Add 50k train step model

config.json

@@ -1,31 +1,32 @@
 {
-    "architectures": [
-      "T5ForConditionalGeneration"
-    ],
-    "d_ff": 3072,
-    "d_kv": 64,
-    "d_model": 768,
-    "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": 36,
-    "num_heads": 12,
-    "num_layers": 36,
-    "output_past": true,
-    "pad_token_id": 0,
-    "relative_attention_max_distance": 128,
-    "relative_attention_num_buckets": 32,
-    "tie_word_embeddings": false,
-    "torch_dtype": "float32",
-    "transformers_version": "4.20.1",
-    "use_cache": true,
-    "vocab_size": 32128
-  }
+  "_name_or_path": "./",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 36,
+  "num_heads": 12,
+  "num_layers": 36,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aca80f851cef0865834cdf9e210cbaf7f423adae2146a2dc72d12d06807d0cd
+size 3255640203

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bd2911201cdff91021c360aaf8911c5deb6c34d9401304b2e5b4eeb2c8e963
+size 3255876157

train/events.out.tfevents.1666371310.t1v-n-12f94ad0-w-0.556051.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec174375c1c148e5ef07745a54fd61dc130b962b15bad8738104f278650d97f
-size 7475
+oid sha256:7e7d697d5580620db45e645540ef5ab6bee7e91acae95abe8b178ea4b03aa51f
+size 15195

training_eval/pretrain_finnish_ul2/events.out.tfevents.1666371310.t1v-n-12f94ad0-w-0.556051.1.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d4be65a8327d80518f5112f644459714a7c9b936736d60465b726bb44abfb6d
-size 1414
+oid sha256:27371b1e492a9305ec62a39655915c0a02f594a34201adecb1de150f59096f97
+size 7939