Saving weights and logs of epoch 6

config.json

@@ -1,72 +1,56 @@
 {
-  "activation_dropout": 0.1,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
   "architectures": [
-    "BartForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
-  "classif_dropout": 0.1,
-  "classifier_dropout": 0.0,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "early_stopping": true,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
-  "eos_token_id": 2,
-  "forced_eos_token_id": 2,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
   "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
+  "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_position_embeddings": 1024,
-  "model_type": "bart",
-  "no_repeat_ngram_size": 3,
-  "normalize_before": false,
-  "normalize_embedding": true,
-  "num_beams": 4,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "scale_embedding": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
   "task_specific_params": {
     "summarization": {
-      "length_penalty": 1.0,
-      "max_length": 128,
-      "min_length": 12,
-      "num_beams": 4
-    },
-    "summarization_cnn": {
+      "early_stopping": true,
       "length_penalty": 2.0,
-      "max_length": 142,
-      "min_length": 56,
-      "num_beams": 4
+      "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: "
     },
-    "summarization_xsum": {
-      "length_penalty": 1.0,
-      "max_length": 62,
-      "min_length": 11,
-      "num_beams": 6
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
     }
   },
   "transformers_version": "4.9.0.dev0",
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 32128
 }

events.out.tfevents.1625748488.t1v-n-55481057-w-0.11425.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ec6cfa32670697f1020442545113d0ad7d318ea7dcb49eb6e9c43db1bb6a07
+size 40

events.out.tfevents.1625750642.t1v-n-55481057-w-0.13150.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd708a2e432614fa47e6c6aa1067025104a83b520c50ab3216e78a5a34af4029
+size 40

events.out.tfevents.1625751050.t1v-n-55481057-w-0.14560.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc9a343c02cd4d8da5b72b2340b1de36be03daf037cc7fd36978e3fcd21a9a2d
+size 40

events.out.tfevents.1625751784.t1v-n-55481057-w-0.16113.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54355ab814762385332d951d85e8552c147a1b780d50c45dea937dea727a4b67
+size 360093

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2967dc84e5986b6da3d8dee96b9fda24588ad9232ad087badae5c69a0b82cc8a
-size 557891914
+oid sha256:f97bea09ce90bbdea07aa8a1604a586e3b7ed2793438419907b508a1cc081354
+size 242032202