Periodic upload

README.md

@@ -9,7 +9,7 @@ library_name: transformers
 
 ## Progreso de Entrenamiento
 
-- **Datasets procesados:** 0.0
-- **Ejemplos de texto procesados:** 0.0
-- **Tokens procesados:** 0.0
-- **Última subida:** 2025-05-06 14:31:08 UTC
+- **Datasets procesados:** 3.0
+- **Ejemplos de texto procesados:** 9.0
+- **Tokens procesados:** 4434.0
+- **Última subida:** 2025-05-06 14:32:12 UTC

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3ef577587882ee849f7128857a15ba4dd2c5885c6d189bf033b15f343182f5
+oid sha256:5ec694330f318cc4748e5749da1919ab636e66c0dbdcbd15b60aae6061228e77
 size 51957256

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -6,16 +6,7 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Left",
-    "pad_to_multiple_of": null,
-    "pad_id": 2,
-    "pad_type_id": 0,
-    "pad_token": "</s>"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training.log

@@ -7,3 +7,14 @@
 2025-05-06 16:30:41,433 INFO: HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK"
 2025-05-06 16:31:07,974 INFO: Fetched 379843 datasets to process.
 2025-05-06 16:31:08,585 INFO: Preparing data for nvidia/Nemotron-CrossThink, config: default
+2025-05-06 16:31:12,688 INFO: Upload successful.
+2025-05-06 16:31:12,688 INFO: Preparing data for nvidia/OpenMathReasoning, config: default
+2025-05-06 16:31:14,303 INFO: Starting model update for nvidia/Nemotron-CrossThink, config: default
+2025-05-06 16:31:17,591 INFO: Finished training and saved model/tokenizer for nvidia/Nemotron-CrossThink config default
+2025-05-06 16:31:17,595 ERROR: Error in background_training_loop task scheduling: local variable 'merged_model' referenced before assignment
+2025-05-06 16:31:17,970 INFO: Preparing data for nvidia/OpenCodeReasoning, config: split_0
+2025-05-06 16:31:18,439 INFO: Starting model update for nvidia/OpenMathReasoning, config: default
+2025-05-06 16:31:21,695 INFO: Finished training and saved model/tokenizer for nvidia/OpenMathReasoning config default
+2025-05-06 16:31:21,776 ERROR: Failed to get configs for rajpurkarlab/ReXGradient-160K: Dataset 'rajpurkarlab/ReXGradient-160K' is a gated dataset on the Hub. Visit the dataset page at https://huggingface.co/datasets/rajpurkarlab/ReXGradient-160K to ask for access.
+2025-05-06 16:31:29,921 INFO: Starting model update for nvidia/OpenCodeReasoning, config: split_0
+2025-05-06 16:31:39,156 INFO: Finished training and saved model/tokenizer for nvidia/OpenCodeReasoning config split_0