Upload model files with correct config

checkpoint-30000/config.json

@@ -0,0 +1,61 @@
+{
+  "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": 8,
+  "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: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

checkpoint-30000/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": "4.54.1"
+}

checkpoint-30000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45802daa7bae4dbb119f8c9e54b494886f3da733db731badb5e1a781b7a11a41
+size 307867048

checkpoint-30000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7465b33ee8e1899b510d652948492e3633883083bbaedc499364fd88f14346
+size 615849867

checkpoint-30000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c04c16f2163f2089182aa0ff39aacbf9a4f62462ce846f1265bf1ce9b46a7e49
+size 14645

checkpoint-30000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9956e4035c40af4cd4c7e5f857691af0027a19a553f94e40b887d66e5eae64a
+size 1465

checkpoint-30000/special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "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": {
+    "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
+  }
+}

checkpoint-30000/tokenizer_config.json

@@ -0,0 +1,940 @@
+{
+  "add_prefix_space": null,
+  "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
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-30000/trainer_state.json

@@ -0,0 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.995203836930456,
+  "eval_steps": 500,
+  "global_step": 30000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019984012789768184,
+      "grad_norm": 10.435233116149902,
+      "learning_rate": 4.9835131894484415e-05,
+      "loss": 14.0782,
+      "step": 100
+    },
+    {
+      "epoch": 0.03996802557953637,
+      "grad_norm": 19.157014846801758,
+      "learning_rate": 4.966859845456968e-05,
+      "loss": 3.596,
+      "step": 200
+    },
+    {
+      "epoch": 0.05995203836930456,
+      "grad_norm": 5.946423530578613,
+      "learning_rate": 4.950206501465495e-05,
+      "loss": 2.0558,
+      "step": 300
+    },
+    {
+      "epoch": 0.07993605115907274,
+      "grad_norm": 2.1558027267456055,
+      "learning_rate": 4.9335531574740214e-05,
+      "loss": 1.3957,
+      "step": 400
+    },
+    {
+      "epoch": 0.09992006394884093,
+      "grad_norm": 2.5541210174560547,
+      "learning_rate": 4.916899813482548e-05,
+      "loss": 1.252,
+      "step": 500
+    },
+    {
+      "epoch": 0.11990407673860912,
+      "grad_norm": 1.8417296409606934,
+      "learning_rate": 4.9002464694910735e-05,
+      "loss": 1.1695,
+      "step": 600
+    },
+    {
+      "epoch": 0.1398880895283773,
+      "grad_norm": 1.654639720916748,
+      "learning_rate": 4.8835931254996005e-05,
+      "loss": 1.1848,
+      "step": 700
+    },
+    {
+      "epoch": 0.15987210231814547,
+      "grad_norm": 2.093991756439209,
+      "learning_rate": 4.866939781508127e-05,
+      "loss": 1.1056,
+      "step": 800
+    },
+    {
+      "epoch": 0.17985611510791366,
+      "grad_norm": 1.9905765056610107,
+      "learning_rate": 4.850286437516653e-05,
+      "loss": 1.1186,
+      "step": 900
+    },
+    {
+      "epoch": 0.19984012789768185,
+      "grad_norm": 1.2864068746566772,
+      "learning_rate": 4.83363309352518e-05,
+      "loss": 1.1394,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21982414068745004,
+      "grad_norm": 1.5142974853515625,
+      "learning_rate": 4.816979749533707e-05,
+      "loss": 1.1162,
+      "step": 1100
+    },
+    {
+      "epoch": 0.23980815347721823,
+      "grad_norm": 0.9597436189651489,
+      "learning_rate": 4.800326405542233e-05,
+      "loss": 1.0922,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2597921662669864,
+      "grad_norm": 1.7915301322937012,
+      "learning_rate": 4.7836730615507595e-05,
+      "loss": 1.0711,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2797761790567546,
+      "grad_norm": 1.1338952779769897,
+      "learning_rate": 4.767019717559286e-05,
+      "loss": 0.9945,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2997601918465228,
+      "grad_norm": 1.3437297344207764,
+      "learning_rate": 4.750366373567813e-05,
+      "loss": 1.0322,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31974420463629094,
+      "grad_norm": 1.2949973344802856,
+      "learning_rate": 4.733713029576339e-05,
+      "loss": 1.0613,
+      "step": 1600
+    },
+    {
+      "epoch": 0.33972821742605913,
+      "grad_norm": 1.1362179517745972,
+      "learning_rate": 4.717059685584866e-05,
+      "loss": 1.0122,
+      "step": 1700
+    },
+    {
+      "epoch": 0.3597122302158273,
+      "grad_norm": 1.1878063678741455,
+      "learning_rate": 4.700406341593392e-05,
+      "loss": 1.0068,
+      "step": 1800
+    },
+    {
+      "epoch": 0.3796962430055955,
+      "grad_norm": 1.3588361740112305,
+      "learning_rate": 4.6837529976019185e-05,
+      "loss": 0.955,
+      "step": 1900
+    },
+    {
+      "epoch": 0.3996802557953637,
+      "grad_norm": 1.1428577899932861,
+      "learning_rate": 4.667099653610445e-05,
+      "loss": 0.9863,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4196642685851319,
+      "grad_norm": 1.6441487073898315,
+      "learning_rate": 4.650446309618971e-05,
+      "loss": 0.9532,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4396482813749001,
+      "grad_norm": 2.607586145401001,
+      "learning_rate": 4.633792965627498e-05,
+      "loss": 0.9877,
+      "step": 2200
+    },
+    {
+      "epoch": 0.4596322941646683,
+      "grad_norm": 2.24434757232666,
+      "learning_rate": 4.617139621636025e-05,
+      "loss": 0.9956,
+      "step": 2300
+    },
+    {
+      "epoch": 0.47961630695443647,
+      "grad_norm": 1.8238356113433838,
+      "learning_rate": 4.600486277644551e-05,
+      "loss": 0.9769,
+      "step": 2400
+    },
+    {
+      "epoch": 0.49960031974420466,
+      "grad_norm": 2.0538158416748047,
+      "learning_rate": 4.5838329336530775e-05,
+      "loss": 0.9458,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5195843325339728,
+      "grad_norm": 2.1354427337646484,
+      "learning_rate": 4.5671795896616045e-05,
+      "loss": 0.975,
+      "step": 2600
+    },
+    {
+      "epoch": 0.539568345323741,
+      "grad_norm": 1.3763636350631714,
+      "learning_rate": 4.550526245670131e-05,
+      "loss": 0.9464,
+      "step": 2700
+    },
+    {
+      "epoch": 0.5595523581135092,
+      "grad_norm": 2.6834394931793213,
+      "learning_rate": 4.533872901678657e-05,
+      "loss": 0.9437,
+      "step": 2800
+    },
+    {
+      "epoch": 0.5795363709032774,
+      "grad_norm": 1.3325830698013306,
+      "learning_rate": 4.517219557687184e-05,
+      "loss": 0.9617,
+      "step": 2900
+    },
+    {
+      "epoch": 0.5995203836930456,
+      "grad_norm": 1.841642141342163,
+      "learning_rate": 4.500566213695711e-05,
+      "loss": 0.9489,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6195043964828137,
+      "grad_norm": 1.0305529832839966,
+      "learning_rate": 4.483912869704237e-05,
+      "loss": 0.9432,
+      "step": 3100
+    },
+    {
+      "epoch": 0.6394884092725819,
+      "grad_norm": 1.4249075651168823,
+      "learning_rate": 4.467259525712763e-05,
+      "loss": 0.952,
+      "step": 3200
+    },
+    {
+      "epoch": 0.6594724220623501,
+      "grad_norm": 1.2994813919067383,
+      "learning_rate": 4.45060618172129e-05,
+      "loss": 1.0247,
+      "step": 3300
+    },
+    {
+      "epoch": 0.6794564348521183,
+      "grad_norm": 1.537548303604126,
+      "learning_rate": 4.433952837729816e-05,
+      "loss": 0.928,
+      "step": 3400
+    },
+    {
+      "epoch": 0.6994404476418865,
+      "grad_norm": 1.646200180053711,
+      "learning_rate": 4.4172994937383427e-05,
+      "loss": 0.9817,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7194244604316546,
+      "grad_norm": 1.2779592275619507,
+      "learning_rate": 4.400646149746869e-05,
+      "loss": 0.8974,
+      "step": 3600
+    },
+    {
+      "epoch": 0.7394084732214229,
+      "grad_norm": 1.7886369228363037,
+      "learning_rate": 4.383992805755396e-05,
+      "loss": 0.9351,
+      "step": 3700
+    },
+    {
+      "epoch": 0.759392486011191,
+      "grad_norm": 1.5072957277297974,
+      "learning_rate": 4.3673394617639225e-05,
+      "loss": 0.882,
+      "step": 3800
+    },
+    {
+      "epoch": 0.7793764988009593,
+      "grad_norm": 2.019421339035034,
+      "learning_rate": 4.350686117772449e-05,
+      "loss": 0.9324,
+      "step": 3900
+    },
+    {
+      "epoch": 0.7993605115907274,
+      "grad_norm": 1.7232331037521362,
+      "learning_rate": 4.334032773780975e-05,
+      "loss": 0.9094,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8193445243804957,
+      "grad_norm": 1.7297419309616089,
+      "learning_rate": 4.317379429789502e-05,
+      "loss": 0.9658,
+      "step": 4100
+    },
+    {
+      "epoch": 0.8393285371702638,
+      "grad_norm": 1.560420274734497,
+      "learning_rate": 4.300726085798029e-05,
+      "loss": 0.9613,
+      "step": 4200
+    },
+    {
+      "epoch": 0.8593125499600319,
+      "grad_norm": 1.9014427661895752,
+      "learning_rate": 4.284072741806555e-05,
+      "loss": 0.9047,
+      "step": 4300
+    },
+    {
+      "epoch": 0.8792965627498002,
+      "grad_norm": 1.4741132259368896,
+      "learning_rate": 4.2674193978150815e-05,
+      "loss": 0.7914,
+      "step": 4400
+    },
+    {
+      "epoch": 0.8992805755395683,
+      "grad_norm": 0.8008555173873901,
+      "learning_rate": 4.250766053823608e-05,
+      "loss": 0.8678,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9192645883293366,
+      "grad_norm": 1.5738321542739868,
+      "learning_rate": 4.234112709832134e-05,
+      "loss": 0.8379,
+      "step": 4600
+    },
+    {
+      "epoch": 0.9392486011191047,
+      "grad_norm": 1.7838175296783447,
+      "learning_rate": 4.2174593658406606e-05,
+      "loss": 0.9581,
+      "step": 4700
+    },
+    {
+      "epoch": 0.9592326139088729,
+      "grad_norm": 1.6761012077331543,
+      "learning_rate": 4.200806021849188e-05,
+      "loss": 0.8583,
+      "step": 4800
+    },
+    {
+      "epoch": 0.9792166266986411,
+      "grad_norm": 1.320033073425293,
+      "learning_rate": 4.184152677857714e-05,
+      "loss": 0.8709,
+      "step": 4900
+    },
+    {
+      "epoch": 0.9992006394884093,
+      "grad_norm": 2.0931804180145264,
+      "learning_rate": 4.1674993338662404e-05,
+      "loss": 0.9064,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0191846522781776,
+      "grad_norm": 1.1682066917419434,
+      "learning_rate": 4.150845989874767e-05,
+      "loss": 0.8728,
+      "step": 5100
+    },
+    {
+      "epoch": 1.0391686650679457,
+      "grad_norm": 1.2569072246551514,
+      "learning_rate": 4.134192645883294e-05,
+      "loss": 0.8921,
+      "step": 5200
+    },
+    {
+      "epoch": 1.0591526778577138,
+      "grad_norm": 1.4215683937072754,
+      "learning_rate": 4.11753930189182e-05,
+      "loss": 0.8211,
+      "step": 5300
+    },
+    {
+      "epoch": 1.079136690647482,
+      "grad_norm": 1.6081187725067139,
+      "learning_rate": 4.1008859579003467e-05,
+      "loss": 0.9338,
+      "step": 5400
+    },
+    {
+      "epoch": 1.09912070343725,
+      "grad_norm": 1.4916200637817383,
+      "learning_rate": 4.084232613908873e-05,
+      "loss": 0.8142,
+      "step": 5500
+    },
+    {
+      "epoch": 1.1191047162270185,
+      "grad_norm": 1.8639625310897827,
+      "learning_rate": 4.0675792699174e-05,
+      "loss": 0.8746,
+      "step": 5600
+    },
+    {
+      "epoch": 1.1390887290167866,
+      "grad_norm": 1.1741764545440674,
+      "learning_rate": 4.0509259259259265e-05,
+      "loss": 0.8032,
+      "step": 5700
+    },
+    {
+      "epoch": 1.1590727418065547,
+      "grad_norm": 1.7627875804901123,
+      "learning_rate": 4.034272581934453e-05,
+      "loss": 0.8681,
+      "step": 5800
+    },
+    {
+      "epoch": 1.1790567545963229,
+      "grad_norm": 0.7432733178138733,
+      "learning_rate": 4.0176192379429786e-05,
+      "loss": 0.8968,
+      "step": 5900
+    },
+    {
+      "epoch": 1.1990407673860912,
+      "grad_norm": 1.5172642469406128,
+      "learning_rate": 4.0009658939515056e-05,
+      "loss": 0.9653,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2190247801758594,
+      "grad_norm": 2.0822958946228027,
+      "learning_rate": 3.984312549960032e-05,
+      "loss": 0.8038,
+      "step": 6100
+    },
+    {
+      "epoch": 1.2390087929656275,
+      "grad_norm": 2.2852039337158203,
+      "learning_rate": 3.9676592059685584e-05,
+      "loss": 0.8041,
+      "step": 6200
+    },
+    {
+      "epoch": 1.2589928057553956,
+      "grad_norm": 1.214968204498291,
+      "learning_rate": 3.951005861977085e-05,
+      "loss": 0.8382,
+      "step": 6300
+    },
+    {
+      "epoch": 1.2789768185451638,
+      "grad_norm": 2.792722225189209,
+      "learning_rate": 3.934352517985612e-05,
+      "loss": 0.8534,
+      "step": 6400
+    },
+    {
+      "epoch": 1.2989608313349321,
+      "grad_norm": 1.6279624700546265,
+      "learning_rate": 3.917699173994138e-05,
+      "loss": 0.8387,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3189448441247003,
+      "grad_norm": 1.57301664352417,
+      "learning_rate": 3.9010458300026646e-05,
+      "loss": 0.8583,
+      "step": 6600
+    },
+    {
+      "epoch": 1.3389288569144684,
+      "grad_norm": 1.2693675756454468,
+      "learning_rate": 3.884392486011191e-05,
+      "loss": 0.7893,
+      "step": 6700
+    },
+    {
+      "epoch": 1.3589128697042367,
+      "grad_norm": 1.1760280132293701,
+      "learning_rate": 3.867739142019718e-05,
+      "loss": 0.8204,
+      "step": 6800
+    },
+    {
+      "epoch": 1.3788968824940047,
+      "grad_norm": 1.8213127851486206,
+      "learning_rate": 3.8510857980282444e-05,
+      "loss": 0.9061,
+      "step": 6900
+    },
+    {
+      "epoch": 1.398880895283773,
+      "grad_norm": 1.2589592933654785,
+      "learning_rate": 3.834432454036771e-05,
+      "loss": 0.856,
+      "step": 7000
+    },
+    {
+      "epoch": 1.4188649080735412,
+      "grad_norm": 2.5817718505859375,
+      "learning_rate": 3.817779110045297e-05,
+      "loss": 0.8542,
+      "step": 7100
+    },
+    {
+      "epoch": 1.4388489208633093,
+      "grad_norm": 1.1825404167175293,
+      "learning_rate": 3.8011257660538236e-05,
+      "loss": 0.8298,
+      "step": 7200
+    },
+    {
+      "epoch": 1.4588329336530776,
+      "grad_norm": 1.6443575620651245,
+      "learning_rate": 3.78447242206235e-05,
+      "loss": 0.823,
+      "step": 7300
+    },
+    {
+      "epoch": 1.4788169464428458,
+      "grad_norm": 1.9887899160385132,
+      "learning_rate": 3.7678190780708764e-05,
+      "loss": 0.7936,
+      "step": 7400
+    },
+    {
+      "epoch": 1.498800959232614,
+      "grad_norm": 1.8799304962158203,
+      "learning_rate": 3.7511657340794034e-05,
+      "loss": 0.8755,
+      "step": 7500
+    },
+    {
+      "epoch": 1.518784972022382,
+      "grad_norm": 1.6680015325546265,
+      "learning_rate": 3.73451239008793e-05,
+      "loss": 0.8669,
+      "step": 7600
+    },
+    {
+      "epoch": 1.5387689848121502,
+      "grad_norm": 1.7756261825561523,
+      "learning_rate": 3.717859046096456e-05,
+      "loss": 0.8572,
+      "step": 7700
+    },
+    {
+      "epoch": 1.5587529976019185,
+      "grad_norm": 1.3951911926269531,
+      "learning_rate": 3.7012057021049826e-05,
+      "loss": 0.8422,
+      "step": 7800
+    },
+    {
+      "epoch": 1.5787370103916867,
+      "grad_norm": 1.8145322799682617,
+      "learning_rate": 3.6845523581135096e-05,
+      "loss": 0.783,
+      "step": 7900
+    },
+    {
+      "epoch": 1.5987210231814548,
+      "grad_norm": 1.4113447666168213,
+      "learning_rate": 3.667899014122036e-05,
+      "loss": 0.8368,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6187050359712232,
+      "grad_norm": 1.5562957525253296,
+      "learning_rate": 3.6512456701305624e-05,
+      "loss": 0.8232,
+      "step": 8100
+    },
+    {
+      "epoch": 1.638689048760991,
+      "grad_norm": 2.0334463119506836,
+      "learning_rate": 3.634592326139089e-05,
+      "loss": 0.8272,
+      "step": 8200
+    },
+    {
+      "epoch": 1.6586730615507594,
+      "grad_norm": 2.305115222930908,
+      "learning_rate": 3.617938982147616e-05,
+      "loss": 0.8708,
+      "step": 8300
+    },
+    {
+      "epoch": 1.6786570743405276,
+      "grad_norm": 1.9576376676559448,
+      "learning_rate": 3.601285638156142e-05,
+      "loss": 0.8437,
+      "step": 8400
+    },
+    {
+      "epoch": 1.6986410871302957,
+      "grad_norm": 1.324064016342163,
+      "learning_rate": 3.584632294164668e-05,
+      "loss": 0.8197,
+      "step": 8500
+    },
+    {
+      "epoch": 1.718625099920064,
+      "grad_norm": 1.5594903230667114,
+      "learning_rate": 3.567978950173195e-05,
+      "loss": 0.8365,
+      "step": 8600
+    },
+    {
+      "epoch": 1.738609112709832,
+      "grad_norm": 1.853633999824524,
+      "learning_rate": 3.5513256061817214e-05,
+      "loss": 0.7914,
+      "step": 8700
+    },
+    {
+      "epoch": 1.7585931254996003,
+      "grad_norm": 1.839158296585083,
+      "learning_rate": 3.534672262190248e-05,
+      "loss": 0.9374,
+      "step": 8800
+    },
+    {
+      "epoch": 1.7785771382893685,
+      "grad_norm": 2.5038366317749023,
+      "learning_rate": 3.518018918198774e-05,
+      "loss": 0.8202,
+      "step": 8900
+    },
+    {
+      "epoch": 1.7985611510791366,
+      "grad_norm": 1.7603284120559692,
+      "learning_rate": 3.501365574207301e-05,
+      "loss": 0.8346,
+      "step": 9000
+    },
+    {
+      "epoch": 1.818545163868905,
+      "grad_norm": 1.9243416786193848,
+      "learning_rate": 3.4847122302158276e-05,
+      "loss": 0.8141,
+      "step": 9100
+    },
+    {
+      "epoch": 1.838529176658673,
+      "grad_norm": 1.6993930339813232,
+      "learning_rate": 3.468058886224354e-05,
+      "loss": 0.7974,
+      "step": 9200
+    },
+    {
+      "epoch": 1.8585131894484412,
+      "grad_norm": 1.9248780012130737,
+      "learning_rate": 3.4514055422328804e-05,
+      "loss": 0.8543,
+      "step": 9300
+    },
+    {
+      "epoch": 1.8784972022382096,
+      "grad_norm": 1.7247469425201416,
+      "learning_rate": 3.4347521982414074e-05,
+      "loss": 0.7968,
+      "step": 9400
+    },
+    {
+      "epoch": 1.8984812150279775,
+      "grad_norm": 1.165992259979248,
+      "learning_rate": 3.418098854249934e-05,
+      "loss": 0.7946,
+      "step": 9500
+    },
+    {
+      "epoch": 1.9184652278177459,
+      "grad_norm": 1.5617034435272217,
+      "learning_rate": 3.40144551025846e-05,
+      "loss": 0.8452,
+      "step": 9600
+    },
+    {
+      "epoch": 1.938449240607514,
+      "grad_norm": 1.9524955749511719,
+      "learning_rate": 3.3847921662669866e-05,
+      "loss": 0.821,
+      "step": 9700
+    },
+    {
+      "epoch": 1.9584332533972821,
+      "grad_norm": 1.201984167098999,
+      "learning_rate": 3.3681388222755136e-05,
+      "loss": 0.8244,
+      "step": 9800
+    },
+    {
+      "epoch": 1.9784172661870505,
+      "grad_norm": 1.5261083841323853,
+      "learning_rate": 3.3514854782840393e-05,
+      "loss": 0.8521,
+      "step": 9900
+    },
+    {
+      "epoch": 1.9984012789768184,
+      "grad_norm": 0.8879593014717102,
+      "learning_rate": 3.334832134292566e-05,
+      "loss": 0.7745,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0183852917665868,
+      "grad_norm": 1.9460114240646362,
+      "learning_rate": 3.318178790301093e-05,
+      "loss": 0.7926,
+      "step": 10100
+    },
+    {
+      "epoch": 2.038369304556355,
+      "grad_norm": 2.0698747634887695,
+      "learning_rate": 3.301525446309619e-05,
+      "loss": 0.8668,
+      "step": 10200
+    },
+    {
+      "epoch": 2.058353317346123,
+      "grad_norm": 1.6188371181488037,
+      "learning_rate": 3.2848721023181456e-05,
+      "loss": 0.7743,
+      "step": 10300
+    },
+    {
+      "epoch": 2.0783373301358914,
+      "grad_norm": 1.4746142625808716,
+      "learning_rate": 3.268218758326672e-05,
+      "loss": 0.776,
+      "step": 10400
+    },
+    {
+      "epoch": 2.0983213429256593,
+      "grad_norm": 2.6285245418548584,
+      "learning_rate": 3.251565414335199e-05,
+      "loss": 0.7952,
+      "step": 10500
+    },
+    {
+      "epoch": 2.1183053557154277,
+      "grad_norm": 2.9462263584136963,
+      "learning_rate": 3.2349120703437254e-05,
+      "loss": 0.8492,
+      "step": 10600
+    },
+    {
+      "epoch": 2.138289368505196,
+      "grad_norm": 2.2768771648406982,
+      "learning_rate": 3.218258726352252e-05,
+      "loss": 0.7773,
+      "step": 10700
+    },
+    {
+      "epoch": 2.158273381294964,
+      "grad_norm": 2.4314112663269043,
+      "learning_rate": 3.201605382360778e-05,
+      "loss": 0.7789,
+      "step": 10800
+    },
+    {
+      "epoch": 2.1782573940847323,
+      "grad_norm": 2.631697654724121,
+      "learning_rate": 3.184952038369305e-05,
+      "loss": 0.7809,
+      "step": 10900
+    },
+    {
+      "epoch": 2.1982414068745,
+      "grad_norm": 2.0636370182037354,
+      "learning_rate": 3.1682986943778316e-05,
+      "loss": 0.7627,
+      "step": 11000
+    },
+    {
+      "epoch": 2.2182254196642686,
+      "grad_norm": 1.861494779586792,
+      "learning_rate": 3.151645350386358e-05,
+      "loss": 0.7454,
+      "step": 11100
+    },
+    {
+      "epoch": 2.238209432454037,
+      "grad_norm": 1.6431078910827637,
+      "learning_rate": 3.134992006394884e-05,
+      "loss": 0.8208,
+      "step": 11200
+    },
+    {
+      "epoch": 2.258193445243805,
+      "grad_norm": 1.1081715822219849,
+      "learning_rate": 3.118338662403411e-05,
+      "loss": 0.7963,
+      "step": 11300
+    },
+    {
+      "epoch": 2.278177458033573,
+      "grad_norm": 1.6696077585220337,
+      "learning_rate": 3.101685318411937e-05,
+      "loss": 0.7948,
+      "step": 11400
+    },
+    {
+      "epoch": 2.2981614708233415,
+      "grad_norm": 1.1712377071380615,
+      "learning_rate": 3.0850319744204635e-05,
+      "loss": 0.7907,
+      "step": 11500
+    },
+    {
+      "epoch": 2.3181454836131095,
+      "grad_norm": 1.28898024559021,
+      "learning_rate": 3.06837863042899e-05,
+      "loss": 0.7791,
+      "step": 11600
+    },
+    {
+      "epoch": 2.338129496402878,
+      "grad_norm": 1.3267985582351685,
+      "learning_rate": 3.0517252864375166e-05,
+      "loss": 0.7819,
+      "step": 11700
+    },
+    {
+      "epoch": 2.3581135091926457,
+      "grad_norm": 1.4074293375015259,
+      "learning_rate": 3.0350719424460434e-05,
+      "loss": 0.818,
+      "step": 11800
+    },
+    {
+      "epoch": 2.378097521982414,
+      "grad_norm": 0.9492627382278442,
+      "learning_rate": 3.0184185984545697e-05,
+      "loss": 0.7689,
+      "step": 11900
+    },
+    {
+      "epoch": 2.3980815347721824,
+      "grad_norm": 1.8090003728866577,
+      "learning_rate": 3.0017652544630965e-05,
+      "loss": 0.7845,
+      "step": 12000
+    },
+    {
+      "epoch": 2.4180655475619504,
+      "grad_norm": 1.899207353591919,
+      "learning_rate": 2.985111910471623e-05,
+      "loss": 0.7742,
+      "step": 12100
+    },
+    {
+      "epoch": 2.4380495603517187,
+      "grad_norm": 2.0821797847747803,
+      "learning_rate": 2.9684585664801496e-05,
+      "loss": 0.7696,
+      "step": 12200
+    },
+    {
+      "epoch": 2.4580335731414866,
+      "grad_norm": 1.089876651763916,
+      "learning_rate": 2.951805222488676e-05,
+      "loss": 0.7873,
+      "step": 12300
+    },
+    {
+      "epoch": 2.478017585931255,
+      "grad_norm": 1.265599250793457,
+      "learning_rate": 2.9351518784972027e-05,
+      "loss": 0.7504,
+      "step": 12400
+    },
+    {
+      "epoch": 2.4980015987210233,
+      "grad_norm": 2.7753829956054688,
+      "learning_rate": 2.9184985345057287e-05,
+      "loss": 0.7824,
+      "step": 12500
+    },
+    {
+      "epoch": 2.5179856115107913,
+      "grad_norm": 1.0310410261154175,
+      "learning_rate": 2.901845190514255e-05,
+      "loss": 0.7326,
+      "step": 12600
+    },
+    {
+      "epoch": 2.5379696243005596,
+      "grad_norm": 2.056279182434082,
+      "learning_rate": 2.8851918465227818e-05,
+      "loss": 0.8411,
+      "step": 12700
+    },
+    {
+      "epoch": 2.5579536370903275,
+      "grad_norm": 1.1815407276153564,
+      "learning_rate": 2.8685385025313082e-05,
+      "loss": 0.805,
+      "step": 12800
+    },
+    {
+      "epoch": 2.577937649880096,
+      "grad_norm": 1.6167210340499878,
+      "learning_rate": 2.851885158539835e-05,
+      "loss": 0.7311,
+      "step": 12900
+    },
+    {
+      "epoch": 2.5979216626698642,
+      "grad_norm": 1.488755226135254,
+      "learning_rate": 2.8352318145483613e-05,
+      "loss": 0.8335,
+      "step": 13000
+    },
+    {
+      "epoch": 2.617905675459632,
+      "grad_norm": 2.5013859272003174,
+      "learning_rate": 2.818578470556888e-05,
+      "loss": 0.7833,
+      "step": 13100
+    },
+    {
+      "epoch": 2.6378896882494005,
+      "grad_norm": 1.102152943611145,
+      "learning_rate": 2.8019251265654144e-05,
+      "loss": 0.7536,
+      "step": 13200
+    },
+    {
+      "epoch": 2.6578737010391684,
+      "grad_norm": 1.3805499076843262,
+      "learning_rate": 2.785271782573941e-05,
+      "loss": 0.775,
+      "step": 13300
+    },
+    {
+      "epoch": 2.677857713828937,
+      "grad_norm": 2.189347505569458,
+      "learning_rate": 2.7686184385824675e-05,
+      "loss": 0.8178,
+      "step": 13400
+    },
+    {
+      "epoch": 2.697841726618705,
+      "grad_norm": 0.9750763177871704,
+      "learning_rate": 2.7519650945909942e-05,
+      "loss": 0.7743,
+      "step": 13500
+    },
+    {
+      "epoch": 2.7178257394084735,
+      "grad_norm": 1.2844312191009521,
+      "learning_rate": 2.7353117505995206e-05,
+      "loss": 0.7631,
+      "step": 13600
+    },
+    {
+      "epoch": 2.7378097521982414,
+      "grad_norm": 1.4551914930343628,
+      "learning_rate": 2.7186584066080474e-05,
+      "loss": 0.76,
+      "step": 13700
+    },
+    {
+      "epoch": 2.7577937649880093,
+      "grad_norm": 0.8891064524650574,
+      "learning_rate": 2.7020050626165734e-05,
+      "loss": 0.8252,
+      "step": 13800
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 1.9776784181594849,
+      "learning_rate": 2.6853517186250998e-05,
+      "loss": 0.8037,
+      "step": 13900
+    },
+    {
+      "epoch": 2.797761790567546,
+      "grad_norm": 1.429692029953003,
+      "learning_rate": 2.6686983746336265e-05,
+      "loss": 0.7369,
+      "step": 14000
+    },
+    {
+      "epoch": 2.8177458033573144,
+      "grad_norm": 2.0837855339050293,
+      "learning_rate": 2.652045030642153e-05,
+      "loss": 0.742,
+      "step": 14100
+    },
+    {
+      "epoch": 2.8377298161470823,
+      "grad_norm": 1.2353509664535522,
+      "learning_rate": 2.6353916866506796e-05,
+      "loss": 0.7615,
+      "step": 14200
+    },
+    {
+      "epoch": 2.8577138289368507,
+      "grad_norm": 0.8735284209251404,
+      "learning_rate": 2.618738342659206e-05,
+      "loss": 0.7872,
+      "step": 14300
+    },
+    {
+      "epoch": 2.8776978417266186,
+      "grad_norm": 1.0889009237289429,
+      "learning_rate": 2.6020849986677327e-05,
+      "loss": 0.7455,
+      "step": 14400
+    },
+    {
+      "epoch": 2.897681854516387,
+      "grad_norm": 1.506787657737732,
+      "learning_rate": 2.585431654676259e-05,
+      "loss": 0.792,
+      "step": 14500
+    },
+    {
+      "epoch": 2.9176658673061553,
+      "grad_norm": 0.7630636096000671,
+      "learning_rate": 2.5687783106847858e-05,
+      "loss": 0.7918,
+      "step": 14600
+    },
+    {
+      "epoch": 2.937649880095923,
+      "grad_norm": 1.6361045837402344,
+      "learning_rate": 2.5521249666933122e-05,
+      "loss": 0.7357,
+      "step": 14700
+    },
+    {
+      "epoch": 2.9576338928856916,
+      "grad_norm": 2.248220920562744,
+      "learning_rate": 2.535471622701839e-05,
+      "loss": 0.7954,
+      "step": 14800
+    },
+    {
+      "epoch": 2.9776179056754595,
+      "grad_norm": 1.14662766456604,
+      "learning_rate": 2.5188182787103653e-05,
+      "loss": 0.7865,
+      "step": 14900
+    },
+    {
+      "epoch": 2.997601918465228,
+      "grad_norm": 1.3895844221115112,
+      "learning_rate": 2.502164934718892e-05,
+      "loss": 0.7364,
+      "step": 15000
+    },
+    {
+      "epoch": 3.017585931254996,
+      "grad_norm": 2.1330533027648926,
+      "learning_rate": 2.485511590727418e-05,
+      "loss": 0.7244,
+      "step": 15100
+    },
+    {
+      "epoch": 3.037569944044764,
+      "grad_norm": 1.384775996208191,
+      "learning_rate": 2.4688582467359448e-05,
+      "loss": 0.7393,
+      "step": 15200
+    },
+    {
+      "epoch": 3.0575539568345325,
+      "grad_norm": 0.9841705560684204,
+      "learning_rate": 2.4522049027444712e-05,
+      "loss": 0.8051,
+      "step": 15300
+    },
+    {
+      "epoch": 3.0775379696243004,
+      "grad_norm": 1.224924921989441,
+      "learning_rate": 2.435551558752998e-05,
+      "loss": 0.8004,
+      "step": 15400
+    },
+    {
+      "epoch": 3.0975219824140687,
+      "grad_norm": 2.2387399673461914,
+      "learning_rate": 2.418898214761524e-05,
+      "loss": 0.8051,
+      "step": 15500
+    },
+    {
+      "epoch": 3.117505995203837,
+      "grad_norm": 1.8771803379058838,
+      "learning_rate": 2.4022448707700507e-05,
+      "loss": 0.7903,
+      "step": 15600
+    },
+    {
+      "epoch": 3.137490007993605,
+      "grad_norm": 1.786600112915039,
+      "learning_rate": 2.385591526778577e-05,
+      "loss": 0.7796,
+      "step": 15700
+    },
+    {
+      "epoch": 3.1574740207833734,
+      "grad_norm": 1.0823020935058594,
+      "learning_rate": 2.3689381827871038e-05,
+      "loss": 0.7468,
+      "step": 15800
+    },
+    {
+      "epoch": 3.1774580335731413,
+      "grad_norm": 1.9462608098983765,
+      "learning_rate": 2.35228483879563e-05,
+      "loss": 0.7854,
+      "step": 15900
+    },
+    {
+      "epoch": 3.1974420463629096,
+      "grad_norm": 1.3235732316970825,
+      "learning_rate": 2.335631494804157e-05,
+      "loss": 0.7584,
+      "step": 16000
+    },
+    {
+      "epoch": 3.217426059152678,
+      "grad_norm": 1.5206961631774902,
+      "learning_rate": 2.3189781508126833e-05,
+      "loss": 0.8104,
+      "step": 16100
+    },
+    {
+      "epoch": 3.237410071942446,
+      "grad_norm": 1.4281466007232666,
+      "learning_rate": 2.3023248068212097e-05,
+      "loss": 0.7505,
+      "step": 16200
+    },
+    {
+      "epoch": 3.2573940847322143,
+      "grad_norm": 1.9032511711120605,
+      "learning_rate": 2.2856714628297364e-05,
+      "loss": 0.7813,
+      "step": 16300
+    },
+    {
+      "epoch": 3.277378097521982,
+      "grad_norm": 2.10361909866333,
+      "learning_rate": 2.2690181188382628e-05,
+      "loss": 0.7369,
+      "step": 16400
+    },
+    {
+      "epoch": 3.2973621103117505,
+      "grad_norm": 1.440158486366272,
+      "learning_rate": 2.2523647748467895e-05,
+      "loss": 0.7576,
+      "step": 16500
+    },
+    {
+      "epoch": 3.317346123101519,
+      "grad_norm": 1.8777798414230347,
+      "learning_rate": 2.235711430855316e-05,
+      "loss": 0.7317,
+      "step": 16600
+    },
+    {
+      "epoch": 3.337330135891287,
+      "grad_norm": 1.6413357257843018,
+      "learning_rate": 2.2190580868638426e-05,
+      "loss": 0.7802,
+      "step": 16700
+    },
+    {
+      "epoch": 3.357314148681055,
+      "grad_norm": 1.820087194442749,
+      "learning_rate": 2.2024047428723686e-05,
+      "loss": 0.7435,
+      "step": 16800
+    },
+    {
+      "epoch": 3.3772981614708235,
+      "grad_norm": 2.5140113830566406,
+      "learning_rate": 2.1857513988808954e-05,
+      "loss": 0.7532,
+      "step": 16900
+    },
+    {
+      "epoch": 3.3972821742605914,
+      "grad_norm": 1.7011070251464844,
+      "learning_rate": 2.1690980548894217e-05,
+      "loss": 0.728,
+      "step": 17000
+    },
+    {
+      "epoch": 3.41726618705036,
+      "grad_norm": 1.3051706552505493,
+      "learning_rate": 2.1524447108979485e-05,
+      "loss": 0.7493,
+      "step": 17100
+    },
+    {
+      "epoch": 3.437250199840128,
+      "grad_norm": 0.9745834469795227,
+      "learning_rate": 2.135791366906475e-05,
+      "loss": 0.7219,
+      "step": 17200
+    },
+    {
+      "epoch": 3.457234212629896,
+      "grad_norm": 1.3213515281677246,
+      "learning_rate": 2.1191380229150016e-05,
+      "loss": 0.7703,
+      "step": 17300
+    },
+    {
+      "epoch": 3.4772182254196644,
+      "grad_norm": 0.735060453414917,
+      "learning_rate": 2.102484678923528e-05,
+      "loss": 0.7342,
+      "step": 17400
+    },
+    {
+      "epoch": 3.4972022382094323,
+      "grad_norm": 1.073197603225708,
+      "learning_rate": 2.0858313349320543e-05,
+      "loss": 0.7023,
+      "step": 17500
+    },
+    {
+      "epoch": 3.5171862509992007,
+      "grad_norm": 1.797711730003357,
+      "learning_rate": 2.069177990940581e-05,
+      "loss": 0.7944,
+      "step": 17600
+    },
+    {
+      "epoch": 3.537170263788969,
+      "grad_norm": 1.3365331888198853,
+      "learning_rate": 2.0525246469491074e-05,
+      "loss": 0.7773,
+      "step": 17700
+    },
+    {
+      "epoch": 3.557154276578737,
+      "grad_norm": 1.451333999633789,
+      "learning_rate": 2.035871302957634e-05,
+      "loss": 0.7659,
+      "step": 17800
+    },
+    {
+      "epoch": 3.5771382893685053,
+      "grad_norm": 1.5622735023498535,
+      "learning_rate": 2.0192179589661606e-05,
+      "loss": 0.7676,
+      "step": 17900
+    },
+    {
+      "epoch": 3.597122302158273,
+      "grad_norm": 1.5826952457427979,
+      "learning_rate": 2.0025646149746873e-05,
+      "loss": 0.7393,
+      "step": 18000
+    },
+    {
+      "epoch": 3.6171063149480416,
+      "grad_norm": 0.7937633991241455,
+      "learning_rate": 1.9859112709832133e-05,
+      "loss": 0.7112,
+      "step": 18100
+    },
+    {
+      "epoch": 3.63709032773781,
+      "grad_norm": 1.8199377059936523,
+      "learning_rate": 1.96925792699174e-05,
+      "loss": 0.7722,
+      "step": 18200
+    },
+    {
+      "epoch": 3.657074340527578,
+      "grad_norm": 2.317171573638916,
+      "learning_rate": 1.9526045830002664e-05,
+      "loss": 0.7735,
+      "step": 18300
+    },
+    {
+      "epoch": 3.677058353317346,
+      "grad_norm": 0.9344459772109985,
+      "learning_rate": 1.935951239008793e-05,
+      "loss": 0.7168,
+      "step": 18400
+    },
+    {
+      "epoch": 3.697042366107114,
+      "grad_norm": 1.833892583847046,
+      "learning_rate": 1.9192978950173195e-05,
+      "loss": 0.6825,
+      "step": 18500
+    },
+    {
+      "epoch": 3.7170263788968825,
+      "grad_norm": 1.4093741178512573,
+      "learning_rate": 1.9026445510258463e-05,
+      "loss": 0.7087,
+      "step": 18600
+    },
+    {
+      "epoch": 3.737010391686651,
+      "grad_norm": 2.0284645557403564,
+      "learning_rate": 1.8859912070343726e-05,
+      "loss": 0.7579,
+      "step": 18700
+    },
+    {
+      "epoch": 3.7569944044764187,
+      "grad_norm": 1.8383668661117554,
+      "learning_rate": 1.869337863042899e-05,
+      "loss": 0.7603,
+      "step": 18800
+    },
+    {
+      "epoch": 3.776978417266187,
+      "grad_norm": 1.5985366106033325,
+      "learning_rate": 1.8526845190514254e-05,
+      "loss": 0.7166,
+      "step": 18900
+    },
+    {
+      "epoch": 3.796962430055955,
+      "grad_norm": 1.5089521408081055,
+      "learning_rate": 1.836031175059952e-05,
+      "loss": 0.7678,
+      "step": 19000
+    },
+    {
+      "epoch": 3.8169464428457234,
+      "grad_norm": 1.2770063877105713,
+      "learning_rate": 1.8193778310684785e-05,
+      "loss": 0.7213,
+      "step": 19100
+    },
+    {
+      "epoch": 3.8369304556354917,
+      "grad_norm": 2.4528274536132812,
+      "learning_rate": 1.8027244870770052e-05,
+      "loss": 0.7255,
+      "step": 19200
+    },
+    {
+      "epoch": 3.8569144684252596,
+      "grad_norm": 1.736755132675171,
+      "learning_rate": 1.7860711430855316e-05,
+      "loss": 0.6784,
+      "step": 19300
+    },
+    {
+      "epoch": 3.876898481215028,
+      "grad_norm": 1.719307780265808,
+      "learning_rate": 1.7694177990940583e-05,
+      "loss": 0.7795,
+      "step": 19400
+    },
+    {
+      "epoch": 3.896882494004796,
+      "grad_norm": 2.070528984069824,
+      "learning_rate": 1.7527644551025847e-05,
+      "loss": 0.7509,
+      "step": 19500
+    },
+    {
+      "epoch": 3.9168665067945643,
+      "grad_norm": 1.6482255458831787,
+      "learning_rate": 1.736111111111111e-05,
+      "loss": 0.7202,
+      "step": 19600
+    },
+    {
+      "epoch": 3.9368505195843326,
+      "grad_norm": 1.1660830974578857,
+      "learning_rate": 1.719457767119638e-05,
+      "loss": 0.7042,
+      "step": 19700
+    },
+    {
+      "epoch": 3.956834532374101,
+      "grad_norm": 1.0131560564041138,
+      "learning_rate": 1.7028044231281642e-05,
+      "loss": 0.7059,
+      "step": 19800
+    },
+    {
+      "epoch": 3.976818545163869,
+      "grad_norm": 1.1839569807052612,
+      "learning_rate": 1.686151079136691e-05,
+      "loss": 0.77,
+      "step": 19900
+    },
+    {
+      "epoch": 3.996802557953637,
+      "grad_norm": 1.736053705215454,
+      "learning_rate": 1.6694977351452173e-05,
+      "loss": 0.7703,
+      "step": 20000
+    },
+    {
+      "epoch": 4.016786570743405,
+      "grad_norm": 1.3700270652770996,
+      "learning_rate": 1.6528443911537437e-05,
+      "loss": 0.6643,
+      "step": 20100
+    },
+    {
+      "epoch": 4.0367705835331735,
+      "grad_norm": 1.347440481185913,
+      "learning_rate": 1.63619104716227e-05,
+      "loss": 0.7502,
+      "step": 20200
+    },
+    {
+      "epoch": 4.056754596322942,
+      "grad_norm": 1.9421720504760742,
+      "learning_rate": 1.6195377031707968e-05,
+      "loss": 0.7382,
+      "step": 20300
+    },
+    {
+      "epoch": 4.07673860911271,
+      "grad_norm": 0.9211772084236145,
+      "learning_rate": 1.6028843591793232e-05,
+      "loss": 0.7249,
+      "step": 20400
+    },
+    {
+      "epoch": 4.096722621902478,
+      "grad_norm": 2.1698520183563232,
+      "learning_rate": 1.58623101518785e-05,
+      "loss": 0.7339,
+      "step": 20500
+    },
+    {
+      "epoch": 4.116706634692246,
+      "grad_norm": 1.6852116584777832,
+      "learning_rate": 1.5695776711963763e-05,
+      "loss": 0.7525,
+      "step": 20600
+    },
+    {
+      "epoch": 4.136690647482014,
+      "grad_norm": 1.8582841157913208,
+      "learning_rate": 1.552924327204903e-05,
+      "loss": 0.7168,
+      "step": 20700
+    },
+    {
+      "epoch": 4.156674660271783,
+      "grad_norm": 1.3949832916259766,
+      "learning_rate": 1.536270983213429e-05,
+      "loss": 0.6835,
+      "step": 20800
+    },
+    {
+      "epoch": 4.176658673061551,
+      "grad_norm": 2.044853925704956,
+      "learning_rate": 1.5196176392219558e-05,
+      "loss": 0.7332,
+      "step": 20900
+    },
+    {
+      "epoch": 4.196642685851319,
+      "grad_norm": 1.3187381029129028,
+      "learning_rate": 1.5029642952304823e-05,
+      "loss": 0.7724,
+      "step": 21000
+    },
+    {
+      "epoch": 4.216626698641087,
+      "grad_norm": 1.18405020236969,
+      "learning_rate": 1.4863109512390089e-05,
+      "loss": 0.7677,
+      "step": 21100
+    },
+    {
+      "epoch": 4.236610711430855,
+      "grad_norm": 1.2868226766586304,
+      "learning_rate": 1.4696576072475355e-05,
+      "loss": 0.7168,
+      "step": 21200
+    },
+    {
+      "epoch": 4.256594724220624,
+      "grad_norm": 2.145659923553467,
+      "learning_rate": 1.453004263256062e-05,
+      "loss": 0.7574,
+      "step": 21300
+    },
+    {
+      "epoch": 4.276578737010392,
+      "grad_norm": 1.0491008758544922,
+      "learning_rate": 1.4363509192645886e-05,
+      "loss": 0.7274,
+      "step": 21400
+    },
+    {
+      "epoch": 4.2965627498001595,
+      "grad_norm": 1.9524632692337036,
+      "learning_rate": 1.4196975752731148e-05,
+      "loss": 0.7256,
+      "step": 21500
+    },
+    {
+      "epoch": 4.316546762589928,
+      "grad_norm": 1.6348446607589722,
+      "learning_rate": 1.4030442312816413e-05,
+      "loss": 0.6971,
+      "step": 21600
+    },
+    {
+      "epoch": 4.336530775379696,
+      "grad_norm": 1.6102409362792969,
+      "learning_rate": 1.3863908872901679e-05,
+      "loss": 0.7031,
+      "step": 21700
+    },
+    {
+      "epoch": 4.356514788169465,
+      "grad_norm": 1.4496809244155884,
+      "learning_rate": 1.3697375432986944e-05,
+      "loss": 0.76,
+      "step": 21800
+    },
+    {
+      "epoch": 4.376498800959233,
+      "grad_norm": 2.370002508163452,
+      "learning_rate": 1.353084199307221e-05,
+      "loss": 0.7098,
+      "step": 21900
+    },
+    {
+      "epoch": 4.396482813749,
+      "grad_norm": 1.1416559219360352,
+      "learning_rate": 1.3364308553157475e-05,
+      "loss": 0.7565,
+      "step": 22000
+    },
+    {
+      "epoch": 4.416466826538769,
+      "grad_norm": 1.6672168970108032,
+      "learning_rate": 1.319777511324274e-05,
+      "loss": 0.7939,
+      "step": 22100
+    },
+    {
+      "epoch": 4.436450839328537,
+      "grad_norm": 1.1106956005096436,
+      "learning_rate": 1.3031241673328005e-05,
+      "loss": 0.6645,
+      "step": 22200
+    },
+    {
+      "epoch": 4.4564348521183055,
+      "grad_norm": 1.4987940788269043,
+      "learning_rate": 1.286470823341327e-05,
+      "loss": 0.7117,
+      "step": 22300
+    },
+    {
+      "epoch": 4.476418864908074,
+      "grad_norm": 2.063014268875122,
+      "learning_rate": 1.2698174793498536e-05,
+      "loss": 0.767,
+      "step": 22400
+    },
+    {
+      "epoch": 4.496402877697841,
+      "grad_norm": 0.748756468296051,
+      "learning_rate": 1.2531641353583801e-05,
+      "loss": 0.7393,
+      "step": 22500
+    },
+    {
+      "epoch": 4.51638689048761,
+      "grad_norm": 1.3971226215362549,
+      "learning_rate": 1.2365107913669065e-05,
+      "loss": 0.7782,
+      "step": 22600
+    },
+    {
+      "epoch": 4.536370903277378,
+      "grad_norm": 1.5306447744369507,
+      "learning_rate": 1.219857447375433e-05,
+      "loss": 0.7299,
+      "step": 22700
+    },
+    {
+      "epoch": 4.556354916067146,
+      "grad_norm": 1.409225344657898,
+      "learning_rate": 1.2032041033839596e-05,
+      "loss": 0.6752,
+      "step": 22800
+    },
+    {
+      "epoch": 4.576338928856915,
+      "grad_norm": 1.396794080734253,
+      "learning_rate": 1.186550759392486e-05,
+      "loss": 0.6417,
+      "step": 22900
+    },
+    {
+      "epoch": 4.596322941646683,
+      "grad_norm": 1.6455470323562622,
+      "learning_rate": 1.1698974154010126e-05,
+      "loss": 0.7545,
+      "step": 23000
+    },
+    {
+      "epoch": 4.616306954436451,
+      "grad_norm": 1.4188311100006104,
+      "learning_rate": 1.1532440714095391e-05,
+      "loss": 0.7217,
+      "step": 23100
+    },
+    {
+      "epoch": 4.636290967226219,
+      "grad_norm": 1.1025303602218628,
+      "learning_rate": 1.1365907274180657e-05,
+      "loss": 0.7419,
+      "step": 23200
+    },
+    {
+      "epoch": 4.656274980015987,
+      "grad_norm": 1.0919783115386963,
+      "learning_rate": 1.119937383426592e-05,
+      "loss": 0.725,
+      "step": 23300
+    },
+    {
+      "epoch": 4.676258992805756,
+      "grad_norm": 2.179637908935547,
+      "learning_rate": 1.1032840394351186e-05,
+      "loss": 0.7052,
+      "step": 23400
+    },
+    {
+      "epoch": 4.696243005595523,
+      "grad_norm": 1.4243191480636597,
+      "learning_rate": 1.0866306954436452e-05,
+      "loss": 0.7437,
+      "step": 23500
+    },
+    {
+      "epoch": 4.7162270183852915,
+      "grad_norm": 1.6711329221725464,
+      "learning_rate": 1.0699773514521715e-05,
+      "loss": 0.7378,
+      "step": 23600
+    },
+    {
+      "epoch": 4.73621103117506,
+      "grad_norm": 1.2967829704284668,
+      "learning_rate": 1.0533240074606981e-05,
+      "loss": 0.7386,
+      "step": 23700
+    },
+    {
+      "epoch": 4.756195043964828,
+      "grad_norm": 1.737625002861023,
+      "learning_rate": 1.0366706634692246e-05,
+      "loss": 0.7012,
+      "step": 23800
+    },
+    {
+      "epoch": 4.7761790567545965,
+      "grad_norm": 1.062472939491272,
+      "learning_rate": 1.020017319477751e-05,
+      "loss": 0.6797,
+      "step": 23900
+    },
+    {
+      "epoch": 4.796163069544365,
+      "grad_norm": 1.044542908668518,
+      "learning_rate": 1.0033639754862776e-05,
+      "loss": 0.7285,
+      "step": 24000
+    },
+    {
+      "epoch": 4.816147082334132,
+      "grad_norm": 1.70567786693573,
+      "learning_rate": 9.867106314948041e-06,
+      "loss": 0.7777,
+      "step": 24100
+    },
+    {
+      "epoch": 4.836131095123901,
+      "grad_norm": 1.6937395334243774,
+      "learning_rate": 9.700572875033307e-06,
+      "loss": 0.7378,
+      "step": 24200
+    },
+    {
+      "epoch": 4.856115107913669,
+      "grad_norm": 2.7036936283111572,
+      "learning_rate": 9.534039435118572e-06,
+      "loss": 0.7813,
+      "step": 24300
+    },
+    {
+      "epoch": 4.876099120703437,
+      "grad_norm": 1.1682194471359253,
+      "learning_rate": 9.367505995203838e-06,
+      "loss": 0.7155,
+      "step": 24400
+    },
+    {
+      "epoch": 4.896083133493206,
+      "grad_norm": 1.2117973566055298,
+      "learning_rate": 9.200972555289104e-06,
+      "loss": 0.7273,
+      "step": 24500
+    },
+    {
+      "epoch": 4.916067146282973,
+      "grad_norm": 0.9339836239814758,
+      "learning_rate": 9.034439115374367e-06,
+      "loss": 0.7368,
+      "step": 24600
+    },
+    {
+      "epoch": 4.936051159072742,
+      "grad_norm": 1.3919428586959839,
+      "learning_rate": 8.867905675459633e-06,
+      "loss": 0.7059,
+      "step": 24700
+    },
+    {
+      "epoch": 4.95603517186251,
+      "grad_norm": 2.1438040733337402,
+      "learning_rate": 8.701372235544898e-06,
+      "loss": 0.7197,
+      "step": 24800
+    },
+    {
+      "epoch": 4.976019184652278,
+      "grad_norm": 1.892350435256958,
+      "learning_rate": 8.534838795630162e-06,
+      "loss": 0.7292,
+      "step": 24900
+    },
+    {
+      "epoch": 4.996003197442047,
+      "grad_norm": 2.050062656402588,
+      "learning_rate": 8.368305355715428e-06,
+      "loss": 0.7791,
+      "step": 25000
+    },
+    {
+      "epoch": 5.015987210231814,
+      "grad_norm": 2.285053014755249,
+      "learning_rate": 8.201771915800693e-06,
+      "loss": 0.6937,
+      "step": 25100
+    },
+    {
+      "epoch": 5.0359712230215825,
+      "grad_norm": 1.6725279092788696,
+      "learning_rate": 8.035238475885959e-06,
+      "loss": 0.7443,
+      "step": 25200
+    },
+    {
+      "epoch": 5.055955235811351,
+      "grad_norm": 1.590450644493103,
+      "learning_rate": 7.868705035971223e-06,
+      "loss": 0.7069,
+      "step": 25300
+    },
+    {
+      "epoch": 5.075939248601119,
+      "grad_norm": 0.7603669762611389,
+      "learning_rate": 7.702171596056488e-06,
+      "loss": 0.6778,
+      "step": 25400
+    },
+    {
+      "epoch": 5.095923261390888,
+      "grad_norm": 1.8916963338851929,
+      "learning_rate": 7.535638156141754e-06,
+      "loss": 0.769,
+      "step": 25500
+    },
+    {
+      "epoch": 5.115907274180655,
+      "grad_norm": 1.6110832691192627,
+      "learning_rate": 7.3691047162270184e-06,
+      "loss": 0.7027,
+      "step": 25600
+    },
+    {
+      "epoch": 5.135891286970423,
+      "grad_norm": 1.796796202659607,
+      "learning_rate": 7.202571276312284e-06,
+      "loss": 0.72,
+      "step": 25700
+    },
+    {
+      "epoch": 5.155875299760192,
+      "grad_norm": 1.8212794065475464,
+      "learning_rate": 7.0360378363975495e-06,
+      "loss": 0.7004,
+      "step": 25800
+    },
+    {
+      "epoch": 5.17585931254996,
+      "grad_norm": 1.0340906381607056,
+      "learning_rate": 6.869504396482813e-06,
+      "loss": 0.6687,
+      "step": 25900
+    },
+    {
+      "epoch": 5.1958433253397285,
+      "grad_norm": 1.8287034034729004,
+      "learning_rate": 6.702970956568079e-06,
+      "loss": 0.6774,
+      "step": 26000
+    },
+    {
+      "epoch": 5.215827338129497,
+      "grad_norm": 1.657259225845337,
+      "learning_rate": 6.536437516653344e-06,
+      "loss": 0.6995,
+      "step": 26100
+    },
+    {
+      "epoch": 5.235811350919264,
+      "grad_norm": 1.8235076665878296,
+      "learning_rate": 6.36990407673861e-06,
+      "loss": 0.7814,
+      "step": 26200
+    },
+    {
+      "epoch": 5.255795363709033,
+      "grad_norm": 1.6127688884735107,
+      "learning_rate": 6.203370636823875e-06,
+      "loss": 0.6797,
+      "step": 26300
+    },
+    {
+      "epoch": 5.275779376498801,
+      "grad_norm": 1.2275160551071167,
+      "learning_rate": 6.03683719690914e-06,
+      "loss": 0.7336,
+      "step": 26400
+    },
+    {
+      "epoch": 5.295763389288569,
+      "grad_norm": 1.6593281030654907,
+      "learning_rate": 5.870303756994405e-06,
+      "loss": 0.6988,
+      "step": 26500
+    },
+    {
+      "epoch": 5.315747402078338,
+      "grad_norm": 1.1069490909576416,
+      "learning_rate": 5.70377031707967e-06,
+      "loss": 0.801,
+      "step": 26600
+    },
+    {
+      "epoch": 5.335731414868105,
+      "grad_norm": 1.7498623132705688,
+      "learning_rate": 5.537236877164935e-06,
+      "loss": 0.715,
+      "step": 26700
+    },
+    {
+      "epoch": 5.355715427657874,
+      "grad_norm": 1.7322038412094116,
+      "learning_rate": 5.3707034372502e-06,
+      "loss": 0.7076,
+      "step": 26800
+    },
+    {
+      "epoch": 5.375699440447642,
+      "grad_norm": 1.2660248279571533,
+      "learning_rate": 5.204169997335465e-06,
+      "loss": 0.7494,
+      "step": 26900
+    },
+    {
+      "epoch": 5.39568345323741,
+      "grad_norm": 2.537752628326416,
+      "learning_rate": 5.03763655742073e-06,
+      "loss": 0.7326,
+      "step": 27000
+    },
+    {
+      "epoch": 5.415667466027179,
+      "grad_norm": 0.991534411907196,
+      "learning_rate": 4.8711031175059955e-06,
+      "loss": 0.6929,
+      "step": 27100
+    },
+    {
+      "epoch": 5.435651478816946,
+      "grad_norm": 2.0230729579925537,
+      "learning_rate": 4.70456967759126e-06,
+      "loss": 0.6787,
+      "step": 27200
+    },
+    {
+      "epoch": 5.4556354916067145,
+      "grad_norm": 1.5560120344161987,
+      "learning_rate": 4.538036237676526e-06,
+      "loss": 0.7251,
+      "step": 27300
+    },
+    {
+      "epoch": 5.475619504396483,
+      "grad_norm": 1.5086272954940796,
+      "learning_rate": 4.371502797761791e-06,
+      "loss": 0.7066,
+      "step": 27400
+    },
+    {
+      "epoch": 5.495603517186251,
+      "grad_norm": 1.6183174848556519,
+      "learning_rate": 4.204969357847056e-06,
+      "loss": 0.7161,
+      "step": 27500
+    },
+    {
+      "epoch": 5.5155875299760195,
+      "grad_norm": 1.1214239597320557,
+      "learning_rate": 4.0384359179323214e-06,
+      "loss": 0.7414,
+      "step": 27600
+    },
+    {
+      "epoch": 5.535571542765787,
+      "grad_norm": 1.4948476552963257,
+      "learning_rate": 3.871902478017586e-06,
+      "loss": 0.7303,
+      "step": 27700
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 1.094460368156433,
+      "learning_rate": 3.705369038102851e-06,
+      "loss": 0.7214,
+      "step": 27800
+    },
+    {
+      "epoch": 5.575539568345324,
+      "grad_norm": 1.8006253242492676,
+      "learning_rate": 3.5388355981881163e-06,
+      "loss": 0.7382,
+      "step": 27900
+    },
+    {
+      "epoch": 5.595523581135092,
+      "grad_norm": 1.0595532655715942,
+      "learning_rate": 3.3723021582733815e-06,
+      "loss": 0.6835,
+      "step": 28000
+    },
+    {
+      "epoch": 5.61550759392486,
+      "grad_norm": 1.5675129890441895,
+      "learning_rate": 3.205768718358647e-06,
+      "loss": 0.7426,
+      "step": 28100
+    },
+    {
+      "epoch": 5.635491606714629,
+      "grad_norm": 1.543182134628296,
+      "learning_rate": 3.0392352784439117e-06,
+      "loss": 0.7393,
+      "step": 28200
+    },
+    {
+      "epoch": 5.655475619504396,
+      "grad_norm": 1.6735225915908813,
+      "learning_rate": 2.8727018385291768e-06,
+      "loss": 0.7106,
+      "step": 28300
+    },
+    {
+      "epoch": 5.675459632294165,
+      "grad_norm": 1.2037389278411865,
+      "learning_rate": 2.706168398614442e-06,
+      "loss": 0.6928,
+      "step": 28400
+    },
+    {
+      "epoch": 5.695443645083933,
+      "grad_norm": 1.957836627960205,
+      "learning_rate": 2.539634958699707e-06,
+      "loss": 0.8086,
+      "step": 28500
+    },
+    {
+      "epoch": 5.715427657873701,
+      "grad_norm": 2.085599899291992,
+      "learning_rate": 2.373101518784972e-06,
+      "loss": 0.7587,
+      "step": 28600
+    },
+    {
+      "epoch": 5.735411670663469,
+      "grad_norm": 1.3564984798431396,
+      "learning_rate": 2.206568078870237e-06,
+      "loss": 0.7197,
+      "step": 28700
+    },
+    {
+      "epoch": 5.755395683453237,
+      "grad_norm": 1.659226655960083,
+      "learning_rate": 2.0400346389555023e-06,
+      "loss": 0.728,
+      "step": 28800
+    },
+    {
+      "epoch": 5.7753796962430055,
+      "grad_norm": 1.3784935474395752,
+      "learning_rate": 1.8735011990407676e-06,
+      "loss": 0.7561,
+      "step": 28900
+    },
+    {
+      "epoch": 5.795363709032774,
+      "grad_norm": 1.4514496326446533,
+      "learning_rate": 1.7069677591260325e-06,
+      "loss": 0.7205,
+      "step": 29000
+    },
+    {
+      "epoch": 5.815347721822542,
+      "grad_norm": 1.7896771430969238,
+      "learning_rate": 1.5404343192112976e-06,
+      "loss": 0.667,
+      "step": 29100
+    },
+    {
+      "epoch": 5.835331734612311,
+      "grad_norm": 1.4074804782867432,
+      "learning_rate": 1.3739008792965628e-06,
+      "loss": 0.71,
+      "step": 29200
+    },
+    {
+      "epoch": 5.855315747402078,
+      "grad_norm": 1.33772873878479,
+      "learning_rate": 1.2073674393818279e-06,
+      "loss": 0.7688,
+      "step": 29300
+    },
+    {
+      "epoch": 5.875299760191846,
+      "grad_norm": 1.8295559883117676,
+      "learning_rate": 1.040833999467093e-06,
+      "loss": 0.7439,
+      "step": 29400
+    },
+    {
+      "epoch": 5.895283772981615,
+      "grad_norm": 0.9400151371955872,
+      "learning_rate": 8.743005595523582e-07,
+      "loss": 0.6891,
+      "step": 29500
+    },
+    {
+      "epoch": 5.915267785771383,
+      "grad_norm": 1.7990922927856445,
+      "learning_rate": 7.077671196376233e-07,
+      "loss": 0.6384,
+      "step": 29600
+    },
+    {
+      "epoch": 5.935251798561151,
+      "grad_norm": 1.74308180809021,
+      "learning_rate": 5.412336797228884e-07,
+      "loss": 0.6973,
+      "step": 29700
+    },
+    {
+      "epoch": 5.955235811350919,
+      "grad_norm": 1.1248557567596436,
+      "learning_rate": 3.747002398081535e-07,
+      "loss": 0.7265,
+      "step": 29800
+    },
+    {
+      "epoch": 5.975219824140687,
+      "grad_norm": 1.9805783033370972,
+      "learning_rate": 2.0816679989341861e-07,
+      "loss": 0.7107,
+      "step": 29900
+    },
+    {
+      "epoch": 5.995203836930456,
+      "grad_norm": 1.6576383113861084,
+      "learning_rate": 4.163335997868372e-08,
+      "loss": 0.7073,
+      "step": 30000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 30024,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.230686056448e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-30000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef669be81d20daf424937932b11920f44997980d862a4dbeacd08759cb53271
+size 5713

checkpoint-30024/config.json

@@ -0,0 +1,61 @@
+{
+  "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": 8,
+  "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: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

checkpoint-30024/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": "4.54.1"
+}

checkpoint-30024/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d7d9cb3c9cd110d27b0464310c8b788a909e82f8d23c4e56ae2fdbee5cc903
+size 307867048

checkpoint-30024/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be76fb56a8461899878d683831a8113766928fdf72349559d6d10597ce0d517e
+size 615849867

checkpoint-30024/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8567b48fb50aa0903245359bf3618906e48927b97b119f418f4717d526db011
+size 14645

checkpoint-30024/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2565f85582426109645d0a1ce803714f38f9ac7ea0969f70393bc74d611d4530
+size 1465

checkpoint-30024/special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "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": {
+    "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
+  }
+}

checkpoint-30024/tokenizer_config.json

@@ -0,0 +1,940 @@
+{
+  "add_prefix_space": null,
+  "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
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-30024/trainer_state.json

@@ -0,0 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 30024,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.019984012789768184,
+      "grad_norm": 10.435233116149902,
+      "learning_rate": 4.9835131894484415e-05,
+      "loss": 14.0782,
+      "step": 100
+    },
+    {
+      "epoch": 0.03996802557953637,
+      "grad_norm": 19.157014846801758,
+      "learning_rate": 4.966859845456968e-05,
+      "loss": 3.596,
+      "step": 200
+    },
+    {
+      "epoch": 0.05995203836930456,
+      "grad_norm": 5.946423530578613,
+      "learning_rate": 4.950206501465495e-05,
+      "loss": 2.0558,
+      "step": 300
+    },
+    {
+      "epoch": 0.07993605115907274,
+      "grad_norm": 2.1558027267456055,
+      "learning_rate": 4.9335531574740214e-05,
+      "loss": 1.3957,
+      "step": 400
+    },
+    {
+      "epoch": 0.09992006394884093,
+      "grad_norm": 2.5541210174560547,
+      "learning_rate": 4.916899813482548e-05,
+      "loss": 1.252,
+      "step": 500
+    },
+    {
+      "epoch": 0.11990407673860912,
+      "grad_norm": 1.8417296409606934,
+      "learning_rate": 4.9002464694910735e-05,
+      "loss": 1.1695,
+      "step": 600
+    },
+    {
+      "epoch": 0.1398880895283773,
+      "grad_norm": 1.654639720916748,
+      "learning_rate": 4.8835931254996005e-05,
+      "loss": 1.1848,
+      "step": 700
+    },
+    {
+      "epoch": 0.15987210231814547,
+      "grad_norm": 2.093991756439209,
+      "learning_rate": 4.866939781508127e-05,
+      "loss": 1.1056,
+      "step": 800
+    },
+    {
+      "epoch": 0.17985611510791366,
+      "grad_norm": 1.9905765056610107,
+      "learning_rate": 4.850286437516653e-05,
+      "loss": 1.1186,
+      "step": 900
+    },
+    {
+      "epoch": 0.19984012789768185,
+      "grad_norm": 1.2864068746566772,
+      "learning_rate": 4.83363309352518e-05,
+      "loss": 1.1394,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21982414068745004,
+      "grad_norm": 1.5142974853515625,
+      "learning_rate": 4.816979749533707e-05,
+      "loss": 1.1162,
+      "step": 1100
+    },
+    {
+      "epoch": 0.23980815347721823,
+      "grad_norm": 0.9597436189651489,
+      "learning_rate": 4.800326405542233e-05,
+      "loss": 1.0922,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2597921662669864,
+      "grad_norm": 1.7915301322937012,
+      "learning_rate": 4.7836730615507595e-05,
+      "loss": 1.0711,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2797761790567546,
+      "grad_norm": 1.1338952779769897,
+      "learning_rate": 4.767019717559286e-05,
+      "loss": 0.9945,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2997601918465228,
+      "grad_norm": 1.3437297344207764,
+      "learning_rate": 4.750366373567813e-05,
+      "loss": 1.0322,
+      "step": 1500
+    },
+    {
+      "epoch": 0.31974420463629094,
+      "grad_norm": 1.2949973344802856,
+      "learning_rate": 4.733713029576339e-05,
+      "loss": 1.0613,
+      "step": 1600
+    },
+    {
+      "epoch": 0.33972821742605913,
+      "grad_norm": 1.1362179517745972,
+      "learning_rate": 4.717059685584866e-05,
+      "loss": 1.0122,
+      "step": 1700
+    },
+    {
+      "epoch": 0.3597122302158273,
+      "grad_norm": 1.1878063678741455,
+      "learning_rate": 4.700406341593392e-05,
+      "loss": 1.0068,
+      "step": 1800
+    },
+    {
+      "epoch": 0.3796962430055955,
+      "grad_norm": 1.3588361740112305,
+      "learning_rate": 4.6837529976019185e-05,
+      "loss": 0.955,
+      "step": 1900
+    },
+    {
+      "epoch": 0.3996802557953637,
+      "grad_norm": 1.1428577899932861,
+      "learning_rate": 4.667099653610445e-05,
+      "loss": 0.9863,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4196642685851319,
+      "grad_norm": 1.6441487073898315,
+      "learning_rate": 4.650446309618971e-05,
+      "loss": 0.9532,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4396482813749001,
+      "grad_norm": 2.607586145401001,
+      "learning_rate": 4.633792965627498e-05,
+      "loss": 0.9877,
+      "step": 2200
+    },
+    {
+      "epoch": 0.4596322941646683,
+      "grad_norm": 2.24434757232666,
+      "learning_rate": 4.617139621636025e-05,
+      "loss": 0.9956,
+      "step": 2300
+    },
+    {
+      "epoch": 0.47961630695443647,
+      "grad_norm": 1.8238356113433838,
+      "learning_rate": 4.600486277644551e-05,
+      "loss": 0.9769,
+      "step": 2400
+    },
+    {
+      "epoch": 0.49960031974420466,
+      "grad_norm": 2.0538158416748047,
+      "learning_rate": 4.5838329336530775e-05,
+      "loss": 0.9458,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5195843325339728,
+      "grad_norm": 2.1354427337646484,
+      "learning_rate": 4.5671795896616045e-05,
+      "loss": 0.975,
+      "step": 2600
+    },
+    {
+      "epoch": 0.539568345323741,
+      "grad_norm": 1.3763636350631714,
+      "learning_rate": 4.550526245670131e-05,
+      "loss": 0.9464,
+      "step": 2700
+    },
+    {
+      "epoch": 0.5595523581135092,
+      "grad_norm": 2.6834394931793213,
+      "learning_rate": 4.533872901678657e-05,
+      "loss": 0.9437,
+      "step": 2800
+    },
+    {
+      "epoch": 0.5795363709032774,
+      "grad_norm": 1.3325830698013306,
+      "learning_rate": 4.517219557687184e-05,
+      "loss": 0.9617,
+      "step": 2900
+    },
+    {
+      "epoch": 0.5995203836930456,
+      "grad_norm": 1.841642141342163,
+      "learning_rate": 4.500566213695711e-05,
+      "loss": 0.9489,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6195043964828137,
+      "grad_norm": 1.0305529832839966,
+      "learning_rate": 4.483912869704237e-05,
+      "loss": 0.9432,
+      "step": 3100
+    },
+    {
+      "epoch": 0.6394884092725819,
+      "grad_norm": 1.4249075651168823,
+      "learning_rate": 4.467259525712763e-05,
+      "loss": 0.952,
+      "step": 3200
+    },
+    {
+      "epoch": 0.6594724220623501,
+      "grad_norm": 1.2994813919067383,
+      "learning_rate": 4.45060618172129e-05,
+      "loss": 1.0247,
+      "step": 3300
+    },
+    {
+      "epoch": 0.6794564348521183,
+      "grad_norm": 1.537548303604126,
+      "learning_rate": 4.433952837729816e-05,
+      "loss": 0.928,
+      "step": 3400
+    },
+    {
+      "epoch": 0.6994404476418865,
+      "grad_norm": 1.646200180053711,
+      "learning_rate": 4.4172994937383427e-05,
+      "loss": 0.9817,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7194244604316546,
+      "grad_norm": 1.2779592275619507,
+      "learning_rate": 4.400646149746869e-05,
+      "loss": 0.8974,
+      "step": 3600
+    },
+    {
+      "epoch": 0.7394084732214229,
+      "grad_norm": 1.7886369228363037,
+      "learning_rate": 4.383992805755396e-05,
+      "loss": 0.9351,
+      "step": 3700
+    },
+    {
+      "epoch": 0.759392486011191,
+      "grad_norm": 1.5072957277297974,
+      "learning_rate": 4.3673394617639225e-05,
+      "loss": 0.882,
+      "step": 3800
+    },
+    {
+      "epoch": 0.7793764988009593,
+      "grad_norm": 2.019421339035034,
+      "learning_rate": 4.350686117772449e-05,
+      "loss": 0.9324,
+      "step": 3900
+    },
+    {
+      "epoch": 0.7993605115907274,
+      "grad_norm": 1.7232331037521362,
+      "learning_rate": 4.334032773780975e-05,
+      "loss": 0.9094,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8193445243804957,
+      "grad_norm": 1.7297419309616089,
+      "learning_rate": 4.317379429789502e-05,
+      "loss": 0.9658,
+      "step": 4100
+    },
+    {
+      "epoch": 0.8393285371702638,
+      "grad_norm": 1.560420274734497,
+      "learning_rate": 4.300726085798029e-05,
+      "loss": 0.9613,
+      "step": 4200
+    },
+    {
+      "epoch": 0.8593125499600319,
+      "grad_norm": 1.9014427661895752,
+      "learning_rate": 4.284072741806555e-05,
+      "loss": 0.9047,
+      "step": 4300
+    },
+    {
+      "epoch": 0.8792965627498002,
+      "grad_norm": 1.4741132259368896,
+      "learning_rate": 4.2674193978150815e-05,
+      "loss": 0.7914,
+      "step": 4400
+    },
+    {
+      "epoch": 0.8992805755395683,
+      "grad_norm": 0.8008555173873901,
+      "learning_rate": 4.250766053823608e-05,
+      "loss": 0.8678,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9192645883293366,
+      "grad_norm": 1.5738321542739868,
+      "learning_rate": 4.234112709832134e-05,
+      "loss": 0.8379,
+      "step": 4600
+    },
+    {
+      "epoch": 0.9392486011191047,
+      "grad_norm": 1.7838175296783447,
+      "learning_rate": 4.2174593658406606e-05,
+      "loss": 0.9581,
+      "step": 4700
+    },
+    {
+      "epoch": 0.9592326139088729,
+      "grad_norm": 1.6761012077331543,
+      "learning_rate": 4.200806021849188e-05,
+      "loss": 0.8583,
+      "step": 4800
+    },
+    {
+      "epoch": 0.9792166266986411,
+      "grad_norm": 1.320033073425293,
+      "learning_rate": 4.184152677857714e-05,
+      "loss": 0.8709,
+      "step": 4900
+    },
+    {
+      "epoch": 0.9992006394884093,
+      "grad_norm": 2.0931804180145264,
+      "learning_rate": 4.1674993338662404e-05,
+      "loss": 0.9064,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0191846522781776,
+      "grad_norm": 1.1682066917419434,
+      "learning_rate": 4.150845989874767e-05,
+      "loss": 0.8728,
+      "step": 5100
+    },
+    {
+      "epoch": 1.0391686650679457,
+      "grad_norm": 1.2569072246551514,
+      "learning_rate": 4.134192645883294e-05,
+      "loss": 0.8921,
+      "step": 5200
+    },
+    {
+      "epoch": 1.0591526778577138,
+      "grad_norm": 1.4215683937072754,
+      "learning_rate": 4.11753930189182e-05,
+      "loss": 0.8211,
+      "step": 5300
+    },
+    {
+      "epoch": 1.079136690647482,
+      "grad_norm": 1.6081187725067139,
+      "learning_rate": 4.1008859579003467e-05,
+      "loss": 0.9338,
+      "step": 5400
+    },
+    {
+      "epoch": 1.09912070343725,
+      "grad_norm": 1.4916200637817383,
+      "learning_rate": 4.084232613908873e-05,
+      "loss": 0.8142,
+      "step": 5500
+    },
+    {
+      "epoch": 1.1191047162270185,
+      "grad_norm": 1.8639625310897827,
+      "learning_rate": 4.0675792699174e-05,
+      "loss": 0.8746,
+      "step": 5600
+    },
+    {
+      "epoch": 1.1390887290167866,
+      "grad_norm": 1.1741764545440674,
+      "learning_rate": 4.0509259259259265e-05,
+      "loss": 0.8032,
+      "step": 5700
+    },
+    {
+      "epoch": 1.1590727418065547,
+      "grad_norm": 1.7627875804901123,
+      "learning_rate": 4.034272581934453e-05,
+      "loss": 0.8681,
+      "step": 5800
+    },
+    {
+      "epoch": 1.1790567545963229,
+      "grad_norm": 0.7432733178138733,
+      "learning_rate": 4.0176192379429786e-05,
+      "loss": 0.8968,
+      "step": 5900
+    },
+    {
+      "epoch": 1.1990407673860912,
+      "grad_norm": 1.5172642469406128,
+      "learning_rate": 4.0009658939515056e-05,
+      "loss": 0.9653,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2190247801758594,
+      "grad_norm": 2.0822958946228027,
+      "learning_rate": 3.984312549960032e-05,
+      "loss": 0.8038,
+      "step": 6100
+    },
+    {
+      "epoch": 1.2390087929656275,
+      "grad_norm": 2.2852039337158203,
+      "learning_rate": 3.9676592059685584e-05,
+      "loss": 0.8041,
+      "step": 6200
+    },
+    {
+      "epoch": 1.2589928057553956,
+      "grad_norm": 1.214968204498291,
+      "learning_rate": 3.951005861977085e-05,
+      "loss": 0.8382,
+      "step": 6300
+    },
+    {
+      "epoch": 1.2789768185451638,
+      "grad_norm": 2.792722225189209,
+      "learning_rate": 3.934352517985612e-05,
+      "loss": 0.8534,
+      "step": 6400
+    },
+    {
+      "epoch": 1.2989608313349321,
+      "grad_norm": 1.6279624700546265,
+      "learning_rate": 3.917699173994138e-05,
+      "loss": 0.8387,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3189448441247003,
+      "grad_norm": 1.57301664352417,
+      "learning_rate": 3.9010458300026646e-05,
+      "loss": 0.8583,
+      "step": 6600
+    },
+    {
+      "epoch": 1.3389288569144684,
+      "grad_norm": 1.2693675756454468,
+      "learning_rate": 3.884392486011191e-05,
+      "loss": 0.7893,
+      "step": 6700
+    },
+    {
+      "epoch": 1.3589128697042367,
+      "grad_norm": 1.1760280132293701,
+      "learning_rate": 3.867739142019718e-05,
+      "loss": 0.8204,
+      "step": 6800
+    },
+    {
+      "epoch": 1.3788968824940047,
+      "grad_norm": 1.8213127851486206,
+      "learning_rate": 3.8510857980282444e-05,
+      "loss": 0.9061,
+      "step": 6900
+    },
+    {
+      "epoch": 1.398880895283773,
+      "grad_norm": 1.2589592933654785,
+      "learning_rate": 3.834432454036771e-05,
+      "loss": 0.856,
+      "step": 7000
+    },
+    {
+      "epoch": 1.4188649080735412,
+      "grad_norm": 2.5817718505859375,
+      "learning_rate": 3.817779110045297e-05,
+      "loss": 0.8542,
+      "step": 7100
+    },
+    {
+      "epoch": 1.4388489208633093,
+      "grad_norm": 1.1825404167175293,
+      "learning_rate": 3.8011257660538236e-05,
+      "loss": 0.8298,
+      "step": 7200
+    },
+    {
+      "epoch": 1.4588329336530776,
+      "grad_norm": 1.6443575620651245,
+      "learning_rate": 3.78447242206235e-05,
+      "loss": 0.823,
+      "step": 7300
+    },
+    {
+      "epoch": 1.4788169464428458,
+      "grad_norm": 1.9887899160385132,
+      "learning_rate": 3.7678190780708764e-05,
+      "loss": 0.7936,
+      "step": 7400
+    },
+    {
+      "epoch": 1.498800959232614,
+      "grad_norm": 1.8799304962158203,
+      "learning_rate": 3.7511657340794034e-05,
+      "loss": 0.8755,
+      "step": 7500
+    },
+    {
+      "epoch": 1.518784972022382,
+      "grad_norm": 1.6680015325546265,
+      "learning_rate": 3.73451239008793e-05,
+      "loss": 0.8669,
+      "step": 7600
+    },
+    {
+      "epoch": 1.5387689848121502,
+      "grad_norm": 1.7756261825561523,
+      "learning_rate": 3.717859046096456e-05,
+      "loss": 0.8572,
+      "step": 7700
+    },
+    {
+      "epoch": 1.5587529976019185,
+      "grad_norm": 1.3951911926269531,
+      "learning_rate": 3.7012057021049826e-05,
+      "loss": 0.8422,
+      "step": 7800
+    },
+    {
+      "epoch": 1.5787370103916867,
+      "grad_norm": 1.8145322799682617,
+      "learning_rate": 3.6845523581135096e-05,
+      "loss": 0.783,
+      "step": 7900
+    },
+    {
+      "epoch": 1.5987210231814548,
+      "grad_norm": 1.4113447666168213,
+      "learning_rate": 3.667899014122036e-05,
+      "loss": 0.8368,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6187050359712232,
+      "grad_norm": 1.5562957525253296,
+      "learning_rate": 3.6512456701305624e-05,
+      "loss": 0.8232,
+      "step": 8100
+    },
+    {
+      "epoch": 1.638689048760991,
+      "grad_norm": 2.0334463119506836,
+      "learning_rate": 3.634592326139089e-05,
+      "loss": 0.8272,
+      "step": 8200
+    },
+    {
+      "epoch": 1.6586730615507594,
+      "grad_norm": 2.305115222930908,
+      "learning_rate": 3.617938982147616e-05,
+      "loss": 0.8708,
+      "step": 8300
+    },
+    {
+      "epoch": 1.6786570743405276,
+      "grad_norm": 1.9576376676559448,
+      "learning_rate": 3.601285638156142e-05,
+      "loss": 0.8437,
+      "step": 8400
+    },
+    {
+      "epoch": 1.6986410871302957,
+      "grad_norm": 1.324064016342163,
+      "learning_rate": 3.584632294164668e-05,
+      "loss": 0.8197,
+      "step": 8500
+    },
+    {
+      "epoch": 1.718625099920064,
+      "grad_norm": 1.5594903230667114,
+      "learning_rate": 3.567978950173195e-05,
+      "loss": 0.8365,
+      "step": 8600
+    },
+    {
+      "epoch": 1.738609112709832,
+      "grad_norm": 1.853633999824524,
+      "learning_rate": 3.5513256061817214e-05,
+      "loss": 0.7914,
+      "step": 8700
+    },
+    {
+      "epoch": 1.7585931254996003,
+      "grad_norm": 1.839158296585083,
+      "learning_rate": 3.534672262190248e-05,
+      "loss": 0.9374,
+      "step": 8800
+    },
+    {
+      "epoch": 1.7785771382893685,
+      "grad_norm": 2.5038366317749023,
+      "learning_rate": 3.518018918198774e-05,
+      "loss": 0.8202,
+      "step": 8900
+    },
+    {
+      "epoch": 1.7985611510791366,
+      "grad_norm": 1.7603284120559692,
+      "learning_rate": 3.501365574207301e-05,
+      "loss": 0.8346,
+      "step": 9000
+    },
+    {
+      "epoch": 1.818545163868905,
+      "grad_norm": 1.9243416786193848,
+      "learning_rate": 3.4847122302158276e-05,
+      "loss": 0.8141,
+      "step": 9100
+    },
+    {
+      "epoch": 1.838529176658673,
+      "grad_norm": 1.6993930339813232,
+      "learning_rate": 3.468058886224354e-05,
+      "loss": 0.7974,
+      "step": 9200
+    },
+    {
+      "epoch": 1.8585131894484412,
+      "grad_norm": 1.9248780012130737,
+      "learning_rate": 3.4514055422328804e-05,
+      "loss": 0.8543,
+      "step": 9300
+    },
+    {
+      "epoch": 1.8784972022382096,
+      "grad_norm": 1.7247469425201416,
+      "learning_rate": 3.4347521982414074e-05,
+      "loss": 0.7968,
+      "step": 9400
+    },
+    {
+      "epoch": 1.8984812150279775,
+      "grad_norm": 1.165992259979248,
+      "learning_rate": 3.418098854249934e-05,
+      "loss": 0.7946,
+      "step": 9500
+    },
+    {
+      "epoch": 1.9184652278177459,
+      "grad_norm": 1.5617034435272217,
+      "learning_rate": 3.40144551025846e-05,
+      "loss": 0.8452,
+      "step": 9600
+    },
+    {
+      "epoch": 1.938449240607514,
+      "grad_norm": 1.9524955749511719,
+      "learning_rate": 3.3847921662669866e-05,
+      "loss": 0.821,
+      "step": 9700
+    },
+    {
+      "epoch": 1.9584332533972821,
+      "grad_norm": 1.201984167098999,
+      "learning_rate": 3.3681388222755136e-05,
+      "loss": 0.8244,
+      "step": 9800
+    },
+    {
+      "epoch": 1.9784172661870505,
+      "grad_norm": 1.5261083841323853,
+      "learning_rate": 3.3514854782840393e-05,
+      "loss": 0.8521,
+      "step": 9900
+    },
+    {
+      "epoch": 1.9984012789768184,
+      "grad_norm": 0.8879593014717102,
+      "learning_rate": 3.334832134292566e-05,
+      "loss": 0.7745,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0183852917665868,
+      "grad_norm": 1.9460114240646362,
+      "learning_rate": 3.318178790301093e-05,
+      "loss": 0.7926,
+      "step": 10100
+    },
+    {
+      "epoch": 2.038369304556355,
+      "grad_norm": 2.0698747634887695,
+      "learning_rate": 3.301525446309619e-05,
+      "loss": 0.8668,
+      "step": 10200
+    },
+    {
+      "epoch": 2.058353317346123,
+      "grad_norm": 1.6188371181488037,
+      "learning_rate": 3.2848721023181456e-05,
+      "loss": 0.7743,
+      "step": 10300
+    },
+    {
+      "epoch": 2.0783373301358914,
+      "grad_norm": 1.4746142625808716,
+      "learning_rate": 3.268218758326672e-05,
+      "loss": 0.776,
+      "step": 10400
+    },
+    {
+      "epoch": 2.0983213429256593,
+      "grad_norm": 2.6285245418548584,
+      "learning_rate": 3.251565414335199e-05,
+      "loss": 0.7952,
+      "step": 10500
+    },
+    {
+      "epoch": 2.1183053557154277,
+      "grad_norm": 2.9462263584136963,
+      "learning_rate": 3.2349120703437254e-05,
+      "loss": 0.8492,
+      "step": 10600
+    },
+    {
+      "epoch": 2.138289368505196,
+      "grad_norm": 2.2768771648406982,
+      "learning_rate": 3.218258726352252e-05,
+      "loss": 0.7773,
+      "step": 10700
+    },
+    {
+      "epoch": 2.158273381294964,
+      "grad_norm": 2.4314112663269043,
+      "learning_rate": 3.201605382360778e-05,
+      "loss": 0.7789,
+      "step": 10800
+    },
+    {
+      "epoch": 2.1782573940847323,
+      "grad_norm": 2.631697654724121,
+      "learning_rate": 3.184952038369305e-05,
+      "loss": 0.7809,
+      "step": 10900
+    },
+    {
+      "epoch": 2.1982414068745,
+      "grad_norm": 2.0636370182037354,
+      "learning_rate": 3.1682986943778316e-05,
+      "loss": 0.7627,
+      "step": 11000
+    },
+    {
+      "epoch": 2.2182254196642686,
+      "grad_norm": 1.861494779586792,
+      "learning_rate": 3.151645350386358e-05,
+      "loss": 0.7454,
+      "step": 11100
+    },
+    {
+      "epoch": 2.238209432454037,
+      "grad_norm": 1.6431078910827637,
+      "learning_rate": 3.134992006394884e-05,
+      "loss": 0.8208,
+      "step": 11200
+    },
+    {
+      "epoch": 2.258193445243805,
+      "grad_norm": 1.1081715822219849,
+      "learning_rate": 3.118338662403411e-05,
+      "loss": 0.7963,
+      "step": 11300
+    },
+    {
+      "epoch": 2.278177458033573,
+      "grad_norm": 1.6696077585220337,
+      "learning_rate": 3.101685318411937e-05,
+      "loss": 0.7948,
+      "step": 11400
+    },
+    {
+      "epoch": 2.2981614708233415,
+      "grad_norm": 1.1712377071380615,
+      "learning_rate": 3.0850319744204635e-05,
+      "loss": 0.7907,
+      "step": 11500
+    },
+    {
+      "epoch": 2.3181454836131095,
+      "grad_norm": 1.28898024559021,
+      "learning_rate": 3.06837863042899e-05,
+      "loss": 0.7791,
+      "step": 11600
+    },
+    {
+      "epoch": 2.338129496402878,
+      "grad_norm": 1.3267985582351685,
+      "learning_rate": 3.0517252864375166e-05,
+      "loss": 0.7819,
+      "step": 11700
+    },
+    {
+      "epoch": 2.3581135091926457,
+      "grad_norm": 1.4074293375015259,
+      "learning_rate": 3.0350719424460434e-05,
+      "loss": 0.818,
+      "step": 11800
+    },
+    {
+      "epoch": 2.378097521982414,
+      "grad_norm": 0.9492627382278442,
+      "learning_rate": 3.0184185984545697e-05,
+      "loss": 0.7689,
+      "step": 11900
+    },
+    {
+      "epoch": 2.3980815347721824,
+      "grad_norm": 1.8090003728866577,
+      "learning_rate": 3.0017652544630965e-05,
+      "loss": 0.7845,
+      "step": 12000
+    },
+    {
+      "epoch": 2.4180655475619504,
+      "grad_norm": 1.899207353591919,
+      "learning_rate": 2.985111910471623e-05,
+      "loss": 0.7742,
+      "step": 12100
+    },
+    {
+      "epoch": 2.4380495603517187,
+      "grad_norm": 2.0821797847747803,
+      "learning_rate": 2.9684585664801496e-05,
+      "loss": 0.7696,
+      "step": 12200
+    },
+    {
+      "epoch": 2.4580335731414866,
+      "grad_norm": 1.089876651763916,
+      "learning_rate": 2.951805222488676e-05,
+      "loss": 0.7873,
+      "step": 12300
+    },
+    {
+      "epoch": 2.478017585931255,
+      "grad_norm": 1.265599250793457,
+      "learning_rate": 2.9351518784972027e-05,
+      "loss": 0.7504,
+      "step": 12400
+    },
+    {
+      "epoch": 2.4980015987210233,
+      "grad_norm": 2.7753829956054688,
+      "learning_rate": 2.9184985345057287e-05,
+      "loss": 0.7824,
+      "step": 12500
+    },
+    {
+      "epoch": 2.5179856115107913,
+      "grad_norm": 1.0310410261154175,
+      "learning_rate": 2.901845190514255e-05,
+      "loss": 0.7326,
+      "step": 12600
+    },
+    {
+      "epoch": 2.5379696243005596,
+      "grad_norm": 2.056279182434082,
+      "learning_rate": 2.8851918465227818e-05,
+      "loss": 0.8411,
+      "step": 12700
+    },
+    {
+      "epoch": 2.5579536370903275,
+      "grad_norm": 1.1815407276153564,
+      "learning_rate": 2.8685385025313082e-05,
+      "loss": 0.805,
+      "step": 12800
+    },
+    {
+      "epoch": 2.577937649880096,
+      "grad_norm": 1.6167210340499878,
+      "learning_rate": 2.851885158539835e-05,
+      "loss": 0.7311,
+      "step": 12900
+    },
+    {
+      "epoch": 2.5979216626698642,
+      "grad_norm": 1.488755226135254,
+      "learning_rate": 2.8352318145483613e-05,
+      "loss": 0.8335,
+      "step": 13000
+    },
+    {
+      "epoch": 2.617905675459632,
+      "grad_norm": 2.5013859272003174,
+      "learning_rate": 2.818578470556888e-05,
+      "loss": 0.7833,
+      "step": 13100
+    },
+    {
+      "epoch": 2.6378896882494005,
+      "grad_norm": 1.102152943611145,
+      "learning_rate": 2.8019251265654144e-05,
+      "loss": 0.7536,
+      "step": 13200
+    },
+    {
+      "epoch": 2.6578737010391684,
+      "grad_norm": 1.3805499076843262,
+      "learning_rate": 2.785271782573941e-05,
+      "loss": 0.775,
+      "step": 13300
+    },
+    {
+      "epoch": 2.677857713828937,
+      "grad_norm": 2.189347505569458,
+      "learning_rate": 2.7686184385824675e-05,
+      "loss": 0.8178,
+      "step": 13400
+    },
+    {
+      "epoch": 2.697841726618705,
+      "grad_norm": 0.9750763177871704,
+      "learning_rate": 2.7519650945909942e-05,
+      "loss": 0.7743,
+      "step": 13500
+    },
+    {
+      "epoch": 2.7178257394084735,
+      "grad_norm": 1.2844312191009521,
+      "learning_rate": 2.7353117505995206e-05,
+      "loss": 0.7631,
+      "step": 13600
+    },
+    {
+      "epoch": 2.7378097521982414,
+      "grad_norm": 1.4551914930343628,
+      "learning_rate": 2.7186584066080474e-05,
+      "loss": 0.76,
+      "step": 13700
+    },
+    {
+      "epoch": 2.7577937649880093,
+      "grad_norm": 0.8891064524650574,
+      "learning_rate": 2.7020050626165734e-05,
+      "loss": 0.8252,
+      "step": 13800
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 1.9776784181594849,
+      "learning_rate": 2.6853517186250998e-05,
+      "loss": 0.8037,
+      "step": 13900
+    },
+    {
+      "epoch": 2.797761790567546,
+      "grad_norm": 1.429692029953003,
+      "learning_rate": 2.6686983746336265e-05,
+      "loss": 0.7369,
+      "step": 14000
+    },
+    {
+      "epoch": 2.8177458033573144,
+      "grad_norm": 2.0837855339050293,
+      "learning_rate": 2.652045030642153e-05,
+      "loss": 0.742,
+      "step": 14100
+    },
+    {
+      "epoch": 2.8377298161470823,
+      "grad_norm": 1.2353509664535522,
+      "learning_rate": 2.6353916866506796e-05,
+      "loss": 0.7615,
+      "step": 14200
+    },
+    {
+      "epoch": 2.8577138289368507,
+      "grad_norm": 0.8735284209251404,
+      "learning_rate": 2.618738342659206e-05,
+      "loss": 0.7872,
+      "step": 14300
+    },
+    {
+      "epoch": 2.8776978417266186,
+      "grad_norm": 1.0889009237289429,
+      "learning_rate": 2.6020849986677327e-05,
+      "loss": 0.7455,
+      "step": 14400
+    },
+    {
+      "epoch": 2.897681854516387,
+      "grad_norm": 1.506787657737732,
+      "learning_rate": 2.585431654676259e-05,
+      "loss": 0.792,
+      "step": 14500
+    },
+    {
+      "epoch": 2.9176658673061553,
+      "grad_norm": 0.7630636096000671,
+      "learning_rate": 2.5687783106847858e-05,
+      "loss": 0.7918,
+      "step": 14600
+    },
+    {
+      "epoch": 2.937649880095923,
+      "grad_norm": 1.6361045837402344,
+      "learning_rate": 2.5521249666933122e-05,
+      "loss": 0.7357,
+      "step": 14700
+    },
+    {
+      "epoch": 2.9576338928856916,
+      "grad_norm": 2.248220920562744,
+      "learning_rate": 2.535471622701839e-05,
+      "loss": 0.7954,
+      "step": 14800
+    },
+    {
+      "epoch": 2.9776179056754595,
+      "grad_norm": 1.14662766456604,
+      "learning_rate": 2.5188182787103653e-05,
+      "loss": 0.7865,
+      "step": 14900
+    },
+    {
+      "epoch": 2.997601918465228,
+      "grad_norm": 1.3895844221115112,
+      "learning_rate": 2.502164934718892e-05,
+      "loss": 0.7364,
+      "step": 15000
+    },
+    {
+      "epoch": 3.017585931254996,
+      "grad_norm": 2.1330533027648926,
+      "learning_rate": 2.485511590727418e-05,
+      "loss": 0.7244,
+      "step": 15100
+    },
+    {
+      "epoch": 3.037569944044764,
+      "grad_norm": 1.384775996208191,
+      "learning_rate": 2.4688582467359448e-05,
+      "loss": 0.7393,
+      "step": 15200
+    },
+    {
+      "epoch": 3.0575539568345325,
+      "grad_norm": 0.9841705560684204,
+      "learning_rate": 2.4522049027444712e-05,
+      "loss": 0.8051,
+      "step": 15300
+    },
+    {
+      "epoch": 3.0775379696243004,
+      "grad_norm": 1.224924921989441,
+      "learning_rate": 2.435551558752998e-05,
+      "loss": 0.8004,
+      "step": 15400
+    },
+    {
+      "epoch": 3.0975219824140687,
+      "grad_norm": 2.2387399673461914,
+      "learning_rate": 2.418898214761524e-05,
+      "loss": 0.8051,
+      "step": 15500
+    },
+    {
+      "epoch": 3.117505995203837,
+      "grad_norm": 1.8771803379058838,
+      "learning_rate": 2.4022448707700507e-05,
+      "loss": 0.7903,
+      "step": 15600
+    },
+    {
+      "epoch": 3.137490007993605,
+      "grad_norm": 1.786600112915039,
+      "learning_rate": 2.385591526778577e-05,
+      "loss": 0.7796,
+      "step": 15700
+    },
+    {
+      "epoch": 3.1574740207833734,
+      "grad_norm": 1.0823020935058594,
+      "learning_rate": 2.3689381827871038e-05,
+      "loss": 0.7468,
+      "step": 15800
+    },
+    {
+      "epoch": 3.1774580335731413,
+      "grad_norm": 1.9462608098983765,
+      "learning_rate": 2.35228483879563e-05,
+      "loss": 0.7854,
+      "step": 15900
+    },
+    {
+      "epoch": 3.1974420463629096,
+      "grad_norm": 1.3235732316970825,
+      "learning_rate": 2.335631494804157e-05,
+      "loss": 0.7584,
+      "step": 16000
+    },
+    {
+      "epoch": 3.217426059152678,
+      "grad_norm": 1.5206961631774902,
+      "learning_rate": 2.3189781508126833e-05,
+      "loss": 0.8104,
+      "step": 16100
+    },
+    {
+      "epoch": 3.237410071942446,
+      "grad_norm": 1.4281466007232666,
+      "learning_rate": 2.3023248068212097e-05,
+      "loss": 0.7505,
+      "step": 16200
+    },
+    {
+      "epoch": 3.2573940847322143,
+      "grad_norm": 1.9032511711120605,
+      "learning_rate": 2.2856714628297364e-05,
+      "loss": 0.7813,
+      "step": 16300
+    },
+    {
+      "epoch": 3.277378097521982,
+      "grad_norm": 2.10361909866333,
+      "learning_rate": 2.2690181188382628e-05,
+      "loss": 0.7369,
+      "step": 16400
+    },
+    {
+      "epoch": 3.2973621103117505,
+      "grad_norm": 1.440158486366272,
+      "learning_rate": 2.2523647748467895e-05,
+      "loss": 0.7576,
+      "step": 16500
+    },
+    {
+      "epoch": 3.317346123101519,
+      "grad_norm": 1.8777798414230347,
+      "learning_rate": 2.235711430855316e-05,
+      "loss": 0.7317,
+      "step": 16600
+    },
+    {
+      "epoch": 3.337330135891287,
+      "grad_norm": 1.6413357257843018,
+      "learning_rate": 2.2190580868638426e-05,
+      "loss": 0.7802,
+      "step": 16700
+    },
+    {
+      "epoch": 3.357314148681055,
+      "grad_norm": 1.820087194442749,
+      "learning_rate": 2.2024047428723686e-05,
+      "loss": 0.7435,
+      "step": 16800
+    },
+    {
+      "epoch": 3.3772981614708235,
+      "grad_norm": 2.5140113830566406,
+      "learning_rate": 2.1857513988808954e-05,
+      "loss": 0.7532,
+      "step": 16900
+    },
+    {
+      "epoch": 3.3972821742605914,
+      "grad_norm": 1.7011070251464844,
+      "learning_rate": 2.1690980548894217e-05,
+      "loss": 0.728,
+      "step": 17000
+    },
+    {
+      "epoch": 3.41726618705036,
+      "grad_norm": 1.3051706552505493,
+      "learning_rate": 2.1524447108979485e-05,
+      "loss": 0.7493,
+      "step": 17100
+    },
+    {
+      "epoch": 3.437250199840128,
+      "grad_norm": 0.9745834469795227,
+      "learning_rate": 2.135791366906475e-05,
+      "loss": 0.7219,
+      "step": 17200
+    },
+    {
+      "epoch": 3.457234212629896,
+      "grad_norm": 1.3213515281677246,
+      "learning_rate": 2.1191380229150016e-05,
+      "loss": 0.7703,
+      "step": 17300
+    },
+    {
+      "epoch": 3.4772182254196644,
+      "grad_norm": 0.735060453414917,
+      "learning_rate": 2.102484678923528e-05,
+      "loss": 0.7342,
+      "step": 17400
+    },
+    {
+      "epoch": 3.4972022382094323,
+      "grad_norm": 1.073197603225708,
+      "learning_rate": 2.0858313349320543e-05,
+      "loss": 0.7023,
+      "step": 17500
+    },
+    {
+      "epoch": 3.5171862509992007,
+      "grad_norm": 1.797711730003357,
+      "learning_rate": 2.069177990940581e-05,
+      "loss": 0.7944,
+      "step": 17600
+    },
+    {
+      "epoch": 3.537170263788969,
+      "grad_norm": 1.3365331888198853,
+      "learning_rate": 2.0525246469491074e-05,
+      "loss": 0.7773,
+      "step": 17700
+    },
+    {
+      "epoch": 3.557154276578737,
+      "grad_norm": 1.451333999633789,
+      "learning_rate": 2.035871302957634e-05,
+      "loss": 0.7659,
+      "step": 17800
+    },
+    {
+      "epoch": 3.5771382893685053,
+      "grad_norm": 1.5622735023498535,
+      "learning_rate": 2.0192179589661606e-05,
+      "loss": 0.7676,
+      "step": 17900
+    },
+    {
+      "epoch": 3.597122302158273,
+      "grad_norm": 1.5826952457427979,
+      "learning_rate": 2.0025646149746873e-05,
+      "loss": 0.7393,
+      "step": 18000
+    },
+    {
+      "epoch": 3.6171063149480416,
+      "grad_norm": 0.7937633991241455,
+      "learning_rate": 1.9859112709832133e-05,
+      "loss": 0.7112,
+      "step": 18100
+    },
+    {
+      "epoch": 3.63709032773781,
+      "grad_norm": 1.8199377059936523,
+      "learning_rate": 1.96925792699174e-05,
+      "loss": 0.7722,
+      "step": 18200
+    },
+    {
+      "epoch": 3.657074340527578,
+      "grad_norm": 2.317171573638916,
+      "learning_rate": 1.9526045830002664e-05,
+      "loss": 0.7735,
+      "step": 18300
+    },
+    {
+      "epoch": 3.677058353317346,
+      "grad_norm": 0.9344459772109985,
+      "learning_rate": 1.935951239008793e-05,
+      "loss": 0.7168,
+      "step": 18400
+    },
+    {
+      "epoch": 3.697042366107114,
+      "grad_norm": 1.833892583847046,
+      "learning_rate": 1.9192978950173195e-05,
+      "loss": 0.6825,
+      "step": 18500
+    },
+    {
+      "epoch": 3.7170263788968825,
+      "grad_norm": 1.4093741178512573,
+      "learning_rate": 1.9026445510258463e-05,
+      "loss": 0.7087,
+      "step": 18600
+    },
+    {
+      "epoch": 3.737010391686651,
+      "grad_norm": 2.0284645557403564,
+      "learning_rate": 1.8859912070343726e-05,
+      "loss": 0.7579,
+      "step": 18700
+    },
+    {
+      "epoch": 3.7569944044764187,
+      "grad_norm": 1.8383668661117554,
+      "learning_rate": 1.869337863042899e-05,
+      "loss": 0.7603,
+      "step": 18800
+    },
+    {
+      "epoch": 3.776978417266187,
+      "grad_norm": 1.5985366106033325,
+      "learning_rate": 1.8526845190514254e-05,
+      "loss": 0.7166,
+      "step": 18900
+    },
+    {
+      "epoch": 3.796962430055955,
+      "grad_norm": 1.5089521408081055,
+      "learning_rate": 1.836031175059952e-05,
+      "loss": 0.7678,
+      "step": 19000
+    },
+    {
+      "epoch": 3.8169464428457234,
+      "grad_norm": 1.2770063877105713,
+      "learning_rate": 1.8193778310684785e-05,
+      "loss": 0.7213,
+      "step": 19100
+    },
+    {
+      "epoch": 3.8369304556354917,
+      "grad_norm": 2.4528274536132812,
+      "learning_rate": 1.8027244870770052e-05,
+      "loss": 0.7255,
+      "step": 19200
+    },
+    {
+      "epoch": 3.8569144684252596,
+      "grad_norm": 1.736755132675171,
+      "learning_rate": 1.7860711430855316e-05,
+      "loss": 0.6784,
+      "step": 19300
+    },
+    {
+      "epoch": 3.876898481215028,
+      "grad_norm": 1.719307780265808,
+      "learning_rate": 1.7694177990940583e-05,
+      "loss": 0.7795,
+      "step": 19400
+    },
+    {
+      "epoch": 3.896882494004796,
+      "grad_norm": 2.070528984069824,
+      "learning_rate": 1.7527644551025847e-05,
+      "loss": 0.7509,
+      "step": 19500
+    },
+    {
+      "epoch": 3.9168665067945643,
+      "grad_norm": 1.6482255458831787,
+      "learning_rate": 1.736111111111111e-05,
+      "loss": 0.7202,
+      "step": 19600
+    },
+    {
+      "epoch": 3.9368505195843326,
+      "grad_norm": 1.1660830974578857,
+      "learning_rate": 1.719457767119638e-05,
+      "loss": 0.7042,
+      "step": 19700
+    },
+    {
+      "epoch": 3.956834532374101,
+      "grad_norm": 1.0131560564041138,
+      "learning_rate": 1.7028044231281642e-05,
+      "loss": 0.7059,
+      "step": 19800
+    },
+    {
+      "epoch": 3.976818545163869,
+      "grad_norm": 1.1839569807052612,
+      "learning_rate": 1.686151079136691e-05,
+      "loss": 0.77,
+      "step": 19900
+    },
+    {
+      "epoch": 3.996802557953637,
+      "grad_norm": 1.736053705215454,
+      "learning_rate": 1.6694977351452173e-05,
+      "loss": 0.7703,
+      "step": 20000
+    },
+    {
+      "epoch": 4.016786570743405,
+      "grad_norm": 1.3700270652770996,
+      "learning_rate": 1.6528443911537437e-05,
+      "loss": 0.6643,
+      "step": 20100
+    },
+    {
+      "epoch": 4.0367705835331735,
+      "grad_norm": 1.347440481185913,
+      "learning_rate": 1.63619104716227e-05,
+      "loss": 0.7502,
+      "step": 20200
+    },
+    {
+      "epoch": 4.056754596322942,
+      "grad_norm": 1.9421720504760742,
+      "learning_rate": 1.6195377031707968e-05,
+      "loss": 0.7382,
+      "step": 20300
+    },
+    {
+      "epoch": 4.07673860911271,
+      "grad_norm": 0.9211772084236145,
+      "learning_rate": 1.6028843591793232e-05,
+      "loss": 0.7249,
+      "step": 20400
+    },
+    {
+      "epoch": 4.096722621902478,
+      "grad_norm": 2.1698520183563232,
+      "learning_rate": 1.58623101518785e-05,
+      "loss": 0.7339,
+      "step": 20500
+    },
+    {
+      "epoch": 4.116706634692246,
+      "grad_norm": 1.6852116584777832,
+      "learning_rate": 1.5695776711963763e-05,
+      "loss": 0.7525,
+      "step": 20600
+    },
+    {
+      "epoch": 4.136690647482014,
+      "grad_norm": 1.8582841157913208,
+      "learning_rate": 1.552924327204903e-05,
+      "loss": 0.7168,
+      "step": 20700
+    },
+    {
+      "epoch": 4.156674660271783,
+      "grad_norm": 1.3949832916259766,
+      "learning_rate": 1.536270983213429e-05,
+      "loss": 0.6835,
+      "step": 20800
+    },
+    {
+      "epoch": 4.176658673061551,
+      "grad_norm": 2.044853925704956,
+      "learning_rate": 1.5196176392219558e-05,
+      "loss": 0.7332,
+      "step": 20900
+    },
+    {
+      "epoch": 4.196642685851319,
+      "grad_norm": 1.3187381029129028,
+      "learning_rate": 1.5029642952304823e-05,
+      "loss": 0.7724,
+      "step": 21000
+    },
+    {
+      "epoch": 4.216626698641087,
+      "grad_norm": 1.18405020236969,
+      "learning_rate": 1.4863109512390089e-05,
+      "loss": 0.7677,
+      "step": 21100
+    },
+    {
+      "epoch": 4.236610711430855,
+      "grad_norm": 1.2868226766586304,
+      "learning_rate": 1.4696576072475355e-05,
+      "loss": 0.7168,
+      "step": 21200
+    },
+    {
+      "epoch": 4.256594724220624,
+      "grad_norm": 2.145659923553467,
+      "learning_rate": 1.453004263256062e-05,
+      "loss": 0.7574,
+      "step": 21300
+    },
+    {
+      "epoch": 4.276578737010392,
+      "grad_norm": 1.0491008758544922,
+      "learning_rate": 1.4363509192645886e-05,
+      "loss": 0.7274,
+      "step": 21400
+    },
+    {
+      "epoch": 4.2965627498001595,
+      "grad_norm": 1.9524632692337036,
+      "learning_rate": 1.4196975752731148e-05,
+      "loss": 0.7256,
+      "step": 21500
+    },
+    {
+      "epoch": 4.316546762589928,
+      "grad_norm": 1.6348446607589722,
+      "learning_rate": 1.4030442312816413e-05,
+      "loss": 0.6971,
+      "step": 21600
+    },
+    {
+      "epoch": 4.336530775379696,
+      "grad_norm": 1.6102409362792969,
+      "learning_rate": 1.3863908872901679e-05,
+      "loss": 0.7031,
+      "step": 21700
+    },
+    {
+      "epoch": 4.356514788169465,
+      "grad_norm": 1.4496809244155884,
+      "learning_rate": 1.3697375432986944e-05,
+      "loss": 0.76,
+      "step": 21800
+    },
+    {
+      "epoch": 4.376498800959233,
+      "grad_norm": 2.370002508163452,
+      "learning_rate": 1.353084199307221e-05,
+      "loss": 0.7098,
+      "step": 21900
+    },
+    {
+      "epoch": 4.396482813749,
+      "grad_norm": 1.1416559219360352,
+      "learning_rate": 1.3364308553157475e-05,
+      "loss": 0.7565,
+      "step": 22000
+    },
+    {
+      "epoch": 4.416466826538769,
+      "grad_norm": 1.6672168970108032,
+      "learning_rate": 1.319777511324274e-05,
+      "loss": 0.7939,
+      "step": 22100
+    },
+    {
+      "epoch": 4.436450839328537,
+      "grad_norm": 1.1106956005096436,
+      "learning_rate": 1.3031241673328005e-05,
+      "loss": 0.6645,
+      "step": 22200
+    },
+    {
+      "epoch": 4.4564348521183055,
+      "grad_norm": 1.4987940788269043,
+      "learning_rate": 1.286470823341327e-05,
+      "loss": 0.7117,
+      "step": 22300
+    },
+    {
+      "epoch": 4.476418864908074,
+      "grad_norm": 2.063014268875122,
+      "learning_rate": 1.2698174793498536e-05,
+      "loss": 0.767,
+      "step": 22400
+    },
+    {
+      "epoch": 4.496402877697841,
+      "grad_norm": 0.748756468296051,
+      "learning_rate": 1.2531641353583801e-05,
+      "loss": 0.7393,
+      "step": 22500
+    },
+    {
+      "epoch": 4.51638689048761,
+      "grad_norm": 1.3971226215362549,
+      "learning_rate": 1.2365107913669065e-05,
+      "loss": 0.7782,
+      "step": 22600
+    },
+    {
+      "epoch": 4.536370903277378,
+      "grad_norm": 1.5306447744369507,
+      "learning_rate": 1.219857447375433e-05,
+      "loss": 0.7299,
+      "step": 22700
+    },
+    {
+      "epoch": 4.556354916067146,
+      "grad_norm": 1.409225344657898,
+      "learning_rate": 1.2032041033839596e-05,
+      "loss": 0.6752,
+      "step": 22800
+    },
+    {
+      "epoch": 4.576338928856915,
+      "grad_norm": 1.396794080734253,
+      "learning_rate": 1.186550759392486e-05,
+      "loss": 0.6417,
+      "step": 22900
+    },
+    {
+      "epoch": 4.596322941646683,
+      "grad_norm": 1.6455470323562622,
+      "learning_rate": 1.1698974154010126e-05,
+      "loss": 0.7545,
+      "step": 23000
+    },
+    {
+      "epoch": 4.616306954436451,
+      "grad_norm": 1.4188311100006104,
+      "learning_rate": 1.1532440714095391e-05,
+      "loss": 0.7217,
+      "step": 23100
+    },
+    {
+      "epoch": 4.636290967226219,
+      "grad_norm": 1.1025303602218628,
+      "learning_rate": 1.1365907274180657e-05,
+      "loss": 0.7419,
+      "step": 23200
+    },
+    {
+      "epoch": 4.656274980015987,
+      "grad_norm": 1.0919783115386963,
+      "learning_rate": 1.119937383426592e-05,
+      "loss": 0.725,
+      "step": 23300
+    },
+    {
+      "epoch": 4.676258992805756,
+      "grad_norm": 2.179637908935547,
+      "learning_rate": 1.1032840394351186e-05,
+      "loss": 0.7052,
+      "step": 23400
+    },
+    {
+      "epoch": 4.696243005595523,
+      "grad_norm": 1.4243191480636597,
+      "learning_rate": 1.0866306954436452e-05,
+      "loss": 0.7437,
+      "step": 23500
+    },
+    {
+      "epoch": 4.7162270183852915,
+      "grad_norm": 1.6711329221725464,
+      "learning_rate": 1.0699773514521715e-05,
+      "loss": 0.7378,
+      "step": 23600
+    },
+    {
+      "epoch": 4.73621103117506,
+      "grad_norm": 1.2967829704284668,
+      "learning_rate": 1.0533240074606981e-05,
+      "loss": 0.7386,
+      "step": 23700
+    },
+    {
+      "epoch": 4.756195043964828,
+      "grad_norm": 1.737625002861023,
+      "learning_rate": 1.0366706634692246e-05,
+      "loss": 0.7012,
+      "step": 23800
+    },
+    {
+      "epoch": 4.7761790567545965,
+      "grad_norm": 1.062472939491272,
+      "learning_rate": 1.020017319477751e-05,
+      "loss": 0.6797,
+      "step": 23900
+    },
+    {
+      "epoch": 4.796163069544365,
+      "grad_norm": 1.044542908668518,
+      "learning_rate": 1.0033639754862776e-05,
+      "loss": 0.7285,
+      "step": 24000
+    },
+    {
+      "epoch": 4.816147082334132,
+      "grad_norm": 1.70567786693573,
+      "learning_rate": 9.867106314948041e-06,
+      "loss": 0.7777,
+      "step": 24100
+    },
+    {
+      "epoch": 4.836131095123901,
+      "grad_norm": 1.6937395334243774,
+      "learning_rate": 9.700572875033307e-06,
+      "loss": 0.7378,
+      "step": 24200
+    },
+    {
+      "epoch": 4.856115107913669,
+      "grad_norm": 2.7036936283111572,
+      "learning_rate": 9.534039435118572e-06,
+      "loss": 0.7813,
+      "step": 24300
+    },
+    {
+      "epoch": 4.876099120703437,
+      "grad_norm": 1.1682194471359253,
+      "learning_rate": 9.367505995203838e-06,
+      "loss": 0.7155,
+      "step": 24400
+    },
+    {
+      "epoch": 4.896083133493206,
+      "grad_norm": 1.2117973566055298,
+      "learning_rate": 9.200972555289104e-06,
+      "loss": 0.7273,
+      "step": 24500
+    },
+    {
+      "epoch": 4.916067146282973,
+      "grad_norm": 0.9339836239814758,
+      "learning_rate": 9.034439115374367e-06,
+      "loss": 0.7368,
+      "step": 24600
+    },
+    {
+      "epoch": 4.936051159072742,
+      "grad_norm": 1.3919428586959839,
+      "learning_rate": 8.867905675459633e-06,
+      "loss": 0.7059,
+      "step": 24700
+    },
+    {
+      "epoch": 4.95603517186251,
+      "grad_norm": 2.1438040733337402,
+      "learning_rate": 8.701372235544898e-06,
+      "loss": 0.7197,
+      "step": 24800
+    },
+    {
+      "epoch": 4.976019184652278,
+      "grad_norm": 1.892350435256958,
+      "learning_rate": 8.534838795630162e-06,
+      "loss": 0.7292,
+      "step": 24900
+    },
+    {
+      "epoch": 4.996003197442047,
+      "grad_norm": 2.050062656402588,
+      "learning_rate": 8.368305355715428e-06,
+      "loss": 0.7791,
+      "step": 25000
+    },
+    {
+      "epoch": 5.015987210231814,
+      "grad_norm": 2.285053014755249,
+      "learning_rate": 8.201771915800693e-06,
+      "loss": 0.6937,
+      "step": 25100
+    },
+    {
+      "epoch": 5.0359712230215825,
+      "grad_norm": 1.6725279092788696,
+      "learning_rate": 8.035238475885959e-06,
+      "loss": 0.7443,
+      "step": 25200
+    },
+    {
+      "epoch": 5.055955235811351,
+      "grad_norm": 1.590450644493103,
+      "learning_rate": 7.868705035971223e-06,
+      "loss": 0.7069,
+      "step": 25300
+    },
+    {
+      "epoch": 5.075939248601119,
+      "grad_norm": 0.7603669762611389,
+      "learning_rate": 7.702171596056488e-06,
+      "loss": 0.6778,
+      "step": 25400
+    },
+    {
+      "epoch": 5.095923261390888,
+      "grad_norm": 1.8916963338851929,
+      "learning_rate": 7.535638156141754e-06,
+      "loss": 0.769,
+      "step": 25500
+    },
+    {
+      "epoch": 5.115907274180655,
+      "grad_norm": 1.6110832691192627,
+      "learning_rate": 7.3691047162270184e-06,
+      "loss": 0.7027,
+      "step": 25600
+    },
+    {
+      "epoch": 5.135891286970423,
+      "grad_norm": 1.796796202659607,
+      "learning_rate": 7.202571276312284e-06,
+      "loss": 0.72,
+      "step": 25700
+    },
+    {
+      "epoch": 5.155875299760192,
+      "grad_norm": 1.8212794065475464,
+      "learning_rate": 7.0360378363975495e-06,
+      "loss": 0.7004,
+      "step": 25800
+    },
+    {
+      "epoch": 5.17585931254996,
+      "grad_norm": 1.0340906381607056,
+      "learning_rate": 6.869504396482813e-06,
+      "loss": 0.6687,
+      "step": 25900
+    },
+    {
+      "epoch": 5.1958433253397285,
+      "grad_norm": 1.8287034034729004,
+      "learning_rate": 6.702970956568079e-06,
+      "loss": 0.6774,
+      "step": 26000
+    },
+    {
+      "epoch": 5.215827338129497,
+      "grad_norm": 1.657259225845337,
+      "learning_rate": 6.536437516653344e-06,
+      "loss": 0.6995,
+      "step": 26100
+    },
+    {
+      "epoch": 5.235811350919264,
+      "grad_norm": 1.8235076665878296,
+      "learning_rate": 6.36990407673861e-06,
+      "loss": 0.7814,
+      "step": 26200
+    },
+    {
+      "epoch": 5.255795363709033,
+      "grad_norm": 1.6127688884735107,
+      "learning_rate": 6.203370636823875e-06,
+      "loss": 0.6797,
+      "step": 26300
+    },
+    {
+      "epoch": 5.275779376498801,
+      "grad_norm": 1.2275160551071167,
+      "learning_rate": 6.03683719690914e-06,
+      "loss": 0.7336,
+      "step": 26400
+    },
+    {
+      "epoch": 5.295763389288569,
+      "grad_norm": 1.6593281030654907,
+      "learning_rate": 5.870303756994405e-06,
+      "loss": 0.6988,
+      "step": 26500
+    },
+    {
+      "epoch": 5.315747402078338,
+      "grad_norm": 1.1069490909576416,
+      "learning_rate": 5.70377031707967e-06,
+      "loss": 0.801,
+      "step": 26600
+    },
+    {
+      "epoch": 5.335731414868105,
+      "grad_norm": 1.7498623132705688,
+      "learning_rate": 5.537236877164935e-06,
+      "loss": 0.715,
+      "step": 26700
+    },
+    {
+      "epoch": 5.355715427657874,
+      "grad_norm": 1.7322038412094116,
+      "learning_rate": 5.3707034372502e-06,
+      "loss": 0.7076,
+      "step": 26800
+    },
+    {
+      "epoch": 5.375699440447642,
+      "grad_norm": 1.2660248279571533,
+      "learning_rate": 5.204169997335465e-06,
+      "loss": 0.7494,
+      "step": 26900
+    },
+    {
+      "epoch": 5.39568345323741,
+      "grad_norm": 2.537752628326416,
+      "learning_rate": 5.03763655742073e-06,
+      "loss": 0.7326,
+      "step": 27000
+    },
+    {
+      "epoch": 5.415667466027179,
+      "grad_norm": 0.991534411907196,
+      "learning_rate": 4.8711031175059955e-06,
+      "loss": 0.6929,
+      "step": 27100
+    },
+    {
+      "epoch": 5.435651478816946,
+      "grad_norm": 2.0230729579925537,
+      "learning_rate": 4.70456967759126e-06,
+      "loss": 0.6787,
+      "step": 27200
+    },
+    {
+      "epoch": 5.4556354916067145,
+      "grad_norm": 1.5560120344161987,
+      "learning_rate": 4.538036237676526e-06,
+      "loss": 0.7251,
+      "step": 27300
+    },
+    {
+      "epoch": 5.475619504396483,
+      "grad_norm": 1.5086272954940796,
+      "learning_rate": 4.371502797761791e-06,
+      "loss": 0.7066,
+      "step": 27400
+    },
+    {
+      "epoch": 5.495603517186251,
+      "grad_norm": 1.6183174848556519,
+      "learning_rate": 4.204969357847056e-06,
+      "loss": 0.7161,
+      "step": 27500
+    },
+    {
+      "epoch": 5.5155875299760195,
+      "grad_norm": 1.1214239597320557,
+      "learning_rate": 4.0384359179323214e-06,
+      "loss": 0.7414,
+      "step": 27600
+    },
+    {
+      "epoch": 5.535571542765787,
+      "grad_norm": 1.4948476552963257,
+      "learning_rate": 3.871902478017586e-06,
+      "loss": 0.7303,
+      "step": 27700
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 1.094460368156433,
+      "learning_rate": 3.705369038102851e-06,
+      "loss": 0.7214,
+      "step": 27800
+    },
+    {
+      "epoch": 5.575539568345324,
+      "grad_norm": 1.8006253242492676,
+      "learning_rate": 3.5388355981881163e-06,
+      "loss": 0.7382,
+      "step": 27900
+    },
+    {
+      "epoch": 5.595523581135092,
+      "grad_norm": 1.0595532655715942,
+      "learning_rate": 3.3723021582733815e-06,
+      "loss": 0.6835,
+      "step": 28000
+    },
+    {
+      "epoch": 5.61550759392486,
+      "grad_norm": 1.5675129890441895,
+      "learning_rate": 3.205768718358647e-06,
+      "loss": 0.7426,
+      "step": 28100
+    },
+    {
+      "epoch": 5.635491606714629,
+      "grad_norm": 1.543182134628296,
+      "learning_rate": 3.0392352784439117e-06,
+      "loss": 0.7393,
+      "step": 28200
+    },
+    {
+      "epoch": 5.655475619504396,
+      "grad_norm": 1.6735225915908813,
+      "learning_rate": 2.8727018385291768e-06,
+      "loss": 0.7106,
+      "step": 28300
+    },
+    {
+      "epoch": 5.675459632294165,
+      "grad_norm": 1.2037389278411865,
+      "learning_rate": 2.706168398614442e-06,
+      "loss": 0.6928,
+      "step": 28400
+    },
+    {
+      "epoch": 5.695443645083933,
+      "grad_norm": 1.957836627960205,
+      "learning_rate": 2.539634958699707e-06,
+      "loss": 0.8086,
+      "step": 28500
+    },
+    {
+      "epoch": 5.715427657873701,
+      "grad_norm": 2.085599899291992,
+      "learning_rate": 2.373101518784972e-06,
+      "loss": 0.7587,
+      "step": 28600
+    },
+    {
+      "epoch": 5.735411670663469,
+      "grad_norm": 1.3564984798431396,
+      "learning_rate": 2.206568078870237e-06,
+      "loss": 0.7197,
+      "step": 28700
+    },
+    {
+      "epoch": 5.755395683453237,
+      "grad_norm": 1.659226655960083,
+      "learning_rate": 2.0400346389555023e-06,
+      "loss": 0.728,
+      "step": 28800
+    },
+    {
+      "epoch": 5.7753796962430055,
+      "grad_norm": 1.3784935474395752,
+      "learning_rate": 1.8735011990407676e-06,
+      "loss": 0.7561,
+      "step": 28900
+    },
+    {
+      "epoch": 5.795363709032774,
+      "grad_norm": 1.4514496326446533,
+      "learning_rate": 1.7069677591260325e-06,
+      "loss": 0.7205,
+      "step": 29000
+    },
+    {
+      "epoch": 5.815347721822542,
+      "grad_norm": 1.7896771430969238,
+      "learning_rate": 1.5404343192112976e-06,
+      "loss": 0.667,
+      "step": 29100
+    },
+    {
+      "epoch": 5.835331734612311,
+      "grad_norm": 1.4074804782867432,
+      "learning_rate": 1.3739008792965628e-06,
+      "loss": 0.71,
+      "step": 29200
+    },
+    {
+      "epoch": 5.855315747402078,
+      "grad_norm": 1.33772873878479,
+      "learning_rate": 1.2073674393818279e-06,
+      "loss": 0.7688,
+      "step": 29300
+    },
+    {
+      "epoch": 5.875299760191846,
+      "grad_norm": 1.8295559883117676,
+      "learning_rate": 1.040833999467093e-06,
+      "loss": 0.7439,
+      "step": 29400
+    },
+    {
+      "epoch": 5.895283772981615,
+      "grad_norm": 0.9400151371955872,
+      "learning_rate": 8.743005595523582e-07,
+      "loss": 0.6891,
+      "step": 29500
+    },
+    {
+      "epoch": 5.915267785771383,
+      "grad_norm": 1.7990922927856445,
+      "learning_rate": 7.077671196376233e-07,
+      "loss": 0.6384,
+      "step": 29600
+    },
+    {
+      "epoch": 5.935251798561151,
+      "grad_norm": 1.74308180809021,
+      "learning_rate": 5.412336797228884e-07,
+      "loss": 0.6973,
+      "step": 29700
+    },
+    {
+      "epoch": 5.955235811350919,
+      "grad_norm": 1.1248557567596436,
+      "learning_rate": 3.747002398081535e-07,
+      "loss": 0.7265,
+      "step": 29800
+    },
+    {
+      "epoch": 5.975219824140687,
+      "grad_norm": 1.9805783033370972,
+      "learning_rate": 2.0816679989341861e-07,
+      "loss": 0.7107,
+      "step": 29900
+    },
+    {
+      "epoch": 5.995203836930456,
+      "grad_norm": 1.6576383113861084,
+      "learning_rate": 4.163335997868372e-08,
+      "loss": 0.7073,
+      "step": 30000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 30024,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2324706052931584e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-30024/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef669be81d20daf424937932b11920f44997980d862a4dbeacd08759cb53271
+size 5713

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "model_type": "t5",
+  "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,
+  
+  "n_positions": 512,
+  "num_decoder_layers": 8,
+  "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: "
+    }
+    
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.1",
+  "use_cache": true,
+  "vocab_size": 32128
+  
+
+}

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": "4.54.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d7d9cb3c9cd110d27b0464310c8b788a909e82f8d23c4e56ae2fdbee5cc903
+size 307867048

special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "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": {
+    "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_config.json

@@ -0,0 +1,940 @@
+{
+  "add_prefix_space": null,
+  "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
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}