update

README.md

@@ -60,7 +60,7 @@ wandb_log_model:
 
 gradient_accumulation_steps: 1
 micro_batch_size: 4
-num_epochs: 2
+num_epochs: 1
 optimizer: adamw_hf
 learning_rate: 0.00002
 max_grad_norm: 1.0
@@ -93,7 +93,7 @@ special_tokens:
 
 This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2243
+- Loss: 1.0862
 
 ## Model description
 
@@ -117,26 +117,22 @@ The following hyperparameters were used during training:
 - eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 4
-- total_train_batch_size: 16
-- total_eval_batch_size: 16
+- num_devices: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 10
-- num_epochs: 2
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.8618        | 0.0014 | 1    | 1.4421          |
-| 1.6356        | 0.2503 | 181  | 1.1632          |
-| 1.4334        | 0.5007 | 362  | 1.1478          |
-| 1.3555        | 0.7510 | 543  | 1.1586          |
-| 1.3751        | 1.0014 | 724  | 1.1762          |
-| 1.2987        | 1.2517 | 905  | 1.2000          |
-| 1.2318        | 1.5021 | 1086 | 1.2222          |
-| 1.1481        | 1.7524 | 1267 | 1.2243          |
+| 1.8205        | 0.0028 | 1    | 1.3241          |
+| 1.5548        | 0.2514 | 91   | 1.1252          |
+| 1.3893        | 0.5028 | 182  | 1.0946          |
+| 1.492         | 0.7541 | 273  | 1.0862          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
-    "k_proj",
-    "o_proj",
     "q_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
     "down_proj",
-    "up_proj"
+    "v_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e65c0d64407f86d21802318ffaa749792ce701aa7bdb2a53ef997efa6fbe6f
+oid sha256:5b06326a272a6f853e6d5ad091be136b283576afffddee6523b66588a0231aea
 size 84047370

checkpoint-1446/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a2c1917b9b05464a6d53849e44fb1720c931d9549023bb0bc2c9039348323b4e
-size 83945296

checkpoint-1446/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7ce73828a75822cea97f340e4a1bfe4956451220279f985d61fa75c2cec78884
-size 168037626

{checkpoint-1446 → checkpoint-362}/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
-    "k_proj",
-    "o_proj",
     "q_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
     "down_proj",
-    "up_proj"
+    "v_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

{checkpoint-723 → checkpoint-362}/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4328bcad29cc36fbe7ea058ad3dadfa43ba44719e4031183edc65605310f3b9
+oid sha256:b135fc7232ab9240737cb0e618cc8e19f4e3d2015dced4d65a1e6451f932453f
 size 83945296

{checkpoint-723 → checkpoint-362}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc6f9666d3e6968ba323874417579a3ad49dbe72cae83981d41b2486a78082b6
+oid sha256:e2185829937f9b79f81c23cf1ca362fa037ae57aa973cc68d5fafc917371e389
 size 168037626

{checkpoint-723 → checkpoint-362}/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa05f993f12929a3cb8deb93dafe6d25aaca07a72679615c5cbe5a65b8cad948
-size 15024
+oid sha256:d97c8d39a4be0f1786aaab39521f5078b3988ace6a554982b01634e6ea48018d
+size 15984

{checkpoint-1446 → checkpoint-362}/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e20cab82a4a688cf079ca37c55dfa951b4858cdb81ef5e050a453f27ac33e5
-size 15024
+oid sha256:63bb852f934606fc9091904bba884dc668ad515522a5f7d90e0f585a3d0e75ad
+size 15984

{checkpoint-723 → checkpoint-362}/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6cb502fcf0fe36b97236d93e9bb13f9558bc46a1018b30ce085447f66e10725
-size 15024
+oid sha256:d25d97fe56e77effff3938774032d854e86f9f44fe8fb7807f64c71c40b11926
+size 15984

{checkpoint-723 → checkpoint-362}/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62085f46e8bcc3a76b7855a7f9a19b921b3219dfcc4221ba232c1c3466470687
-size 15024
+oid sha256:48a148e0b174c07977d424783405d224b7360e3b7fd3539d0f4b35514208ac40
+size 15984

checkpoint-1446/rng_state_3.pth → checkpoint-362/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83984669a468399ab4c4ffeb73840ec24e4bf008123c8b88337d9e1dd1d6d645
-size 15024
+oid sha256:5b4fe5e52c63a620f752baad742c4dd668b32cc495e886b422e3fdff660fa690
+size 15984

checkpoint-1446/rng_state_2.pth → checkpoint-362/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a32d42e9872bcedb9fa9e64096490a8a106af4a8728db761e670e7c6bb73f5aa
-size 15024
+oid sha256:40d8ccbbde3aebdc9a36e10e9385c3633e1588c1b53e079317d8e91d91828ee2
+size 15984

checkpoint-1446/rng_state_0.pth → checkpoint-362/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e095176a998748252b79fd6c14f558c245d6b9aa4cf094f7a9e2012cc718d23e
-size 15024
+oid sha256:7550a2beb49f1e67e93b70efb9f198f2fff71c205a2416673894063837f965d6
+size 15984

checkpoint-362/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc20b41e04d7287b4277367d7a9f81a275ed05cde5b65a31160d4c68a2c1356a
+size 15984

{checkpoint-1446 → checkpoint-362}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d000d78b861e47d18f2c986174c129926c26e6f71786d60c0317c2bec6f50f6
+oid sha256:23a0b0b6ce6258fe3317ec8c5a06c14be812854fa9ae79cacacaf43daff93af9
 size 1064

checkpoint-362/trainer_state.json

@@ -0,0 +1,2599 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 91,
+  "global_step": 362,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027624309392265192,
+      "grad_norm": 0.48932084441185,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.8205,
+      "step": 1
+    },
+    {
+      "epoch": 0.0027624309392265192,
+      "eval_loss": 1.3241183757781982,
+      "eval_runtime": 113.149,
+      "eval_samples_per_second": 12.656,
+      "eval_steps_per_second": 0.398,
+      "step": 1
+    },
+    {
+      "epoch": 0.0055248618784530384,
+      "grad_norm": 0.5005388855934143,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.8,
+      "step": 2
+    },
+    {
+      "epoch": 0.008287292817679558,
+      "grad_norm": 0.4582345187664032,
+      "learning_rate": 6e-06,
+      "loss": 1.789,
+      "step": 3
+    },
+    {
+      "epoch": 0.011049723756906077,
+      "grad_norm": 0.48251956701278687,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.7407,
+      "step": 4
+    },
+    {
+      "epoch": 0.013812154696132596,
+      "grad_norm": 0.4910590350627899,
+      "learning_rate": 1e-05,
+      "loss": 1.8319,
+      "step": 5
+    },
+    {
+      "epoch": 0.016574585635359115,
+      "grad_norm": 0.5089210867881775,
+      "learning_rate": 1.2e-05,
+      "loss": 1.8182,
+      "step": 6
+    },
+    {
+      "epoch": 0.019337016574585635,
+      "grad_norm": 0.4595086872577667,
+      "learning_rate": 1.4e-05,
+      "loss": 1.699,
+      "step": 7
+    },
+    {
+      "epoch": 0.022099447513812154,
+      "grad_norm": 0.4870719313621521,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.8706,
+      "step": 8
+    },
+    {
+      "epoch": 0.024861878453038673,
+      "grad_norm": 0.4908638596534729,
+      "learning_rate": 1.8e-05,
+      "loss": 1.8573,
+      "step": 9
+    },
+    {
+      "epoch": 0.027624309392265192,
+      "grad_norm": 0.4424334466457367,
+      "learning_rate": 2e-05,
+      "loss": 1.7578,
+      "step": 10
+    },
+    {
+      "epoch": 0.03038674033149171,
+      "grad_norm": 0.4217472970485687,
+      "learning_rate": 1.9999601726381415e-05,
+      "loss": 1.7004,
+      "step": 11
+    },
+    {
+      "epoch": 0.03314917127071823,
+      "grad_norm": 0.43210622668266296,
+      "learning_rate": 1.9998406937250035e-05,
+      "loss": 1.7536,
+      "step": 12
+    },
+    {
+      "epoch": 0.03591160220994475,
+      "grad_norm": 0.47083866596221924,
+      "learning_rate": 1.9996415727776456e-05,
+      "loss": 1.7408,
+      "step": 13
+    },
+    {
+      "epoch": 0.03867403314917127,
+      "grad_norm": 0.4322583079338074,
+      "learning_rate": 1.999362825656992e-05,
+      "loss": 1.7328,
+      "step": 14
+    },
+    {
+      "epoch": 0.04143646408839779,
+      "grad_norm": 0.42204034328460693,
+      "learning_rate": 1.9990044745665672e-05,
+      "loss": 1.6725,
+      "step": 15
+    },
+    {
+      "epoch": 0.04419889502762431,
+      "grad_norm": 0.518390417098999,
+      "learning_rate": 1.998566548050729e-05,
+      "loss": 1.7359,
+      "step": 16
+    },
+    {
+      "epoch": 0.04696132596685083,
+      "grad_norm": 0.511297345161438,
+      "learning_rate": 1.9980490809923928e-05,
+      "loss": 1.7428,
+      "step": 17
+    },
+    {
+      "epoch": 0.049723756906077346,
+      "grad_norm": 0.4457204043865204,
+      "learning_rate": 1.9974521146102535e-05,
+      "loss": 1.6937,
+      "step": 18
+    },
+    {
+      "epoch": 0.052486187845303865,
+      "grad_norm": 0.4381752610206604,
+      "learning_rate": 1.9967756964555044e-05,
+      "loss": 1.7153,
+      "step": 19
+    },
+    {
+      "epoch": 0.055248618784530384,
+      "grad_norm": 0.39109915494918823,
+      "learning_rate": 1.9960198804080462e-05,
+      "loss": 1.6743,
+      "step": 20
+    },
+    {
+      "epoch": 0.058011049723756904,
+      "grad_norm": 0.38451671600341797,
+      "learning_rate": 1.995184726672197e-05,
+      "loss": 1.7517,
+      "step": 21
+    },
+    {
+      "epoch": 0.06077348066298342,
+      "grad_norm": 0.37345442175865173,
+      "learning_rate": 1.9942703017718977e-05,
+      "loss": 1.6271,
+      "step": 22
+    },
+    {
+      "epoch": 0.06353591160220995,
+      "grad_norm": 0.39129161834716797,
+      "learning_rate": 1.99327667854541e-05,
+      "loss": 1.5744,
+      "step": 23
+    },
+    {
+      "epoch": 0.06629834254143646,
+      "grad_norm": 0.3991231322288513,
+      "learning_rate": 1.9922039361395186e-05,
+      "loss": 1.591,
+      "step": 24
+    },
+    {
+      "epoch": 0.06906077348066299,
+      "grad_norm": 0.43718066811561584,
+      "learning_rate": 1.991052160003223e-05,
+      "loss": 1.7202,
+      "step": 25
+    },
+    {
+      "epoch": 0.0718232044198895,
+      "grad_norm": 0.4119918942451477,
+      "learning_rate": 1.989821441880933e-05,
+      "loss": 1.7014,
+      "step": 26
+    },
+    {
+      "epoch": 0.07458563535911603,
+      "grad_norm": 0.42767152190208435,
+      "learning_rate": 1.9885118798051607e-05,
+      "loss": 1.6435,
+      "step": 27
+    },
+    {
+      "epoch": 0.07734806629834254,
+      "grad_norm": 0.4115113317966461,
+      "learning_rate": 1.9871235780887114e-05,
+      "loss": 1.6327,
+      "step": 28
+    },
+    {
+      "epoch": 0.08011049723756906,
+      "grad_norm": 0.42583850026130676,
+      "learning_rate": 1.9856566473163747e-05,
+      "loss": 1.6849,
+      "step": 29
+    },
+    {
+      "epoch": 0.08287292817679558,
+      "grad_norm": 0.4189465641975403,
+      "learning_rate": 1.984111204336116e-05,
+      "loss": 1.6373,
+      "step": 30
+    },
+    {
+      "epoch": 0.0856353591160221,
+      "grad_norm": 0.40879184007644653,
+      "learning_rate": 1.9824873722497694e-05,
+      "loss": 1.66,
+      "step": 31
+    },
+    {
+      "epoch": 0.08839779005524862,
+      "grad_norm": 0.3914012014865875,
+      "learning_rate": 1.9807852804032306e-05,
+      "loss": 1.619,
+      "step": 32
+    },
+    {
+      "epoch": 0.09116022099447514,
+      "grad_norm": 0.45330777764320374,
+      "learning_rate": 1.9790050643761552e-05,
+      "loss": 1.6531,
+      "step": 33
+    },
+    {
+      "epoch": 0.09392265193370165,
+      "grad_norm": 0.4007306396961212,
+      "learning_rate": 1.9771468659711595e-05,
+      "loss": 1.7629,
+      "step": 34
+    },
+    {
+      "epoch": 0.09668508287292818,
+      "grad_norm": 0.3851756453514099,
+      "learning_rate": 1.975210833202524e-05,
+      "loss": 1.6243,
+      "step": 35
+    },
+    {
+      "epoch": 0.09944751381215469,
+      "grad_norm": 0.43640199303627014,
+      "learning_rate": 1.9731971202844036e-05,
+      "loss": 1.6158,
+      "step": 36
+    },
+    {
+      "epoch": 0.10220994475138122,
+      "grad_norm": 0.39339712262153625,
+      "learning_rate": 1.9711058876185446e-05,
+      "loss": 1.5864,
+      "step": 37
+    },
+    {
+      "epoch": 0.10497237569060773,
+      "grad_norm": 0.38844239711761475,
+      "learning_rate": 1.9689373017815076e-05,
+      "loss": 1.6341,
+      "step": 38
+    },
+    {
+      "epoch": 0.10773480662983426,
+      "grad_norm": 0.3856898546218872,
+      "learning_rate": 1.9666915355113976e-05,
+      "loss": 1.6241,
+      "step": 39
+    },
+    {
+      "epoch": 0.11049723756906077,
+      "grad_norm": 0.37264493107795715,
+      "learning_rate": 1.964368767694107e-05,
+      "loss": 1.6442,
+      "step": 40
+    },
+    {
+      "epoch": 0.1132596685082873,
+      "grad_norm": 0.396114319562912,
+      "learning_rate": 1.9619691833490645e-05,
+      "loss": 1.6446,
+      "step": 41
+    },
+    {
+      "epoch": 0.11602209944751381,
+      "grad_norm": 0.3990415334701538,
+      "learning_rate": 1.9594929736144978e-05,
+      "loss": 1.5871,
+      "step": 42
+    },
+    {
+      "epoch": 0.11878453038674033,
+      "grad_norm": 0.4188508689403534,
+      "learning_rate": 1.956940335732209e-05,
+      "loss": 1.6345,
+      "step": 43
+    },
+    {
+      "epoch": 0.12154696132596685,
+      "grad_norm": 0.42161405086517334,
+      "learning_rate": 1.954311473031864e-05,
+      "loss": 1.5946,
+      "step": 44
+    },
+    {
+      "epoch": 0.12430939226519337,
+      "grad_norm": 0.3864198625087738,
+      "learning_rate": 1.9516065949147945e-05,
+      "loss": 1.6201,
+      "step": 45
+    },
+    {
+      "epoch": 0.1270718232044199,
+      "grad_norm": 0.433458536863327,
+      "learning_rate": 1.9488259168373198e-05,
+      "loss": 1.6167,
+      "step": 46
+    },
+    {
+      "epoch": 0.1298342541436464,
+      "grad_norm": 0.4243655800819397,
+      "learning_rate": 1.9459696602935838e-05,
+      "loss": 1.537,
+      "step": 47
+    },
+    {
+      "epoch": 0.13259668508287292,
+      "grad_norm": 0.3996981978416443,
+      "learning_rate": 1.9430380527979124e-05,
+      "loss": 1.5925,
+      "step": 48
+    },
+    {
+      "epoch": 0.13535911602209943,
+      "grad_norm": 0.4238079786300659,
+      "learning_rate": 1.94003132786669e-05,
+      "loss": 1.614,
+      "step": 49
+    },
+    {
+      "epoch": 0.13812154696132597,
+      "grad_norm": 0.4197547137737274,
+      "learning_rate": 1.936949724999762e-05,
+      "loss": 1.6384,
+      "step": 50
+    },
+    {
+      "epoch": 0.1408839779005525,
+      "grad_norm": 0.42430204153060913,
+      "learning_rate": 1.9337934896613516e-05,
+      "loss": 1.6359,
+      "step": 51
+    },
+    {
+      "epoch": 0.143646408839779,
+      "grad_norm": 0.4299282431602478,
+      "learning_rate": 1.930562873260514e-05,
+      "loss": 1.5938,
+      "step": 52
+    },
+    {
+      "epoch": 0.1464088397790055,
+      "grad_norm": 0.42186489701271057,
+      "learning_rate": 1.927258133131105e-05,
+      "loss": 1.5929,
+      "step": 53
+    },
+    {
+      "epoch": 0.14917127071823205,
+      "grad_norm": 0.4173223674297333,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 1.3682,
+      "step": 54
+    },
+    {
+      "epoch": 0.15193370165745856,
+      "grad_norm": 0.4620716869831085,
+      "learning_rate": 1.9204273405225588e-05,
+      "loss": 1.5031,
+      "step": 55
+    },
+    {
+      "epoch": 0.15469613259668508,
+      "grad_norm": 0.4603283703327179,
+      "learning_rate": 1.9169018321483198e-05,
+      "loss": 1.649,
+      "step": 56
+    },
+    {
+      "epoch": 0.1574585635359116,
+      "grad_norm": 0.4401739835739136,
+      "learning_rate": 1.9133032882119656e-05,
+      "loss": 1.5398,
+      "step": 57
+    },
+    {
+      "epoch": 0.16022099447513813,
+      "grad_norm": 0.4578686058521271,
+      "learning_rate": 1.9096319953545186e-05,
+      "loss": 1.5914,
+      "step": 58
+    },
+    {
+      "epoch": 0.16298342541436464,
+      "grad_norm": 0.43309640884399414,
+      "learning_rate": 1.9058882460117972e-05,
+      "loss": 1.6138,
+      "step": 59
+    },
+    {
+      "epoch": 0.16574585635359115,
+      "grad_norm": 0.5025528073310852,
+      "learning_rate": 1.9020723383911214e-05,
+      "loss": 1.54,
+      "step": 60
+    },
+    {
+      "epoch": 0.1685082872928177,
+      "grad_norm": 0.46925926208496094,
+      "learning_rate": 1.8981845764475585e-05,
+      "loss": 1.5897,
+      "step": 61
+    },
+    {
+      "epoch": 0.1712707182320442,
+      "grad_norm": 0.4543595612049103,
+      "learning_rate": 1.8942252698597113e-05,
+      "loss": 1.5394,
+      "step": 62
+    },
+    {
+      "epoch": 0.17403314917127072,
+      "grad_norm": 0.5239660739898682,
+      "learning_rate": 1.890194734005053e-05,
+      "loss": 1.5473,
+      "step": 63
+    },
+    {
+      "epoch": 0.17679558011049723,
+      "grad_norm": 0.4903659522533417,
+      "learning_rate": 1.8860932899348028e-05,
+      "loss": 1.5214,
+      "step": 64
+    },
+    {
+      "epoch": 0.17955801104972377,
+      "grad_norm": 0.48124420642852783,
+      "learning_rate": 1.881921264348355e-05,
+      "loss": 1.5389,
+      "step": 65
+    },
+    {
+      "epoch": 0.18232044198895028,
+      "grad_norm": 0.4901920557022095,
+      "learning_rate": 1.8776789895672557e-05,
+      "loss": 1.5736,
+      "step": 66
+    },
+    {
+      "epoch": 0.1850828729281768,
+      "grad_norm": 0.5033126473426819,
+      "learning_rate": 1.8733668035087302e-05,
+      "loss": 1.5464,
+      "step": 67
+    },
+    {
+      "epoch": 0.1878453038674033,
+      "grad_norm": 0.4777933955192566,
+      "learning_rate": 1.8689850496587674e-05,
+      "loss": 1.592,
+      "step": 68
+    },
+    {
+      "epoch": 0.19060773480662985,
+      "grad_norm": 0.49811434745788574,
+      "learning_rate": 1.8645340770447595e-05,
+      "loss": 1.5821,
+      "step": 69
+    },
+    {
+      "epoch": 0.19337016574585636,
+      "grad_norm": 0.5094152092933655,
+      "learning_rate": 1.8600142402077006e-05,
+      "loss": 1.5816,
+      "step": 70
+    },
+    {
+      "epoch": 0.19613259668508287,
+      "grad_norm": 0.4730343520641327,
+      "learning_rate": 1.8554258991739454e-05,
+      "loss": 1.554,
+      "step": 71
+    },
+    {
+      "epoch": 0.19889502762430938,
+      "grad_norm": 0.5121309757232666,
+      "learning_rate": 1.850769419426531e-05,
+      "loss": 1.5367,
+      "step": 72
+    },
+    {
+      "epoch": 0.20165745856353592,
+      "grad_norm": 0.5479581356048584,
+      "learning_rate": 1.8460451718760653e-05,
+      "loss": 1.5859,
+      "step": 73
+    },
+    {
+      "epoch": 0.20441988950276244,
+      "grad_norm": 0.5554270148277283,
+      "learning_rate": 1.8412535328311813e-05,
+      "loss": 1.5029,
+      "step": 74
+    },
+    {
+      "epoch": 0.20718232044198895,
+      "grad_norm": 0.49664542078971863,
+      "learning_rate": 1.8363948839685638e-05,
+      "loss": 1.6311,
+      "step": 75
+    },
+    {
+      "epoch": 0.20994475138121546,
+      "grad_norm": 0.4820622205734253,
+      "learning_rate": 1.8314696123025456e-05,
+      "loss": 1.5878,
+      "step": 76
+    },
+    {
+      "epoch": 0.212707182320442,
+      "grad_norm": 0.5548580288887024,
+      "learning_rate": 1.8264781101542797e-05,
+      "loss": 1.4964,
+      "step": 77
+    },
+    {
+      "epoch": 0.2154696132596685,
+      "grad_norm": 0.5179187655448914,
+      "learning_rate": 1.8214207751204917e-05,
+      "loss": 1.5173,
+      "step": 78
+    },
+    {
+      "epoch": 0.21823204419889503,
+      "grad_norm": 0.5284916758537292,
+      "learning_rate": 1.816298010041806e-05,
+      "loss": 1.4862,
+      "step": 79
+    },
+    {
+      "epoch": 0.22099447513812154,
+      "grad_norm": 0.5448415279388428,
+      "learning_rate": 1.8111102229706593e-05,
+      "loss": 1.571,
+      "step": 80
+    },
+    {
+      "epoch": 0.22375690607734808,
+      "grad_norm": 0.534216582775116,
+      "learning_rate": 1.805857827138798e-05,
+      "loss": 1.4929,
+      "step": 81
+    },
+    {
+      "epoch": 0.2265193370165746,
+      "grad_norm": 0.5475566387176514,
+      "learning_rate": 1.8005412409243604e-05,
+      "loss": 1.6112,
+      "step": 82
+    },
+    {
+      "epoch": 0.2292817679558011,
+      "grad_norm": 0.5975603461265564,
+      "learning_rate": 1.7951608878185533e-05,
+      "loss": 1.4222,
+      "step": 83
+    },
+    {
+      "epoch": 0.23204419889502761,
+      "grad_norm": 0.5566644072532654,
+      "learning_rate": 1.789717196391916e-05,
+      "loss": 1.5952,
+      "step": 84
+    },
+    {
+      "epoch": 0.23480662983425415,
+      "grad_norm": 0.6141032576560974,
+      "learning_rate": 1.7842106002601854e-05,
+      "loss": 1.5542,
+      "step": 85
+    },
+    {
+      "epoch": 0.23756906077348067,
+      "grad_norm": 0.6016777157783508,
+      "learning_rate": 1.778641538049755e-05,
+      "loss": 1.5648,
+      "step": 86
+    },
+    {
+      "epoch": 0.24033149171270718,
+      "grad_norm": 0.5828099250793457,
+      "learning_rate": 1.773010453362737e-05,
+      "loss": 1.5593,
+      "step": 87
+    },
+    {
+      "epoch": 0.2430939226519337,
+      "grad_norm": 0.5992968678474426,
+      "learning_rate": 1.7673177947416258e-05,
+      "loss": 1.5456,
+      "step": 88
+    },
+    {
+      "epoch": 0.24585635359116023,
+      "grad_norm": 0.5443550944328308,
+      "learning_rate": 1.7615640156335713e-05,
+      "loss": 1.52,
+      "step": 89
+    },
+    {
+      "epoch": 0.24861878453038674,
+      "grad_norm": 0.6033780574798584,
+      "learning_rate": 1.7557495743542586e-05,
+      "loss": 1.5622,
+      "step": 90
+    },
+    {
+      "epoch": 0.2513812154696133,
+      "grad_norm": 0.545807957649231,
+      "learning_rate": 1.749874934051401e-05,
+      "loss": 1.5548,
+      "step": 91
+    },
+    {
+      "epoch": 0.2513812154696133,
+      "eval_loss": 1.1252354383468628,
+      "eval_runtime": 126.3795,
+      "eval_samples_per_second": 11.331,
+      "eval_steps_per_second": 0.356,
+      "step": 91
+    },
+    {
+      "epoch": 0.2541436464088398,
+      "grad_norm": 0.5675923824310303,
+      "learning_rate": 1.7439405626678496e-05,
+      "loss": 1.5421,
+      "step": 92
+    },
+    {
+      "epoch": 0.2569060773480663,
+      "grad_norm": 0.5341032147407532,
+      "learning_rate": 1.7379469329043166e-05,
+      "loss": 1.3576,
+      "step": 93
+    },
+    {
+      "epoch": 0.2596685082872928,
+      "grad_norm": 0.610197126865387,
+      "learning_rate": 1.7318945221817255e-05,
+      "loss": 1.505,
+      "step": 94
+    },
+    {
+      "epoch": 0.26243093922651933,
+      "grad_norm": 0.5908088088035583,
+      "learning_rate": 1.7257838126031797e-05,
+      "loss": 1.2847,
+      "step": 95
+    },
+    {
+      "epoch": 0.26519337016574585,
+      "grad_norm": 0.6427506804466248,
+      "learning_rate": 1.719615290915563e-05,
+      "loss": 1.5017,
+      "step": 96
+    },
+    {
+      "epoch": 0.26795580110497236,
+      "grad_norm": 0.6517511010169983,
+      "learning_rate": 1.7133894484707657e-05,
+      "loss": 1.4913,
+      "step": 97
+    },
+    {
+      "epoch": 0.27071823204419887,
+      "grad_norm": 0.6169045567512512,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 1.4697,
+      "step": 98
+    },
+    {
+      "epoch": 0.27348066298342544,
+      "grad_norm": 0.5691592693328857,
+      "learning_rate": 1.7007677895070358e-05,
+      "loss": 1.4697,
+      "step": 99
+    },
+    {
+      "epoch": 0.27624309392265195,
+      "grad_norm": 0.6089439988136292,
+      "learning_rate": 1.694372978362861e-05,
+      "loss": 1.5556,
+      "step": 100
+    },
+    {
+      "epoch": 0.27900552486187846,
+      "grad_norm": 0.608332097530365,
+      "learning_rate": 1.6879228571309377e-05,
+      "loss": 1.6086,
+      "step": 101
+    },
+    {
+      "epoch": 0.281767955801105,
+      "grad_norm": 0.60256028175354,
+      "learning_rate": 1.6814179395938915e-05,
+      "loss": 1.398,
+      "step": 102
+    },
+    {
+      "epoch": 0.2845303867403315,
+      "grad_norm": 0.6815750598907471,
+      "learning_rate": 1.6748587438991303e-05,
+      "loss": 1.5855,
+      "step": 103
+    },
+    {
+      "epoch": 0.287292817679558,
+      "grad_norm": 0.5973678827285767,
+      "learning_rate": 1.6682457925175762e-05,
+      "loss": 1.4901,
+      "step": 104
+    },
+    {
+      "epoch": 0.2900552486187845,
+      "grad_norm": 0.6231850981712341,
+      "learning_rate": 1.6615796122020443e-05,
+      "loss": 1.5055,
+      "step": 105
+    },
+    {
+      "epoch": 0.292817679558011,
+      "grad_norm": 0.6111463904380798,
+      "learning_rate": 1.6548607339452853e-05,
+      "loss": 1.5461,
+      "step": 106
+    },
+    {
+      "epoch": 0.2955801104972376,
+      "grad_norm": 0.6073287725448608,
+      "learning_rate": 1.6480896929376905e-05,
+      "loss": 1.5502,
+      "step": 107
+    },
+    {
+      "epoch": 0.2983425414364641,
+      "grad_norm": 0.6183845400810242,
+      "learning_rate": 1.641267028524661e-05,
+      "loss": 1.5892,
+      "step": 108
+    },
+    {
+      "epoch": 0.3011049723756906,
+      "grad_norm": 0.6584267616271973,
+      "learning_rate": 1.6343932841636455e-05,
+      "loss": 1.4904,
+      "step": 109
+    },
+    {
+      "epoch": 0.30386740331491713,
+      "grad_norm": 0.651483416557312,
+      "learning_rate": 1.627469007380852e-05,
+      "loss": 1.5145,
+      "step": 110
+    },
+    {
+      "epoch": 0.30662983425414364,
+      "grad_norm": 0.5964000225067139,
+      "learning_rate": 1.6204947497276346e-05,
+      "loss": 1.4672,
+      "step": 111
+    },
+    {
+      "epoch": 0.30939226519337015,
+      "grad_norm": 0.5882562398910522,
+      "learning_rate": 1.6134710667365598e-05,
+      "loss": 1.5103,
+      "step": 112
+    },
+    {
+      "epoch": 0.31215469613259667,
+      "grad_norm": 0.710396945476532,
+      "learning_rate": 1.6063985178771555e-05,
+      "loss": 1.4297,
+      "step": 113
+    },
+    {
+      "epoch": 0.3149171270718232,
+      "grad_norm": 0.7119180560112,
+      "learning_rate": 1.599277666511347e-05,
+      "loss": 1.5547,
+      "step": 114
+    },
+    {
+      "epoch": 0.31767955801104975,
+      "grad_norm": 0.5978303551673889,
+      "learning_rate": 1.592109079848583e-05,
+      "loss": 1.5943,
+      "step": 115
+    },
+    {
+      "epoch": 0.32044198895027626,
+      "grad_norm": 0.6321621537208557,
+      "learning_rate": 1.584893328900653e-05,
+      "loss": 1.5289,
+      "step": 116
+    },
+    {
+      "epoch": 0.32320441988950277,
+      "grad_norm": 0.6637874245643616,
+      "learning_rate": 1.577630988436206e-05,
+      "loss": 1.5003,
+      "step": 117
+    },
+    {
+      "epoch": 0.3259668508287293,
+      "grad_norm": 0.6861926913261414,
+      "learning_rate": 1.5703226369349642e-05,
+      "loss": 1.5015,
+      "step": 118
+    },
+    {
+      "epoch": 0.3287292817679558,
+      "grad_norm": 0.6874920129776001,
+      "learning_rate": 1.562968856541648e-05,
+      "loss": 1.5143,
+      "step": 119
+    },
+    {
+      "epoch": 0.3314917127071823,
+      "grad_norm": 0.8108745813369751,
+      "learning_rate": 1.5555702330196024e-05,
+      "loss": 1.4077,
+      "step": 120
+    },
+    {
+      "epoch": 0.3342541436464088,
+      "grad_norm": 0.6551744341850281,
+      "learning_rate": 1.5481273557041402e-05,
+      "loss": 1.5427,
+      "step": 121
+    },
+    {
+      "epoch": 0.3370165745856354,
+      "grad_norm": 0.7033353447914124,
+      "learning_rate": 1.5406408174555978e-05,
+      "loss": 1.5386,
+      "step": 122
+    },
+    {
+      "epoch": 0.3397790055248619,
+      "grad_norm": 0.744612991809845,
+      "learning_rate": 1.5331112146121104e-05,
+      "loss": 1.4391,
+      "step": 123
+    },
+    {
+      "epoch": 0.3425414364640884,
+      "grad_norm": 0.7087468504905701,
+      "learning_rate": 1.525539146942113e-05,
+      "loss": 1.4572,
+      "step": 124
+    },
+    {
+      "epoch": 0.3453038674033149,
+      "grad_norm": 0.6906458139419556,
+      "learning_rate": 1.5179252175965632e-05,
+      "loss": 1.4383,
+      "step": 125
+    },
+    {
+      "epoch": 0.34806629834254144,
+      "grad_norm": 0.6855905652046204,
+      "learning_rate": 1.5102700330609e-05,
+      "loss": 1.5606,
+      "step": 126
+    },
+    {
+      "epoch": 0.35082872928176795,
+      "grad_norm": 0.6799173355102539,
+      "learning_rate": 1.5025742031067316e-05,
+      "loss": 1.5069,
+      "step": 127
+    },
+    {
+      "epoch": 0.35359116022099446,
+      "grad_norm": 0.7122651934623718,
+      "learning_rate": 1.4948383407432678e-05,
+      "loss": 1.4342,
+      "step": 128
+    },
+    {
+      "epoch": 0.356353591160221,
+      "grad_norm": 0.6611509323120117,
+      "learning_rate": 1.4870630621684873e-05,
+      "loss": 1.5387,
+      "step": 129
+    },
+    {
+      "epoch": 0.35911602209944754,
+      "grad_norm": 0.6705402135848999,
+      "learning_rate": 1.479248986720057e-05,
+      "loss": 1.4611,
+      "step": 130
+    },
+    {
+      "epoch": 0.36187845303867405,
+      "grad_norm": 0.6791753768920898,
+      "learning_rate": 1.4713967368259981e-05,
+      "loss": 1.4796,
+      "step": 131
+    },
+    {
+      "epoch": 0.36464088397790057,
+      "grad_norm": 0.6923907995223999,
+      "learning_rate": 1.4635069379551054e-05,
+      "loss": 1.4616,
+      "step": 132
+    },
+    {
+      "epoch": 0.3674033149171271,
+      "grad_norm": 0.7138407826423645,
+      "learning_rate": 1.4555802185671297e-05,
+      "loss": 1.5116,
+      "step": 133
+    },
+    {
+      "epoch": 0.3701657458563536,
+      "grad_norm": 0.7438933253288269,
+      "learning_rate": 1.4476172100627127e-05,
+      "loss": 1.4314,
+      "step": 134
+    },
+    {
+      "epoch": 0.3729281767955801,
+      "grad_norm": 0.7759312391281128,
+      "learning_rate": 1.4396185467330974e-05,
+      "loss": 1.5002,
+      "step": 135
+    },
+    {
+      "epoch": 0.3756906077348066,
+      "grad_norm": 0.6731029152870178,
+      "learning_rate": 1.4315848657096006e-05,
+      "loss": 1.4599,
+      "step": 136
+    },
+    {
+      "epoch": 0.3784530386740331,
+      "grad_norm": 0.7549765110015869,
+      "learning_rate": 1.4235168069128657e-05,
+      "loss": 1.3872,
+      "step": 137
+    },
+    {
+      "epoch": 0.3812154696132597,
+      "grad_norm": 0.7021876573562622,
+      "learning_rate": 1.4154150130018867e-05,
+      "loss": 1.4071,
+      "step": 138
+    },
+    {
+      "epoch": 0.3839779005524862,
+      "grad_norm": 0.7599930763244629,
+      "learning_rate": 1.407280129322819e-05,
+      "loss": 1.5215,
+      "step": 139
+    },
+    {
+      "epoch": 0.3867403314917127,
+      "grad_norm": 0.7097262740135193,
+      "learning_rate": 1.3991128038575741e-05,
+      "loss": 1.4198,
+      "step": 140
+    },
+    {
+      "epoch": 0.38950276243093923,
+      "grad_norm": 0.70546555519104,
+      "learning_rate": 1.3909136871722066e-05,
+      "loss": 1.316,
+      "step": 141
+    },
+    {
+      "epoch": 0.39226519337016574,
+      "grad_norm": 0.7452008724212646,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 1.4108,
+      "step": 142
+    },
+    {
+      "epoch": 0.39502762430939226,
+      "grad_norm": 0.7480429410934448,
+      "learning_rate": 1.374422695014897e-05,
+      "loss": 1.4793,
+      "step": 143
+    },
+    {
+      "epoch": 0.39779005524861877,
+      "grad_norm": 0.7833120822906494,
+      "learning_rate": 1.3661321331283796e-05,
+      "loss": 1.4256,
+      "step": 144
+    },
+    {
+      "epoch": 0.4005524861878453,
+      "grad_norm": 0.7384762763977051,
+      "learning_rate": 1.3578124070879534e-05,
+      "loss": 1.5426,
+      "step": 145
+    },
+    {
+      "epoch": 0.40331491712707185,
+      "grad_norm": 0.7010709047317505,
+      "learning_rate": 1.3494641795990986e-05,
+      "loss": 1.5354,
+      "step": 146
+    },
+    {
+      "epoch": 0.40607734806629836,
+      "grad_norm": 0.8359608054161072,
+      "learning_rate": 1.3410881156375684e-05,
+      "loss": 1.5266,
+      "step": 147
+    },
+    {
+      "epoch": 0.4088397790055249,
+      "grad_norm": 0.7560956478118896,
+      "learning_rate": 1.3326848823964243e-05,
+      "loss": 1.4138,
+      "step": 148
+    },
+    {
+      "epoch": 0.4116022099447514,
+      "grad_norm": 0.7910446524620056,
+      "learning_rate": 1.3242551492328875e-05,
+      "loss": 1.4711,
+      "step": 149
+    },
+    {
+      "epoch": 0.4143646408839779,
+      "grad_norm": 0.7551384568214417,
+      "learning_rate": 1.3157995876150252e-05,
+      "loss": 1.4297,
+      "step": 150
+    },
+    {
+      "epoch": 0.4171270718232044,
+      "grad_norm": 0.7447769045829773,
+      "learning_rate": 1.3073188710682612e-05,
+      "loss": 1.4609,
+      "step": 151
+    },
+    {
+      "epoch": 0.4198895027624309,
+      "grad_norm": 0.6754193305969238,
+      "learning_rate": 1.2988136751217292e-05,
+      "loss": 1.4454,
+      "step": 152
+    },
+    {
+      "epoch": 0.42265193370165743,
+      "grad_norm": 0.7343276143074036,
+      "learning_rate": 1.2902846772544625e-05,
+      "loss": 1.4708,
+      "step": 153
+    },
+    {
+      "epoch": 0.425414364640884,
+      "grad_norm": 0.8059439659118652,
+      "learning_rate": 1.2817325568414299e-05,
+      "loss": 1.4791,
+      "step": 154
+    },
+    {
+      "epoch": 0.4281767955801105,
+      "grad_norm": 0.7605715990066528,
+      "learning_rate": 1.27315799509942e-05,
+      "loss": 1.4409,
+      "step": 155
+    },
+    {
+      "epoch": 0.430939226519337,
+      "grad_norm": 0.7782636880874634,
+      "learning_rate": 1.2645616750327792e-05,
+      "loss": 1.4821,
+      "step": 156
+    },
+    {
+      "epoch": 0.43370165745856354,
+      "grad_norm": 0.754604697227478,
+      "learning_rate": 1.2559442813790077e-05,
+      "loss": 1.3753,
+      "step": 157
+    },
+    {
+      "epoch": 0.43646408839779005,
+      "grad_norm": 0.7628011107444763,
+      "learning_rate": 1.2473065005542155e-05,
+      "loss": 1.4782,
+      "step": 158
+    },
+    {
+      "epoch": 0.43922651933701656,
+      "grad_norm": 0.7928145527839661,
+      "learning_rate": 1.2386490205984488e-05,
+      "loss": 1.5086,
+      "step": 159
+    },
+    {
+      "epoch": 0.4419889502762431,
+      "grad_norm": 0.8027752041816711,
+      "learning_rate": 1.2299725311208807e-05,
+      "loss": 1.5125,
+      "step": 160
+    },
+    {
+      "epoch": 0.4447513812154696,
+      "grad_norm": 0.8248247504234314,
+      "learning_rate": 1.2212777232448837e-05,
+      "loss": 1.4784,
+      "step": 161
+    },
+    {
+      "epoch": 0.44751381215469616,
+      "grad_norm": 0.7129939794540405,
+      "learning_rate": 1.2125652895529766e-05,
+      "loss": 1.4658,
+      "step": 162
+    },
+    {
+      "epoch": 0.45027624309392267,
+      "grad_norm": 0.8178958892822266,
+      "learning_rate": 1.2038359240316589e-05,
+      "loss": 1.4601,
+      "step": 163
+    },
+    {
+      "epoch": 0.4530386740331492,
+      "grad_norm": 0.7721039652824402,
+      "learning_rate": 1.1950903220161286e-05,
+      "loss": 1.503,
+      "step": 164
+    },
+    {
+      "epoch": 0.4558011049723757,
+      "grad_norm": 0.8325313925743103,
+      "learning_rate": 1.186329180134898e-05,
+      "loss": 1.4498,
+      "step": 165
+    },
+    {
+      "epoch": 0.4585635359116022,
+      "grad_norm": 0.743294358253479,
+      "learning_rate": 1.1775531962543036e-05,
+      "loss": 1.4356,
+      "step": 166
+    },
+    {
+      "epoch": 0.4613259668508287,
+      "grad_norm": 0.7665619254112244,
+      "learning_rate": 1.1687630694229159e-05,
+      "loss": 1.4829,
+      "step": 167
+    },
+    {
+      "epoch": 0.46408839779005523,
+      "grad_norm": 0.8083658218383789,
+      "learning_rate": 1.1599594998158602e-05,
+      "loss": 1.4472,
+      "step": 168
+    },
+    {
+      "epoch": 0.46685082872928174,
+      "grad_norm": 0.8675556182861328,
+      "learning_rate": 1.1511431886790407e-05,
+      "loss": 1.3883,
+      "step": 169
+    },
+    {
+      "epoch": 0.4696132596685083,
+      "grad_norm": 0.8435657024383545,
+      "learning_rate": 1.1423148382732854e-05,
+      "loss": 1.4281,
+      "step": 170
+    },
+    {
+      "epoch": 0.4723756906077348,
+      "grad_norm": 0.7853896617889404,
+      "learning_rate": 1.1334751518184062e-05,
+      "loss": 1.4601,
+      "step": 171
+    },
+    {
+      "epoch": 0.47513812154696133,
+      "grad_norm": 0.7415674328804016,
+      "learning_rate": 1.124624833437186e-05,
+      "loss": 1.495,
+      "step": 172
+    },
+    {
+      "epoch": 0.47790055248618785,
+      "grad_norm": 0.8834148645401001,
+      "learning_rate": 1.1157645880992901e-05,
+      "loss": 1.4277,
+      "step": 173
+    },
+    {
+      "epoch": 0.48066298342541436,
+      "grad_norm": 0.7571101784706116,
+      "learning_rate": 1.1068951215651132e-05,
+      "loss": 1.4135,
+      "step": 174
+    },
+    {
+      "epoch": 0.48342541436464087,
+      "grad_norm": 0.7815778255462646,
+      "learning_rate": 1.098017140329561e-05,
+      "loss": 1.4555,
+      "step": 175
+    },
+    {
+      "epoch": 0.4861878453038674,
+      "grad_norm": 0.8531723022460938,
+      "learning_rate": 1.089131351565776e-05,
+      "loss": 1.5423,
+      "step": 176
+    },
+    {
+      "epoch": 0.4889502762430939,
+      "grad_norm": 0.7706172466278076,
+      "learning_rate": 1.080238463068808e-05,
+      "loss": 1.4961,
+      "step": 177
+    },
+    {
+      "epoch": 0.49171270718232046,
+      "grad_norm": 0.8223702907562256,
+      "learning_rate": 1.0713391831992324e-05,
+      "loss": 1.4259,
+      "step": 178
+    },
+    {
+      "epoch": 0.494475138121547,
+      "grad_norm": 0.8095825910568237,
+      "learning_rate": 1.0624342208267293e-05,
+      "loss": 1.4858,
+      "step": 179
+    },
+    {
+      "epoch": 0.4972375690607735,
+      "grad_norm": 0.7966883778572083,
+      "learning_rate": 1.0535242852736152e-05,
+      "loss": 1.496,
+      "step": 180
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8368972539901733,
+      "learning_rate": 1.0446100862583459e-05,
+      "loss": 1.447,
+      "step": 181
+    },
+    {
+      "epoch": 0.5027624309392266,
+      "grad_norm": 0.836999237537384,
+      "learning_rate": 1.0356923338389807e-05,
+      "loss": 1.3893,
+      "step": 182
+    },
+    {
+      "epoch": 0.5027624309392266,
+      "eval_loss": 1.0946398973464966,
+      "eval_runtime": 126.053,
+      "eval_samples_per_second": 11.36,
+      "eval_steps_per_second": 0.357,
+      "step": 182
+    },
+    {
+      "epoch": 0.505524861878453,
+      "grad_norm": 0.8300839066505432,
+      "learning_rate": 1.0267717383566247e-05,
+      "loss": 1.4232,
+      "step": 183
+    },
+    {
+      "epoch": 0.5082872928176796,
+      "grad_norm": 0.9312767386436462,
+      "learning_rate": 1.0178490103788462e-05,
+      "loss": 1.4498,
+      "step": 184
+    },
+    {
+      "epoch": 0.511049723756906,
+      "grad_norm": 0.8420562148094177,
+      "learning_rate": 1.0089248606430775e-05,
+      "loss": 1.5166,
+      "step": 185
+    },
+    {
+      "epoch": 0.5138121546961326,
+      "grad_norm": 0.8379613161087036,
+      "learning_rate": 1e-05,
+      "loss": 1.4043,
+      "step": 186
+    },
+    {
+      "epoch": 0.5165745856353591,
+      "grad_norm": 0.8052487969398499,
+      "learning_rate": 9.910751393569228e-06,
+      "loss": 1.4343,
+      "step": 187
+    },
+    {
+      "epoch": 0.5193370165745856,
+      "grad_norm": 0.7437810301780701,
+      "learning_rate": 9.82150989621154e-06,
+      "loss": 1.4832,
+      "step": 188
+    },
+    {
+      "epoch": 0.5220994475138122,
+      "grad_norm": 0.8680680394172668,
+      "learning_rate": 9.732282616433756e-06,
+      "loss": 1.4136,
+      "step": 189
+    },
+    {
+      "epoch": 0.5248618784530387,
+      "grad_norm": 0.8093543648719788,
+      "learning_rate": 9.643076661610197e-06,
+      "loss": 1.456,
+      "step": 190
+    },
+    {
+      "epoch": 0.5276243093922652,
+      "grad_norm": 0.8746613264083862,
+      "learning_rate": 9.553899137416546e-06,
+      "loss": 1.4926,
+      "step": 191
+    },
+    {
+      "epoch": 0.5303867403314917,
+      "grad_norm": 0.8815398812294006,
+      "learning_rate": 9.464757147263849e-06,
+      "loss": 1.4904,
+      "step": 192
+    },
+    {
+      "epoch": 0.5331491712707183,
+      "grad_norm": 0.7982166409492493,
+      "learning_rate": 9.37565779173271e-06,
+      "loss": 1.5623,
+      "step": 193
+    },
+    {
+      "epoch": 0.5359116022099447,
+      "grad_norm": 0.793260395526886,
+      "learning_rate": 9.286608168007678e-06,
+      "loss": 1.4303,
+      "step": 194
+    },
+    {
+      "epoch": 0.5386740331491713,
+      "grad_norm": 0.7854033708572388,
+      "learning_rate": 9.197615369311926e-06,
+      "loss": 1.5027,
+      "step": 195
+    },
+    {
+      "epoch": 0.5414364640883977,
+      "grad_norm": 0.8385631442070007,
+      "learning_rate": 9.108686484342241e-06,
+      "loss": 1.4795,
+      "step": 196
+    },
+    {
+      "epoch": 0.5441988950276243,
+      "grad_norm": 0.7929366827011108,
+      "learning_rate": 9.019828596704394e-06,
+      "loss": 1.4528,
+      "step": 197
+    },
+    {
+      "epoch": 0.5469613259668509,
+      "grad_norm": 0.8112191557884216,
+      "learning_rate": 8.931048784348875e-06,
+      "loss": 1.4798,
+      "step": 198
+    },
+    {
+      "epoch": 0.5497237569060773,
+      "grad_norm": 0.8285465240478516,
+      "learning_rate": 8.8423541190071e-06,
+      "loss": 1.4393,
+      "step": 199
+    },
+    {
+      "epoch": 0.5524861878453039,
+      "grad_norm": 0.8163523077964783,
+      "learning_rate": 8.753751665628141e-06,
+      "loss": 1.4303,
+      "step": 200
+    },
+    {
+      "epoch": 0.5552486187845304,
+      "grad_norm": 0.8884555697441101,
+      "learning_rate": 8.665248481815941e-06,
+      "loss": 1.4192,
+      "step": 201
+    },
+    {
+      "epoch": 0.5580110497237569,
+      "grad_norm": 0.8568834662437439,
+      "learning_rate": 8.576851617267151e-06,
+      "loss": 1.4873,
+      "step": 202
+    },
+    {
+      "epoch": 0.5607734806629834,
+      "grad_norm": 0.8569784760475159,
+      "learning_rate": 8.488568113209593e-06,
+      "loss": 1.4147,
+      "step": 203
+    },
+    {
+      "epoch": 0.56353591160221,
+      "grad_norm": 0.865711510181427,
+      "learning_rate": 8.4004050018414e-06,
+      "loss": 1.4441,
+      "step": 204
+    },
+    {
+      "epoch": 0.5662983425414365,
+      "grad_norm": 0.8934774398803711,
+      "learning_rate": 8.312369305770843e-06,
+      "loss": 1.5166,
+      "step": 205
+    },
+    {
+      "epoch": 0.569060773480663,
+      "grad_norm": 0.8222982287406921,
+      "learning_rate": 8.224468037456969e-06,
+      "loss": 1.4456,
+      "step": 206
+    },
+    {
+      "epoch": 0.5718232044198895,
+      "grad_norm": 0.8560197949409485,
+      "learning_rate": 8.136708198651022e-06,
+      "loss": 1.4419,
+      "step": 207
+    },
+    {
+      "epoch": 0.574585635359116,
+      "grad_norm": 0.8806837201118469,
+      "learning_rate": 8.04909677983872e-06,
+      "loss": 1.4493,
+      "step": 208
+    },
+    {
+      "epoch": 0.5773480662983426,
+      "grad_norm": 0.775467574596405,
+      "learning_rate": 7.961640759683416e-06,
+      "loss": 1.3158,
+      "step": 209
+    },
+    {
+      "epoch": 0.580110497237569,
+      "grad_norm": 0.8313515782356262,
+      "learning_rate": 7.874347104470234e-06,
+      "loss": 1.4309,
+      "step": 210
+    },
+    {
+      "epoch": 0.5828729281767956,
+      "grad_norm": 0.7876120209693909,
+      "learning_rate": 7.787222767551164e-06,
+      "loss": 1.2899,
+      "step": 211
+    },
+    {
+      "epoch": 0.585635359116022,
+      "grad_norm": 0.8478537201881409,
+      "learning_rate": 7.700274688791196e-06,
+      "loss": 1.5375,
+      "step": 212
+    },
+    {
+      "epoch": 0.5883977900552486,
+      "grad_norm": 0.8331094980239868,
+      "learning_rate": 7.613509794015517e-06,
+      "loss": 1.5305,
+      "step": 213
+    },
+    {
+      "epoch": 0.5911602209944752,
+      "grad_norm": 0.7719265818595886,
+      "learning_rate": 7.5269349944578454e-06,
+      "loss": 1.4768,
+      "step": 214
+    },
+    {
+      "epoch": 0.5939226519337016,
+      "grad_norm": 0.8830012083053589,
+      "learning_rate": 7.440557186209927e-06,
+      "loss": 1.4991,
+      "step": 215
+    },
+    {
+      "epoch": 0.5966850828729282,
+      "grad_norm": 0.8031134009361267,
+      "learning_rate": 7.354383249672212e-06,
+      "loss": 1.4687,
+      "step": 216
+    },
+    {
+      "epoch": 0.5994475138121547,
+      "grad_norm": 0.8189630508422852,
+      "learning_rate": 7.268420049005806e-06,
+      "loss": 1.448,
+      "step": 217
+    },
+    {
+      "epoch": 0.6022099447513812,
+      "grad_norm": 0.8882380723953247,
+      "learning_rate": 7.182674431585703e-06,
+      "loss": 1.3632,
+      "step": 218
+    },
+    {
+      "epoch": 0.6049723756906077,
+      "grad_norm": 0.9311167001724243,
+      "learning_rate": 7.097153227455379e-06,
+      "loss": 1.4632,
+      "step": 219
+    },
+    {
+      "epoch": 0.6077348066298343,
+      "grad_norm": 0.9001882076263428,
+      "learning_rate": 7.011863248782711e-06,
+      "loss": 1.4163,
+      "step": 220
+    },
+    {
+      "epoch": 0.6104972375690608,
+      "grad_norm": 0.8973594307899475,
+      "learning_rate": 6.92681128931739e-06,
+      "loss": 1.5515,
+      "step": 221
+    },
+    {
+      "epoch": 0.6132596685082873,
+      "grad_norm": 0.8810942769050598,
+      "learning_rate": 6.8420041238497525e-06,
+      "loss": 1.466,
+      "step": 222
+    },
+    {
+      "epoch": 0.6160220994475138,
+      "grad_norm": 0.8725515604019165,
+      "learning_rate": 6.7574485076711285e-06,
+      "loss": 1.4719,
+      "step": 223
+    },
+    {
+      "epoch": 0.6187845303867403,
+      "grad_norm": 0.837231457233429,
+      "learning_rate": 6.673151176035762e-06,
+      "loss": 1.4055,
+      "step": 224
+    },
+    {
+      "epoch": 0.6215469613259669,
+      "grad_norm": 0.8521233201026917,
+      "learning_rate": 6.589118843624316e-06,
+      "loss": 1.4228,
+      "step": 225
+    },
+    {
+      "epoch": 0.6243093922651933,
+      "grad_norm": 0.8560497164726257,
+      "learning_rate": 6.505358204009018e-06,
+      "loss": 1.3778,
+      "step": 226
+    },
+    {
+      "epoch": 0.6270718232044199,
+      "grad_norm": 0.8782879114151001,
+      "learning_rate": 6.421875929120469e-06,
+      "loss": 1.4595,
+      "step": 227
+    },
+    {
+      "epoch": 0.6298342541436464,
+      "grad_norm": 0.8700959086418152,
+      "learning_rate": 6.33867866871621e-06,
+      "loss": 1.4755,
+      "step": 228
+    },
+    {
+      "epoch": 0.6325966850828729,
+      "grad_norm": 0.8127918243408203,
+      "learning_rate": 6.25577304985103e-06,
+      "loss": 1.2702,
+      "step": 229
+    },
+    {
+      "epoch": 0.6353591160220995,
+      "grad_norm": 0.8742533922195435,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 1.4818,
+      "step": 230
+    },
+    {
+      "epoch": 0.638121546961326,
+      "grad_norm": 0.8978452086448669,
+      "learning_rate": 6.090863128277938e-06,
+      "loss": 1.4342,
+      "step": 231
+    },
+    {
+      "epoch": 0.6408839779005525,
+      "grad_norm": 0.8721697330474854,
+      "learning_rate": 6.008871961424259e-06,
+      "loss": 1.4321,
+      "step": 232
+    },
+    {
+      "epoch": 0.643646408839779,
+      "grad_norm": 0.8660262823104858,
+      "learning_rate": 5.927198706771813e-06,
+      "loss": 1.4375,
+      "step": 233
+    },
+    {
+      "epoch": 0.6464088397790055,
+      "grad_norm": 0.7931360006332397,
+      "learning_rate": 5.845849869981137e-06,
+      "loss": 1.4948,
+      "step": 234
+    },
+    {
+      "epoch": 0.649171270718232,
+      "grad_norm": 0.89198237657547,
+      "learning_rate": 5.764831930871346e-06,
+      "loss": 1.3788,
+      "step": 235
+    },
+    {
+      "epoch": 0.6519337016574586,
+      "grad_norm": 0.8168386220932007,
+      "learning_rate": 5.684151342903992e-06,
+      "loss": 1.4724,
+      "step": 236
+    },
+    {
+      "epoch": 0.6546961325966851,
+      "grad_norm": 0.8248292803764343,
+      "learning_rate": 5.603814532669032e-06,
+      "loss": 1.4688,
+      "step": 237
+    },
+    {
+      "epoch": 0.6574585635359116,
+      "grad_norm": 0.8722935318946838,
+      "learning_rate": 5.523827899372876e-06,
+      "loss": 1.4153,
+      "step": 238
+    },
+    {
+      "epoch": 0.6602209944751382,
+      "grad_norm": 0.8159798979759216,
+      "learning_rate": 5.444197814328707e-06,
+      "loss": 1.3893,
+      "step": 239
+    },
+    {
+      "epoch": 0.6629834254143646,
+      "grad_norm": 0.8457385897636414,
+      "learning_rate": 5.364930620448946e-06,
+      "loss": 1.4112,
+      "step": 240
+    },
+    {
+      "epoch": 0.6657458563535912,
+      "grad_norm": 0.9089652299880981,
+      "learning_rate": 5.286032631740023e-06,
+      "loss": 1.4384,
+      "step": 241
+    },
+    {
+      "epoch": 0.6685082872928176,
+      "grad_norm": 0.8519241213798523,
+      "learning_rate": 5.207510132799436e-06,
+      "loss": 1.4535,
+      "step": 242
+    },
+    {
+      "epoch": 0.6712707182320442,
+      "grad_norm": 0.833229124546051,
+      "learning_rate": 5.129369378315128e-06,
+      "loss": 1.4037,
+      "step": 243
+    },
+    {
+      "epoch": 0.6740331491712708,
+      "grad_norm": 0.9149712324142456,
+      "learning_rate": 5.051616592567323e-06,
+      "loss": 1.2153,
+      "step": 244
+    },
+    {
+      "epoch": 0.6767955801104972,
+      "grad_norm": 0.9115061163902283,
+      "learning_rate": 4.974257968932687e-06,
+      "loss": 1.3796,
+      "step": 245
+    },
+    {
+      "epoch": 0.6795580110497238,
+      "grad_norm": 0.8361886143684387,
+      "learning_rate": 4.897299669391006e-06,
+      "loss": 1.4624,
+      "step": 246
+    },
+    {
+      "epoch": 0.6823204419889503,
+      "grad_norm": 0.9515158534049988,
+      "learning_rate": 4.820747824034369e-06,
+      "loss": 1.4505,
+      "step": 247
+    },
+    {
+      "epoch": 0.6850828729281768,
+      "grad_norm": 0.8650820255279541,
+      "learning_rate": 4.744608530578872e-06,
+      "loss": 1.4711,
+      "step": 248
+    },
+    {
+      "epoch": 0.6878453038674033,
+      "grad_norm": 0.9377123713493347,
+      "learning_rate": 4.668887853878896e-06,
+      "loss": 1.3971,
+      "step": 249
+    },
+    {
+      "epoch": 0.6906077348066298,
+      "grad_norm": 0.8555616140365601,
+      "learning_rate": 4.593591825444028e-06,
+      "loss": 1.46,
+      "step": 250
+    },
+    {
+      "epoch": 0.6933701657458563,
+      "grad_norm": 0.8596077561378479,
+      "learning_rate": 4.518726442958599e-06,
+      "loss": 1.4312,
+      "step": 251
+    },
+    {
+      "epoch": 0.6961325966850829,
+      "grad_norm": 0.883187472820282,
+      "learning_rate": 4.444297669803981e-06,
+      "loss": 1.4086,
+      "step": 252
+    },
+    {
+      "epoch": 0.6988950276243094,
+      "grad_norm": 0.8663387298583984,
+      "learning_rate": 4.370311434583525e-06,
+      "loss": 1.4276,
+      "step": 253
+    },
+    {
+      "epoch": 0.7016574585635359,
+      "grad_norm": 0.9428577423095703,
+      "learning_rate": 4.296773630650358e-06,
+      "loss": 1.453,
+      "step": 254
+    },
+    {
+      "epoch": 0.7044198895027625,
+      "grad_norm": 0.9764917492866516,
+      "learning_rate": 4.223690115637944e-06,
+      "loss": 1.364,
+      "step": 255
+    },
+    {
+      "epoch": 0.7071823204419889,
+      "grad_norm": 0.9113486409187317,
+      "learning_rate": 4.15106671099347e-06,
+      "loss": 1.3832,
+      "step": 256
+    },
+    {
+      "epoch": 0.7099447513812155,
+      "grad_norm": 0.9364597201347351,
+      "learning_rate": 4.078909201514172e-06,
+      "loss": 1.4344,
+      "step": 257
+    },
+    {
+      "epoch": 0.712707182320442,
+      "grad_norm": 0.8799552321434021,
+      "learning_rate": 4.007223334886531e-06,
+      "loss": 1.4095,
+      "step": 258
+    },
+    {
+      "epoch": 0.7154696132596685,
+      "grad_norm": 0.9230160117149353,
+      "learning_rate": 3.936014821228448e-06,
+      "loss": 1.4143,
+      "step": 259
+    },
+    {
+      "epoch": 0.7182320441988951,
+      "grad_norm": 0.884773313999176,
+      "learning_rate": 3.865289332634407e-06,
+      "loss": 1.4485,
+      "step": 260
+    },
+    {
+      "epoch": 0.7209944751381215,
+      "grad_norm": 0.9042539596557617,
+      "learning_rate": 3.7950525027236585e-06,
+      "loss": 1.4732,
+      "step": 261
+    },
+    {
+      "epoch": 0.7237569060773481,
+      "grad_norm": 0.9420682787895203,
+      "learning_rate": 3.7253099261914794e-06,
+      "loss": 1.3888,
+      "step": 262
+    },
+    {
+      "epoch": 0.7265193370165746,
+      "grad_norm": 0.8805732131004333,
+      "learning_rate": 3.6560671583635467e-06,
+      "loss": 1.3925,
+      "step": 263
+    },
+    {
+      "epoch": 0.7292817679558011,
+      "grad_norm": 0.8690923452377319,
+      "learning_rate": 3.5873297147533913e-06,
+      "loss": 1.4381,
+      "step": 264
+    },
+    {
+      "epoch": 0.7320441988950276,
+      "grad_norm": 0.9199298024177551,
+      "learning_rate": 3.5191030706230967e-06,
+      "loss": 1.4263,
+      "step": 265
+    },
+    {
+      "epoch": 0.7348066298342542,
+      "grad_norm": 0.9645051956176758,
+      "learning_rate": 3.4513926605471504e-06,
+      "loss": 1.466,
+      "step": 266
+    },
+    {
+      "epoch": 0.7375690607734806,
+      "grad_norm": 0.9399710893630981,
+      "learning_rate": 3.3842038779795594e-06,
+      "loss": 1.4011,
+      "step": 267
+    },
+    {
+      "epoch": 0.7403314917127072,
+      "grad_norm": 0.9479338526725769,
+      "learning_rate": 3.3175420748242405e-06,
+      "loss": 1.4001,
+      "step": 268
+    },
+    {
+      "epoch": 0.7430939226519337,
+      "grad_norm": 0.8783372640609741,
+      "learning_rate": 3.2514125610086957e-06,
+      "loss": 1.4476,
+      "step": 269
+    },
+    {
+      "epoch": 0.7458563535911602,
+      "grad_norm": 0.9430367946624756,
+      "learning_rate": 3.1858206040610883e-06,
+      "loss": 1.4774,
+      "step": 270
+    },
+    {
+      "epoch": 0.7486187845303868,
+      "grad_norm": 0.9073113203048706,
+      "learning_rate": 3.1207714286906253e-06,
+      "loss": 1.4754,
+      "step": 271
+    },
+    {
+      "epoch": 0.7513812154696132,
+      "grad_norm": 0.947472870349884,
+      "learning_rate": 3.0562702163713954e-06,
+      "loss": 1.3923,
+      "step": 272
+    },
+    {
+      "epoch": 0.7541436464088398,
+      "grad_norm": 0.8627873659133911,
+      "learning_rate": 2.9923221049296448e-06,
+      "loss": 1.492,
+      "step": 273
+    },
+    {
+      "epoch": 0.7541436464088398,
+      "eval_loss": 1.086176872253418,
+      "eval_runtime": 126.497,
+      "eval_samples_per_second": 11.32,
+      "eval_steps_per_second": 0.356,
+      "step": 273
+    },
+    {
+      "epoch": 0.7569060773480663,
+      "grad_norm": 0.9082939028739929,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 1.4281,
+      "step": 274
+    },
+    {
+      "epoch": 0.7596685082872928,
+      "grad_norm": 0.8859499096870422,
+      "learning_rate": 2.8661055152923456e-06,
+      "loss": 1.4502,
+      "step": 275
+    },
+    {
+      "epoch": 0.7624309392265194,
+      "grad_norm": 1.017196536064148,
+      "learning_rate": 2.8038470908443717e-06,
+      "loss": 1.4254,
+      "step": 276
+    },
+    {
+      "epoch": 0.7651933701657458,
+      "grad_norm": 0.9072262048721313,
+      "learning_rate": 2.742161873968202e-06,
+      "loss": 1.4445,
+      "step": 277
+    },
+    {
+      "epoch": 0.7679558011049724,
+      "grad_norm": 0.9374067783355713,
+      "learning_rate": 2.681054778182748e-06,
+      "loss": 1.401,
+      "step": 278
+    },
+    {
+      "epoch": 0.7707182320441989,
+      "grad_norm": 0.9527032971382141,
+      "learning_rate": 2.6205306709568358e-06,
+      "loss": 1.4027,
+      "step": 279
+    },
+    {
+      "epoch": 0.7734806629834254,
+      "grad_norm": 0.9139413833618164,
+      "learning_rate": 2.5605943733215044e-06,
+      "loss": 1.3755,
+      "step": 280
+    },
+    {
+      "epoch": 0.7762430939226519,
+      "grad_norm": 0.9385672807693481,
+      "learning_rate": 2.501250659485992e-06,
+      "loss": 1.3584,
+      "step": 281
+    },
+    {
+      "epoch": 0.7790055248618785,
+      "grad_norm": 0.8780643343925476,
+      "learning_rate": 2.4425042564574186e-06,
+      "loss": 1.4766,
+      "step": 282
+    },
+    {
+      "epoch": 0.7817679558011049,
+      "grad_norm": 0.8696600198745728,
+      "learning_rate": 2.38435984366429e-06,
+      "loss": 1.4363,
+      "step": 283
+    },
+    {
+      "epoch": 0.7845303867403315,
+      "grad_norm": 0.9084115028381348,
+      "learning_rate": 2.3268220525837436e-06,
+      "loss": 1.4428,
+      "step": 284
+    },
+    {
+      "epoch": 0.787292817679558,
+      "grad_norm": 0.9125878214836121,
+      "learning_rate": 2.26989546637263e-06,
+      "loss": 1.432,
+      "step": 285
+    },
+    {
+      "epoch": 0.7900552486187845,
+      "grad_norm": 0.855888307094574,
+      "learning_rate": 2.213584619502451e-06,
+      "loss": 1.4207,
+      "step": 286
+    },
+    {
+      "epoch": 0.7928176795580111,
+      "grad_norm": 0.9291403889656067,
+      "learning_rate": 2.157893997398146e-06,
+      "loss": 1.3608,
+      "step": 287
+    },
+    {
+      "epoch": 0.7955801104972375,
+      "grad_norm": 1.0609382390975952,
+      "learning_rate": 2.1028280360808405e-06,
+      "loss": 1.3775,
+      "step": 288
+    },
+    {
+      "epoch": 0.7983425414364641,
+      "grad_norm": 0.9883527755737305,
+      "learning_rate": 2.0483911218144713e-06,
+      "loss": 1.3714,
+      "step": 289
+    },
+    {
+      "epoch": 0.8011049723756906,
+      "grad_norm": 0.9266678094863892,
+      "learning_rate": 1.994587590756397e-06,
+      "loss": 1.3421,
+      "step": 290
+    },
+    {
+      "epoch": 0.8038674033149171,
+      "grad_norm": 0.9002796411514282,
+      "learning_rate": 1.941421728612023e-06,
+      "loss": 1.4329,
+      "step": 291
+    },
+    {
+      "epoch": 0.8066298342541437,
+      "grad_norm": 0.9300910830497742,
+      "learning_rate": 1.8888977702934086e-06,
+      "loss": 1.4207,
+      "step": 292
+    },
+    {
+      "epoch": 0.8093922651933702,
+      "grad_norm": 0.8839243054389954,
+      "learning_rate": 1.8370198995819432e-06,
+      "loss": 1.4385,
+      "step": 293
+    },
+    {
+      "epoch": 0.8121546961325967,
+      "grad_norm": 0.9355608224868774,
+      "learning_rate": 1.7857922487950873e-06,
+      "loss": 1.405,
+      "step": 294
+    },
+    {
+      "epoch": 0.8149171270718232,
+      "grad_norm": 0.8696985840797424,
+      "learning_rate": 1.7352188984572026e-06,
+      "loss": 1.4654,
+      "step": 295
+    },
+    {
+      "epoch": 0.8176795580110497,
+      "grad_norm": 0.9162890315055847,
+      "learning_rate": 1.6853038769745466e-06,
+      "loss": 1.4809,
+      "step": 296
+    },
+    {
+      "epoch": 0.8204419889502762,
+      "grad_norm": 0.9043356776237488,
+      "learning_rate": 1.6360511603143648e-06,
+      "loss": 1.3899,
+      "step": 297
+    },
+    {
+      "epoch": 0.8232044198895028,
+      "grad_norm": 0.877433717250824,
+      "learning_rate": 1.587464671688187e-06,
+      "loss": 1.3792,
+      "step": 298
+    },
+    {
+      "epoch": 0.8259668508287292,
+      "grad_norm": 0.939689040184021,
+      "learning_rate": 1.5395482812393513e-06,
+      "loss": 1.463,
+      "step": 299
+    },
+    {
+      "epoch": 0.8287292817679558,
+      "grad_norm": 0.9307026267051697,
+      "learning_rate": 1.492305805734693e-06,
+      "loss": 1.3848,
+      "step": 300
+    },
+    {
+      "epoch": 0.8314917127071824,
+      "grad_norm": 0.9378739595413208,
+      "learning_rate": 1.4457410082605483e-06,
+      "loss": 1.4531,
+      "step": 301
+    },
+    {
+      "epoch": 0.8342541436464088,
+      "grad_norm": 0.9288903474807739,
+      "learning_rate": 1.3998575979229944e-06,
+      "loss": 1.5031,
+      "step": 302
+    },
+    {
+      "epoch": 0.8370165745856354,
+      "grad_norm": 0.9209362864494324,
+      "learning_rate": 1.3546592295524075e-06,
+      "loss": 1.4257,
+      "step": 303
+    },
+    {
+      "epoch": 0.8397790055248618,
+      "grad_norm": 0.9554373025894165,
+      "learning_rate": 1.3101495034123313e-06,
+      "loss": 1.3836,
+      "step": 304
+    },
+    {
+      "epoch": 0.8425414364640884,
+      "grad_norm": 0.9340296983718872,
+      "learning_rate": 1.2663319649127025e-06,
+      "loss": 1.4377,
+      "step": 305
+    },
+    {
+      "epoch": 0.8453038674033149,
+      "grad_norm": 0.8898835182189941,
+      "learning_rate": 1.2232101043274437e-06,
+      "loss": 1.4425,
+      "step": 306
+    },
+    {
+      "epoch": 0.8480662983425414,
+      "grad_norm": 0.9213349223136902,
+      "learning_rate": 1.1807873565164507e-06,
+      "loss": 1.3703,
+      "step": 307
+    },
+    {
+      "epoch": 0.850828729281768,
+      "grad_norm": 0.9146559238433838,
+      "learning_rate": 1.139067100651976e-06,
+      "loss": 1.4069,
+      "step": 308
+    },
+    {
+      "epoch": 0.8535911602209945,
+      "grad_norm": 0.9761607050895691,
+      "learning_rate": 1.0980526599494733e-06,
+      "loss": 1.3289,
+      "step": 309
+    },
+    {
+      "epoch": 0.856353591160221,
+      "grad_norm": 0.9104629755020142,
+      "learning_rate": 1.0577473014028872e-06,
+      "loss": 1.3388,
+      "step": 310
+    },
+    {
+      "epoch": 0.8591160220994475,
+      "grad_norm": 0.9511966109275818,
+      "learning_rate": 1.0181542355244167e-06,
+      "loss": 1.4944,
+      "step": 311
+    },
+    {
+      "epoch": 0.861878453038674,
+      "grad_norm": 0.9397574663162231,
+      "learning_rate": 9.792766160887868e-07,
+      "loss": 1.3277,
+      "step": 312
+    },
+    {
+      "epoch": 0.8646408839779005,
+      "grad_norm": 0.9395145773887634,
+      "learning_rate": 9.411175398820271e-07,
+      "loss": 1.393,
+      "step": 313
+    },
+    {
+      "epoch": 0.8674033149171271,
+      "grad_norm": 0.902461051940918,
+      "learning_rate": 9.036800464548157e-07,
+      "loss": 1.4936,
+      "step": 314
+    },
+    {
+      "epoch": 0.8701657458563536,
+      "grad_norm": 0.9002877473831177,
+      "learning_rate": 8.669671178803485e-07,
+      "loss": 1.4795,
+      "step": 315
+    },
+    {
+      "epoch": 0.8729281767955801,
+      "grad_norm": 0.9265264868736267,
+      "learning_rate": 8.309816785168035e-07,
+      "loss": 1.4026,
+      "step": 316
+    },
+    {
+      "epoch": 0.8756906077348067,
+      "grad_norm": 0.8972640037536621,
+      "learning_rate": 7.957265947744131e-07,
+      "loss": 1.3753,
+      "step": 317
+    },
+    {
+      "epoch": 0.8784530386740331,
+      "grad_norm": 0.896083414554596,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 1.4335,
+      "step": 318
+    },
+    {
+      "epoch": 0.8812154696132597,
+      "grad_norm": 0.9599345922470093,
+      "learning_rate": 7.274186686889539e-07,
+      "loss": 1.3298,
+      "step": 319
+    },
+    {
+      "epoch": 0.8839779005524862,
+      "grad_norm": 0.9055171012878418,
+      "learning_rate": 6.943712673948643e-07,
+      "loss": 1.3585,
+      "step": 320
+    },
+    {
+      "epoch": 0.8867403314917127,
+      "grad_norm": 0.9201679229736328,
+      "learning_rate": 6.620651033864844e-07,
+      "loss": 1.4686,
+      "step": 321
+    },
+    {
+      "epoch": 0.8895027624309392,
+      "grad_norm": 0.9608058929443359,
+      "learning_rate": 6.305027500023841e-07,
+      "loss": 1.4166,
+      "step": 322
+    },
+    {
+      "epoch": 0.8922651933701657,
+      "grad_norm": 0.9788545966148376,
+      "learning_rate": 5.996867213330993e-07,
+      "loss": 1.4833,
+      "step": 323
+    },
+    {
+      "epoch": 0.8950276243093923,
+      "grad_norm": 0.9282844662666321,
+      "learning_rate": 5.696194720208792e-07,
+      "loss": 1.4275,
+      "step": 324
+    },
+    {
+      "epoch": 0.8977900552486188,
+      "grad_norm": 1.050364375114441,
+      "learning_rate": 5.403033970641647e-07,
+      "loss": 1.3425,
+      "step": 325
+    },
+    {
+      "epoch": 0.9005524861878453,
+      "grad_norm": 0.9263676404953003,
+      "learning_rate": 5.117408316268047e-07,
+      "loss": 1.4753,
+      "step": 326
+    },
+    {
+      "epoch": 0.9033149171270718,
+      "grad_norm": 0.8985906839370728,
+      "learning_rate": 4.839340508520563e-07,
+      "loss": 1.241,
+      "step": 327
+    },
+    {
+      "epoch": 0.9060773480662984,
+      "grad_norm": 1.0023422241210938,
+      "learning_rate": 4.5688526968136193e-07,
+      "loss": 1.2997,
+      "step": 328
+    },
+    {
+      "epoch": 0.9088397790055248,
+      "grad_norm": 0.8664121627807617,
+      "learning_rate": 4.305966426779118e-07,
+      "loss": 1.4895,
+      "step": 329
+    },
+    {
+      "epoch": 0.9116022099447514,
+      "grad_norm": 0.8682915568351746,
+      "learning_rate": 4.0507026385502747e-07,
+      "loss": 1.4453,
+      "step": 330
+    },
+    {
+      "epoch": 0.914364640883978,
+      "grad_norm": 0.9119102954864502,
+      "learning_rate": 3.8030816650935777e-07,
+      "loss": 1.4974,
+      "step": 331
+    },
+    {
+      "epoch": 0.9171270718232044,
+      "grad_norm": 0.8785637021064758,
+      "learning_rate": 3.5631232305893047e-07,
+      "loss": 1.4397,
+      "step": 332
+    },
+    {
+      "epoch": 0.919889502762431,
+      "grad_norm": 0.8890804648399353,
+      "learning_rate": 3.3308464488602587e-07,
+      "loss": 1.4053,
+      "step": 333
+    },
+    {
+      "epoch": 0.9226519337016574,
+      "grad_norm": 0.9314624071121216,
+      "learning_rate": 3.106269821849273e-07,
+      "loss": 1.4412,
+      "step": 334
+    },
+    {
+      "epoch": 0.925414364640884,
+      "grad_norm": 0.8827205896377563,
+      "learning_rate": 2.889411238145545e-07,
+      "loss": 1.3467,
+      "step": 335
+    },
+    {
+      "epoch": 0.9281767955801105,
+      "grad_norm": 0.9344226717948914,
+      "learning_rate": 2.6802879715596585e-07,
+      "loss": 1.4252,
+      "step": 336
+    },
+    {
+      "epoch": 0.930939226519337,
+      "grad_norm": 0.9009850025177002,
+      "learning_rate": 2.478916679747623e-07,
+      "loss": 1.4194,
+      "step": 337
+    },
+    {
+      "epoch": 0.9337016574585635,
+      "grad_norm": 0.9627113342285156,
+      "learning_rate": 2.2853134028840594e-07,
+      "loss": 1.4451,
+      "step": 338
+    },
+    {
+      "epoch": 0.93646408839779,
+      "grad_norm": 0.9164440631866455,
+      "learning_rate": 2.099493562384469e-07,
+      "loss": 1.3981,
+      "step": 339
+    },
+    {
+      "epoch": 0.9392265193370166,
+      "grad_norm": 0.8945847749710083,
+      "learning_rate": 1.921471959676957e-07,
+      "loss": 1.3487,
+      "step": 340
+    },
+    {
+      "epoch": 0.9419889502762431,
+      "grad_norm": 0.8356913328170776,
+      "learning_rate": 1.7512627750230772e-07,
+      "loss": 1.4971,
+      "step": 341
+    },
+    {
+      "epoch": 0.9447513812154696,
+      "grad_norm": 0.9447980523109436,
+      "learning_rate": 1.5888795663883904e-07,
+      "loss": 1.3828,
+      "step": 342
+    },
+    {
+      "epoch": 0.9475138121546961,
+      "grad_norm": 1.0205456018447876,
+      "learning_rate": 1.4343352683625412e-07,
+      "loss": 1.3057,
+      "step": 343
+    },
+    {
+      "epoch": 0.9502762430939227,
+      "grad_norm": 0.850608229637146,
+      "learning_rate": 1.2876421911288906e-07,
+      "loss": 1.3937,
+      "step": 344
+    },
+    {
+      "epoch": 0.9530386740331491,
+      "grad_norm": 1.000903606414795,
+      "learning_rate": 1.148812019483958e-07,
+      "loss": 1.4076,
+      "step": 345
+    },
+    {
+      "epoch": 0.9558011049723757,
+      "grad_norm": 0.9791882634162903,
+      "learning_rate": 1.0178558119067316e-07,
+      "loss": 1.4057,
+      "step": 346
+    },
+    {
+      "epoch": 0.9585635359116023,
+      "grad_norm": 0.9408354163169861,
+      "learning_rate": 8.947839996777286e-08,
+      "loss": 1.3266,
+      "step": 347
+    },
+    {
+      "epoch": 0.9613259668508287,
+      "grad_norm": 0.8975253105163574,
+      "learning_rate": 7.796063860481595e-08,
+      "loss": 1.46,
+      "step": 348
+    },
+    {
+      "epoch": 0.9640883977900553,
+      "grad_norm": 0.891627848148346,
+      "learning_rate": 6.723321454590093e-08,
+      "loss": 1.4529,
+      "step": 349
+    },
+    {
+      "epoch": 0.9668508287292817,
+      "grad_norm": 0.9184878468513489,
+      "learning_rate": 5.7296982281026534e-08,
+      "loss": 1.3415,
+      "step": 350
+    },
+    {
+      "epoch": 0.9696132596685083,
+      "grad_norm": 0.8612070679664612,
+      "learning_rate": 4.815273327803183e-08,
+      "loss": 1.3639,
+      "step": 351
+    },
+    {
+      "epoch": 0.9723756906077348,
+      "grad_norm": 0.9538889527320862,
+      "learning_rate": 3.980119591954101e-08,
+      "loss": 1.3331,
+      "step": 352
+    },
+    {
+      "epoch": 0.9751381215469613,
+      "grad_norm": 0.8873268365859985,
+      "learning_rate": 3.224303544495766e-08,
+      "loss": 1.4182,
+      "step": 353
+    },
+    {
+      "epoch": 0.9779005524861878,
+      "grad_norm": 0.8183327317237854,
+      "learning_rate": 2.547885389746485e-08,
+      "loss": 1.2914,
+      "step": 354
+    },
+    {
+      "epoch": 0.9806629834254144,
+      "grad_norm": 0.9462449550628662,
+      "learning_rate": 1.9509190076074657e-08,
+      "loss": 1.3229,
+      "step": 355
+    },
+    {
+      "epoch": 0.9834254143646409,
+      "grad_norm": 0.9248088598251343,
+      "learning_rate": 1.4334519492711362e-08,
+      "loss": 1.4762,
+      "step": 356
+    },
+    {
+      "epoch": 0.9861878453038674,
+      "grad_norm": 0.8894135355949402,
+      "learning_rate": 9.955254334328424e-09,
+      "loss": 1.4353,
+      "step": 357
+    },
+    {
+      "epoch": 0.988950276243094,
+      "grad_norm": 0.936488151550293,
+      "learning_rate": 6.371743430082511e-09,
+      "loss": 1.4634,
+      "step": 358
+    },
+    {
+      "epoch": 0.9917127071823204,
+      "grad_norm": 0.9139291644096375,
+      "learning_rate": 3.5842722235468475e-09,
+      "loss": 1.3508,
+      "step": 359
+    },
+    {
+      "epoch": 0.994475138121547,
+      "grad_norm": 0.886863112449646,
+      "learning_rate": 1.593062749967178e-09,
+      "loss": 1.4296,
+      "step": 360
+    },
+    {
+      "epoch": 0.9972375690607734,
+      "grad_norm": 0.9713277816772461,
+      "learning_rate": 3.982736185859093e-10,
+      "loss": 1.4559,
+      "step": 361
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9464192986488342,
+      "learning_rate": 0.0,
+      "loss": 1.4281,
+      "step": 362
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 362,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4060387535872328e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

{checkpoint-1446 → checkpoint-362}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:822e9ecd3c6cae4121c1ca48be3e43529504212f53af9850a5695094a2e7c768
+oid sha256:bf9ad6bb9b3339138a3d0a63767dce4daa41857e39097a36078203d7f04e972a
 size 6200

checkpoint-723/README.md

@@ -1,202 +0,0 @@
----
-base_model: unsloth/Meta-Llama-3.1-8B-Instruct
-library_name: peft
----
-
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.12.0

checkpoint-723/adapter_config.json

@@ -1,34 +0,0 @@
-{
-  "alpha_pattern": {},
-  "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct",
-  "bias": "none",
-  "fan_in_fan_out": null,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "v_proj",
-    "gate_proj",
-    "k_proj",
-    "o_proj",
-    "q_proj",
-    "down_proj",
-    "up_proj"
-  ],
-  "task_type": "CAUSAL_LM",
-  "use_dora": false,
-  "use_rslora": false
-}

checkpoint-723/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5815bc4053a43ee357f92bd97e312aa041de714c24e76d01b0755ec77c2c3e9a
-size 15024

checkpoint-723/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:56573cd42c7ee0479d656e7eac67f27bcdf3dd4d6d31efbb12a740276a0c6b8f
-size 1064

checkpoint-723/special_tokens_map.json

@@ -1,23 +0,0 @@
-{
-  "bos_token": {
-    "content": "<|begin_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|eot_id|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|end_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

checkpoint-723/tokenizer_config.json

@@ -1,2064 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "128000": {
-      "content": "<|begin_of_text|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128001": {
-      "content": "<|end_of_text|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128002": {
-      "content": "<|reserved_special_token_0|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128003": {
-      "content": "<|reserved_special_token_1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128004": {
-      "content": "<|finetune_right_pad_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128005": {
-      "content": "<|reserved_special_token_2|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128006": {
-      "content": "<|start_header_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128007": {
-      "content": "<|end_header_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128008": {
-      "content": "<|eom_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128009": {
-      "content": "<|eot_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128010": {
-      "content": "<|python_tag|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128011": {
-      "content": "<|reserved_special_token_3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128012": {
-      "content": "<|reserved_special_token_4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128013": {
-      "content": "<|reserved_special_token_5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128014": {
-      "content": "<|reserved_special_token_6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128015": {
-      "content": "<|reserved_special_token_7|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128016": {
-      "content": "<|reserved_special_token_8|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128017": {
-      "content": "<|reserved_special_token_9|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128018": {
-      "content": "<|reserved_special_token_10|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128019": {
-      "content": "<|reserved_special_token_11|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128020": {
-      "content": "<|reserved_special_token_12|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128021": {
-      "content": "<|reserved_special_token_13|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128022": {
-      "content": "<|reserved_special_token_14|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128023": {
-      "content": "<|reserved_special_token_15|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128024": {
-      "content": "<|reserved_special_token_16|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128025": {
-      "content": "<|reserved_special_token_17|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128026": {
-      "content": "<|reserved_special_token_18|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128027": {
-      "content": "<|reserved_special_token_19|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128028": {
-      "content": "<|reserved_special_token_20|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128029": {
-      "content": "<|reserved_special_token_21|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128030": {
-      "content": "<|reserved_special_token_22|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128031": {
-      "content": "<|reserved_special_token_23|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128032": {
-      "content": "<|reserved_special_token_24|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128033": {
-      "content": "<|reserved_special_token_25|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128034": {
-      "content": "<|reserved_special_token_26|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128035": {
-      "content": "<|reserved_special_token_27|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128036": {
-      "content": "<|reserved_special_token_28|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128037": {
-      "content": "<|reserved_special_token_29|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128038": {
-      "content": "<|reserved_special_token_30|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128039": {
-      "content": "<|reserved_special_token_31|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128040": {
-      "content": "<|reserved_special_token_32|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128041": {
-      "content": "<|reserved_special_token_33|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128042": {
-      "content": "<|reserved_special_token_34|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128043": {
-      "content": "<|reserved_special_token_35|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128044": {
-      "content": "<|reserved_special_token_36|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128045": {
-      "content": "<|reserved_special_token_37|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128046": {
-      "content": "<|reserved_special_token_38|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128047": {
-      "content": "<|reserved_special_token_39|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128048": {
-      "content": "<|reserved_special_token_40|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128049": {
-      "content": "<|reserved_special_token_41|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128050": {
-      "content": "<|reserved_special_token_42|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128051": {
-      "content": "<|reserved_special_token_43|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128052": {
-      "content": "<|reserved_special_token_44|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128053": {
-      "content": "<|reserved_special_token_45|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128054": {
-      "content": "<|reserved_special_token_46|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128055": {
-      "content": "<|reserved_special_token_47|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128056": {
-      "content": "<|reserved_special_token_48|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128057": {
-      "content": "<|reserved_special_token_49|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128058": {
-      "content": "<|reserved_special_token_50|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128059": {
-      "content": "<|reserved_special_token_51|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128060": {
-      "content": "<|reserved_special_token_52|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128061": {
-      "content": "<|reserved_special_token_53|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128062": {
-      "content": "<|reserved_special_token_54|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128063": {
-      "content": "<|reserved_special_token_55|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128064": {
-      "content": "<|reserved_special_token_56|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128065": {
-      "content": "<|reserved_special_token_57|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128066": {
-      "content": "<|reserved_special_token_58|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128067": {
-      "content": "<|reserved_special_token_59|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128068": {
-      "content": "<|reserved_special_token_60|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128069": {
-      "content": "<|reserved_special_token_61|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128070": {
-      "content": "<|reserved_special_token_62|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128071": {
-      "content": "<|reserved_special_token_63|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128072": {
-      "content": "<|reserved_special_token_64|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128073": {
-      "content": "<|reserved_special_token_65|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128074": {
-      "content": "<|reserved_special_token_66|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128075": {
-      "content": "<|reserved_special_token_67|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128076": {
-      "content": "<|reserved_special_token_68|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128077": {
-      "content": "<|reserved_special_token_69|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128078": {
-      "content": "<|reserved_special_token_70|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128079": {
-      "content": "<|reserved_special_token_71|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128080": {
-      "content": "<|reserved_special_token_72|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128081": {
-      "content": "<|reserved_special_token_73|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128082": {
-      "content": "<|reserved_special_token_74|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128083": {
-      "content": "<|reserved_special_token_75|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128084": {
-      "content": "<|reserved_special_token_76|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128085": {
-      "content": "<|reserved_special_token_77|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128086": {
-      "content": "<|reserved_special_token_78|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128087": {
-      "content": "<|reserved_special_token_79|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128088": {
-      "content": "<|reserved_special_token_80|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128089": {
-      "content": "<|reserved_special_token_81|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128090": {
-      "content": "<|reserved_special_token_82|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128091": {
-      "content": "<|reserved_special_token_83|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128092": {
-      "content": "<|reserved_special_token_84|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128093": {
-      "content": "<|reserved_special_token_85|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128094": {
-      "content": "<|reserved_special_token_86|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128095": {
-      "content": "<|reserved_special_token_87|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128096": {
-      "content": "<|reserved_special_token_88|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128097": {
-      "content": "<|reserved_special_token_89|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128098": {
-      "content": "<|reserved_special_token_90|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128099": {
-      "content": "<|reserved_special_token_91|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128100": {
-      "content": "<|reserved_special_token_92|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128101": {
-      "content": "<|reserved_special_token_93|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128102": {
-      "content": "<|reserved_special_token_94|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128103": {
-      "content": "<|reserved_special_token_95|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128104": {
-      "content": "<|reserved_special_token_96|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128105": {
-      "content": "<|reserved_special_token_97|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128106": {
-      "content": "<|reserved_special_token_98|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128107": {
-      "content": "<|reserved_special_token_99|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128108": {
-      "content": "<|reserved_special_token_100|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128109": {
-      "content": "<|reserved_special_token_101|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128110": {
-      "content": "<|reserved_special_token_102|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128111": {
-      "content": "<|reserved_special_token_103|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128112": {
-      "content": "<|reserved_special_token_104|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128113": {
-      "content": "<|reserved_special_token_105|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128114": {
-      "content": "<|reserved_special_token_106|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128115": {
-      "content": "<|reserved_special_token_107|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128116": {
-      "content": "<|reserved_special_token_108|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128117": {
-      "content": "<|reserved_special_token_109|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128118": {
-      "content": "<|reserved_special_token_110|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128119": {
-      "content": "<|reserved_special_token_111|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128120": {
-      "content": "<|reserved_special_token_112|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128121": {
-      "content": "<|reserved_special_token_113|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128122": {
-      "content": "<|reserved_special_token_114|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128123": {
-      "content": "<|reserved_special_token_115|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128124": {
-      "content": "<|reserved_special_token_116|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128125": {
-      "content": "<|reserved_special_token_117|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128126": {
-      "content": "<|reserved_special_token_118|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128127": {
-      "content": "<|reserved_special_token_119|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128128": {
-      "content": "<|reserved_special_token_120|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128129": {
-      "content": "<|reserved_special_token_121|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128130": {
-      "content": "<|reserved_special_token_122|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128131": {
-      "content": "<|reserved_special_token_123|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128132": {
-      "content": "<|reserved_special_token_124|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128133": {
-      "content": "<|reserved_special_token_125|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128134": {
-      "content": "<|reserved_special_token_126|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128135": {
-      "content": "<|reserved_special_token_127|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128136": {
-      "content": "<|reserved_special_token_128|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128137": {
-      "content": "<|reserved_special_token_129|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128138": {
-      "content": "<|reserved_special_token_130|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128139": {
-      "content": "<|reserved_special_token_131|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128140": {
-      "content": "<|reserved_special_token_132|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128141": {
-      "content": "<|reserved_special_token_133|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128142": {
-      "content": "<|reserved_special_token_134|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128143": {
-      "content": "<|reserved_special_token_135|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128144": {
-      "content": "<|reserved_special_token_136|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128145": {
-      "content": "<|reserved_special_token_137|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128146": {
-      "content": "<|reserved_special_token_138|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128147": {
-      "content": "<|reserved_special_token_139|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128148": {
-      "content": "<|reserved_special_token_140|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128149": {
-      "content": "<|reserved_special_token_141|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128150": {
-      "content": "<|reserved_special_token_142|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128151": {
-      "content": "<|reserved_special_token_143|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128152": {
-      "content": "<|reserved_special_token_144|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128153": {
-      "content": "<|reserved_special_token_145|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128154": {
-      "content": "<|reserved_special_token_146|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128155": {
-      "content": "<|reserved_special_token_147|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128156": {
-      "content": "<|reserved_special_token_148|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128157": {
-      "content": "<|reserved_special_token_149|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128158": {
-      "content": "<|reserved_special_token_150|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128159": {
-      "content": "<|reserved_special_token_151|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128160": {
-      "content": "<|reserved_special_token_152|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128161": {
-      "content": "<|reserved_special_token_153|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128162": {
-      "content": "<|reserved_special_token_154|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128163": {
-      "content": "<|reserved_special_token_155|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128164": {
-      "content": "<|reserved_special_token_156|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128165": {
-      "content": "<|reserved_special_token_157|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128166": {
-      "content": "<|reserved_special_token_158|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128167": {
-      "content": "<|reserved_special_token_159|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128168": {
-      "content": "<|reserved_special_token_160|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128169": {
-      "content": "<|reserved_special_token_161|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128170": {
-      "content": "<|reserved_special_token_162|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128171": {
-      "content": "<|reserved_special_token_163|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128172": {
-      "content": "<|reserved_special_token_164|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128173": {
-      "content": "<|reserved_special_token_165|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128174": {
-      "content": "<|reserved_special_token_166|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128175": {
-      "content": "<|reserved_special_token_167|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128176": {
-      "content": "<|reserved_special_token_168|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128177": {
-      "content": "<|reserved_special_token_169|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128178": {
-      "content": "<|reserved_special_token_170|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128179": {
-      "content": "<|reserved_special_token_171|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128180": {
-      "content": "<|reserved_special_token_172|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128181": {
-      "content": "<|reserved_special_token_173|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128182": {
-      "content": "<|reserved_special_token_174|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128183": {
-      "content": "<|reserved_special_token_175|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128184": {
-      "content": "<|reserved_special_token_176|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128185": {
-      "content": "<|reserved_special_token_177|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128186": {
-      "content": "<|reserved_special_token_178|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128187": {
-      "content": "<|reserved_special_token_179|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128188": {
-      "content": "<|reserved_special_token_180|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128189": {
-      "content": "<|reserved_special_token_181|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128190": {
-      "content": "<|reserved_special_token_182|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128191": {
-      "content": "<|reserved_special_token_183|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128192": {
-      "content": "<|reserved_special_token_184|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128193": {
-      "content": "<|reserved_special_token_185|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128194": {
-      "content": "<|reserved_special_token_186|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128195": {
-      "content": "<|reserved_special_token_187|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128196": {
-      "content": "<|reserved_special_token_188|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128197": {
-      "content": "<|reserved_special_token_189|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128198": {
-      "content": "<|reserved_special_token_190|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128199": {
-      "content": "<|reserved_special_token_191|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128200": {
-      "content": "<|reserved_special_token_192|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128201": {
-      "content": "<|reserved_special_token_193|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128202": {
-      "content": "<|reserved_special_token_194|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128203": {
-      "content": "<|reserved_special_token_195|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128204": {
-      "content": "<|reserved_special_token_196|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128205": {
-      "content": "<|reserved_special_token_197|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128206": {
-      "content": "<|reserved_special_token_198|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128207": {
-      "content": "<|reserved_special_token_199|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128208": {
-      "content": "<|reserved_special_token_200|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128209": {
-      "content": "<|reserved_special_token_201|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128210": {
-      "content": "<|reserved_special_token_202|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128211": {
-      "content": "<|reserved_special_token_203|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128212": {
-      "content": "<|reserved_special_token_204|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128213": {
-      "content": "<|reserved_special_token_205|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128214": {
-      "content": "<|reserved_special_token_206|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128215": {
-      "content": "<|reserved_special_token_207|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128216": {
-      "content": "<|reserved_special_token_208|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128217": {
-      "content": "<|reserved_special_token_209|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128218": {
-      "content": "<|reserved_special_token_210|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128219": {
-      "content": "<|reserved_special_token_211|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128220": {
-      "content": "<|reserved_special_token_212|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128221": {
-      "content": "<|reserved_special_token_213|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128222": {
-      "content": "<|reserved_special_token_214|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128223": {
-      "content": "<|reserved_special_token_215|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128224": {
-      "content": "<|reserved_special_token_216|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128225": {
-      "content": "<|reserved_special_token_217|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128226": {
-      "content": "<|reserved_special_token_218|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128227": {
-      "content": "<|reserved_special_token_219|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128228": {
-      "content": "<|reserved_special_token_220|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128229": {
-      "content": "<|reserved_special_token_221|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128230": {
-      "content": "<|reserved_special_token_222|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128231": {
-      "content": "<|reserved_special_token_223|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128232": {
-      "content": "<|reserved_special_token_224|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128233": {
-      "content": "<|reserved_special_token_225|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128234": {
-      "content": "<|reserved_special_token_226|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128235": {
-      "content": "<|reserved_special_token_227|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128236": {
-      "content": "<|reserved_special_token_228|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128237": {
-      "content": "<|reserved_special_token_229|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128238": {
-      "content": "<|reserved_special_token_230|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128239": {
-      "content": "<|reserved_special_token_231|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128240": {
-      "content": "<|reserved_special_token_232|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128241": {
-      "content": "<|reserved_special_token_233|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128242": {
-      "content": "<|reserved_special_token_234|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128243": {
-      "content": "<|reserved_special_token_235|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128244": {
-      "content": "<|reserved_special_token_236|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128245": {
-      "content": "<|reserved_special_token_237|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128246": {
-      "content": "<|reserved_special_token_238|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128247": {
-      "content": "<|reserved_special_token_239|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128248": {
-      "content": "<|reserved_special_token_240|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128249": {
-      "content": "<|reserved_special_token_241|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128250": {
-      "content": "<|reserved_special_token_242|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128251": {
-      "content": "<|reserved_special_token_243|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128252": {
-      "content": "<|reserved_special_token_244|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128253": {
-      "content": "<|reserved_special_token_245|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128254": {
-      "content": "<|reserved_special_token_246|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128255": {
-      "content": "<|reserved_special_token_247|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 131072,
-  "pad_token": "<|end_of_text|>",
-  "padding_side": "left",
-  "tokenizer_class": "PreTrainedTokenizerFast"
-}

checkpoint-723/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:822e9ecd3c6cae4121c1ca48be3e43529504212f53af9850a5695094a2e7c768
-size 6200

config.json

@@ -31,7 +31,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.0",
-  "unsloth_version": "2024.8",
+  "unsloth_version": "2024.9",
   "use_cache": false,
   "vocab_size": 128256
 }