": 2.956997406572544e+16,
     "train_loss": 2.2712038545097473,

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 10.0,
-    "eval_loss": 1.9963876008987427,
-    "eval_runtime": 19.7328,
-    "eval_samples_per_second": 504.035,
-    "eval_steps_per_second": 31.521
+    "eval_loss": 2.0134475231170654,
+    "eval_runtime": 19.8825,
+    "eval_samples_per_second": 500.238,
+    "eval_steps_per_second": 31.284
 }

train_results.json

@@ -1,9 +1,8 @@
 {
     "epoch": 10.0,
-    "step": 56170,
-    "total_flos": 2.956997406572544e+16,
-    "train_loss": 2.2712038545097473,
-    "train_runtime": 6201.2863,
-    "train_samples_per_second": 144.928,
-    "train_steps_per_second": 9.058
+    "eval_loss": 2.044799327850342,
+    "eval_runtime": 19.8691,
+    "eval_samples_per_second": 500.576,
+    "eval_steps_per_second": 31.305,
+    "step": 56170
 }

trainer_state.json

@@ -175,6 +175,30 @@
       "eval_samples_per_second": 504.035,
       "eval_steps_per_second": 31.521,
       "step": 56170
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.996718406677246,
+      "eval_runtime": 20.2309,
+      "eval_samples_per_second": 491.623,
+      "eval_steps_per_second": 30.745,
+      "step": 56170
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.044799327850342,
+      "eval_runtime": 19.8691,
+      "eval_samples_per_second": 500.576,
+      "eval_steps_per_second": 31.305,
+      "step": 56170
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.0134475231170654,
+      "eval_runtime": 19.8825,
+      "eval_samples_per_second": 500.238,
+      "eval_steps_per_second": 31.284,
+      "step": 56170
     }
   ],
   "logging_steps": 500,