Upload folder using huggingface_hub

checkpoint-1500-new/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-1500-new/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "jordiclive/tasky",
+  "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-1500-new/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-1500-new/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c642ce01c255d944c92108dcc7f37c16111eb9d89ce3530218d1e58b954cdd
+size 4985006064

checkpoint-1500-new/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6935bada5e5efe6113e3c91a4e0465e550a674a4d93d1217198e65bfac9c737
+size 714678248

checkpoint-1500-new/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-1500-new/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb0eb18a21eec39de7f81e4f82299717c9afe88f3dc7af555c83d61c7e313f9
+size 10612076

checkpoint-1500-new/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71108e9c6dfde69a170b9afc53c7023230728df202e612a85d104ad4bab7964c
+size 14244

checkpoint-1500-new/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae5d9936fbebd71ef45a9dbd13b0d7fb1aac66727675e8ee37fc10eaf1665cb
+size 1064

checkpoint-1500-new/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-1500-new/tokenizer.model

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

checkpoint-1500-new/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-1500-new/trainer_state.json

@@ -0,0 +1,1107 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.646660212971926,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.030977734753146177,
+      "grad_norm": 99.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.9661,
+      "step": 10
+    },
+    {
+      "epoch": 0.061955469506292354,
+      "grad_norm": 374.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.2124,
+      "step": 20
+    },
+    {
+      "epoch": 0.09293320425943853,
+      "grad_norm": 1392640.0,
+      "learning_rate": 3e-06,
+      "loss": 2.2122,
+      "step": 30
+    },
+    {
+      "epoch": 0.12391093901258471,
+      "grad_norm": 78.5,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.9339,
+      "step": 40
+    },
+    {
+      "epoch": 0.15488867376573087,
+      "grad_norm": 13500416.0,
+      "learning_rate": 5e-06,
+      "loss": 1.8448,
+      "step": 50
+    },
+    {
+      "epoch": 0.18586640851887706,
+      "grad_norm": 98.0,
+      "learning_rate": 6e-06,
+      "loss": 1.9577,
+      "step": 60
+    },
+    {
+      "epoch": 0.21684414327202323,
+      "grad_norm": 11337728.0,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 2.089,
+      "step": 70
+    },
+    {
+      "epoch": 0.24782187802516942,
+      "grad_norm": 20736.0,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.8571,
+      "step": 80
+    },
+    {
+      "epoch": 0.2787996127783156,
+      "grad_norm": 8512.0,
+      "learning_rate": 9e-06,
+      "loss": 2.0639,
+      "step": 90
+    },
+    {
+      "epoch": 0.30977734753146174,
+      "grad_norm": 1004.0,
+      "learning_rate": 1e-05,
+      "loss": 1.978,
+      "step": 100
+    },
+    {
+      "epoch": 0.34075508228460794,
+      "grad_norm": 470.0,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 1.9845,
+      "step": 110
+    },
+    {
+      "epoch": 0.3717328170377541,
+      "grad_norm": 268435456.0,
+      "learning_rate": 1.2e-05,
+      "loss": 1.9825,
+      "step": 120
+    },
+    {
+      "epoch": 0.4027105517909003,
+      "grad_norm": 50593792.0,
+      "learning_rate": 1.3000000000000001e-05,
+      "loss": 2.0309,
+      "step": 130
+    },
+    {
+      "epoch": 0.43368828654404645,
+      "grad_norm": 942080.0,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.804,
+      "step": 140
+    },
+    {
+      "epoch": 0.46466602129719264,
+      "grad_norm": 93.5,
+      "learning_rate": 1.5e-05,
+      "loss": 1.9188,
+      "step": 150
+    },
+    {
+      "epoch": 0.49564375605033884,
+      "grad_norm": 138.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.7755,
+      "step": 160
+    },
+    {
+      "epoch": 0.526621490803485,
+      "grad_norm": 2310144.0,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 1.9404,
+      "step": 170
+    },
+    {
+      "epoch": 0.5575992255566312,
+      "grad_norm": 252928.0,
+      "learning_rate": 1.8e-05,
+      "loss": 1.9115,
+      "step": 180
+    },
+    {
+      "epoch": 0.5885769603097774,
+      "grad_norm": 36096.0,
+      "learning_rate": 1.9e-05,
+      "loss": 2.0781,
+      "step": 190
+    },
+    {
+      "epoch": 0.6195546950629235,
+      "grad_norm": 143.0,
+      "learning_rate": 2e-05,
+      "loss": 1.8338,
+      "step": 200
+    },
+    {
+      "epoch": 0.6505324298160697,
+      "grad_norm": 222208.0,
+      "learning_rate": 2.1e-05,
+      "loss": 1.9065,
+      "step": 210
+    },
+    {
+      "epoch": 0.6815101645692159,
+      "grad_norm": 11599872.0,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.8142,
+      "step": 220
+    },
+    {
+      "epoch": 0.712487899322362,
+      "grad_norm": 3568.0,
+      "learning_rate": 2.3000000000000003e-05,
+      "loss": 1.7811,
+      "step": 230
+    },
+    {
+      "epoch": 0.7434656340755083,
+      "grad_norm": 81.5,
+      "learning_rate": 2.4e-05,
+      "loss": 1.7512,
+      "step": 240
+    },
+    {
+      "epoch": 0.7744433688286544,
+      "grad_norm": 3696.0,
+      "learning_rate": 2.5e-05,
+      "loss": 1.8697,
+      "step": 250
+    },
+    {
+      "epoch": 0.8054211035818006,
+      "grad_norm": 63744.0,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.7677,
+      "step": 260
+    },
+    {
+      "epoch": 0.8363988383349468,
+      "grad_norm": 55.5,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 1.7307,
+      "step": 270
+    },
+    {
+      "epoch": 0.8673765730880929,
+      "grad_norm": 202.0,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.9074,
+      "step": 280
+    },
+    {
+      "epoch": 0.8983543078412392,
+      "grad_norm": 348.0,
+      "learning_rate": 2.9e-05,
+      "loss": 1.7037,
+      "step": 290
+    },
+    {
+      "epoch": 0.9293320425943853,
+      "grad_norm": 342.0,
+      "learning_rate": 3e-05,
+      "loss": 1.5886,
+      "step": 300
+    },
+    {
+      "epoch": 0.9603097773475314,
+      "grad_norm": 62.5,
+      "learning_rate": 3.1e-05,
+      "loss": 1.6942,
+      "step": 310
+    },
+    {
+      "epoch": 0.9912875121006777,
+      "grad_norm": 91.5,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.5326,
+      "step": 320
+    },
+    {
+      "epoch": 1.0222652468538238,
+      "grad_norm": 6560.0,
+      "learning_rate": 3.3e-05,
+      "loss": 1.6642,
+      "step": 330
+    },
+    {
+      "epoch": 1.05324298160697,
+      "grad_norm": 51.5,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.5624,
+      "step": 340
+    },
+    {
+      "epoch": 1.084220716360116,
+      "grad_norm": 1752.0,
+      "learning_rate": 3.5e-05,
+      "loss": 1.447,
+      "step": 350
+    },
+    {
+      "epoch": 1.1151984511132624,
+      "grad_norm": 48.25,
+      "learning_rate": 3.6e-05,
+      "loss": 1.6133,
+      "step": 360
+    },
+    {
+      "epoch": 1.1461761858664086,
+      "grad_norm": 52.25,
+      "learning_rate": 3.7e-05,
+      "loss": 1.4596,
+      "step": 370
+    },
+    {
+      "epoch": 1.1771539206195547,
+      "grad_norm": 12032.0,
+      "learning_rate": 3.8e-05,
+      "loss": 1.5244,
+      "step": 380
+    },
+    {
+      "epoch": 1.2081316553727008,
+      "grad_norm": 49.0,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 1.5972,
+      "step": 390
+    },
+    {
+      "epoch": 1.239109390125847,
+      "grad_norm": 39.25,
+      "learning_rate": 4e-05,
+      "loss": 1.2712,
+      "step": 400
+    },
+    {
+      "epoch": 1.2700871248789931,
+      "grad_norm": 1120.0,
+      "learning_rate": 4.1e-05,
+      "loss": 1.4318,
+      "step": 410
+    },
+    {
+      "epoch": 1.3010648596321395,
+      "grad_norm": 28160.0,
+      "learning_rate": 4.2e-05,
+      "loss": 1.3211,
+      "step": 420
+    },
+    {
+      "epoch": 1.3320425943852856,
+      "grad_norm": 12845056.0,
+      "learning_rate": 4.3e-05,
+      "loss": 1.4051,
+      "step": 430
+    },
+    {
+      "epoch": 1.3630203291384317,
+      "grad_norm": 6979584.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.2505,
+      "step": 440
+    },
+    {
+      "epoch": 1.3939980638915779,
+      "grad_norm": 27.75,
+      "learning_rate": 4.5e-05,
+      "loss": 1.1342,
+      "step": 450
+    },
+    {
+      "epoch": 1.424975798644724,
+      "grad_norm": 73.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.2342,
+      "step": 460
+    },
+    {
+      "epoch": 1.4559535333978704,
+      "grad_norm": 19.75,
+      "learning_rate": 4.7e-05,
+      "loss": 1.0688,
+      "step": 470
+    },
+    {
+      "epoch": 1.4869312681510165,
+      "grad_norm": 604.0,
+      "learning_rate": 4.8e-05,
+      "loss": 1.0641,
+      "step": 480
+    },
+    {
+      "epoch": 1.5179090029041626,
+      "grad_norm": 79.5,
+      "learning_rate": 4.9e-05,
+      "loss": 1.0869,
+      "step": 490
+    },
+    {
+      "epoch": 1.5488867376573088,
+      "grad_norm": 2144.0,
+      "learning_rate": 5e-05,
+      "loss": 1.0356,
+      "step": 500
+    },
+    {
+      "epoch": 1.5488867376573088,
+      "eval_loss": 0.21533620357513428,
+      "eval_runtime": 145.9664,
+      "eval_samples_per_second": 10.276,
+      "eval_steps_per_second": 2.569,
+      "step": 500
+    },
+    {
+      "epoch": 1.579864472410455,
+      "grad_norm": 125.0,
+      "learning_rate": 5.1000000000000006e-05,
+      "loss": 1.0417,
+      "step": 510
+    },
+    {
+      "epoch": 1.6108422071636013,
+      "grad_norm": 17.875,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 1.0518,
+      "step": 520
+    },
+    {
+      "epoch": 1.6418199419167472,
+      "grad_norm": 68.0,
+      "learning_rate": 5.300000000000001e-05,
+      "loss": 1.1404,
+      "step": 530
+    },
+    {
+      "epoch": 1.6727976766698935,
+      "grad_norm": 19.5,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.9938,
+      "step": 540
+    },
+    {
+      "epoch": 1.7037754114230397,
+      "grad_norm": 290.0,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9374,
+      "step": 550
+    },
+    {
+      "epoch": 1.7347531461761858,
+      "grad_norm": 58.5,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.0777,
+      "step": 560
+    },
+    {
+      "epoch": 1.7657308809293322,
+      "grad_norm": 422.0,
+      "learning_rate": 5.6999999999999996e-05,
+      "loss": 1.059,
+      "step": 570
+    },
+    {
+      "epoch": 1.796708615682478,
+      "grad_norm": 28.625,
+      "learning_rate": 5.8e-05,
+      "loss": 0.965,
+      "step": 580
+    },
+    {
+      "epoch": 1.8276863504356244,
+      "grad_norm": 43.75,
+      "learning_rate": 5.9e-05,
+      "loss": 0.9527,
+      "step": 590
+    },
+    {
+      "epoch": 1.8586640851887706,
+      "grad_norm": 12.75,
+      "learning_rate": 6e-05,
+      "loss": 0.8296,
+      "step": 600
+    },
+    {
+      "epoch": 1.8896418199419167,
+      "grad_norm": 16.0,
+      "learning_rate": 6.1e-05,
+      "loss": 0.933,
+      "step": 610
+    },
+    {
+      "epoch": 1.920619554695063,
+      "grad_norm": 11.875,
+      "learning_rate": 6.2e-05,
+      "loss": 0.8117,
+      "step": 620
+    },
+    {
+      "epoch": 1.951597289448209,
+      "grad_norm": 50.0,
+      "learning_rate": 6.3e-05,
+      "loss": 0.9475,
+      "step": 630
+    },
+    {
+      "epoch": 1.9825750242013553,
+      "grad_norm": 143.0,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.8241,
+      "step": 640
+    },
+    {
+      "epoch": 2.0135527589545013,
+      "grad_norm": 108.5,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 0.7861,
+      "step": 650
+    },
+    {
+      "epoch": 2.0445304937076476,
+      "grad_norm": 13184.0,
+      "learning_rate": 6.6e-05,
+      "loss": 0.8384,
+      "step": 660
+    },
+    {
+      "epoch": 2.075508228460794,
+      "grad_norm": 1736704.0,
+      "learning_rate": 6.7e-05,
+      "loss": 0.8896,
+      "step": 670
+    },
+    {
+      "epoch": 2.10648596321394,
+      "grad_norm": 48.75,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 0.9377,
+      "step": 680
+    },
+    {
+      "epoch": 2.1374636979670862,
+      "grad_norm": 2816.0,
+      "learning_rate": 6.9e-05,
+      "loss": 0.8322,
+      "step": 690
+    },
+    {
+      "epoch": 2.168441432720232,
+      "grad_norm": 3.125,
+      "learning_rate": 7e-05,
+      "loss": 0.8397,
+      "step": 700
+    },
+    {
+      "epoch": 2.1994191674733785,
+      "grad_norm": 8.6875,
+      "learning_rate": 7.1e-05,
+      "loss": 0.9265,
+      "step": 710
+    },
+    {
+      "epoch": 2.230396902226525,
+      "grad_norm": 9.875,
+      "learning_rate": 7.2e-05,
+      "loss": 0.8141,
+      "step": 720
+    },
+    {
+      "epoch": 2.261374636979671,
+      "grad_norm": 14.8125,
+      "learning_rate": 7.3e-05,
+      "loss": 0.7629,
+      "step": 730
+    },
+    {
+      "epoch": 2.292352371732817,
+      "grad_norm": 6.4375,
+      "learning_rate": 7.4e-05,
+      "loss": 0.85,
+      "step": 740
+    },
+    {
+      "epoch": 2.323330106485963,
+      "grad_norm": 3.796875,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.9116,
+      "step": 750
+    },
+    {
+      "epoch": 2.3543078412391094,
+      "grad_norm": 544768.0,
+      "learning_rate": 7.6e-05,
+      "loss": 0.8437,
+      "step": 760
+    },
+    {
+      "epoch": 2.3852855759922553,
+      "grad_norm": 117760.0,
+      "learning_rate": 7.7e-05,
+      "loss": 0.9072,
+      "step": 770
+    },
+    {
+      "epoch": 2.4162633107454017,
+      "grad_norm": 22.75,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.0168,
+      "step": 780
+    },
+    {
+      "epoch": 2.447241045498548,
+      "grad_norm": 2211840.0,
+      "learning_rate": 7.900000000000001e-05,
+      "loss": 1.1433,
+      "step": 790
+    },
+    {
+      "epoch": 2.478218780251694,
+      "grad_norm": 41.5,
+      "learning_rate": 8e-05,
+      "loss": 0.7485,
+      "step": 800
+    },
+    {
+      "epoch": 2.5091965150048403,
+      "grad_norm": 1810432.0,
+      "learning_rate": 8.1e-05,
+      "loss": 0.9516,
+      "step": 810
+    },
+    {
+      "epoch": 2.5401742497579862,
+      "grad_norm": 1081344.0,
+      "learning_rate": 8.2e-05,
+      "loss": 1.0742,
+      "step": 820
+    },
+    {
+      "epoch": 2.5711519845111326,
+      "grad_norm": 337641472.0,
+      "learning_rate": 8.3e-05,
+      "loss": 1.023,
+      "step": 830
+    },
+    {
+      "epoch": 2.602129719264279,
+      "grad_norm": 14548992.0,
+      "learning_rate": 8.4e-05,
+      "loss": 1.185,
+      "step": 840
+    },
+    {
+      "epoch": 2.633107454017425,
+      "grad_norm": 4.71875,
+      "learning_rate": 8.5e-05,
+      "loss": 1.3584,
+      "step": 850
+    },
+    {
+      "epoch": 2.664085188770571,
+      "grad_norm": 618496.0,
+      "learning_rate": 8.6e-05,
+      "loss": 0.9947,
+      "step": 860
+    },
+    {
+      "epoch": 2.695062923523717,
+      "grad_norm": 22151168.0,
+      "learning_rate": 8.7e-05,
+      "loss": 1.0296,
+      "step": 870
+    },
+    {
+      "epoch": 2.7260406582768635,
+      "grad_norm": 77824.0,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 0.8889,
+      "step": 880
+    },
+    {
+      "epoch": 2.75701839303001,
+      "grad_norm": 2.640625,
+      "learning_rate": 8.900000000000001e-05,
+      "loss": 0.733,
+      "step": 890
+    },
+    {
+      "epoch": 2.7879961277831558,
+      "grad_norm": 18.625,
+      "learning_rate": 9e-05,
+      "loss": 0.7786,
+      "step": 900
+    },
+    {
+      "epoch": 2.818973862536302,
+      "grad_norm": 9.0625,
+      "learning_rate": 9.1e-05,
+      "loss": 0.7221,
+      "step": 910
+    },
+    {
+      "epoch": 2.849951597289448,
+      "grad_norm": 10.4375,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 0.6316,
+      "step": 920
+    },
+    {
+      "epoch": 2.8809293320425944,
+      "grad_norm": 4.84375,
+      "learning_rate": 9.300000000000001e-05,
+      "loss": 0.7015,
+      "step": 930
+    },
+    {
+      "epoch": 2.9119070667957407,
+      "grad_norm": 4.1875,
+      "learning_rate": 9.4e-05,
+      "loss": 0.7161,
+      "step": 940
+    },
+    {
+      "epoch": 2.9428848015488867,
+      "grad_norm": 2.8125,
+      "learning_rate": 9.5e-05,
+      "loss": 0.7325,
+      "step": 950
+    },
+    {
+      "epoch": 2.973862536302033,
+      "grad_norm": 5.90625,
+      "learning_rate": 9.6e-05,
+      "loss": 0.6447,
+      "step": 960
+    },
+    {
+      "epoch": 3.004840271055179,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.7e-05,
+      "loss": 0.7079,
+      "step": 970
+    },
+    {
+      "epoch": 3.0358180058083253,
+      "grad_norm": 3.8125,
+      "learning_rate": 9.8e-05,
+      "loss": 0.6075,
+      "step": 980
+    },
+    {
+      "epoch": 3.0667957405614716,
+      "grad_norm": 1.9140625,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 0.697,
+      "step": 990
+    },
+    {
+      "epoch": 3.0977734753146176,
+      "grad_norm": 1.140625,
+      "learning_rate": 0.0001,
+      "loss": 0.7175,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0977734753146176,
+      "eval_loss": 0.1426076889038086,
+      "eval_runtime": 146.0018,
+      "eval_samples_per_second": 10.274,
+      "eval_steps_per_second": 2.568,
+      "step": 1000
+    },
+    {
+      "epoch": 3.128751210067764,
+      "grad_norm": 1.6328125,
+      "learning_rate": 9.988452655889145e-05,
+      "loss": 0.5774,
+      "step": 1010
+    },
+    {
+      "epoch": 3.15972894482091,
+      "grad_norm": 24.125,
+      "learning_rate": 9.976905311778292e-05,
+      "loss": 0.5575,
+      "step": 1020
+    },
+    {
+      "epoch": 3.190706679574056,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.965357967667437e-05,
+      "loss": 0.5609,
+      "step": 1030
+    },
+    {
+      "epoch": 3.2216844143272025,
+      "grad_norm": 0.6015625,
+      "learning_rate": 9.953810623556582e-05,
+      "loss": 0.5562,
+      "step": 1040
+    },
+    {
+      "epoch": 3.2526621490803485,
+      "grad_norm": 37748736.0,
+      "learning_rate": 9.942263279445728e-05,
+      "loss": 0.6574,
+      "step": 1050
+    },
+    {
+      "epoch": 3.283639883833495,
+      "grad_norm": 0.66015625,
+      "learning_rate": 9.930715935334873e-05,
+      "loss": 0.5348,
+      "step": 1060
+    },
+    {
+      "epoch": 3.3146176185866407,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.919168591224018e-05,
+      "loss": 0.5574,
+      "step": 1070
+    },
+    {
+      "epoch": 3.345595353339787,
+      "grad_norm": 0.9453125,
+      "learning_rate": 9.907621247113164e-05,
+      "loss": 0.5546,
+      "step": 1080
+    },
+    {
+      "epoch": 3.3765730880929334,
+      "grad_norm": 0.49609375,
+      "learning_rate": 9.896073903002309e-05,
+      "loss": 0.4716,
+      "step": 1090
+    },
+    {
+      "epoch": 3.4075508228460794,
+      "grad_norm": 1.1015625,
+      "learning_rate": 9.884526558891456e-05,
+      "loss": 0.4992,
+      "step": 1100
+    },
+    {
+      "epoch": 3.4385285575992257,
+      "grad_norm": 1.9609375,
+      "learning_rate": 9.8729792147806e-05,
+      "loss": 0.4814,
+      "step": 1110
+    },
+    {
+      "epoch": 3.4695062923523716,
+      "grad_norm": 0.81640625,
+      "learning_rate": 9.861431870669747e-05,
+      "loss": 0.5451,
+      "step": 1120
+    },
+    {
+      "epoch": 3.500484027105518,
+      "grad_norm": 1.3046875,
+      "learning_rate": 9.849884526558892e-05,
+      "loss": 0.5436,
+      "step": 1130
+    },
+    {
+      "epoch": 3.5314617618586643,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.838337182448038e-05,
+      "loss": 0.5237,
+      "step": 1140
+    },
+    {
+      "epoch": 3.5624394966118103,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.826789838337183e-05,
+      "loss": 0.4595,
+      "step": 1150
+    },
+    {
+      "epoch": 3.593417231364956,
+      "grad_norm": 3.015625,
+      "learning_rate": 9.81524249422633e-05,
+      "loss": 0.5892,
+      "step": 1160
+    },
+    {
+      "epoch": 3.6243949661181025,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.803695150115474e-05,
+      "loss": 0.4804,
+      "step": 1170
+    },
+    {
+      "epoch": 3.655372700871249,
+      "grad_norm": 0.484375,
+      "learning_rate": 9.79214780600462e-05,
+      "loss": 0.471,
+      "step": 1180
+    },
+    {
+      "epoch": 3.6863504356243952,
+      "grad_norm": 0.6171875,
+      "learning_rate": 9.780600461893766e-05,
+      "loss": 0.5353,
+      "step": 1190
+    },
+    {
+      "epoch": 3.717328170377541,
+      "grad_norm": 1.6015625,
+      "learning_rate": 9.76905311778291e-05,
+      "loss": 0.5112,
+      "step": 1200
+    },
+    {
+      "epoch": 3.748305905130687,
+      "grad_norm": 28.25,
+      "learning_rate": 9.757505773672056e-05,
+      "loss": 0.5225,
+      "step": 1210
+    },
+    {
+      "epoch": 3.7792836398838334,
+      "grad_norm": 0.98828125,
+      "learning_rate": 9.745958429561202e-05,
+      "loss": 0.4663,
+      "step": 1220
+    },
+    {
+      "epoch": 3.81026137463698,
+      "grad_norm": 0.6640625,
+      "learning_rate": 9.734411085450347e-05,
+      "loss": 0.5263,
+      "step": 1230
+    },
+    {
+      "epoch": 3.8412391093901257,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.722863741339492e-05,
+      "loss": 0.5353,
+      "step": 1240
+    },
+    {
+      "epoch": 3.872216844143272,
+      "grad_norm": 0.28515625,
+      "learning_rate": 9.711316397228638e-05,
+      "loss": 0.4615,
+      "step": 1250
+    },
+    {
+      "epoch": 3.903194578896418,
+      "grad_norm": 0.515625,
+      "learning_rate": 9.699769053117783e-05,
+      "loss": 0.4887,
+      "step": 1260
+    },
+    {
+      "epoch": 3.9341723136495643,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.68822170900693e-05,
+      "loss": 0.4658,
+      "step": 1270
+    },
+    {
+      "epoch": 3.9651500484027107,
+      "grad_norm": 0.455078125,
+      "learning_rate": 9.676674364896074e-05,
+      "loss": 0.4914,
+      "step": 1280
+    },
+    {
+      "epoch": 3.9961277831558566,
+      "grad_norm": 0.67578125,
+      "learning_rate": 9.66512702078522e-05,
+      "loss": 0.5355,
+      "step": 1290
+    },
+    {
+      "epoch": 4.0271055179090025,
+      "grad_norm": 0.5390625,
+      "learning_rate": 9.653579676674366e-05,
+      "loss": 0.5068,
+      "step": 1300
+    },
+    {
+      "epoch": 4.058083252662149,
+      "grad_norm": 0.71875,
+      "learning_rate": 9.64203233256351e-05,
+      "loss": 0.4409,
+      "step": 1310
+    },
+    {
+      "epoch": 4.089060987415295,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.630484988452656e-05,
+      "loss": 0.4788,
+      "step": 1320
+    },
+    {
+      "epoch": 4.120038722168442,
+      "grad_norm": 0.443359375,
+      "learning_rate": 9.618937644341802e-05,
+      "loss": 0.4901,
+      "step": 1330
+    },
+    {
+      "epoch": 4.151016456921588,
+      "grad_norm": 0.33203125,
+      "learning_rate": 9.607390300230947e-05,
+      "loss": 0.4119,
+      "step": 1340
+    },
+    {
+      "epoch": 4.181994191674733,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.595842956120092e-05,
+      "loss": 0.4597,
+      "step": 1350
+    },
+    {
+      "epoch": 4.21297192642788,
+      "grad_norm": 0.953125,
+      "learning_rate": 9.584295612009238e-05,
+      "loss": 0.5134,
+      "step": 1360
+    },
+    {
+      "epoch": 4.243949661181026,
+      "grad_norm": 0.73046875,
+      "learning_rate": 9.572748267898383e-05,
+      "loss": 0.4222,
+      "step": 1370
+    },
+    {
+      "epoch": 4.2749273959341725,
+      "grad_norm": 0.412109375,
+      "learning_rate": 9.56120092378753e-05,
+      "loss": 0.4851,
+      "step": 1380
+    },
+    {
+      "epoch": 4.305905130687319,
+      "grad_norm": 0.7578125,
+      "learning_rate": 9.549653579676674e-05,
+      "loss": 0.505,
+      "step": 1390
+    },
+    {
+      "epoch": 4.336882865440464,
+      "grad_norm": 0.453125,
+      "learning_rate": 9.538106235565821e-05,
+      "loss": 0.4439,
+      "step": 1400
+    },
+    {
+      "epoch": 4.367860600193611,
+      "grad_norm": 0.609375,
+      "learning_rate": 9.526558891454966e-05,
+      "loss": 0.4311,
+      "step": 1410
+    },
+    {
+      "epoch": 4.398838334946757,
+      "grad_norm": 0.302734375,
+      "learning_rate": 9.515011547344112e-05,
+      "loss": 0.4369,
+      "step": 1420
+    },
+    {
+      "epoch": 4.429816069699903,
+      "grad_norm": 0.30859375,
+      "learning_rate": 9.503464203233257e-05,
+      "loss": 0.4863,
+      "step": 1430
+    },
+    {
+      "epoch": 4.46079380445305,
+      "grad_norm": 0.43359375,
+      "learning_rate": 9.491916859122403e-05,
+      "loss": 0.4471,
+      "step": 1440
+    },
+    {
+      "epoch": 4.491771539206195,
+      "grad_norm": 0.345703125,
+      "learning_rate": 9.480369515011548e-05,
+      "loss": 0.4816,
+      "step": 1450
+    },
+    {
+      "epoch": 4.522749273959342,
+      "grad_norm": 0.28125,
+      "learning_rate": 9.468822170900693e-05,
+      "loss": 0.4363,
+      "step": 1460
+    },
+    {
+      "epoch": 4.553727008712488,
+      "grad_norm": 0.5390625,
+      "learning_rate": 9.45727482678984e-05,
+      "loss": 0.414,
+      "step": 1470
+    },
+    {
+      "epoch": 4.584704743465634,
+      "grad_norm": 0.29296875,
+      "learning_rate": 9.445727482678985e-05,
+      "loss": 0.4318,
+      "step": 1480
+    },
+    {
+      "epoch": 4.615682478218781,
+      "grad_norm": 0.298828125,
+      "learning_rate": 9.43418013856813e-05,
+      "loss": 0.456,
+      "step": 1490
+    },
+    {
+      "epoch": 4.646660212971926,
+      "grad_norm": 0.4375,
+      "learning_rate": 9.422632794457276e-05,
+      "loss": 0.4453,
+      "step": 1500
+    },
+    {
+      "epoch": 4.646660212971926,
+      "eval_loss": 0.10397772490978241,
+      "eval_runtime": 145.9588,
+      "eval_samples_per_second": 10.277,
+      "eval_steps_per_second": 2.569,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 9660,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6419762303223726e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500-new/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b22490c1bbafc1074f2feb7b3164d8f91a3f6337a482725dc516362253bc4a
+size 5240