End of training

all_results.json

@@ -1 +1 @@
-{"eval_rouge-1": {"r": 0.01, "p": 0.008333333333333333, "f": 0.008999999804000004}, "eval_rouge-2": {"r": 0.0, "p": 0.0, "f": 0.0}, "eval_rouge-l": {"r": 0.01, "p": 0.008333333333333333, "f": 0.008999999804000004}, "eval_train_loss": 25.8240478515625, "eval_epoch": 0, "eval_step": 1}
+{"eval_rouge-1": {"r": 0.1802347756169341, "p": 0.2915507716979137, "f": 0.21042771186220902}, "eval_rouge-2": {"r": 0.07126234516244569, "p": 0.11686090216568425, "f": 0.08278711388462458}, "eval_rouge-l": {"r": 0.16555153326277958, "p": 0.26936008093199915, "f": 0.19361095894891645}}

config.json

@@ -3,15 +3,18 @@
   "architectures": [
     "MT5ForConditionalGeneration"
   ],
+  "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": "mt5",
   "num_decoder_layers": 8,
@@ -23,7 +26,7 @@
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.18.0.dev0",
+  "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 250112
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.1"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6b432432b3a2bb6b90862f31c7fd87f96492677e5765d02ce6b4c3317f5fc06
+oid sha256:d2ff68fc514141ab3bb7d9944b2a334a30728ee174af4ec6b04af037fc213ec8
 size 1200773058

special_tokens_map.json

@@ -1 +1,23 @@
-{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af95700bf514fc57a9f58055fec955839f0a378f707ddbc3df840291cbb709db
-size 16330466
+oid sha256:4ebf4569386813d4b10b8198e64a3c0cdd75cd8ad27824426b3a558e7e861053
+size 16330494

tokenizer_config.json

@@ -1 +1,38 @@
-{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/yubin/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}