End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
+- Loss: 1.4653
 
 ## Model description
 
@@ -42,13 +42,14 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 2
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 0.9316        | 1.0   | 8134  | nan             |
-| 0.7836        | 2.0   | 16268 | nan             |
+| 1.3678        | 1.0   | 8134  | 1.4974          |
+| 1.1809        | 2.0   | 16268 | 1.4653          |
 
 
 ### Framework versions

config.json

@@ -20,5 +20,5 @@
   "transformers_version": "4.57.1",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30523
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e20e70325bc2b04edfedb4e579e588f7cd79b760045af7a77c1b673953fb0d0
-size 132876360
+oid sha256:05f5ffd839326b9220d1c28a932e820badfad6bb2c8bc6b72d932140154a293c
+size 132874824

runs/Nov20_03-14-07_26cd4a53f5b5/events.out.tfevents.1763608469.26cd4a53f5b5.285.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43eb94c897b5ff07d4efc529d48c6820577f3cfb22bbff0c0795655760a327d2
+size 40020

tokenizer.json

@@ -1,14 +1,7 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": {
-    "strategy": "BatchLongest",
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,
@@ -54,15 +47,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 30522,
-      "content": "<no_answer>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": true,
-      "special": false
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -39,14 +39,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "30522": {
-      "content": "<no_answer>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "clean_up_tokenization_spaces": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6af54618a182499fbc4c29b222e2ef83f7628c325d27b2cd7d78932d872b0eb9
+oid sha256:498c5d0fc3f7a62a2d8f4e0d73a974ec2f3d7b792fb80caafbb5a0cc19250cad
 size 5841