update sanity check

.gitattributes

@@ -107,3 +107,28 @@ modernbert-crux-researchy-pos_high.neg_quarter.b64_n512.1e-4.512/checkpoint-5000
 .git/lfs/objects/f0/69/f069e96d36df3a41005ecc6796d5ed8429bdffa25d9e9d133e6191cbf90b3de7 filter=lfs diff=lfs merge=lfs -text
 .git/lfs/objects/65/f2/65f21ce22f521a5d6f2e5456473256b7984e5c46122adc14ec92997d9ca30764 filter=lfs diff=lfs merge=lfs -text
 .git/lfs/objects/fd/d7/fdd7dd2e666a3126c4ed005d62b97fc63ca51fad19f7d480fb83d6eac7bfbbd0 filter=lfs diff=lfs merge=lfs -text
+modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-7500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-7500/model.safetensors filter=lfs diff=lfs merge=lfs -text
+modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/model.safetensors filter=lfs diff=lfs merge=lfs -text
+modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/model.safetensors filter=lfs diff=lfs merge=lfs -text
+modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-10000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-10000/model.safetensors filter=lfs diff=lfs merge=lfs -text
+modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-5000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-5000/model.safetensors filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/ed/b6/edb64b8cef0a3dfc25477198f91d7185d0407eac4e6e1ff0b31a40675c252898 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/35/96/359606993b57d8c0f8ae8f11c19d83fa5bd0004e9f16e205fb29e0c76ea064a0 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/aa/64/aa648019534a54da16e5df11fb28257398ac4ee886de2d2ef90e587b14a698f7 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/83/c9/83c938cffc4bd2b7aba816252155e7a073b49156075d36b5e9739c943826f1d7 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/83/be/83be8eb89686758cb1c6bb53429a3ff95a125cadcb5e094a8fc370c9402eef3e filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/d3/1c/d31c3ab1921e789d288696803d5d979c0569615bfc7fb11abd0061e241dab455 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/6a/ec/6aecd4553a1d58ca11b17030014708270f38be0c51df4dcd752bb2e3ddc8dd81 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/95/ab/95abf5b468df379a3475d3d44f54f063c491a08404f3ee22e428ad5a24c21300 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/1a/47/1a47b56f6d386053d17cfa1c908b16dcebcec2fa8dbf6ea679e0add277be30b3 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/b4/c7/b4c7bd3cbbb5534b9ae5fdc58267b3f7c3be44f0a133f6e0ec52249d605d0c0d filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/d4/8b/d48bd01953728d4eac963af505f6d4253af613156cb9e6895810b87c6d7b7524 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/4c/8c/4c8ced7bda17e694a323b59668f51b10dbaf3dd3577d631459b9cb69ef78adb7 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/be/4b/be4bee97568d7f026a805d2492cc6019c96edf730d7a4a52ad2fd4ef410975c6 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/56/03/560363724cc297d305f7f508a44b62eb6e5b3c38cc93a253e113fc093e5591d2 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/9c/20/9c2008894a8e5de34bd7573bfffe3d7e11c209ec55fd2a07336628edc06d6423 filter=lfs diff=lfs merge=lfs -text
+.git/lfs/objects/e0/30/e030bc5d9a25e135113d1a5b5746b18f93841dc8941845cf34057ac91120ef2f filter=lfs diff=lfs merge=lfs -text

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-10000/config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "bfloat16",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "transformers_version": "4.57.1",
+  "vocab_size": 50368
+}

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497c0250f011068b2187e2dbf2b9faa58acb723801636dc0ec52e7d5cd643a2a
+size 298041696

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb02d371523850c7952bcb32701ef852c8b2606387c3f23c86e3112453f2857
+size 596170443

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-10000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ee43c5708ab629e89ec026a42d31db0b1425d3f3ea3766e3d04dd6693801ec
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-10000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad91751348c745b01f71fdee312758089f1b054529b93bd0ca588dbf1aea5c58
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-10000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b59c265d32d1f647f3156e6f90ab7b87c65a70c219d8edcbfdbac6ae8e0074f8
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-10000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2db9bc1d3c24f68bfd231264e5caee728a20dce1258e71dbb27efa995be60a
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d02be6d8bda4ea9c67040ed89f878acdc986bd4df3fbc60440a9d3eacca02d63
+size 1465

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f79b1b43ade0180c39b8f014b5f2fe646f5535faf28e9f0584073d0ff47d33
+size 6161

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "bfloat16",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "transformers_version": "4.57.1",
+  "vocab_size": 50368
+}

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7064e8e8cf09c17a88bbf16e0793992c5fcdbeafb0fd63d51afff676488d62b
+size 298041696

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c55d74c76c1d6d6b77a663fb38015cefabc0f88cc98e4db401db93ffa2d19d
+size 596170443

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff16acfda6bbc5cf50b99aa265031ad0b4a77a4ea996fe62e798c2b245c7d95
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a794a90df9c5b0631ebe2e7987dab57982f6a583f0010d55836d1074ee1a40d
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6668393a5bc1b0de5d288b1691ef425f75f4c9702525195c76ff72f801ebb1
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24d02dcb6989a54f9b8b9339108aafa5df8c99759987bdb33d7a9ef54169400
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a752d3f24f72817376cd37ffda577fd802575961fb476ede3db67c3cc89113bf
+size 1465

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/trainer_state.json

@@ -0,0 +1,2109 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5100401606425704,
+  "eval_steps": 100,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010040160642570281,
+      "grad_norm": 17.75,
+      "learning_rate": 9e-07,
+      "loss": 5.9904,
+      "step": 10
+    },
+    {
+      "epoch": 0.020080321285140562,
+      "grad_norm": 24.5,
+      "learning_rate": 1.9e-06,
+      "loss": 6.0295,
+      "step": 20
+    },
+    {
+      "epoch": 0.030120481927710843,
+      "grad_norm": 14.8125,
+      "learning_rate": 2.9e-06,
+      "loss": 5.9579,
+      "step": 30
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "grad_norm": 16.75,
+      "learning_rate": 3.9e-06,
+      "loss": 5.978,
+      "step": 40
+    },
+    {
+      "epoch": 0.050200803212851405,
+      "grad_norm": 19.0,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 5.976,
+      "step": 50
+    },
+    {
+      "epoch": 0.060240963855421686,
+      "grad_norm": 21.25,
+      "learning_rate": 5.9e-06,
+      "loss": 6.0175,
+      "step": 60
+    },
+    {
+      "epoch": 0.07028112449799197,
+      "grad_norm": 15.375,
+      "learning_rate": 6.900000000000001e-06,
+      "loss": 5.9138,
+      "step": 70
+    },
+    {
+      "epoch": 0.08032128514056225,
+      "grad_norm": 29.375,
+      "learning_rate": 7.9e-06,
+      "loss": 5.8973,
+      "step": 80
+    },
+    {
+      "epoch": 0.09036144578313253,
+      "grad_norm": 19.625,
+      "learning_rate": 8.9e-06,
+      "loss": 5.8365,
+      "step": 90
+    },
+    {
+      "epoch": 0.10040160642570281,
+      "grad_norm": 16.375,
+      "learning_rate": 9.900000000000002e-06,
+      "loss": 5.809,
+      "step": 100
+    },
+    {
+      "epoch": 0.10040160642570281,
+      "eval/acc": 4.069767475128174,
+      "step": 100
+    },
+    {
+      "epoch": 0.10040160642570281,
+      "eval_loss": 5.030523300170898,
+      "eval_runtime": 2.7523,
+      "eval_samples_per_second": 15.623,
+      "eval_steps_per_second": 0.363,
+      "step": 100
+    },
+    {
+      "epoch": 0.11044176706827309,
+      "grad_norm": 20.375,
+      "learning_rate": 1.09e-05,
+      "loss": 5.655,
+      "step": 110
+    },
+    {
+      "epoch": 0.12048192771084337,
+      "grad_norm": 15.875,
+      "learning_rate": 1.19e-05,
+      "loss": 5.6139,
+      "step": 120
+    },
+    {
+      "epoch": 0.13052208835341367,
+      "grad_norm": 18.5,
+      "learning_rate": 1.29e-05,
+      "loss": 5.5668,
+      "step": 130
+    },
+    {
+      "epoch": 0.14056224899598393,
+      "grad_norm": 23.125,
+      "learning_rate": 1.3900000000000002e-05,
+      "loss": 5.4738,
+      "step": 140
+    },
+    {
+      "epoch": 0.15060240963855423,
+      "grad_norm": 17.25,
+      "learning_rate": 1.49e-05,
+      "loss": 5.3557,
+      "step": 150
+    },
+    {
+      "epoch": 0.1606425702811245,
+      "grad_norm": 18.625,
+      "learning_rate": 1.59e-05,
+      "loss": 5.1627,
+      "step": 160
+    },
+    {
+      "epoch": 0.1706827309236948,
+      "grad_norm": 25.0,
+      "learning_rate": 1.69e-05,
+      "loss": 4.995,
+      "step": 170
+    },
+    {
+      "epoch": 0.18072289156626506,
+      "grad_norm": 23.125,
+      "learning_rate": 1.79e-05,
+      "loss": 4.73,
+      "step": 180
+    },
+    {
+      "epoch": 0.19076305220883535,
+      "grad_norm": 23.875,
+      "learning_rate": 1.8900000000000002e-05,
+      "loss": 4.4144,
+      "step": 190
+    },
+    {
+      "epoch": 0.20080321285140562,
+      "grad_norm": 22.125,
+      "learning_rate": 1.9900000000000003e-05,
+      "loss": 4.1671,
+      "step": 200
+    },
+    {
+      "epoch": 0.20080321285140562,
+      "eval/acc": 11.627906799316406,
+      "step": 200
+    },
+    {
+      "epoch": 0.20080321285140562,
+      "eval_loss": 3.953169822692871,
+      "eval_runtime": 0.2214,
+      "eval_samples_per_second": 194.201,
+      "eval_steps_per_second": 4.516,
+      "step": 200
+    },
+    {
+      "epoch": 0.21084337349397592,
+      "grad_norm": 27.125,
+      "learning_rate": 2.09e-05,
+      "loss": 4.0765,
+      "step": 210
+    },
+    {
+      "epoch": 0.22088353413654618,
+      "grad_norm": 22.625,
+      "learning_rate": 2.19e-05,
+      "loss": 3.8343,
+      "step": 220
+    },
+    {
+      "epoch": 0.23092369477911648,
+      "grad_norm": 18.25,
+      "learning_rate": 2.29e-05,
+      "loss": 3.6944,
+      "step": 230
+    },
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 23.375,
+      "learning_rate": 2.39e-05,
+      "loss": 3.6236,
+      "step": 240
+    },
+    {
+      "epoch": 0.25100401606425704,
+      "grad_norm": 16.625,
+      "learning_rate": 2.4900000000000002e-05,
+      "loss": 3.5688,
+      "step": 250
+    },
+    {
+      "epoch": 0.26104417670682734,
+      "grad_norm": 25.125,
+      "learning_rate": 2.5900000000000003e-05,
+      "loss": 3.5022,
+      "step": 260
+    },
+    {
+      "epoch": 0.2710843373493976,
+      "grad_norm": 22.5,
+      "learning_rate": 2.6900000000000003e-05,
+      "loss": 3.7471,
+      "step": 270
+    },
+    {
+      "epoch": 0.28112449799196787,
+      "grad_norm": 15.5,
+      "learning_rate": 2.7900000000000004e-05,
+      "loss": 3.6346,
+      "step": 280
+    },
+    {
+      "epoch": 0.29116465863453816,
+      "grad_norm": 32.0,
+      "learning_rate": 2.8899999999999998e-05,
+      "loss": 3.3499,
+      "step": 290
+    },
+    {
+      "epoch": 0.30120481927710846,
+      "grad_norm": 17.125,
+      "learning_rate": 2.9900000000000002e-05,
+      "loss": 3.3495,
+      "step": 300
+    },
+    {
+      "epoch": 0.30120481927710846,
+      "eval/acc": 11.627906799316406,
+      "step": 300
+    },
+    {
+      "epoch": 0.30120481927710846,
+      "eval_loss": 3.4145164489746094,
+      "eval_runtime": 0.2134,
+      "eval_samples_per_second": 201.53,
+      "eval_steps_per_second": 4.687,
+      "step": 300
+    },
+    {
+      "epoch": 0.3112449799196787,
+      "grad_norm": 17.375,
+      "learning_rate": 3.09e-05,
+      "loss": 3.4094,
+      "step": 310
+    },
+    {
+      "epoch": 0.321285140562249,
+      "grad_norm": 19.0,
+      "learning_rate": 3.19e-05,
+      "loss": 3.317,
+      "step": 320
+    },
+    {
+      "epoch": 0.3313253012048193,
+      "grad_norm": 45.5,
+      "learning_rate": 3.29e-05,
+      "loss": 3.1893,
+      "step": 330
+    },
+    {
+      "epoch": 0.3413654618473896,
+      "grad_norm": 17.75,
+      "learning_rate": 3.3900000000000004e-05,
+      "loss": 3.3158,
+      "step": 340
+    },
+    {
+      "epoch": 0.3514056224899598,
+      "grad_norm": 27.25,
+      "learning_rate": 3.49e-05,
+      "loss": 3.2379,
+      "step": 350
+    },
+    {
+      "epoch": 0.3614457831325301,
+      "grad_norm": 18.0,
+      "learning_rate": 3.59e-05,
+      "loss": 3.1244,
+      "step": 360
+    },
+    {
+      "epoch": 0.3714859437751004,
+      "grad_norm": 39.0,
+      "learning_rate": 3.69e-05,
+      "loss": 3.2652,
+      "step": 370
+    },
+    {
+      "epoch": 0.3815261044176707,
+      "grad_norm": 21.625,
+      "learning_rate": 3.79e-05,
+      "loss": 3.1246,
+      "step": 380
+    },
+    {
+      "epoch": 0.39156626506024095,
+      "grad_norm": 17.0,
+      "learning_rate": 3.8900000000000004e-05,
+      "loss": 3.172,
+      "step": 390
+    },
+    {
+      "epoch": 0.40160642570281124,
+      "grad_norm": 17.375,
+      "learning_rate": 3.99e-05,
+      "loss": 3.0608,
+      "step": 400
+    },
+    {
+      "epoch": 0.40160642570281124,
+      "eval/acc": 20.930233001708984,
+      "step": 400
+    },
+    {
+      "epoch": 0.40160642570281124,
+      "eval_loss": 3.104855537414551,
+      "eval_runtime": 0.2197,
+      "eval_samples_per_second": 195.707,
+      "eval_steps_per_second": 4.551,
+      "step": 400
+    },
+    {
+      "epoch": 0.41164658634538154,
+      "grad_norm": 13.8125,
+      "learning_rate": 4.09e-05,
+      "loss": 2.9306,
+      "step": 410
+    },
+    {
+      "epoch": 0.42168674698795183,
+      "grad_norm": 20.0,
+      "learning_rate": 4.19e-05,
+      "loss": 3.0238,
+      "step": 420
+    },
+    {
+      "epoch": 0.43172690763052207,
+      "grad_norm": 14.4375,
+      "learning_rate": 4.29e-05,
+      "loss": 2.8947,
+      "step": 430
+    },
+    {
+      "epoch": 0.44176706827309237,
+      "grad_norm": 22.625,
+      "learning_rate": 4.39e-05,
+      "loss": 2.9078,
+      "step": 440
+    },
+    {
+      "epoch": 0.45180722891566266,
+      "grad_norm": 18.5,
+      "learning_rate": 4.49e-05,
+      "loss": 2.9072,
+      "step": 450
+    },
+    {
+      "epoch": 0.46184738955823296,
+      "grad_norm": 38.5,
+      "learning_rate": 4.5900000000000004e-05,
+      "loss": 2.9743,
+      "step": 460
+    },
+    {
+      "epoch": 0.4718875502008032,
+      "grad_norm": 17.375,
+      "learning_rate": 4.69e-05,
+      "loss": 2.8601,
+      "step": 470
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 19.625,
+      "learning_rate": 4.79e-05,
+      "loss": 2.8817,
+      "step": 480
+    },
+    {
+      "epoch": 0.4919678714859438,
+      "grad_norm": 34.75,
+      "learning_rate": 4.89e-05,
+      "loss": 3.0213,
+      "step": 490
+    },
+    {
+      "epoch": 0.5020080321285141,
+      "grad_norm": 33.5,
+      "learning_rate": 4.99e-05,
+      "loss": 2.8036,
+      "step": 500
+    },
+    {
+      "epoch": 0.5020080321285141,
+      "eval/acc": 23.837209701538086,
+      "step": 500
+    },
+    {
+      "epoch": 0.5020080321285141,
+      "eval_loss": 3.002290725708008,
+      "eval_runtime": 0.3957,
+      "eval_samples_per_second": 108.657,
+      "eval_steps_per_second": 2.527,
+      "step": 500
+    },
+    {
+      "epoch": 0.5120481927710844,
+      "grad_norm": 15.5625,
+      "learning_rate": 5.0900000000000004e-05,
+      "loss": 2.8824,
+      "step": 510
+    },
+    {
+      "epoch": 0.5220883534136547,
+      "grad_norm": 16.25,
+      "learning_rate": 5.19e-05,
+      "loss": 2.7604,
+      "step": 520
+    },
+    {
+      "epoch": 0.5321285140562249,
+      "grad_norm": 28.5,
+      "learning_rate": 5.2900000000000005e-05,
+      "loss": 2.7252,
+      "step": 530
+    },
+    {
+      "epoch": 0.5421686746987951,
+      "grad_norm": 17.125,
+      "learning_rate": 5.390000000000001e-05,
+      "loss": 2.9156,
+      "step": 540
+    },
+    {
+      "epoch": 0.5522088353413654,
+      "grad_norm": 22.5,
+      "learning_rate": 5.4900000000000006e-05,
+      "loss": 2.7753,
+      "step": 550
+    },
+    {
+      "epoch": 0.5622489959839357,
+      "grad_norm": 31.625,
+      "learning_rate": 5.590000000000001e-05,
+      "loss": 2.8055,
+      "step": 560
+    },
+    {
+      "epoch": 0.572289156626506,
+      "grad_norm": 14.125,
+      "learning_rate": 5.69e-05,
+      "loss": 2.7953,
+      "step": 570
+    },
+    {
+      "epoch": 0.5823293172690763,
+      "grad_norm": 22.5,
+      "learning_rate": 5.79e-05,
+      "loss": 2.7515,
+      "step": 580
+    },
+    {
+      "epoch": 0.5923694779116466,
+      "grad_norm": 29.625,
+      "learning_rate": 5.89e-05,
+      "loss": 2.6936,
+      "step": 590
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "grad_norm": 16.75,
+      "learning_rate": 5.99e-05,
+      "loss": 2.844,
+      "step": 600
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "eval/acc": 20.930233001708984,
+      "step": 600
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "eval_loss": 2.962186813354492,
+      "eval_runtime": 0.2212,
+      "eval_samples_per_second": 194.41,
+      "eval_steps_per_second": 4.521,
+      "step": 600
+    },
+    {
+      "epoch": 0.6124497991967871,
+      "grad_norm": 13.8125,
+      "learning_rate": 6.09e-05,
+      "loss": 2.673,
+      "step": 610
+    },
+    {
+      "epoch": 0.6224899598393574,
+      "grad_norm": 13.375,
+      "learning_rate": 6.19e-05,
+      "loss": 2.6404,
+      "step": 620
+    },
+    {
+      "epoch": 0.6325301204819277,
+      "grad_norm": 13.25,
+      "learning_rate": 6.29e-05,
+      "loss": 2.6487,
+      "step": 630
+    },
+    {
+      "epoch": 0.642570281124498,
+      "grad_norm": 14.875,
+      "learning_rate": 6.390000000000001e-05,
+      "loss": 2.809,
+      "step": 640
+    },
+    {
+      "epoch": 0.6526104417670683,
+      "grad_norm": 17.875,
+      "learning_rate": 6.49e-05,
+      "loss": 2.6443,
+      "step": 650
+    },
+    {
+      "epoch": 0.6626506024096386,
+      "grad_norm": 16.125,
+      "learning_rate": 6.59e-05,
+      "loss": 2.8367,
+      "step": 660
+    },
+    {
+      "epoch": 0.6726907630522089,
+      "grad_norm": 11.9375,
+      "learning_rate": 6.690000000000001e-05,
+      "loss": 2.563,
+      "step": 670
+    },
+    {
+      "epoch": 0.6827309236947792,
+      "grad_norm": 14.125,
+      "learning_rate": 6.790000000000001e-05,
+      "loss": 2.7697,
+      "step": 680
+    },
+    {
+      "epoch": 0.6927710843373494,
+      "grad_norm": 14.1875,
+      "learning_rate": 6.89e-05,
+      "loss": 2.6001,
+      "step": 690
+    },
+    {
+      "epoch": 0.7028112449799196,
+      "grad_norm": 15.75,
+      "learning_rate": 6.99e-05,
+      "loss": 2.5766,
+      "step": 700
+    },
+    {
+      "epoch": 0.7028112449799196,
+      "eval/acc": 27.9069766998291,
+      "step": 700
+    },
+    {
+      "epoch": 0.7028112449799196,
+      "eval_loss": 2.834120273590088,
+      "eval_runtime": 0.3085,
+      "eval_samples_per_second": 139.377,
+      "eval_steps_per_second": 3.241,
+      "step": 700
+    },
+    {
+      "epoch": 0.7128514056224899,
+      "grad_norm": 13.5625,
+      "learning_rate": 7.09e-05,
+      "loss": 2.5764,
+      "step": 710
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 11.875,
+      "learning_rate": 7.19e-05,
+      "loss": 2.6843,
+      "step": 720
+    },
+    {
+      "epoch": 0.7329317269076305,
+      "grad_norm": 11.0,
+      "learning_rate": 7.29e-05,
+      "loss": 2.4658,
+      "step": 730
+    },
+    {
+      "epoch": 0.7429718875502008,
+      "grad_norm": 15.25,
+      "learning_rate": 7.390000000000001e-05,
+      "loss": 2.5037,
+      "step": 740
+    },
+    {
+      "epoch": 0.7530120481927711,
+      "grad_norm": 14.125,
+      "learning_rate": 7.49e-05,
+      "loss": 2.454,
+      "step": 750
+    },
+    {
+      "epoch": 0.7630522088353414,
+      "grad_norm": 11.75,
+      "learning_rate": 7.59e-05,
+      "loss": 2.6892,
+      "step": 760
+    },
+    {
+      "epoch": 0.7730923694779116,
+      "grad_norm": 14.625,
+      "learning_rate": 7.69e-05,
+      "loss": 2.6287,
+      "step": 770
+    },
+    {
+      "epoch": 0.7831325301204819,
+      "grad_norm": 22.375,
+      "learning_rate": 7.790000000000001e-05,
+      "loss": 2.5941,
+      "step": 780
+    },
+    {
+      "epoch": 0.7931726907630522,
+      "grad_norm": 16.25,
+      "learning_rate": 7.890000000000001e-05,
+      "loss": 2.6715,
+      "step": 790
+    },
+    {
+      "epoch": 0.8032128514056225,
+      "grad_norm": 15.0625,
+      "learning_rate": 7.99e-05,
+      "loss": 2.4618,
+      "step": 800
+    },
+    {
+      "epoch": 0.8032128514056225,
+      "eval/acc": 27.9069766998291,
+      "step": 800
+    },
+    {
+      "epoch": 0.8032128514056225,
+      "eval_loss": 2.8701114654541016,
+      "eval_runtime": 0.2154,
+      "eval_samples_per_second": 199.62,
+      "eval_steps_per_second": 4.642,
+      "step": 800
+    },
+    {
+      "epoch": 0.8132530120481928,
+      "grad_norm": 19.625,
+      "learning_rate": 8.090000000000001e-05,
+      "loss": 2.5517,
+      "step": 810
+    },
+    {
+      "epoch": 0.8232931726907631,
+      "grad_norm": 12.25,
+      "learning_rate": 8.19e-05,
+      "loss": 2.634,
+      "step": 820
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 12.4375,
+      "learning_rate": 8.29e-05,
+      "loss": 2.6088,
+      "step": 830
+    },
+    {
+      "epoch": 0.8433734939759037,
+      "grad_norm": 11.3125,
+      "learning_rate": 8.39e-05,
+      "loss": 2.5604,
+      "step": 840
+    },
+    {
+      "epoch": 0.8534136546184738,
+      "grad_norm": 12.4375,
+      "learning_rate": 8.49e-05,
+      "loss": 2.5627,
+      "step": 850
+    },
+    {
+      "epoch": 0.8634538152610441,
+      "grad_norm": 14.0,
+      "learning_rate": 8.59e-05,
+      "loss": 2.5785,
+      "step": 860
+    },
+    {
+      "epoch": 0.8734939759036144,
+      "grad_norm": 13.9375,
+      "learning_rate": 8.69e-05,
+      "loss": 2.6124,
+      "step": 870
+    },
+    {
+      "epoch": 0.8835341365461847,
+      "grad_norm": 12.0625,
+      "learning_rate": 8.790000000000001e-05,
+      "loss": 2.3575,
+      "step": 880
+    },
+    {
+      "epoch": 0.893574297188755,
+      "grad_norm": 11.3125,
+      "learning_rate": 8.89e-05,
+      "loss": 2.5904,
+      "step": 890
+    },
+    {
+      "epoch": 0.9036144578313253,
+      "grad_norm": 13.375,
+      "learning_rate": 8.99e-05,
+      "loss": 2.4287,
+      "step": 900
+    },
+    {
+      "epoch": 0.9036144578313253,
+      "eval/acc": 25.581396102905273,
+      "step": 900
+    },
+    {
+      "epoch": 0.9036144578313253,
+      "eval_loss": 2.8205268383026123,
+      "eval_runtime": 0.2169,
+      "eval_samples_per_second": 198.229,
+      "eval_steps_per_second": 4.61,
+      "step": 900
+    },
+    {
+      "epoch": 0.9136546184738956,
+      "grad_norm": 13.5625,
+      "learning_rate": 9.090000000000001e-05,
+      "loss": 2.5028,
+      "step": 910
+    },
+    {
+      "epoch": 0.9236947791164659,
+      "grad_norm": 14.9375,
+      "learning_rate": 9.190000000000001e-05,
+      "loss": 2.3536,
+      "step": 920
+    },
+    {
+      "epoch": 0.9337349397590361,
+      "grad_norm": 13.1875,
+      "learning_rate": 9.290000000000001e-05,
+      "loss": 2.5969,
+      "step": 930
+    },
+    {
+      "epoch": 0.9437751004016064,
+      "grad_norm": 13.0625,
+      "learning_rate": 9.39e-05,
+      "loss": 2.5027,
+      "step": 940
+    },
+    {
+      "epoch": 0.9538152610441767,
+      "grad_norm": 11.875,
+      "learning_rate": 9.49e-05,
+      "loss": 2.4594,
+      "step": 950
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 10.6875,
+      "learning_rate": 9.59e-05,
+      "loss": 2.4078,
+      "step": 960
+    },
+    {
+      "epoch": 0.9738955823293173,
+      "grad_norm": 11.25,
+      "learning_rate": 9.69e-05,
+      "loss": 2.6305,
+      "step": 970
+    },
+    {
+      "epoch": 0.9839357429718876,
+      "grad_norm": 10.5,
+      "learning_rate": 9.790000000000001e-05,
+      "loss": 2.3873,
+      "step": 980
+    },
+    {
+      "epoch": 0.9939759036144579,
+      "grad_norm": 12.375,
+      "learning_rate": 9.89e-05,
+      "loss": 2.5356,
+      "step": 990
+    },
+    {
+      "epoch": 1.0040160642570282,
+      "grad_norm": 15.625,
+      "learning_rate": 9.99e-05,
+      "loss": 2.5491,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0040160642570282,
+      "eval/acc": 27.325580596923828,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0040160642570282,
+      "eval_loss": 2.8992457389831543,
+      "eval_runtime": 0.4661,
+      "eval_samples_per_second": 92.25,
+      "eval_steps_per_second": 2.145,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0140562248995983,
+      "grad_norm": 14.125,
+      "learning_rate": 9.99e-05,
+      "loss": 2.6677,
+      "step": 1010
+    },
+    {
+      "epoch": 1.0240963855421688,
+      "grad_norm": 11.0,
+      "learning_rate": 9.97888888888889e-05,
+      "loss": 2.3165,
+      "step": 1020
+    },
+    {
+      "epoch": 1.034136546184739,
+      "grad_norm": 11.9375,
+      "learning_rate": 9.967777777777779e-05,
+      "loss": 2.5861,
+      "step": 1030
+    },
+    {
+      "epoch": 1.0441767068273093,
+      "grad_norm": 10.75,
+      "learning_rate": 9.956666666666667e-05,
+      "loss": 2.5602,
+      "step": 1040
+    },
+    {
+      "epoch": 1.0542168674698795,
+      "grad_norm": 11.1875,
+      "learning_rate": 9.945555555555555e-05,
+      "loss": 2.4804,
+      "step": 1050
+    },
+    {
+      "epoch": 1.0642570281124497,
+      "grad_norm": 11.0625,
+      "learning_rate": 9.934444444444445e-05,
+      "loss": 2.5128,
+      "step": 1060
+    },
+    {
+      "epoch": 1.0742971887550201,
+      "grad_norm": 15.25,
+      "learning_rate": 9.923333333333334e-05,
+      "loss": 2.4529,
+      "step": 1070
+    },
+    {
+      "epoch": 1.0843373493975903,
+      "grad_norm": 20.75,
+      "learning_rate": 9.912222222222222e-05,
+      "loss": 2.3672,
+      "step": 1080
+    },
+    {
+      "epoch": 1.0943775100401607,
+      "grad_norm": 14.4375,
+      "learning_rate": 9.901111111111112e-05,
+      "loss": 2.4006,
+      "step": 1090
+    },
+    {
+      "epoch": 1.104417670682731,
+      "grad_norm": 11.125,
+      "learning_rate": 9.89e-05,
+      "loss": 2.4514,
+      "step": 1100
+    },
+    {
+      "epoch": 1.104417670682731,
+      "eval/acc": 23.837209701538086,
+      "step": 1100
+    },
+    {
+      "epoch": 1.104417670682731,
+      "eval_loss": 2.972341537475586,
+      "eval_runtime": 0.3123,
+      "eval_samples_per_second": 137.686,
+      "eval_steps_per_second": 3.202,
+      "step": 1100
+    },
+    {
+      "epoch": 1.1144578313253013,
+      "grad_norm": 15.1875,
+      "learning_rate": 9.87888888888889e-05,
+      "loss": 2.4682,
+      "step": 1110
+    },
+    {
+      "epoch": 1.1244979919678715,
+      "grad_norm": 10.3125,
+      "learning_rate": 9.867777777777777e-05,
+      "loss": 2.5043,
+      "step": 1120
+    },
+    {
+      "epoch": 1.1345381526104417,
+      "grad_norm": 19.375,
+      "learning_rate": 9.856666666666667e-05,
+      "loss": 2.4447,
+      "step": 1130
+    },
+    {
+      "epoch": 1.144578313253012,
+      "grad_norm": 11.9375,
+      "learning_rate": 9.845555555555556e-05,
+      "loss": 2.3247,
+      "step": 1140
+    },
+    {
+      "epoch": 1.1546184738955823,
+      "grad_norm": 10.6875,
+      "learning_rate": 9.834444444444446e-05,
+      "loss": 2.3527,
+      "step": 1150
+    },
+    {
+      "epoch": 1.1646586345381527,
+      "grad_norm": 9.875,
+      "learning_rate": 9.823333333333333e-05,
+      "loss": 2.3293,
+      "step": 1160
+    },
+    {
+      "epoch": 1.1746987951807228,
+      "grad_norm": 13.0625,
+      "learning_rate": 9.812222222222223e-05,
+      "loss": 2.3429,
+      "step": 1170
+    },
+    {
+      "epoch": 1.1847389558232932,
+      "grad_norm": 14.0625,
+      "learning_rate": 9.801111111111112e-05,
+      "loss": 2.453,
+      "step": 1180
+    },
+    {
+      "epoch": 1.1947791164658634,
+      "grad_norm": 13.9375,
+      "learning_rate": 9.790000000000001e-05,
+      "loss": 2.4068,
+      "step": 1190
+    },
+    {
+      "epoch": 1.2048192771084336,
+      "grad_norm": 10.4375,
+      "learning_rate": 9.778888888888889e-05,
+      "loss": 2.2791,
+      "step": 1200
+    },
+    {
+      "epoch": 1.2048192771084336,
+      "eval/acc": 27.325580596923828,
+      "step": 1200
+    },
+    {
+      "epoch": 1.2048192771084336,
+      "eval_loss": 2.985332727432251,
+      "eval_runtime": 0.2141,
+      "eval_samples_per_second": 200.861,
+      "eval_steps_per_second": 4.671,
+      "step": 1200
+    },
+    {
+      "epoch": 1.214859437751004,
+      "grad_norm": 17.875,
+      "learning_rate": 9.767777777777778e-05,
+      "loss": 2.4781,
+      "step": 1210
+    },
+    {
+      "epoch": 1.2248995983935742,
+      "grad_norm": 12.25,
+      "learning_rate": 9.756666666666668e-05,
+      "loss": 2.4539,
+      "step": 1220
+    },
+    {
+      "epoch": 1.2349397590361446,
+      "grad_norm": 18.75,
+      "learning_rate": 9.745555555555556e-05,
+      "loss": 2.4721,
+      "step": 1230
+    },
+    {
+      "epoch": 1.2449799196787148,
+      "grad_norm": 9.0,
+      "learning_rate": 9.734444444444444e-05,
+      "loss": 2.3875,
+      "step": 1240
+    },
+    {
+      "epoch": 1.2550200803212852,
+      "grad_norm": 12.9375,
+      "learning_rate": 9.723333333333334e-05,
+      "loss": 2.3652,
+      "step": 1250
+    },
+    {
+      "epoch": 1.2650602409638554,
+      "grad_norm": 9.5,
+      "learning_rate": 9.712222222222223e-05,
+      "loss": 2.4948,
+      "step": 1260
+    },
+    {
+      "epoch": 1.2751004016064256,
+      "grad_norm": 10.375,
+      "learning_rate": 9.701111111111111e-05,
+      "loss": 2.4305,
+      "step": 1270
+    },
+    {
+      "epoch": 1.285140562248996,
+      "grad_norm": 34.25,
+      "learning_rate": 9.69e-05,
+      "loss": 2.263,
+      "step": 1280
+    },
+    {
+      "epoch": 1.2951807228915664,
+      "grad_norm": 12.125,
+      "learning_rate": 9.67888888888889e-05,
+      "loss": 2.4056,
+      "step": 1290
+    },
+    {
+      "epoch": 1.3052208835341366,
+      "grad_norm": 12.5,
+      "learning_rate": 9.667777777777778e-05,
+      "loss": 2.2805,
+      "step": 1300
+    },
+    {
+      "epoch": 1.3052208835341366,
+      "eval/acc": 27.9069766998291,
+      "step": 1300
+    },
+    {
+      "epoch": 1.3052208835341366,
+      "eval_loss": 2.8425893783569336,
+      "eval_runtime": 0.222,
+      "eval_samples_per_second": 193.71,
+      "eval_steps_per_second": 4.505,
+      "step": 1300
+    },
+    {
+      "epoch": 1.3152610441767068,
+      "grad_norm": 14.125,
+      "learning_rate": 9.656666666666668e-05,
+      "loss": 2.3235,
+      "step": 1310
+    },
+    {
+      "epoch": 1.3253012048192772,
+      "grad_norm": 14.5,
+      "learning_rate": 9.645555555555556e-05,
+      "loss": 2.4175,
+      "step": 1320
+    },
+    {
+      "epoch": 1.3353413654618473,
+      "grad_norm": 21.5,
+      "learning_rate": 9.634444444444445e-05,
+      "loss": 2.2898,
+      "step": 1330
+    },
+    {
+      "epoch": 1.3453815261044177,
+      "grad_norm": 11.75,
+      "learning_rate": 9.623333333333335e-05,
+      "loss": 2.3425,
+      "step": 1340
+    },
+    {
+      "epoch": 1.355421686746988,
+      "grad_norm": 9.625,
+      "learning_rate": 9.612222222222223e-05,
+      "loss": 2.3347,
+      "step": 1350
+    },
+    {
+      "epoch": 1.3654618473895583,
+      "grad_norm": 9.9375,
+      "learning_rate": 9.601111111111112e-05,
+      "loss": 2.2746,
+      "step": 1360
+    },
+    {
+      "epoch": 1.3755020080321285,
+      "grad_norm": 10.75,
+      "learning_rate": 9.59e-05,
+      "loss": 2.3279,
+      "step": 1370
+    },
+    {
+      "epoch": 1.3855421686746987,
+      "grad_norm": 26.375,
+      "learning_rate": 9.57888888888889e-05,
+      "loss": 2.354,
+      "step": 1380
+    },
+    {
+      "epoch": 1.395582329317269,
+      "grad_norm": 10.4375,
+      "learning_rate": 9.567777777777778e-05,
+      "loss": 2.2012,
+      "step": 1390
+    },
+    {
+      "epoch": 1.4056224899598393,
+      "grad_norm": 14.75,
+      "learning_rate": 9.556666666666667e-05,
+      "loss": 2.1396,
+      "step": 1400
+    },
+    {
+      "epoch": 1.4056224899598393,
+      "eval/acc": 32.55813980102539,
+      "step": 1400
+    },
+    {
+      "epoch": 1.4056224899598393,
+      "eval_loss": 2.860133171081543,
+      "eval_runtime": 0.2527,
+      "eval_samples_per_second": 170.172,
+      "eval_steps_per_second": 3.957,
+      "step": 1400
+    },
+    {
+      "epoch": 1.4156626506024097,
+      "grad_norm": 9.3125,
+      "learning_rate": 9.545555555555557e-05,
+      "loss": 2.38,
+      "step": 1410
+    },
+    {
+      "epoch": 1.4257028112449799,
+      "grad_norm": 12.6875,
+      "learning_rate": 9.534444444444445e-05,
+      "loss": 2.2429,
+      "step": 1420
+    },
+    {
+      "epoch": 1.4357429718875503,
+      "grad_norm": 14.625,
+      "learning_rate": 9.523333333333334e-05,
+      "loss": 2.1962,
+      "step": 1430
+    },
+    {
+      "epoch": 1.4457831325301205,
+      "grad_norm": 14.6875,
+      "learning_rate": 9.512222222222222e-05,
+      "loss": 2.3026,
+      "step": 1440
+    },
+    {
+      "epoch": 1.4558232931726907,
+      "grad_norm": 10.625,
+      "learning_rate": 9.501111111111112e-05,
+      "loss": 2.3292,
+      "step": 1450
+    },
+    {
+      "epoch": 1.465863453815261,
+      "grad_norm": 13.9375,
+      "learning_rate": 9.49e-05,
+      "loss": 2.286,
+      "step": 1460
+    },
+    {
+      "epoch": 1.4759036144578312,
+      "grad_norm": 10.625,
+      "learning_rate": 9.478888888888889e-05,
+      "loss": 2.2671,
+      "step": 1470
+    },
+    {
+      "epoch": 1.4859437751004017,
+      "grad_norm": 10.4375,
+      "learning_rate": 9.467777777777779e-05,
+      "loss": 2.169,
+      "step": 1480
+    },
+    {
+      "epoch": 1.4959839357429718,
+      "grad_norm": 10.5625,
+      "learning_rate": 9.456666666666667e-05,
+      "loss": 2.3373,
+      "step": 1490
+    },
+    {
+      "epoch": 1.5060240963855422,
+      "grad_norm": 10.8125,
+      "learning_rate": 9.445555555555557e-05,
+      "loss": 2.2517,
+      "step": 1500
+    },
+    {
+      "epoch": 1.5060240963855422,
+      "eval/acc": 30.23255729675293,
+      "step": 1500
+    },
+    {
+      "epoch": 1.5060240963855422,
+      "eval_loss": 2.9082565307617188,
+      "eval_runtime": 0.2301,
+      "eval_samples_per_second": 186.895,
+      "eval_steps_per_second": 4.346,
+      "step": 1500
+    },
+    {
+      "epoch": 1.5160642570281124,
+      "grad_norm": 10.5,
+      "learning_rate": 9.434444444444444e-05,
+      "loss": 2.4585,
+      "step": 1510
+    },
+    {
+      "epoch": 1.5261044176706826,
+      "grad_norm": 9.6875,
+      "learning_rate": 9.423333333333334e-05,
+      "loss": 2.0853,
+      "step": 1520
+    },
+    {
+      "epoch": 1.536144578313253,
+      "grad_norm": 11.375,
+      "learning_rate": 9.412222222222222e-05,
+      "loss": 2.36,
+      "step": 1530
+    },
+    {
+      "epoch": 1.5461847389558234,
+      "grad_norm": 10.6875,
+      "learning_rate": 9.401111111111112e-05,
+      "loss": 2.3243,
+      "step": 1540
+    },
+    {
+      "epoch": 1.5562248995983936,
+      "grad_norm": 10.4375,
+      "learning_rate": 9.39e-05,
+      "loss": 2.1452,
+      "step": 1550
+    },
+    {
+      "epoch": 1.5662650602409638,
+      "grad_norm": 10.125,
+      "learning_rate": 9.378888888888889e-05,
+      "loss": 2.3594,
+      "step": 1560
+    },
+    {
+      "epoch": 1.5763052208835342,
+      "grad_norm": 13.6875,
+      "learning_rate": 9.367777777777779e-05,
+      "loss": 2.4113,
+      "step": 1570
+    },
+    {
+      "epoch": 1.5863453815261044,
+      "grad_norm": 11.9375,
+      "learning_rate": 9.356666666666667e-05,
+      "loss": 2.3425,
+      "step": 1580
+    },
+    {
+      "epoch": 1.5963855421686746,
+      "grad_norm": 10.375,
+      "learning_rate": 9.345555555555556e-05,
+      "loss": 2.1349,
+      "step": 1590
+    },
+    {
+      "epoch": 1.606425702811245,
+      "grad_norm": 25.375,
+      "learning_rate": 9.334444444444444e-05,
+      "loss": 2.2785,
+      "step": 1600
+    },
+    {
+      "epoch": 1.606425702811245,
+      "eval/acc": 30.23255729675293,
+      "step": 1600
+    },
+    {
+      "epoch": 1.606425702811245,
+      "eval_loss": 2.863983392715454,
+      "eval_runtime": 0.2338,
+      "eval_samples_per_second": 183.921,
+      "eval_steps_per_second": 4.277,
+      "step": 1600
+    },
+    {
+      "epoch": 1.6164658634538154,
+      "grad_norm": 12.3125,
+      "learning_rate": 9.323333333333334e-05,
+      "loss": 2.2134,
+      "step": 1610
+    },
+    {
+      "epoch": 1.6265060240963856,
+      "grad_norm": 10.25,
+      "learning_rate": 9.312222222222223e-05,
+      "loss": 2.1332,
+      "step": 1620
+    },
+    {
+      "epoch": 1.6365461847389557,
+      "grad_norm": 9.4375,
+      "learning_rate": 9.301111111111111e-05,
+      "loss": 2.43,
+      "step": 1630
+    },
+    {
+      "epoch": 1.6465863453815262,
+      "grad_norm": 11.4375,
+      "learning_rate": 9.290000000000001e-05,
+      "loss": 2.2511,
+      "step": 1640
+    },
+    {
+      "epoch": 1.6566265060240963,
+      "grad_norm": 9.5625,
+      "learning_rate": 9.278888888888889e-05,
+      "loss": 2.2298,
+      "step": 1650
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 11.25,
+      "learning_rate": 9.267777777777779e-05,
+      "loss": 2.3455,
+      "step": 1660
+    },
+    {
+      "epoch": 1.676706827309237,
+      "grad_norm": 8.3125,
+      "learning_rate": 9.256666666666666e-05,
+      "loss": 2.355,
+      "step": 1670
+    },
+    {
+      "epoch": 1.6867469879518073,
+      "grad_norm": 10.125,
+      "learning_rate": 9.245555555555556e-05,
+      "loss": 2.2654,
+      "step": 1680
+    },
+    {
+      "epoch": 1.6967871485943775,
+      "grad_norm": 9.25,
+      "learning_rate": 9.234444444444445e-05,
+      "loss": 2.2464,
+      "step": 1690
+    },
+    {
+      "epoch": 1.7068273092369477,
+      "grad_norm": 10.4375,
+      "learning_rate": 9.223333333333334e-05,
+      "loss": 2.1857,
+      "step": 1700
+    },
+    {
+      "epoch": 1.7068273092369477,
+      "eval/acc": 27.9069766998291,
+      "step": 1700
+    },
+    {
+      "epoch": 1.7068273092369477,
+      "eval_loss": 2.885897159576416,
+      "eval_runtime": 0.2125,
+      "eval_samples_per_second": 202.336,
+      "eval_steps_per_second": 4.705,
+      "step": 1700
+    },
+    {
+      "epoch": 1.716867469879518,
+      "grad_norm": 12.8125,
+      "learning_rate": 9.212222222222223e-05,
+      "loss": 2.3943,
+      "step": 1710
+    },
+    {
+      "epoch": 1.7269076305220885,
+      "grad_norm": 10.625,
+      "learning_rate": 9.201111111111111e-05,
+      "loss": 2.3082,
+      "step": 1720
+    },
+    {
+      "epoch": 1.7369477911646585,
+      "grad_norm": 9.5625,
+      "learning_rate": 9.190000000000001e-05,
+      "loss": 2.3202,
+      "step": 1730
+    },
+    {
+      "epoch": 1.7469879518072289,
+      "grad_norm": 9.125,
+      "learning_rate": 9.17888888888889e-05,
+      "loss": 2.3082,
+      "step": 1740
+    },
+    {
+      "epoch": 1.7570281124497993,
+      "grad_norm": 12.125,
+      "learning_rate": 9.167777777777778e-05,
+      "loss": 2.2875,
+      "step": 1750
+    },
+    {
+      "epoch": 1.7670682730923695,
+      "grad_norm": 10.8125,
+      "learning_rate": 9.156666666666667e-05,
+      "loss": 2.2007,
+      "step": 1760
+    },
+    {
+      "epoch": 1.7771084337349397,
+      "grad_norm": 8.8125,
+      "learning_rate": 9.145555555555556e-05,
+      "loss": 2.399,
+      "step": 1770
+    },
+    {
+      "epoch": 1.78714859437751,
+      "grad_norm": 18.25,
+      "learning_rate": 9.134444444444445e-05,
+      "loss": 2.3376,
+      "step": 1780
+    },
+    {
+      "epoch": 1.7971887550200805,
+      "grad_norm": 11.25,
+      "learning_rate": 9.123333333333333e-05,
+      "loss": 2.1304,
+      "step": 1790
+    },
+    {
+      "epoch": 1.8072289156626506,
+      "grad_norm": 10.375,
+      "learning_rate": 9.112222222222223e-05,
+      "loss": 2.3081,
+      "step": 1800
+    },
+    {
+      "epoch": 1.8072289156626506,
+      "eval/acc": 27.9069766998291,
+      "step": 1800
+    },
+    {
+      "epoch": 1.8072289156626506,
+      "eval_loss": 2.9158363342285156,
+      "eval_runtime": 0.2125,
+      "eval_samples_per_second": 202.377,
+      "eval_steps_per_second": 4.706,
+      "step": 1800
+    },
+    {
+      "epoch": 1.8172690763052208,
+      "grad_norm": 13.25,
+      "learning_rate": 9.101111111111112e-05,
+      "loss": 2.2629,
+      "step": 1810
+    },
+    {
+      "epoch": 1.8273092369477912,
+      "grad_norm": 9.125,
+      "learning_rate": 9.090000000000001e-05,
+      "loss": 2.1954,
+      "step": 1820
+    },
+    {
+      "epoch": 1.8373493975903614,
+      "grad_norm": 8.875,
+      "learning_rate": 9.078888888888889e-05,
+      "loss": 2.3442,
+      "step": 1830
+    },
+    {
+      "epoch": 1.8473895582329316,
+      "grad_norm": 9.6875,
+      "learning_rate": 9.067777777777778e-05,
+      "loss": 2.3602,
+      "step": 1840
+    },
+    {
+      "epoch": 1.857429718875502,
+      "grad_norm": 11.3125,
+      "learning_rate": 9.056666666666667e-05,
+      "loss": 2.3202,
+      "step": 1850
+    },
+    {
+      "epoch": 1.8674698795180724,
+      "grad_norm": 19.25,
+      "learning_rate": 9.045555555555557e-05,
+      "loss": 2.2292,
+      "step": 1860
+    },
+    {
+      "epoch": 1.8775100401606426,
+      "grad_norm": 9.5625,
+      "learning_rate": 9.034444444444445e-05,
+      "loss": 2.1523,
+      "step": 1870
+    },
+    {
+      "epoch": 1.8875502008032128,
+      "grad_norm": 15.9375,
+      "learning_rate": 9.023333333333334e-05,
+      "loss": 2.3017,
+      "step": 1880
+    },
+    {
+      "epoch": 1.8975903614457832,
+      "grad_norm": 12.625,
+      "learning_rate": 9.012222222222223e-05,
+      "loss": 2.2211,
+      "step": 1890
+    },
+    {
+      "epoch": 1.9076305220883534,
+      "grad_norm": 14.1875,
+      "learning_rate": 9.001111111111112e-05,
+      "loss": 2.3003,
+      "step": 1900
+    },
+    {
+      "epoch": 1.9076305220883534,
+      "eval/acc": 28.488372802734375,
+      "step": 1900
+    },
+    {
+      "epoch": 1.9076305220883534,
+      "eval_loss": 2.846564292907715,
+      "eval_runtime": 0.2624,
+      "eval_samples_per_second": 163.845,
+      "eval_steps_per_second": 3.81,
+      "step": 1900
+    },
+    {
+      "epoch": 1.9176706827309236,
+      "grad_norm": 9.875,
+      "learning_rate": 8.99e-05,
+      "loss": 2.2214,
+      "step": 1910
+    },
+    {
+      "epoch": 1.927710843373494,
+      "grad_norm": 9.375,
+      "learning_rate": 8.978888888888889e-05,
+      "loss": 2.182,
+      "step": 1920
+    },
+    {
+      "epoch": 1.9377510040160644,
+      "grad_norm": 13.875,
+      "learning_rate": 8.967777777777779e-05,
+      "loss": 2.2589,
+      "step": 1930
+    },
+    {
+      "epoch": 1.9477911646586346,
+      "grad_norm": 15.5,
+      "learning_rate": 8.956666666666667e-05,
+      "loss": 2.2425,
+      "step": 1940
+    },
+    {
+      "epoch": 1.9578313253012047,
+      "grad_norm": 11.125,
+      "learning_rate": 8.945555555555556e-05,
+      "loss": 2.2385,
+      "step": 1950
+    },
+    {
+      "epoch": 1.9678714859437751,
+      "grad_norm": 10.375,
+      "learning_rate": 8.934444444444445e-05,
+      "loss": 2.2774,
+      "step": 1960
+    },
+    {
+      "epoch": 1.9779116465863453,
+      "grad_norm": 10.125,
+      "learning_rate": 8.923333333333334e-05,
+      "loss": 2.1548,
+      "step": 1970
+    },
+    {
+      "epoch": 1.9879518072289155,
+      "grad_norm": 12.8125,
+      "learning_rate": 8.912222222222222e-05,
+      "loss": 2.2229,
+      "step": 1980
+    },
+    {
+      "epoch": 1.997991967871486,
+      "grad_norm": 12.1875,
+      "learning_rate": 8.901111111111111e-05,
+      "loss": 2.2029,
+      "step": 1990
+    },
+    {
+      "epoch": 2.0080321285140563,
+      "grad_norm": 14.875,
+      "learning_rate": 8.89e-05,
+      "loss": 2.1605,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0080321285140563,
+      "eval/acc": 37.20930099487305,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0080321285140563,
+      "eval_loss": 2.356771945953369,
+      "eval_runtime": 0.5428,
+      "eval_samples_per_second": 79.214,
+      "eval_steps_per_second": 1.842,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0180722891566263,
+      "grad_norm": 11.5,
+      "learning_rate": 8.878888888888889e-05,
+      "loss": 2.2117,
+      "step": 2010
+    },
+    {
+      "epoch": 2.0281124497991967,
+      "grad_norm": 10.25,
+      "learning_rate": 8.867777777777778e-05,
+      "loss": 2.304,
+      "step": 2020
+    },
+    {
+      "epoch": 2.038152610441767,
+      "grad_norm": 12.375,
+      "learning_rate": 8.856666666666667e-05,
+      "loss": 2.1229,
+      "step": 2030
+    },
+    {
+      "epoch": 2.0481927710843375,
+      "grad_norm": 10.875,
+      "learning_rate": 8.845555555555556e-05,
+      "loss": 2.2708,
+      "step": 2040
+    },
+    {
+      "epoch": 2.0582329317269075,
+      "grad_norm": 12.5625,
+      "learning_rate": 8.834444444444446e-05,
+      "loss": 2.2427,
+      "step": 2050
+    },
+    {
+      "epoch": 2.068273092369478,
+      "grad_norm": 9.6875,
+      "learning_rate": 8.823333333333334e-05,
+      "loss": 2.0905,
+      "step": 2060
+    },
+    {
+      "epoch": 2.0783132530120483,
+      "grad_norm": 10.4375,
+      "learning_rate": 8.812222222222223e-05,
+      "loss": 2.2414,
+      "step": 2070
+    },
+    {
+      "epoch": 2.0883534136546187,
+      "grad_norm": 10.9375,
+      "learning_rate": 8.801111111111111e-05,
+      "loss": 2.1266,
+      "step": 2080
+    },
+    {
+      "epoch": 2.0983935742971886,
+      "grad_norm": 9.75,
+      "learning_rate": 8.790000000000001e-05,
+      "loss": 2.2238,
+      "step": 2090
+    },
+    {
+      "epoch": 2.108433734939759,
+      "grad_norm": 9.0625,
+      "learning_rate": 8.77888888888889e-05,
+      "loss": 2.1869,
+      "step": 2100
+    },
+    {
+      "epoch": 2.108433734939759,
+      "eval/acc": 32.55813980102539,
+      "step": 2100
+    },
+    {
+      "epoch": 2.108433734939759,
+      "eval_loss": 2.387972831726074,
+      "eval_runtime": 0.2222,
+      "eval_samples_per_second": 193.548,
+      "eval_steps_per_second": 4.501,
+      "step": 2100
+    },
+    {
+      "epoch": 2.1184738955823295,
+      "grad_norm": 10.125,
+      "learning_rate": 8.767777777777778e-05,
+      "loss": 2.1548,
+      "step": 2110
+    },
+    {
+      "epoch": 2.1285140562248994,
+      "grad_norm": 11.75,
+      "learning_rate": 8.756666666666668e-05,
+      "loss": 2.2169,
+      "step": 2120
+    },
+    {
+      "epoch": 2.13855421686747,
+      "grad_norm": 10.1875,
+      "learning_rate": 8.745555555555556e-05,
+      "loss": 2.042,
+      "step": 2130
+    },
+    {
+      "epoch": 2.1485943775100402,
+      "grad_norm": 9.1875,
+      "learning_rate": 8.734444444444445e-05,
+      "loss": 2.386,
+      "step": 2140
+    },
+    {
+      "epoch": 2.1586345381526106,
+      "grad_norm": 13.6875,
+      "learning_rate": 8.723333333333333e-05,
+      "loss": 2.2033,
+      "step": 2150
+    },
+    {
+      "epoch": 2.1686746987951806,
+      "grad_norm": 10.25,
+      "learning_rate": 8.712222222222223e-05,
+      "loss": 2.2436,
+      "step": 2160
+    },
+    {
+      "epoch": 2.178714859437751,
+      "grad_norm": 9.875,
+      "learning_rate": 8.701111111111111e-05,
+      "loss": 2.2067,
+      "step": 2170
+    },
+    {
+      "epoch": 2.1887550200803214,
+      "grad_norm": 9.6875,
+      "learning_rate": 8.69e-05,
+      "loss": 2.1712,
+      "step": 2180
+    },
+    {
+      "epoch": 2.1987951807228914,
+      "grad_norm": 9.375,
+      "learning_rate": 8.67888888888889e-05,
+      "loss": 2.1688,
+      "step": 2190
+    },
+    {
+      "epoch": 2.208835341365462,
+      "grad_norm": 17.0,
+      "learning_rate": 8.667777777777778e-05,
+      "loss": 2.0712,
+      "step": 2200
+    },
+    {
+      "epoch": 2.208835341365462,
+      "eval/acc": 34.30232620239258,
+      "step": 2200
+    },
+    {
+      "epoch": 2.208835341365462,
+      "eval_loss": 2.371060848236084,
+      "eval_runtime": 0.2198,
+      "eval_samples_per_second": 195.604,
+      "eval_steps_per_second": 4.549,
+      "step": 2200
+    },
+    {
+      "epoch": 2.218875502008032,
+      "grad_norm": 8.9375,
+      "learning_rate": 8.656666666666668e-05,
+      "loss": 2.1793,
+      "step": 2210
+    },
+    {
+      "epoch": 2.2289156626506026,
+      "grad_norm": 9.625,
+      "learning_rate": 8.645555555555555e-05,
+      "loss": 2.2478,
+      "step": 2220
+    },
+    {
+      "epoch": 2.2389558232931726,
+      "grad_norm": 10.25,
+      "learning_rate": 8.634444444444445e-05,
+      "loss": 2.1995,
+      "step": 2230
+    },
+    {
+      "epoch": 2.248995983935743,
+      "grad_norm": 10.875,
+      "learning_rate": 8.623333333333333e-05,
+      "loss": 2.2004,
+      "step": 2240
+    },
+    {
+      "epoch": 2.2590361445783134,
+      "grad_norm": 17.75,
+      "learning_rate": 8.612222222222223e-05,
+      "loss": 2.1135,
+      "step": 2250
+    },
+    {
+      "epoch": 2.2690763052208833,
+      "grad_norm": 13.875,
+      "learning_rate": 8.601111111111112e-05,
+      "loss": 2.1026,
+      "step": 2260
+    },
+    {
+      "epoch": 2.2791164658634537,
+      "grad_norm": 10.625,
+      "learning_rate": 8.59e-05,
+      "loss": 2.1027,
+      "step": 2270
+    },
+    {
+      "epoch": 2.289156626506024,
+      "grad_norm": 13.3125,
+      "learning_rate": 8.57888888888889e-05,
+      "loss": 2.1481,
+      "step": 2280
+    },
+    {
+      "epoch": 2.2991967871485945,
+      "grad_norm": 10.125,
+      "learning_rate": 8.567777777777778e-05,
+      "loss": 2.2875,
+      "step": 2290
+    },
+    {
+      "epoch": 2.3092369477911645,
+      "grad_norm": 16.5,
+      "learning_rate": 8.556666666666667e-05,
+      "loss": 2.0918,
+      "step": 2300
+    },
+    {
+      "epoch": 2.3092369477911645,
+      "eval/acc": 32.55813980102539,
+      "step": 2300
+    },
+    {
+      "epoch": 2.3092369477911645,
+      "eval_loss": 2.3044633865356445,
+      "eval_runtime": 0.2272,
+      "eval_samples_per_second": 189.267,
+      "eval_steps_per_second": 4.402,
+      "step": 2300
+    },
+    {
+      "epoch": 2.319277108433735,
+      "grad_norm": 9.25,
+      "learning_rate": 8.545555555555555e-05,
+      "loss": 2.1223,
+      "step": 2310
+    },
+    {
+      "epoch": 2.3293172690763053,
+      "grad_norm": 10.0,
+      "learning_rate": 8.534444444444445e-05,
+      "loss": 2.2322,
+      "step": 2320
+    },
+    {
+      "epoch": 2.3393574297188753,
+      "grad_norm": 10.875,
+      "learning_rate": 8.523333333333334e-05,
+      "loss": 2.2498,
+      "step": 2330
+    },
+    {
+      "epoch": 2.3493975903614457,
+      "grad_norm": 11.0,
+      "learning_rate": 8.512222222222222e-05,
+      "loss": 2.1688,
+      "step": 2340
+    },
+    {
+      "epoch": 2.359437751004016,
+      "grad_norm": 10.1875,
+      "learning_rate": 8.501111111111112e-05,
+      "loss": 2.1724,
+      "step": 2350
+    },
+    {
+      "epoch": 2.3694779116465865,
+      "grad_norm": 10.125,
+      "learning_rate": 8.49e-05,
+      "loss": 2.18,
+      "step": 2360
+    },
+    {
+      "epoch": 2.3795180722891565,
+      "grad_norm": 10.25,
+      "learning_rate": 8.47888888888889e-05,
+      "loss": 2.3115,
+      "step": 2370
+    },
+    {
+      "epoch": 2.389558232931727,
+      "grad_norm": 11.4375,
+      "learning_rate": 8.467777777777777e-05,
+      "loss": 2.1828,
+      "step": 2380
+    },
+    {
+      "epoch": 2.3995983935742973,
+      "grad_norm": 9.625,
+      "learning_rate": 8.456666666666667e-05,
+      "loss": 2.1441,
+      "step": 2390
+    },
+    {
+      "epoch": 2.4096385542168672,
+      "grad_norm": 10.4375,
+      "learning_rate": 8.445555555555556e-05,
+      "loss": 2.1474,
+      "step": 2400
+    },
+    {
+      "epoch": 2.4096385542168672,
+      "eval/acc": 35.46511459350586,
+      "step": 2400
+    },
+    {
+      "epoch": 2.4096385542168672,
+      "eval_loss": 2.2873964309692383,
+      "eval_runtime": 0.2272,
+      "eval_samples_per_second": 189.265,
+      "eval_steps_per_second": 4.402,
+      "step": 2400
+    },
+    {
+      "epoch": 2.4196787148594376,
+      "grad_norm": 11.9375,
+      "learning_rate": 8.434444444444445e-05,
+      "loss": 2.0695,
+      "step": 2410
+    },
+    {
+      "epoch": 2.429718875502008,
+      "grad_norm": 12.5,
+      "learning_rate": 8.423333333333334e-05,
+      "loss": 2.1822,
+      "step": 2420
+    },
+    {
+      "epoch": 2.4397590361445785,
+      "grad_norm": 27.125,
+      "learning_rate": 8.412222222222222e-05,
+      "loss": 2.2321,
+      "step": 2430
+    },
+    {
+      "epoch": 2.4497991967871484,
+      "grad_norm": 9.75,
+      "learning_rate": 8.401111111111112e-05,
+      "loss": 2.2346,
+      "step": 2440
+    },
+    {
+      "epoch": 2.459839357429719,
+      "grad_norm": 8.1875,
+      "learning_rate": 8.39e-05,
+      "loss": 2.0637,
+      "step": 2450
+    },
+    {
+      "epoch": 2.4698795180722892,
+      "grad_norm": 9.125,
+      "learning_rate": 8.378888888888889e-05,
+      "loss": 2.165,
+      "step": 2460
+    },
+    {
+      "epoch": 2.479919678714859,
+      "grad_norm": 9.875,
+      "learning_rate": 8.367777777777778e-05,
+      "loss": 2.2242,
+      "step": 2470
+    },
+    {
+      "epoch": 2.4899598393574296,
+      "grad_norm": 12.3125,
+      "learning_rate": 8.356666666666667e-05,
+      "loss": 2.1483,
+      "step": 2480
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 13.375,
+      "learning_rate": 8.345555555555556e-05,
+      "loss": 2.3,
+      "step": 2490
+    },
+    {
+      "epoch": 2.5100401606425704,
+      "grad_norm": 9.0625,
+      "learning_rate": 8.334444444444444e-05,
+      "loss": 1.9901,
+      "step": 2500
+    },
+    {
+      "epoch": 2.5100401606425704,
+      "eval/acc": 31.976743698120117,
+      "step": 2500
+    },
+    {
+      "epoch": 2.5100401606425704,
+      "eval_loss": 2.2542452812194824,
+      "eval_runtime": 0.2214,
+      "eval_samples_per_second": 194.201,
+      "eval_steps_per_second": 4.516,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 11,
+  "save_steps": 2500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f79b1b43ade0180c39b8f014b5f2fe646f5535faf28e9f0584073d0ff47d33
+size 6161

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-5000/config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "bfloat16",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "transformers_version": "4.57.1",
+  "vocab_size": 50368
+}

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3074b3100a8b8cdcb062aeee3afe840bab8c3d3691adbaf10cca4af3a75d8abd
+size 298041696

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a607a99966f9cb4dedb5a53dc2fe355b442dc535af626ec61731c43ccb41cf
+size 596170443

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-5000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d29993cb39c04f6539a77ac9a44061d65e2acb0b63932182e8168d30dfd72f7
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-5000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97aa25b772a00496444be3ba7735d2335a1093f23149ed380416da0373e8ca95
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-5000/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92a8cc58a0188c52c524374cc3aafbaf9d42381ca9eecf468a7ccd750954830
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-5000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc2d0c96ee1ca5e6b4959540d3bfe108944107af9227be392417a025fda089cb
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506f6e39bd983d811639cf9d5aea75be4643e6c5adeffc1e40a2ab6e23817ea8
+size 1465

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f79b1b43ade0180c39b8f014b5f2fe646f5535faf28e9f0584073d0ff47d33
+size 6161

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-7500/config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "bfloat16",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "transformers_version": "4.57.1",
+  "vocab_size": 50368
+}

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-7500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d1cfaa7318833590d8d4dff43bafb2a03f524de00f97d730a0796b23f02ba6
+size 298041696

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-7500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439f17a3ad2b5d1ca518937675b56a6db768076e7597ba005700d9990b4aabe2
+size 596170443

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-7500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2caf86abc5cbfc36845c8a67c0441535c8680a4fa1a42756eb172962e102fc
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-7500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305a84128cb1786fd361d209de69142739bf3a10663f0129b61cf3cfe5a077e5
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-7500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c97d014be1644a0ea2a2dd06a1584267daa32699ef52ca01ebc9971d58480c43
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-7500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a038053cf1b7077a196c4fa557ec3b102cfc800180a18f22a542eecf41ba1bd5
+size 15429

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-7500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773947218d8d7737c8670043d737e80a30fe17375af8e46749692f7803f2df3b
+size 1465

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/checkpoint-7500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f79b1b43ade0180c39b8f014b5f2fe646f5535faf28e9f0584073d0ff47d33
+size 6161

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "bfloat16",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "transformers_version": "4.57.1",
+  "vocab_size": 50368
+}

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497c0250f011068b2187e2dbf2b9faa58acb723801636dc0ec52e7d5cd643a2a
+size 298041696

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/runs/Nov26_01-14-08_nid005065/events.out.tfevents.1764112711.nid005065.105463.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:259b498a5dbbde81284fb5b2f84c5498b0660ed89b6c6d298b7073271588e5ad
+size 254613

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/tokenizer_config.json

@@ -0,0 +1,945 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50282": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50283": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50284": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50285": {
+      "content": "[unused0]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "[unused1]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "[unused2]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "[unused3]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "[unused4]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "[unused5]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "[unused6]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "[unused7]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "[unused8]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "[unused9]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "[unused10]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": "[unused11]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "[unused12]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "[unused13]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": "[unused14]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": "[unused15]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": "[unused16]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "[unused17]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": "[unused18]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": "[unused19]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "[unused20]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": "[unused21]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "[unused22]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": "[unused23]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "[unused24]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": "[unused25]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "[unused26]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "[unused27]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": "[unused28]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": "[unused29]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "[unused30]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "[unused31]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "[unused32]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "[unused33]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": "[unused34]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": "[unused35]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "[unused36]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": "[unused37]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": "[unused38]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": "[unused39]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": "[unused40]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "[unused41]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": "[unused42]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "[unused43]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "[unused44]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": "[unused45]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": "[unused46]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": "[unused47]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "[unused48]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": "[unused49]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": "[unused50]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": "[unused51]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "[unused52]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "[unused53]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": "[unused54]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": "[unused55]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "[unused56]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": "[unused57]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": "[unused58]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": "[unused59]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "[unused60]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": "[unused61]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "[unused62]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "[unused63]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": "[unused64]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": "[unused65]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": "[unused66]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "[unused67]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": "[unused68]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": "[unused69]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": "[unused70]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "[unused71]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "[unused72]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": "[unused73]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": "[unused74]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": "[unused75]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": "[unused76]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": "[unused77]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": "[unused78]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50364": {
+      "content": "[unused79]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50365": {
+      "content": "[unused80]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50366": {
+      "content": "[unused81]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50367": {
+      "content": "[unused82]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

modernbert-crux-researchy-pos_zero.neg_high.b64_n512.1e-4.512/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f79b1b43ade0180c39b8f014b5f2fe646f5535faf28e9f0584073d0ff47d33
+size 6161