Upload folder using huggingface_hub

checkpoint-2400/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-2400/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "EleutherAI/pile-t5-xl",
+  "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-2400/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-2400/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed49c6d9816b7fe095ecb64cea26200484ed3b5e9603c5953e4081192d07363
+size 4985006064

checkpoint-2400/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b3a9d84d111a673c07239b824d0ac8e16c26cd9e2f6d6282c2503a384beda7
+size 714678248

checkpoint-2400/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-2400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7cf14f37aae086bf1739df7891d1edc1e7882bf870ad0088204581bb999e4a6
+size 10612076

checkpoint-2400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb387891ce75408b6fb276d2cb507468ea2e9cfdf595bd1d79e304d21cb70aaf
+size 14244

checkpoint-2400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b733721ae5a6cbf16672743ca66d7f2059c6e35795719de2fc2bbccaa721ab
+size 1064

checkpoint-2400/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-2400/tokenizer.model

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

checkpoint-2400/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-2400/trainer_state.json

@@ -0,0 +1,1745 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.717328170377541,
+  "eval_steps": 600,
+  "global_step": 2400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015488867376573089,
+      "grad_norm": 421527552.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 61.1175,
+      "step": 10
+    },
+    {
+      "epoch": 0.030977734753146177,
+      "grad_norm": 337641472.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 60.1666,
+      "step": 20
+    },
+    {
+      "epoch": 0.046466602129719266,
+      "grad_norm": 413138944.0,
+      "learning_rate": 3e-06,
+      "loss": 60.9036,
+      "step": 30
+    },
+    {
+      "epoch": 0.061955469506292354,
+      "grad_norm": 1367343104.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 61.7597,
+      "step": 40
+    },
+    {
+      "epoch": 0.07744433688286544,
+      "grad_norm": 57933824.0,
+      "learning_rate": 5e-06,
+      "loss": 61.2844,
+      "step": 50
+    },
+    {
+      "epoch": 0.09293320425943853,
+      "grad_norm": 94371840.0,
+      "learning_rate": 6e-06,
+      "loss": 60.3878,
+      "step": 60
+    },
+    {
+      "epoch": 0.10842207163601161,
+      "grad_norm": 40632320.0,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 59.0391,
+      "step": 70
+    },
+    {
+      "epoch": 0.12391093901258471,
+      "grad_norm": 20971520.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 61.2704,
+      "step": 80
+    },
+    {
+      "epoch": 0.1393998063891578,
+      "grad_norm": 110624768.0,
+      "learning_rate": 9e-06,
+      "loss": 59.6674,
+      "step": 90
+    },
+    {
+      "epoch": 0.15488867376573087,
+      "grad_norm": 66584576.0,
+      "learning_rate": 1e-05,
+      "loss": 59.4588,
+      "step": 100
+    },
+    {
+      "epoch": 0.17037754114230397,
+      "grad_norm": 89653248.0,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 58.9144,
+      "step": 110
+    },
+    {
+      "epoch": 0.18586640851887706,
+      "grad_norm": 56360960.0,
+      "learning_rate": 1.2e-05,
+      "loss": 58.3093,
+      "step": 120
+    },
+    {
+      "epoch": 0.20135527589545016,
+      "grad_norm": 19791872.0,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 58.0143,
+      "step": 130
+    },
+    {
+      "epoch": 0.21684414327202323,
+      "grad_norm": 5242880.0,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 56.9984,
+      "step": 140
+    },
+    {
+      "epoch": 0.23233301064859632,
+      "grad_norm": 55050240.0,
+      "learning_rate": 1.5e-05,
+      "loss": 57.6238,
+      "step": 150
+    },
+    {
+      "epoch": 0.24782187802516942,
+      "grad_norm": 118489088.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 55.2309,
+      "step": 160
+    },
+    {
+      "epoch": 0.2633107454017425,
+      "grad_norm": 61865984.0,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 54.6207,
+      "step": 170
+    },
+    {
+      "epoch": 0.2787996127783156,
+      "grad_norm": 13041664.0,
+      "learning_rate": 1.8e-05,
+      "loss": 52.8616,
+      "step": 180
+    },
+    {
+      "epoch": 0.2942884801548887,
+      "grad_norm": 87031808.0,
+      "learning_rate": 1.9e-05,
+      "loss": 52.4976,
+      "step": 190
+    },
+    {
+      "epoch": 0.30977734753146174,
+      "grad_norm": 3129344.0,
+      "learning_rate": 2e-05,
+      "loss": 52.6041,
+      "step": 200
+    },
+    {
+      "epoch": 0.32526621490803487,
+      "grad_norm": 99090432.0,
+      "learning_rate": 2.1e-05,
+      "loss": 54.6559,
+      "step": 210
+    },
+    {
+      "epoch": 0.34075508228460794,
+      "grad_norm": 3238002688.0,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 52.2666,
+      "step": 220
+    },
+    {
+      "epoch": 0.356243949661181,
+      "grad_norm": 8454144.0,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 51.7553,
+      "step": 230
+    },
+    {
+      "epoch": 0.3717328170377541,
+      "grad_norm": 81264640.0,
+      "learning_rate": 2.4e-05,
+      "loss": 49.4186,
+      "step": 240
+    },
+    {
+      "epoch": 0.3872216844143272,
+      "grad_norm": 1531904.0,
+      "learning_rate": 2.5e-05,
+      "loss": 48.724,
+      "step": 250
+    },
+    {
+      "epoch": 0.4027105517909003,
+      "grad_norm": 6782976.0,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 47.4897,
+      "step": 260
+    },
+    {
+      "epoch": 0.4181994191674734,
+      "grad_norm": 462848.0,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 46.1025,
+      "step": 270
+    },
+    {
+      "epoch": 0.43368828654404645,
+      "grad_norm": 227328.0,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 43.953,
+      "step": 280
+    },
+    {
+      "epoch": 0.4491771539206196,
+      "grad_norm": 212992.0,
+      "learning_rate": 2.9e-05,
+      "loss": 42.786,
+      "step": 290
+    },
+    {
+      "epoch": 0.46466602129719264,
+      "grad_norm": 40704.0,
+      "learning_rate": 3e-05,
+      "loss": 41.3757,
+      "step": 300
+    },
+    {
+      "epoch": 0.4801548886737657,
+      "grad_norm": 42991616.0,
+      "learning_rate": 3.1e-05,
+      "loss": 42.0031,
+      "step": 310
+    },
+    {
+      "epoch": 0.49564375605033884,
+      "grad_norm": 21102592.0,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 41.9207,
+      "step": 320
+    },
+    {
+      "epoch": 0.5111326234269119,
+      "grad_norm": 16187392.0,
+      "learning_rate": 3.3e-05,
+      "loss": 42.2336,
+      "step": 330
+    },
+    {
+      "epoch": 0.526621490803485,
+      "grad_norm": 164864.0,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 40.6817,
+      "step": 340
+    },
+    {
+      "epoch": 0.542110358180058,
+      "grad_norm": 517996544.0,
+      "learning_rate": 3.5e-05,
+      "loss": 44.9866,
+      "step": 350
+    },
+    {
+      "epoch": 0.5575992255566312,
+      "grad_norm": 87556096.0,
+      "learning_rate": 3.6e-05,
+      "loss": 47.7577,
+      "step": 360
+    },
+    {
+      "epoch": 0.5730880929332043,
+      "grad_norm": 29753344.0,
+      "learning_rate": 3.7e-05,
+      "loss": 50.8352,
+      "step": 370
+    },
+    {
+      "epoch": 0.5885769603097774,
+      "grad_norm": 38273024.0,
+      "learning_rate": 3.8e-05,
+      "loss": 50.4585,
+      "step": 380
+    },
+    {
+      "epoch": 0.6040658276863504,
+      "grad_norm": 24248320.0,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 53.4794,
+      "step": 390
+    },
+    {
+      "epoch": 0.6195546950629235,
+      "grad_norm": 637534208.0,
+      "learning_rate": 4e-05,
+      "loss": 53.7074,
+      "step": 400
+    },
+    {
+      "epoch": 0.6350435624394967,
+      "grad_norm": 679477248.0,
+      "learning_rate": 4.1e-05,
+      "loss": 57.4144,
+      "step": 410
+    },
+    {
+      "epoch": 0.6505324298160697,
+      "grad_norm": 583008256.0,
+      "learning_rate": 4.2e-05,
+      "loss": 53.7095,
+      "step": 420
+    },
+    {
+      "epoch": 0.6660212971926428,
+      "grad_norm": 57933824.0,
+      "learning_rate": 4.3e-05,
+      "loss": 54.9929,
+      "step": 430
+    },
+    {
+      "epoch": 0.6815101645692159,
+      "grad_norm": 61079552.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 59.2993,
+      "step": 440
+    },
+    {
+      "epoch": 0.6969990319457889,
+      "grad_norm": 227540992.0,
+      "learning_rate": 4.5e-05,
+      "loss": 60.4038,
+      "step": 450
+    },
+    {
+      "epoch": 0.712487899322362,
+      "grad_norm": 190840832.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 63.1003,
+      "step": 460
+    },
+    {
+      "epoch": 0.7279767666989352,
+      "grad_norm": 327155712.0,
+      "learning_rate": 4.7e-05,
+      "loss": 64.5368,
+      "step": 470
+    },
+    {
+      "epoch": 0.7434656340755083,
+      "grad_norm": 679477248.0,
+      "learning_rate": 4.8e-05,
+      "loss": 61.6716,
+      "step": 480
+    },
+    {
+      "epoch": 0.7589545014520813,
+      "grad_norm": 276824064.0,
+      "learning_rate": 4.9e-05,
+      "loss": 62.8625,
+      "step": 490
+    },
+    {
+      "epoch": 0.7744433688286544,
+      "grad_norm": 78643200.0,
+      "learning_rate": 5e-05,
+      "loss": 63.9848,
+      "step": 500
+    },
+    {
+      "epoch": 0.7899322362052275,
+      "grad_norm": 224395264.0,
+      "learning_rate": 5.1000000000000006e-05,
+      "loss": 64.5113,
+      "step": 510
+    },
+    {
+      "epoch": 0.8054211035818006,
+      "grad_norm": 154140672.0,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 64.9807,
+      "step": 520
+    },
+    {
+      "epoch": 0.8209099709583737,
+      "grad_norm": 805306368.0,
+      "learning_rate": 5.300000000000001e-05,
+      "loss": 65.7812,
+      "step": 530
+    },
+    {
+      "epoch": 0.8363988383349468,
+      "grad_norm": 339738624.0,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 67.1272,
+      "step": 540
+    },
+    {
+      "epoch": 0.8518877057115198,
+      "grad_norm": 1002438656.0,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 66.3905,
+      "step": 550
+    },
+    {
+      "epoch": 0.8673765730880929,
+      "grad_norm": 2583691264.0,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 66.0419,
+      "step": 560
+    },
+    {
+      "epoch": 0.882865440464666,
+      "grad_norm": 411041792.0,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 62.0064,
+      "step": 570
+    },
+    {
+      "epoch": 0.8983543078412392,
+      "grad_norm": 70254592.0,
+      "learning_rate": 5.8e-05,
+      "loss": 63.6127,
+      "step": 580
+    },
+    {
+      "epoch": 0.9138431752178122,
+      "grad_norm": 191889408.0,
+      "learning_rate": 5.9e-05,
+      "loss": 63.481,
+      "step": 590
+    },
+    {
+      "epoch": 0.9293320425943853,
+      "grad_norm": 436207616.0,
+      "learning_rate": 6e-05,
+      "loss": 66.0833,
+      "step": 600
+    },
+    {
+      "epoch": 0.9293320425943853,
+      "eval_loss": 69.23383331298828,
+      "eval_runtime": 141.0364,
+      "eval_samples_per_second": 10.636,
+      "eval_steps_per_second": 2.659,
+      "step": 600
+    },
+    {
+      "epoch": 0.9448209099709584,
+      "grad_norm": 33161216.0,
+      "learning_rate": 6.1e-05,
+      "loss": 65.1055,
+      "step": 610
+    },
+    {
+      "epoch": 0.9603097773475314,
+      "grad_norm": 79167488.0,
+      "learning_rate": 6.2e-05,
+      "loss": 65.4074,
+      "step": 620
+    },
+    {
+      "epoch": 0.9757986447241046,
+      "grad_norm": 119013376.0,
+      "learning_rate": 6.3e-05,
+      "loss": 64.0661,
+      "step": 630
+    },
+    {
+      "epoch": 0.9912875121006777,
+      "grad_norm": 116391936.0,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 63.0841,
+      "step": 640
+    },
+    {
+      "epoch": 1.0067763794772506,
+      "grad_norm": 191889408.0,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 63.6633,
+      "step": 650
+    },
+    {
+      "epoch": 1.0222652468538238,
+      "grad_norm": 35389440.0,
+      "learning_rate": 6.6e-05,
+      "loss": 63.879,
+      "step": 660
+    },
+    {
+      "epoch": 1.037754114230397,
+      "grad_norm": 219152384.0,
+      "learning_rate": 6.7e-05,
+      "loss": 65.5105,
+      "step": 670
+    },
+    {
+      "epoch": 1.05324298160697,
+      "grad_norm": 476053504.0,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 66.3527,
+      "step": 680
+    },
+    {
+      "epoch": 1.0687318489835431,
+      "grad_norm": 2348810240.0,
+      "learning_rate": 6.9e-05,
+      "loss": 66.1827,
+      "step": 690
+    },
+    {
+      "epoch": 1.084220716360116,
+      "grad_norm": 452984832.0,
+      "learning_rate": 7e-05,
+      "loss": 67.8703,
+      "step": 700
+    },
+    {
+      "epoch": 1.0997095837366893,
+      "grad_norm": 46137344.0,
+      "learning_rate": 7.1e-05,
+      "loss": 67.2648,
+      "step": 710
+    },
+    {
+      "epoch": 1.1151984511132624,
+      "grad_norm": 70778880.0,
+      "learning_rate": 7.2e-05,
+      "loss": 62.0604,
+      "step": 720
+    },
+    {
+      "epoch": 1.1306873184898354,
+      "grad_norm": 283115520.0,
+      "learning_rate": 7.3e-05,
+      "loss": 60.8914,
+      "step": 730
+    },
+    {
+      "epoch": 1.1461761858664086,
+      "grad_norm": 78118912.0,
+      "learning_rate": 7.4e-05,
+      "loss": 60.0754,
+      "step": 740
+    },
+    {
+      "epoch": 1.1616650532429815,
+      "grad_norm": 120061952.0,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 63.6695,
+      "step": 750
+    },
+    {
+      "epoch": 1.1771539206195547,
+      "grad_norm": 90701824.0,
+      "learning_rate": 7.6e-05,
+      "loss": 65.6076,
+      "step": 760
+    },
+    {
+      "epoch": 1.1926427879961277,
+      "grad_norm": 23724032.0,
+      "learning_rate": 7.7e-05,
+      "loss": 64.6991,
+      "step": 770
+    },
+    {
+      "epoch": 1.2081316553727008,
+      "grad_norm": 22806528.0,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 64.4208,
+      "step": 780
+    },
+    {
+      "epoch": 1.223620522749274,
+      "grad_norm": 19529728.0,
+      "learning_rate": 7.900000000000001e-05,
+      "loss": 58.9719,
+      "step": 790
+    },
+    {
+      "epoch": 1.239109390125847,
+      "grad_norm": 154140672.0,
+      "learning_rate": 8e-05,
+      "loss": 58.4048,
+      "step": 800
+    },
+    {
+      "epoch": 1.2545982575024202,
+      "grad_norm": 4882432.0,
+      "learning_rate": 8.1e-05,
+      "loss": 63.3226,
+      "step": 810
+    },
+    {
+      "epoch": 1.2700871248789931,
+      "grad_norm": 4718592.0,
+      "learning_rate": 8.2e-05,
+      "loss": 62.6276,
+      "step": 820
+    },
+    {
+      "epoch": 1.2855759922555663,
+      "grad_norm": 56098816.0,
+      "learning_rate": 8.3e-05,
+      "loss": 57.6699,
+      "step": 830
+    },
+    {
+      "epoch": 1.3010648596321395,
+      "grad_norm": 2281701376.0,
+      "learning_rate": 8.4e-05,
+      "loss": 55.8831,
+      "step": 840
+    },
+    {
+      "epoch": 1.3165537270087124,
+      "grad_norm": 63963136.0,
+      "learning_rate": 8.5e-05,
+      "loss": 58.8188,
+      "step": 850
+    },
+    {
+      "epoch": 1.3320425943852856,
+      "grad_norm": 66322432.0,
+      "learning_rate": 8.6e-05,
+      "loss": 57.2062,
+      "step": 860
+    },
+    {
+      "epoch": 1.3475314617618586,
+      "grad_norm": 17956864.0,
+      "learning_rate": 8.7e-05,
+      "loss": 59.4092,
+      "step": 870
+    },
+    {
+      "epoch": 1.3630203291384317,
+      "grad_norm": 246415360.0,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 56.8145,
+      "step": 880
+    },
+    {
+      "epoch": 1.378509196515005,
+      "grad_norm": 205520896.0,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 56.4558,
+      "step": 890
+    },
+    {
+      "epoch": 1.3939980638915779,
+      "grad_norm": 90177536.0,
+      "learning_rate": 9e-05,
+      "loss": 54.4208,
+      "step": 900
+    },
+    {
+      "epoch": 1.409486931268151,
+      "grad_norm": 383778816.0,
+      "learning_rate": 9.1e-05,
+      "loss": 53.8711,
+      "step": 910
+    },
+    {
+      "epoch": 1.424975798644724,
+      "grad_norm": 23461888.0,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 52.0157,
+      "step": 920
+    },
+    {
+      "epoch": 1.4404646660212972,
+      "grad_norm": 27394048.0,
+      "learning_rate": 9.300000000000001e-05,
+      "loss": 48.0571,
+      "step": 930
+    },
+    {
+      "epoch": 1.4559535333978704,
+      "grad_norm": 8716288.0,
+      "learning_rate": 9.4e-05,
+      "loss": 43.4202,
+      "step": 940
+    },
+    {
+      "epoch": 1.4714424007744433,
+      "grad_norm": 5570560.0,
+      "learning_rate": 9.5e-05,
+      "loss": 40.7559,
+      "step": 950
+    },
+    {
+      "epoch": 1.4869312681510165,
+      "grad_norm": 20316160.0,
+      "learning_rate": 9.6e-05,
+      "loss": 39.1436,
+      "step": 960
+    },
+    {
+      "epoch": 1.5024201355275895,
+      "grad_norm": 15204352.0,
+      "learning_rate": 9.7e-05,
+      "loss": 36.618,
+      "step": 970
+    },
+    {
+      "epoch": 1.5179090029041626,
+      "grad_norm": 5832704.0,
+      "learning_rate": 9.8e-05,
+      "loss": 34.3857,
+      "step": 980
+    },
+    {
+      "epoch": 1.5333978702807358,
+      "grad_norm": 2293760.0,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 29.7184,
+      "step": 990
+    },
+    {
+      "epoch": 1.5488867376573088,
+      "grad_norm": 22282240.0,
+      "learning_rate": 0.0001,
+      "loss": 24.8724,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5643756050338817,
+      "grad_norm": 10682368.0,
+      "learning_rate": 9.98165137614679e-05,
+      "loss": 21.2392,
+      "step": 1010
+    },
+    {
+      "epoch": 1.579864472410455,
+      "grad_norm": 25690112.0,
+      "learning_rate": 9.963302752293578e-05,
+      "loss": 18.7594,
+      "step": 1020
+    },
+    {
+      "epoch": 1.595353339787028,
+      "grad_norm": 15400960.0,
+      "learning_rate": 9.944954128440368e-05,
+      "loss": 17.9276,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6108422071636013,
+      "grad_norm": 2359296.0,
+      "learning_rate": 9.926605504587157e-05,
+      "loss": 16.505,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6263310745401742,
+      "grad_norm": 19005440.0,
+      "learning_rate": 9.908256880733946e-05,
+      "loss": 15.258,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6418199419167472,
+      "grad_norm": 9240576.0,
+      "learning_rate": 9.889908256880734e-05,
+      "loss": 13.9628,
+      "step": 1060
+    },
+    {
+      "epoch": 1.6573088092933204,
+      "grad_norm": 7012352.0,
+      "learning_rate": 9.871559633027525e-05,
+      "loss": 14.8131,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6727976766698935,
+      "grad_norm": 8388608.0,
+      "learning_rate": 9.853211009174312e-05,
+      "loss": 13.4851,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6882865440464667,
+      "grad_norm": 1286144.0,
+      "learning_rate": 9.834862385321102e-05,
+      "loss": 12.8225,
+      "step": 1090
+    },
+    {
+      "epoch": 1.7037754114230397,
+      "grad_norm": 2490368.0,
+      "learning_rate": 9.816513761467891e-05,
+      "loss": 11.7111,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7192642787996126,
+      "grad_norm": 1064960.0,
+      "learning_rate": 9.79816513761468e-05,
+      "loss": 11.347,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7347531461761858,
+      "grad_norm": 352256.0,
+      "learning_rate": 9.779816513761468e-05,
+      "loss": 10.6953,
+      "step": 1120
+    },
+    {
+      "epoch": 1.750242013552759,
+      "grad_norm": 4046848.0,
+      "learning_rate": 9.761467889908259e-05,
+      "loss": 10.3879,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7657308809293322,
+      "grad_norm": 348160.0,
+      "learning_rate": 9.743119266055046e-05,
+      "loss": 10.5364,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7812197483059051,
+      "grad_norm": 6193152.0,
+      "learning_rate": 9.724770642201836e-05,
+      "loss": 10.7673,
+      "step": 1150
+    },
+    {
+      "epoch": 1.796708615682478,
+      "grad_norm": 671744.0,
+      "learning_rate": 9.706422018348625e-05,
+      "loss": 10.0088,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8121974830590513,
+      "grad_norm": 557056.0,
+      "learning_rate": 9.688073394495414e-05,
+      "loss": 10.1469,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8276863504356244,
+      "grad_norm": 835584.0,
+      "learning_rate": 9.669724770642202e-05,
+      "loss": 10.2772,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8431752178121976,
+      "grad_norm": 2277376.0,
+      "learning_rate": 9.651376146788991e-05,
+      "loss": 9.8019,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8586640851887706,
+      "grad_norm": 307200.0,
+      "learning_rate": 9.63302752293578e-05,
+      "loss": 9.5204,
+      "step": 1200
+    },
+    {
+      "epoch": 1.8586640851887706,
+      "eval_loss": 9.286345481872559,
+      "eval_runtime": 140.9651,
+      "eval_samples_per_second": 10.641,
+      "eval_steps_per_second": 2.66,
+      "step": 1200
+    },
+    {
+      "epoch": 1.8741529525653435,
+      "grad_norm": 315392.0,
+      "learning_rate": 9.61467889908257e-05,
+      "loss": 9.7153,
+      "step": 1210
+    },
+    {
+      "epoch": 1.8896418199419167,
+      "grad_norm": 1089536.0,
+      "learning_rate": 9.596330275229359e-05,
+      "loss": 9.847,
+      "step": 1220
+    },
+    {
+      "epoch": 1.90513068731849,
+      "grad_norm": 1597440.0,
+      "learning_rate": 9.577981651376148e-05,
+      "loss": 9.5979,
+      "step": 1230
+    },
+    {
+      "epoch": 1.920619554695063,
+      "grad_norm": 481280.0,
+      "learning_rate": 9.559633027522936e-05,
+      "loss": 9.4879,
+      "step": 1240
+    },
+    {
+      "epoch": 1.936108422071636,
+      "grad_norm": 847872.0,
+      "learning_rate": 9.541284403669725e-05,
+      "loss": 8.8939,
+      "step": 1250
+    },
+    {
+      "epoch": 1.951597289448209,
+      "grad_norm": 292864.0,
+      "learning_rate": 9.522935779816514e-05,
+      "loss": 9.2976,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9670861568247822,
+      "grad_norm": 1630208.0,
+      "learning_rate": 9.504587155963304e-05,
+      "loss": 8.9201,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9825750242013553,
+      "grad_norm": 471040.0,
+      "learning_rate": 9.486238532110093e-05,
+      "loss": 8.9614,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9980638915779285,
+      "grad_norm": 761856.0,
+      "learning_rate": 9.467889908256882e-05,
+      "loss": 9.0607,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0135527589545013,
+      "grad_norm": 512000.0,
+      "learning_rate": 9.44954128440367e-05,
+      "loss": 9.3156,
+      "step": 1300
+    },
+    {
+      "epoch": 2.0290416263310744,
+      "grad_norm": 321536.0,
+      "learning_rate": 9.431192660550459e-05,
+      "loss": 9.0155,
+      "step": 1310
+    },
+    {
+      "epoch": 2.0445304937076476,
+      "grad_norm": 2555904.0,
+      "learning_rate": 9.412844036697248e-05,
+      "loss": 8.7237,
+      "step": 1320
+    },
+    {
+      "epoch": 2.060019361084221,
+      "grad_norm": 1638400.0,
+      "learning_rate": 9.394495412844038e-05,
+      "loss": 8.559,
+      "step": 1330
+    },
+    {
+      "epoch": 2.075508228460794,
+      "grad_norm": 6914048.0,
+      "learning_rate": 9.376146788990827e-05,
+      "loss": 8.7204,
+      "step": 1340
+    },
+    {
+      "epoch": 2.0909970958373667,
+      "grad_norm": 270336.0,
+      "learning_rate": 9.357798165137616e-05,
+      "loss": 8.7914,
+      "step": 1350
+    },
+    {
+      "epoch": 2.10648596321394,
+      "grad_norm": 3145728.0,
+      "learning_rate": 9.339449541284404e-05,
+      "loss": 10.1368,
+      "step": 1360
+    },
+    {
+      "epoch": 2.121974830590513,
+      "grad_norm": 305152.0,
+      "learning_rate": 9.321100917431193e-05,
+      "loss": 9.0641,
+      "step": 1370
+    },
+    {
+      "epoch": 2.1374636979670862,
+      "grad_norm": 651264.0,
+      "learning_rate": 9.302752293577982e-05,
+      "loss": 8.5292,
+      "step": 1380
+    },
+    {
+      "epoch": 2.1529525653436594,
+      "grad_norm": 323584.0,
+      "learning_rate": 9.284403669724772e-05,
+      "loss": 8.3136,
+      "step": 1390
+    },
+    {
+      "epoch": 2.168441432720232,
+      "grad_norm": 692224.0,
+      "learning_rate": 9.266055045871561e-05,
+      "loss": 8.4924,
+      "step": 1400
+    },
+    {
+      "epoch": 2.1839303000968053,
+      "grad_norm": 1941504.0,
+      "learning_rate": 9.24770642201835e-05,
+      "loss": 7.9653,
+      "step": 1410
+    },
+    {
+      "epoch": 2.1994191674733785,
+      "grad_norm": 3325952.0,
+      "learning_rate": 9.229357798165138e-05,
+      "loss": 8.2938,
+      "step": 1420
+    },
+    {
+      "epoch": 2.2149080348499517,
+      "grad_norm": 7897088.0,
+      "learning_rate": 9.211009174311927e-05,
+      "loss": 8.6513,
+      "step": 1430
+    },
+    {
+      "epoch": 2.230396902226525,
+      "grad_norm": 229638144.0,
+      "learning_rate": 9.192660550458716e-05,
+      "loss": 8.9772,
+      "step": 1440
+    },
+    {
+      "epoch": 2.2458857696030976,
+      "grad_norm": 1990656.0,
+      "learning_rate": 9.174311926605506e-05,
+      "loss": 9.0591,
+      "step": 1450
+    },
+    {
+      "epoch": 2.261374636979671,
+      "grad_norm": 2113536.0,
+      "learning_rate": 9.155963302752293e-05,
+      "loss": 8.5508,
+      "step": 1460
+    },
+    {
+      "epoch": 2.276863504356244,
+      "grad_norm": 14352384.0,
+      "learning_rate": 9.137614678899083e-05,
+      "loss": 8.6085,
+      "step": 1470
+    },
+    {
+      "epoch": 2.292352371732817,
+      "grad_norm": 2277376.0,
+      "learning_rate": 9.119266055045872e-05,
+      "loss": 8.8426,
+      "step": 1480
+    },
+    {
+      "epoch": 2.3078412391093903,
+      "grad_norm": 26476544.0,
+      "learning_rate": 9.100917431192661e-05,
+      "loss": 9.0669,
+      "step": 1490
+    },
+    {
+      "epoch": 2.323330106485963,
+      "grad_norm": 85458944.0,
+      "learning_rate": 9.08256880733945e-05,
+      "loss": 9.6445,
+      "step": 1500
+    },
+    {
+      "epoch": 2.3388189738625362,
+      "grad_norm": 128974848.0,
+      "learning_rate": 9.06422018348624e-05,
+      "loss": 9.6751,
+      "step": 1510
+    },
+    {
+      "epoch": 2.3543078412391094,
+      "grad_norm": 32636928.0,
+      "learning_rate": 9.045871559633027e-05,
+      "loss": 9.2084,
+      "step": 1520
+    },
+    {
+      "epoch": 2.3697967086156826,
+      "grad_norm": 175112192.0,
+      "learning_rate": 9.027522935779817e-05,
+      "loss": 9.3795,
+      "step": 1530
+    },
+    {
+      "epoch": 2.3852855759922553,
+      "grad_norm": 25034752.0,
+      "learning_rate": 9.009174311926606e-05,
+      "loss": 9.6548,
+      "step": 1540
+    },
+    {
+      "epoch": 2.4007744433688285,
+      "grad_norm": 8093696.0,
+      "learning_rate": 8.990825688073395e-05,
+      "loss": 9.0062,
+      "step": 1550
+    },
+    {
+      "epoch": 2.4162633107454017,
+      "grad_norm": 3866624.0,
+      "learning_rate": 8.972477064220184e-05,
+      "loss": 8.6427,
+      "step": 1560
+    },
+    {
+      "epoch": 2.431752178121975,
+      "grad_norm": 1433600.0,
+      "learning_rate": 8.954128440366974e-05,
+      "loss": 8.9959,
+      "step": 1570
+    },
+    {
+      "epoch": 2.447241045498548,
+      "grad_norm": 4030464.0,
+      "learning_rate": 8.935779816513761e-05,
+      "loss": 8.9193,
+      "step": 1580
+    },
+    {
+      "epoch": 2.4627299128751208,
+      "grad_norm": 37224448.0,
+      "learning_rate": 8.917431192660551e-05,
+      "loss": 8.9464,
+      "step": 1590
+    },
+    {
+      "epoch": 2.478218780251694,
+      "grad_norm": 1003520.0,
+      "learning_rate": 8.89908256880734e-05,
+      "loss": 9.1216,
+      "step": 1600
+    },
+    {
+      "epoch": 2.493707647628267,
+      "grad_norm": 2801664.0,
+      "learning_rate": 8.880733944954129e-05,
+      "loss": 8.9064,
+      "step": 1610
+    },
+    {
+      "epoch": 2.5091965150048403,
+      "grad_norm": 2211840.0,
+      "learning_rate": 8.862385321100918e-05,
+      "loss": 9.062,
+      "step": 1620
+    },
+    {
+      "epoch": 2.5246853823814135,
+      "grad_norm": 868352.0,
+      "learning_rate": 8.844036697247708e-05,
+      "loss": 9.2384,
+      "step": 1630
+    },
+    {
+      "epoch": 2.5401742497579862,
+      "grad_norm": 3964928.0,
+      "learning_rate": 8.825688073394495e-05,
+      "loss": 9.0259,
+      "step": 1640
+    },
+    {
+      "epoch": 2.5556631171345594,
+      "grad_norm": 1802240.0,
+      "learning_rate": 8.807339449541285e-05,
+      "loss": 9.0643,
+      "step": 1650
+    },
+    {
+      "epoch": 2.5711519845111326,
+      "grad_norm": 73216.0,
+      "learning_rate": 8.788990825688074e-05,
+      "loss": 8.8911,
+      "step": 1660
+    },
+    {
+      "epoch": 2.5866408518877058,
+      "grad_norm": 2719744.0,
+      "learning_rate": 8.770642201834863e-05,
+      "loss": 8.7628,
+      "step": 1670
+    },
+    {
+      "epoch": 2.602129719264279,
+      "grad_norm": 1908736.0,
+      "learning_rate": 8.752293577981652e-05,
+      "loss": 8.3985,
+      "step": 1680
+    },
+    {
+      "epoch": 2.6176185866408517,
+      "grad_norm": 55574528.0,
+      "learning_rate": 8.733944954128442e-05,
+      "loss": 8.386,
+      "step": 1690
+    },
+    {
+      "epoch": 2.633107454017425,
+      "grad_norm": 561152.0,
+      "learning_rate": 8.715596330275229e-05,
+      "loss": 7.9368,
+      "step": 1700
+    },
+    {
+      "epoch": 2.648596321393998,
+      "grad_norm": 179200.0,
+      "learning_rate": 8.697247706422019e-05,
+      "loss": 7.37,
+      "step": 1710
+    },
+    {
+      "epoch": 2.664085188770571,
+      "grad_norm": 56320.0,
+      "learning_rate": 8.678899082568808e-05,
+      "loss": 7.0107,
+      "step": 1720
+    },
+    {
+      "epoch": 2.6795740561471444,
+      "grad_norm": 32256.0,
+      "learning_rate": 8.660550458715597e-05,
+      "loss": 6.9978,
+      "step": 1730
+    },
+    {
+      "epoch": 2.695062923523717,
+      "grad_norm": 91136.0,
+      "learning_rate": 8.642201834862386e-05,
+      "loss": 6.2097,
+      "step": 1740
+    },
+    {
+      "epoch": 2.7105517909002903,
+      "grad_norm": 35584.0,
+      "learning_rate": 8.623853211009176e-05,
+      "loss": 5.6404,
+      "step": 1750
+    },
+    {
+      "epoch": 2.7260406582768635,
+      "grad_norm": 146432.0,
+      "learning_rate": 8.605504587155963e-05,
+      "loss": 5.6008,
+      "step": 1760
+    },
+    {
+      "epoch": 2.7415295256534367,
+      "grad_norm": 229376.0,
+      "learning_rate": 8.587155963302753e-05,
+      "loss": 4.993,
+      "step": 1770
+    },
+    {
+      "epoch": 2.75701839303001,
+      "grad_norm": 208896.0,
+      "learning_rate": 8.568807339449542e-05,
+      "loss": 5.0213,
+      "step": 1780
+    },
+    {
+      "epoch": 2.7725072604065826,
+      "grad_norm": 41156608.0,
+      "learning_rate": 8.550458715596331e-05,
+      "loss": 8.4373,
+      "step": 1790
+    },
+    {
+      "epoch": 2.7879961277831558,
+      "grad_norm": 72351744.0,
+      "learning_rate": 8.53211009174312e-05,
+      "loss": 11.2268,
+      "step": 1800
+    },
+    {
+      "epoch": 2.7879961277831558,
+      "eval_loss": 3.6953983306884766,
+      "eval_runtime": 140.9159,
+      "eval_samples_per_second": 10.645,
+      "eval_steps_per_second": 2.661,
+      "step": 1800
+    },
+    {
+      "epoch": 2.803484995159729,
+      "grad_norm": 4292608.0,
+      "learning_rate": 8.51376146788991e-05,
+      "loss": 7.2401,
+      "step": 1810
+    },
+    {
+      "epoch": 2.818973862536302,
+      "grad_norm": 78336.0,
+      "learning_rate": 8.495412844036697e-05,
+      "loss": 10.0121,
+      "step": 1820
+    },
+    {
+      "epoch": 2.8344627299128753,
+      "grad_norm": 51118080.0,
+      "learning_rate": 8.477064220183487e-05,
+      "loss": 8.6225,
+      "step": 1830
+    },
+    {
+      "epoch": 2.849951597289448,
+      "grad_norm": 80896.0,
+      "learning_rate": 8.458715596330276e-05,
+      "loss": 11.3472,
+      "step": 1840
+    },
+    {
+      "epoch": 2.865440464666021,
+      "grad_norm": 42991616.0,
+      "learning_rate": 8.440366972477065e-05,
+      "loss": 8.5839,
+      "step": 1850
+    },
+    {
+      "epoch": 2.8809293320425944,
+      "grad_norm": 3604480.0,
+      "learning_rate": 8.422018348623854e-05,
+      "loss": 7.3366,
+      "step": 1860
+    },
+    {
+      "epoch": 2.8964181994191676,
+      "grad_norm": 429916160.0,
+      "learning_rate": 8.403669724770644e-05,
+      "loss": 9.0048,
+      "step": 1870
+    },
+    {
+      "epoch": 2.9119070667957407,
+      "grad_norm": 1358954496.0,
+      "learning_rate": 8.385321100917431e-05,
+      "loss": 12.7748,
+      "step": 1880
+    },
+    {
+      "epoch": 2.9273959341723135,
+      "grad_norm": 11408506880.0,
+      "learning_rate": 8.366972477064221e-05,
+      "loss": 14.6054,
+      "step": 1890
+    },
+    {
+      "epoch": 2.9428848015488867,
+      "grad_norm": 276824064.0,
+      "learning_rate": 8.34862385321101e-05,
+      "loss": 10.7776,
+      "step": 1900
+    },
+    {
+      "epoch": 2.95837366892546,
+      "grad_norm": 9193914368.0,
+      "learning_rate": 8.330275229357799e-05,
+      "loss": 11.4151,
+      "step": 1910
+    },
+    {
+      "epoch": 2.973862536302033,
+      "grad_norm": 2382364672.0,
+      "learning_rate": 8.311926605504588e-05,
+      "loss": 8.8062,
+      "step": 1920
+    },
+    {
+      "epoch": 2.989351403678606,
+      "grad_norm": 73400320.0,
+      "learning_rate": 8.293577981651378e-05,
+      "loss": 10.1995,
+      "step": 1930
+    },
+    {
+      "epoch": 3.004840271055179,
+      "grad_norm": 87031808.0,
+      "learning_rate": 8.275229357798165e-05,
+      "loss": 8.5145,
+      "step": 1940
+    },
+    {
+      "epoch": 3.020329138431752,
+      "grad_norm": 7046430720.0,
+      "learning_rate": 8.256880733944955e-05,
+      "loss": 9.7012,
+      "step": 1950
+    },
+    {
+      "epoch": 3.0358180058083253,
+      "grad_norm": 2533359616.0,
+      "learning_rate": 8.238532110091744e-05,
+      "loss": 9.9511,
+      "step": 1960
+    },
+    {
+      "epoch": 3.0513068731848985,
+      "grad_norm": 5079040.0,
+      "learning_rate": 8.220183486238533e-05,
+      "loss": 8.072,
+      "step": 1970
+    },
+    {
+      "epoch": 3.0667957405614716,
+      "grad_norm": 724992.0,
+      "learning_rate": 8.201834862385321e-05,
+      "loss": 7.4696,
+      "step": 1980
+    },
+    {
+      "epoch": 3.0822846079380444,
+      "grad_norm": 82837504.0,
+      "learning_rate": 8.183486238532112e-05,
+      "loss": 7.2543,
+      "step": 1990
+    },
+    {
+      "epoch": 3.0977734753146176,
+      "grad_norm": 2785280.0,
+      "learning_rate": 8.165137614678899e-05,
+      "loss": 6.9033,
+      "step": 2000
+    },
+    {
+      "epoch": 3.1132623426911907,
+      "grad_norm": 9830400.0,
+      "learning_rate": 8.146788990825689e-05,
+      "loss": 10.1325,
+      "step": 2010
+    },
+    {
+      "epoch": 3.128751210067764,
+      "grad_norm": 3640655872.0,
+      "learning_rate": 8.128440366972478e-05,
+      "loss": 9.1776,
+      "step": 2020
+    },
+    {
+      "epoch": 3.144240077444337,
+      "grad_norm": 6815744.0,
+      "learning_rate": 8.110091743119267e-05,
+      "loss": 8.3169,
+      "step": 2030
+    },
+    {
+      "epoch": 3.15972894482091,
+      "grad_norm": 956301312.0,
+      "learning_rate": 8.091743119266055e-05,
+      "loss": 7.2157,
+      "step": 2040
+    },
+    {
+      "epoch": 3.175217812197483,
+      "grad_norm": 167772160.0,
+      "learning_rate": 8.073394495412844e-05,
+      "loss": 11.944,
+      "step": 2050
+    },
+    {
+      "epoch": 3.190706679574056,
+      "grad_norm": 27000832.0,
+      "learning_rate": 8.055045871559633e-05,
+      "loss": 14.3998,
+      "step": 2060
+    },
+    {
+      "epoch": 3.2061955469506294,
+      "grad_norm": 3571712.0,
+      "learning_rate": 8.036697247706423e-05,
+      "loss": 10.9291,
+      "step": 2070
+    },
+    {
+      "epoch": 3.2216844143272025,
+      "grad_norm": 232783872.0,
+      "learning_rate": 8.018348623853212e-05,
+      "loss": 8.4304,
+      "step": 2080
+    },
+    {
+      "epoch": 3.2371732817037753,
+      "grad_norm": 612368384.0,
+      "learning_rate": 8e-05,
+      "loss": 9.7251,
+      "step": 2090
+    },
+    {
+      "epoch": 3.2526621490803485,
+      "grad_norm": 149946368.0,
+      "learning_rate": 7.98165137614679e-05,
+      "loss": 16.7679,
+      "step": 2100
+    },
+    {
+      "epoch": 3.2681510164569216,
+      "grad_norm": 19791872.0,
+      "learning_rate": 7.963302752293578e-05,
+      "loss": 16.4714,
+      "step": 2110
+    },
+    {
+      "epoch": 3.283639883833495,
+      "grad_norm": 7798784.0,
+      "learning_rate": 7.944954128440367e-05,
+      "loss": 12.975,
+      "step": 2120
+    },
+    {
+      "epoch": 3.299128751210068,
+      "grad_norm": 10420224.0,
+      "learning_rate": 7.926605504587157e-05,
+      "loss": 12.5423,
+      "step": 2130
+    },
+    {
+      "epoch": 3.3146176185866407,
+      "grad_norm": 2523136.0,
+      "learning_rate": 7.908256880733946e-05,
+      "loss": 14.3525,
+      "step": 2140
+    },
+    {
+      "epoch": 3.330106485963214,
+      "grad_norm": 1996488704.0,
+      "learning_rate": 7.889908256880735e-05,
+      "loss": 12.2418,
+      "step": 2150
+    },
+    {
+      "epoch": 3.345595353339787,
+      "grad_norm": 2852126720.0,
+      "learning_rate": 7.871559633027523e-05,
+      "loss": 12.295,
+      "step": 2160
+    },
+    {
+      "epoch": 3.3610842207163603,
+      "grad_norm": 94896128.0,
+      "learning_rate": 7.853211009174312e-05,
+      "loss": 13.6261,
+      "step": 2170
+    },
+    {
+      "epoch": 3.3765730880929334,
+      "grad_norm": 63176704.0,
+      "learning_rate": 7.834862385321101e-05,
+      "loss": 16.2585,
+      "step": 2180
+    },
+    {
+      "epoch": 3.392061955469506,
+      "grad_norm": 22806528.0,
+      "learning_rate": 7.816513761467891e-05,
+      "loss": 13.0167,
+      "step": 2190
+    },
+    {
+      "epoch": 3.4075508228460794,
+      "grad_norm": 171008.0,
+      "learning_rate": 7.79816513761468e-05,
+      "loss": 14.2586,
+      "step": 2200
+    },
+    {
+      "epoch": 3.4230396902226525,
+      "grad_norm": 514048.0,
+      "learning_rate": 7.779816513761469e-05,
+      "loss": 13.1638,
+      "step": 2210
+    },
+    {
+      "epoch": 3.4385285575992257,
+      "grad_norm": 1949696.0,
+      "learning_rate": 7.761467889908257e-05,
+      "loss": 12.0993,
+      "step": 2220
+    },
+    {
+      "epoch": 3.454017424975799,
+      "grad_norm": 1146880.0,
+      "learning_rate": 7.743119266055046e-05,
+      "loss": 14.4118,
+      "step": 2230
+    },
+    {
+      "epoch": 3.4695062923523716,
+      "grad_norm": 6225920.0,
+      "learning_rate": 7.724770642201835e-05,
+      "loss": 13.5697,
+      "step": 2240
+    },
+    {
+      "epoch": 3.484995159728945,
+      "grad_norm": 876544.0,
+      "learning_rate": 7.706422018348625e-05,
+      "loss": 13.0038,
+      "step": 2250
+    },
+    {
+      "epoch": 3.500484027105518,
+      "grad_norm": 169984.0,
+      "learning_rate": 7.688073394495412e-05,
+      "loss": 7.2399,
+      "step": 2260
+    },
+    {
+      "epoch": 3.515972894482091,
+      "grad_norm": 11328.0,
+      "learning_rate": 7.669724770642203e-05,
+      "loss": 5.2788,
+      "step": 2270
+    },
+    {
+      "epoch": 3.5314617618586643,
+      "grad_norm": 38144.0,
+      "learning_rate": 7.651376146788991e-05,
+      "loss": 4.7646,
+      "step": 2280
+    },
+    {
+      "epoch": 3.546950629235237,
+      "grad_norm": 33792.0,
+      "learning_rate": 7.63302752293578e-05,
+      "loss": 4.3227,
+      "step": 2290
+    },
+    {
+      "epoch": 3.5624394966118103,
+      "grad_norm": 230400.0,
+      "learning_rate": 7.614678899082569e-05,
+      "loss": 3.6174,
+      "step": 2300
+    },
+    {
+      "epoch": 3.5779283639883834,
+      "grad_norm": 5952.0,
+      "learning_rate": 7.596330275229359e-05,
+      "loss": 3.7957,
+      "step": 2310
+    },
+    {
+      "epoch": 3.593417231364956,
+      "grad_norm": 306.0,
+      "learning_rate": 7.577981651376146e-05,
+      "loss": 3.1113,
+      "step": 2320
+    },
+    {
+      "epoch": 3.60890609874153,
+      "grad_norm": 4456448.0,
+      "learning_rate": 7.559633027522937e-05,
+      "loss": 2.8727,
+      "step": 2330
+    },
+    {
+      "epoch": 3.6243949661181025,
+      "grad_norm": 644.0,
+      "learning_rate": 7.541284403669725e-05,
+      "loss": 3.0421,
+      "step": 2340
+    },
+    {
+      "epoch": 3.6398838334946757,
+      "grad_norm": 2523136.0,
+      "learning_rate": 7.522935779816514e-05,
+      "loss": 2.5395,
+      "step": 2350
+    },
+    {
+      "epoch": 3.655372700871249,
+      "grad_norm": 183296.0,
+      "learning_rate": 7.504587155963303e-05,
+      "loss": 2.1641,
+      "step": 2360
+    },
+    {
+      "epoch": 3.6708615682478216,
+      "grad_norm": 852.0,
+      "learning_rate": 7.486238532110093e-05,
+      "loss": 2.6632,
+      "step": 2370
+    },
+    {
+      "epoch": 3.6863504356243952,
+      "grad_norm": 767557632.0,
+      "learning_rate": 7.46788990825688e-05,
+      "loss": 2.4136,
+      "step": 2380
+    },
+    {
+      "epoch": 3.701839303000968,
+      "grad_norm": 1896.0,
+      "learning_rate": 7.44954128440367e-05,
+      "loss": 2.1181,
+      "step": 2390
+    },
+    {
+      "epoch": 3.717328170377541,
+      "grad_norm": 158.0,
+      "learning_rate": 7.431192660550459e-05,
+      "loss": 2.4009,
+      "step": 2400
+    },
+    {
+      "epoch": 3.717328170377541,
+      "eval_loss": 0.6069380640983582,
+      "eval_runtime": 141.2808,
+      "eval_samples_per_second": 10.617,
+      "eval_steps_per_second": 2.654,
+      "step": 2400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 6450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 600,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3135844049577574e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c0b316232148013de61dc43a03078821b20092aa7c5dd826a3c43110d7a932
+size 5240