Upload folder using huggingface_hub

checkpoint-1000/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4f851237b7a0755e0cbdb41b0297f38e5fa2f981f8eb78180a9a32e3328443
+size 28442834134

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2807191e3b5063f5f0a185ef4d36caa911e19d4eddcf54828cb5ae4153d4b279
+size 14221467522

checkpoint-1000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca36311bbd57901806c620666131a44cde8c190cbf5560d295f16934f982a60
+size 15984

checkpoint-1000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6513186409e1e6081bcca47cc4ff01d87ecd1af0291a404c7e78e9524b0a0418
+size 15984

checkpoint-1000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5fcb7a571caaabb18c46317925a84fceed83d237d51d219894eec507842a52
+size 15984

checkpoint-1000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b9eeca5ef68429a6920538de6a374f3d77603f82da23762d3bb5a0dd5e3c82
+size 15984

checkpoint-1000/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2cddacb3f050a2319baea833d0fb0821a788cce7e9c287d27e512999355648
+size 15984

checkpoint-1000/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba6d68d5c751e88d19b0c12593ea9e0aa4e416ce95c720be54228e38334c24cf
+size 15984

checkpoint-1000/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5924ad176078fb57aaeca6a01dc2a6669118eec88c0b436d823c438527ab46
+size 15984

checkpoint-1000/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff1590184d5fd27f49e8f0c4e2ad8d9d147db3dfe018cd0c2d1f4428f0b19d4d
+size 15984

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2895b0e3f1c28bf5c8fcf1e694d1dd1665857bd510ab8f8631b1e346e84826c
+size 1064

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f768ad49686ec36b5a8b570468ea76bd56614d5acbd36a18ffbbf3ba397fe3e
+size 4728

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc047d75f5def686fee76a6b48cf2442208e63ffde523cfd873e46d059b0be5
+size 28442834134

checkpoint-500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab470f8cc790ad6406631b14b1b0a4aa3dbc9b949a3b09ded273d3fd9a54e153
+size 14221467522

checkpoint-500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316f8f4ba01b8af4eacf324be0e9dcd61cc461a2f357b6d03d35d0096273c67f
+size 15920

checkpoint-500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f89d809197df5975468e91a28e06dddf2b23368e1b7031b7c922bae4eb54bfa
+size 15920

checkpoint-500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b265bf483088ec1468a8dab2adf69dd0fd177cbc8d5577b6b8d0aa0796de4348
+size 15920

checkpoint-500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abbcc0bb563141e251842f9994c1f53fd688d0858f5936ff06b69535c4a6ec8c
+size 15920

checkpoint-500/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8606ebf688c0e0478e77e9538aa3265e84b6c60f6e3e7ddd56b67ead26cc8c22
+size 15920

checkpoint-500/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76119ff45a6e3986f100f8ef46b98b8849ba353b26d7dc187d97188d8d57f1a6
+size 15920

checkpoint-500/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ecd755eaf7f75cfc2075fbf76eca964f09d3cdcbb3caa0c3e97c3a386f660db
+size 15920

checkpoint-500/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfbd310549d8eaa959e0e6f6bbd6ef9e84bec6bc7fda2341c53b9c192d0478a2
+size 15920

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d340feb7bcf864481a7391a71f0217c0632c294086494acb7f8c90d216e571b3
+size 1064

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,3019 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.10434056761268781,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.263157894736843e-07,
+      "loss": 5.6888,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 5.0454,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 4.8812,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 4.4258,
+      "step": 4
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 3.3052,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 2.6706,
+      "step": 6
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 1.8629,
+      "step": 7
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 1.3825,
+      "step": 8
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 1.2787,
+      "step": 9
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 0.9156,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.789473684210527e-06,
+      "loss": 0.765,
+      "step": 11
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.31578947368421e-06,
+      "loss": 0.7249,
+      "step": 12
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.6445,
+      "step": 13
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.368421052631579e-06,
+      "loss": 0.5672,
+      "step": 14
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.894736842105265e-06,
+      "loss": 0.6509,
+      "step": 15
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 0.4831,
+      "step": 16
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.947368421052632e-06,
+      "loss": 0.4905,
+      "step": 17
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.473684210526315e-06,
+      "loss": 0.4829,
+      "step": 18
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1e-05,
+      "loss": 0.4507,
+      "step": 19
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.4224,
+      "step": 20
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.105263157894737e-05,
+      "loss": 0.5246,
+      "step": 21
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.1578947368421053e-05,
+      "loss": 0.466,
+      "step": 22
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.2105263157894737e-05,
+      "loss": 0.4438,
+      "step": 23
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.263157894736842e-05,
+      "loss": 0.3526,
+      "step": 24
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3157894736842108e-05,
+      "loss": 0.4781,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3684210526315791e-05,
+      "loss": 0.352,
+      "step": 26
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4210526315789475e-05,
+      "loss": 0.4221,
+      "step": 27
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.4736842105263159e-05,
+      "loss": 0.4257,
+      "step": 28
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5263157894736846e-05,
+      "loss": 0.5535,
+      "step": 29
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.578947368421053e-05,
+      "loss": 0.4652,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6315789473684213e-05,
+      "loss": 0.4701,
+      "step": 31
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6842105263157896e-05,
+      "loss": 0.5148,
+      "step": 32
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.736842105263158e-05,
+      "loss": 0.4468,
+      "step": 33
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.7894736842105264e-05,
+      "loss": 0.4368,
+      "step": 34
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.8421052631578947e-05,
+      "loss": 0.3875,
+      "step": 35
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.894736842105263e-05,
+      "loss": 0.3662,
+      "step": 36
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9473684210526318e-05,
+      "loss": 0.4751,
+      "step": 37
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2e-05,
+      "loss": 0.4075,
+      "step": 38
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.998353909465021e-05,
+      "loss": 0.5052,
+      "step": 39
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9967078189300412e-05,
+      "loss": 0.4403,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.995061728395062e-05,
+      "loss": 0.4207,
+      "step": 41
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9934156378600823e-05,
+      "loss": 0.5641,
+      "step": 42
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.991769547325103e-05,
+      "loss": 0.378,
+      "step": 43
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9901234567901237e-05,
+      "loss": 0.557,
+      "step": 44
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.988477366255144e-05,
+      "loss": 0.4744,
+      "step": 45
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9868312757201648e-05,
+      "loss": 0.6027,
+      "step": 46
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9851851851851855e-05,
+      "loss": 0.4544,
+      "step": 47
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.983539094650206e-05,
+      "loss": 0.4577,
+      "step": 48
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9818930041152265e-05,
+      "loss": 0.4558,
+      "step": 49
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9802469135802472e-05,
+      "loss": 0.354,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9786008230452676e-05,
+      "loss": 0.3544,
+      "step": 51
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9769547325102883e-05,
+      "loss": 0.3501,
+      "step": 52
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9753086419753087e-05,
+      "loss": 0.4362,
+      "step": 53
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9736625514403294e-05,
+      "loss": 0.519,
+      "step": 54
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.97201646090535e-05,
+      "loss": 0.4156,
+      "step": 55
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9703703703703704e-05,
+      "loss": 0.4067,
+      "step": 56
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.968724279835391e-05,
+      "loss": 0.3812,
+      "step": 57
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9670781893004115e-05,
+      "loss": 0.458,
+      "step": 58
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9654320987654322e-05,
+      "loss": 0.435,
+      "step": 59
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.963786008230453e-05,
+      "loss": 0.4768,
+      "step": 60
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9621399176954733e-05,
+      "loss": 0.3556,
+      "step": 61
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.960493827160494e-05,
+      "loss": 0.3906,
+      "step": 62
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9588477366255147e-05,
+      "loss": 0.4025,
+      "step": 63
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9572016460905354e-05,
+      "loss": 0.4406,
+      "step": 64
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9555555555555557e-05,
+      "loss": 0.4496,
+      "step": 65
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9539094650205764e-05,
+      "loss": 0.3887,
+      "step": 66
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9522633744855968e-05,
+      "loss": 0.5111,
+      "step": 67
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9506172839506175e-05,
+      "loss": 0.4888,
+      "step": 68
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9489711934156382e-05,
+      "loss": 0.5124,
+      "step": 69
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9473251028806586e-05,
+      "loss": 0.3195,
+      "step": 70
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9456790123456793e-05,
+      "loss": 0.4139,
+      "step": 71
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9440329218106996e-05,
+      "loss": 0.4456,
+      "step": 72
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9423868312757203e-05,
+      "loss": 0.5004,
+      "step": 73
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9407407407407407e-05,
+      "loss": 0.5038,
+      "step": 74
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9390946502057614e-05,
+      "loss": 0.4608,
+      "step": 75
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.937448559670782e-05,
+      "loss": 0.3851,
+      "step": 76
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9358024691358025e-05,
+      "loss": 0.5264,
+      "step": 77
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.934156378600823e-05,
+      "loss": 0.5149,
+      "step": 78
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.932510288065844e-05,
+      "loss": 0.5098,
+      "step": 79
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9308641975308646e-05,
+      "loss": 0.4661,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.929218106995885e-05,
+      "loss": 0.4772,
+      "step": 81
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9275720164609056e-05,
+      "loss": 0.4011,
+      "step": 82
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.925925925925926e-05,
+      "loss": 0.4493,
+      "step": 83
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9242798353909467e-05,
+      "loss": 0.4032,
+      "step": 84
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9226337448559674e-05,
+      "loss": 0.3873,
+      "step": 85
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9209876543209878e-05,
+      "loss": 0.3721,
+      "step": 86
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9193415637860085e-05,
+      "loss": 0.3647,
+      "step": 87
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9176954732510288e-05,
+      "loss": 0.4311,
+      "step": 88
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9160493827160495e-05,
+      "loss": 0.543,
+      "step": 89
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.91440329218107e-05,
+      "loss": 0.4659,
+      "step": 90
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9127572016460906e-05,
+      "loss": 0.3962,
+      "step": 91
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9111111111111113e-05,
+      "loss": 0.4703,
+      "step": 92
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9094650205761317e-05,
+      "loss": 0.4232,
+      "step": 93
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9078189300411524e-05,
+      "loss": 0.4152,
+      "step": 94
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.906172839506173e-05,
+      "loss": 0.4784,
+      "step": 95
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9045267489711938e-05,
+      "loss": 0.364,
+      "step": 96
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.902880658436214e-05,
+      "loss": 0.4181,
+      "step": 97
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.901234567901235e-05,
+      "loss": 0.3675,
+      "step": 98
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8995884773662555e-05,
+      "loss": 0.5369,
+      "step": 99
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.897942386831276e-05,
+      "loss": 0.3382,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8962962962962966e-05,
+      "loss": 0.439,
+      "step": 101
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.894650205761317e-05,
+      "loss": 0.3888,
+      "step": 102
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8930041152263377e-05,
+      "loss": 0.4476,
+      "step": 103
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.891358024691358e-05,
+      "loss": 0.4458,
+      "step": 104
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8897119341563787e-05,
+      "loss": 0.3931,
+      "step": 105
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8880658436213994e-05,
+      "loss": 0.3731,
+      "step": 106
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8864197530864198e-05,
+      "loss": 0.4539,
+      "step": 107
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8847736625514405e-05,
+      "loss": 0.3523,
+      "step": 108
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.883127572016461e-05,
+      "loss": 0.4001,
+      "step": 109
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8814814814814816e-05,
+      "loss": 0.2399,
+      "step": 110
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8798353909465023e-05,
+      "loss": 0.5446,
+      "step": 111
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.878189300411523e-05,
+      "loss": 0.4942,
+      "step": 112
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8765432098765433e-05,
+      "loss": 0.3957,
+      "step": 113
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.874897119341564e-05,
+      "loss": 0.4916,
+      "step": 114
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8732510288065847e-05,
+      "loss": 0.3397,
+      "step": 115
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.871604938271605e-05,
+      "loss": 0.4224,
+      "step": 116
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.8699588477366258e-05,
+      "loss": 0.3766,
+      "step": 117
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.868312757201646e-05,
+      "loss": 0.4517,
+      "step": 118
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.4887,
+      "step": 119
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8650205761316872e-05,
+      "loss": 0.3778,
+      "step": 120
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.863374485596708e-05,
+      "loss": 0.3754,
+      "step": 121
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8617283950617286e-05,
+      "loss": 0.3367,
+      "step": 122
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.860082304526749e-05,
+      "loss": 0.4036,
+      "step": 123
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8584362139917697e-05,
+      "loss": 0.4064,
+      "step": 124
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.85679012345679e-05,
+      "loss": 0.3674,
+      "step": 125
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8551440329218108e-05,
+      "loss": 0.4007,
+      "step": 126
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8534979423868315e-05,
+      "loss": 0.4,
+      "step": 127
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.851851851851852e-05,
+      "loss": 0.3448,
+      "step": 128
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8502057613168725e-05,
+      "loss": 0.3736,
+      "step": 129
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8485596707818932e-05,
+      "loss": 0.4869,
+      "step": 130
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.846913580246914e-05,
+      "loss": 0.4034,
+      "step": 131
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8452674897119343e-05,
+      "loss": 0.4811,
+      "step": 132
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.843621399176955e-05,
+      "loss": 0.3918,
+      "step": 133
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8419753086419754e-05,
+      "loss": 0.4295,
+      "step": 134
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.840329218106996e-05,
+      "loss": 0.4187,
+      "step": 135
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8386831275720164e-05,
+      "loss": 0.3605,
+      "step": 136
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.837037037037037e-05,
+      "loss": 0.3696,
+      "step": 137
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.835390946502058e-05,
+      "loss": 0.4477,
+      "step": 138
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8337448559670782e-05,
+      "loss": 0.5395,
+      "step": 139
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.832098765432099e-05,
+      "loss": 0.4135,
+      "step": 140
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8304526748971193e-05,
+      "loss": 0.3599,
+      "step": 141
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.82880658436214e-05,
+      "loss": 0.3749,
+      "step": 142
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8271604938271607e-05,
+      "loss": 0.307,
+      "step": 143
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8255144032921814e-05,
+      "loss": 0.3178,
+      "step": 144
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8238683127572017e-05,
+      "loss": 0.3468,
+      "step": 145
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8222222222222224e-05,
+      "loss": 0.3562,
+      "step": 146
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.820576131687243e-05,
+      "loss": 0.3996,
+      "step": 147
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8189300411522635e-05,
+      "loss": 0.3896,
+      "step": 148
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8172839506172842e-05,
+      "loss": 0.3735,
+      "step": 149
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8156378600823046e-05,
+      "loss": 0.3152,
+      "step": 150
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8139917695473253e-05,
+      "loss": 0.4473,
+      "step": 151
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.812345679012346e-05,
+      "loss": 0.4143,
+      "step": 152
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8106995884773663e-05,
+      "loss": 0.3974,
+      "step": 153
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.809053497942387e-05,
+      "loss": 0.5082,
+      "step": 154
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8074074074074074e-05,
+      "loss": 0.3978,
+      "step": 155
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.805761316872428e-05,
+      "loss": 0.4421,
+      "step": 156
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8041152263374485e-05,
+      "loss": 0.4486,
+      "step": 157
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.802469135802469e-05,
+      "loss": 0.3171,
+      "step": 158
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.80082304526749e-05,
+      "loss": 0.4101,
+      "step": 159
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7991769547325106e-05,
+      "loss": 0.3966,
+      "step": 160
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.797530864197531e-05,
+      "loss": 0.4174,
+      "step": 161
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7958847736625516e-05,
+      "loss": 0.3673,
+      "step": 162
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7942386831275723e-05,
+      "loss": 0.4502,
+      "step": 163
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7925925925925927e-05,
+      "loss": 0.44,
+      "step": 164
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7909465020576134e-05,
+      "loss": 0.349,
+      "step": 165
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7893004115226338e-05,
+      "loss": 0.3959,
+      "step": 166
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.7876543209876545e-05,
+      "loss": 0.3136,
+      "step": 167
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.786008230452675e-05,
+      "loss": 0.402,
+      "step": 168
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7843621399176955e-05,
+      "loss": 0.3123,
+      "step": 169
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7827160493827162e-05,
+      "loss": 0.4913,
+      "step": 170
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7810699588477366e-05,
+      "loss": 0.3062,
+      "step": 171
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7794238683127573e-05,
+      "loss": 0.3527,
+      "step": 172
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.4381,
+      "step": 173
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7761316872427984e-05,
+      "loss": 0.4016,
+      "step": 174
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.774485596707819e-05,
+      "loss": 0.4025,
+      "step": 175
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7728395061728398e-05,
+      "loss": 0.3111,
+      "step": 176
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.77119341563786e-05,
+      "loss": 0.3972,
+      "step": 177
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.769547325102881e-05,
+      "loss": 0.3924,
+      "step": 178
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7679012345679015e-05,
+      "loss": 0.3827,
+      "step": 179
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.766255144032922e-05,
+      "loss": 0.3921,
+      "step": 180
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7646090534979426e-05,
+      "loss": 0.4678,
+      "step": 181
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7629629629629633e-05,
+      "loss": 0.4044,
+      "step": 182
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7613168724279837e-05,
+      "loss": 0.4464,
+      "step": 183
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7596707818930044e-05,
+      "loss": 0.4067,
+      "step": 184
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7580246913580247e-05,
+      "loss": 0.4357,
+      "step": 185
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7563786008230454e-05,
+      "loss": 0.4399,
+      "step": 186
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7547325102880658e-05,
+      "loss": 0.4798,
+      "step": 187
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7530864197530865e-05,
+      "loss": 0.4868,
+      "step": 188
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7514403292181072e-05,
+      "loss": 0.4026,
+      "step": 189
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7497942386831276e-05,
+      "loss": 0.3769,
+      "step": 190
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7481481481481483e-05,
+      "loss": 0.3638,
+      "step": 191
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.746502057613169e-05,
+      "loss": 0.3285,
+      "step": 192
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7448559670781893e-05,
+      "loss": 0.4887,
+      "step": 193
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.74320987654321e-05,
+      "loss": 0.3189,
+      "step": 194
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7415637860082307e-05,
+      "loss": 0.4173,
+      "step": 195
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.739917695473251e-05,
+      "loss": 0.3422,
+      "step": 196
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7382716049382718e-05,
+      "loss": 0.3464,
+      "step": 197
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7366255144032925e-05,
+      "loss": 0.3964,
+      "step": 198
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.734979423868313e-05,
+      "loss": 0.3926,
+      "step": 199
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 0.4175,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.731687242798354e-05,
+      "loss": 0.4374,
+      "step": 201
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7300411522633746e-05,
+      "loss": 0.4897,
+      "step": 202
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.728395061728395e-05,
+      "loss": 0.3859,
+      "step": 203
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7267489711934157e-05,
+      "loss": 0.3788,
+      "step": 204
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7251028806584364e-05,
+      "loss": 0.3544,
+      "step": 205
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7234567901234568e-05,
+      "loss": 0.3685,
+      "step": 206
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7218106995884775e-05,
+      "loss": 0.3924,
+      "step": 207
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.720164609053498e-05,
+      "loss": 0.3965,
+      "step": 208
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7185185185185185e-05,
+      "loss": 0.3659,
+      "step": 209
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7168724279835392e-05,
+      "loss": 0.3092,
+      "step": 210
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.71522633744856e-05,
+      "loss": 0.4032,
+      "step": 211
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7135802469135806e-05,
+      "loss": 0.4603,
+      "step": 212
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.711934156378601e-05,
+      "loss": 0.3343,
+      "step": 213
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.7102880658436217e-05,
+      "loss": 0.4551,
+      "step": 214
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.708641975308642e-05,
+      "loss": 0.3632,
+      "step": 215
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.7069958847736628e-05,
+      "loss": 0.4198,
+      "step": 216
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.705349794238683e-05,
+      "loss": 0.3267,
+      "step": 217
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.7037037037037038e-05,
+      "loss": 0.3981,
+      "step": 218
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.7020576131687242e-05,
+      "loss": 0.3944,
+      "step": 219
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.700411522633745e-05,
+      "loss": 0.4355,
+      "step": 220
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6987654320987656e-05,
+      "loss": 0.4652,
+      "step": 221
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.697119341563786e-05,
+      "loss": 0.3894,
+      "step": 222
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6954732510288067e-05,
+      "loss": 0.4541,
+      "step": 223
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6938271604938274e-05,
+      "loss": 0.6168,
+      "step": 224
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.692181069958848e-05,
+      "loss": 0.355,
+      "step": 225
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6905349794238684e-05,
+      "loss": 0.3723,
+      "step": 226
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.688888888888889e-05,
+      "loss": 0.3276,
+      "step": 227
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.68724279835391e-05,
+      "loss": 0.481,
+      "step": 228
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6855967078189302e-05,
+      "loss": 0.4071,
+      "step": 229
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.683950617283951e-05,
+      "loss": 0.3346,
+      "step": 230
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6823045267489713e-05,
+      "loss": 0.4174,
+      "step": 231
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.680658436213992e-05,
+      "loss": 0.4829,
+      "step": 232
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6790123456790123e-05,
+      "loss": 0.4351,
+      "step": 233
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.677366255144033e-05,
+      "loss": 0.3687,
+      "step": 234
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6757201646090537e-05,
+      "loss": 0.4449,
+      "step": 235
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.674074074074074e-05,
+      "loss": 0.3935,
+      "step": 236
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6724279835390948e-05,
+      "loss": 0.4641,
+      "step": 237
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.670781893004115e-05,
+      "loss": 0.283,
+      "step": 238
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.669135802469136e-05,
+      "loss": 0.3843,
+      "step": 239
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6674897119341566e-05,
+      "loss": 0.3586,
+      "step": 240
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6658436213991773e-05,
+      "loss": 0.4016,
+      "step": 241
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6641975308641976e-05,
+      "loss": 0.3483,
+      "step": 242
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6625514403292183e-05,
+      "loss": 0.3939,
+      "step": 243
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.660905349794239e-05,
+      "loss": 0.4346,
+      "step": 244
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6592592592592594e-05,
+      "loss": 0.3228,
+      "step": 245
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.65761316872428e-05,
+      "loss": 0.3403,
+      "step": 246
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6559670781893005e-05,
+      "loss": 0.4482,
+      "step": 247
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.654320987654321e-05,
+      "loss": 0.3429,
+      "step": 248
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6526748971193415e-05,
+      "loss": 0.4401,
+      "step": 249
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6510288065843622e-05,
+      "loss": 0.3427,
+      "step": 250
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.649382716049383e-05,
+      "loss": 0.3857,
+      "step": 251
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6477366255144033e-05,
+      "loss": 0.2981,
+      "step": 252
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.646090534979424e-05,
+      "loss": 0.4754,
+      "step": 253
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6444444444444444e-05,
+      "loss": 0.3108,
+      "step": 254
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.642798353909465e-05,
+      "loss": 0.4435,
+      "step": 255
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6411522633744858e-05,
+      "loss": 0.3834,
+      "step": 256
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6395061728395065e-05,
+      "loss": 0.4469,
+      "step": 257
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6378600823045268e-05,
+      "loss": 0.4308,
+      "step": 258
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6362139917695475e-05,
+      "loss": 0.4737,
+      "step": 259
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6345679012345682e-05,
+      "loss": 0.3781,
+      "step": 260
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6329218106995886e-05,
+      "loss": 0.3341,
+      "step": 261
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6312757201646093e-05,
+      "loss": 0.3724,
+      "step": 262
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6296296296296297e-05,
+      "loss": 0.4333,
+      "step": 263
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6279835390946504e-05,
+      "loss": 0.3296,
+      "step": 264
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.626337448559671e-05,
+      "loss": 0.4457,
+      "step": 265
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6246913580246914e-05,
+      "loss": 0.3633,
+      "step": 266
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.623045267489712e-05,
+      "loss": 0.3704,
+      "step": 267
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6213991769547325e-05,
+      "loss": 0.3162,
+      "step": 268
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6197530864197532e-05,
+      "loss": 0.3351,
+      "step": 269
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6181069958847736e-05,
+      "loss": 0.427,
+      "step": 270
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6164609053497943e-05,
+      "loss": 0.4071,
+      "step": 271
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.614814814814815e-05,
+      "loss": 0.3493,
+      "step": 272
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6131687242798357e-05,
+      "loss": 0.3527,
+      "step": 273
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.611522633744856e-05,
+      "loss": 0.4353,
+      "step": 274
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6098765432098767e-05,
+      "loss": 0.3331,
+      "step": 275
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6082304526748974e-05,
+      "loss": 0.4455,
+      "step": 276
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6065843621399178e-05,
+      "loss": 0.3604,
+      "step": 277
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6049382716049385e-05,
+      "loss": 0.3725,
+      "step": 278
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.603292181069959e-05,
+      "loss": 0.3634,
+      "step": 279
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6016460905349796e-05,
+      "loss": 0.3471,
+      "step": 280
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.4957,
+      "step": 281
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5983539094650206e-05,
+      "loss": 0.3329,
+      "step": 282
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5967078189300413e-05,
+      "loss": 0.3813,
+      "step": 283
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5950617283950617e-05,
+      "loss": 0.3336,
+      "step": 284
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5934156378600824e-05,
+      "loss": 0.3203,
+      "step": 285
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5917695473251028e-05,
+      "loss": 0.3797,
+      "step": 286
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5901234567901235e-05,
+      "loss": 0.3415,
+      "step": 287
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.588477366255144e-05,
+      "loss": 0.4192,
+      "step": 288
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.586831275720165e-05,
+      "loss": 0.4433,
+      "step": 289
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5851851851851852e-05,
+      "loss": 0.3177,
+      "step": 290
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.583539094650206e-05,
+      "loss": 0.3823,
+      "step": 291
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5818930041152266e-05,
+      "loss": 0.4626,
+      "step": 292
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.580246913580247e-05,
+      "loss": 0.4563,
+      "step": 293
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5786008230452677e-05,
+      "loss": 0.5166,
+      "step": 294
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5769547325102884e-05,
+      "loss": 0.3401,
+      "step": 295
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5753086419753088e-05,
+      "loss": 0.3565,
+      "step": 296
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5736625514403295e-05,
+      "loss": 0.3119,
+      "step": 297
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5720164609053498e-05,
+      "loss": 0.3234,
+      "step": 298
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5703703703703705e-05,
+      "loss": 0.4157,
+      "step": 299
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.568724279835391e-05,
+      "loss": 0.3348,
+      "step": 300
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5670781893004116e-05,
+      "loss": 0.3829,
+      "step": 301
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.565432098765432e-05,
+      "loss": 0.3549,
+      "step": 302
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5637860082304527e-05,
+      "loss": 0.4123,
+      "step": 303
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5621399176954734e-05,
+      "loss": 0.3378,
+      "step": 304
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.560493827160494e-05,
+      "loss": 0.2703,
+      "step": 305
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5588477366255144e-05,
+      "loss": 0.3996,
+      "step": 306
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.557201646090535e-05,
+      "loss": 0.2899,
+      "step": 307
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.442,
+      "step": 308
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5539094650205762e-05,
+      "loss": 0.3393,
+      "step": 309
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.552263374485597e-05,
+      "loss": 0.4991,
+      "step": 310
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.5506172839506176e-05,
+      "loss": 0.441,
+      "step": 311
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.548971193415638e-05,
+      "loss": 0.269,
+      "step": 312
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5473251028806587e-05,
+      "loss": 0.3894,
+      "step": 313
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.545679012345679e-05,
+      "loss": 0.3443,
+      "step": 314
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5440329218106997e-05,
+      "loss": 0.4439,
+      "step": 315
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.54238683127572e-05,
+      "loss": 0.3945,
+      "step": 316
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5407407407407408e-05,
+      "loss": 0.343,
+      "step": 317
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5390946502057615e-05,
+      "loss": 0.37,
+      "step": 318
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.537448559670782e-05,
+      "loss": 0.3407,
+      "step": 319
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5358024691358026e-05,
+      "loss": 0.4155,
+      "step": 320
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5341563786008233e-05,
+      "loss": 0.3395,
+      "step": 321
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5325102880658436e-05,
+      "loss": 0.3877,
+      "step": 322
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5308641975308643e-05,
+      "loss": 0.4577,
+      "step": 323
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.529218106995885e-05,
+      "loss": 0.4159,
+      "step": 324
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5275720164609057e-05,
+      "loss": 0.3902,
+      "step": 325
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.525925925925926e-05,
+      "loss": 0.379,
+      "step": 326
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5242798353909466e-05,
+      "loss": 0.4805,
+      "step": 327
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5226337448559672e-05,
+      "loss": 0.3841,
+      "step": 328
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5209876543209879e-05,
+      "loss": 0.3271,
+      "step": 329
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5193415637860082e-05,
+      "loss": 0.441,
+      "step": 330
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.517695473251029e-05,
+      "loss": 0.4386,
+      "step": 331
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5160493827160495e-05,
+      "loss": 0.3656,
+      "step": 332
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.51440329218107e-05,
+      "loss": 0.3541,
+      "step": 333
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5127572016460907e-05,
+      "loss": 0.3207,
+      "step": 334
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5111111111111112e-05,
+      "loss": 0.3754,
+      "step": 335
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.509465020576132e-05,
+      "loss": 0.3895,
+      "step": 336
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5078189300411523e-05,
+      "loss": 0.3153,
+      "step": 337
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.506172839506173e-05,
+      "loss": 0.4253,
+      "step": 338
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5045267489711934e-05,
+      "loss": 0.3902,
+      "step": 339
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.502880658436214e-05,
+      "loss": 0.3469,
+      "step": 340
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5012345679012348e-05,
+      "loss": 0.3505,
+      "step": 341
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4995884773662553e-05,
+      "loss": 0.3173,
+      "step": 342
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4979423868312758e-05,
+      "loss": 0.4535,
+      "step": 343
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4962962962962964e-05,
+      "loss": 0.482,
+      "step": 344
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.494650205761317e-05,
+      "loss": 0.3513,
+      "step": 345
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4930041152263374e-05,
+      "loss": 0.4741,
+      "step": 346
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4913580246913581e-05,
+      "loss": 0.4279,
+      "step": 347
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4897119341563788e-05,
+      "loss": 0.3729,
+      "step": 348
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4880658436213992e-05,
+      "loss": 0.3572,
+      "step": 349
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4864197530864199e-05,
+      "loss": 0.3935,
+      "step": 350
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4847736625514404e-05,
+      "loss": 0.2628,
+      "step": 351
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4831275720164611e-05,
+      "loss": 0.3107,
+      "step": 352
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.4372,
+      "step": 353
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4798353909465022e-05,
+      "loss": 0.3705,
+      "step": 354
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4781893004115229e-05,
+      "loss": 0.4677,
+      "step": 355
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4765432098765433e-05,
+      "loss": 0.3333,
+      "step": 356
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.474897119341564e-05,
+      "loss": 0.4412,
+      "step": 357
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4732510288065845e-05,
+      "loss": 0.4585,
+      "step": 358
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.471604938271605e-05,
+      "loss": 0.4365,
+      "step": 359
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4699588477366256e-05,
+      "loss": 0.3039,
+      "step": 360
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4683127572016463e-05,
+      "loss": 0.4435,
+      "step": 361
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.2515,
+      "step": 362
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4650205761316873e-05,
+      "loss": 0.3805,
+      "step": 363
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.463374485596708e-05,
+      "loss": 0.2981,
+      "step": 364
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4617283950617284e-05,
+      "loss": 0.2568,
+      "step": 365
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4600823045267491e-05,
+      "loss": 0.3739,
+      "step": 366
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4584362139917696e-05,
+      "loss": 0.4102,
+      "step": 367
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4567901234567903e-05,
+      "loss": 0.3221,
+      "step": 368
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4551440329218107e-05,
+      "loss": 0.3714,
+      "step": 369
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4534979423868314e-05,
+      "loss": 0.4069,
+      "step": 370
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4518518518518521e-05,
+      "loss": 0.3146,
+      "step": 371
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4502057613168725e-05,
+      "loss": 0.344,
+      "step": 372
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4485596707818932e-05,
+      "loss": 0.4919,
+      "step": 373
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4469135802469137e-05,
+      "loss": 0.4057,
+      "step": 374
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4452674897119342e-05,
+      "loss": 0.3375,
+      "step": 375
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4436213991769548e-05,
+      "loss": 0.4297,
+      "step": 376
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4419753086419755e-05,
+      "loss": 0.4922,
+      "step": 377
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4403292181069962e-05,
+      "loss": 0.4206,
+      "step": 378
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4386831275720165e-05,
+      "loss": 0.3866,
+      "step": 379
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4370370370370372e-05,
+      "loss": 0.3612,
+      "step": 380
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4353909465020578e-05,
+      "loss": 0.2977,
+      "step": 381
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4337448559670783e-05,
+      "loss": 0.2621,
+      "step": 382
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4320987654320988e-05,
+      "loss": 0.366,
+      "step": 383
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4304526748971195e-05,
+      "loss": 0.2643,
+      "step": 384
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4288065843621399e-05,
+      "loss": 0.3707,
+      "step": 385
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4271604938271606e-05,
+      "loss": 0.3152,
+      "step": 386
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4255144032921813e-05,
+      "loss": 0.4019,
+      "step": 387
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4238683127572017e-05,
+      "loss": 0.5402,
+      "step": 388
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4222222222222224e-05,
+      "loss": 0.2943,
+      "step": 389
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4205761316872429e-05,
+      "loss": 0.3746,
+      "step": 390
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4189300411522636e-05,
+      "loss": 0.3904,
+      "step": 391
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.417283950617284e-05,
+      "loss": 0.4219,
+      "step": 392
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4156378600823047e-05,
+      "loss": 0.3397,
+      "step": 393
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4139917695473254e-05,
+      "loss": 0.2991,
+      "step": 394
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4123456790123457e-05,
+      "loss": 0.3144,
+      "step": 395
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4106995884773664e-05,
+      "loss": 0.4191,
+      "step": 396
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.409053497942387e-05,
+      "loss": 0.3163,
+      "step": 397
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4074074074074075e-05,
+      "loss": 0.4588,
+      "step": 398
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.405761316872428e-05,
+      "loss": 0.3934,
+      "step": 399
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4041152263374487e-05,
+      "loss": 0.3465,
+      "step": 400
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4024691358024694e-05,
+      "loss": 0.3763,
+      "step": 401
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.4008230452674898e-05,
+      "loss": 0.3422,
+      "step": 402
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3991769547325105e-05,
+      "loss": 0.402,
+      "step": 403
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3975308641975309e-05,
+      "loss": 0.3675,
+      "step": 404
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3958847736625516e-05,
+      "loss": 0.3448,
+      "step": 405
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3942386831275721e-05,
+      "loss": 0.3576,
+      "step": 406
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3925925925925928e-05,
+      "loss": 0.3369,
+      "step": 407
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3909465020576133e-05,
+      "loss": 0.2911,
+      "step": 408
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3893004115226339e-05,
+      "loss": 0.3524,
+      "step": 409
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3876543209876546e-05,
+      "loss": 0.4033,
+      "step": 410
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.386008230452675e-05,
+      "loss": 0.3484,
+      "step": 411
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3843621399176956e-05,
+      "loss": 0.327,
+      "step": 412
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3827160493827162e-05,
+      "loss": 0.3669,
+      "step": 413
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3810699588477367e-05,
+      "loss": 0.3665,
+      "step": 414
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3794238683127572e-05,
+      "loss": 0.2736,
+      "step": 415
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.377777777777778e-05,
+      "loss": 0.3945,
+      "step": 416
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3761316872427986e-05,
+      "loss": 0.3285,
+      "step": 417
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.374485596707819e-05,
+      "loss": 0.354,
+      "step": 418
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3728395061728397e-05,
+      "loss": 0.3447,
+      "step": 419
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.37119341563786e-05,
+      "loss": 0.2864,
+      "step": 420
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3695473251028808e-05,
+      "loss": 0.294,
+      "step": 421
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3679012345679013e-05,
+      "loss": 0.346,
+      "step": 422
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.366255144032922e-05,
+      "loss": 0.3769,
+      "step": 423
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3646090534979425e-05,
+      "loss": 0.3316,
+      "step": 424
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.362962962962963e-05,
+      "loss": 0.3219,
+      "step": 425
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3613168724279838e-05,
+      "loss": 0.3413,
+      "step": 426
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3596707818930041e-05,
+      "loss": 0.3495,
+      "step": 427
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3580246913580248e-05,
+      "loss": 0.3294,
+      "step": 428
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3563786008230454e-05,
+      "loss": 0.3042,
+      "step": 429
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3547325102880659e-05,
+      "loss": 0.3673,
+      "step": 430
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3530864197530866e-05,
+      "loss": 0.2992,
+      "step": 431
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3514403292181071e-05,
+      "loss": 0.2866,
+      "step": 432
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3497942386831278e-05,
+      "loss": 0.4294,
+      "step": 433
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3481481481481482e-05,
+      "loss": 0.381,
+      "step": 434
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3465020576131689e-05,
+      "loss": 0.2669,
+      "step": 435
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3448559670781893e-05,
+      "loss": 0.3166,
+      "step": 436
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.34320987654321e-05,
+      "loss": 0.2913,
+      "step": 437
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3415637860082307e-05,
+      "loss": 0.3239,
+      "step": 438
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3399176954732512e-05,
+      "loss": 0.3154,
+      "step": 439
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3382716049382717e-05,
+      "loss": 0.4102,
+      "step": 440
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3366255144032923e-05,
+      "loss": 0.2735,
+      "step": 441
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.334979423868313e-05,
+      "loss": 0.3109,
+      "step": 442
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.41,
+      "step": 443
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.331687242798354e-05,
+      "loss": 0.3857,
+      "step": 444
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3300411522633746e-05,
+      "loss": 0.3749,
+      "step": 445
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3283950617283951e-05,
+      "loss": 0.3313,
+      "step": 446
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3267489711934158e-05,
+      "loss": 0.4282,
+      "step": 447
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3251028806584363e-05,
+      "loss": 0.3211,
+      "step": 448
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.323456790123457e-05,
+      "loss": 0.2531,
+      "step": 449
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3218106995884774e-05,
+      "loss": 0.3261,
+      "step": 450
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3201646090534981e-05,
+      "loss": 0.347,
+      "step": 451
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3185185185185185e-05,
+      "loss": 0.3412,
+      "step": 452
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3168724279835392e-05,
+      "loss": 0.3614,
+      "step": 453
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3152263374485599e-05,
+      "loss": 0.3441,
+      "step": 454
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.3135802469135804e-05,
+      "loss": 0.3408,
+      "step": 455
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.311934156378601e-05,
+      "loss": 0.404,
+      "step": 456
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.3102880658436215e-05,
+      "loss": 0.3117,
+      "step": 457
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.3086419753086422e-05,
+      "loss": 0.2961,
+      "step": 458
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.3069958847736625e-05,
+      "loss": 0.4622,
+      "step": 459
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.3053497942386832e-05,
+      "loss": 0.2617,
+      "step": 460
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.303703703703704e-05,
+      "loss": 0.3371,
+      "step": 461
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.3020576131687243e-05,
+      "loss": 0.3452,
+      "step": 462
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.300411522633745e-05,
+      "loss": 0.3898,
+      "step": 463
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2987654320987655e-05,
+      "loss": 0.2803,
+      "step": 464
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2971193415637862e-05,
+      "loss": 0.3472,
+      "step": 465
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2954732510288066e-05,
+      "loss": 0.3625,
+      "step": 466
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2938271604938273e-05,
+      "loss": 0.3455,
+      "step": 467
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2921810699588477e-05,
+      "loss": 0.359,
+      "step": 468
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2905349794238684e-05,
+      "loss": 0.3567,
+      "step": 469
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.288888888888889e-05,
+      "loss": 0.2884,
+      "step": 470
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2872427983539096e-05,
+      "loss": 0.2859,
+      "step": 471
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2855967078189301e-05,
+      "loss": 0.3415,
+      "step": 472
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2839506172839507e-05,
+      "loss": 0.3571,
+      "step": 473
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2823045267489714e-05,
+      "loss": 0.2856,
+      "step": 474
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2806584362139917e-05,
+      "loss": 0.3536,
+      "step": 475
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2790123456790124e-05,
+      "loss": 0.3306,
+      "step": 476
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2773662551440331e-05,
+      "loss": 0.444,
+      "step": 477
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2757201646090535e-05,
+      "loss": 0.3345,
+      "step": 478
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2740740740740742e-05,
+      "loss": 0.2992,
+      "step": 479
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2724279835390947e-05,
+      "loss": 0.3479,
+      "step": 480
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2707818930041154e-05,
+      "loss": 0.3584,
+      "step": 481
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2691358024691358e-05,
+      "loss": 0.3945,
+      "step": 482
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2674897119341565e-05,
+      "loss": 0.3087,
+      "step": 483
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2658436213991772e-05,
+      "loss": 0.4507,
+      "step": 484
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2641975308641976e-05,
+      "loss": 0.2884,
+      "step": 485
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2625514403292183e-05,
+      "loss": 0.3667,
+      "step": 486
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2609053497942388e-05,
+      "loss": 0.2725,
+      "step": 487
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2592592592592593e-05,
+      "loss": 0.3079,
+      "step": 488
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2576131687242799e-05,
+      "loss": 0.3374,
+      "step": 489
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2559670781893006e-05,
+      "loss": 0.3399,
+      "step": 490
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2543209876543213e-05,
+      "loss": 0.3581,
+      "step": 491
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2526748971193416e-05,
+      "loss": 0.3052,
+      "step": 492
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2510288065843623e-05,
+      "loss": 0.3658,
+      "step": 493
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2493827160493827e-05,
+      "loss": 0.3265,
+      "step": 494
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2477366255144034e-05,
+      "loss": 0.3122,
+      "step": 495
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.246090534979424e-05,
+      "loss": 0.3255,
+      "step": 496
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2444444444444446e-05,
+      "loss": 0.3199,
+      "step": 497
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.242798353909465e-05,
+      "loss": 0.2982,
+      "step": 498
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2411522633744857e-05,
+      "loss": 0.2721,
+      "step": 499
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.2395061728395064e-05,
+      "loss": 0.3035,
+      "step": 500
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1253,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f768ad49686ec36b5a8b570468ea76bd56614d5acbd36a18ffbbf3ba397fe3e
+size 4728

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97b0457145bd7c833ba8ea4cf3b957fa4966ef2d41ea053e7e02df8209d67a1
+size 14221467522

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f768ad49686ec36b5a8b570468ea76bd56614d5acbd36a18ffbbf3ba397fe3e
+size 4728