Training in progress, epoch 1

config.json

@@ -22,19 +22,8 @@
   "pad_token_id": 1,
   "position_embedding_type": "rotary",
   "problem_type": "single_label_classification",
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float32",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": false,
-    "load_in_8bit": true
-  },
   "token_dropout": true,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.31.0",
   "use_cache": true,
   "vocab_list": null,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30f7ba1e20b77366e29f751191b30532d1226d9fcbaf515389673894b944d86e
-size 657690261
+oid sha256:fbafb3bbca982740175cabf68ac5f591354fa1f164bff086d4651b159973f6b7
+size 2609624697

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06addd99c04ccb23a824f9e83bb80578e0ea875f43501b7629aed8583e3f69a
+oid sha256:ed234b1823f669796312a7d2385490a2c047dbd7a9ad601142b6b79af633e56a
 size 4027