devoted-puddle-246 training run with 'None' result when uncertain and some removed layers

.gitattributes

@@ -43,3 +43,15 @@ onnx/encoder_model_quantized.onnx filter=lfs diff=lfs merge=lfs -text
 onnx/decoder_model.onnx filter=lfs diff=lfs merge=lfs -text
 onnx/decoder_model_merged.onnx filter=lfs diff=lfs merge=lfs -text
 spiece.model filter=lfs diff=lfs merge=lfs -text
+onnx/encoder_model_fp16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/encoder_model_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_fp16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_fp16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_model_merged_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model_fp16.onnx filter=lfs diff=lfs merge=lfs -text
+onnx/decoder_with_past_model_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/encoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,64 +1,61 @@
 {
-    "_name_or_path": "elated-lake-212",
-    "architectures": [
-        "T5ForConditionalGeneration"
-    ],
-    "classifier_dropout": 0.0,
-    "d_ff": 1024,
-    "d_kv": 64,
-    "d_model": 512,
-    "decoder_start_token_id": 0,
-    "dense_act_fn": "gelu_new",
-    "dropout_rate": 0.1,
-    "eos_token_id": 1,
-    "feed_forward_proj": "gated-gelu",
-    "initializer_factor": 1.0,
-    "is_encoder_decoder": true,
-    "is_gated_act": true,
-    "layer_norm_epsilon": 1e-06,
-    "model_type": "t5",
-    "n_positions": 512,
-    "num_decoder_layers": 2,
-    "num_heads": 6,
-    "num_layers": 8,
-    "output_past": true,
-    "pad_token_id": 0,
-    "relative_attention_max_distance": 128,
-    "relative_attention_num_buckets": 32,
-    "task_specific_params": {
-        "summarization": {
-            "early_stopping": true,
-            "length_penalty": 2.0,
-            "max_length": 200,
-            "min_length": 30,
-            "no_repeat_ngram_size": 3,
-            "num_beams": 4,
-            "prefix": "summarize: "
-        },
-        "translation_en_to_de": {
-            "early_stopping": true,
-            "max_length": 300,
-            "num_beams": 4,
-            "prefix": "translate English to German: "
-        },
-        "translation_en_to_fr": {
-            "early_stopping": true,
-            "max_length": 300,
-            "num_beams": 4,
-            "prefix": "translate English to French: "
-        },
-        "translation_en_to_ro": {
-            "early_stopping": true,
-            "max_length": 300,
-            "num_beams": 4,
-            "prefix": "translate English to Romanian: "
-        }
+  "_name_or_path": "devoted-puddle-246",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 3,
+  "num_heads": 6,
+  "num_layers": 8,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
     },
-    "tie_word_embeddings": false,
-    "transformers_version": "4.43.4",
-    "use_cache": true,
-    "vocab_size": 32128,
-    "transformers.js_config": {
-        "use_external_data_format": true
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
     }
-}
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "vocab_size": 32128
+}

onnx/decoder_model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0917a6356c30c16edf61db3d65ec651bdbc69fa0894f18938780c5154b7890
-size 80917
+oid sha256:b731e634c14a3e86cf31ca62173f339b46fac394d9b55d339f64fa28fbb6ecd2
+size 169472581

onnx/decoder_model_merged.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b332727c9e4650f644a0bc898a68e35a06931ac30c12d1554d89ddcc800bc3
-size 161054
+oid sha256:4b104f740ae1330a68d2db15abc1389f4dee07f898f89b7b5f63579841c545b3
+size 169578960

onnx/decoder_model_merged_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:047291bc4dc783282486336a9a954991be953cbfc45bbcb817f130224d2ead45
-size 432464
+oid sha256:915cd97d536211a024dee8a5c8fd62f28df7500d2adbe2d34cb52f50cff2b0b9
+size 42895015

onnx/decoder_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3d6730dabdd14036c4d0e4b4933f6a9451137ec8f511973ce3e58b6ab66fef2
-size 328569
+oid sha256:e66f9c506e24690ef63f3d688c04f32463ed0787e10ee32778ded37dafcb2dac
+size 42753832

onnx/decoder_with_past_model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0018eea69567573479b6f2101bb442b4101393cc5bdb7130252560d1bb567b24
-size 71294
+oid sha256:010e70e77e71c88c77e104a41cdbad9f18cdec1a076c2e2b03e2afac16bd17f8
+size 164738287

onnx/decoder_with_past_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb3b930e98e235dd81ef5547aa5c882ed4aa163acf0e2323c7a2988a705cf38
-size 307198
+oid sha256:7df1ded87f3bcc663a7354cb0849bcdcd6b59e1a10f68210bd382fde20123f17
+size 41540983

onnx/encoder_model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35de487ada66c4963c4f8a09d774c1913c210d6481a906746abcd45ee80e7437
-size 142063
+oid sha256:71f91c192b68cae3580efa4149ccc86bf5191d27e12308c30d0bceb18046aaec
+size 141467235

onnx/encoder_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a83b15590f4ed47ba4fec268388c06a400cbdf514a59193617f84f967d515f0
-size 374009
+oid sha256:b63e157a37a2fe369d5d5923e2c2ec229ffb0d119ee79b25a2a5d247e7eb2d15
+size 35726832