Training in progress, step 500

config.json

@@ -1,54 +1,60 @@
 {
-  "_name_or_path": "sshleifer/tiny-mbart",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": true,
+  "_name_or_path": "allenai/unifiedqa-t5-small",
   "architectures": [
-    "MBartForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classif_dropout": 0.0,
-  "classifier_dropout": 0.0,
-  "d_model": 2,
-  "decoder_attention_heads": 1,
-  "decoder_ffn_dim": 4,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 2,
-  "dropout": 0.1,
-  "encoder_attention_heads": 1,
-  "encoder_ffn_dim": 4,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 2,
-  "eos_token_id": 2,
-  "extra_pos_embeddings": 2,
-  "forced_eos_token_id": 2,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_position_embeddings": 1024,
-  "model_type": "mbart",
-  "normalize_before": true,
-  "normalize_embedding": true,
-  "num_beams": 2,
-  "num_hidden_layers": 12,
+  "is_gated_act": 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": 1,
-  "scale_embedding": true,
-  "static_position_embeddings": false,
+  "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: "
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.27.4",
   "use_cache": true,
-  "vocab_size": 250027
+  "vocab_size": 32128
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45926d2d29f29874d15a57de5cb66b3fe26a6b8819b3b6d070677b181bcbb595
-size 3048849
+oid sha256:e73d209ccb44d403f58fc3d42b34d45a32fa1a39df5618b6b7707d9483d9c7ed
+size 242071641

runs/Apr06_19-39-43_47dcbd1ef39a/1680810003.815973/events.out.tfevents.1680810003.47dcbd1ef39a.328.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77fbdfb61a09d4da1bbf037634c1408b8e4e11d4166776333e38dd969e53e6ad
+size 6059

runs/Apr06_19-39-43_47dcbd1ef39a/events.out.tfevents.1680810003.47dcbd1ef39a.328.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d24a7f58d0b9c854b6199d51c0908071c23c7754efa94a633f57f1c52b4fc31
+size 4184

runs/Apr06_19-41-14_47dcbd1ef39a/1680810101.25111/events.out.tfevents.1680810101.47dcbd1ef39a.27865.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7b577a8c17165740e19f49d1ea90630c93311c2ebf0c683485cb30a9954ea1
+size 6059

runs/Apr06_19-41-14_47dcbd1ef39a/events.out.tfevents.1680810101.47dcbd1ef39a.27865.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465d394244c12dd82d73078fcade5ea578c4e24463e7777264403fd0ecefc7d6
+size 5069

special_tokens_map.json

@@ -1,36 +1,107 @@
 {
   "additional_special_tokens": [
-    "ar_AR",
-    "cs_CZ",
-    "de_DE",
-    "en_XX",
-    "es_XX",
-    "et_EE",
-    "fi_FI",
-    "fr_XX",
-    "gu_IN",
-    "hi_IN",
-    "it_IT",
-    "ja_XX",
-    "kk_KZ",
-    "ko_KR",
-    "lt_LT",
-    "lv_LV",
-    "my_MM",
-    "ne_NP",
-    "nl_XX",
-    "ro_RO",
-    "ru_RU",
-    "si_LK",
-    "tr_TR",
-    "vi_VN",
-    "zh_CN"
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
   ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": "<mask>",
   "pad_token": "<pad>",
-  "sep_token": "</s>",
   "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74bffd4a8169261070f051ed2d4c68a28c4182dd65289e561ec3c1d24e3ed1b4
-size 17103689
+oid sha256:b3f1e36a9d2c8260890158dc6f113ab221fc696374666d348b4f4fdcf9f4eca7
+size 2424162

tokenizer_config.json

@@ -1,23 +1,112 @@
 {
-  "additional_special_tokens": null,
-  "bos_token": "<s>",
-  "cls_token": "<s>",
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
   "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 1024,
+  "extra_ids": 100,
+  "model_max_length": 512,
   "pad_token": "<pad>",
-  "sep_token": "</s>",
   "sp_model_kwargs": {},
-  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--sshleifer--tiny-mbart/snapshots/9d6b9b3b2774b464bb6b14eda4efe30f82846136/special_tokens_map.json",
-  "src_lang": null,
-  "tgt_lang": null,
-  "tokenizer_class": "MBartTokenizer",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--allenai--unifiedqa-t5-small/snapshots/10c4e0cdd2d24039b09ca2057a80e7e893b9d618/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:428dcf2f0157272fb5e7030bc1bdba0337eb18cbf651000a484744fb5acd3a58
+oid sha256:59ccc9e178bebb22ac6767367e7eed33a66645d768925aaaa9d65ec36720977d
 size 3707