Upload folder using huggingface_hub

checkpoint-500/added_tokens.json

@@ -0,0 +1,102 @@
+{
+  "<extra_id_0>": 32099,
+  "<extra_id_10>": 32089,
+  "<extra_id_11>": 32088,
+  "<extra_id_12>": 32087,
+  "<extra_id_13>": 32086,
+  "<extra_id_14>": 32085,
+  "<extra_id_15>": 32084,
+  "<extra_id_16>": 32083,
+  "<extra_id_17>": 32082,
+  "<extra_id_18>": 32081,
+  "<extra_id_19>": 32080,
+  "<extra_id_1>": 32098,
+  "<extra_id_20>": 32079,
+  "<extra_id_21>": 32078,
+  "<extra_id_22>": 32077,
+  "<extra_id_23>": 32076,
+  "<extra_id_24>": 32075,
+  "<extra_id_25>": 32074,
+  "<extra_id_26>": 32073,
+  "<extra_id_27>": 32072,
+  "<extra_id_28>": 32071,
+  "<extra_id_29>": 32070,
+  "<extra_id_2>": 32097,
+  "<extra_id_30>": 32069,
+  "<extra_id_31>": 32068,
+  "<extra_id_32>": 32067,
+  "<extra_id_33>": 32066,
+  "<extra_id_34>": 32065,
+  "<extra_id_35>": 32064,
+  "<extra_id_36>": 32063,
+  "<extra_id_37>": 32062,
+  "<extra_id_38>": 32061,
+  "<extra_id_39>": 32060,
+  "<extra_id_3>": 32096,
+  "<extra_id_40>": 32059,
+  "<extra_id_41>": 32058,
+  "<extra_id_42>": 32057,
+  "<extra_id_43>": 32056,
+  "<extra_id_44>": 32055,
+  "<extra_id_45>": 32054,
+  "<extra_id_46>": 32053,
+  "<extra_id_47>": 32052,
+  "<extra_id_48>": 32051,
+  "<extra_id_49>": 32050,
+  "<extra_id_4>": 32095,
+  "<extra_id_50>": 32049,
+  "<extra_id_51>": 32048,
+  "<extra_id_52>": 32047,
+  "<extra_id_53>": 32046,
+  "<extra_id_54>": 32045,
+  "<extra_id_55>": 32044,
+  "<extra_id_56>": 32043,
+  "<extra_id_57>": 32042,
+  "<extra_id_58>": 32041,
+  "<extra_id_59>": 32040,
+  "<extra_id_5>": 32094,
+  "<extra_id_60>": 32039,
+  "<extra_id_61>": 32038,
+  "<extra_id_62>": 32037,
+  "<extra_id_63>": 32036,
+  "<extra_id_64>": 32035,
+  "<extra_id_65>": 32034,
+  "<extra_id_66>": 32033,
+  "<extra_id_67>": 32032,
+  "<extra_id_68>": 32031,
+  "<extra_id_69>": 32030,
+  "<extra_id_6>": 32093,
+  "<extra_id_70>": 32029,
+  "<extra_id_71>": 32028,
+  "<extra_id_72>": 32027,
+  "<extra_id_73>": 32026,
+  "<extra_id_74>": 32025,
+  "<extra_id_75>": 32024,
+  "<extra_id_76>": 32023,
+  "<extra_id_77>": 32022,
+  "<extra_id_78>": 32021,
+  "<extra_id_79>": 32020,
+  "<extra_id_7>": 32092,
+  "<extra_id_80>": 32019,
+  "<extra_id_81>": 32018,
+  "<extra_id_82>": 32017,
+  "<extra_id_83>": 32016,
+  "<extra_id_84>": 32015,
+  "<extra_id_85>": 32014,
+  "<extra_id_86>": 32013,
+  "<extra_id_87>": 32012,
+  "<extra_id_88>": 32011,
+  "<extra_id_89>": 32010,
+  "<extra_id_8>": 32091,
+  "<extra_id_90>": 32009,
+  "<extra_id_91>": 32008,
+  "<extra_id_92>": 32007,
+  "<extra_id_93>": 32006,
+  "<extra_id_94>": 32005,
+  "<extra_id_95>": 32004,
+  "<extra_id_96>": 32003,
+  "<extra_id_97>": 32002,
+  "<extra_id_98>": 32001,
+  "<extra_id_99>": 32000,
+  "<extra_id_9>": 32090
+}

checkpoint-500/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/workspace/HFTrainer/tasky_output_with_adam/20240720_1736/checkpoint-100",
+  "architectures": [
+    "UMT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 5120,
+  "d_kv": 64,
+  "d_model": 2048,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 2,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "umt5",
+  "num_decoder_layers": 24,
+  "num_heads": 32,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "scalable_attention": true,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 32128
+}

checkpoint-500/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "max_new_tokens": 256,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

checkpoint-500/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d2f04e216967326acbacbeee7cf8404659b7bc77441f19d5ad27be81348ce7
+size 4985006064

checkpoint-500/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b855b1174954ec7e69b1510b61e2469bb3e384f1b9f88fc7c40ff705a0b63a55
+size 714678248

checkpoint-500/model.safetensors.index.json

@@ -0,0 +1,611 @@
+{
+  "metadata": {
+    "total_size": 5699608576
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.14.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.15.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.16.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.17.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.18.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "shared.weight": "model-00001-of-00002.safetensors"
+  }
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49bd55dfd4b206c7019bffe348144e4a8eb745e26a717557b3107ec774294c26
+size 10612076

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89e11ed756c402e47d8745cbaa6e8e54454b26c7f296b49f5800780cf0cfb09
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f60996ac774c0b8a066dc9ee037903625867bde903c528b497c450c1d182d443
+size 1064

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,126 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_99>",
+    "<extra_id_98>",
+    "<extra_id_97>",
+    "<extra_id_96>",
+    "<extra_id_95>",
+    "<extra_id_94>",
+    "<extra_id_93>",
+    "<extra_id_92>",
+    "<extra_id_91>",
+    "<extra_id_90>",
+    "<extra_id_89>",
+    "<extra_id_88>",
+    "<extra_id_87>",
+    "<extra_id_86>",
+    "<extra_id_85>",
+    "<extra_id_84>",
+    "<extra_id_83>",
+    "<extra_id_82>",
+    "<extra_id_81>",
+    "<extra_id_80>",
+    "<extra_id_79>",
+    "<extra_id_78>",
+    "<extra_id_77>",
+    "<extra_id_76>",
+    "<extra_id_75>",
+    "<extra_id_74>",
+    "<extra_id_73>",
+    "<extra_id_72>",
+    "<extra_id_71>",
+    "<extra_id_70>",
+    "<extra_id_69>",
+    "<extra_id_68>",
+    "<extra_id_67>",
+    "<extra_id_66>",
+    "<extra_id_65>",
+    "<extra_id_64>",
+    "<extra_id_63>",
+    "<extra_id_62>",
+    "<extra_id_61>",
+    "<extra_id_60>",
+    "<extra_id_59>",
+    "<extra_id_58>",
+    "<extra_id_57>",
+    "<extra_id_56>",
+    "<extra_id_55>",
+    "<extra_id_54>",
+    "<extra_id_53>",
+    "<extra_id_52>",
+    "<extra_id_51>",
+    "<extra_id_50>",
+    "<extra_id_49>",
+    "<extra_id_48>",
+    "<extra_id_47>",
+    "<extra_id_46>",
+    "<extra_id_45>",
+    "<extra_id_44>",
+    "<extra_id_43>",
+    "<extra_id_42>",
+    "<extra_id_41>",
+    "<extra_id_40>",
+    "<extra_id_39>",
+    "<extra_id_38>",
+    "<extra_id_37>",
+    "<extra_id_36>",
+    "<extra_id_35>",
+    "<extra_id_34>",
+    "<extra_id_33>",
+    "<extra_id_32>",
+    "<extra_id_31>",
+    "<extra_id_30>",
+    "<extra_id_29>",
+    "<extra_id_28>",
+    "<extra_id_27>",
+    "<extra_id_26>",
+    "<extra_id_25>",
+    "<extra_id_24>",
+    "<extra_id_23>",
+    "<extra_id_22>",
+    "<extra_id_21>",
+    "<extra_id_20>",
+    "<extra_id_19>",
+    "<extra_id_18>",
+    "<extra_id_17>",
+    "<extra_id_16>",
+    "<extra_id_15>",
+    "<extra_id_14>",
+    "<extra_id_13>",
+    "<extra_id_12>",
+    "<extra_id_11>",
+    "<extra_id_10>",
+    "<extra_id_9>",
+    "<extra_id_8>",
+    "<extra_id_7>",
+    "<extra_id_6>",
+    "<extra_id_5>",
+    "<extra_id_4>",
+    "<extra_id_3>",
+    "<extra_id_2>",
+    "<extra_id_1>",
+    "<extra_id_0>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,945 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": true,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "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": "</s>",
+      "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_99>",
+    "<extra_id_98>",
+    "<extra_id_97>",
+    "<extra_id_96>",
+    "<extra_id_95>",
+    "<extra_id_94>",
+    "<extra_id_93>",
+    "<extra_id_92>",
+    "<extra_id_91>",
+    "<extra_id_90>",
+    "<extra_id_89>",
+    "<extra_id_88>",
+    "<extra_id_87>",
+    "<extra_id_86>",
+    "<extra_id_85>",
+    "<extra_id_84>",
+    "<extra_id_83>",
+    "<extra_id_82>",
+    "<extra_id_81>",
+    "<extra_id_80>",
+    "<extra_id_79>",
+    "<extra_id_78>",
+    "<extra_id_77>",
+    "<extra_id_76>",
+    "<extra_id_75>",
+    "<extra_id_74>",
+    "<extra_id_73>",
+    "<extra_id_72>",
+    "<extra_id_71>",
+    "<extra_id_70>",
+    "<extra_id_69>",
+    "<extra_id_68>",
+    "<extra_id_67>",
+    "<extra_id_66>",
+    "<extra_id_65>",
+    "<extra_id_64>",
+    "<extra_id_63>",
+    "<extra_id_62>",
+    "<extra_id_61>",
+    "<extra_id_60>",
+    "<extra_id_59>",
+    "<extra_id_58>",
+    "<extra_id_57>",
+    "<extra_id_56>",
+    "<extra_id_55>",
+    "<extra_id_54>",
+    "<extra_id_53>",
+    "<extra_id_52>",
+    "<extra_id_51>",
+    "<extra_id_50>",
+    "<extra_id_49>",
+    "<extra_id_48>",
+    "<extra_id_47>",
+    "<extra_id_46>",
+    "<extra_id_45>",
+    "<extra_id_44>",
+    "<extra_id_43>",
+    "<extra_id_42>",
+    "<extra_id_41>",
+    "<extra_id_40>",
+    "<extra_id_39>",
+    "<extra_id_38>",
+    "<extra_id_37>",
+    "<extra_id_36>",
+    "<extra_id_35>",
+    "<extra_id_34>",
+    "<extra_id_33>",
+    "<extra_id_32>",
+    "<extra_id_31>",
+    "<extra_id_30>",
+    "<extra_id_29>",
+    "<extra_id_28>",
+    "<extra_id_27>",
+    "<extra_id_26>",
+    "<extra_id_25>",
+    "<extra_id_24>",
+    "<extra_id_23>",
+    "<extra_id_22>",
+    "<extra_id_21>",
+    "<extra_id_20>",
+    "<extra_id_19>",
+    "<extra_id_18>",
+    "<extra_id_17>",
+    "<extra_id_16>",
+    "<extra_id_15>",
+    "<extra_id_14>",
+    "<extra_id_13>",
+    "<extra_id_12>",
+    "<extra_id_11>",
+    "<extra_id_10>",
+    "<extra_id_9>",
+    "<extra_id_8>",
+    "<extra_id_7>",
+    "<extra_id_6>",
+    "<extra_id_5>",
+    "<extra_id_4>",
+    "<extra_id_3>",
+    "<extra_id_2>",
+    "<extra_id_1>",
+    "<extra_id_0>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 512,
+  "pad_token": "<s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,423 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5488867376573088,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.030977734753146177,
+      "grad_norm": 70.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 7.5845,
+      "step": 10
+    },
+    {
+      "epoch": 0.061955469506292354,
+      "grad_norm": 52.5,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 7.5258,
+      "step": 20
+    },
+    {
+      "epoch": 0.09293320425943853,
+      "grad_norm": 44.0,
+      "learning_rate": 3e-06,
+      "loss": 7.5572,
+      "step": 30
+    },
+    {
+      "epoch": 0.12391093901258471,
+      "grad_norm": 46.25,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 7.5497,
+      "step": 40
+    },
+    {
+      "epoch": 0.15488867376573087,
+      "grad_norm": 28.625,
+      "learning_rate": 5e-06,
+      "loss": 7.4982,
+      "step": 50
+    },
+    {
+      "epoch": 0.18586640851887706,
+      "grad_norm": 38.5,
+      "learning_rate": 6e-06,
+      "loss": 7.4251,
+      "step": 60
+    },
+    {
+      "epoch": 0.21684414327202323,
+      "grad_norm": 1968.0,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 7.3471,
+      "step": 70
+    },
+    {
+      "epoch": 0.24782187802516942,
+      "grad_norm": 323584.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 7.2784,
+      "step": 80
+    },
+    {
+      "epoch": 0.2787996127783156,
+      "grad_norm": 38.25,
+      "learning_rate": 9e-06,
+      "loss": 7.1812,
+      "step": 90
+    },
+    {
+      "epoch": 0.30977734753146174,
+      "grad_norm": 46.25,
+      "learning_rate": 1e-05,
+      "loss": 7.083,
+      "step": 100
+    },
+    {
+      "epoch": 0.30977734753146174,
+      "eval_loss": 6.660160064697266,
+      "eval_runtime": 145.1043,
+      "eval_samples_per_second": 10.337,
+      "eval_steps_per_second": 2.584,
+      "step": 100
+    },
+    {
+      "epoch": 0.34075508228460794,
+      "grad_norm": 75.0,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 6.8485,
+      "step": 110
+    },
+    {
+      "epoch": 0.3717328170377541,
+      "grad_norm": 48.75,
+      "learning_rate": 1.2e-05,
+      "loss": 6.4221,
+      "step": 120
+    },
+    {
+      "epoch": 0.4027105517909003,
+      "grad_norm": 88.0,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 5.869,
+      "step": 130
+    },
+    {
+      "epoch": 0.43368828654404645,
+      "grad_norm": 108.5,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 5.026,
+      "step": 140
+    },
+    {
+      "epoch": 0.46466602129719264,
+      "grad_norm": 253.0,
+      "learning_rate": 1.5e-05,
+      "loss": 3.9355,
+      "step": 150
+    },
+    {
+      "epoch": 0.49564375605033884,
+      "grad_norm": 2528.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 3.0847,
+      "step": 160
+    },
+    {
+      "epoch": 0.526621490803485,
+      "grad_norm": 165.0,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 2.6829,
+      "step": 170
+    },
+    {
+      "epoch": 0.5575992255566312,
+      "grad_norm": 4768.0,
+      "learning_rate": 1.8e-05,
+      "loss": 2.4876,
+      "step": 180
+    },
+    {
+      "epoch": 0.5885769603097774,
+      "grad_norm": 177.0,
+      "learning_rate": 1.9e-05,
+      "loss": 2.2394,
+      "step": 190
+    },
+    {
+      "epoch": 0.6195546950629235,
+      "grad_norm": 1384.0,
+      "learning_rate": 2e-05,
+      "loss": 2.0657,
+      "step": 200
+    },
+    {
+      "epoch": 0.6195546950629235,
+      "eval_loss": 0.878921389579773,
+      "eval_runtime": 144.9013,
+      "eval_samples_per_second": 10.352,
+      "eval_steps_per_second": 2.588,
+      "step": 200
+    },
+    {
+      "epoch": 0.6505324298160697,
+      "grad_norm": 81.5,
+      "learning_rate": 2.1e-05,
+      "loss": 2.0229,
+      "step": 210
+    },
+    {
+      "epoch": 0.6815101645692159,
+      "grad_norm": 90.5,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.9117,
+      "step": 220
+    },
+    {
+      "epoch": 0.712487899322362,
+      "grad_norm": 255.0,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 1.9205,
+      "step": 230
+    },
+    {
+      "epoch": 0.7434656340755083,
+      "grad_norm": 226.0,
+      "learning_rate": 2.4e-05,
+      "loss": 1.8112,
+      "step": 240
+    },
+    {
+      "epoch": 0.7744433688286544,
+      "grad_norm": 109.5,
+      "learning_rate": 2.5e-05,
+      "loss": 1.7503,
+      "step": 250
+    },
+    {
+      "epoch": 0.8054211035818006,
+      "grad_norm": 67.0,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.687,
+      "step": 260
+    },
+    {
+      "epoch": 0.8363988383349468,
+      "grad_norm": 103.0,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.7016,
+      "step": 270
+    },
+    {
+      "epoch": 0.8673765730880929,
+      "grad_norm": 233.0,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.7346,
+      "step": 280
+    },
+    {
+      "epoch": 0.8983543078412392,
+      "grad_norm": 92.5,
+      "learning_rate": 2.9e-05,
+      "loss": 1.656,
+      "step": 290
+    },
+    {
+      "epoch": 0.9293320425943853,
+      "grad_norm": 47.25,
+      "learning_rate": 3e-05,
+      "loss": 1.5532,
+      "step": 300
+    },
+    {
+      "epoch": 0.9293320425943853,
+      "eval_loss": 0.8598520755767822,
+      "eval_runtime": 144.9013,
+      "eval_samples_per_second": 10.352,
+      "eval_steps_per_second": 2.588,
+      "step": 300
+    },
+    {
+      "epoch": 0.9603097773475314,
+      "grad_norm": 188.0,
+      "learning_rate": 3.1e-05,
+      "loss": 1.5658,
+      "step": 310
+    },
+    {
+      "epoch": 0.9912875121006777,
+      "grad_norm": 61.75,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.4423,
+      "step": 320
+    },
+    {
+      "epoch": 1.0222652468538238,
+      "grad_norm": 48.5,
+      "learning_rate": 3.3e-05,
+      "loss": 1.5072,
+      "step": 330
+    },
+    {
+      "epoch": 1.05324298160697,
+      "grad_norm": 72.5,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.4358,
+      "step": 340
+    },
+    {
+      "epoch": 1.084220716360116,
+      "grad_norm": 498.0,
+      "learning_rate": 3.5e-05,
+      "loss": 1.3132,
+      "step": 350
+    },
+    {
+      "epoch": 1.1151984511132624,
+      "grad_norm": 54.0,
+      "learning_rate": 3.6e-05,
+      "loss": 1.4264,
+      "step": 360
+    },
+    {
+      "epoch": 1.1461761858664086,
+      "grad_norm": 61.75,
+      "learning_rate": 3.7e-05,
+      "loss": 1.3196,
+      "step": 370
+    },
+    {
+      "epoch": 1.1771539206195547,
+      "grad_norm": 66.5,
+      "learning_rate": 3.8e-05,
+      "loss": 1.2922,
+      "step": 380
+    },
+    {
+      "epoch": 1.2081316553727008,
+      "grad_norm": 41.25,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 1.4018,
+      "step": 390
+    },
+    {
+      "epoch": 1.239109390125847,
+      "grad_norm": 52.5,
+      "learning_rate": 4e-05,
+      "loss": 1.1323,
+      "step": 400
+    },
+    {
+      "epoch": 1.239109390125847,
+      "eval_loss": 0.31075239181518555,
+      "eval_runtime": 144.8169,
+      "eval_samples_per_second": 10.358,
+      "eval_steps_per_second": 2.589,
+      "step": 400
+    },
+    {
+      "epoch": 1.2700871248789931,
+      "grad_norm": 53.0,
+      "learning_rate": 4.1e-05,
+      "loss": 1.1657,
+      "step": 410
+    },
+    {
+      "epoch": 1.3010648596321395,
+      "grad_norm": 888.0,
+      "learning_rate": 4.2e-05,
+      "loss": 1.1344,
+      "step": 420
+    },
+    {
+      "epoch": 1.3320425943852856,
+      "grad_norm": 416.0,
+      "learning_rate": 4.3e-05,
+      "loss": 1.1697,
+      "step": 430
+    },
+    {
+      "epoch": 1.3630203291384317,
+      "grad_norm": 960.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.0632,
+      "step": 440
+    },
+    {
+      "epoch": 1.3939980638915779,
+      "grad_norm": 42.5,
+      "learning_rate": 4.5e-05,
+      "loss": 0.9458,
+      "step": 450
+    },
+    {
+      "epoch": 1.424975798644724,
+      "grad_norm": 35.5,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.9597,
+      "step": 460
+    },
+    {
+      "epoch": 1.4559535333978704,
+      "grad_norm": 90.0,
+      "learning_rate": 4.7e-05,
+      "loss": 0.8533,
+      "step": 470
+    },
+    {
+      "epoch": 1.4869312681510165,
+      "grad_norm": 34.5,
+      "learning_rate": 4.8e-05,
+      "loss": 0.8736,
+      "step": 480
+    },
+    {
+      "epoch": 1.5179090029041626,
+      "grad_norm": 16.0,
+      "learning_rate": 4.9e-05,
+      "loss": 0.9187,
+      "step": 490
+    },
+    {
+      "epoch": 1.5488867376573088,
+      "grad_norm": 55.75,
+      "learning_rate": 5e-05,
+      "loss": 0.8223,
+      "step": 500
+    },
+    {
+      "epoch": 1.5488867376573088,
+      "eval_loss": 0.17174342274665833,
+      "eval_runtime": 144.8992,
+      "eval_samples_per_second": 10.352,
+      "eval_steps_per_second": 2.588,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 9660,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "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": 5.4733111165137715e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332c04b434678063c34e7380c07f9b363144edaff3dd893f217873183bc287b8
+size 5240