Training in progress, step 500

config.json

@@ -51,21 +51,10 @@
   "num_beams": 4,
   "num_hidden_layers": 6,
   "pad_token_id": 53684,
-  "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
-  },
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.30.2",
   "use_cache": true,
   "vocab_size": 53685

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3c46aa7365a2cb2c597e16414f0a1e2e223ae25928ced09807ee92fc0c32c8d
-size 99706629
+oid sha256:a5913eebb80fb8c4269025215a90a1c64d5f7cb8f29226ab155f8edb8aadee2c
+size 286802117

runs/Jun14_20-41-22_f35e615155df/events.out.tfevents.1686775287.f35e615155df.2084.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f3da4d450c15d2eab4a46e38f45eb8cba372e83c8ca6c3f79d2cf7f008adef
+size 5084

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de81070449d08abb1bfc3f450d0d4a1eded1111aa985c9bff410afe8e31103cf
+oid sha256:47f045922a64b99541982fd181635e8c92634f12416ef1590e05a46183ba66f3
 size 4091