diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..3e03d5f619baf8592fb936d63d05366f9304f7b2 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "[PAD]": 32000 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..68b6797e7efe7d14cc02a8cc3e4577f3baa76173 --- /dev/null +++ b/config.json @@ -0,0 +1,23 @@ +{ + "_name_or_path": "./gpt4-x-alpaca/", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 0, + "eos_token_id": 1, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_sequence_length": 2048, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "pad_token_id": -1, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.27.0.dev0", + "use_cache": true, + "vocab_size": 32001 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..92540f6079cb3e94bc001985d1eb8c408255d749 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.27.0.dev0" +} diff --git a/pytorch_model-00001-of-00082.bin b/pytorch_model-00001-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..82c9a9aeaac32c4dd6529c75db190def3456066d --- /dev/null +++ b/pytorch_model-00001-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68d40e3d745af92c526aadb303dcc07f1eefdbcef1a9f218842b61b3696e1f10 +size 380120315 diff --git a/pytorch_model-00002-of-00082.bin b/pytorch_model-00002-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d8a0b12f45df849312a1ec41574c865ee44d27ad --- /dev/null +++ b/pytorch_model-00002-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47844f9ea2d2e3a3270e0366d4b031067bba31fdb0f8d6bc58b5ee7dc86b2d91 +size 298846638 diff --git a/pytorch_model-00003-of-00082.bin b/pytorch_model-00003-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef9340cc5f4231e6868ff48ec956c8308abde1b6 --- /dev/null +++ b/pytorch_model-00003-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac623fabb64faa06b7f4cdb129ead6d5d0d1bddaedf5fa7614e97c5b0ee2839d +size 387996095 diff --git a/pytorch_model-00004-of-00082.bin b/pytorch_model-00004-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..3fdd8c4ffcd9ea998546f543b66bcd75bab7a806 --- /dev/null +++ b/pytorch_model-00004-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd9eaca3f678a80c5d2dc90cc12ec3008fa5437fa13b5cd1196c9598e3daeaff +size 387975598 diff --git a/pytorch_model-00005-of-00082.bin b/pytorch_model-00005-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d3586bd5685e975c22cd003f1add0179116a58ea --- /dev/null +++ b/pytorch_model-00005-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7899289297d73ef6829218f522ce9ecd737113d44772636a85fc7d32bbf52b8 +size 351296801 diff --git a/pytorch_model-00006-of-00082.bin b/pytorch_model-00006-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..8f83cfd64604de6cb547702697f683555bd52ea8 --- /dev/null +++ b/pytorch_model-00006-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f29b287fe55c11181d94e6f7482f1ff21cb029d1fe15df7bf3390a5ec1cd75 +size 283116795 diff --git a/pytorch_model-00007-of-00082.bin b/pytorch_model-00007-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..8902d92c65d8259af078d696e792797c2f28f1a9 --- /dev/null +++ b/pytorch_model-00007-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:728ddf7d379775e59e7ecb4003ce51281c116ac5ac47fac6adbd42e102a9963b +size 351296801 diff --git a/pytorch_model-00008-of-00082.bin b/pytorch_model-00008-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c51c8548a6128303d77c5fe934eebbbeaca2746 --- /dev/null +++ b/pytorch_model-00008-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:493a72db0e07051428ffad790ef66a5df0eea30f64d1d33fb6a7cd03837b6f16 +size 283116795 diff --git a/pytorch_model-00009-of-00082.bin b/pytorch_model-00009-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..47a01a9bd1ef8d1a81e949c0993585cbb9e8d03c --- /dev/null +++ b/pytorch_model-00009-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faa8a4c3fec7ca0cb3cd388e3b9986bc7c27f76d7781727ef7b32ea757197b7a +size 351296801 diff --git a/pytorch_model-00010-of-00082.bin b/pytorch_model-00010-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..74ae3344cd33d7f41c5494486117dc16d1154d31 --- /dev/null +++ b/pytorch_model-00010-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7880df8cac8a85884c201dc74ba1aec4033d65f2d303ca6a8ce84f6c879d997f +size 283116795 diff --git a/pytorch_model-00011-of-00082.bin b/pytorch_model-00011-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..ba77f3a36e85d6554335cbe5555189a71d368e97 --- /dev/null +++ b/pytorch_model-00011-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c1f2aef611771e6945c87f246853c75be8b811515d33b298885ff3f3fa3e597 +size 351296801 diff --git a/pytorch_model-00012-of-00082.bin b/pytorch_model-00012-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..15f5a01054de3723a63f7c0a8ca6e5d4661bb560 --- /dev/null +++ b/pytorch_model-00012-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b71da7d88220eab19a65467ab2e7bcc5a7540eb886a75ae2c0cb435981d643d3 +size 283116795 diff --git a/pytorch_model-00013-of-00082.bin b/pytorch_model-00013-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..084286ee7ac95624b0d77673b31077c344b38366 --- /dev/null +++ b/pytorch_model-00013-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73106eb1439912b019cd41e36b29c93323a85341a3edd0be7e44ce7ec636b002 +size 351296801 diff --git a/pytorch_model-00014-of-00082.bin b/pytorch_model-00014-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..16c35a0dbcc7dc1e56912a7fd0f45bcdf4ba11e5 --- /dev/null +++ b/pytorch_model-00014-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37c66606b85d6ae991b5c8cc288e64d37ea6e1933cd559a631b6eb31e61f1c0e +size 283116795 diff --git a/pytorch_model-00015-of-00082.bin b/pytorch_model-00015-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..a7c910cc29a4b3a21f474ae2939a102ee7c09b19 --- /dev/null +++ b/pytorch_model-00015-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d1f689e8cb63989bee9b14f541a6ff0d6609b05b5f20faa8a2173efb705b70d +size 351296801 diff --git a/pytorch_model-00016-of-00082.bin b/pytorch_model-00016-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d3ed698d1ca6e8c0a92183c7cbc6501ab06641b5 --- /dev/null +++ b/pytorch_model-00016-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d3f0ce6c6cb314c0f76087c4310c9033d2b0f76ff0e93d9bfdfb5ff11a3ace2 +size 283116795 diff --git a/pytorch_model-00017-of-00082.bin b/pytorch_model-00017-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..c205905edc4a0a1e3d25c00ab6d0580fe8201246 --- /dev/null +++ b/pytorch_model-00017-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003a989eb254cb289cc02054abf26389d6c27e3c61c9fea68795ab79009bec4b +size 351296801 diff --git a/pytorch_model-00018-of-00082.bin b/pytorch_model-00018-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..095559fc84cec3621bb1a990ee27ddc7b853082c --- /dev/null +++ b/pytorch_model-00018-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60c7da489748e41c59cdaefd367a34e041ffedc1f8d6237c345ed066d9233f2 +size 283116795 diff --git a/pytorch_model-00019-of-00082.bin b/pytorch_model-00019-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..066add950f3a7277a632d28cfeae59dc0a993072 --- /dev/null +++ b/pytorch_model-00019-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbe020bfb2cba772b8a1b7748ad881c1b6ec7e87a71a88c84c2338f8c407941e +size 351296801 diff --git a/pytorch_model-00020-of-00082.bin b/pytorch_model-00020-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..109711aa6c61ceb845085523bf749b5a58c08e38 --- /dev/null +++ b/pytorch_model-00020-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4342abfb07166124bebf76fc29c9cd31144d0d558baab6641e1438586eefcb84 +size 283116795 diff --git a/pytorch_model-00021-of-00082.bin b/pytorch_model-00021-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..51cefb90794e79fcca118f017b2827c176a4fbb4 --- /dev/null +++ b/pytorch_model-00021-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5600074ec967f706dd4e16da360dab25e220f672474286a1c40a0933833f1e4 +size 351296865 diff --git a/pytorch_model-00022-of-00082.bin b/pytorch_model-00022-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..8682c4d9092feecf02e9a916721e7199dfaad55d --- /dev/null +++ b/pytorch_model-00022-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:937fff7265785ba9f028d119c704b2d67673e021ac4e71a5dcef25683656d0e5 +size 283116795 diff --git a/pytorch_model-00023-of-00082.bin b/pytorch_model-00023-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..19b4633f54c239e9caa8ad68f9657938ca13dcb9 --- /dev/null +++ b/pytorch_model-00023-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7a3a2d512d576fd2514022ffa46d1cb37f87edfbba54bcbea77513ea4e9200 +size 351296865 diff --git a/pytorch_model-00024-of-00082.bin b/pytorch_model-00024-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..a4965600687eda1ff537fd39665e329883539c76 --- /dev/null +++ b/pytorch_model-00024-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:750b3fa510a0a8c88b9f0bc9359fc389365f287610d666838e0a1a9a88a09a89 +size 283116795 diff --git a/pytorch_model-00025-of-00082.bin b/pytorch_model-00025-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..611fdd3889e09161592ba7f53cb5c17633f91db4 --- /dev/null +++ b/pytorch_model-00025-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa2c42685c2c3e3861f93147683b04ccfdf85e254335378e4aca8ef5a1f4d95e +size 351296865 diff --git a/pytorch_model-00026-of-00082.bin b/pytorch_model-00026-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..b89575370bd0b73c2b0225c05242a68e8a869e2e --- /dev/null +++ b/pytorch_model-00026-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f7eab05dc58753189c95db47ee3b7fd3d61bb502c61906fea5c2a53f66c1265 +size 283116795 diff --git a/pytorch_model-00027-of-00082.bin b/pytorch_model-00027-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..4d800e518cf44b4a0001fbb77e357d26bc16682f --- /dev/null +++ b/pytorch_model-00027-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1aea7410ecfd7572d227b026d953b0bad360f1f787ef1a28eda85d5df9451a5 +size 351296865 diff --git a/pytorch_model-00028-of-00082.bin b/pytorch_model-00028-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1344d75f4456f0271b072b41fb2482f761b632f --- /dev/null +++ b/pytorch_model-00028-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d297089fe3775c512d656e591df7fc48545dede417b28449e40271220a1bfc +size 283116795 diff --git a/pytorch_model-00029-of-00082.bin b/pytorch_model-00029-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..0f47065db3d2980943715129e2ee78a8d758f12a --- /dev/null +++ b/pytorch_model-00029-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eedc665af44613b2cb2b5e0dc82e24de8d2dbba135f6cd2eb65dfee033590676 +size 351296865 diff --git a/pytorch_model-00030-of-00082.bin b/pytorch_model-00030-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..984dff1f2cd0f234fa2c65353decdfcae0b23f5c --- /dev/null +++ b/pytorch_model-00030-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c10b45a37b14b10e4c63dd9788a7a6c9c1982c2de26a8280576ea0207103eb +size 283116795 diff --git a/pytorch_model-00031-of-00082.bin b/pytorch_model-00031-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..656d23288de275d16d6005928455762e59b28409 --- /dev/null +++ b/pytorch_model-00031-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7800556b7eb414324b2bbbb0a60a3e7e1a81de7724935ac847abf0c5404ebac1 +size 351296865 diff --git a/pytorch_model-00032-of-00082.bin b/pytorch_model-00032-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..08618259326f00690ca9a0ddbec424c5f7a498d7 --- /dev/null +++ b/pytorch_model-00032-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80f019a690caed250ea3abb13403cfcc4487bbd75b04a705a5c95fca71ab43c1 +size 283116795 diff --git a/pytorch_model-00033-of-00082.bin b/pytorch_model-00033-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..fe74ac014f90020f46fca331069d2925c841e8e8 --- /dev/null +++ b/pytorch_model-00033-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f424730ab7e28ab2753d155a0d941e4f07ba6917fdb12c1e1be4b243663f65dc +size 351296865 diff --git a/pytorch_model-00034-of-00082.bin b/pytorch_model-00034-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..f365d063186394ea26a731b41a6b33f4fd765e93 --- /dev/null +++ b/pytorch_model-00034-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0fd85a2528ea5c8c6adf8e2b3fd4461b19a8f2119e28d9dc5a82e75acd4c938 +size 283116795 diff --git a/pytorch_model-00035-of-00082.bin b/pytorch_model-00035-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..425c91ab88762c60375cdecf3f6f4b7325f46d0e --- /dev/null +++ b/pytorch_model-00035-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a00a872970e0cfafda8f01478f91ca820e0eb0ff6ceb07ca5151ed41d826c7 +size 351296865 diff --git a/pytorch_model-00036-of-00082.bin b/pytorch_model-00036-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..0f057b0cbca1433bfdc20ac4864cafdf4d6c5c66 --- /dev/null +++ b/pytorch_model-00036-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dfb93d9d514600aebdf5bc19b98417335ad8f36133c1a69c90c151f80e07a86 +size 283116795 diff --git a/pytorch_model-00037-of-00082.bin b/pytorch_model-00037-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..3dc9be23e2b18503e1403b9d3fa2426e0de9f47f --- /dev/null +++ b/pytorch_model-00037-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bd67fe4fb1344f39ad5be3d5145a424eb39d8c26b18b49be64e428cfebe1ce4 +size 351296865 diff --git a/pytorch_model-00038-of-00082.bin b/pytorch_model-00038-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..eec272cba1fc5307691ab4d1edfe2e4a33a8354d --- /dev/null +++ b/pytorch_model-00038-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:887a9a59959306b34e2a5b296924da1924ecaef721e5607e0fedd440227365e2 +size 283116795 diff --git a/pytorch_model-00039-of-00082.bin b/pytorch_model-00039-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..3b5c55f81801e98365ac3d8c62bd4476d2ddc752 --- /dev/null +++ b/pytorch_model-00039-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfb7b2e5bcfe6c3ced0d8fa388155b3ccbb97dd540c8cfb05eaf82f34448fda7 +size 351296865 diff --git a/pytorch_model-00040-of-00082.bin b/pytorch_model-00040-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..2bd56b136c11192934b6c4f0e74218c51308d8c5 --- /dev/null +++ b/pytorch_model-00040-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a97e7efd42e8f367c6bb57f8567d5ed945e553ad3060f08cdb1103d962197d +size 283116795 diff --git a/pytorch_model-00041-of-00082.bin b/pytorch_model-00041-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..e03462304122f8639e39665749a193fa85ee9262 --- /dev/null +++ b/pytorch_model-00041-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ac10997ce3e038359406501c8806c5676b651f26df226c7ed9f35a8f2c9061 +size 351296865 diff --git a/pytorch_model-00042-of-00082.bin b/pytorch_model-00042-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..667a52ed90f12627c90682ddd7929fc27023d561 --- /dev/null +++ b/pytorch_model-00042-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b734573bc7df85a70f56af0b1408d6a51bc3dd388b26d6de8be766188484023f +size 283116795 diff --git a/pytorch_model-00043-of-00082.bin b/pytorch_model-00043-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..dc2c49af6fd59721cd1b1ec180bc38d90f08dbe5 --- /dev/null +++ b/pytorch_model-00043-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aceb85212e96cd1488031855cd34dce9049163f6574422b691dcfffda004dbe +size 351296865 diff --git a/pytorch_model-00044-of-00082.bin b/pytorch_model-00044-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..53c917690423274c89d08de8328c5e702b8bdff8 --- /dev/null +++ b/pytorch_model-00044-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:593fe18b227517554d4089379492d634f2b3fc757f11deb42eff2790990d4dc4 +size 283116795 diff --git a/pytorch_model-00045-of-00082.bin b/pytorch_model-00045-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..a7d0f6f0f49107ad03966cdb8e21f0db4d1bd9f2 --- /dev/null +++ b/pytorch_model-00045-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4f2cff79a69f1a7cbc3f50c2b747ff9bca3ee7560e01d53d89fb233acdd1f53 +size 351296865 diff --git a/pytorch_model-00046-of-00082.bin b/pytorch_model-00046-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..29a42b228131f53b8b96c61c5743f8d61a50f658 --- /dev/null +++ b/pytorch_model-00046-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdfbdfef83a1177daa420679ccac0c3de8bf53d0ac276a58150fe0ee26888078 +size 283116795 diff --git a/pytorch_model-00047-of-00082.bin b/pytorch_model-00047-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..933b2aff410a1e0d23a31daed07bc2a888151236 --- /dev/null +++ b/pytorch_model-00047-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f1f1bed8e3467c9b316d8c4171d072ea32869d2245cd80e92cfebeeba2b146 +size 351296865 diff --git a/pytorch_model-00048-of-00082.bin b/pytorch_model-00048-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..79edb901b8386b5bd91949d6f64f2be5255d628e --- /dev/null +++ b/pytorch_model-00048-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce018860d6d4bc40344e8b4456918d535dbaba99d23ce62c8cb29e609ddbe594 +size 283116795 diff --git a/pytorch_model-00049-of-00082.bin b/pytorch_model-00049-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d838b95c916641a53bb35a1912ace34d4b066228 --- /dev/null +++ b/pytorch_model-00049-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6769009413c22bc8a1e7c9c8fead4f267b98768d68a56d86958bee120a03196e +size 351296865 diff --git a/pytorch_model-00050-of-00082.bin b/pytorch_model-00050-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..1f0a19f9b3daa1a5bc20310b7f0093eb1811b611 --- /dev/null +++ b/pytorch_model-00050-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:915cfe76125cb65887dbc987f8e76cbaf31704b98efe94d83d29af0fd37dc56c +size 283116795 diff --git a/pytorch_model-00051-of-00082.bin b/pytorch_model-00051-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..05fa525a825d9c9c859fdb3eeb19578488a59995 --- /dev/null +++ b/pytorch_model-00051-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b9881912273206d2f5f9bedf1b53c42c9f3d3e85dd1fda4a8f38974c2235c8 +size 351296865 diff --git a/pytorch_model-00052-of-00082.bin b/pytorch_model-00052-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..acf71d39d5ebf8904bcaca41edd9000f3ab0928c --- /dev/null +++ b/pytorch_model-00052-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30b8b6cbc9cf3c86340ad1a0f5ec9982f5b22b89b88bc7e1dd9324bd15e214f7 +size 283116795 diff --git a/pytorch_model-00053-of-00082.bin b/pytorch_model-00053-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a359f8340d1b6cef079f3da759bffc8185059ca --- /dev/null +++ b/pytorch_model-00053-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78620cddbd44c40422196d0889c011735e59b9c7f2d2307dbf5f757f4a95c0e9 +size 351296865 diff --git a/pytorch_model-00054-of-00082.bin b/pytorch_model-00054-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..87da8880db6101e82db6cd5868a6bb3e32cfbbe1 --- /dev/null +++ b/pytorch_model-00054-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbba8eb8117289a65247415c5cb80c844bb3073653a81f2da609c4a69ca408a3 +size 283116795 diff --git a/pytorch_model-00055-of-00082.bin b/pytorch_model-00055-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..914cf90cf86bc54e69734799f6558956444b664d --- /dev/null +++ b/pytorch_model-00055-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4af88aed72e4c38a92c786e39c5fb9c7583e2e33259904fcc959d8096d1a4c0 +size 351296865 diff --git a/pytorch_model-00056-of-00082.bin b/pytorch_model-00056-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..96916a9214906c70b5382f741207e197b895411d --- /dev/null +++ b/pytorch_model-00056-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b51d868412e3ddb41bcff8eda3286fea7e540334ce67ce9e18a3b2fadd77bc8 +size 283116795 diff --git a/pytorch_model-00057-of-00082.bin b/pytorch_model-00057-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..46b3d9cfdd326cc12ba9391d5cb7fd76e1967c1e --- /dev/null +++ b/pytorch_model-00057-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d9ec9bb5b228dc4cb1b0f383908e2260805cc8c035ab0b654026fe5d98b8f9 +size 351296865 diff --git a/pytorch_model-00058-of-00082.bin b/pytorch_model-00058-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..37a0291dd5c60642ca2e618c1267a86cd88f1181 --- /dev/null +++ b/pytorch_model-00058-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da14d3f915b7294592d2ffda939335a0695db13aebb26093c477a9e9f2889dd +size 283116795 diff --git a/pytorch_model-00059-of-00082.bin b/pytorch_model-00059-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..b51d7e18aef41bbf30f9409815c39473607dba57 --- /dev/null +++ b/pytorch_model-00059-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae512193cb01b89343d6f5ac0bd3a741bf5e3595eaf8aba38198b50ca07025ab +size 351296865 diff --git a/pytorch_model-00060-of-00082.bin b/pytorch_model-00060-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..bd00beb4707e1cdead2b6c573a5dbb0ad20705b5 --- /dev/null +++ b/pytorch_model-00060-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af986bbba51c998f231eea3f0f5db1721ff0b82d1acc9eee50365dd616ce0955 +size 283116795 diff --git a/pytorch_model-00061-of-00082.bin b/pytorch_model-00061-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..b70ee414da6b40c2ddf8fbe6a3349f4cf52ddae3 --- /dev/null +++ b/pytorch_model-00061-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d7ce585f1d942f912c65c392259f0bc2a3c2c96d9bed933b6036562f225a5c +size 351296865 diff --git a/pytorch_model-00062-of-00082.bin b/pytorch_model-00062-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..fcb255054a39604142dad344a7154c6875d6b478 --- /dev/null +++ b/pytorch_model-00062-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc4075b05e87595a58c509358ec4dbcc45db86a8c5d5710f75a0cd2353182ec1 +size 283116795 diff --git a/pytorch_model-00063-of-00082.bin b/pytorch_model-00063-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..7476d9e8db0305af1452f8aa683e019fd9c97c70 --- /dev/null +++ b/pytorch_model-00063-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7006505f13559aa1d2e2971a61e7a73bdc81b2eb598a1444a98dceaec7ed2d3 +size 351296865 diff --git a/pytorch_model-00064-of-00082.bin b/pytorch_model-00064-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..736621858ec7507183eb951e35cdf59411ed8a39 --- /dev/null +++ b/pytorch_model-00064-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ad7da460437e0909920b0744cf078ba0b4381c65d831816a804edafeb432c3 +size 283116795 diff --git a/pytorch_model-00065-of-00082.bin b/pytorch_model-00065-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..e9827bc16fb813706dc9e1753b120a91360e4879 --- /dev/null +++ b/pytorch_model-00065-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ef521bba8f7fb3ef0b546eb94e33a4537628bbb5ada8eb137f60471c452a54 +size 351296865 diff --git a/pytorch_model-00066-of-00082.bin b/pytorch_model-00066-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d56c1facc0371cc961ba122c6dbffabaa3d08fd1 --- /dev/null +++ b/pytorch_model-00066-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91cfa6c35a06c1ff77a8a2fd55c3e697188bbeb83204fc51dd5305035de921aa +size 283116795 diff --git a/pytorch_model-00067-of-00082.bin b/pytorch_model-00067-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..609d5e92b3a958a38c0461761f76e36ba2b39067 --- /dev/null +++ b/pytorch_model-00067-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e006a5d0b381af501d34121f1dd5ce6bec9dc98a3673ddc2981d0e9e1c048ff6 +size 351296865 diff --git a/pytorch_model-00068-of-00082.bin b/pytorch_model-00068-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..31b6a1fa7c952979093fcff5c5d59b4cc1223b33 --- /dev/null +++ b/pytorch_model-00068-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d72f83e1ca852aed206b6959d74052b51545692a42531d3f25169f05b07b77a7 +size 283116795 diff --git a/pytorch_model-00069-of-00082.bin b/pytorch_model-00069-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..9fa18c56e6087bd31f899482c33f0dbb29e152a6 --- /dev/null +++ b/pytorch_model-00069-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f759b2e924a6ee2881ba1b12321b012ade425557cb89ea6a7c72862d4f722a8 +size 351296865 diff --git a/pytorch_model-00070-of-00082.bin b/pytorch_model-00070-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d99dbabe5761913ecdbd64a95a76b7015c43300e --- /dev/null +++ b/pytorch_model-00070-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6d9b2fc706c193b60cd700fb913ba1753b9bbae3596e46019cec1238fbac81 +size 283116795 diff --git a/pytorch_model-00071-of-00082.bin b/pytorch_model-00071-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..116c62fa9f2aab46a7268bc88c0b16f0e7ca00a6 --- /dev/null +++ b/pytorch_model-00071-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e26fb2db5c93c0e6abddf80396a4ba55a31762d666d817d18c507e30205710 +size 351296865 diff --git a/pytorch_model-00072-of-00082.bin b/pytorch_model-00072-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea6acc5dfee14a938653e26acb6c7bbd1cee06c1 --- /dev/null +++ b/pytorch_model-00072-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1174da5c737096c2e24469cbad1a1921fd1790e703aa5a7c36f888044d2fb6c +size 283116795 diff --git a/pytorch_model-00073-of-00082.bin b/pytorch_model-00073-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..d4f16a17383112ce170e52e326fff2066e085221 --- /dev/null +++ b/pytorch_model-00073-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d7890104a70913ca2d485f65acc6ea189b8d7a7e903df300a0c4428ca895e2b +size 351296865 diff --git a/pytorch_model-00074-of-00082.bin b/pytorch_model-00074-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..321048fc1cb0664f5a728065417b8121b96294f3 --- /dev/null +++ b/pytorch_model-00074-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09aed3c3179593fbc0e4a8ed93ebd19c4eff7097f43277dff51ab121b57e597 +size 283116795 diff --git a/pytorch_model-00075-of-00082.bin b/pytorch_model-00075-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..f9940918d0d52f256c38ce92e8a1c3f31debe88a --- /dev/null +++ b/pytorch_model-00075-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27129708d38900a5556d1b3c354220994a4b3972e3101dde87365401f5460c28 +size 351296865 diff --git a/pytorch_model-00076-of-00082.bin b/pytorch_model-00076-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..663ef81b16d0b4ada9bee23b49dba9a6be9d0e13 --- /dev/null +++ b/pytorch_model-00076-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9157443a6806c14b8c6b2d9def534dae0f9536ed3f4dec6144db236a842ba767 +size 283116795 diff --git a/pytorch_model-00077-of-00082.bin b/pytorch_model-00077-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..666c7a818a63db778bfd5fa5335f56209eee525e --- /dev/null +++ b/pytorch_model-00077-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8228c361281be34582f00fe1d6a10e1ba936a8d383765930167ffd3be6b61174 +size 351296865 diff --git a/pytorch_model-00078-of-00082.bin b/pytorch_model-00078-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..406588cceba9565eb66408b04cd2441f6d31b2eb --- /dev/null +++ b/pytorch_model-00078-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ceb85814b989834dc762927b2f75ad6a09c87e19d06e90a878ecaf646faba07 +size 283116795 diff --git a/pytorch_model-00079-of-00082.bin b/pytorch_model-00079-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..7056c4c64c7913f892010bfd1756a2897e1a96d8 --- /dev/null +++ b/pytorch_model-00079-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74ba7ff8ab144ba3a8b493799543da500be1c2edd15cd1dd919cb194b2493d65 +size 351296865 diff --git a/pytorch_model-00080-of-00082.bin b/pytorch_model-00080-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1fd3dc5fced29a620a4bac4433cfe66a6a6f55d --- /dev/null +++ b/pytorch_model-00080-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22da56777a8465ce5a3d83f17817d38241e43456c5db8da1b6da7ee01f8b1580 +size 283116795 diff --git a/pytorch_model-00081-of-00082.bin b/pytorch_model-00081-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..54b7355dd536755aebc5d9ab16dddd8df508c584 --- /dev/null +++ b/pytorch_model-00081-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ce239ca877b2a07c9ffc4dd48902d164335e13f4bdb322b440211dd8859f884 +size 141590301 diff --git a/pytorch_model-00082-of-00082.bin b/pytorch_model-00082-of-00082.bin new file mode 100644 index 0000000000000000000000000000000000000000..3638915f73c89ff2a550e1f4c5bc4237a4347013 --- /dev/null +++ b/pytorch_model-00082-of-00082.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c83b2314ab98ddfcb8f38138b1aa9de3a4dbdbe00e4ea8476c56c896cf25802 +size 327691178 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5de75a2342c32d8867fdc4a1fe5acb763331f093 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,410 @@ +{ + "metadata": { + "total_size": 26031759360 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00082-of-00082.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00082.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00082.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00082.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00082.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00082.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00082.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00082.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00004-of-00082.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00004-of-00082.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00004-of-00082.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00082.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00082.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00004-of-00082.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00022-of-00082.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00022-of-00082.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00082.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00024-of-00082.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00024-of-00082.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00082.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00023-of-00082.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00026-of-00082.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00026-of-00082.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00082.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00025-of-00082.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00028-of-00082.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00028-of-00082.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00082.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00027-of-00082.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00030-of-00082.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00030-of-00082.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00082.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00029-of-00082.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00032-of-00082.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00032-of-00082.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00082.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00031-of-00082.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00034-of-00082.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00034-of-00082.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00082.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00033-of-00082.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00036-of-00082.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00036-of-00082.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00082.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00035-of-00082.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00038-of-00082.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00038-of-00082.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00037-of-00082.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00037-of-00082.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00040-of-00082.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00040-of-00082.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00039-of-00082.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00039-of-00082.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00006-of-00082.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00006-of-00082.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00082.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00005-of-00082.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00042-of-00082.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00042-of-00082.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00041-of-00082.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00041-of-00082.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00044-of-00082.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00044-of-00082.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00043-of-00082.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00043-of-00082.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00046-of-00082.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00046-of-00082.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00045-of-00082.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00045-of-00082.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00048-of-00082.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00048-of-00082.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00047-of-00082.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00047-of-00082.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00050-of-00082.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00050-of-00082.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00049-of-00082.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00049-of-00082.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00052-of-00082.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00052-of-00082.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00051-of-00082.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00051-of-00082.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00054-of-00082.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00054-of-00082.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00053-of-00082.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00053-of-00082.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00056-of-00082.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00056-of-00082.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00055-of-00082.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00055-of-00082.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00058-of-00082.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00058-of-00082.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00057-of-00082.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00057-of-00082.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00060-of-00082.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00060-of-00082.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00059-of-00082.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00059-of-00082.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00008-of-00082.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00008-of-00082.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00082.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00007-of-00082.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00062-of-00082.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00062-of-00082.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00061-of-00082.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00061-of-00082.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00064-of-00082.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00064-of-00082.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00063-of-00082.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00063-of-00082.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00066-of-00082.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00066-of-00082.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00065-of-00082.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00065-of-00082.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00068-of-00082.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00068-of-00082.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00067-of-00082.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00067-of-00082.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00070-of-00082.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00070-of-00082.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00069-of-00082.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00069-of-00082.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00072-of-00082.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00072-of-00082.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00071-of-00082.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00071-of-00082.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00074-of-00082.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00074-of-00082.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00073-of-00082.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00073-of-00082.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00076-of-00082.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00076-of-00082.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00075-of-00082.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00075-of-00082.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00078-of-00082.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00078-of-00082.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00077-of-00082.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00077-of-00082.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00081-of-00082.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00080-of-00082.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00080-of-00082.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00081-of-00082.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00081-of-00082.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00079-of-00082.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00079-of-00082.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00010-of-00082.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00010-of-00082.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00082.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00009-of-00082.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00012-of-00082.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00012-of-00082.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00082.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00011-of-00082.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00014-of-00082.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00014-of-00082.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00082.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00013-of-00082.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00016-of-00082.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00016-of-00082.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00082.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00015-of-00082.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00018-of-00082.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00018-of-00082.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00082.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00017-of-00082.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00020-of-00082.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00020-of-00082.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00021-of-00082.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00019-of-00082.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00082.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00019-of-00082.bin", + "model.norm.weight": "pytorch_model-00081-of-00082.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..318f9131477d72be713dcfee9da3a2e43d7ac8ad --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "[PAD]", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..6c00c742ce03c627d6cd5b795984876fa49fa899 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..86ad941f053580a392e5c0f0e55e11a8a25a9bcd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,9 @@ +{ + "bos_token": "", + "eos_token": "", + "model_max_length": 2048, + "padding_side": "right", + "special_tokens_map_file": "/root/.cache/huggingface/hub/models--decapoda-research--llama-13b-hf/snapshots/438770a656712a5072229b62256521845d4de5ce/special_tokens_map.json", + "tokenizer_class": "LlamaTokenizer", + "unk_token": "" +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..26d89f7b8dceb4c333cc3e0bc2f0c141a9994e5b --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,5047 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.998657718120805, + "global_step": 837, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 7.692307692307694e-07, + "loss": 1.2482, + "step": 1 + }, + { + "epoch": 0.01, + "learning_rate": 1.5384615384615387e-06, + "loss": 1.2744, + "step": 2 + }, + { + "epoch": 0.01, + "learning_rate": 2.307692307692308e-06, + "loss": 1.1957, + "step": 3 + }, + { + "epoch": 0.01, + "learning_rate": 3.0769230769230774e-06, + "loss": 1.2948, + "step": 4 + }, + { + "epoch": 0.02, + "learning_rate": 3.846153846153847e-06, + "loss": 1.1654, + "step": 5 + }, + { + "epoch": 0.02, + "learning_rate": 4.615384615384616e-06, + "loss": 1.2073, + "step": 6 + }, + { + "epoch": 0.03, + "learning_rate": 5.384615384615385e-06, + "loss": 1.0494, + "step": 7 + }, + { + "epoch": 0.03, + "learning_rate": 6.153846153846155e-06, + "loss": 1.0375, + "step": 8 + }, + { + "epoch": 0.03, + "learning_rate": 6.923076923076923e-06, + "loss": 1.0477, + "step": 9 + }, + { + "epoch": 0.04, + "learning_rate": 7.692307692307694e-06, + "loss": 1.0384, + "step": 10 + }, + { + "epoch": 0.04, + "learning_rate": 8.461538461538462e-06, + "loss": 1.0251, + "step": 11 + }, + { + "epoch": 0.04, + "learning_rate": 9.230769230769232e-06, + "loss": 1.0019, + "step": 12 + }, + { + "epoch": 0.05, + "learning_rate": 1e-05, + "loss": 0.9472, + "step": 13 + }, + { + "epoch": 0.05, + "learning_rate": 1.076923076923077e-05, + "loss": 0.9319, + "step": 14 + }, + { + "epoch": 0.05, + "learning_rate": 1.1538461538461538e-05, + "loss": 0.9633, + "step": 15 + }, + { + "epoch": 0.06, + "learning_rate": 1.230769230769231e-05, + "loss": 1.0054, + "step": 16 + }, + { + "epoch": 0.06, + "learning_rate": 1.3076923076923078e-05, + "loss": 0.9386, + "step": 17 + }, + { + "epoch": 0.06, + "learning_rate": 1.3846153846153847e-05, + "loss": 1.0091, + "step": 18 + }, + { + "epoch": 0.07, + "learning_rate": 1.4615384615384615e-05, + "loss": 0.9047, + "step": 19 + }, + { + "epoch": 0.07, + "learning_rate": 1.5384615384615387e-05, + "loss": 0.9849, + "step": 20 + }, + { + "epoch": 0.08, + "learning_rate": 1.6153846153846154e-05, + "loss": 0.9594, + "step": 21 + }, + { + "epoch": 0.08, + "learning_rate": 1.6923076923076924e-05, + "loss": 0.992, + "step": 22 + }, + { + "epoch": 0.08, + "learning_rate": 1.7692307692307694e-05, + "loss": 0.9684, + "step": 23 + }, + { + "epoch": 0.09, + "learning_rate": 1.8461538461538465e-05, + "loss": 0.8521, + "step": 24 + }, + { + "epoch": 0.09, + "learning_rate": 1.923076923076923e-05, + "loss": 0.9664, + "step": 25 + }, + { + "epoch": 0.09, + "learning_rate": 2e-05, + "loss": 1.0167, + "step": 26 + }, + { + "epoch": 0.1, + "learning_rate": 1.999992497128677e-05, + "loss": 1.0072, + "step": 27 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999699886272926e-05, + "loss": 0.8529, + "step": 28 + }, + { + "epoch": 0.1, + "learning_rate": 1.999932474833605e-05, + "loss": 0.8749, + "step": 29 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998799563105358e-05, + "loss": 0.8796, + "step": 30 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998124338461647e-05, + "loss": 0.8526, + "step": 31 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997299084537164e-05, + "loss": 0.8067, + "step": 32 + }, + { + "epoch": 0.12, + "learning_rate": 1.999632381371545e-05, + "loss": 0.9855, + "step": 33 + }, + { + "epoch": 0.12, + "learning_rate": 1.9995198540631178e-05, + "loss": 0.816, + "step": 34 + }, + { + "epoch": 0.13, + "learning_rate": 1.9993923282169905e-05, + "loss": 0.9606, + "step": 35 + }, + { + "epoch": 0.13, + "learning_rate": 1.9992498057467824e-05, + "loss": 0.8706, + "step": 36 + }, + { + "epoch": 0.13, + "learning_rate": 1.9990922887911495e-05, + "loss": 0.9688, + "step": 37 + }, + { + "epoch": 0.14, + "learning_rate": 1.998919779713751e-05, + "loss": 0.8851, + "step": 38 + }, + { + "epoch": 0.14, + "learning_rate": 1.998732281103213e-05, + "loss": 1.0347, + "step": 39 + }, + { + "epoch": 0.14, + "learning_rate": 1.998529795773092e-05, + "loss": 0.8212, + "step": 40 + }, + { + "epoch": 0.15, + "learning_rate": 1.9983123267618306e-05, + "loss": 0.8904, + "step": 41 + }, + { + "epoch": 0.15, + "learning_rate": 1.9980798773327127e-05, + "loss": 0.8989, + "step": 42 + }, + { + "epoch": 0.15, + "learning_rate": 1.9978324509738147e-05, + "loss": 0.9613, + "step": 43 + }, + { + "epoch": 0.16, + "learning_rate": 1.9975700513979527e-05, + "loss": 0.9202, + "step": 44 + }, + { + "epoch": 0.16, + "learning_rate": 1.9972926825426273e-05, + "loss": 0.819, + "step": 45 + }, + { + "epoch": 0.16, + "learning_rate": 1.997000348569964e-05, + "loss": 0.8932, + "step": 46 + }, + { + "epoch": 0.17, + "learning_rate": 1.996693053866652e-05, + "loss": 0.8892, + "step": 47 + }, + { + "epoch": 0.17, + "learning_rate": 1.9963708030438754e-05, + "loss": 0.8988, + "step": 48 + }, + { + "epoch": 0.18, + "learning_rate": 1.9960336009372475e-05, + "loss": 0.9144, + "step": 49 + }, + { + "epoch": 0.18, + "learning_rate": 1.995681452606737e-05, + "loss": 0.9539, + "step": 50 + }, + { + "epoch": 0.18, + "learning_rate": 1.99531436333659e-05, + "loss": 0.9287, + "step": 51 + }, + { + "epoch": 0.19, + "learning_rate": 1.9949323386352546e-05, + "loss": 0.8457, + "step": 52 + }, + { + "epoch": 0.19, + "learning_rate": 1.9945353842352943e-05, + "loss": 0.9088, + "step": 53 + }, + { + "epoch": 0.19, + "learning_rate": 1.9941235060933054e-05, + "loss": 0.9656, + "step": 54 + }, + { + "epoch": 0.2, + "learning_rate": 1.993696710389825e-05, + "loss": 0.8841, + "step": 55 + }, + { + "epoch": 0.2, + "learning_rate": 1.9932550035292393e-05, + "loss": 0.8781, + "step": 56 + }, + { + "epoch": 0.2, + "learning_rate": 1.9927983921396887e-05, + "loss": 0.8821, + "step": 57 + }, + { + "epoch": 0.21, + "learning_rate": 1.992326883072965e-05, + "loss": 0.9134, + "step": 58 + }, + { + "epoch": 0.21, + "learning_rate": 1.9918404834044124e-05, + "loss": 0.9101, + "step": 59 + }, + { + "epoch": 0.21, + "learning_rate": 1.9913392004328192e-05, + "loss": 0.8517, + "step": 60 + }, + { + "epoch": 0.22, + "learning_rate": 1.9908230416803093e-05, + "loss": 0.882, + "step": 61 + }, + { + "epoch": 0.22, + "learning_rate": 1.990292014892227e-05, + "loss": 0.867, + "step": 62 + }, + { + "epoch": 0.23, + "learning_rate": 1.989746128037024e-05, + "loss": 0.9157, + "step": 63 + }, + { + "epoch": 0.23, + "learning_rate": 1.9891853893061385e-05, + "loss": 0.818, + "step": 64 + }, + { + "epoch": 0.23, + "learning_rate": 1.988609807113871e-05, + "loss": 0.9161, + "step": 65 + }, + { + "epoch": 0.24, + "learning_rate": 1.98801939009726e-05, + "loss": 0.8978, + "step": 66 + }, + { + "epoch": 0.24, + "learning_rate": 1.987414147115951e-05, + "loss": 0.9753, + "step": 67 + }, + { + "epoch": 0.24, + "learning_rate": 1.9867940872520646e-05, + "loss": 0.9747, + "step": 68 + }, + { + "epoch": 0.25, + "learning_rate": 1.9861592198100597e-05, + "loss": 0.907, + "step": 69 + }, + { + "epoch": 0.25, + "learning_rate": 1.9855095543165937e-05, + "loss": 0.8603, + "step": 70 + }, + { + "epoch": 0.25, + "learning_rate": 1.9848451005203795e-05, + "loss": 0.9485, + "step": 71 + }, + { + "epoch": 0.26, + "learning_rate": 1.98416586839204e-05, + "loss": 0.8396, + "step": 72 + }, + { + "epoch": 0.26, + "learning_rate": 1.983471868123958e-05, + "loss": 0.836, + "step": 73 + }, + { + "epoch": 0.26, + "learning_rate": 1.9827631101301225e-05, + "loss": 0.8105, + "step": 74 + }, + { + "epoch": 0.27, + "learning_rate": 1.9820396050459738e-05, + "loss": 0.8443, + "step": 75 + }, + { + "epoch": 0.27, + "learning_rate": 1.9813013637282426e-05, + "loss": 0.943, + "step": 76 + }, + { + "epoch": 0.28, + "learning_rate": 1.9805483972547884e-05, + "loss": 0.9041, + "step": 77 + }, + { + "epoch": 0.28, + "learning_rate": 1.9797807169244326e-05, + "loss": 0.807, + "step": 78 + }, + { + "epoch": 0.28, + "learning_rate": 1.9789983342567885e-05, + "loss": 0.7927, + "step": 79 + }, + { + "epoch": 0.29, + "learning_rate": 1.9782012609920887e-05, + "loss": 0.8045, + "step": 80 + }, + { + "epoch": 0.29, + "learning_rate": 1.9773895090910098e-05, + "loss": 0.8763, + "step": 81 + }, + { + "epoch": 0.29, + "learning_rate": 1.976563090734492e-05, + "loss": 0.8811, + "step": 82 + }, + { + "epoch": 0.3, + "learning_rate": 1.975722018323556e-05, + "loss": 0.9376, + "step": 83 + }, + { + "epoch": 0.3, + "learning_rate": 1.9748663044791185e-05, + "loss": 0.8448, + "step": 84 + }, + { + "epoch": 0.3, + "learning_rate": 1.973995962041801e-05, + "loss": 0.8725, + "step": 85 + }, + { + "epoch": 0.31, + "learning_rate": 1.9731110040717384e-05, + "loss": 0.9644, + "step": 86 + }, + { + "epoch": 0.31, + "learning_rate": 1.9722114438483814e-05, + "loss": 0.8595, + "step": 87 + }, + { + "epoch": 0.31, + "learning_rate": 1.9712972948703006e-05, + "loss": 0.805, + "step": 88 + }, + { + "epoch": 0.32, + "learning_rate": 1.9703685708549787e-05, + "loss": 0.7906, + "step": 89 + }, + { + "epoch": 0.32, + "learning_rate": 1.9694252857386103e-05, + "loss": 0.8252, + "step": 90 + }, + { + "epoch": 0.33, + "learning_rate": 1.9684674536758894e-05, + "loss": 0.7953, + "step": 91 + }, + { + "epoch": 0.33, + "learning_rate": 1.9674950890397965e-05, + "loss": 0.9881, + "step": 92 + }, + { + "epoch": 0.33, + "learning_rate": 1.9665082064213856e-05, + "loss": 0.9094, + "step": 93 + }, + { + "epoch": 0.34, + "learning_rate": 1.965506820629563e-05, + "loss": 0.8355, + "step": 94 + }, + { + "epoch": 0.34, + "learning_rate": 1.9644909466908664e-05, + "loss": 0.9551, + "step": 95 + }, + { + "epoch": 0.34, + "learning_rate": 1.9634605998492386e-05, + "loss": 0.7924, + "step": 96 + }, + { + "epoch": 0.35, + "learning_rate": 1.962415795565799e-05, + "loss": 0.928, + "step": 97 + }, + { + "epoch": 0.35, + "learning_rate": 1.9613565495186126e-05, + "loss": 0.9711, + "step": 98 + }, + { + "epoch": 0.35, + "learning_rate": 1.960282877602452e-05, + "loss": 1.0001, + "step": 99 + }, + { + "epoch": 0.36, + "learning_rate": 1.9591947959285622e-05, + "loss": 0.9109, + "step": 100 + }, + { + "epoch": 0.36, + "learning_rate": 1.958092320824417e-05, + "loss": 0.9282, + "step": 101 + }, + { + "epoch": 0.37, + "learning_rate": 1.956975468833473e-05, + "loss": 0.8891, + "step": 102 + }, + { + "epoch": 0.37, + "learning_rate": 1.9558442567149244e-05, + "loss": 0.8778, + "step": 103 + }, + { + "epoch": 0.37, + "learning_rate": 1.9546987014434494e-05, + "loss": 0.8379, + "step": 104 + }, + { + "epoch": 0.38, + "learning_rate": 1.9535388202089555e-05, + "loss": 0.9404, + "step": 105 + }, + { + "epoch": 0.38, + "learning_rate": 1.952364630416322e-05, + "loss": 0.8996, + "step": 106 + }, + { + "epoch": 0.38, + "learning_rate": 1.9511761496851382e-05, + "loss": 0.8506, + "step": 107 + }, + { + "epoch": 0.39, + "learning_rate": 1.9499733958494405e-05, + "loss": 1.022, + "step": 108 + }, + { + "epoch": 0.39, + "learning_rate": 1.948756386957444e-05, + "loss": 0.8509, + "step": 109 + }, + { + "epoch": 0.39, + "learning_rate": 1.94752514127127e-05, + "loss": 0.8793, + "step": 110 + }, + { + "epoch": 0.4, + "learning_rate": 1.9462796772666746e-05, + "loss": 0.7822, + "step": 111 + }, + { + "epoch": 0.4, + "learning_rate": 1.9450200136327705e-05, + "loss": 0.8077, + "step": 112 + }, + { + "epoch": 0.4, + "learning_rate": 1.943746169271746e-05, + "loss": 0.8818, + "step": 113 + }, + { + "epoch": 0.41, + "learning_rate": 1.9424581632985812e-05, + "loss": 0.8624, + "step": 114 + }, + { + "epoch": 0.41, + "learning_rate": 1.941156015040763e-05, + "loss": 0.8163, + "step": 115 + }, + { + "epoch": 0.42, + "learning_rate": 1.9398397440379923e-05, + "loss": 0.9071, + "step": 116 + }, + { + "epoch": 0.42, + "learning_rate": 1.9385093700418936e-05, + "loss": 0.9254, + "step": 117 + }, + { + "epoch": 0.42, + "learning_rate": 1.9371649130157166e-05, + "loss": 0.7863, + "step": 118 + }, + { + "epoch": 0.43, + "learning_rate": 1.9358063931340375e-05, + "loss": 0.893, + "step": 119 + }, + { + "epoch": 0.43, + "learning_rate": 1.9344338307824554e-05, + "loss": 0.8356, + "step": 120 + }, + { + "epoch": 0.43, + "learning_rate": 1.9330472465572883e-05, + "loss": 0.8866, + "step": 121 + }, + { + "epoch": 0.44, + "learning_rate": 1.9316466612652623e-05, + "loss": 0.8881, + "step": 122 + }, + { + "epoch": 0.44, + "learning_rate": 1.9302320959231997e-05, + "loss": 0.7993, + "step": 123 + }, + { + "epoch": 0.44, + "learning_rate": 1.9288035717577037e-05, + "loss": 0.9191, + "step": 124 + }, + { + "epoch": 0.45, + "learning_rate": 1.9273611102048406e-05, + "loss": 0.9254, + "step": 125 + }, + { + "epoch": 0.45, + "learning_rate": 1.9259047329098173e-05, + "loss": 0.823, + "step": 126 + }, + { + "epoch": 0.45, + "learning_rate": 1.9244344617266565e-05, + "loss": 0.7906, + "step": 127 + }, + { + "epoch": 0.46, + "learning_rate": 1.9229503187178694e-05, + "loss": 0.8566, + "step": 128 + }, + { + "epoch": 0.46, + "learning_rate": 1.9214523261541236e-05, + "loss": 0.849, + "step": 129 + }, + { + "epoch": 0.47, + "learning_rate": 1.9199405065139105e-05, + "loss": 0.8412, + "step": 130 + }, + { + "epoch": 0.47, + "learning_rate": 1.918414882483206e-05, + "loss": 0.8831, + "step": 131 + }, + { + "epoch": 0.47, + "learning_rate": 1.9168754769551326e-05, + "loss": 0.9345, + "step": 132 + }, + { + "epoch": 0.48, + "learning_rate": 1.9153223130296125e-05, + "loss": 0.9188, + "step": 133 + }, + { + "epoch": 0.48, + "learning_rate": 1.9137554140130246e-05, + "loss": 0.7862, + "step": 134 + }, + { + "epoch": 0.48, + "learning_rate": 1.9121748034178516e-05, + "loss": 0.8999, + "step": 135 + }, + { + "epoch": 0.49, + "learning_rate": 1.91058050496233e-05, + "loss": 0.9189, + "step": 136 + }, + { + "epoch": 0.49, + "learning_rate": 1.9089725425700917e-05, + "loss": 0.9438, + "step": 137 + }, + { + "epoch": 0.49, + "learning_rate": 1.9073509403698062e-05, + "loss": 0.9002, + "step": 138 + }, + { + "epoch": 0.5, + "learning_rate": 1.90571572269482e-05, + "loss": 0.8889, + "step": 139 + }, + { + "epoch": 0.5, + "learning_rate": 1.9040669140827875e-05, + "loss": 0.8656, + "step": 140 + }, + { + "epoch": 0.5, + "learning_rate": 1.902404539275307e-05, + "loss": 0.8452, + "step": 141 + }, + { + "epoch": 0.51, + "learning_rate": 1.9007286232175466e-05, + "loss": 0.8758, + "step": 142 + }, + { + "epoch": 0.51, + "learning_rate": 1.899039191057872e-05, + "loss": 0.889, + "step": 143 + }, + { + "epoch": 0.52, + "learning_rate": 1.897336268147467e-05, + "loss": 0.7384, + "step": 144 + }, + { + "epoch": 0.52, + "learning_rate": 1.8956198800399543e-05, + "loss": 0.8519, + "step": 145 + }, + { + "epoch": 0.52, + "learning_rate": 1.8938900524910128e-05, + "loss": 0.911, + "step": 146 + }, + { + "epoch": 0.53, + "learning_rate": 1.892146811457989e-05, + "loss": 0.8269, + "step": 147 + }, + { + "epoch": 0.53, + "learning_rate": 1.8903901830995093e-05, + "loss": 0.8018, + "step": 148 + }, + { + "epoch": 0.53, + "learning_rate": 1.888620193775087e-05, + "loss": 0.8537, + "step": 149 + }, + { + "epoch": 0.54, + "learning_rate": 1.8868368700447258e-05, + "loss": 0.9076, + "step": 150 + }, + { + "epoch": 0.54, + "learning_rate": 1.8850402386685235e-05, + "loss": 0.8821, + "step": 151 + }, + { + "epoch": 0.54, + "learning_rate": 1.883230326606268e-05, + "loss": 0.8246, + "step": 152 + }, + { + "epoch": 0.55, + "learning_rate": 1.881407161017033e-05, + "loss": 0.8629, + "step": 153 + }, + { + "epoch": 0.55, + "learning_rate": 1.879570769258773e-05, + "loss": 0.8795, + "step": 154 + }, + { + "epoch": 0.55, + "learning_rate": 1.87772117888791e-05, + "loss": 0.9347, + "step": 155 + }, + { + "epoch": 0.56, + "learning_rate": 1.875858417658921e-05, + "loss": 0.7919, + "step": 156 + }, + { + "epoch": 0.56, + "learning_rate": 1.8739825135239216e-05, + "loss": 0.8385, + "step": 157 + }, + { + "epoch": 0.57, + "learning_rate": 1.8720934946322466e-05, + "loss": 0.9529, + "step": 158 + }, + { + "epoch": 0.57, + "learning_rate": 1.8701913893300272e-05, + "loss": 0.893, + "step": 159 + }, + { + "epoch": 0.57, + "learning_rate": 1.868276226159766e-05, + "loss": 0.8894, + "step": 160 + }, + { + "epoch": 0.58, + "learning_rate": 1.866348033859909e-05, + "loss": 0.8624, + "step": 161 + }, + { + "epoch": 0.58, + "learning_rate": 1.8644068413644134e-05, + "loss": 0.8289, + "step": 162 + }, + { + "epoch": 0.58, + "learning_rate": 1.8624526778023142e-05, + "loss": 0.7326, + "step": 163 + }, + { + "epoch": 0.59, + "learning_rate": 1.860485572497287e-05, + "loss": 0.8636, + "step": 164 + }, + { + "epoch": 0.59, + "learning_rate": 1.858505554967207e-05, + "loss": 0.8702, + "step": 165 + }, + { + "epoch": 0.59, + "learning_rate": 1.8565126549237092e-05, + "loss": 0.8396, + "step": 166 + }, + { + "epoch": 0.6, + "learning_rate": 1.8545069022717374e-05, + "loss": 0.8703, + "step": 167 + }, + { + "epoch": 0.6, + "learning_rate": 1.8524883271091004e-05, + "loss": 0.7619, + "step": 168 + }, + { + "epoch": 0.6, + "learning_rate": 1.8504569597260178e-05, + "loss": 0.8855, + "step": 169 + }, + { + "epoch": 0.61, + "learning_rate": 1.848412830604665e-05, + "loss": 0.7781, + "step": 170 + }, + { + "epoch": 0.61, + "learning_rate": 1.846355970418718e-05, + "loss": 0.8302, + "step": 171 + }, + { + "epoch": 0.62, + "learning_rate": 1.8442864100328915e-05, + "loss": 0.8635, + "step": 172 + }, + { + "epoch": 0.62, + "learning_rate": 1.842204180502476e-05, + "loss": 0.9332, + "step": 173 + }, + { + "epoch": 0.62, + "learning_rate": 1.8401093130728717e-05, + "loss": 0.8643, + "step": 174 + }, + { + "epoch": 0.63, + "learning_rate": 1.8380018391791203e-05, + "loss": 0.905, + "step": 175 + }, + { + "epoch": 0.63, + "learning_rate": 1.8358817904454328e-05, + "loss": 0.9312, + "step": 176 + }, + { + "epoch": 0.63, + "learning_rate": 1.833749198684715e-05, + "loss": 0.8619, + "step": 177 + }, + { + "epoch": 0.64, + "learning_rate": 1.8316040958980896e-05, + "loss": 0.8519, + "step": 178 + }, + { + "epoch": 0.64, + "learning_rate": 1.829446514274417e-05, + "loss": 0.8565, + "step": 179 + }, + { + "epoch": 0.64, + "learning_rate": 1.8272764861898122e-05, + "loss": 1.0034, + "step": 180 + }, + { + "epoch": 0.65, + "learning_rate": 1.825094044207158e-05, + "loss": 0.7983, + "step": 181 + }, + { + "epoch": 0.65, + "learning_rate": 1.8228992210756166e-05, + "loss": 0.8168, + "step": 182 + }, + { + "epoch": 0.66, + "learning_rate": 1.82069204973014e-05, + "loss": 0.7707, + "step": 183 + }, + { + "epoch": 0.66, + "learning_rate": 1.818472563290973e-05, + "loss": 0.8362, + "step": 184 + }, + { + "epoch": 0.66, + "learning_rate": 1.8162407950631575e-05, + "loss": 0.8141, + "step": 185 + }, + { + "epoch": 0.67, + "learning_rate": 1.8139967785360338e-05, + "loss": 0.8943, + "step": 186 + }, + { + "epoch": 0.67, + "learning_rate": 1.811740547382736e-05, + "loss": 0.8399, + "step": 187 + }, + { + "epoch": 0.67, + "learning_rate": 1.809472135459688e-05, + "loss": 0.8999, + "step": 188 + }, + { + "epoch": 0.68, + "learning_rate": 1.8071915768060962e-05, + "loss": 0.899, + "step": 189 + }, + { + "epoch": 0.68, + "learning_rate": 1.8048989056434356e-05, + "loss": 0.886, + "step": 190 + }, + { + "epoch": 0.68, + "learning_rate": 1.8025941563749407e-05, + "loss": 0.888, + "step": 191 + }, + { + "epoch": 0.69, + "learning_rate": 1.8002773635850855e-05, + "loss": 0.8748, + "step": 192 + }, + { + "epoch": 0.69, + "learning_rate": 1.797948562039066e-05, + "loss": 0.8893, + "step": 193 + }, + { + "epoch": 0.69, + "learning_rate": 1.7956077866822794e-05, + "loss": 0.9131, + "step": 194 + }, + { + "epoch": 0.7, + "learning_rate": 1.793255072639798e-05, + "loss": 0.9468, + "step": 195 + }, + { + "epoch": 0.7, + "learning_rate": 1.7908904552158435e-05, + "loss": 0.9824, + "step": 196 + }, + { + "epoch": 0.71, + "learning_rate": 1.7885139698932563e-05, + "loss": 0.9275, + "step": 197 + }, + { + "epoch": 0.71, + "learning_rate": 1.7861256523329634e-05, + "loss": 0.9027, + "step": 198 + }, + { + "epoch": 0.71, + "learning_rate": 1.7837255383734436e-05, + "loss": 0.8939, + "step": 199 + }, + { + "epoch": 0.72, + "learning_rate": 1.7813136640301894e-05, + "loss": 0.8171, + "step": 200 + }, + { + "epoch": 0.72, + "learning_rate": 1.7788900654951664e-05, + "loss": 0.8073, + "step": 201 + }, + { + "epoch": 0.72, + "learning_rate": 1.7764547791362704e-05, + "loss": 0.8052, + "step": 202 + }, + { + "epoch": 0.73, + "learning_rate": 1.7740078414967817e-05, + "loss": 0.8605, + "step": 203 + }, + { + "epoch": 0.73, + "learning_rate": 1.7715492892948172e-05, + "loss": 0.7666, + "step": 204 + }, + { + "epoch": 0.73, + "learning_rate": 1.7690791594227784e-05, + "loss": 0.8865, + "step": 205 + }, + { + "epoch": 0.74, + "learning_rate": 1.766597488946798e-05, + "loss": 0.8808, + "step": 206 + }, + { + "epoch": 0.74, + "learning_rate": 1.764104315106185e-05, + "loss": 0.8213, + "step": 207 + }, + { + "epoch": 0.74, + "learning_rate": 1.761599675312864e-05, + "loss": 0.7597, + "step": 208 + }, + { + "epoch": 0.75, + "learning_rate": 1.759083607150816e-05, + "loss": 0.8374, + "step": 209 + }, + { + "epoch": 0.75, + "learning_rate": 1.7565561483755112e-05, + "loss": 0.8789, + "step": 210 + }, + { + "epoch": 0.76, + "learning_rate": 1.7540173369133463e-05, + "loss": 0.7987, + "step": 211 + }, + { + "epoch": 0.76, + "learning_rate": 1.7514672108610722e-05, + "loss": 0.828, + "step": 212 + }, + { + "epoch": 0.76, + "learning_rate": 1.7489058084852247e-05, + "loss": 0.8383, + "step": 213 + }, + { + "epoch": 0.77, + "learning_rate": 1.7463331682215488e-05, + "loss": 0.8263, + "step": 214 + }, + { + "epoch": 0.77, + "learning_rate": 1.7437493286744215e-05, + "loss": 0.7801, + "step": 215 + }, + { + "epoch": 0.77, + "learning_rate": 1.741154328616274e-05, + "loss": 0.851, + "step": 216 + }, + { + "epoch": 0.78, + "learning_rate": 1.7385482069870107e-05, + "loss": 0.7719, + "step": 217 + }, + { + "epoch": 0.78, + "learning_rate": 1.73593100289342e-05, + "loss": 0.8586, + "step": 218 + }, + { + "epoch": 0.78, + "learning_rate": 1.733302755608595e-05, + "loss": 0.8419, + "step": 219 + }, + { + "epoch": 0.79, + "learning_rate": 1.7306635045713372e-05, + "loss": 0.9245, + "step": 220 + }, + { + "epoch": 0.79, + "learning_rate": 1.728013289385568e-05, + "loss": 0.7995, + "step": 221 + }, + { + "epoch": 0.79, + "learning_rate": 1.7253521498197354e-05, + "loss": 0.8501, + "step": 222 + }, + { + "epoch": 0.8, + "learning_rate": 1.722680125806214e-05, + "loss": 0.7985, + "step": 223 + }, + { + "epoch": 0.8, + "learning_rate": 1.7199972574407087e-05, + "loss": 0.7836, + "step": 224 + }, + { + "epoch": 0.81, + "learning_rate": 1.717303584981652e-05, + "loss": 0.9024, + "step": 225 + }, + { + "epoch": 0.81, + "learning_rate": 1.7145991488495997e-05, + "loss": 0.8636, + "step": 226 + }, + { + "epoch": 0.81, + "learning_rate": 1.711883989626624e-05, + "loss": 0.9235, + "step": 227 + }, + { + "epoch": 0.82, + "learning_rate": 1.7091581480557057e-05, + "loss": 0.8536, + "step": 228 + }, + { + "epoch": 0.82, + "learning_rate": 1.7064216650401217e-05, + "loss": 0.9074, + "step": 229 + }, + { + "epoch": 0.82, + "learning_rate": 1.703674581642832e-05, + "loss": 0.9014, + "step": 230 + }, + { + "epoch": 0.83, + "learning_rate": 1.7009169390858635e-05, + "loss": 0.8277, + "step": 231 + }, + { + "epoch": 0.83, + "learning_rate": 1.69814877874969e-05, + "loss": 0.7759, + "step": 232 + }, + { + "epoch": 0.83, + "learning_rate": 1.695370142172614e-05, + "loss": 0.8478, + "step": 233 + }, + { + "epoch": 0.84, + "learning_rate": 1.6925810710501394e-05, + "loss": 0.8816, + "step": 234 + }, + { + "epoch": 0.84, + "learning_rate": 1.6897816072343515e-05, + "loss": 0.8193, + "step": 235 + }, + { + "epoch": 0.84, + "learning_rate": 1.6869717927332825e-05, + "loss": 0.8108, + "step": 236 + }, + { + "epoch": 0.85, + "learning_rate": 1.6841516697102866e-05, + "loss": 0.8304, + "step": 237 + }, + { + "epoch": 0.85, + "learning_rate": 1.6813212804834033e-05, + "loss": 0.8298, + "step": 238 + }, + { + "epoch": 0.86, + "learning_rate": 1.678480667524725e-05, + "loss": 0.7688, + "step": 239 + }, + { + "epoch": 0.86, + "learning_rate": 1.6756298734597596e-05, + "loss": 0.8906, + "step": 240 + }, + { + "epoch": 0.86, + "learning_rate": 1.6727689410667887e-05, + "loss": 0.9109, + "step": 241 + }, + { + "epoch": 0.87, + "learning_rate": 1.669897913276227e-05, + "loss": 0.7968, + "step": 242 + }, + { + "epoch": 0.87, + "learning_rate": 1.667016833169979e-05, + "loss": 0.8012, + "step": 243 + }, + { + "epoch": 0.87, + "learning_rate": 1.664125743980792e-05, + "loss": 0.9036, + "step": 244 + }, + { + "epoch": 0.88, + "learning_rate": 1.6612246890916056e-05, + "loss": 0.8734, + "step": 245 + }, + { + "epoch": 0.88, + "learning_rate": 1.6583137120349028e-05, + "loss": 0.7571, + "step": 246 + }, + { + "epoch": 0.88, + "learning_rate": 1.6553928564920565e-05, + "loss": 0.8532, + "step": 247 + }, + { + "epoch": 0.89, + "learning_rate": 1.6524621662926733e-05, + "loss": 0.9272, + "step": 248 + }, + { + "epoch": 0.89, + "learning_rate": 1.649521685413936e-05, + "loss": 0.8616, + "step": 249 + }, + { + "epoch": 0.89, + "learning_rate": 1.6465714579799435e-05, + "loss": 0.8194, + "step": 250 + }, + { + "epoch": 0.9, + "learning_rate": 1.64361152826105e-05, + "loss": 0.785, + "step": 251 + }, + { + "epoch": 0.9, + "learning_rate": 1.6406419406731992e-05, + "loss": 0.8429, + "step": 252 + }, + { + "epoch": 0.91, + "learning_rate": 1.6376627397772576e-05, + "loss": 0.9032, + "step": 253 + }, + { + "epoch": 0.91, + "learning_rate": 1.6346739702783477e-05, + "loss": 0.8941, + "step": 254 + }, + { + "epoch": 0.91, + "learning_rate": 1.6316756770251754e-05, + "loss": 0.8268, + "step": 255 + }, + { + "epoch": 0.92, + "learning_rate": 1.6286679050093573e-05, + "loss": 0.9194, + "step": 256 + }, + { + "epoch": 0.92, + "learning_rate": 1.625650699364746e-05, + "loss": 0.8604, + "step": 257 + }, + { + "epoch": 0.92, + "learning_rate": 1.6226241053667536e-05, + "loss": 0.8021, + "step": 258 + }, + { + "epoch": 0.93, + "learning_rate": 1.619588168431671e-05, + "loss": 0.834, + "step": 259 + }, + { + "epoch": 0.93, + "learning_rate": 1.6165429341159852e-05, + "loss": 0.849, + "step": 260 + }, + { + "epoch": 0.93, + "learning_rate": 1.6134884481156994e-05, + "loss": 0.8477, + "step": 261 + }, + { + "epoch": 0.94, + "learning_rate": 1.6104247562656447e-05, + "loss": 0.8983, + "step": 262 + }, + { + "epoch": 0.94, + "learning_rate": 1.607351904538792e-05, + "loss": 0.8679, + "step": 263 + }, + { + "epoch": 0.94, + "learning_rate": 1.604269939045564e-05, + "loss": 0.8236, + "step": 264 + }, + { + "epoch": 0.95, + "learning_rate": 1.6011789060331417e-05, + "loss": 0.774, + "step": 265 + }, + { + "epoch": 0.95, + "learning_rate": 1.5980788518847706e-05, + "loss": 0.8579, + "step": 266 + }, + { + "epoch": 0.96, + "learning_rate": 1.594969823119066e-05, + "loss": 0.9195, + "step": 267 + }, + { + "epoch": 0.96, + "learning_rate": 1.5918518663893124e-05, + "loss": 0.8451, + "step": 268 + }, + { + "epoch": 0.96, + "learning_rate": 1.5887250284827672e-05, + "loss": 0.8238, + "step": 269 + }, + { + "epoch": 0.97, + "learning_rate": 1.585589356319955e-05, + "loss": 0.9041, + "step": 270 + }, + { + "epoch": 0.97, + "learning_rate": 1.5824448969539653e-05, + "loss": 0.8183, + "step": 271 + }, + { + "epoch": 0.97, + "learning_rate": 1.5792916975697455e-05, + "loss": 0.8716, + "step": 272 + }, + { + "epoch": 0.98, + "learning_rate": 1.5761298054833947e-05, + "loss": 0.7952, + "step": 273 + }, + { + "epoch": 0.98, + "learning_rate": 1.572959268141452e-05, + "loss": 0.8742, + "step": 274 + }, + { + "epoch": 0.98, + "learning_rate": 1.5697801331201846e-05, + "loss": 0.8474, + "step": 275 + }, + { + "epoch": 0.99, + "learning_rate": 1.566592448124874e-05, + "loss": 0.9467, + "step": 276 + }, + { + "epoch": 0.99, + "learning_rate": 1.5633962609891016e-05, + "loss": 0.8541, + "step": 277 + }, + { + "epoch": 1.0, + "learning_rate": 1.5601916196740283e-05, + "loss": 0.8572, + "step": 278 + }, + { + "epoch": 1.0, + "learning_rate": 1.5569785722676774e-05, + "loss": 0.895, + "step": 279 + }, + { + "epoch": 1.0, + "learning_rate": 1.5537571669842114e-05, + "loss": 0.7402, + "step": 280 + }, + { + "epoch": 1.01, + "learning_rate": 1.550527452163209e-05, + "loss": 0.4291, + "step": 281 + }, + { + "epoch": 1.01, + "learning_rate": 1.5472894762689393e-05, + "loss": 0.3613, + "step": 282 + }, + { + "epoch": 1.01, + "learning_rate": 1.544043287889635e-05, + "loss": 0.464, + "step": 283 + }, + { + "epoch": 1.02, + "learning_rate": 1.5407889357367648e-05, + "loss": 0.4705, + "step": 284 + }, + { + "epoch": 1.02, + "learning_rate": 1.5375264686442985e-05, + "loss": 0.4017, + "step": 285 + }, + { + "epoch": 1.03, + "learning_rate": 1.5342559355679776e-05, + "loss": 0.4202, + "step": 286 + }, + { + "epoch": 1.03, + "learning_rate": 1.5309773855845803e-05, + "loss": 0.4101, + "step": 287 + }, + { + "epoch": 1.03, + "learning_rate": 1.5276908678911837e-05, + "loss": 0.4464, + "step": 288 + }, + { + "epoch": 1.04, + "learning_rate": 1.5243964318044261e-05, + "loss": 0.4441, + "step": 289 + }, + { + "epoch": 1.04, + "learning_rate": 1.5210941267597684e-05, + "loss": 0.358, + "step": 290 + }, + { + "epoch": 1.04, + "learning_rate": 1.5177840023107498e-05, + "loss": 0.4246, + "step": 291 + }, + { + "epoch": 1.05, + "learning_rate": 1.5144661081282456e-05, + "loss": 0.3918, + "step": 292 + }, + { + "epoch": 1.05, + "learning_rate": 1.5111404939997227e-05, + "loss": 0.3367, + "step": 293 + }, + { + "epoch": 1.05, + "learning_rate": 1.5078072098284906e-05, + "loss": 0.3579, + "step": 294 + }, + { + "epoch": 1.06, + "learning_rate": 1.5044663056329531e-05, + "loss": 0.4092, + "step": 295 + }, + { + "epoch": 1.06, + "learning_rate": 1.5011178315458601e-05, + "loss": 0.4172, + "step": 296 + }, + { + "epoch": 1.06, + "learning_rate": 1.4977618378135507e-05, + "loss": 0.3996, + "step": 297 + }, + { + "epoch": 1.07, + "learning_rate": 1.494398374795204e-05, + "loss": 0.3266, + "step": 298 + }, + { + "epoch": 1.07, + "learning_rate": 1.4910274929620798e-05, + "loss": 0.346, + "step": 299 + }, + { + "epoch": 1.08, + "learning_rate": 1.487649242896764e-05, + "loss": 0.4124, + "step": 300 + }, + { + "epoch": 1.08, + "learning_rate": 1.4842636752924073e-05, + "loss": 0.3397, + "step": 301 + }, + { + "epoch": 1.08, + "learning_rate": 1.480870840951966e-05, + "loss": 0.3479, + "step": 302 + }, + { + "epoch": 1.09, + "learning_rate": 1.4774707907874392e-05, + "loss": 0.3544, + "step": 303 + }, + { + "epoch": 1.09, + "learning_rate": 1.4740635758191044e-05, + "loss": 0.4099, + "step": 304 + }, + { + "epoch": 1.09, + "learning_rate": 1.470649247174753e-05, + "loss": 0.4382, + "step": 305 + }, + { + "epoch": 1.1, + "learning_rate": 1.467227856088921e-05, + "loss": 0.368, + "step": 306 + }, + { + "epoch": 1.1, + "learning_rate": 1.4637994539021237e-05, + "loss": 0.4068, + "step": 307 + }, + { + "epoch": 1.1, + "learning_rate": 1.4603640920600813e-05, + "loss": 0.3729, + "step": 308 + }, + { + "epoch": 1.11, + "learning_rate": 1.4569218221129493e-05, + "loss": 0.3203, + "step": 309 + }, + { + "epoch": 1.11, + "learning_rate": 1.4534726957145453e-05, + "loss": 0.4071, + "step": 310 + }, + { + "epoch": 1.11, + "learning_rate": 1.4500167646215722e-05, + "loss": 0.392, + "step": 311 + }, + { + "epoch": 1.12, + "learning_rate": 1.4465540806928419e-05, + "loss": 0.3869, + "step": 312 + }, + { + "epoch": 1.12, + "learning_rate": 1.4430846958884995e-05, + "loss": 0.4022, + "step": 313 + }, + { + "epoch": 1.13, + "learning_rate": 1.4396086622692398e-05, + "loss": 0.3389, + "step": 314 + }, + { + "epoch": 1.13, + "learning_rate": 1.4361260319955288e-05, + "loss": 0.3977, + "step": 315 + }, + { + "epoch": 1.13, + "learning_rate": 1.4326368573268199e-05, + "loss": 0.3581, + "step": 316 + }, + { + "epoch": 1.14, + "learning_rate": 1.4291411906207706e-05, + "loss": 0.3489, + "step": 317 + }, + { + "epoch": 1.14, + "learning_rate": 1.4256390843324556e-05, + "loss": 0.2793, + "step": 318 + }, + { + "epoch": 1.14, + "learning_rate": 1.4221305910135808e-05, + "loss": 0.3773, + "step": 319 + }, + { + "epoch": 1.15, + "learning_rate": 1.4186157633116942e-05, + "loss": 0.3058, + "step": 320 + }, + { + "epoch": 1.15, + "learning_rate": 1.415094653969395e-05, + "loss": 0.3481, + "step": 321 + }, + { + "epoch": 1.15, + "learning_rate": 1.4115673158235449e-05, + "loss": 0.3234, + "step": 322 + }, + { + "epoch": 1.16, + "learning_rate": 1.4080338018044712e-05, + "loss": 0.3918, + "step": 323 + }, + { + "epoch": 1.16, + "learning_rate": 1.4044941649351767e-05, + "loss": 0.3341, + "step": 324 + }, + { + "epoch": 1.16, + "learning_rate": 1.400948458330541e-05, + "loss": 0.3794, + "step": 325 + }, + { + "epoch": 1.17, + "learning_rate": 1.397396735196525e-05, + "loss": 0.4144, + "step": 326 + }, + { + "epoch": 1.17, + "learning_rate": 1.3938390488293721e-05, + "loss": 0.3713, + "step": 327 + }, + { + "epoch": 1.18, + "learning_rate": 1.390275452614808e-05, + "loss": 0.4265, + "step": 328 + }, + { + "epoch": 1.18, + "learning_rate": 1.386706000027241e-05, + "loss": 0.4543, + "step": 329 + }, + { + "epoch": 1.18, + "learning_rate": 1.3831307446289573e-05, + "loss": 0.4582, + "step": 330 + }, + { + "epoch": 1.19, + "learning_rate": 1.3795497400693198e-05, + "loss": 0.3439, + "step": 331 + }, + { + "epoch": 1.19, + "learning_rate": 1.3759630400839613e-05, + "loss": 0.4263, + "step": 332 + }, + { + "epoch": 1.19, + "learning_rate": 1.3723706984939783e-05, + "loss": 0.3158, + "step": 333 + }, + { + "epoch": 1.2, + "learning_rate": 1.368772769205125e-05, + "loss": 0.3681, + "step": 334 + }, + { + "epoch": 1.2, + "learning_rate": 1.3651693062070013e-05, + "loss": 0.3588, + "step": 335 + }, + { + "epoch": 1.2, + "learning_rate": 1.3615603635722463e-05, + "loss": 0.3437, + "step": 336 + }, + { + "epoch": 1.21, + "learning_rate": 1.3579459954557246e-05, + "loss": 0.3589, + "step": 337 + }, + { + "epoch": 1.21, + "learning_rate": 1.3543262560937135e-05, + "loss": 0.3674, + "step": 338 + }, + { + "epoch": 1.21, + "learning_rate": 1.3507011998030905e-05, + "loss": 0.3564, + "step": 339 + }, + { + "epoch": 1.22, + "learning_rate": 1.3470708809805171e-05, + "loss": 0.391, + "step": 340 + }, + { + "epoch": 1.22, + "learning_rate": 1.3434353541016238e-05, + "loss": 0.3767, + "step": 341 + }, + { + "epoch": 1.23, + "learning_rate": 1.339794673720191e-05, + "loss": 0.3867, + "step": 342 + }, + { + "epoch": 1.23, + "learning_rate": 1.3361488944673315e-05, + "loss": 0.3405, + "step": 343 + }, + { + "epoch": 1.23, + "learning_rate": 1.332498071050671e-05, + "loss": 0.3241, + "step": 344 + }, + { + "epoch": 1.24, + "learning_rate": 1.3288422582535254e-05, + "loss": 0.3203, + "step": 345 + }, + { + "epoch": 1.24, + "learning_rate": 1.3251815109340813e-05, + "loss": 0.3885, + "step": 346 + }, + { + "epoch": 1.24, + "learning_rate": 1.3215158840245705e-05, + "loss": 0.399, + "step": 347 + }, + { + "epoch": 1.25, + "learning_rate": 1.3178454325304472e-05, + "loss": 0.3792, + "step": 348 + }, + { + "epoch": 1.25, + "learning_rate": 1.3141702115295623e-05, + "loss": 0.4046, + "step": 349 + }, + { + "epoch": 1.25, + "learning_rate": 1.3104902761713354e-05, + "loss": 0.3731, + "step": 350 + }, + { + "epoch": 1.26, + "learning_rate": 1.3068056816759303e-05, + "loss": 0.3908, + "step": 351 + }, + { + "epoch": 1.26, + "learning_rate": 1.303116483333423e-05, + "loss": 0.3924, + "step": 352 + }, + { + "epoch": 1.26, + "learning_rate": 1.2994227365029752e-05, + "loss": 0.3768, + "step": 353 + }, + { + "epoch": 1.27, + "learning_rate": 1.2957244966120007e-05, + "loss": 0.3851, + "step": 354 + }, + { + "epoch": 1.27, + "learning_rate": 1.2920218191553358e-05, + "loss": 0.3737, + "step": 355 + }, + { + "epoch": 1.28, + "learning_rate": 1.2883147596944054e-05, + "loss": 0.3679, + "step": 356 + }, + { + "epoch": 1.28, + "learning_rate": 1.2846033738563897e-05, + "loss": 0.3238, + "step": 357 + }, + { + "epoch": 1.28, + "learning_rate": 1.2808877173333896e-05, + "loss": 0.3571, + "step": 358 + }, + { + "epoch": 1.29, + "learning_rate": 1.2771678458815906e-05, + "loss": 0.348, + "step": 359 + }, + { + "epoch": 1.29, + "learning_rate": 1.273443815320426e-05, + "loss": 0.3391, + "step": 360 + }, + { + "epoch": 1.29, + "learning_rate": 1.2697156815317409e-05, + "loss": 0.4168, + "step": 361 + }, + { + "epoch": 1.3, + "learning_rate": 1.2659835004589507e-05, + "loss": 0.3877, + "step": 362 + }, + { + "epoch": 1.3, + "learning_rate": 1.2622473281062042e-05, + "loss": 0.3795, + "step": 363 + }, + { + "epoch": 1.3, + "learning_rate": 1.2585072205375424e-05, + "loss": 0.3607, + "step": 364 + }, + { + "epoch": 1.31, + "learning_rate": 1.2547632338760569e-05, + "loss": 0.3754, + "step": 365 + }, + { + "epoch": 1.31, + "learning_rate": 1.2510154243030482e-05, + "loss": 0.321, + "step": 366 + }, + { + "epoch": 1.31, + "learning_rate": 1.2472638480571817e-05, + "loss": 0.3514, + "step": 367 + }, + { + "epoch": 1.32, + "learning_rate": 1.2435085614336459e-05, + "loss": 0.3445, + "step": 368 + }, + { + "epoch": 1.32, + "learning_rate": 1.2397496207833046e-05, + "loss": 0.3527, + "step": 369 + }, + { + "epoch": 1.33, + "learning_rate": 1.2359870825118543e-05, + "loss": 0.4348, + "step": 370 + }, + { + "epoch": 1.33, + "learning_rate": 1.2322210030789759e-05, + "loss": 0.3978, + "step": 371 + }, + { + "epoch": 1.33, + "learning_rate": 1.228451438997488e-05, + "loss": 0.3501, + "step": 372 + }, + { + "epoch": 1.34, + "learning_rate": 1.2246784468324993e-05, + "loss": 0.3833, + "step": 373 + }, + { + "epoch": 1.34, + "learning_rate": 1.220902083200559e-05, + "loss": 0.3403, + "step": 374 + }, + { + "epoch": 1.34, + "learning_rate": 1.2171224047688084e-05, + "loss": 0.3921, + "step": 375 + }, + { + "epoch": 1.35, + "learning_rate": 1.2133394682541287e-05, + "loss": 0.311, + "step": 376 + }, + { + "epoch": 1.35, + "learning_rate": 1.209553330422292e-05, + "loss": 0.406, + "step": 377 + }, + { + "epoch": 1.35, + "learning_rate": 1.2057640480871084e-05, + "loss": 0.333, + "step": 378 + }, + { + "epoch": 1.36, + "learning_rate": 1.2019716781095732e-05, + "loss": 0.3709, + "step": 379 + }, + { + "epoch": 1.36, + "learning_rate": 1.1981762773970142e-05, + "loss": 0.3434, + "step": 380 + }, + { + "epoch": 1.37, + "learning_rate": 1.194377902902238e-05, + "loss": 0.3981, + "step": 381 + }, + { + "epoch": 1.37, + "learning_rate": 1.1905766116226746e-05, + "loss": 0.4167, + "step": 382 + }, + { + "epoch": 1.37, + "learning_rate": 1.186772460599523e-05, + "loss": 0.3312, + "step": 383 + }, + { + "epoch": 1.38, + "learning_rate": 1.1829655069168937e-05, + "loss": 0.3819, + "step": 384 + }, + { + "epoch": 1.38, + "learning_rate": 1.1791558077009548e-05, + "loss": 0.3875, + "step": 385 + }, + { + "epoch": 1.38, + "learning_rate": 1.1753434201190716e-05, + "loss": 0.3793, + "step": 386 + }, + { + "epoch": 1.39, + "learning_rate": 1.1715284013789514e-05, + "loss": 0.3499, + "step": 387 + }, + { + "epoch": 1.39, + "learning_rate": 1.1677108087277835e-05, + "loss": 0.3445, + "step": 388 + }, + { + "epoch": 1.39, + "learning_rate": 1.1638906994513805e-05, + "loss": 0.4091, + "step": 389 + }, + { + "epoch": 1.4, + "learning_rate": 1.1600681308733198e-05, + "loss": 0.4281, + "step": 390 + }, + { + "epoch": 1.4, + "learning_rate": 1.1562431603540807e-05, + "loss": 0.3548, + "step": 391 + }, + { + "epoch": 1.4, + "learning_rate": 1.1524158452901877e-05, + "loss": 0.3428, + "step": 392 + }, + { + "epoch": 1.41, + "learning_rate": 1.1485862431133445e-05, + "loss": 0.3889, + "step": 393 + }, + { + "epoch": 1.41, + "learning_rate": 1.1447544112895765e-05, + "loss": 0.36, + "step": 394 + }, + { + "epoch": 1.42, + "learning_rate": 1.1409204073183657e-05, + "loss": 0.3671, + "step": 395 + }, + { + "epoch": 1.42, + "learning_rate": 1.1370842887317888e-05, + "loss": 0.3925, + "step": 396 + }, + { + "epoch": 1.42, + "learning_rate": 1.1332461130936545e-05, + "loss": 0.3427, + "step": 397 + }, + { + "epoch": 1.43, + "learning_rate": 1.1294059379986384e-05, + "loss": 0.401, + "step": 398 + }, + { + "epoch": 1.43, + "learning_rate": 1.1255638210714198e-05, + "loss": 0.3303, + "step": 399 + }, + { + "epoch": 1.43, + "learning_rate": 1.121719819965816e-05, + "loss": 0.4695, + "step": 400 + }, + { + "epoch": 1.44, + "learning_rate": 1.117873992363919e-05, + "loss": 0.3225, + "step": 401 + }, + { + "epoch": 1.44, + "learning_rate": 1.1140263959752285e-05, + "loss": 0.3662, + "step": 402 + }, + { + "epoch": 1.44, + "learning_rate": 1.1101770885357843e-05, + "loss": 0.357, + "step": 403 + }, + { + "epoch": 1.45, + "learning_rate": 1.1063261278073044e-05, + "loss": 0.4042, + "step": 404 + }, + { + "epoch": 1.45, + "learning_rate": 1.1024735715763137e-05, + "loss": 0.3971, + "step": 405 + }, + { + "epoch": 1.45, + "learning_rate": 1.09861947765328e-05, + "loss": 0.3433, + "step": 406 + }, + { + "epoch": 1.46, + "learning_rate": 1.0947639038717446e-05, + "loss": 0.4021, + "step": 407 + }, + { + "epoch": 1.46, + "learning_rate": 1.0909069080874556e-05, + "loss": 0.3688, + "step": 408 + }, + { + "epoch": 1.47, + "learning_rate": 1.087048548177499e-05, + "loss": 0.3935, + "step": 409 + }, + { + "epoch": 1.47, + "learning_rate": 1.0831888820394306e-05, + "loss": 0.3496, + "step": 410 + }, + { + "epoch": 1.47, + "learning_rate": 1.0793279675904072e-05, + "loss": 0.34, + "step": 411 + }, + { + "epoch": 1.48, + "learning_rate": 1.0754658627663175e-05, + "loss": 0.3734, + "step": 412 + }, + { + "epoch": 1.48, + "learning_rate": 1.0716026255209124e-05, + "loss": 0.378, + "step": 413 + }, + { + "epoch": 1.48, + "learning_rate": 1.0677383138249362e-05, + "loss": 0.3178, + "step": 414 + }, + { + "epoch": 1.49, + "learning_rate": 1.0638729856652554e-05, + "loss": 0.3855, + "step": 415 + }, + { + "epoch": 1.49, + "learning_rate": 1.0600066990439895e-05, + "loss": 0.3495, + "step": 416 + }, + { + "epoch": 1.49, + "learning_rate": 1.0561395119776405e-05, + "loss": 0.3443, + "step": 417 + }, + { + "epoch": 1.5, + "learning_rate": 1.0522714824962228e-05, + "loss": 0.3604, + "step": 418 + }, + { + "epoch": 1.5, + "learning_rate": 1.0484026686423907e-05, + "loss": 0.3782, + "step": 419 + }, + { + "epoch": 1.5, + "learning_rate": 1.0445331284705695e-05, + "loss": 0.382, + "step": 420 + }, + { + "epoch": 1.51, + "learning_rate": 1.0406629200460836e-05, + "loss": 0.4019, + "step": 421 + }, + { + "epoch": 1.51, + "learning_rate": 1.0367921014442839e-05, + "loss": 0.3839, + "step": 422 + }, + { + "epoch": 1.52, + "learning_rate": 1.0329207307496785e-05, + "loss": 0.4177, + "step": 423 + }, + { + "epoch": 1.52, + "learning_rate": 1.02904886605506e-05, + "loss": 0.3711, + "step": 424 + }, + { + "epoch": 1.52, + "learning_rate": 1.0251765654606332e-05, + "loss": 0.4006, + "step": 425 + }, + { + "epoch": 1.53, + "learning_rate": 1.0213038870731443e-05, + "loss": 0.3476, + "step": 426 + }, + { + "epoch": 1.53, + "learning_rate": 1.0174308890050083e-05, + "loss": 0.4126, + "step": 427 + }, + { + "epoch": 1.53, + "learning_rate": 1.0135576293734381e-05, + "loss": 0.4101, + "step": 428 + }, + { + "epoch": 1.54, + "learning_rate": 1.0096841662995707e-05, + "loss": 0.3522, + "step": 429 + }, + { + "epoch": 1.54, + "learning_rate": 1.0058105579075958e-05, + "loss": 0.3981, + "step": 430 + }, + { + "epoch": 1.54, + "learning_rate": 1.0019368623238845e-05, + "loss": 0.3783, + "step": 431 + }, + { + "epoch": 1.55, + "learning_rate": 9.980631376761155e-06, + "loss": 0.3641, + "step": 432 + }, + { + "epoch": 1.55, + "learning_rate": 9.941894420924044e-06, + "loss": 0.3602, + "step": 433 + }, + { + "epoch": 1.55, + "learning_rate": 9.903158337004296e-06, + "loss": 0.3251, + "step": 434 + }, + { + "epoch": 1.56, + "learning_rate": 9.86442370626562e-06, + "loss": 0.3337, + "step": 435 + }, + { + "epoch": 1.56, + "learning_rate": 9.82569110994992e-06, + "loss": 0.4194, + "step": 436 + }, + { + "epoch": 1.57, + "learning_rate": 9.786961129268562e-06, + "loss": 0.3674, + "step": 437 + }, + { + "epoch": 1.57, + "learning_rate": 9.748234345393672e-06, + "loss": 0.355, + "step": 438 + }, + { + "epoch": 1.57, + "learning_rate": 9.709511339449405e-06, + "loss": 0.3123, + "step": 439 + }, + { + "epoch": 1.58, + "learning_rate": 9.670792692503218e-06, + "loss": 0.3669, + "step": 440 + }, + { + "epoch": 1.58, + "learning_rate": 9.632078985557163e-06, + "loss": 0.3285, + "step": 441 + }, + { + "epoch": 1.58, + "learning_rate": 9.593370799539168e-06, + "loss": 0.3798, + "step": 442 + }, + { + "epoch": 1.59, + "learning_rate": 9.554668715294305e-06, + "loss": 0.3643, + "step": 443 + }, + { + "epoch": 1.59, + "learning_rate": 9.515973313576094e-06, + "loss": 0.378, + "step": 444 + }, + { + "epoch": 1.59, + "learning_rate": 9.477285175037775e-06, + "loss": 0.3766, + "step": 445 + }, + { + "epoch": 1.6, + "learning_rate": 9.438604880223595e-06, + "loss": 0.3839, + "step": 446 + }, + { + "epoch": 1.6, + "learning_rate": 9.399933009560108e-06, + "loss": 0.352, + "step": 447 + }, + { + "epoch": 1.6, + "learning_rate": 9.361270143347452e-06, + "loss": 0.401, + "step": 448 + }, + { + "epoch": 1.61, + "learning_rate": 9.32261686175064e-06, + "loss": 0.4056, + "step": 449 + }, + { + "epoch": 1.61, + "learning_rate": 9.283973744790879e-06, + "loss": 0.3543, + "step": 450 + }, + { + "epoch": 1.62, + "learning_rate": 9.245341372336829e-06, + "loss": 0.3494, + "step": 451 + }, + { + "epoch": 1.62, + "learning_rate": 9.206720324095931e-06, + "loss": 0.4065, + "step": 452 + }, + { + "epoch": 1.62, + "learning_rate": 9.1681111796057e-06, + "loss": 0.3048, + "step": 453 + }, + { + "epoch": 1.63, + "learning_rate": 9.129514518225016e-06, + "loss": 0.3373, + "step": 454 + }, + { + "epoch": 1.63, + "learning_rate": 9.090930919125446e-06, + "loss": 0.3332, + "step": 455 + }, + { + "epoch": 1.63, + "learning_rate": 9.052360961282558e-06, + "loss": 0.3545, + "step": 456 + }, + { + "epoch": 1.64, + "learning_rate": 9.013805223467204e-06, + "loss": 0.3741, + "step": 457 + }, + { + "epoch": 1.64, + "learning_rate": 8.975264284236866e-06, + "loss": 0.3587, + "step": 458 + }, + { + "epoch": 1.64, + "learning_rate": 8.93673872192696e-06, + "loss": 0.3604, + "step": 459 + }, + { + "epoch": 1.65, + "learning_rate": 8.898229114642157e-06, + "loss": 0.3534, + "step": 460 + }, + { + "epoch": 1.65, + "learning_rate": 8.859736040247719e-06, + "loss": 0.3547, + "step": 461 + }, + { + "epoch": 1.66, + "learning_rate": 8.821260076360812e-06, + "loss": 0.3665, + "step": 462 + }, + { + "epoch": 1.66, + "learning_rate": 8.78280180034184e-06, + "loss": 0.3643, + "step": 463 + }, + { + "epoch": 1.66, + "learning_rate": 8.744361789285806e-06, + "loss": 0.3363, + "step": 464 + }, + { + "epoch": 1.67, + "learning_rate": 8.705940620013621e-06, + "loss": 0.4258, + "step": 465 + }, + { + "epoch": 1.67, + "learning_rate": 8.667538869063456e-06, + "loss": 0.3604, + "step": 466 + }, + { + "epoch": 1.67, + "learning_rate": 8.629157112682115e-06, + "loss": 0.376, + "step": 467 + }, + { + "epoch": 1.68, + "learning_rate": 8.590795926816348e-06, + "loss": 0.3199, + "step": 468 + }, + { + "epoch": 1.68, + "learning_rate": 8.552455887104238e-06, + "loss": 0.3135, + "step": 469 + }, + { + "epoch": 1.68, + "learning_rate": 8.514137568866558e-06, + "loss": 0.4133, + "step": 470 + }, + { + "epoch": 1.69, + "learning_rate": 8.475841547098128e-06, + "loss": 0.3431, + "step": 471 + }, + { + "epoch": 1.69, + "learning_rate": 8.437568396459193e-06, + "loss": 0.3722, + "step": 472 + }, + { + "epoch": 1.69, + "learning_rate": 8.399318691266806e-06, + "loss": 0.3392, + "step": 473 + }, + { + "epoch": 1.7, + "learning_rate": 8.361093005486198e-06, + "loss": 0.4159, + "step": 474 + }, + { + "epoch": 1.7, + "learning_rate": 8.322891912722168e-06, + "loss": 0.3209, + "step": 475 + }, + { + "epoch": 1.71, + "learning_rate": 8.28471598621049e-06, + "loss": 0.4085, + "step": 476 + }, + { + "epoch": 1.71, + "learning_rate": 8.246565798809289e-06, + "loss": 0.3674, + "step": 477 + }, + { + "epoch": 1.71, + "learning_rate": 8.208441922990454e-06, + "loss": 0.3601, + "step": 478 + }, + { + "epoch": 1.72, + "learning_rate": 8.170344930831066e-06, + "loss": 0.3424, + "step": 479 + }, + { + "epoch": 1.72, + "learning_rate": 8.132275394004772e-06, + "loss": 0.3245, + "step": 480 + }, + { + "epoch": 1.72, + "learning_rate": 8.094233883773255e-06, + "loss": 0.3564, + "step": 481 + }, + { + "epoch": 1.73, + "learning_rate": 8.056220970977622e-06, + "loss": 0.3988, + "step": 482 + }, + { + "epoch": 1.73, + "learning_rate": 8.01823722602986e-06, + "loss": 0.3307, + "step": 483 + }, + { + "epoch": 1.73, + "learning_rate": 7.980283218904272e-06, + "loss": 0.3465, + "step": 484 + }, + { + "epoch": 1.74, + "learning_rate": 7.942359519128919e-06, + "loss": 0.3747, + "step": 485 + }, + { + "epoch": 1.74, + "learning_rate": 7.904466695777082e-06, + "loss": 0.3353, + "step": 486 + }, + { + "epoch": 1.74, + "learning_rate": 7.866605317458715e-06, + "loss": 0.395, + "step": 487 + }, + { + "epoch": 1.75, + "learning_rate": 7.828775952311921e-06, + "loss": 0.36, + "step": 488 + }, + { + "epoch": 1.75, + "learning_rate": 7.79097916799441e-06, + "loss": 0.36, + "step": 489 + }, + { + "epoch": 1.76, + "learning_rate": 7.75321553167501e-06, + "loss": 0.3368, + "step": 490 + }, + { + "epoch": 1.76, + "learning_rate": 7.715485610025124e-06, + "loss": 0.3674, + "step": 491 + }, + { + "epoch": 1.76, + "learning_rate": 7.677789969210245e-06, + "loss": 0.3927, + "step": 492 + }, + { + "epoch": 1.77, + "learning_rate": 7.64012917488146e-06, + "loss": 0.3731, + "step": 493 + }, + { + "epoch": 1.77, + "learning_rate": 7.6025037921669585e-06, + "loss": 0.3057, + "step": 494 + }, + { + "epoch": 1.77, + "learning_rate": 7.564914385663543e-06, + "loss": 0.3633, + "step": 495 + }, + { + "epoch": 1.78, + "learning_rate": 7.5273615194281845e-06, + "loss": 0.3405, + "step": 496 + }, + { + "epoch": 1.78, + "learning_rate": 7.489845756969518e-06, + "loss": 0.3518, + "step": 497 + }, + { + "epoch": 1.78, + "learning_rate": 7.452367661239433e-06, + "loss": 0.3735, + "step": 498 + }, + { + "epoch": 1.79, + "learning_rate": 7.414927794624579e-06, + "loss": 0.3902, + "step": 499 + }, + { + "epoch": 1.79, + "learning_rate": 7.377526718937959e-06, + "loss": 0.3618, + "step": 500 + }, + { + "epoch": 1.79, + "learning_rate": 7.340164995410497e-06, + "loss": 0.3561, + "step": 501 + }, + { + "epoch": 1.8, + "learning_rate": 7.302843184682596e-06, + "loss": 0.3734, + "step": 502 + }, + { + "epoch": 1.8, + "learning_rate": 7.265561846795741e-06, + "loss": 0.3866, + "step": 503 + }, + { + "epoch": 1.81, + "learning_rate": 7.2283215411840975e-06, + "loss": 0.3289, + "step": 504 + }, + { + "epoch": 1.81, + "learning_rate": 7.1911228266661085e-06, + "loss": 0.3924, + "step": 505 + }, + { + "epoch": 1.81, + "learning_rate": 7.153966261436105e-06, + "loss": 0.3893, + "step": 506 + }, + { + "epoch": 1.82, + "learning_rate": 7.11685240305595e-06, + "loss": 0.3539, + "step": 507 + }, + { + "epoch": 1.82, + "learning_rate": 7.079781808446648e-06, + "loss": 0.2927, + "step": 508 + }, + { + "epoch": 1.82, + "learning_rate": 7.042755033879995e-06, + "loss": 0.3379, + "step": 509 + }, + { + "epoch": 1.83, + "learning_rate": 7.0057726349702495e-06, + "loss": 0.3467, + "step": 510 + }, + { + "epoch": 1.83, + "learning_rate": 6.968835166665774e-06, + "loss": 0.3213, + "step": 511 + }, + { + "epoch": 1.83, + "learning_rate": 6.931943183240699e-06, + "loss": 0.374, + "step": 512 + }, + { + "epoch": 1.84, + "learning_rate": 6.89509723828665e-06, + "loss": 0.3599, + "step": 513 + }, + { + "epoch": 1.84, + "learning_rate": 6.858297884704384e-06, + "loss": 0.375, + "step": 514 + }, + { + "epoch": 1.84, + "learning_rate": 6.8215456746955285e-06, + "loss": 0.3963, + "step": 515 + }, + { + "epoch": 1.85, + "learning_rate": 6.784841159754299e-06, + "loss": 0.3102, + "step": 516 + }, + { + "epoch": 1.85, + "learning_rate": 6.748184890659188e-06, + "loss": 0.3576, + "step": 517 + }, + { + "epoch": 1.86, + "learning_rate": 6.7115774174647475e-06, + "loss": 0.3423, + "step": 518 + }, + { + "epoch": 1.86, + "learning_rate": 6.675019289493294e-06, + "loss": 0.3516, + "step": 519 + }, + { + "epoch": 1.86, + "learning_rate": 6.638511055326685e-06, + "loss": 0.3702, + "step": 520 + }, + { + "epoch": 1.87, + "learning_rate": 6.602053262798091e-06, + "loss": 0.4085, + "step": 521 + }, + { + "epoch": 1.87, + "learning_rate": 6.565646458983765e-06, + "loss": 0.3816, + "step": 522 + }, + { + "epoch": 1.87, + "learning_rate": 6.529291190194829e-06, + "loss": 0.2939, + "step": 523 + }, + { + "epoch": 1.88, + "learning_rate": 6.492988001969098e-06, + "loss": 0.3334, + "step": 524 + }, + { + "epoch": 1.88, + "learning_rate": 6.4567374390628705e-06, + "loss": 0.364, + "step": 525 + }, + { + "epoch": 1.88, + "learning_rate": 6.420540045442756e-06, + "loss": 0.2818, + "step": 526 + }, + { + "epoch": 1.89, + "learning_rate": 6.38439636427754e-06, + "loss": 0.3477, + "step": 527 + }, + { + "epoch": 1.89, + "learning_rate": 6.348306937929991e-06, + "loss": 0.3407, + "step": 528 + }, + { + "epoch": 1.89, + "learning_rate": 6.312272307948755e-06, + "loss": 0.3565, + "step": 529 + }, + { + "epoch": 1.9, + "learning_rate": 6.27629301506022e-06, + "loss": 0.3384, + "step": 530 + }, + { + "epoch": 1.9, + "learning_rate": 6.240369599160393e-06, + "loss": 0.4058, + "step": 531 + }, + { + "epoch": 1.91, + "learning_rate": 6.204502599306805e-06, + "loss": 0.3668, + "step": 532 + }, + { + "epoch": 1.91, + "learning_rate": 6.1686925537104306e-06, + "loss": 0.3885, + "step": 533 + }, + { + "epoch": 1.91, + "learning_rate": 6.132939999727593e-06, + "loss": 0.3844, + "step": 534 + }, + { + "epoch": 1.92, + "learning_rate": 6.09724547385192e-06, + "loss": 0.3559, + "step": 535 + }, + { + "epoch": 1.92, + "learning_rate": 6.061609511706282e-06, + "loss": 0.3147, + "step": 536 + }, + { + "epoch": 1.92, + "learning_rate": 6.026032648034751e-06, + "loss": 0.3883, + "step": 537 + }, + { + "epoch": 1.93, + "learning_rate": 5.990515416694591e-06, + "loss": 0.3635, + "step": 538 + }, + { + "epoch": 1.93, + "learning_rate": 5.955058350648235e-06, + "loss": 0.3639, + "step": 539 + }, + { + "epoch": 1.93, + "learning_rate": 5.919661981955289e-06, + "loss": 0.3132, + "step": 540 + }, + { + "epoch": 1.94, + "learning_rate": 5.884326841764555e-06, + "loss": 0.3811, + "step": 541 + }, + { + "epoch": 1.94, + "learning_rate": 5.849053460306053e-06, + "loss": 0.3456, + "step": 542 + }, + { + "epoch": 1.94, + "learning_rate": 5.8138423668830605e-06, + "loss": 0.359, + "step": 543 + }, + { + "epoch": 1.95, + "learning_rate": 5.778694089864192e-06, + "loss": 0.4166, + "step": 544 + }, + { + "epoch": 1.95, + "learning_rate": 5.7436091566754445e-06, + "loss": 0.3695, + "step": 545 + }, + { + "epoch": 1.96, + "learning_rate": 5.7085880937922974e-06, + "loss": 0.3277, + "step": 546 + }, + { + "epoch": 1.96, + "learning_rate": 5.673631426731805e-06, + "loss": 0.377, + "step": 547 + }, + { + "epoch": 1.96, + "learning_rate": 5.638739680044718e-06, + "loss": 0.3193, + "step": 548 + }, + { + "epoch": 1.97, + "learning_rate": 5.603913377307604e-06, + "loss": 0.3717, + "step": 549 + }, + { + "epoch": 1.97, + "learning_rate": 5.5691530411150095e-06, + "loss": 0.3658, + "step": 550 + }, + { + "epoch": 1.97, + "learning_rate": 5.534459193071584e-06, + "loss": 0.3202, + "step": 551 + }, + { + "epoch": 1.98, + "learning_rate": 5.499832353784282e-06, + "loss": 0.3569, + "step": 552 + }, + { + "epoch": 1.98, + "learning_rate": 5.465273042854551e-06, + "loss": 0.366, + "step": 553 + }, + { + "epoch": 1.98, + "learning_rate": 5.430781778870506e-06, + "loss": 0.3094, + "step": 554 + }, + { + "epoch": 1.99, + "learning_rate": 5.396359079399194e-06, + "loss": 0.3616, + "step": 555 + }, + { + "epoch": 1.99, + "learning_rate": 5.36200546097877e-06, + "loss": 0.3434, + "step": 556 + }, + { + "epoch": 2.0, + "learning_rate": 5.327721439110791e-06, + "loss": 0.4494, + "step": 557 + }, + { + "epoch": 2.0, + "learning_rate": 5.293507528252474e-06, + "loss": 0.3772, + "step": 558 + }, + { + "epoch": 2.0, + "learning_rate": 5.259364241808957e-06, + "loss": 0.2895, + "step": 559 + }, + { + "epoch": 2.01, + "learning_rate": 5.225292092125611e-06, + "loss": 0.1797, + "step": 560 + }, + { + "epoch": 2.01, + "learning_rate": 5.191291590480343e-06, + "loss": 0.1427, + "step": 561 + }, + { + "epoch": 2.01, + "learning_rate": 5.157363247075931e-06, + "loss": 0.147, + "step": 562 + }, + { + "epoch": 2.02, + "learning_rate": 5.12350757103236e-06, + "loss": 0.115, + "step": 563 + }, + { + "epoch": 2.02, + "learning_rate": 5.089725070379203e-06, + "loss": 0.1493, + "step": 564 + }, + { + "epoch": 2.03, + "learning_rate": 5.056016252047967e-06, + "loss": 0.1248, + "step": 565 + }, + { + "epoch": 2.03, + "learning_rate": 5.022381621864496e-06, + "loss": 0.1538, + "step": 566 + }, + { + "epoch": 2.03, + "learning_rate": 4.988821684541403e-06, + "loss": 0.1174, + "step": 567 + }, + { + "epoch": 2.04, + "learning_rate": 4.95533694367047e-06, + "loss": 0.1192, + "step": 568 + }, + { + "epoch": 2.04, + "learning_rate": 4.921927901715099e-06, + "loss": 0.1254, + "step": 569 + }, + { + "epoch": 2.04, + "learning_rate": 4.888595060002776e-06, + "loss": 0.1477, + "step": 570 + }, + { + "epoch": 2.05, + "learning_rate": 4.8553389187175435e-06, + "loss": 0.1046, + "step": 571 + }, + { + "epoch": 2.05, + "learning_rate": 4.822159976892504e-06, + "loss": 0.0791, + "step": 572 + }, + { + "epoch": 2.05, + "learning_rate": 4.789058732402319e-06, + "loss": 0.0942, + "step": 573 + }, + { + "epoch": 2.06, + "learning_rate": 4.75603568195574e-06, + "loss": 0.114, + "step": 574 + }, + { + "epoch": 2.06, + "learning_rate": 4.7230913210881676e-06, + "loss": 0.1284, + "step": 575 + }, + { + "epoch": 2.06, + "learning_rate": 4.690226144154202e-06, + "loss": 0.1177, + "step": 576 + }, + { + "epoch": 2.07, + "learning_rate": 4.657440644320226e-06, + "loss": 0.0898, + "step": 577 + }, + { + "epoch": 2.07, + "learning_rate": 4.624735313557019e-06, + "loss": 0.0985, + "step": 578 + }, + { + "epoch": 2.08, + "learning_rate": 4.592110642632355e-06, + "loss": 0.1085, + "step": 579 + }, + { + "epoch": 2.08, + "learning_rate": 4.559567121103649e-06, + "loss": 0.1178, + "step": 580 + }, + { + "epoch": 2.08, + "learning_rate": 4.527105237310612e-06, + "loss": 0.1117, + "step": 581 + }, + { + "epoch": 2.09, + "learning_rate": 4.494725478367915e-06, + "loss": 0.1084, + "step": 582 + }, + { + "epoch": 2.09, + "learning_rate": 4.462428330157886e-06, + "loss": 0.1322, + "step": 583 + }, + { + "epoch": 2.09, + "learning_rate": 4.430214277323231e-06, + "loss": 0.1196, + "step": 584 + }, + { + "epoch": 2.1, + "learning_rate": 4.398083803259723e-06, + "loss": 0.0956, + "step": 585 + }, + { + "epoch": 2.1, + "learning_rate": 4.366037390108988e-06, + "loss": 0.1368, + "step": 586 + }, + { + "epoch": 2.1, + "learning_rate": 4.334075518751263e-06, + "loss": 0.1048, + "step": 587 + }, + { + "epoch": 2.11, + "learning_rate": 4.302198668798159e-06, + "loss": 0.1234, + "step": 588 + }, + { + "epoch": 2.11, + "learning_rate": 4.270407318585483e-06, + "loss": 0.0992, + "step": 589 + }, + { + "epoch": 2.11, + "learning_rate": 4.238701945166055e-06, + "loss": 0.0869, + "step": 590 + }, + { + "epoch": 2.12, + "learning_rate": 4.207083024302545e-06, + "loss": 0.1129, + "step": 591 + }, + { + "epoch": 2.12, + "learning_rate": 4.1755510304603505e-06, + "loss": 0.1136, + "step": 592 + }, + { + "epoch": 2.13, + "learning_rate": 4.144106436800453e-06, + "loss": 0.1164, + "step": 593 + }, + { + "epoch": 2.13, + "learning_rate": 4.112749715172329e-06, + "loss": 0.1168, + "step": 594 + }, + { + "epoch": 2.13, + "learning_rate": 4.081481336106878e-06, + "loss": 0.0917, + "step": 595 + }, + { + "epoch": 2.14, + "learning_rate": 4.050301768809346e-06, + "loss": 0.1123, + "step": 596 + }, + { + "epoch": 2.14, + "learning_rate": 4.019211481152294e-06, + "loss": 0.1042, + "step": 597 + }, + { + "epoch": 2.14, + "learning_rate": 3.9882109396685845e-06, + "loss": 0.1174, + "step": 598 + }, + { + "epoch": 2.15, + "learning_rate": 3.957300609544364e-06, + "loss": 0.1208, + "step": 599 + }, + { + "epoch": 2.15, + "learning_rate": 3.926480954612079e-06, + "loss": 0.139, + "step": 600 + }, + { + "epoch": 2.15, + "learning_rate": 3.895752437343555e-06, + "loss": 0.1049, + "step": 601 + }, + { + "epoch": 2.16, + "learning_rate": 3.865115518843008e-06, + "loss": 0.1052, + "step": 602 + }, + { + "epoch": 2.16, + "learning_rate": 3.834570658840152e-06, + "loss": 0.1156, + "step": 603 + }, + { + "epoch": 2.16, + "learning_rate": 3.804118315683296e-06, + "loss": 0.1193, + "step": 604 + }, + { + "epoch": 2.17, + "learning_rate": 3.7737589463324652e-06, + "loss": 0.1102, + "step": 605 + }, + { + "epoch": 2.17, + "learning_rate": 3.7434930063525386e-06, + "loss": 0.1395, + "step": 606 + }, + { + "epoch": 2.18, + "learning_rate": 3.713320949906429e-06, + "loss": 0.1132, + "step": 607 + }, + { + "epoch": 2.18, + "learning_rate": 3.683243229748249e-06, + "loss": 0.117, + "step": 608 + }, + { + "epoch": 2.18, + "learning_rate": 3.653260297216524e-06, + "loss": 0.118, + "step": 609 + }, + { + "epoch": 2.19, + "learning_rate": 3.623372602227425e-06, + "loss": 0.0862, + "step": 610 + }, + { + "epoch": 2.19, + "learning_rate": 3.593580593268008e-06, + "loss": 0.1143, + "step": 611 + }, + { + "epoch": 2.19, + "learning_rate": 3.5638847173895e-06, + "loss": 0.111, + "step": 612 + }, + { + "epoch": 2.2, + "learning_rate": 3.5342854202005696e-06, + "loss": 0.1125, + "step": 613 + }, + { + "epoch": 2.2, + "learning_rate": 3.504783145860644e-06, + "loss": 0.1267, + "step": 614 + }, + { + "epoch": 2.2, + "learning_rate": 3.4753783370732695e-06, + "loss": 0.124, + "step": 615 + }, + { + "epoch": 2.21, + "learning_rate": 3.4460714350794366e-06, + "loss": 0.1115, + "step": 616 + }, + { + "epoch": 2.21, + "learning_rate": 3.4168628796509706e-06, + "loss": 0.1026, + "step": 617 + }, + { + "epoch": 2.21, + "learning_rate": 3.3877531090839478e-06, + "loss": 0.1131, + "step": 618 + }, + { + "epoch": 2.22, + "learning_rate": 3.3587425601920833e-06, + "loss": 0.1008, + "step": 619 + }, + { + "epoch": 2.22, + "learning_rate": 3.3298316683002075e-06, + "loss": 0.1088, + "step": 620 + }, + { + "epoch": 2.23, + "learning_rate": 3.301020867237731e-06, + "loss": 0.0988, + "step": 621 + }, + { + "epoch": 2.23, + "learning_rate": 3.272310589332117e-06, + "loss": 0.115, + "step": 622 + }, + { + "epoch": 2.23, + "learning_rate": 3.2437012654024057e-06, + "loss": 0.1049, + "step": 623 + }, + { + "epoch": 2.24, + "learning_rate": 3.215193324752751e-06, + "loss": 0.1257, + "step": 624 + }, + { + "epoch": 2.24, + "learning_rate": 3.1867871951659735e-06, + "loss": 0.1026, + "step": 625 + }, + { + "epoch": 2.24, + "learning_rate": 3.1584833028971385e-06, + "loss": 0.1224, + "step": 626 + }, + { + "epoch": 2.25, + "learning_rate": 3.1302820726671766e-06, + "loss": 0.1357, + "step": 627 + }, + { + "epoch": 2.25, + "learning_rate": 3.102183927656488e-06, + "loss": 0.0885, + "step": 628 + }, + { + "epoch": 2.25, + "learning_rate": 3.0741892894986057e-06, + "loss": 0.1083, + "step": 629 + }, + { + "epoch": 2.26, + "learning_rate": 3.046298578273866e-06, + "loss": 0.1205, + "step": 630 + }, + { + "epoch": 2.26, + "learning_rate": 3.0185122125030984e-06, + "loss": 0.1149, + "step": 631 + }, + { + "epoch": 2.26, + "learning_rate": 2.9908306091413687e-06, + "loss": 0.0813, + "step": 632 + }, + { + "epoch": 2.27, + "learning_rate": 2.963254183571682e-06, + "loss": 0.1175, + "step": 633 + }, + { + "epoch": 2.27, + "learning_rate": 2.935783349598784e-06, + "loss": 0.1115, + "step": 634 + }, + { + "epoch": 2.28, + "learning_rate": 2.908418519442946e-06, + "loss": 0.1069, + "step": 635 + }, + { + "epoch": 2.28, + "learning_rate": 2.8811601037337633e-06, + "loss": 0.1055, + "step": 636 + }, + { + "epoch": 2.28, + "learning_rate": 2.8540085115040072e-06, + "loss": 0.1289, + "step": 637 + }, + { + "epoch": 2.29, + "learning_rate": 2.8269641501834834e-06, + "loss": 0.1332, + "step": 638 + }, + { + "epoch": 2.29, + "learning_rate": 2.8000274255929173e-06, + "loss": 0.0796, + "step": 639 + }, + { + "epoch": 2.29, + "learning_rate": 2.7731987419378636e-06, + "loss": 0.1097, + "step": 640 + }, + { + "epoch": 2.3, + "learning_rate": 2.7464785018026507e-06, + "loss": 0.1083, + "step": 641 + }, + { + "epoch": 2.3, + "learning_rate": 2.719867106144325e-06, + "loss": 0.1157, + "step": 642 + }, + { + "epoch": 2.3, + "learning_rate": 2.6933649542866326e-06, + "loss": 0.1165, + "step": 643 + }, + { + "epoch": 2.31, + "learning_rate": 2.666972443914052e-06, + "loss": 0.1062, + "step": 644 + }, + { + "epoch": 2.31, + "learning_rate": 2.6406899710657972e-06, + "loss": 0.1083, + "step": 645 + }, + { + "epoch": 2.31, + "learning_rate": 2.6145179301298973e-06, + "loss": 0.1046, + "step": 646 + }, + { + "epoch": 2.32, + "learning_rate": 2.588456713837263e-06, + "loss": 0.0909, + "step": 647 + }, + { + "epoch": 2.32, + "learning_rate": 2.562506713255789e-06, + "loss": 0.1267, + "step": 648 + }, + { + "epoch": 2.33, + "learning_rate": 2.5366683177845164e-06, + "loss": 0.1187, + "step": 649 + }, + { + "epoch": 2.33, + "learning_rate": 2.5109419151477544e-06, + "loss": 0.1445, + "step": 650 + }, + { + "epoch": 2.33, + "learning_rate": 2.4853278913892796e-06, + "loss": 0.1248, + "step": 651 + }, + { + "epoch": 2.34, + "learning_rate": 2.4598266308665418e-06, + "loss": 0.1078, + "step": 652 + }, + { + "epoch": 2.34, + "learning_rate": 2.4344385162448924e-06, + "loss": 0.0979, + "step": 653 + }, + { + "epoch": 2.34, + "learning_rate": 2.4091639284918443e-06, + "loss": 0.1369, + "step": 654 + }, + { + "epoch": 2.35, + "learning_rate": 2.3840032468713602e-06, + "loss": 0.1071, + "step": 655 + }, + { + "epoch": 2.35, + "learning_rate": 2.3589568489381533e-06, + "loss": 0.1045, + "step": 656 + }, + { + "epoch": 2.35, + "learning_rate": 2.3340251105320233e-06, + "loss": 0.1034, + "step": 657 + }, + { + "epoch": 2.36, + "learning_rate": 2.309208405772221e-06, + "loss": 0.1355, + "step": 658 + }, + { + "epoch": 2.36, + "learning_rate": 2.284507107051831e-06, + "loss": 0.0955, + "step": 659 + }, + { + "epoch": 2.37, + "learning_rate": 2.259921585032183e-06, + "loss": 0.1051, + "step": 660 + }, + { + "epoch": 2.37, + "learning_rate": 2.235452208637301e-06, + "loss": 0.1039, + "step": 661 + }, + { + "epoch": 2.37, + "learning_rate": 2.211099345048339e-06, + "loss": 0.1052, + "step": 662 + }, + { + "epoch": 2.38, + "learning_rate": 2.186863359698108e-06, + "loss": 0.1058, + "step": 663 + }, + { + "epoch": 2.38, + "learning_rate": 2.1627446162655653e-06, + "loss": 0.1158, + "step": 664 + }, + { + "epoch": 2.38, + "learning_rate": 2.138743476670366e-06, + "loss": 0.0962, + "step": 665 + }, + { + "epoch": 2.39, + "learning_rate": 2.1148603010674405e-06, + "loss": 0.1075, + "step": 666 + }, + { + "epoch": 2.39, + "learning_rate": 2.0910954478415678e-06, + "loss": 0.097, + "step": 667 + }, + { + "epoch": 2.39, + "learning_rate": 2.06744927360202e-06, + "loss": 0.0929, + "step": 668 + }, + { + "epoch": 2.4, + "learning_rate": 2.0439221331772075e-06, + "loss": 0.1006, + "step": 669 + }, + { + "epoch": 2.4, + "learning_rate": 2.0205143796093417e-06, + "loss": 0.1171, + "step": 670 + }, + { + "epoch": 2.4, + "learning_rate": 1.9972263641491486e-06, + "loss": 0.137, + "step": 671 + }, + { + "epoch": 2.41, + "learning_rate": 1.9740584362505954e-06, + "loss": 0.1056, + "step": 672 + }, + { + "epoch": 2.41, + "learning_rate": 1.9510109435656457e-06, + "loss": 0.1018, + "step": 673 + }, + { + "epoch": 2.42, + "learning_rate": 1.92808423193904e-06, + "loss": 0.0991, + "step": 674 + }, + { + "epoch": 2.42, + "learning_rate": 1.9052786454031192e-06, + "loss": 0.0935, + "step": 675 + }, + { + "epoch": 2.42, + "learning_rate": 1.8825945261726442e-06, + "loss": 0.0897, + "step": 676 + }, + { + "epoch": 2.43, + "learning_rate": 1.8600322146396644e-06, + "loss": 0.1088, + "step": 677 + }, + { + "epoch": 2.43, + "learning_rate": 1.8375920493684264e-06, + "loss": 0.1095, + "step": 678 + }, + { + "epoch": 2.43, + "learning_rate": 1.815274367090274e-06, + "loss": 0.1127, + "step": 679 + }, + { + "epoch": 2.44, + "learning_rate": 1.7930795026986025e-06, + "loss": 0.0975, + "step": 680 + }, + { + "epoch": 2.44, + "learning_rate": 1.7710077892438348e-06, + "loss": 0.0967, + "step": 681 + }, + { + "epoch": 2.44, + "learning_rate": 1.7490595579284231e-06, + "loss": 0.1037, + "step": 682 + }, + { + "epoch": 2.45, + "learning_rate": 1.7272351381018792e-06, + "loss": 0.1152, + "step": 683 + }, + { + "epoch": 2.45, + "learning_rate": 1.7055348572558316e-06, + "loss": 0.1145, + "step": 684 + }, + { + "epoch": 2.45, + "learning_rate": 1.6839590410191076e-06, + "loss": 0.1186, + "step": 685 + }, + { + "epoch": 2.46, + "learning_rate": 1.6625080131528538e-06, + "loss": 0.1078, + "step": 686 + }, + { + "epoch": 2.46, + "learning_rate": 1.6411820955456737e-06, + "loss": 0.0923, + "step": 687 + }, + { + "epoch": 2.47, + "learning_rate": 1.619981608208796e-06, + "loss": 0.1031, + "step": 688 + }, + { + "epoch": 2.47, + "learning_rate": 1.5989068692712827e-06, + "loss": 0.1206, + "step": 689 + }, + { + "epoch": 2.47, + "learning_rate": 1.5779581949752408e-06, + "loss": 0.1184, + "step": 690 + }, + { + "epoch": 2.48, + "learning_rate": 1.5571358996710862e-06, + "loss": 0.0985, + "step": 691 + }, + { + "epoch": 2.48, + "learning_rate": 1.536440295812821e-06, + "loss": 0.1015, + "step": 692 + }, + { + "epoch": 2.48, + "learning_rate": 1.5158716939533524e-06, + "loss": 0.1028, + "step": 693 + }, + { + "epoch": 2.49, + "learning_rate": 1.4954304027398236e-06, + "loss": 0.1073, + "step": 694 + }, + { + "epoch": 2.49, + "learning_rate": 1.4751167289089974e-06, + "loss": 0.1044, + "step": 695 + }, + { + "epoch": 2.49, + "learning_rate": 1.4549309772826291e-06, + "loss": 0.0924, + "step": 696 + }, + { + "epoch": 2.5, + "learning_rate": 1.4348734507629114e-06, + "loss": 0.1274, + "step": 697 + }, + { + "epoch": 2.5, + "learning_rate": 1.4149444503279297e-06, + "loss": 0.1162, + "step": 698 + }, + { + "epoch": 2.5, + "learning_rate": 1.3951442750271349e-06, + "loss": 0.139, + "step": 699 + }, + { + "epoch": 2.51, + "learning_rate": 1.3754732219768619e-06, + "loss": 0.0789, + "step": 700 + }, + { + "epoch": 2.51, + "learning_rate": 1.3559315863558697e-06, + "loss": 0.1139, + "step": 701 + }, + { + "epoch": 2.52, + "learning_rate": 1.3365196614009101e-06, + "loss": 0.104, + "step": 702 + }, + { + "epoch": 2.52, + "learning_rate": 1.3172377384023393e-06, + "loss": 0.1339, + "step": 703 + }, + { + "epoch": 2.52, + "learning_rate": 1.2980861066997296e-06, + "loss": 0.1264, + "step": 704 + }, + { + "epoch": 2.53, + "learning_rate": 1.2790650536775363e-06, + "loss": 0.095, + "step": 705 + }, + { + "epoch": 2.53, + "learning_rate": 1.2601748647607858e-06, + "loss": 0.093, + "step": 706 + }, + { + "epoch": 2.53, + "learning_rate": 1.2414158234107921e-06, + "loss": 0.1233, + "step": 707 + }, + { + "epoch": 2.54, + "learning_rate": 1.2227882111209011e-06, + "loss": 0.1064, + "step": 708 + }, + { + "epoch": 2.54, + "learning_rate": 1.2042923074122704e-06, + "loss": 0.1391, + "step": 709 + }, + { + "epoch": 2.54, + "learning_rate": 1.1859283898296735e-06, + "loss": 0.1035, + "step": 710 + }, + { + "epoch": 2.55, + "learning_rate": 1.1676967339373247e-06, + "loss": 0.1091, + "step": 711 + }, + { + "epoch": 2.55, + "learning_rate": 1.1495976133147669e-06, + "loss": 0.0833, + "step": 712 + }, + { + "epoch": 2.55, + "learning_rate": 1.1316312995527424e-06, + "loss": 0.0992, + "step": 713 + }, + { + "epoch": 2.56, + "learning_rate": 1.113798062249134e-06, + "loss": 0.1234, + "step": 714 + }, + { + "epoch": 2.56, + "learning_rate": 1.09609816900491e-06, + "loss": 0.1092, + "step": 715 + }, + { + "epoch": 2.57, + "learning_rate": 1.0785318854201144e-06, + "loss": 0.1309, + "step": 716 + }, + { + "epoch": 2.57, + "learning_rate": 1.061099475089874e-06, + "loss": 0.1183, + "step": 717 + }, + { + "epoch": 2.57, + "learning_rate": 1.0438011996004581e-06, + "loss": 0.0984, + "step": 718 + }, + { + "epoch": 2.58, + "learning_rate": 1.0266373185253331e-06, + "loss": 0.1039, + "step": 719 + }, + { + "epoch": 2.58, + "learning_rate": 1.0096080894212833e-06, + "loss": 0.1078, + "step": 720 + }, + { + "epoch": 2.58, + "learning_rate": 9.927137678245359e-07, + "loss": 0.1449, + "step": 721 + }, + { + "epoch": 2.59, + "learning_rate": 9.759546072469328e-07, + "loss": 0.0881, + "step": 722 + }, + { + "epoch": 2.59, + "learning_rate": 9.593308591721274e-07, + "loss": 0.0843, + "step": 723 + }, + { + "epoch": 2.59, + "learning_rate": 9.428427730518053e-07, + "loss": 0.0902, + "step": 724 + }, + { + "epoch": 2.6, + "learning_rate": 9.264905963019377e-07, + "loss": 0.081, + "step": 725 + }, + { + "epoch": 2.6, + "learning_rate": 9.102745742990871e-07, + "loss": 0.1284, + "step": 726 + }, + { + "epoch": 2.6, + "learning_rate": 8.941949503767033e-07, + "loss": 0.0951, + "step": 727 + }, + { + "epoch": 2.61, + "learning_rate": 8.78251965821485e-07, + "loss": 0.0968, + "step": 728 + }, + { + "epoch": 2.61, + "learning_rate": 8.624458598697582e-07, + "loss": 0.0866, + "step": 729 + }, + { + "epoch": 2.62, + "learning_rate": 8.46776869703877e-07, + "loss": 0.1007, + "step": 730 + }, + { + "epoch": 2.62, + "learning_rate": 8.312452304486763e-07, + "loss": 0.1365, + "step": 731 + }, + { + "epoch": 2.62, + "learning_rate": 8.158511751679399e-07, + "loss": 0.1058, + "step": 732 + }, + { + "epoch": 2.63, + "learning_rate": 8.005949348608977e-07, + "loss": 0.072, + "step": 733 + }, + { + "epoch": 2.63, + "learning_rate": 7.85476738458767e-07, + "loss": 0.1178, + "step": 734 + }, + { + "epoch": 2.63, + "learning_rate": 7.704968128213108e-07, + "loss": 0.1111, + "step": 735 + }, + { + "epoch": 2.64, + "learning_rate": 7.556553827334368e-07, + "loss": 0.1099, + "step": 736 + }, + { + "epoch": 2.64, + "learning_rate": 7.409526709018289e-07, + "loss": 0.1057, + "step": 737 + }, + { + "epoch": 2.64, + "learning_rate": 7.263888979515954e-07, + "loss": 0.0977, + "step": 738 + }, + { + "epoch": 2.65, + "learning_rate": 7.119642824229655e-07, + "loss": 0.1156, + "step": 739 + }, + { + "epoch": 2.65, + "learning_rate": 6.976790407680068e-07, + "loss": 0.078, + "step": 740 + }, + { + "epoch": 2.66, + "learning_rate": 6.835333873473793e-07, + "loss": 0.1214, + "step": 741 + }, + { + "epoch": 2.66, + "learning_rate": 6.695275344271168e-07, + "loss": 0.1052, + "step": 742 + }, + { + "epoch": 2.66, + "learning_rate": 6.556616921754489e-07, + "loss": 0.1021, + "step": 743 + }, + { + "epoch": 2.67, + "learning_rate": 6.419360686596299e-07, + "loss": 0.1136, + "step": 744 + }, + { + "epoch": 2.67, + "learning_rate": 6.283508698428353e-07, + "loss": 0.1151, + "step": 745 + }, + { + "epoch": 2.67, + "learning_rate": 6.14906299581064e-07, + "loss": 0.0984, + "step": 746 + }, + { + "epoch": 2.68, + "learning_rate": 6.01602559620077e-07, + "loss": 0.0857, + "step": 747 + }, + { + "epoch": 2.68, + "learning_rate": 5.884398495923727e-07, + "loss": 0.1283, + "step": 748 + }, + { + "epoch": 2.68, + "learning_rate": 5.754183670141888e-07, + "loss": 0.1021, + "step": 749 + }, + { + "epoch": 2.69, + "learning_rate": 5.62538307282543e-07, + "loss": 0.092, + "step": 750 + }, + { + "epoch": 2.69, + "learning_rate": 5.497998636722956e-07, + "loss": 0.1514, + "step": 751 + }, + { + "epoch": 2.69, + "learning_rate": 5.37203227333255e-07, + "loss": 0.1, + "step": 752 + }, + { + "epoch": 2.7, + "learning_rate": 5.247485872873026e-07, + "loss": 0.0851, + "step": 753 + }, + { + "epoch": 2.7, + "learning_rate": 5.124361304255632e-07, + "loss": 0.0732, + "step": 754 + }, + { + "epoch": 2.71, + "learning_rate": 5.002660415055949e-07, + "loss": 0.1175, + "step": 755 + }, + { + "epoch": 2.71, + "learning_rate": 4.882385031486192e-07, + "loss": 0.1262, + "step": 756 + }, + { + "epoch": 2.71, + "learning_rate": 4.763536958367843e-07, + "loss": 0.1056, + "step": 757 + }, + { + "epoch": 2.72, + "learning_rate": 4.6461179791044806e-07, + "loss": 0.122, + "step": 758 + }, + { + "epoch": 2.72, + "learning_rate": 4.5301298556550745e-07, + "loss": 0.0958, + "step": 759 + }, + { + "epoch": 2.72, + "learning_rate": 4.415574328507577e-07, + "loss": 0.081, + "step": 760 + }, + { + "epoch": 2.73, + "learning_rate": 4.3024531166527494e-07, + "loss": 0.1189, + "step": 761 + }, + { + "epoch": 2.73, + "learning_rate": 4.1907679175583696e-07, + "loss": 0.0962, + "step": 762 + }, + { + "epoch": 2.73, + "learning_rate": 4.0805204071437953e-07, + "loss": 0.1148, + "step": 763 + }, + { + "epoch": 2.74, + "learning_rate": 3.9717122397548104e-07, + "loss": 0.1212, + "step": 764 + }, + { + "epoch": 2.74, + "learning_rate": 3.8643450481387513e-07, + "loss": 0.1204, + "step": 765 + }, + { + "epoch": 2.74, + "learning_rate": 3.7584204434200857e-07, + "loss": 0.1256, + "step": 766 + }, + { + "epoch": 2.75, + "learning_rate": 3.6539400150761517e-07, + "loss": 0.1088, + "step": 767 + }, + { + "epoch": 2.75, + "learning_rate": 3.55090533091339e-07, + "loss": 0.1006, + "step": 768 + }, + { + "epoch": 2.76, + "learning_rate": 3.449317937043728e-07, + "loss": 0.1383, + "step": 769 + }, + { + "epoch": 2.76, + "learning_rate": 3.349179357861487e-07, + "loss": 0.0906, + "step": 770 + }, + { + "epoch": 2.76, + "learning_rate": 3.2504910960203694e-07, + "loss": 0.0846, + "step": 771 + }, + { + "epoch": 2.77, + "learning_rate": 3.153254632411096e-07, + "loss": 0.1098, + "step": 772 + }, + { + "epoch": 2.77, + "learning_rate": 3.057471426138958e-07, + "loss": 0.1118, + "step": 773 + }, + { + "epoch": 2.77, + "learning_rate": 2.963142914502137e-07, + "loss": 0.1211, + "step": 774 + }, + { + "epoch": 2.78, + "learning_rate": 2.870270512969986e-07, + "loss": 0.137, + "step": 775 + }, + { + "epoch": 2.78, + "learning_rate": 2.7788556151618463e-07, + "loss": 0.0953, + "step": 776 + }, + { + "epoch": 2.78, + "learning_rate": 2.6888995928262e-07, + "loss": 0.118, + "step": 777 + }, + { + "epoch": 2.79, + "learning_rate": 2.6004037958199167e-07, + "loss": 0.1092, + "step": 778 + }, + { + "epoch": 2.79, + "learning_rate": 2.5133695520881516e-07, + "loss": 0.1221, + "step": 779 + }, + { + "epoch": 2.79, + "learning_rate": 2.4277981676444017e-07, + "loss": 0.1182, + "step": 780 + }, + { + "epoch": 2.8, + "learning_rate": 2.3436909265508235e-07, + "loss": 0.0971, + "step": 781 + }, + { + "epoch": 2.8, + "learning_rate": 2.2610490908990367e-07, + "loss": 0.1065, + "step": 782 + }, + { + "epoch": 2.81, + "learning_rate": 2.1798739007911517e-07, + "loss": 0.0921, + "step": 783 + }, + { + "epoch": 2.81, + "learning_rate": 2.100166574321172e-07, + "loss": 0.0998, + "step": 784 + }, + { + "epoch": 2.81, + "learning_rate": 2.021928307556742e-07, + "loss": 0.1185, + "step": 785 + }, + { + "epoch": 2.82, + "learning_rate": 1.9451602745211518e-07, + "loss": 0.1116, + "step": 786 + }, + { + "epoch": 2.82, + "learning_rate": 1.8698636271757608e-07, + "loss": 0.0869, + "step": 787 + }, + { + "epoch": 2.82, + "learning_rate": 1.796039495402646e-07, + "loss": 0.1073, + "step": 788 + }, + { + "epoch": 2.83, + "learning_rate": 1.7236889869877592e-07, + "loss": 0.0918, + "step": 789 + }, + { + "epoch": 2.83, + "learning_rate": 1.6528131876042187e-07, + "loss": 0.1262, + "step": 790 + }, + { + "epoch": 2.83, + "learning_rate": 1.583413160795999e-07, + "loss": 0.1169, + "step": 791 + }, + { + "epoch": 2.84, + "learning_rate": 1.5154899479620677e-07, + "loss": 0.11, + "step": 792 + }, + { + "epoch": 2.84, + "learning_rate": 1.449044568340663e-07, + "loss": 0.1153, + "step": 793 + }, + { + "epoch": 2.84, + "learning_rate": 1.3840780189940507e-07, + "loss": 0.0995, + "step": 794 + }, + { + "epoch": 2.85, + "learning_rate": 1.320591274793559e-07, + "loss": 0.1225, + "step": 795 + }, + { + "epoch": 2.85, + "learning_rate": 1.2585852884049343e-07, + "loss": 0.116, + "step": 796 + }, + { + "epoch": 2.86, + "learning_rate": 1.1980609902740413e-07, + "loss": 0.1126, + "step": 797 + }, + { + "epoch": 2.86, + "learning_rate": 1.1390192886129304e-07, + "loss": 0.0833, + "step": 798 + }, + { + "epoch": 2.86, + "learning_rate": 1.0814610693861694e-07, + "loss": 0.1178, + "step": 799 + }, + { + "epoch": 2.87, + "learning_rate": 1.0253871962976003e-07, + "loss": 0.103, + "step": 800 + }, + { + "epoch": 2.87, + "learning_rate": 9.707985107773266e-08, + "loss": 0.1308, + "step": 801 + }, + { + "epoch": 2.87, + "learning_rate": 9.17695831969101e-08, + "loss": 0.1254, + "step": 802 + }, + { + "epoch": 2.88, + "learning_rate": 8.6607995671808e-08, + "loss": 0.107, + "step": 803 + }, + { + "epoch": 2.88, + "learning_rate": 8.159516595587779e-08, + "loss": 0.1203, + "step": 804 + }, + { + "epoch": 2.88, + "learning_rate": 7.673116927035318e-08, + "loss": 0.133, + "step": 805 + }, + { + "epoch": 2.89, + "learning_rate": 7.201607860311877e-08, + "loss": 0.1112, + "step": 806 + }, + { + "epoch": 2.89, + "learning_rate": 6.744996470760767e-08, + "loss": 0.1349, + "step": 807 + }, + { + "epoch": 2.89, + "learning_rate": 6.303289610175233e-08, + "loss": 0.0754, + "step": 808 + }, + { + "epoch": 2.9, + "learning_rate": 5.876493906694758e-08, + "loss": 0.1184, + "step": 809 + }, + { + "epoch": 2.9, + "learning_rate": 5.464615764705805e-08, + "loss": 0.0848, + "step": 810 + }, + { + "epoch": 2.91, + "learning_rate": 5.0676613647457906e-08, + "loss": 0.1011, + "step": 811 + }, + { + "epoch": 2.91, + "learning_rate": 4.6856366634101534e-08, + "loss": 0.109, + "step": 812 + }, + { + "epoch": 2.91, + "learning_rate": 4.318547393263317e-08, + "loss": 0.094, + "step": 813 + }, + { + "epoch": 2.92, + "learning_rate": 3.966399062752535e-08, + "loss": 0.1202, + "step": 814 + }, + { + "epoch": 2.92, + "learning_rate": 3.6291969561248476e-08, + "loss": 0.1031, + "step": 815 + }, + { + "epoch": 2.92, + "learning_rate": 3.3069461333483655e-08, + "loss": 0.0668, + "step": 816 + }, + { + "epoch": 2.93, + "learning_rate": 2.999651430035999e-08, + "loss": 0.1109, + "step": 817 + }, + { + "epoch": 2.93, + "learning_rate": 2.70731745737296e-08, + "loss": 0.0852, + "step": 818 + }, + { + "epoch": 2.93, + "learning_rate": 2.4299486020475937e-08, + "loss": 0.0745, + "step": 819 + }, + { + "epoch": 2.94, + "learning_rate": 2.1675490261856558e-08, + "loss": 0.1148, + "step": 820 + }, + { + "epoch": 2.94, + "learning_rate": 1.9201226672875827e-08, + "loss": 0.0791, + "step": 821 + }, + { + "epoch": 2.94, + "learning_rate": 1.6876732381696515e-08, + "loss": 0.0996, + "step": 822 + }, + { + "epoch": 2.95, + "learning_rate": 1.470204226908134e-08, + "loss": 0.1019, + "step": 823 + }, + { + "epoch": 2.95, + "learning_rate": 1.2677188967871179e-08, + "loss": 0.1051, + "step": 824 + }, + { + "epoch": 2.96, + "learning_rate": 1.0802202862492117e-08, + "loss": 0.1042, + "step": 825 + }, + { + "epoch": 2.96, + "learning_rate": 9.077112088505813e-09, + "loss": 0.1008, + "step": 826 + }, + { + "epoch": 2.96, + "learning_rate": 7.50194253217762e-09, + "loss": 0.1271, + "step": 827 + }, + { + "epoch": 2.97, + "learning_rate": 6.076717830098e-09, + "loss": 0.1136, + "step": 828 + }, + { + "epoch": 2.97, + "learning_rate": 4.801459368822814e-09, + "loss": 0.1031, + "step": 829 + }, + { + "epoch": 2.97, + "learning_rate": 3.6761862845502427e-09, + "loss": 0.1256, + "step": 830 + }, + { + "epoch": 2.98, + "learning_rate": 2.7009154628399036e-09, + "loss": 0.1002, + "step": 831 + }, + { + "epoch": 2.98, + "learning_rate": 1.875661538355278e-09, + "loss": 0.114, + "step": 832 + }, + { + "epoch": 2.98, + "learning_rate": 1.2004368946427758e-09, + "loss": 0.1177, + "step": 833 + }, + { + "epoch": 2.99, + "learning_rate": 6.752516639507711e-10, + "loss": 0.1372, + "step": 834 + }, + { + "epoch": 2.99, + "learning_rate": 3.001137270730592e-10, + "loss": 0.0992, + "step": 835 + }, + { + "epoch": 3.0, + "learning_rate": 7.502871323339378e-11, + "loss": 0.1098, + "step": 836 + }, + { + "epoch": 3.0, + "learning_rate": 0.0, + "loss": 0.1123, + "step": 837 + }, + { + "epoch": 3.0, + "step": 837, + "total_flos": 9.878198526620467e+16, + "train_loss": 0.4548445687303264, + "train_runtime": 3465.3771, + "train_samples_per_second": 15.473, + "train_steps_per_second": 0.242 + } + ], + "max_steps": 837, + "num_train_epochs": 3, + "total_flos": 9.878198526620467e+16, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..12dd211a26807bc410b52ed6ec6082f767d9aa54 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93499e6d2b72f466e8db31be3266bf88f883698f46eeef49a084987dc0e7e0de +size 3707