diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..e02373cbcfee06582e361869ad41fe06719c0cdd 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-10536/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-12292/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1756/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3512/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5268/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-7024/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-8780/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/checkpoint-10536/config.json b/checkpoint-10536/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f744ab25e17fedaffadd5fcb3ae10a7b9e4083bc
--- /dev/null
+++ b/checkpoint-10536/config.json
@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}
diff --git a/checkpoint-10536/model.safetensors b/checkpoint-10536/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f93bd96e79bc1d1ef4dc55d378ec6622bba98879
--- /dev/null
+++ b/checkpoint-10536/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6440a058003a17dd1e8e9f37290457a8d15df03bda5f80db000d0ec55c3b65a3
+size 1109863956
diff --git a/checkpoint-10536/optimizer.pt b/checkpoint-10536/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..963aef4c83eb8f5de1b53ff2cacef00677ec8ed6
--- /dev/null
+++ b/checkpoint-10536/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5aebcdf200787a3d36ad26e97baf2f95a1edbcaa27dfb7de4afd552f457a17d
+size 2219846202
diff --git a/checkpoint-10536/rng_state.pth b/checkpoint-10536/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..872c885addb0a6f48e4aac33446fb62fb68a98ce
--- /dev/null
+++ b/checkpoint-10536/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083825a219aea1d69cbec6e4b693fbcf2e11dad1312750efc78367126c76fbe2
+size 14244
diff --git a/checkpoint-10536/scaler.pt b/checkpoint-10536/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..be2d579c9eb1e892fbc0a2f6f7d7c95ae0e90e91
--- /dev/null
+++ b/checkpoint-10536/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d19f6e3641d81395be9b8e86101ef67c4f91a8f20888a2ad5331c197d7e6e6
+size 988
diff --git a/checkpoint-10536/scheduler.pt b/checkpoint-10536/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..8fee7f3d2cc2ea24e201571ceb19ccf1a2072e53
--- /dev/null
+++ b/checkpoint-10536/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4cd02bf0a083f5bb6fbdae03e00fa68b9cfc022b252c7ffd71dcb9e74d3421a
+size 1064
diff --git a/checkpoint-10536/special_tokens_map.json b/checkpoint-10536/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..d79c0fe029062eb03708803e72c3483296e2ea97
--- /dev/null
+++ b/checkpoint-10536/special_tokens_map.json
@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-10536/tokenizer.json b/checkpoint-10536/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..7126b1d228f6e5f725b6ee02a88b1118c725aeed
--- /dev/null
+++ b/checkpoint-10536/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734
diff --git a/checkpoint-10536/tokenizer_config.json b/checkpoint-10536/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d297107d53da62483767139822cf5ed3a6975e24
--- /dev/null
+++ b/checkpoint-10536/tokenizer_config.json
@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-10536/trainer_state.json b/checkpoint-10536/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..cd9919e6e7196ce2d3a6226b5522f8d04a5f19a8
--- /dev/null
+++ b/checkpoint-10536/trainer_state.json
@@ -0,0 +1,1570 @@
+{
+  "best_global_step": 10536,
+  "best_metric": 0.9557566616390145,
+  "best_model_checkpoint": "C:\\Users\\Shara\\projects\\models\\run_16-lr_2e-05-acc_1-wd_0.01-bs_8-ep_7\\checkpoint-10536",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 10536,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02847380410022779,
+      "grad_norm": 4.8302321434021,
+      "learning_rate": 1.992840872111943e-05,
+      "loss": 0.9994,
+      "step": 50
+    },
+    {
+      "epoch": 0.05694760820045558,
+      "grad_norm": 3.4978649616241455,
+      "learning_rate": 1.9847054995118778e-05,
+      "loss": 0.3939,
+      "step": 100
+    },
+    {
+      "epoch": 0.08542141230068337,
+      "grad_norm": 8.353672981262207,
+      "learning_rate": 1.9765701269118128e-05,
+      "loss": 0.2882,
+      "step": 150
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "grad_norm": 9.822871208190918,
+      "learning_rate": 1.9684347543117477e-05,
+      "loss": 0.1728,
+      "step": 200
+    },
+    {
+      "epoch": 0.14236902050113895,
+      "grad_norm": 3.1411221027374268,
+      "learning_rate": 1.9602993817116827e-05,
+      "loss": 0.1251,
+      "step": 250
+    },
+    {
+      "epoch": 0.17084282460136674,
+      "grad_norm": 8.493424415588379,
+      "learning_rate": 1.9521640091116173e-05,
+      "loss": 0.1405,
+      "step": 300
+    },
+    {
+      "epoch": 0.19931662870159453,
+      "grad_norm": 4.757007122039795,
+      "learning_rate": 1.9440286365115523e-05,
+      "loss": 0.1431,
+      "step": 350
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "grad_norm": 4.339049816131592,
+      "learning_rate": 1.9358932639114873e-05,
+      "loss": 0.0912,
+      "step": 400
+    },
+    {
+      "epoch": 0.25626423690205014,
+      "grad_norm": 14.540772438049316,
+      "learning_rate": 1.9277578913114222e-05,
+      "loss": 0.1048,
+      "step": 450
+    },
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 10.503073692321777,
+      "learning_rate": 1.9196225187113572e-05,
+      "loss": 0.1224,
+      "step": 500
+    },
+    {
+      "epoch": 0.3132118451025057,
+      "grad_norm": 2.738131284713745,
+      "learning_rate": 1.911487146111292e-05,
+      "loss": 0.1025,
+      "step": 550
+    },
+    {
+      "epoch": 0.3416856492027335,
+      "grad_norm": 6.681102752685547,
+      "learning_rate": 1.903351773511227e-05,
+      "loss": 0.0869,
+      "step": 600
+    },
+    {
+      "epoch": 0.3701594533029613,
+      "grad_norm": 1.4330339431762695,
+      "learning_rate": 1.895216400911162e-05,
+      "loss": 0.052,
+      "step": 650
+    },
+    {
+      "epoch": 0.39863325740318906,
+      "grad_norm": 2.581470012664795,
+      "learning_rate": 1.8870810283110967e-05,
+      "loss": 0.0808,
+      "step": 700
+    },
+    {
+      "epoch": 0.4271070615034169,
+      "grad_norm": 5.825100898742676,
+      "learning_rate": 1.8789456557110317e-05,
+      "loss": 0.0716,
+      "step": 750
+    },
+    {
+      "epoch": 0.45558086560364464,
+      "grad_norm": 1.74166738986969,
+      "learning_rate": 1.8708102831109666e-05,
+      "loss": 0.0806,
+      "step": 800
+    },
+    {
+      "epoch": 0.48405466970387245,
+      "grad_norm": 7.3097405433654785,
+      "learning_rate": 1.8626749105109016e-05,
+      "loss": 0.0666,
+      "step": 850
+    },
+    {
+      "epoch": 0.5125284738041003,
+      "grad_norm": 2.220766067504883,
+      "learning_rate": 1.8545395379108362e-05,
+      "loss": 0.0768,
+      "step": 900
+    },
+    {
+      "epoch": 0.541002277904328,
+      "grad_norm": 4.0566511154174805,
+      "learning_rate": 1.8464041653107715e-05,
+      "loss": 0.0707,
+      "step": 950
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.2833240330219269,
+      "learning_rate": 1.8382687927107065e-05,
+      "loss": 0.0858,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5979498861047836,
+      "grad_norm": 21.131481170654297,
+      "learning_rate": 1.8301334201106415e-05,
+      "loss": 0.0595,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6264236902050114,
+      "grad_norm": 27.655433654785156,
+      "learning_rate": 1.821998047510576e-05,
+      "loss": 0.0466,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6548974943052391,
+      "grad_norm": 3.4721717834472656,
+      "learning_rate": 1.813862674910511e-05,
+      "loss": 0.0776,
+      "step": 1150
+    },
+    {
+      "epoch": 0.683371298405467,
+      "grad_norm": 2.4811441898345947,
+      "learning_rate": 1.805727302310446e-05,
+      "loss": 0.0647,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7118451025056948,
+      "grad_norm": 6.169066429138184,
+      "learning_rate": 1.797591929710381e-05,
+      "loss": 0.0724,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7403189066059226,
+      "grad_norm": 8.984748840332031,
+      "learning_rate": 1.7894565571103156e-05,
+      "loss": 0.0838,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7687927107061503,
+      "grad_norm": 5.944505214691162,
+      "learning_rate": 1.7813211845102506e-05,
+      "loss": 0.0683,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7972665148063781,
+      "grad_norm": 0.28812381625175476,
+      "learning_rate": 1.7731858119101856e-05,
+      "loss": 0.0614,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8257403189066059,
+      "grad_norm": 6.176011085510254,
+      "learning_rate": 1.7650504393101205e-05,
+      "loss": 0.0615,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8542141230068337,
+      "grad_norm": 2.5244405269622803,
+      "learning_rate": 1.7569150667100555e-05,
+      "loss": 0.0714,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8826879271070615,
+      "grad_norm": 3.3508074283599854,
+      "learning_rate": 1.7487796941099904e-05,
+      "loss": 0.0563,
+      "step": 1550
+    },
+    {
+      "epoch": 0.9111617312072893,
+      "grad_norm": 9.980842590332031,
+      "learning_rate": 1.7406443215099254e-05,
+      "loss": 0.0647,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9396355353075171,
+      "grad_norm": 3.6959774494171143,
+      "learning_rate": 1.7325089489098604e-05,
+      "loss": 0.0682,
+      "step": 1650
+    },
+    {
+      "epoch": 0.9681093394077449,
+      "grad_norm": 0.626620888710022,
+      "learning_rate": 1.724373576309795e-05,
+      "loss": 0.0499,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9965831435079726,
+      "grad_norm": 7.145672798156738,
+      "learning_rate": 1.71623820370973e-05,
+      "loss": 0.0569,
+      "step": 1750
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9242246437552389,
+      "eval_loss": 0.05600914731621742,
+      "eval_precision": 0.9206746826987308,
+      "eval_recall": 0.927802086839448,
+      "eval_runtime": 3.7538,
+      "eval_samples_per_second": 865.798,
+      "eval_steps_per_second": 108.425,
+      "step": 1756
+    },
+    {
+      "epoch": 1.0250569476082005,
+      "grad_norm": 4.280463695526123,
+      "learning_rate": 1.708102831109665e-05,
+      "loss": 0.0673,
+      "step": 1800
+    },
+    {
+      "epoch": 1.0535307517084282,
+      "grad_norm": 0.06692535430192947,
+      "learning_rate": 1.6999674585096e-05,
+      "loss": 0.0403,
+      "step": 1850
+    },
+    {
+      "epoch": 1.082004555808656,
+      "grad_norm": 0.03789375349879265,
+      "learning_rate": 1.691832085909535e-05,
+      "loss": 0.0496,
+      "step": 1900
+    },
+    {
+      "epoch": 1.1104783599088839,
+      "grad_norm": 3.698348045349121,
+      "learning_rate": 1.6836967133094698e-05,
+      "loss": 0.0381,
+      "step": 1950
+    },
+    {
+      "epoch": 1.1389521640091116,
+      "grad_norm": 2.753032684326172,
+      "learning_rate": 1.6755613407094048e-05,
+      "loss": 0.0432,
+      "step": 2000
+    },
+    {
+      "epoch": 1.1674259681093395,
+      "grad_norm": 0.06336130946874619,
+      "learning_rate": 1.6674259681093398e-05,
+      "loss": 0.0482,
+      "step": 2050
+    },
+    {
+      "epoch": 1.1958997722095672,
+      "grad_norm": 3.9503254890441895,
+      "learning_rate": 1.6592905955092744e-05,
+      "loss": 0.0436,
+      "step": 2100
+    },
+    {
+      "epoch": 1.224373576309795,
+      "grad_norm": 0.08679741621017456,
+      "learning_rate": 1.6511552229092093e-05,
+      "loss": 0.0346,
+      "step": 2150
+    },
+    {
+      "epoch": 1.2528473804100229,
+      "grad_norm": 2.1995127201080322,
+      "learning_rate": 1.6430198503091443e-05,
+      "loss": 0.0312,
+      "step": 2200
+    },
+    {
+      "epoch": 1.2813211845102506,
+      "grad_norm": 5.7709808349609375,
+      "learning_rate": 1.634884477709079e-05,
+      "loss": 0.032,
+      "step": 2250
+    },
+    {
+      "epoch": 1.3097949886104785,
+      "grad_norm": 0.2031829059123993,
+      "learning_rate": 1.626749105109014e-05,
+      "loss": 0.053,
+      "step": 2300
+    },
+    {
+      "epoch": 1.3382687927107062,
+      "grad_norm": 4.292157173156738,
+      "learning_rate": 1.6186137325089492e-05,
+      "loss": 0.0413,
+      "step": 2350
+    },
+    {
+      "epoch": 1.366742596810934,
+      "grad_norm": 0.07821401953697205,
+      "learning_rate": 1.6104783599088842e-05,
+      "loss": 0.0304,
+      "step": 2400
+    },
+    {
+      "epoch": 1.3952164009111616,
+      "grad_norm": 0.5930206179618835,
+      "learning_rate": 1.6023429873088188e-05,
+      "loss": 0.0525,
+      "step": 2450
+    },
+    {
+      "epoch": 1.4236902050113895,
+      "grad_norm": 1.6114712953567505,
+      "learning_rate": 1.5942076147087538e-05,
+      "loss": 0.0391,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4521640091116172,
+      "grad_norm": 0.28632065653800964,
+      "learning_rate": 1.5860722421086887e-05,
+      "loss": 0.0491,
+      "step": 2550
+    },
+    {
+      "epoch": 1.4806378132118452,
+      "grad_norm": 1.0017669200897217,
+      "learning_rate": 1.5779368695086237e-05,
+      "loss": 0.0395,
+      "step": 2600
+    },
+    {
+      "epoch": 1.5091116173120729,
+      "grad_norm": 0.03409272059798241,
+      "learning_rate": 1.5698014969085583e-05,
+      "loss": 0.0399,
+      "step": 2650
+    },
+    {
+      "epoch": 1.5375854214123006,
+      "grad_norm": 3.5108702182769775,
+      "learning_rate": 1.5616661243084933e-05,
+      "loss": 0.0424,
+      "step": 2700
+    },
+    {
+      "epoch": 1.5660592255125285,
+      "grad_norm": 3.5875349044799805,
+      "learning_rate": 1.5535307517084283e-05,
+      "loss": 0.0497,
+      "step": 2750
+    },
+    {
+      "epoch": 1.5945330296127562,
+      "grad_norm": 0.10498251020908356,
+      "learning_rate": 1.5453953791083632e-05,
+      "loss": 0.0461,
+      "step": 2800
+    },
+    {
+      "epoch": 1.6230068337129842,
+      "grad_norm": 7.618963718414307,
+      "learning_rate": 1.5374227139602996e-05,
+      "loss": 0.0394,
+      "step": 2850
+    },
+    {
+      "epoch": 1.6514806378132119,
+      "grad_norm": 3.3920793533325195,
+      "learning_rate": 1.5292873413602346e-05,
+      "loss": 0.0339,
+      "step": 2900
+    },
+    {
+      "epoch": 1.6799544419134396,
+      "grad_norm": 0.04736129939556122,
+      "learning_rate": 1.5211519687601692e-05,
+      "loss": 0.0358,
+      "step": 2950
+    },
+    {
+      "epoch": 1.7084282460136673,
+      "grad_norm": 0.17463508248329163,
+      "learning_rate": 1.5130165961601042e-05,
+      "loss": 0.034,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7369020501138952,
+      "grad_norm": 0.058148205280303955,
+      "learning_rate": 1.5048812235600392e-05,
+      "loss": 0.0317,
+      "step": 3050
+    },
+    {
+      "epoch": 1.7653758542141231,
+      "grad_norm": 3.5262815952301025,
+      "learning_rate": 1.4967458509599741e-05,
+      "loss": 0.0477,
+      "step": 3100
+    },
+    {
+      "epoch": 1.7938496583143508,
+      "grad_norm": 2.971937894821167,
+      "learning_rate": 1.488610478359909e-05,
+      "loss": 0.0364,
+      "step": 3150
+    },
+    {
+      "epoch": 1.8223234624145785,
+      "grad_norm": 0.05181724950671196,
+      "learning_rate": 1.4804751057598439e-05,
+      "loss": 0.0394,
+      "step": 3200
+    },
+    {
+      "epoch": 1.8507972665148062,
+      "grad_norm": 0.2712370455265045,
+      "learning_rate": 1.4723397331597789e-05,
+      "loss": 0.0456,
+      "step": 3250
+    },
+    {
+      "epoch": 1.8792710706150342,
+      "grad_norm": 1.608622431755066,
+      "learning_rate": 1.4642043605597138e-05,
+      "loss": 0.05,
+      "step": 3300
+    },
+    {
+      "epoch": 1.907744874715262,
+      "grad_norm": 5.2423529624938965,
+      "learning_rate": 1.4560689879596486e-05,
+      "loss": 0.0371,
+      "step": 3350
+    },
+    {
+      "epoch": 1.9362186788154898,
+      "grad_norm": 0.04786211624741554,
+      "learning_rate": 1.4479336153595836e-05,
+      "loss": 0.0329,
+      "step": 3400
+    },
+    {
+      "epoch": 1.9646924829157175,
+      "grad_norm": 0.5264931917190552,
+      "learning_rate": 1.4397982427595185e-05,
+      "loss": 0.0379,
+      "step": 3450
+    },
+    {
+      "epoch": 1.9931662870159452,
+      "grad_norm": 0.236006498336792,
+      "learning_rate": 1.4316628701594535e-05,
+      "loss": 0.0253,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9406438631790744,
+      "eval_loss": 0.05223705992102623,
+      "eval_precision": 0.9371867691279653,
+      "eval_recall": 0.9441265567149109,
+      "eval_runtime": 3.7109,
+      "eval_samples_per_second": 875.791,
+      "eval_steps_per_second": 109.676,
+      "step": 3512
+    },
+    {
+      "epoch": 2.021640091116173,
+      "grad_norm": 4.225963115692139,
+      "learning_rate": 1.4235274975593883e-05,
+      "loss": 0.0373,
+      "step": 3550
+    },
+    {
+      "epoch": 2.050113895216401,
+      "grad_norm": 0.15388111770153046,
+      "learning_rate": 1.4153921249593233e-05,
+      "loss": 0.0258,
+      "step": 3600
+    },
+    {
+      "epoch": 2.078587699316629,
+      "grad_norm": 6.3911895751953125,
+      "learning_rate": 1.4072567523592582e-05,
+      "loss": 0.0217,
+      "step": 3650
+    },
+    {
+      "epoch": 2.1070615034168565,
+      "grad_norm": 0.03075530007481575,
+      "learning_rate": 1.3991213797591932e-05,
+      "loss": 0.019,
+      "step": 3700
+    },
+    {
+      "epoch": 2.135535307517084,
+      "grad_norm": 0.16612432897090912,
+      "learning_rate": 1.3909860071591278e-05,
+      "loss": 0.0175,
+      "step": 3750
+    },
+    {
+      "epoch": 2.164009111617312,
+      "grad_norm": 0.14543022215366364,
+      "learning_rate": 1.382850634559063e-05,
+      "loss": 0.0289,
+      "step": 3800
+    },
+    {
+      "epoch": 2.19248291571754,
+      "grad_norm": 2.9880359172821045,
+      "learning_rate": 1.374715261958998e-05,
+      "loss": 0.0208,
+      "step": 3850
+    },
+    {
+      "epoch": 2.2209567198177678,
+      "grad_norm": 9.878133773803711,
+      "learning_rate": 1.3665798893589329e-05,
+      "loss": 0.021,
+      "step": 3900
+    },
+    {
+      "epoch": 2.2494305239179955,
+      "grad_norm": 9.684176445007324,
+      "learning_rate": 1.3584445167588675e-05,
+      "loss": 0.0267,
+      "step": 3950
+    },
+    {
+      "epoch": 2.277904328018223,
+      "grad_norm": 33.15859603881836,
+      "learning_rate": 1.3503091441588025e-05,
+      "loss": 0.0295,
+      "step": 4000
+    },
+    {
+      "epoch": 2.306378132118451,
+      "grad_norm": 2.559544086456299,
+      "learning_rate": 1.3421737715587374e-05,
+      "loss": 0.0292,
+      "step": 4050
+    },
+    {
+      "epoch": 2.334851936218679,
+      "grad_norm": 0.07091552764177322,
+      "learning_rate": 1.3340383989586724e-05,
+      "loss": 0.0262,
+      "step": 4100
+    },
+    {
+      "epoch": 2.3633257403189067,
+      "grad_norm": 1.8119585514068604,
+      "learning_rate": 1.3259030263586072e-05,
+      "loss": 0.03,
+      "step": 4150
+    },
+    {
+      "epoch": 2.3917995444191344,
+      "grad_norm": 0.1476636379957199,
+      "learning_rate": 1.3177676537585422e-05,
+      "loss": 0.0196,
+      "step": 4200
+    },
+    {
+      "epoch": 2.420273348519362,
+      "grad_norm": 0.04482650011777878,
+      "learning_rate": 1.3096322811584771e-05,
+      "loss": 0.0263,
+      "step": 4250
+    },
+    {
+      "epoch": 2.44874715261959,
+      "grad_norm": 0.09201560169458389,
+      "learning_rate": 1.3014969085584121e-05,
+      "loss": 0.0172,
+      "step": 4300
+    },
+    {
+      "epoch": 2.477220956719818,
+      "grad_norm": 0.02215876244008541,
+      "learning_rate": 1.2933615359583469e-05,
+      "loss": 0.0149,
+      "step": 4350
+    },
+    {
+      "epoch": 2.5056947608200457,
+      "grad_norm": 0.6993932127952576,
+      "learning_rate": 1.2852261633582819e-05,
+      "loss": 0.0331,
+      "step": 4400
+    },
+    {
+      "epoch": 2.5341685649202734,
+      "grad_norm": 0.030453965067863464,
+      "learning_rate": 1.2770907907582168e-05,
+      "loss": 0.0307,
+      "step": 4450
+    },
+    {
+      "epoch": 2.562642369020501,
+      "grad_norm": 0.22211593389511108,
+      "learning_rate": 1.2689554181581518e-05,
+      "loss": 0.0183,
+      "step": 4500
+    },
+    {
+      "epoch": 2.591116173120729,
+      "grad_norm": 1.2842738628387451,
+      "learning_rate": 1.2608200455580866e-05,
+      "loss": 0.0226,
+      "step": 4550
+    },
+    {
+      "epoch": 2.619589977220957,
+      "grad_norm": 3.9048423767089844,
+      "learning_rate": 1.2526846729580216e-05,
+      "loss": 0.0239,
+      "step": 4600
+    },
+    {
+      "epoch": 2.6480637813211843,
+      "grad_norm": 0.9887784719467163,
+      "learning_rate": 1.2445493003579565e-05,
+      "loss": 0.0271,
+      "step": 4650
+    },
+    {
+      "epoch": 2.6765375854214124,
+      "grad_norm": 4.759728908538818,
+      "learning_rate": 1.2364139277578915e-05,
+      "loss": 0.0201,
+      "step": 4700
+    },
+    {
+      "epoch": 2.70501138952164,
+      "grad_norm": 0.2671191096305847,
+      "learning_rate": 1.2282785551578263e-05,
+      "loss": 0.0212,
+      "step": 4750
+    },
+    {
+      "epoch": 2.733485193621868,
+      "grad_norm": 0.036626849323511124,
+      "learning_rate": 1.2201431825577612e-05,
+      "loss": 0.0155,
+      "step": 4800
+    },
+    {
+      "epoch": 2.7619589977220955,
+      "grad_norm": 6.877408027648926,
+      "learning_rate": 1.2120078099576962e-05,
+      "loss": 0.0266,
+      "step": 4850
+    },
+    {
+      "epoch": 2.7904328018223232,
+      "grad_norm": 4.725896835327148,
+      "learning_rate": 1.2038724373576312e-05,
+      "loss": 0.0163,
+      "step": 4900
+    },
+    {
+      "epoch": 2.8189066059225514,
+      "grad_norm": 0.11965059489011765,
+      "learning_rate": 1.195737064757566e-05,
+      "loss": 0.0246,
+      "step": 4950
+    },
+    {
+      "epoch": 2.847380410022779,
+      "grad_norm": 0.6634079813957214,
+      "learning_rate": 1.187601692157501e-05,
+      "loss": 0.0304,
+      "step": 5000
+    },
+    {
+      "epoch": 2.875854214123007,
+      "grad_norm": 3.952694892883301,
+      "learning_rate": 1.1794663195574359e-05,
+      "loss": 0.0183,
+      "step": 5050
+    },
+    {
+      "epoch": 2.9043280182232345,
+      "grad_norm": 19.788942337036133,
+      "learning_rate": 1.1713309469573709e-05,
+      "loss": 0.0193,
+      "step": 5100
+    },
+    {
+      "epoch": 2.932801822323462,
+      "grad_norm": 4.989261627197266,
+      "learning_rate": 1.1631955743573055e-05,
+      "loss": 0.023,
+      "step": 5150
+    },
+    {
+      "epoch": 2.9612756264236904,
+      "grad_norm": 9.020853996276855,
+      "learning_rate": 1.1550602017572406e-05,
+      "loss": 0.0231,
+      "step": 5200
+    },
+    {
+      "epoch": 2.989749430523918,
+      "grad_norm": 0.9151140451431274,
+      "learning_rate": 1.1469248291571756e-05,
+      "loss": 0.0314,
+      "step": 5250
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.9470420646891236,
+      "eval_loss": 0.04870199039578438,
+      "eval_precision": 0.943090787716956,
+      "eval_recall": 0.9510265903736116,
+      "eval_runtime": 3.7494,
+      "eval_samples_per_second": 866.805,
+      "eval_steps_per_second": 108.551,
+      "step": 5268
+    },
+    {
+      "epoch": 3.0182232346241458,
+      "grad_norm": 8.62992000579834,
+      "learning_rate": 1.1387894565571106e-05,
+      "loss": 0.0194,
+      "step": 5300
+    },
+    {
+      "epoch": 3.0466970387243735,
+      "grad_norm": 0.5615554451942444,
+      "learning_rate": 1.1306540839570452e-05,
+      "loss": 0.0114,
+      "step": 5350
+    },
+    {
+      "epoch": 3.075170842824601,
+      "grad_norm": 2.5735936164855957,
+      "learning_rate": 1.1225187113569801e-05,
+      "loss": 0.0163,
+      "step": 5400
+    },
+    {
+      "epoch": 3.1036446469248293,
+      "grad_norm": 6.504094123840332,
+      "learning_rate": 1.1143833387569151e-05,
+      "loss": 0.0135,
+      "step": 5450
+    },
+    {
+      "epoch": 3.132118451025057,
+      "grad_norm": 14.477537155151367,
+      "learning_rate": 1.10624796615685e-05,
+      "loss": 0.0129,
+      "step": 5500
+    },
+    {
+      "epoch": 3.1605922551252847,
+      "grad_norm": 0.04929841682314873,
+      "learning_rate": 1.0981125935567849e-05,
+      "loss": 0.0263,
+      "step": 5550
+    },
+    {
+      "epoch": 3.1890660592255125,
+      "grad_norm": 0.08875144273042679,
+      "learning_rate": 1.0899772209567198e-05,
+      "loss": 0.0134,
+      "step": 5600
+    },
+    {
+      "epoch": 3.21753986332574,
+      "grad_norm": 0.6238455772399902,
+      "learning_rate": 1.0818418483566548e-05,
+      "loss": 0.0107,
+      "step": 5650
+    },
+    {
+      "epoch": 3.2460136674259683,
+      "grad_norm": 0.004948179703205824,
+      "learning_rate": 1.0737064757565898e-05,
+      "loss": 0.0167,
+      "step": 5700
+    },
+    {
+      "epoch": 3.274487471526196,
+      "grad_norm": 0.017031218856573105,
+      "learning_rate": 1.0655711031565246e-05,
+      "loss": 0.0085,
+      "step": 5750
+    },
+    {
+      "epoch": 3.3029612756264237,
+      "grad_norm": 2.9840469360351562,
+      "learning_rate": 1.0574357305564595e-05,
+      "loss": 0.0158,
+      "step": 5800
+    },
+    {
+      "epoch": 3.3314350797266514,
+      "grad_norm": 1.7477540969848633,
+      "learning_rate": 1.0493003579563945e-05,
+      "loss": 0.0157,
+      "step": 5850
+    },
+    {
+      "epoch": 3.359908883826879,
+      "grad_norm": 0.03963543102145195,
+      "learning_rate": 1.0411649853563295e-05,
+      "loss": 0.0201,
+      "step": 5900
+    },
+    {
+      "epoch": 3.3883826879271073,
+      "grad_norm": 0.16669808328151703,
+      "learning_rate": 1.0330296127562643e-05,
+      "loss": 0.0159,
+      "step": 5950
+    },
+    {
+      "epoch": 3.416856492027335,
+      "grad_norm": 0.01953568309545517,
+      "learning_rate": 1.0248942401561992e-05,
+      "loss": 0.0117,
+      "step": 6000
+    },
+    {
+      "epoch": 3.4453302961275627,
+      "grad_norm": 0.07708246260881424,
+      "learning_rate": 1.0167588675561342e-05,
+      "loss": 0.0117,
+      "step": 6050
+    },
+    {
+      "epoch": 3.4738041002277904,
+      "grad_norm": 2.423590898513794,
+      "learning_rate": 1.0086234949560691e-05,
+      "loss": 0.0111,
+      "step": 6100
+    },
+    {
+      "epoch": 3.502277904328018,
+      "grad_norm": 0.006337775848805904,
+      "learning_rate": 1.000488122356004e-05,
+      "loss": 0.0052,
+      "step": 6150
+    },
+    {
+      "epoch": 3.5307517084282463,
+      "grad_norm": 0.01373753696680069,
+      "learning_rate": 9.923527497559389e-06,
+      "loss": 0.009,
+      "step": 6200
+    },
+    {
+      "epoch": 3.559225512528474,
+      "grad_norm": 0.11260247975587845,
+      "learning_rate": 9.842173771558739e-06,
+      "loss": 0.0208,
+      "step": 6250
+    },
+    {
+      "epoch": 3.5876993166287017,
+      "grad_norm": 1.240822196006775,
+      "learning_rate": 9.760820045558087e-06,
+      "loss": 0.0157,
+      "step": 6300
+    },
+    {
+      "epoch": 3.6161731207289294,
+      "grad_norm": 0.05271293595433235,
+      "learning_rate": 9.679466319557436e-06,
+      "loss": 0.0175,
+      "step": 6350
+    },
+    {
+      "epoch": 3.644646924829157,
+      "grad_norm": 24.546663284301758,
+      "learning_rate": 9.598112593556786e-06,
+      "loss": 0.015,
+      "step": 6400
+    },
+    {
+      "epoch": 3.6731207289293852,
+      "grad_norm": 5.120173931121826,
+      "learning_rate": 9.516758867556136e-06,
+      "loss": 0.017,
+      "step": 6450
+    },
+    {
+      "epoch": 3.7015945330296125,
+      "grad_norm": 1.1922008991241455,
+      "learning_rate": 9.435405141555484e-06,
+      "loss": 0.0194,
+      "step": 6500
+    },
+    {
+      "epoch": 3.7300683371298406,
+      "grad_norm": 0.039439987391233444,
+      "learning_rate": 9.354051415554833e-06,
+      "loss": 0.0309,
+      "step": 6550
+    },
+    {
+      "epoch": 3.7585421412300684,
+      "grad_norm": 0.04055279493331909,
+      "learning_rate": 9.272697689554181e-06,
+      "loss": 0.0195,
+      "step": 6600
+    },
+    {
+      "epoch": 3.787015945330296,
+      "grad_norm": 0.5971085429191589,
+      "learning_rate": 9.191343963553533e-06,
+      "loss": 0.0156,
+      "step": 6650
+    },
+    {
+      "epoch": 3.8154897494305238,
+      "grad_norm": 0.2191866636276245,
+      "learning_rate": 9.10999023755288e-06,
+      "loss": 0.0174,
+      "step": 6700
+    },
+    {
+      "epoch": 3.8439635535307515,
+      "grad_norm": 0.033559828996658325,
+      "learning_rate": 9.02863651155223e-06,
+      "loss": 0.0149,
+      "step": 6750
+    },
+    {
+      "epoch": 3.8724373576309796,
+      "grad_norm": 3.7128634452819824,
+      "learning_rate": 8.947282785551578e-06,
+      "loss": 0.0221,
+      "step": 6800
+    },
+    {
+      "epoch": 3.9009111617312073,
+      "grad_norm": 0.08547580987215042,
+      "learning_rate": 8.865929059550928e-06,
+      "loss": 0.0153,
+      "step": 6850
+    },
+    {
+      "epoch": 3.929384965831435,
+      "grad_norm": 0.058124080300331116,
+      "learning_rate": 8.784575333550277e-06,
+      "loss": 0.0161,
+      "step": 6900
+    },
+    {
+      "epoch": 3.9578587699316627,
+      "grad_norm": 0.015579139813780785,
+      "learning_rate": 8.703221607549627e-06,
+      "loss": 0.011,
+      "step": 6950
+    },
+    {
+      "epoch": 3.9863325740318905,
+      "grad_norm": 0.12764935195446014,
+      "learning_rate": 8.621867881548975e-06,
+      "loss": 0.0166,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.9525329748802823,
+      "eval_loss": 0.04983380436897278,
+      "eval_precision": 0.9510149303808086,
+      "eval_recall": 0.9540558734432851,
+      "eval_runtime": 3.7495,
+      "eval_samples_per_second": 866.79,
+      "eval_steps_per_second": 108.549,
+      "step": 7024
+    },
+    {
+      "epoch": 4.014806378132119,
+      "grad_norm": 0.04521024227142334,
+      "learning_rate": 8.540514155548325e-06,
+      "loss": 0.0102,
+      "step": 7050
+    },
+    {
+      "epoch": 4.043280182232346,
+      "grad_norm": 0.015535669401288033,
+      "learning_rate": 8.459160429547674e-06,
+      "loss": 0.0068,
+      "step": 7100
+    },
+    {
+      "epoch": 4.071753986332574,
+      "grad_norm": 12.566010475158691,
+      "learning_rate": 8.377806703547024e-06,
+      "loss": 0.0151,
+      "step": 7150
+    },
+    {
+      "epoch": 4.100227790432802,
+      "grad_norm": 0.027761396020650864,
+      "learning_rate": 8.296452977546372e-06,
+      "loss": 0.0053,
+      "step": 7200
+    },
+    {
+      "epoch": 4.128701594533029,
+      "grad_norm": 1.8846938610076904,
+      "learning_rate": 8.215099251545722e-06,
+      "loss": 0.0077,
+      "step": 7250
+    },
+    {
+      "epoch": 4.157175398633258,
+      "grad_norm": 0.005013479385524988,
+      "learning_rate": 8.13374552554507e-06,
+      "loss": 0.0073,
+      "step": 7300
+    },
+    {
+      "epoch": 4.185649202733485,
+      "grad_norm": 0.32696235179901123,
+      "learning_rate": 8.052391799544421e-06,
+      "loss": 0.0092,
+      "step": 7350
+    },
+    {
+      "epoch": 4.214123006833713,
+      "grad_norm": 0.014357910491526127,
+      "learning_rate": 7.971038073543769e-06,
+      "loss": 0.0164,
+      "step": 7400
+    },
+    {
+      "epoch": 4.242596810933941,
+      "grad_norm": 0.010845329612493515,
+      "learning_rate": 7.889684347543118e-06,
+      "loss": 0.0123,
+      "step": 7450
+    },
+    {
+      "epoch": 4.271070615034168,
+      "grad_norm": 0.6969354748725891,
+      "learning_rate": 7.808330621542466e-06,
+      "loss": 0.0103,
+      "step": 7500
+    },
+    {
+      "epoch": 4.2995444191343966,
+      "grad_norm": 0.3575742840766907,
+      "learning_rate": 7.726976895541816e-06,
+      "loss": 0.0161,
+      "step": 7550
+    },
+    {
+      "epoch": 4.328018223234624,
+      "grad_norm": 0.008076228201389313,
+      "learning_rate": 7.645623169541166e-06,
+      "loss": 0.0122,
+      "step": 7600
+    },
+    {
+      "epoch": 4.356492027334852,
+      "grad_norm": 0.029101597145199776,
+      "learning_rate": 7.564269443540515e-06,
+      "loss": 0.0071,
+      "step": 7650
+    },
+    {
+      "epoch": 4.38496583143508,
+      "grad_norm": 0.06841142475605011,
+      "learning_rate": 7.482915717539863e-06,
+      "loss": 0.0091,
+      "step": 7700
+    },
+    {
+      "epoch": 4.413439635535307,
+      "grad_norm": 0.04133535176515579,
+      "learning_rate": 7.401561991539213e-06,
+      "loss": 0.0073,
+      "step": 7750
+    },
+    {
+      "epoch": 4.4419134396355355,
+      "grad_norm": 0.03571132943034172,
+      "learning_rate": 7.320208265538562e-06,
+      "loss": 0.0131,
+      "step": 7800
+    },
+    {
+      "epoch": 4.470387243735763,
+      "grad_norm": 2.8286924362182617,
+      "learning_rate": 7.2388545395379114e-06,
+      "loss": 0.0043,
+      "step": 7850
+    },
+    {
+      "epoch": 4.498861047835991,
+      "grad_norm": 1.3785158395767212,
+      "learning_rate": 7.15750081353726e-06,
+      "loss": 0.0103,
+      "step": 7900
+    },
+    {
+      "epoch": 4.527334851936219,
+      "grad_norm": 0.05979786813259125,
+      "learning_rate": 7.07614708753661e-06,
+      "loss": 0.006,
+      "step": 7950
+    },
+    {
+      "epoch": 4.555808656036446,
+      "grad_norm": 1.3434393405914307,
+      "learning_rate": 6.994793361535959e-06,
+      "loss": 0.0148,
+      "step": 8000
+    },
+    {
+      "epoch": 4.5842824601366745,
+      "grad_norm": 0.019605603069067,
+      "learning_rate": 6.913439635535308e-06,
+      "loss": 0.0068,
+      "step": 8050
+    },
+    {
+      "epoch": 4.612756264236902,
+      "grad_norm": 0.0028891051188111305,
+      "learning_rate": 6.832085909534657e-06,
+      "loss": 0.0075,
+      "step": 8100
+    },
+    {
+      "epoch": 4.64123006833713,
+      "grad_norm": 0.014856363646686077,
+      "learning_rate": 6.750732183534007e-06,
+      "loss": 0.0073,
+      "step": 8150
+    },
+    {
+      "epoch": 4.669703872437358,
+      "grad_norm": 0.0037149768322706223,
+      "learning_rate": 6.669378457533356e-06,
+      "loss": 0.0066,
+      "step": 8200
+    },
+    {
+      "epoch": 4.698177676537585,
+      "grad_norm": 0.008534993045032024,
+      "learning_rate": 6.588024731532705e-06,
+      "loss": 0.0121,
+      "step": 8250
+    },
+    {
+      "epoch": 4.7266514806378135,
+      "grad_norm": 0.013920712284743786,
+      "learning_rate": 6.506671005532054e-06,
+      "loss": 0.013,
+      "step": 8300
+    },
+    {
+      "epoch": 4.755125284738041,
+      "grad_norm": 0.10121840238571167,
+      "learning_rate": 6.425317279531404e-06,
+      "loss": 0.0087,
+      "step": 8350
+    },
+    {
+      "epoch": 4.783599088838269,
+      "grad_norm": 0.07937771081924438,
+      "learning_rate": 6.343963553530752e-06,
+      "loss": 0.0086,
+      "step": 8400
+    },
+    {
+      "epoch": 4.812072892938497,
+      "grad_norm": 0.07674901187419891,
+      "learning_rate": 6.262609827530101e-06,
+      "loss": 0.0052,
+      "step": 8450
+    },
+    {
+      "epoch": 4.840546697038724,
+      "grad_norm": 0.06683178246021271,
+      "learning_rate": 6.18125610152945e-06,
+      "loss": 0.015,
+      "step": 8500
+    },
+    {
+      "epoch": 4.8690205011389525,
+      "grad_norm": 0.08861212432384491,
+      "learning_rate": 6.0999023755288e-06,
+      "loss": 0.0109,
+      "step": 8550
+    },
+    {
+      "epoch": 4.89749430523918,
+      "grad_norm": 0.006198623217642307,
+      "learning_rate": 6.018548649528149e-06,
+      "loss": 0.0181,
+      "step": 8600
+    },
+    {
+      "epoch": 4.925968109339408,
+      "grad_norm": 0.009029284119606018,
+      "learning_rate": 5.937194923527498e-06,
+      "loss": 0.0043,
+      "step": 8650
+    },
+    {
+      "epoch": 4.954441913439636,
+      "grad_norm": 1.1225602626800537,
+      "learning_rate": 5.855841197526847e-06,
+      "loss": 0.0121,
+      "step": 8700
+    },
+    {
+      "epoch": 4.982915717539863,
+      "grad_norm": 0.01218325924128294,
+      "learning_rate": 5.774487471526197e-06,
+      "loss": 0.0115,
+      "step": 8750
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.9533444816053511,
+      "eval_loss": 0.04722925275564194,
+      "eval_precision": 0.9473246925889,
+      "eval_recall": 0.9594412655671491,
+      "eval_runtime": 3.7358,
+      "eval_samples_per_second": 869.968,
+      "eval_steps_per_second": 108.947,
+      "step": 8780
+    },
+    {
+      "epoch": 5.011389521640091,
+      "grad_norm": 0.8161097764968872,
+      "learning_rate": 5.6931337455255455e-06,
+      "loss": 0.0127,
+      "step": 8800
+    },
+    {
+      "epoch": 5.039863325740319,
+      "grad_norm": 0.048089127987623215,
+      "learning_rate": 5.611780019524895e-06,
+      "loss": 0.0116,
+      "step": 8850
+    },
+    {
+      "epoch": 5.068337129840547,
+      "grad_norm": 1.7576072216033936,
+      "learning_rate": 5.530426293524244e-06,
+      "loss": 0.0093,
+      "step": 8900
+    },
+    {
+      "epoch": 5.096810933940774,
+      "grad_norm": 0.07270015776157379,
+      "learning_rate": 5.449072567523594e-06,
+      "loss": 0.0043,
+      "step": 8950
+    },
+    {
+      "epoch": 5.125284738041002,
+      "grad_norm": 0.2580782175064087,
+      "learning_rate": 5.367718841522942e-06,
+      "loss": 0.0058,
+      "step": 9000
+    },
+    {
+      "epoch": 5.15375854214123,
+      "grad_norm": 0.12649740278720856,
+      "learning_rate": 5.286365115522292e-06,
+      "loss": 0.0033,
+      "step": 9050
+    },
+    {
+      "epoch": 5.182232346241458,
+      "grad_norm": 0.06850716471672058,
+      "learning_rate": 5.20501138952164e-06,
+      "loss": 0.003,
+      "step": 9100
+    },
+    {
+      "epoch": 5.210706150341686,
+      "grad_norm": 0.01197959017008543,
+      "learning_rate": 5.12365766352099e-06,
+      "loss": 0.0029,
+      "step": 9150
+    },
+    {
+      "epoch": 5.239179954441913,
+      "grad_norm": 0.10818086564540863,
+      "learning_rate": 5.0423039375203385e-06,
+      "loss": 0.0025,
+      "step": 9200
+    },
+    {
+      "epoch": 5.267653758542141,
+      "grad_norm": 0.035460665822029114,
+      "learning_rate": 4.960950211519688e-06,
+      "loss": 0.0047,
+      "step": 9250
+    },
+    {
+      "epoch": 5.296127562642369,
+      "grad_norm": 4.532562255859375,
+      "learning_rate": 4.879596485519037e-06,
+      "loss": 0.0086,
+      "step": 9300
+    },
+    {
+      "epoch": 5.324601366742597,
+      "grad_norm": 0.013236219063401222,
+      "learning_rate": 4.7982427595183866e-06,
+      "loss": 0.0027,
+      "step": 9350
+    },
+    {
+      "epoch": 5.353075170842825,
+      "grad_norm": 0.018059909343719482,
+      "learning_rate": 4.716889033517735e-06,
+      "loss": 0.0065,
+      "step": 9400
+    },
+    {
+      "epoch": 5.381548974943052,
+      "grad_norm": 0.019096272066235542,
+      "learning_rate": 4.635535307517084e-06,
+      "loss": 0.0053,
+      "step": 9450
+    },
+    {
+      "epoch": 5.41002277904328,
+      "grad_norm": 0.10389436781406403,
+      "learning_rate": 4.554181581516434e-06,
+      "loss": 0.0029,
+      "step": 9500
+    },
+    {
+      "epoch": 5.438496583143508,
+      "grad_norm": 0.0029252381063997746,
+      "learning_rate": 4.472827855515783e-06,
+      "loss": 0.0045,
+      "step": 9550
+    },
+    {
+      "epoch": 5.466970387243736,
+      "grad_norm": 0.004542892333120108,
+      "learning_rate": 4.391474129515132e-06,
+      "loss": 0.0102,
+      "step": 9600
+    },
+    {
+      "epoch": 5.495444191343964,
+      "grad_norm": 0.130916565656662,
+      "learning_rate": 4.310120403514481e-06,
+      "loss": 0.0064,
+      "step": 9650
+    },
+    {
+      "epoch": 5.523917995444191,
+      "grad_norm": 0.008013393729925156,
+      "learning_rate": 4.22876667751383e-06,
+      "loss": 0.005,
+      "step": 9700
+    },
+    {
+      "epoch": 5.552391799544419,
+      "grad_norm": 0.012782514095306396,
+      "learning_rate": 4.1474129515131795e-06,
+      "loss": 0.0122,
+      "step": 9750
+    },
+    {
+      "epoch": 5.5808656036446465,
+      "grad_norm": 0.9617053866386414,
+      "learning_rate": 4.066059225512528e-06,
+      "loss": 0.0063,
+      "step": 9800
+    },
+    {
+      "epoch": 5.609339407744875,
+      "grad_norm": 0.014953136444091797,
+      "learning_rate": 3.984705499511878e-06,
+      "loss": 0.0046,
+      "step": 9850
+    },
+    {
+      "epoch": 5.637813211845103,
+      "grad_norm": 1.0275633335113525,
+      "learning_rate": 3.903351773511227e-06,
+      "loss": 0.0075,
+      "step": 9900
+    },
+    {
+      "epoch": 5.66628701594533,
+      "grad_norm": 0.007999264635145664,
+      "learning_rate": 3.8219980475105764e-06,
+      "loss": 0.0031,
+      "step": 9950
+    },
+    {
+      "epoch": 5.694760820045558,
+      "grad_norm": 0.008241960778832436,
+      "learning_rate": 3.7406443215099252e-06,
+      "loss": 0.0065,
+      "step": 10000
+    },
+    {
+      "epoch": 5.723234624145785,
+      "grad_norm": 2.578386068344116,
+      "learning_rate": 3.6592905955092745e-06,
+      "loss": 0.0057,
+      "step": 10050
+    },
+    {
+      "epoch": 5.751708428246014,
+      "grad_norm": 2.8855443000793457,
+      "learning_rate": 3.5779368695086237e-06,
+      "loss": 0.0038,
+      "step": 10100
+    },
+    {
+      "epoch": 5.780182232346242,
+      "grad_norm": 0.016262667253613472,
+      "learning_rate": 3.496583143507973e-06,
+      "loss": 0.0128,
+      "step": 10150
+    },
+    {
+      "epoch": 5.808656036446469,
+      "grad_norm": 0.045168060809373856,
+      "learning_rate": 3.415229417507322e-06,
+      "loss": 0.0036,
+      "step": 10200
+    },
+    {
+      "epoch": 5.837129840546697,
+      "grad_norm": 0.1192622259259224,
+      "learning_rate": 3.3355027660266842e-06,
+      "loss": 0.0111,
+      "step": 10250
+    },
+    {
+      "epoch": 5.865603644646924,
+      "grad_norm": 0.08544190227985382,
+      "learning_rate": 3.2541490400260335e-06,
+      "loss": 0.0051,
+      "step": 10300
+    },
+    {
+      "epoch": 5.894077448747153,
+      "grad_norm": 3.493161678314209,
+      "learning_rate": 3.1727953140253827e-06,
+      "loss": 0.0054,
+      "step": 10350
+    },
+    {
+      "epoch": 5.922551252847381,
+      "grad_norm": 0.022789066657423973,
+      "learning_rate": 3.0914415880247315e-06,
+      "loss": 0.0033,
+      "step": 10400
+    },
+    {
+      "epoch": 5.951025056947608,
+      "grad_norm": 12.131625175476074,
+      "learning_rate": 3.0100878620240807e-06,
+      "loss": 0.0023,
+      "step": 10450
+    },
+    {
+      "epoch": 5.979498861047836,
+      "grad_norm": 0.03329641371965408,
+      "learning_rate": 2.92873413602343e-06,
+      "loss": 0.0058,
+      "step": 10500
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.9557566616390145,
+      "eval_loss": 0.05410688370466232,
+      "eval_precision": 0.9517690253671562,
+      "eval_recall": 0.9597778525748906,
+      "eval_runtime": 3.6572,
+      "eval_samples_per_second": 888.662,
+      "eval_steps_per_second": 111.288,
+      "step": 10536
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 12292,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2072296586745846.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-10536/training_args.bin b/checkpoint-10536/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5883d1e2ddb42c11dd6ad1fddc79d9ffe7a246f3
--- /dev/null
+++ b/checkpoint-10536/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e08f60c5260f286c88c6054e532ee0950cb5316081a3a51d07b57f6a266f71
+size 5368
diff --git a/checkpoint-12292/config.json b/checkpoint-12292/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f744ab25e17fedaffadd5fcb3ae10a7b9e4083bc
--- /dev/null
+++ b/checkpoint-12292/config.json
@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}
diff --git a/checkpoint-12292/model.safetensors b/checkpoint-12292/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9138b6f1834a9abd518339bbab61b5b8559c4607
--- /dev/null
+++ b/checkpoint-12292/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3aa01fa5d49602728eca2190fb610b286d4348c8e470e053f83959dfd91049
+size 1109863956
diff --git a/checkpoint-12292/optimizer.pt b/checkpoint-12292/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..195893e68ae6f690522c151b09ff1d4bc11b6dfa
--- /dev/null
+++ b/checkpoint-12292/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328145ba117ef4052abfc88cfdc5ed7cb46c854f712b8a60beb15d66d8807396
+size 2219846202
diff --git a/checkpoint-12292/rng_state.pth b/checkpoint-12292/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..576367a78de95019cc8bd62176d2c16e3a27f30e
--- /dev/null
+++ b/checkpoint-12292/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab0a0c2e05c9b19ae2fb7f37ade343bd0d98b553cbd00cc47aa20772252004c6
+size 14244
diff --git a/checkpoint-12292/scaler.pt b/checkpoint-12292/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d61a5c4f84a88a4510f13223a1f7f6d2db3f658b
--- /dev/null
+++ b/checkpoint-12292/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6509928afa01d668bf56b569c4f6a2e6c2fde9763d17681c72b55f19ab92eb20
+size 988
diff --git a/checkpoint-12292/scheduler.pt b/checkpoint-12292/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b88ec99899c104ace02c2c6be36cd3d4d4b59aaa
--- /dev/null
+++ b/checkpoint-12292/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f42e34b774989a80cf2635a24272d37af726ec5ad847c7648079f6697e6b0d3
+size 1064
diff --git a/checkpoint-12292/special_tokens_map.json b/checkpoint-12292/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..d79c0fe029062eb03708803e72c3483296e2ea97
--- /dev/null
+++ b/checkpoint-12292/special_tokens_map.json
@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-12292/tokenizer.json b/checkpoint-12292/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..7126b1d228f6e5f725b6ee02a88b1118c725aeed
--- /dev/null
+++ b/checkpoint-12292/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734
diff --git a/checkpoint-12292/tokenizer_config.json b/checkpoint-12292/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d297107d53da62483767139822cf5ed3a6975e24
--- /dev/null
+++ b/checkpoint-12292/tokenizer_config.json
@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-12292/trainer_state.json b/checkpoint-12292/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c688846b952266f6a1bc7372a95872d5586258e5
--- /dev/null
+++ b/checkpoint-12292/trainer_state.json
@@ -0,0 +1,1826 @@
+{
+  "best_global_step": 12292,
+  "best_metric": 0.9563834240267894,
+  "best_model_checkpoint": "C:\\Users\\Shara\\projects\\models\\run_16-lr_2e-05-acc_1-wd_0.01-bs_8-ep_7\\checkpoint-12292",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 12292,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02847380410022779,
+      "grad_norm": 4.8302321434021,
+      "learning_rate": 1.992840872111943e-05,
+      "loss": 0.9994,
+      "step": 50
+    },
+    {
+      "epoch": 0.05694760820045558,
+      "grad_norm": 3.4978649616241455,
+      "learning_rate": 1.9847054995118778e-05,
+      "loss": 0.3939,
+      "step": 100
+    },
+    {
+      "epoch": 0.08542141230068337,
+      "grad_norm": 8.353672981262207,
+      "learning_rate": 1.9765701269118128e-05,
+      "loss": 0.2882,
+      "step": 150
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "grad_norm": 9.822871208190918,
+      "learning_rate": 1.9684347543117477e-05,
+      "loss": 0.1728,
+      "step": 200
+    },
+    {
+      "epoch": 0.14236902050113895,
+      "grad_norm": 3.1411221027374268,
+      "learning_rate": 1.9602993817116827e-05,
+      "loss": 0.1251,
+      "step": 250
+    },
+    {
+      "epoch": 0.17084282460136674,
+      "grad_norm": 8.493424415588379,
+      "learning_rate": 1.9521640091116173e-05,
+      "loss": 0.1405,
+      "step": 300
+    },
+    {
+      "epoch": 0.19931662870159453,
+      "grad_norm": 4.757007122039795,
+      "learning_rate": 1.9440286365115523e-05,
+      "loss": 0.1431,
+      "step": 350
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "grad_norm": 4.339049816131592,
+      "learning_rate": 1.9358932639114873e-05,
+      "loss": 0.0912,
+      "step": 400
+    },
+    {
+      "epoch": 0.25626423690205014,
+      "grad_norm": 14.540772438049316,
+      "learning_rate": 1.9277578913114222e-05,
+      "loss": 0.1048,
+      "step": 450
+    },
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 10.503073692321777,
+      "learning_rate": 1.9196225187113572e-05,
+      "loss": 0.1224,
+      "step": 500
+    },
+    {
+      "epoch": 0.3132118451025057,
+      "grad_norm": 2.738131284713745,
+      "learning_rate": 1.911487146111292e-05,
+      "loss": 0.1025,
+      "step": 550
+    },
+    {
+      "epoch": 0.3416856492027335,
+      "grad_norm": 6.681102752685547,
+      "learning_rate": 1.903351773511227e-05,
+      "loss": 0.0869,
+      "step": 600
+    },
+    {
+      "epoch": 0.3701594533029613,
+      "grad_norm": 1.4330339431762695,
+      "learning_rate": 1.895216400911162e-05,
+      "loss": 0.052,
+      "step": 650
+    },
+    {
+      "epoch": 0.39863325740318906,
+      "grad_norm": 2.581470012664795,
+      "learning_rate": 1.8870810283110967e-05,
+      "loss": 0.0808,
+      "step": 700
+    },
+    {
+      "epoch": 0.4271070615034169,
+      "grad_norm": 5.825100898742676,
+      "learning_rate": 1.8789456557110317e-05,
+      "loss": 0.0716,
+      "step": 750
+    },
+    {
+      "epoch": 0.45558086560364464,
+      "grad_norm": 1.74166738986969,
+      "learning_rate": 1.8708102831109666e-05,
+      "loss": 0.0806,
+      "step": 800
+    },
+    {
+      "epoch": 0.48405466970387245,
+      "grad_norm": 7.3097405433654785,
+      "learning_rate": 1.8626749105109016e-05,
+      "loss": 0.0666,
+      "step": 850
+    },
+    {
+      "epoch": 0.5125284738041003,
+      "grad_norm": 2.220766067504883,
+      "learning_rate": 1.8545395379108362e-05,
+      "loss": 0.0768,
+      "step": 900
+    },
+    {
+      "epoch": 0.541002277904328,
+      "grad_norm": 4.0566511154174805,
+      "learning_rate": 1.8464041653107715e-05,
+      "loss": 0.0707,
+      "step": 950
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.2833240330219269,
+      "learning_rate": 1.8382687927107065e-05,
+      "loss": 0.0858,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5979498861047836,
+      "grad_norm": 21.131481170654297,
+      "learning_rate": 1.8301334201106415e-05,
+      "loss": 0.0595,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6264236902050114,
+      "grad_norm": 27.655433654785156,
+      "learning_rate": 1.821998047510576e-05,
+      "loss": 0.0466,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6548974943052391,
+      "grad_norm": 3.4721717834472656,
+      "learning_rate": 1.813862674910511e-05,
+      "loss": 0.0776,
+      "step": 1150
+    },
+    {
+      "epoch": 0.683371298405467,
+      "grad_norm": 2.4811441898345947,
+      "learning_rate": 1.805727302310446e-05,
+      "loss": 0.0647,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7118451025056948,
+      "grad_norm": 6.169066429138184,
+      "learning_rate": 1.797591929710381e-05,
+      "loss": 0.0724,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7403189066059226,
+      "grad_norm": 8.984748840332031,
+      "learning_rate": 1.7894565571103156e-05,
+      "loss": 0.0838,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7687927107061503,
+      "grad_norm": 5.944505214691162,
+      "learning_rate": 1.7813211845102506e-05,
+      "loss": 0.0683,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7972665148063781,
+      "grad_norm": 0.28812381625175476,
+      "learning_rate": 1.7731858119101856e-05,
+      "loss": 0.0614,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8257403189066059,
+      "grad_norm": 6.176011085510254,
+      "learning_rate": 1.7650504393101205e-05,
+      "loss": 0.0615,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8542141230068337,
+      "grad_norm": 2.5244405269622803,
+      "learning_rate": 1.7569150667100555e-05,
+      "loss": 0.0714,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8826879271070615,
+      "grad_norm": 3.3508074283599854,
+      "learning_rate": 1.7487796941099904e-05,
+      "loss": 0.0563,
+      "step": 1550
+    },
+    {
+      "epoch": 0.9111617312072893,
+      "grad_norm": 9.980842590332031,
+      "learning_rate": 1.7406443215099254e-05,
+      "loss": 0.0647,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9396355353075171,
+      "grad_norm": 3.6959774494171143,
+      "learning_rate": 1.7325089489098604e-05,
+      "loss": 0.0682,
+      "step": 1650
+    },
+    {
+      "epoch": 0.9681093394077449,
+      "grad_norm": 0.626620888710022,
+      "learning_rate": 1.724373576309795e-05,
+      "loss": 0.0499,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9965831435079726,
+      "grad_norm": 7.145672798156738,
+      "learning_rate": 1.71623820370973e-05,
+      "loss": 0.0569,
+      "step": 1750
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9242246437552389,
+      "eval_loss": 0.05600914731621742,
+      "eval_precision": 0.9206746826987308,
+      "eval_recall": 0.927802086839448,
+      "eval_runtime": 3.7538,
+      "eval_samples_per_second": 865.798,
+      "eval_steps_per_second": 108.425,
+      "step": 1756
+    },
+    {
+      "epoch": 1.0250569476082005,
+      "grad_norm": 4.280463695526123,
+      "learning_rate": 1.708102831109665e-05,
+      "loss": 0.0673,
+      "step": 1800
+    },
+    {
+      "epoch": 1.0535307517084282,
+      "grad_norm": 0.06692535430192947,
+      "learning_rate": 1.6999674585096e-05,
+      "loss": 0.0403,
+      "step": 1850
+    },
+    {
+      "epoch": 1.082004555808656,
+      "grad_norm": 0.03789375349879265,
+      "learning_rate": 1.691832085909535e-05,
+      "loss": 0.0496,
+      "step": 1900
+    },
+    {
+      "epoch": 1.1104783599088839,
+      "grad_norm": 3.698348045349121,
+      "learning_rate": 1.6836967133094698e-05,
+      "loss": 0.0381,
+      "step": 1950
+    },
+    {
+      "epoch": 1.1389521640091116,
+      "grad_norm": 2.753032684326172,
+      "learning_rate": 1.6755613407094048e-05,
+      "loss": 0.0432,
+      "step": 2000
+    },
+    {
+      "epoch": 1.1674259681093395,
+      "grad_norm": 0.06336130946874619,
+      "learning_rate": 1.6674259681093398e-05,
+      "loss": 0.0482,
+      "step": 2050
+    },
+    {
+      "epoch": 1.1958997722095672,
+      "grad_norm": 3.9503254890441895,
+      "learning_rate": 1.6592905955092744e-05,
+      "loss": 0.0436,
+      "step": 2100
+    },
+    {
+      "epoch": 1.224373576309795,
+      "grad_norm": 0.08679741621017456,
+      "learning_rate": 1.6511552229092093e-05,
+      "loss": 0.0346,
+      "step": 2150
+    },
+    {
+      "epoch": 1.2528473804100229,
+      "grad_norm": 2.1995127201080322,
+      "learning_rate": 1.6430198503091443e-05,
+      "loss": 0.0312,
+      "step": 2200
+    },
+    {
+      "epoch": 1.2813211845102506,
+      "grad_norm": 5.7709808349609375,
+      "learning_rate": 1.634884477709079e-05,
+      "loss": 0.032,
+      "step": 2250
+    },
+    {
+      "epoch": 1.3097949886104785,
+      "grad_norm": 0.2031829059123993,
+      "learning_rate": 1.626749105109014e-05,
+      "loss": 0.053,
+      "step": 2300
+    },
+    {
+      "epoch": 1.3382687927107062,
+      "grad_norm": 4.292157173156738,
+      "learning_rate": 1.6186137325089492e-05,
+      "loss": 0.0413,
+      "step": 2350
+    },
+    {
+      "epoch": 1.366742596810934,
+      "grad_norm": 0.07821401953697205,
+      "learning_rate": 1.6104783599088842e-05,
+      "loss": 0.0304,
+      "step": 2400
+    },
+    {
+      "epoch": 1.3952164009111616,
+      "grad_norm": 0.5930206179618835,
+      "learning_rate": 1.6023429873088188e-05,
+      "loss": 0.0525,
+      "step": 2450
+    },
+    {
+      "epoch": 1.4236902050113895,
+      "grad_norm": 1.6114712953567505,
+      "learning_rate": 1.5942076147087538e-05,
+      "loss": 0.0391,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4521640091116172,
+      "grad_norm": 0.28632065653800964,
+      "learning_rate": 1.5860722421086887e-05,
+      "loss": 0.0491,
+      "step": 2550
+    },
+    {
+      "epoch": 1.4806378132118452,
+      "grad_norm": 1.0017669200897217,
+      "learning_rate": 1.5779368695086237e-05,
+      "loss": 0.0395,
+      "step": 2600
+    },
+    {
+      "epoch": 1.5091116173120729,
+      "grad_norm": 0.03409272059798241,
+      "learning_rate": 1.5698014969085583e-05,
+      "loss": 0.0399,
+      "step": 2650
+    },
+    {
+      "epoch": 1.5375854214123006,
+      "grad_norm": 3.5108702182769775,
+      "learning_rate": 1.5616661243084933e-05,
+      "loss": 0.0424,
+      "step": 2700
+    },
+    {
+      "epoch": 1.5660592255125285,
+      "grad_norm": 3.5875349044799805,
+      "learning_rate": 1.5535307517084283e-05,
+      "loss": 0.0497,
+      "step": 2750
+    },
+    {
+      "epoch": 1.5945330296127562,
+      "grad_norm": 0.10498251020908356,
+      "learning_rate": 1.5453953791083632e-05,
+      "loss": 0.0461,
+      "step": 2800
+    },
+    {
+      "epoch": 1.6230068337129842,
+      "grad_norm": 7.618963718414307,
+      "learning_rate": 1.5374227139602996e-05,
+      "loss": 0.0394,
+      "step": 2850
+    },
+    {
+      "epoch": 1.6514806378132119,
+      "grad_norm": 3.3920793533325195,
+      "learning_rate": 1.5292873413602346e-05,
+      "loss": 0.0339,
+      "step": 2900
+    },
+    {
+      "epoch": 1.6799544419134396,
+      "grad_norm": 0.04736129939556122,
+      "learning_rate": 1.5211519687601692e-05,
+      "loss": 0.0358,
+      "step": 2950
+    },
+    {
+      "epoch": 1.7084282460136673,
+      "grad_norm": 0.17463508248329163,
+      "learning_rate": 1.5130165961601042e-05,
+      "loss": 0.034,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7369020501138952,
+      "grad_norm": 0.058148205280303955,
+      "learning_rate": 1.5048812235600392e-05,
+      "loss": 0.0317,
+      "step": 3050
+    },
+    {
+      "epoch": 1.7653758542141231,
+      "grad_norm": 3.5262815952301025,
+      "learning_rate": 1.4967458509599741e-05,
+      "loss": 0.0477,
+      "step": 3100
+    },
+    {
+      "epoch": 1.7938496583143508,
+      "grad_norm": 2.971937894821167,
+      "learning_rate": 1.488610478359909e-05,
+      "loss": 0.0364,
+      "step": 3150
+    },
+    {
+      "epoch": 1.8223234624145785,
+      "grad_norm": 0.05181724950671196,
+      "learning_rate": 1.4804751057598439e-05,
+      "loss": 0.0394,
+      "step": 3200
+    },
+    {
+      "epoch": 1.8507972665148062,
+      "grad_norm": 0.2712370455265045,
+      "learning_rate": 1.4723397331597789e-05,
+      "loss": 0.0456,
+      "step": 3250
+    },
+    {
+      "epoch": 1.8792710706150342,
+      "grad_norm": 1.608622431755066,
+      "learning_rate": 1.4642043605597138e-05,
+      "loss": 0.05,
+      "step": 3300
+    },
+    {
+      "epoch": 1.907744874715262,
+      "grad_norm": 5.2423529624938965,
+      "learning_rate": 1.4560689879596486e-05,
+      "loss": 0.0371,
+      "step": 3350
+    },
+    {
+      "epoch": 1.9362186788154898,
+      "grad_norm": 0.04786211624741554,
+      "learning_rate": 1.4479336153595836e-05,
+      "loss": 0.0329,
+      "step": 3400
+    },
+    {
+      "epoch": 1.9646924829157175,
+      "grad_norm": 0.5264931917190552,
+      "learning_rate": 1.4397982427595185e-05,
+      "loss": 0.0379,
+      "step": 3450
+    },
+    {
+      "epoch": 1.9931662870159452,
+      "grad_norm": 0.236006498336792,
+      "learning_rate": 1.4316628701594535e-05,
+      "loss": 0.0253,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9406438631790744,
+      "eval_loss": 0.05223705992102623,
+      "eval_precision": 0.9371867691279653,
+      "eval_recall": 0.9441265567149109,
+      "eval_runtime": 3.7109,
+      "eval_samples_per_second": 875.791,
+      "eval_steps_per_second": 109.676,
+      "step": 3512
+    },
+    {
+      "epoch": 2.021640091116173,
+      "grad_norm": 4.225963115692139,
+      "learning_rate": 1.4235274975593883e-05,
+      "loss": 0.0373,
+      "step": 3550
+    },
+    {
+      "epoch": 2.050113895216401,
+      "grad_norm": 0.15388111770153046,
+      "learning_rate": 1.4153921249593233e-05,
+      "loss": 0.0258,
+      "step": 3600
+    },
+    {
+      "epoch": 2.078587699316629,
+      "grad_norm": 6.3911895751953125,
+      "learning_rate": 1.4072567523592582e-05,
+      "loss": 0.0217,
+      "step": 3650
+    },
+    {
+      "epoch": 2.1070615034168565,
+      "grad_norm": 0.03075530007481575,
+      "learning_rate": 1.3991213797591932e-05,
+      "loss": 0.019,
+      "step": 3700
+    },
+    {
+      "epoch": 2.135535307517084,
+      "grad_norm": 0.16612432897090912,
+      "learning_rate": 1.3909860071591278e-05,
+      "loss": 0.0175,
+      "step": 3750
+    },
+    {
+      "epoch": 2.164009111617312,
+      "grad_norm": 0.14543022215366364,
+      "learning_rate": 1.382850634559063e-05,
+      "loss": 0.0289,
+      "step": 3800
+    },
+    {
+      "epoch": 2.19248291571754,
+      "grad_norm": 2.9880359172821045,
+      "learning_rate": 1.374715261958998e-05,
+      "loss": 0.0208,
+      "step": 3850
+    },
+    {
+      "epoch": 2.2209567198177678,
+      "grad_norm": 9.878133773803711,
+      "learning_rate": 1.3665798893589329e-05,
+      "loss": 0.021,
+      "step": 3900
+    },
+    {
+      "epoch": 2.2494305239179955,
+      "grad_norm": 9.684176445007324,
+      "learning_rate": 1.3584445167588675e-05,
+      "loss": 0.0267,
+      "step": 3950
+    },
+    {
+      "epoch": 2.277904328018223,
+      "grad_norm": 33.15859603881836,
+      "learning_rate": 1.3503091441588025e-05,
+      "loss": 0.0295,
+      "step": 4000
+    },
+    {
+      "epoch": 2.306378132118451,
+      "grad_norm": 2.559544086456299,
+      "learning_rate": 1.3421737715587374e-05,
+      "loss": 0.0292,
+      "step": 4050
+    },
+    {
+      "epoch": 2.334851936218679,
+      "grad_norm": 0.07091552764177322,
+      "learning_rate": 1.3340383989586724e-05,
+      "loss": 0.0262,
+      "step": 4100
+    },
+    {
+      "epoch": 2.3633257403189067,
+      "grad_norm": 1.8119585514068604,
+      "learning_rate": 1.3259030263586072e-05,
+      "loss": 0.03,
+      "step": 4150
+    },
+    {
+      "epoch": 2.3917995444191344,
+      "grad_norm": 0.1476636379957199,
+      "learning_rate": 1.3177676537585422e-05,
+      "loss": 0.0196,
+      "step": 4200
+    },
+    {
+      "epoch": 2.420273348519362,
+      "grad_norm": 0.04482650011777878,
+      "learning_rate": 1.3096322811584771e-05,
+      "loss": 0.0263,
+      "step": 4250
+    },
+    {
+      "epoch": 2.44874715261959,
+      "grad_norm": 0.09201560169458389,
+      "learning_rate": 1.3014969085584121e-05,
+      "loss": 0.0172,
+      "step": 4300
+    },
+    {
+      "epoch": 2.477220956719818,
+      "grad_norm": 0.02215876244008541,
+      "learning_rate": 1.2933615359583469e-05,
+      "loss": 0.0149,
+      "step": 4350
+    },
+    {
+      "epoch": 2.5056947608200457,
+      "grad_norm": 0.6993932127952576,
+      "learning_rate": 1.2852261633582819e-05,
+      "loss": 0.0331,
+      "step": 4400
+    },
+    {
+      "epoch": 2.5341685649202734,
+      "grad_norm": 0.030453965067863464,
+      "learning_rate": 1.2770907907582168e-05,
+      "loss": 0.0307,
+      "step": 4450
+    },
+    {
+      "epoch": 2.562642369020501,
+      "grad_norm": 0.22211593389511108,
+      "learning_rate": 1.2689554181581518e-05,
+      "loss": 0.0183,
+      "step": 4500
+    },
+    {
+      "epoch": 2.591116173120729,
+      "grad_norm": 1.2842738628387451,
+      "learning_rate": 1.2608200455580866e-05,
+      "loss": 0.0226,
+      "step": 4550
+    },
+    {
+      "epoch": 2.619589977220957,
+      "grad_norm": 3.9048423767089844,
+      "learning_rate": 1.2526846729580216e-05,
+      "loss": 0.0239,
+      "step": 4600
+    },
+    {
+      "epoch": 2.6480637813211843,
+      "grad_norm": 0.9887784719467163,
+      "learning_rate": 1.2445493003579565e-05,
+      "loss": 0.0271,
+      "step": 4650
+    },
+    {
+      "epoch": 2.6765375854214124,
+      "grad_norm": 4.759728908538818,
+      "learning_rate": 1.2364139277578915e-05,
+      "loss": 0.0201,
+      "step": 4700
+    },
+    {
+      "epoch": 2.70501138952164,
+      "grad_norm": 0.2671191096305847,
+      "learning_rate": 1.2282785551578263e-05,
+      "loss": 0.0212,
+      "step": 4750
+    },
+    {
+      "epoch": 2.733485193621868,
+      "grad_norm": 0.036626849323511124,
+      "learning_rate": 1.2201431825577612e-05,
+      "loss": 0.0155,
+      "step": 4800
+    },
+    {
+      "epoch": 2.7619589977220955,
+      "grad_norm": 6.877408027648926,
+      "learning_rate": 1.2120078099576962e-05,
+      "loss": 0.0266,
+      "step": 4850
+    },
+    {
+      "epoch": 2.7904328018223232,
+      "grad_norm": 4.725896835327148,
+      "learning_rate": 1.2038724373576312e-05,
+      "loss": 0.0163,
+      "step": 4900
+    },
+    {
+      "epoch": 2.8189066059225514,
+      "grad_norm": 0.11965059489011765,
+      "learning_rate": 1.195737064757566e-05,
+      "loss": 0.0246,
+      "step": 4950
+    },
+    {
+      "epoch": 2.847380410022779,
+      "grad_norm": 0.6634079813957214,
+      "learning_rate": 1.187601692157501e-05,
+      "loss": 0.0304,
+      "step": 5000
+    },
+    {
+      "epoch": 2.875854214123007,
+      "grad_norm": 3.952694892883301,
+      "learning_rate": 1.1794663195574359e-05,
+      "loss": 0.0183,
+      "step": 5050
+    },
+    {
+      "epoch": 2.9043280182232345,
+      "grad_norm": 19.788942337036133,
+      "learning_rate": 1.1713309469573709e-05,
+      "loss": 0.0193,
+      "step": 5100
+    },
+    {
+      "epoch": 2.932801822323462,
+      "grad_norm": 4.989261627197266,
+      "learning_rate": 1.1631955743573055e-05,
+      "loss": 0.023,
+      "step": 5150
+    },
+    {
+      "epoch": 2.9612756264236904,
+      "grad_norm": 9.020853996276855,
+      "learning_rate": 1.1550602017572406e-05,
+      "loss": 0.0231,
+      "step": 5200
+    },
+    {
+      "epoch": 2.989749430523918,
+      "grad_norm": 0.9151140451431274,
+      "learning_rate": 1.1469248291571756e-05,
+      "loss": 0.0314,
+      "step": 5250
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.9470420646891236,
+      "eval_loss": 0.04870199039578438,
+      "eval_precision": 0.943090787716956,
+      "eval_recall": 0.9510265903736116,
+      "eval_runtime": 3.7494,
+      "eval_samples_per_second": 866.805,
+      "eval_steps_per_second": 108.551,
+      "step": 5268
+    },
+    {
+      "epoch": 3.0182232346241458,
+      "grad_norm": 8.62992000579834,
+      "learning_rate": 1.1387894565571106e-05,
+      "loss": 0.0194,
+      "step": 5300
+    },
+    {
+      "epoch": 3.0466970387243735,
+      "grad_norm": 0.5615554451942444,
+      "learning_rate": 1.1306540839570452e-05,
+      "loss": 0.0114,
+      "step": 5350
+    },
+    {
+      "epoch": 3.075170842824601,
+      "grad_norm": 2.5735936164855957,
+      "learning_rate": 1.1225187113569801e-05,
+      "loss": 0.0163,
+      "step": 5400
+    },
+    {
+      "epoch": 3.1036446469248293,
+      "grad_norm": 6.504094123840332,
+      "learning_rate": 1.1143833387569151e-05,
+      "loss": 0.0135,
+      "step": 5450
+    },
+    {
+      "epoch": 3.132118451025057,
+      "grad_norm": 14.477537155151367,
+      "learning_rate": 1.10624796615685e-05,
+      "loss": 0.0129,
+      "step": 5500
+    },
+    {
+      "epoch": 3.1605922551252847,
+      "grad_norm": 0.04929841682314873,
+      "learning_rate": 1.0981125935567849e-05,
+      "loss": 0.0263,
+      "step": 5550
+    },
+    {
+      "epoch": 3.1890660592255125,
+      "grad_norm": 0.08875144273042679,
+      "learning_rate": 1.0899772209567198e-05,
+      "loss": 0.0134,
+      "step": 5600
+    },
+    {
+      "epoch": 3.21753986332574,
+      "grad_norm": 0.6238455772399902,
+      "learning_rate": 1.0818418483566548e-05,
+      "loss": 0.0107,
+      "step": 5650
+    },
+    {
+      "epoch": 3.2460136674259683,
+      "grad_norm": 0.004948179703205824,
+      "learning_rate": 1.0737064757565898e-05,
+      "loss": 0.0167,
+      "step": 5700
+    },
+    {
+      "epoch": 3.274487471526196,
+      "grad_norm": 0.017031218856573105,
+      "learning_rate": 1.0655711031565246e-05,
+      "loss": 0.0085,
+      "step": 5750
+    },
+    {
+      "epoch": 3.3029612756264237,
+      "grad_norm": 2.9840469360351562,
+      "learning_rate": 1.0574357305564595e-05,
+      "loss": 0.0158,
+      "step": 5800
+    },
+    {
+      "epoch": 3.3314350797266514,
+      "grad_norm": 1.7477540969848633,
+      "learning_rate": 1.0493003579563945e-05,
+      "loss": 0.0157,
+      "step": 5850
+    },
+    {
+      "epoch": 3.359908883826879,
+      "grad_norm": 0.03963543102145195,
+      "learning_rate": 1.0411649853563295e-05,
+      "loss": 0.0201,
+      "step": 5900
+    },
+    {
+      "epoch": 3.3883826879271073,
+      "grad_norm": 0.16669808328151703,
+      "learning_rate": 1.0330296127562643e-05,
+      "loss": 0.0159,
+      "step": 5950
+    },
+    {
+      "epoch": 3.416856492027335,
+      "grad_norm": 0.01953568309545517,
+      "learning_rate": 1.0248942401561992e-05,
+      "loss": 0.0117,
+      "step": 6000
+    },
+    {
+      "epoch": 3.4453302961275627,
+      "grad_norm": 0.07708246260881424,
+      "learning_rate": 1.0167588675561342e-05,
+      "loss": 0.0117,
+      "step": 6050
+    },
+    {
+      "epoch": 3.4738041002277904,
+      "grad_norm": 2.423590898513794,
+      "learning_rate": 1.0086234949560691e-05,
+      "loss": 0.0111,
+      "step": 6100
+    },
+    {
+      "epoch": 3.502277904328018,
+      "grad_norm": 0.006337775848805904,
+      "learning_rate": 1.000488122356004e-05,
+      "loss": 0.0052,
+      "step": 6150
+    },
+    {
+      "epoch": 3.5307517084282463,
+      "grad_norm": 0.01373753696680069,
+      "learning_rate": 9.923527497559389e-06,
+      "loss": 0.009,
+      "step": 6200
+    },
+    {
+      "epoch": 3.559225512528474,
+      "grad_norm": 0.11260247975587845,
+      "learning_rate": 9.842173771558739e-06,
+      "loss": 0.0208,
+      "step": 6250
+    },
+    {
+      "epoch": 3.5876993166287017,
+      "grad_norm": 1.240822196006775,
+      "learning_rate": 9.760820045558087e-06,
+      "loss": 0.0157,
+      "step": 6300
+    },
+    {
+      "epoch": 3.6161731207289294,
+      "grad_norm": 0.05271293595433235,
+      "learning_rate": 9.679466319557436e-06,
+      "loss": 0.0175,
+      "step": 6350
+    },
+    {
+      "epoch": 3.644646924829157,
+      "grad_norm": 24.546663284301758,
+      "learning_rate": 9.598112593556786e-06,
+      "loss": 0.015,
+      "step": 6400
+    },
+    {
+      "epoch": 3.6731207289293852,
+      "grad_norm": 5.120173931121826,
+      "learning_rate": 9.516758867556136e-06,
+      "loss": 0.017,
+      "step": 6450
+    },
+    {
+      "epoch": 3.7015945330296125,
+      "grad_norm": 1.1922008991241455,
+      "learning_rate": 9.435405141555484e-06,
+      "loss": 0.0194,
+      "step": 6500
+    },
+    {
+      "epoch": 3.7300683371298406,
+      "grad_norm": 0.039439987391233444,
+      "learning_rate": 9.354051415554833e-06,
+      "loss": 0.0309,
+      "step": 6550
+    },
+    {
+      "epoch": 3.7585421412300684,
+      "grad_norm": 0.04055279493331909,
+      "learning_rate": 9.272697689554181e-06,
+      "loss": 0.0195,
+      "step": 6600
+    },
+    {
+      "epoch": 3.787015945330296,
+      "grad_norm": 0.5971085429191589,
+      "learning_rate": 9.191343963553533e-06,
+      "loss": 0.0156,
+      "step": 6650
+    },
+    {
+      "epoch": 3.8154897494305238,
+      "grad_norm": 0.2191866636276245,
+      "learning_rate": 9.10999023755288e-06,
+      "loss": 0.0174,
+      "step": 6700
+    },
+    {
+      "epoch": 3.8439635535307515,
+      "grad_norm": 0.033559828996658325,
+      "learning_rate": 9.02863651155223e-06,
+      "loss": 0.0149,
+      "step": 6750
+    },
+    {
+      "epoch": 3.8724373576309796,
+      "grad_norm": 3.7128634452819824,
+      "learning_rate": 8.947282785551578e-06,
+      "loss": 0.0221,
+      "step": 6800
+    },
+    {
+      "epoch": 3.9009111617312073,
+      "grad_norm": 0.08547580987215042,
+      "learning_rate": 8.865929059550928e-06,
+      "loss": 0.0153,
+      "step": 6850
+    },
+    {
+      "epoch": 3.929384965831435,
+      "grad_norm": 0.058124080300331116,
+      "learning_rate": 8.784575333550277e-06,
+      "loss": 0.0161,
+      "step": 6900
+    },
+    {
+      "epoch": 3.9578587699316627,
+      "grad_norm": 0.015579139813780785,
+      "learning_rate": 8.703221607549627e-06,
+      "loss": 0.011,
+      "step": 6950
+    },
+    {
+      "epoch": 3.9863325740318905,
+      "grad_norm": 0.12764935195446014,
+      "learning_rate": 8.621867881548975e-06,
+      "loss": 0.0166,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.9525329748802823,
+      "eval_loss": 0.04983380436897278,
+      "eval_precision": 0.9510149303808086,
+      "eval_recall": 0.9540558734432851,
+      "eval_runtime": 3.7495,
+      "eval_samples_per_second": 866.79,
+      "eval_steps_per_second": 108.549,
+      "step": 7024
+    },
+    {
+      "epoch": 4.014806378132119,
+      "grad_norm": 0.04521024227142334,
+      "learning_rate": 8.540514155548325e-06,
+      "loss": 0.0102,
+      "step": 7050
+    },
+    {
+      "epoch": 4.043280182232346,
+      "grad_norm": 0.015535669401288033,
+      "learning_rate": 8.459160429547674e-06,
+      "loss": 0.0068,
+      "step": 7100
+    },
+    {
+      "epoch": 4.071753986332574,
+      "grad_norm": 12.566010475158691,
+      "learning_rate": 8.377806703547024e-06,
+      "loss": 0.0151,
+      "step": 7150
+    },
+    {
+      "epoch": 4.100227790432802,
+      "grad_norm": 0.027761396020650864,
+      "learning_rate": 8.296452977546372e-06,
+      "loss": 0.0053,
+      "step": 7200
+    },
+    {
+      "epoch": 4.128701594533029,
+      "grad_norm": 1.8846938610076904,
+      "learning_rate": 8.215099251545722e-06,
+      "loss": 0.0077,
+      "step": 7250
+    },
+    {
+      "epoch": 4.157175398633258,
+      "grad_norm": 0.005013479385524988,
+      "learning_rate": 8.13374552554507e-06,
+      "loss": 0.0073,
+      "step": 7300
+    },
+    {
+      "epoch": 4.185649202733485,
+      "grad_norm": 0.32696235179901123,
+      "learning_rate": 8.052391799544421e-06,
+      "loss": 0.0092,
+      "step": 7350
+    },
+    {
+      "epoch": 4.214123006833713,
+      "grad_norm": 0.014357910491526127,
+      "learning_rate": 7.971038073543769e-06,
+      "loss": 0.0164,
+      "step": 7400
+    },
+    {
+      "epoch": 4.242596810933941,
+      "grad_norm": 0.010845329612493515,
+      "learning_rate": 7.889684347543118e-06,
+      "loss": 0.0123,
+      "step": 7450
+    },
+    {
+      "epoch": 4.271070615034168,
+      "grad_norm": 0.6969354748725891,
+      "learning_rate": 7.808330621542466e-06,
+      "loss": 0.0103,
+      "step": 7500
+    },
+    {
+      "epoch": 4.2995444191343966,
+      "grad_norm": 0.3575742840766907,
+      "learning_rate": 7.726976895541816e-06,
+      "loss": 0.0161,
+      "step": 7550
+    },
+    {
+      "epoch": 4.328018223234624,
+      "grad_norm": 0.008076228201389313,
+      "learning_rate": 7.645623169541166e-06,
+      "loss": 0.0122,
+      "step": 7600
+    },
+    {
+      "epoch": 4.356492027334852,
+      "grad_norm": 0.029101597145199776,
+      "learning_rate": 7.564269443540515e-06,
+      "loss": 0.0071,
+      "step": 7650
+    },
+    {
+      "epoch": 4.38496583143508,
+      "grad_norm": 0.06841142475605011,
+      "learning_rate": 7.482915717539863e-06,
+      "loss": 0.0091,
+      "step": 7700
+    },
+    {
+      "epoch": 4.413439635535307,
+      "grad_norm": 0.04133535176515579,
+      "learning_rate": 7.401561991539213e-06,
+      "loss": 0.0073,
+      "step": 7750
+    },
+    {
+      "epoch": 4.4419134396355355,
+      "grad_norm": 0.03571132943034172,
+      "learning_rate": 7.320208265538562e-06,
+      "loss": 0.0131,
+      "step": 7800
+    },
+    {
+      "epoch": 4.470387243735763,
+      "grad_norm": 2.8286924362182617,
+      "learning_rate": 7.2388545395379114e-06,
+      "loss": 0.0043,
+      "step": 7850
+    },
+    {
+      "epoch": 4.498861047835991,
+      "grad_norm": 1.3785158395767212,
+      "learning_rate": 7.15750081353726e-06,
+      "loss": 0.0103,
+      "step": 7900
+    },
+    {
+      "epoch": 4.527334851936219,
+      "grad_norm": 0.05979786813259125,
+      "learning_rate": 7.07614708753661e-06,
+      "loss": 0.006,
+      "step": 7950
+    },
+    {
+      "epoch": 4.555808656036446,
+      "grad_norm": 1.3434393405914307,
+      "learning_rate": 6.994793361535959e-06,
+      "loss": 0.0148,
+      "step": 8000
+    },
+    {
+      "epoch": 4.5842824601366745,
+      "grad_norm": 0.019605603069067,
+      "learning_rate": 6.913439635535308e-06,
+      "loss": 0.0068,
+      "step": 8050
+    },
+    {
+      "epoch": 4.612756264236902,
+      "grad_norm": 0.0028891051188111305,
+      "learning_rate": 6.832085909534657e-06,
+      "loss": 0.0075,
+      "step": 8100
+    },
+    {
+      "epoch": 4.64123006833713,
+      "grad_norm": 0.014856363646686077,
+      "learning_rate": 6.750732183534007e-06,
+      "loss": 0.0073,
+      "step": 8150
+    },
+    {
+      "epoch": 4.669703872437358,
+      "grad_norm": 0.0037149768322706223,
+      "learning_rate": 6.669378457533356e-06,
+      "loss": 0.0066,
+      "step": 8200
+    },
+    {
+      "epoch": 4.698177676537585,
+      "grad_norm": 0.008534993045032024,
+      "learning_rate": 6.588024731532705e-06,
+      "loss": 0.0121,
+      "step": 8250
+    },
+    {
+      "epoch": 4.7266514806378135,
+      "grad_norm": 0.013920712284743786,
+      "learning_rate": 6.506671005532054e-06,
+      "loss": 0.013,
+      "step": 8300
+    },
+    {
+      "epoch": 4.755125284738041,
+      "grad_norm": 0.10121840238571167,
+      "learning_rate": 6.425317279531404e-06,
+      "loss": 0.0087,
+      "step": 8350
+    },
+    {
+      "epoch": 4.783599088838269,
+      "grad_norm": 0.07937771081924438,
+      "learning_rate": 6.343963553530752e-06,
+      "loss": 0.0086,
+      "step": 8400
+    },
+    {
+      "epoch": 4.812072892938497,
+      "grad_norm": 0.07674901187419891,
+      "learning_rate": 6.262609827530101e-06,
+      "loss": 0.0052,
+      "step": 8450
+    },
+    {
+      "epoch": 4.840546697038724,
+      "grad_norm": 0.06683178246021271,
+      "learning_rate": 6.18125610152945e-06,
+      "loss": 0.015,
+      "step": 8500
+    },
+    {
+      "epoch": 4.8690205011389525,
+      "grad_norm": 0.08861212432384491,
+      "learning_rate": 6.0999023755288e-06,
+      "loss": 0.0109,
+      "step": 8550
+    },
+    {
+      "epoch": 4.89749430523918,
+      "grad_norm": 0.006198623217642307,
+      "learning_rate": 6.018548649528149e-06,
+      "loss": 0.0181,
+      "step": 8600
+    },
+    {
+      "epoch": 4.925968109339408,
+      "grad_norm": 0.009029284119606018,
+      "learning_rate": 5.937194923527498e-06,
+      "loss": 0.0043,
+      "step": 8650
+    },
+    {
+      "epoch": 4.954441913439636,
+      "grad_norm": 1.1225602626800537,
+      "learning_rate": 5.855841197526847e-06,
+      "loss": 0.0121,
+      "step": 8700
+    },
+    {
+      "epoch": 4.982915717539863,
+      "grad_norm": 0.01218325924128294,
+      "learning_rate": 5.774487471526197e-06,
+      "loss": 0.0115,
+      "step": 8750
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.9533444816053511,
+      "eval_loss": 0.04722925275564194,
+      "eval_precision": 0.9473246925889,
+      "eval_recall": 0.9594412655671491,
+      "eval_runtime": 3.7358,
+      "eval_samples_per_second": 869.968,
+      "eval_steps_per_second": 108.947,
+      "step": 8780
+    },
+    {
+      "epoch": 5.011389521640091,
+      "grad_norm": 0.8161097764968872,
+      "learning_rate": 5.6931337455255455e-06,
+      "loss": 0.0127,
+      "step": 8800
+    },
+    {
+      "epoch": 5.039863325740319,
+      "grad_norm": 0.048089127987623215,
+      "learning_rate": 5.611780019524895e-06,
+      "loss": 0.0116,
+      "step": 8850
+    },
+    {
+      "epoch": 5.068337129840547,
+      "grad_norm": 1.7576072216033936,
+      "learning_rate": 5.530426293524244e-06,
+      "loss": 0.0093,
+      "step": 8900
+    },
+    {
+      "epoch": 5.096810933940774,
+      "grad_norm": 0.07270015776157379,
+      "learning_rate": 5.449072567523594e-06,
+      "loss": 0.0043,
+      "step": 8950
+    },
+    {
+      "epoch": 5.125284738041002,
+      "grad_norm": 0.2580782175064087,
+      "learning_rate": 5.367718841522942e-06,
+      "loss": 0.0058,
+      "step": 9000
+    },
+    {
+      "epoch": 5.15375854214123,
+      "grad_norm": 0.12649740278720856,
+      "learning_rate": 5.286365115522292e-06,
+      "loss": 0.0033,
+      "step": 9050
+    },
+    {
+      "epoch": 5.182232346241458,
+      "grad_norm": 0.06850716471672058,
+      "learning_rate": 5.20501138952164e-06,
+      "loss": 0.003,
+      "step": 9100
+    },
+    {
+      "epoch": 5.210706150341686,
+      "grad_norm": 0.01197959017008543,
+      "learning_rate": 5.12365766352099e-06,
+      "loss": 0.0029,
+      "step": 9150
+    },
+    {
+      "epoch": 5.239179954441913,
+      "grad_norm": 0.10818086564540863,
+      "learning_rate": 5.0423039375203385e-06,
+      "loss": 0.0025,
+      "step": 9200
+    },
+    {
+      "epoch": 5.267653758542141,
+      "grad_norm": 0.035460665822029114,
+      "learning_rate": 4.960950211519688e-06,
+      "loss": 0.0047,
+      "step": 9250
+    },
+    {
+      "epoch": 5.296127562642369,
+      "grad_norm": 4.532562255859375,
+      "learning_rate": 4.879596485519037e-06,
+      "loss": 0.0086,
+      "step": 9300
+    },
+    {
+      "epoch": 5.324601366742597,
+      "grad_norm": 0.013236219063401222,
+      "learning_rate": 4.7982427595183866e-06,
+      "loss": 0.0027,
+      "step": 9350
+    },
+    {
+      "epoch": 5.353075170842825,
+      "grad_norm": 0.018059909343719482,
+      "learning_rate": 4.716889033517735e-06,
+      "loss": 0.0065,
+      "step": 9400
+    },
+    {
+      "epoch": 5.381548974943052,
+      "grad_norm": 0.019096272066235542,
+      "learning_rate": 4.635535307517084e-06,
+      "loss": 0.0053,
+      "step": 9450
+    },
+    {
+      "epoch": 5.41002277904328,
+      "grad_norm": 0.10389436781406403,
+      "learning_rate": 4.554181581516434e-06,
+      "loss": 0.0029,
+      "step": 9500
+    },
+    {
+      "epoch": 5.438496583143508,
+      "grad_norm": 0.0029252381063997746,
+      "learning_rate": 4.472827855515783e-06,
+      "loss": 0.0045,
+      "step": 9550
+    },
+    {
+      "epoch": 5.466970387243736,
+      "grad_norm": 0.004542892333120108,
+      "learning_rate": 4.391474129515132e-06,
+      "loss": 0.0102,
+      "step": 9600
+    },
+    {
+      "epoch": 5.495444191343964,
+      "grad_norm": 0.130916565656662,
+      "learning_rate": 4.310120403514481e-06,
+      "loss": 0.0064,
+      "step": 9650
+    },
+    {
+      "epoch": 5.523917995444191,
+      "grad_norm": 0.008013393729925156,
+      "learning_rate": 4.22876667751383e-06,
+      "loss": 0.005,
+      "step": 9700
+    },
+    {
+      "epoch": 5.552391799544419,
+      "grad_norm": 0.012782514095306396,
+      "learning_rate": 4.1474129515131795e-06,
+      "loss": 0.0122,
+      "step": 9750
+    },
+    {
+      "epoch": 5.5808656036446465,
+      "grad_norm": 0.9617053866386414,
+      "learning_rate": 4.066059225512528e-06,
+      "loss": 0.0063,
+      "step": 9800
+    },
+    {
+      "epoch": 5.609339407744875,
+      "grad_norm": 0.014953136444091797,
+      "learning_rate": 3.984705499511878e-06,
+      "loss": 0.0046,
+      "step": 9850
+    },
+    {
+      "epoch": 5.637813211845103,
+      "grad_norm": 1.0275633335113525,
+      "learning_rate": 3.903351773511227e-06,
+      "loss": 0.0075,
+      "step": 9900
+    },
+    {
+      "epoch": 5.66628701594533,
+      "grad_norm": 0.007999264635145664,
+      "learning_rate": 3.8219980475105764e-06,
+      "loss": 0.0031,
+      "step": 9950
+    },
+    {
+      "epoch": 5.694760820045558,
+      "grad_norm": 0.008241960778832436,
+      "learning_rate": 3.7406443215099252e-06,
+      "loss": 0.0065,
+      "step": 10000
+    },
+    {
+      "epoch": 5.723234624145785,
+      "grad_norm": 2.578386068344116,
+      "learning_rate": 3.6592905955092745e-06,
+      "loss": 0.0057,
+      "step": 10050
+    },
+    {
+      "epoch": 5.751708428246014,
+      "grad_norm": 2.8855443000793457,
+      "learning_rate": 3.5779368695086237e-06,
+      "loss": 0.0038,
+      "step": 10100
+    },
+    {
+      "epoch": 5.780182232346242,
+      "grad_norm": 0.016262667253613472,
+      "learning_rate": 3.496583143507973e-06,
+      "loss": 0.0128,
+      "step": 10150
+    },
+    {
+      "epoch": 5.808656036446469,
+      "grad_norm": 0.045168060809373856,
+      "learning_rate": 3.415229417507322e-06,
+      "loss": 0.0036,
+      "step": 10200
+    },
+    {
+      "epoch": 5.837129840546697,
+      "grad_norm": 0.1192622259259224,
+      "learning_rate": 3.3355027660266842e-06,
+      "loss": 0.0111,
+      "step": 10250
+    },
+    {
+      "epoch": 5.865603644646924,
+      "grad_norm": 0.08544190227985382,
+      "learning_rate": 3.2541490400260335e-06,
+      "loss": 0.0051,
+      "step": 10300
+    },
+    {
+      "epoch": 5.894077448747153,
+      "grad_norm": 3.493161678314209,
+      "learning_rate": 3.1727953140253827e-06,
+      "loss": 0.0054,
+      "step": 10350
+    },
+    {
+      "epoch": 5.922551252847381,
+      "grad_norm": 0.022789066657423973,
+      "learning_rate": 3.0914415880247315e-06,
+      "loss": 0.0033,
+      "step": 10400
+    },
+    {
+      "epoch": 5.951025056947608,
+      "grad_norm": 12.131625175476074,
+      "learning_rate": 3.0100878620240807e-06,
+      "loss": 0.0023,
+      "step": 10450
+    },
+    {
+      "epoch": 5.979498861047836,
+      "grad_norm": 0.03329641371965408,
+      "learning_rate": 2.92873413602343e-06,
+      "loss": 0.0058,
+      "step": 10500
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1": 0.9557566616390145,
+      "eval_loss": 0.05410688370466232,
+      "eval_precision": 0.9517690253671562,
+      "eval_recall": 0.9597778525748906,
+      "eval_runtime": 3.6572,
+      "eval_samples_per_second": 888.662,
+      "eval_steps_per_second": 111.288,
+      "step": 10536
+    },
+    {
+      "epoch": 6.007972665148063,
+      "grad_norm": 0.008557640947401524,
+      "learning_rate": 2.847380410022779e-06,
+      "loss": 0.0152,
+      "step": 10550
+    },
+    {
+      "epoch": 6.0364464692482915,
+      "grad_norm": 0.08105529844760895,
+      "learning_rate": 2.7660266840221284e-06,
+      "loss": 0.0025,
+      "step": 10600
+    },
+    {
+      "epoch": 6.06492027334852,
+      "grad_norm": 1.100066065788269,
+      "learning_rate": 2.6846729580214776e-06,
+      "loss": 0.0015,
+      "step": 10650
+    },
+    {
+      "epoch": 6.093394077448747,
+      "grad_norm": 1.96909761428833,
+      "learning_rate": 2.603319232020827e-06,
+      "loss": 0.0021,
+      "step": 10700
+    },
+    {
+      "epoch": 6.121867881548975,
+      "grad_norm": 0.00583766121417284,
+      "learning_rate": 2.5219655060201757e-06,
+      "loss": 0.0127,
+      "step": 10750
+    },
+    {
+      "epoch": 6.150341685649202,
+      "grad_norm": 0.026862677186727524,
+      "learning_rate": 2.440611780019525e-06,
+      "loss": 0.004,
+      "step": 10800
+    },
+    {
+      "epoch": 6.1788154897494305,
+      "grad_norm": 0.010042566806077957,
+      "learning_rate": 2.359258054018874e-06,
+      "loss": 0.0033,
+      "step": 10850
+    },
+    {
+      "epoch": 6.207289293849659,
+      "grad_norm": 0.8956929445266724,
+      "learning_rate": 2.2779043280182233e-06,
+      "loss": 0.0031,
+      "step": 10900
+    },
+    {
+      "epoch": 6.235763097949886,
+      "grad_norm": 0.009118441492319107,
+      "learning_rate": 2.1965506020175726e-06,
+      "loss": 0.0039,
+      "step": 10950
+    },
+    {
+      "epoch": 6.264236902050114,
+      "grad_norm": 0.22793921828269958,
+      "learning_rate": 2.115196876016922e-06,
+      "loss": 0.0013,
+      "step": 11000
+    },
+    {
+      "epoch": 6.292710706150341,
+      "grad_norm": 0.015608682297170162,
+      "learning_rate": 2.033843150016271e-06,
+      "loss": 0.0021,
+      "step": 11050
+    },
+    {
+      "epoch": 6.3211845102505695,
+      "grad_norm": 0.004031027667224407,
+      "learning_rate": 1.95248942401562e-06,
+      "loss": 0.0011,
+      "step": 11100
+    },
+    {
+      "epoch": 6.349658314350798,
+      "grad_norm": 0.008949857205152512,
+      "learning_rate": 1.8711356980149693e-06,
+      "loss": 0.0049,
+      "step": 11150
+    },
+    {
+      "epoch": 6.378132118451025,
+      "grad_norm": 0.018670039251446724,
+      "learning_rate": 1.7897819720143183e-06,
+      "loss": 0.003,
+      "step": 11200
+    },
+    {
+      "epoch": 6.406605922551253,
+      "grad_norm": 0.032393742352724075,
+      "learning_rate": 1.7084282460136675e-06,
+      "loss": 0.0051,
+      "step": 11250
+    },
+    {
+      "epoch": 6.43507972665148,
+      "grad_norm": 0.11851054430007935,
+      "learning_rate": 1.6270745200130167e-06,
+      "loss": 0.0046,
+      "step": 11300
+    },
+    {
+      "epoch": 6.4635535307517085,
+      "grad_norm": 0.09247086197137833,
+      "learning_rate": 1.5457207940123657e-06,
+      "loss": 0.0049,
+      "step": 11350
+    },
+    {
+      "epoch": 6.492027334851937,
+      "grad_norm": 0.002555207349359989,
+      "learning_rate": 1.464367068011715e-06,
+      "loss": 0.0026,
+      "step": 11400
+    },
+    {
+      "epoch": 6.520501138952164,
+      "grad_norm": 3.7294840812683105,
+      "learning_rate": 1.3830133420110642e-06,
+      "loss": 0.0014,
+      "step": 11450
+    },
+    {
+      "epoch": 6.548974943052392,
+      "grad_norm": 0.00703430688008666,
+      "learning_rate": 1.3016596160104134e-06,
+      "loss": 0.0035,
+      "step": 11500
+    },
+    {
+      "epoch": 6.577448747152619,
+      "grad_norm": 12.061240196228027,
+      "learning_rate": 1.2203058900097624e-06,
+      "loss": 0.0078,
+      "step": 11550
+    },
+    {
+      "epoch": 6.605922551252847,
+      "grad_norm": 0.011964640580117702,
+      "learning_rate": 1.1389521640091117e-06,
+      "loss": 0.0024,
+      "step": 11600
+    },
+    {
+      "epoch": 6.634396355353076,
+      "grad_norm": 0.014603933319449425,
+      "learning_rate": 1.057598438008461e-06,
+      "loss": 0.0072,
+      "step": 11650
+    },
+    {
+      "epoch": 6.662870159453303,
+      "grad_norm": 0.026642296463251114,
+      "learning_rate": 9.7624471200781e-07,
+      "loss": 0.0007,
+      "step": 11700
+    },
+    {
+      "epoch": 6.691343963553531,
+      "grad_norm": 3.3646230697631836,
+      "learning_rate": 8.948909860071591e-07,
+      "loss": 0.0046,
+      "step": 11750
+    },
+    {
+      "epoch": 6.719817767653758,
+      "grad_norm": 0.027053840458393097,
+      "learning_rate": 8.135372600065084e-07,
+      "loss": 0.0031,
+      "step": 11800
+    },
+    {
+      "epoch": 6.748291571753986,
+      "grad_norm": 2.6146697998046875,
+      "learning_rate": 7.321835340058575e-07,
+      "loss": 0.003,
+      "step": 11850
+    },
+    {
+      "epoch": 6.776765375854215,
+      "grad_norm": 8.964512825012207,
+      "learning_rate": 6.508298080052067e-07,
+      "loss": 0.0069,
+      "step": 11900
+    },
+    {
+      "epoch": 6.805239179954442,
+      "grad_norm": 0.3086203932762146,
+      "learning_rate": 5.694760820045558e-07,
+      "loss": 0.0035,
+      "step": 11950
+    },
+    {
+      "epoch": 6.83371298405467,
+      "grad_norm": 0.018831729888916016,
+      "learning_rate": 4.88122356003905e-07,
+      "loss": 0.0033,
+      "step": 12000
+    },
+    {
+      "epoch": 6.862186788154897,
+      "grad_norm": 0.0018483272287994623,
+      "learning_rate": 4.067686300032542e-07,
+      "loss": 0.0022,
+      "step": 12050
+    },
+    {
+      "epoch": 6.890660592255125,
+      "grad_norm": 0.003242627950385213,
+      "learning_rate": 3.2541490400260336e-07,
+      "loss": 0.0043,
+      "step": 12100
+    },
+    {
+      "epoch": 6.9191343963553535,
+      "grad_norm": 0.002707740291953087,
+      "learning_rate": 2.440611780019525e-07,
+      "loss": 0.0017,
+      "step": 12150
+    },
+    {
+      "epoch": 6.947608200455581,
+      "grad_norm": 0.21824024617671967,
+      "learning_rate": 1.6270745200130168e-07,
+      "loss": 0.0069,
+      "step": 12200
+    },
+    {
+      "epoch": 6.976082004555809,
+      "grad_norm": 0.008130647242069244,
+      "learning_rate": 8.135372600065084e-08,
+      "loss": 0.0047,
+      "step": 12250
+    },
+    {
+      "epoch": 7.0,
+      "eval_f1": 0.9563834240267894,
+      "eval_loss": 0.052909377962350845,
+      "eval_precision": 0.9515242378810594,
+      "eval_recall": 0.9612924941097274,
+      "eval_runtime": 3.7426,
+      "eval_samples_per_second": 868.392,
+      "eval_steps_per_second": 108.749,
+      "step": 12292
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 12292,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 2418024281348142.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-12292/training_args.bin b/checkpoint-12292/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5883d1e2ddb42c11dd6ad1fddc79d9ffe7a246f3
--- /dev/null
+++ b/checkpoint-12292/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e08f60c5260f286c88c6054e532ee0950cb5316081a3a51d07b57f6a266f71
+size 5368
diff --git a/checkpoint-1756/config.json b/checkpoint-1756/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f744ab25e17fedaffadd5fcb3ae10a7b9e4083bc
--- /dev/null
+++ b/checkpoint-1756/config.json
@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}
diff --git a/checkpoint-1756/model.safetensors b/checkpoint-1756/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f121f2424aa7a655a0871d95aaa5fad0f5d8d335
--- /dev/null
+++ b/checkpoint-1756/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b877b1e180a68933eb90e92f3711348a19892e9e1c0e85f1c0c0ac31c900843d
+size 1109863956
diff --git a/checkpoint-1756/optimizer.pt b/checkpoint-1756/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..45d234243e949de2365398c42097e7367d2a74a6
--- /dev/null
+++ b/checkpoint-1756/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2787580e6c0160af6a4dc99a4e9ce84ae377ab3d6296a6416012dc8df5bfbdf
+size 2219846202
diff --git a/checkpoint-1756/rng_state.pth b/checkpoint-1756/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2e4a785ea487beecc8e27e32e602c17c6df96196
--- /dev/null
+++ b/checkpoint-1756/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c3bcda270a9bbdc01c80b4119b83fd5b30aca083ec25b4059eed0da02a64608
+size 14244
diff --git a/checkpoint-1756/scaler.pt b/checkpoint-1756/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..34c11e9fa5110e65e1f00e540985dc9a22ea37ae
--- /dev/null
+++ b/checkpoint-1756/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d81f85e057ecf3b4e4481a5b7b37c25917c66b4c3f8f132282d8a277499dbbb3
+size 988
diff --git a/checkpoint-1756/scheduler.pt b/checkpoint-1756/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..80b73ee68a100ec723df1b6bbbe216ea6c9f871e
--- /dev/null
+++ b/checkpoint-1756/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9284fedcb9e147844c4eb634bfce0b54551832557512f611ba8e58c50ee1d23f
+size 1064
diff --git a/checkpoint-1756/special_tokens_map.json b/checkpoint-1756/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..d79c0fe029062eb03708803e72c3483296e2ea97
--- /dev/null
+++ b/checkpoint-1756/special_tokens_map.json
@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-1756/tokenizer.json b/checkpoint-1756/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..7126b1d228f6e5f725b6ee02a88b1118c725aeed
--- /dev/null
+++ b/checkpoint-1756/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734
diff --git a/checkpoint-1756/tokenizer_config.json b/checkpoint-1756/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d297107d53da62483767139822cf5ed3a6975e24
--- /dev/null
+++ b/checkpoint-1756/tokenizer_config.json
@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-1756/trainer_state.json b/checkpoint-1756/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..51d204ab54aff0dca513bb07660dbc448980a364
--- /dev/null
+++ b/checkpoint-1756/trainer_state.json
@@ -0,0 +1,290 @@
+{
+  "best_global_step": 1756,
+  "best_metric": 0.9242246437552389,
+  "best_model_checkpoint": "C:\\Users\\Shara\\projects\\models\\run_16-lr_2e-05-acc_1-wd_0.01-bs_8-ep_7\\checkpoint-1756",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1756,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02847380410022779,
+      "grad_norm": 4.8302321434021,
+      "learning_rate": 1.992840872111943e-05,
+      "loss": 0.9994,
+      "step": 50
+    },
+    {
+      "epoch": 0.05694760820045558,
+      "grad_norm": 3.4978649616241455,
+      "learning_rate": 1.9847054995118778e-05,
+      "loss": 0.3939,
+      "step": 100
+    },
+    {
+      "epoch": 0.08542141230068337,
+      "grad_norm": 8.353672981262207,
+      "learning_rate": 1.9765701269118128e-05,
+      "loss": 0.2882,
+      "step": 150
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "grad_norm": 9.822871208190918,
+      "learning_rate": 1.9684347543117477e-05,
+      "loss": 0.1728,
+      "step": 200
+    },
+    {
+      "epoch": 0.14236902050113895,
+      "grad_norm": 3.1411221027374268,
+      "learning_rate": 1.9602993817116827e-05,
+      "loss": 0.1251,
+      "step": 250
+    },
+    {
+      "epoch": 0.17084282460136674,
+      "grad_norm": 8.493424415588379,
+      "learning_rate": 1.9521640091116173e-05,
+      "loss": 0.1405,
+      "step": 300
+    },
+    {
+      "epoch": 0.19931662870159453,
+      "grad_norm": 4.757007122039795,
+      "learning_rate": 1.9440286365115523e-05,
+      "loss": 0.1431,
+      "step": 350
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "grad_norm": 4.339049816131592,
+      "learning_rate": 1.9358932639114873e-05,
+      "loss": 0.0912,
+      "step": 400
+    },
+    {
+      "epoch": 0.25626423690205014,
+      "grad_norm": 14.540772438049316,
+      "learning_rate": 1.9277578913114222e-05,
+      "loss": 0.1048,
+      "step": 450
+    },
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 10.503073692321777,
+      "learning_rate": 1.9196225187113572e-05,
+      "loss": 0.1224,
+      "step": 500
+    },
+    {
+      "epoch": 0.3132118451025057,
+      "grad_norm": 2.738131284713745,
+      "learning_rate": 1.911487146111292e-05,
+      "loss": 0.1025,
+      "step": 550
+    },
+    {
+      "epoch": 0.3416856492027335,
+      "grad_norm": 6.681102752685547,
+      "learning_rate": 1.903351773511227e-05,
+      "loss": 0.0869,
+      "step": 600
+    },
+    {
+      "epoch": 0.3701594533029613,
+      "grad_norm": 1.4330339431762695,
+      "learning_rate": 1.895216400911162e-05,
+      "loss": 0.052,
+      "step": 650
+    },
+    {
+      "epoch": 0.39863325740318906,
+      "grad_norm": 2.581470012664795,
+      "learning_rate": 1.8870810283110967e-05,
+      "loss": 0.0808,
+      "step": 700
+    },
+    {
+      "epoch": 0.4271070615034169,
+      "grad_norm": 5.825100898742676,
+      "learning_rate": 1.8789456557110317e-05,
+      "loss": 0.0716,
+      "step": 750
+    },
+    {
+      "epoch": 0.45558086560364464,
+      "grad_norm": 1.74166738986969,
+      "learning_rate": 1.8708102831109666e-05,
+      "loss": 0.0806,
+      "step": 800
+    },
+    {
+      "epoch": 0.48405466970387245,
+      "grad_norm": 7.3097405433654785,
+      "learning_rate": 1.8626749105109016e-05,
+      "loss": 0.0666,
+      "step": 850
+    },
+    {
+      "epoch": 0.5125284738041003,
+      "grad_norm": 2.220766067504883,
+      "learning_rate": 1.8545395379108362e-05,
+      "loss": 0.0768,
+      "step": 900
+    },
+    {
+      "epoch": 0.541002277904328,
+      "grad_norm": 4.0566511154174805,
+      "learning_rate": 1.8464041653107715e-05,
+      "loss": 0.0707,
+      "step": 950
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.2833240330219269,
+      "learning_rate": 1.8382687927107065e-05,
+      "loss": 0.0858,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5979498861047836,
+      "grad_norm": 21.131481170654297,
+      "learning_rate": 1.8301334201106415e-05,
+      "loss": 0.0595,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6264236902050114,
+      "grad_norm": 27.655433654785156,
+      "learning_rate": 1.821998047510576e-05,
+      "loss": 0.0466,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6548974943052391,
+      "grad_norm": 3.4721717834472656,
+      "learning_rate": 1.813862674910511e-05,
+      "loss": 0.0776,
+      "step": 1150
+    },
+    {
+      "epoch": 0.683371298405467,
+      "grad_norm": 2.4811441898345947,
+      "learning_rate": 1.805727302310446e-05,
+      "loss": 0.0647,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7118451025056948,
+      "grad_norm": 6.169066429138184,
+      "learning_rate": 1.797591929710381e-05,
+      "loss": 0.0724,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7403189066059226,
+      "grad_norm": 8.984748840332031,
+      "learning_rate": 1.7894565571103156e-05,
+      "loss": 0.0838,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7687927107061503,
+      "grad_norm": 5.944505214691162,
+      "learning_rate": 1.7813211845102506e-05,
+      "loss": 0.0683,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7972665148063781,
+      "grad_norm": 0.28812381625175476,
+      "learning_rate": 1.7731858119101856e-05,
+      "loss": 0.0614,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8257403189066059,
+      "grad_norm": 6.176011085510254,
+      "learning_rate": 1.7650504393101205e-05,
+      "loss": 0.0615,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8542141230068337,
+      "grad_norm": 2.5244405269622803,
+      "learning_rate": 1.7569150667100555e-05,
+      "loss": 0.0714,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8826879271070615,
+      "grad_norm": 3.3508074283599854,
+      "learning_rate": 1.7487796941099904e-05,
+      "loss": 0.0563,
+      "step": 1550
+    },
+    {
+      "epoch": 0.9111617312072893,
+      "grad_norm": 9.980842590332031,
+      "learning_rate": 1.7406443215099254e-05,
+      "loss": 0.0647,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9396355353075171,
+      "grad_norm": 3.6959774494171143,
+      "learning_rate": 1.7325089489098604e-05,
+      "loss": 0.0682,
+      "step": 1650
+    },
+    {
+      "epoch": 0.9681093394077449,
+      "grad_norm": 0.626620888710022,
+      "learning_rate": 1.724373576309795e-05,
+      "loss": 0.0499,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9965831435079726,
+      "grad_norm": 7.145672798156738,
+      "learning_rate": 1.71623820370973e-05,
+      "loss": 0.0569,
+      "step": 1750
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9242246437552389,
+      "eval_loss": 0.05600914731621742,
+      "eval_precision": 0.9206746826987308,
+      "eval_recall": 0.927802086839448,
+      "eval_runtime": 3.7538,
+      "eval_samples_per_second": 865.798,
+      "eval_steps_per_second": 108.425,
+      "step": 1756
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 12292,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 344842189594686.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1756/training_args.bin b/checkpoint-1756/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5883d1e2ddb42c11dd6ad1fddc79d9ffe7a246f3
--- /dev/null
+++ b/checkpoint-1756/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e08f60c5260f286c88c6054e532ee0950cb5316081a3a51d07b57f6a266f71
+size 5368
diff --git a/checkpoint-3512/config.json b/checkpoint-3512/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f744ab25e17fedaffadd5fcb3ae10a7b9e4083bc
--- /dev/null
+++ b/checkpoint-3512/config.json
@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}
diff --git a/checkpoint-3512/model.safetensors b/checkpoint-3512/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..313a8e9862204486b6fea2181fe31337e42c5e75
--- /dev/null
+++ b/checkpoint-3512/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbcca6c4d038a5447fa9bf8ac31d433d751923346e36fedb24008cd64521f50
+size 1109863956
diff --git a/checkpoint-3512/optimizer.pt b/checkpoint-3512/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e8d01dba71e58c0890bd4580995e74344c17db9f
--- /dev/null
+++ b/checkpoint-3512/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f038c2d0551d74e2318c48245eab9294694194b187f0a6c8635336b32a4a3845
+size 2219846202
diff --git a/checkpoint-3512/rng_state.pth b/checkpoint-3512/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..93182b1d7b742d2ace5e6d0ef54bed007f67ce0b
--- /dev/null
+++ b/checkpoint-3512/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da10cefa2cb8a2be8114fc291a5c55cb96e1047f75b823fc7fb82422f79ce2f
+size 14244
diff --git a/checkpoint-3512/scaler.pt b/checkpoint-3512/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7fb15881a7d7c21f1415df4343a484353802a2b0
--- /dev/null
+++ b/checkpoint-3512/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bcbd0d9500d8ef0ef7916a5d9e57b44de8cfee243837f363bfae8f0865c9c6
+size 988
diff --git a/checkpoint-3512/scheduler.pt b/checkpoint-3512/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..984b272c57f991e685ebad10e1bb86ee8f11287f
--- /dev/null
+++ b/checkpoint-3512/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe09b89711b4ddfda2986487d23873a7e0ee48f39bf17155748cec806279077
+size 1064
diff --git a/checkpoint-3512/special_tokens_map.json b/checkpoint-3512/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..d79c0fe029062eb03708803e72c3483296e2ea97
--- /dev/null
+++ b/checkpoint-3512/special_tokens_map.json
@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-3512/tokenizer.json b/checkpoint-3512/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..7126b1d228f6e5f725b6ee02a88b1118c725aeed
--- /dev/null
+++ b/checkpoint-3512/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734
diff --git a/checkpoint-3512/tokenizer_config.json b/checkpoint-3512/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d297107d53da62483767139822cf5ed3a6975e24
--- /dev/null
+++ b/checkpoint-3512/tokenizer_config.json
@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-3512/trainer_state.json b/checkpoint-3512/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..2fedb337bdaacc0efd9713b1d6dc2389907d8e06
--- /dev/null
+++ b/checkpoint-3512/trainer_state.json
@@ -0,0 +1,546 @@
+{
+  "best_global_step": 3512,
+  "best_metric": 0.9406438631790744,
+  "best_model_checkpoint": "C:\\Users\\Shara\\projects\\models\\run_16-lr_2e-05-acc_1-wd_0.01-bs_8-ep_7\\checkpoint-3512",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3512,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02847380410022779,
+      "grad_norm": 4.8302321434021,
+      "learning_rate": 1.992840872111943e-05,
+      "loss": 0.9994,
+      "step": 50
+    },
+    {
+      "epoch": 0.05694760820045558,
+      "grad_norm": 3.4978649616241455,
+      "learning_rate": 1.9847054995118778e-05,
+      "loss": 0.3939,
+      "step": 100
+    },
+    {
+      "epoch": 0.08542141230068337,
+      "grad_norm": 8.353672981262207,
+      "learning_rate": 1.9765701269118128e-05,
+      "loss": 0.2882,
+      "step": 150
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "grad_norm": 9.822871208190918,
+      "learning_rate": 1.9684347543117477e-05,
+      "loss": 0.1728,
+      "step": 200
+    },
+    {
+      "epoch": 0.14236902050113895,
+      "grad_norm": 3.1411221027374268,
+      "learning_rate": 1.9602993817116827e-05,
+      "loss": 0.1251,
+      "step": 250
+    },
+    {
+      "epoch": 0.17084282460136674,
+      "grad_norm": 8.493424415588379,
+      "learning_rate": 1.9521640091116173e-05,
+      "loss": 0.1405,
+      "step": 300
+    },
+    {
+      "epoch": 0.19931662870159453,
+      "grad_norm": 4.757007122039795,
+      "learning_rate": 1.9440286365115523e-05,
+      "loss": 0.1431,
+      "step": 350
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "grad_norm": 4.339049816131592,
+      "learning_rate": 1.9358932639114873e-05,
+      "loss": 0.0912,
+      "step": 400
+    },
+    {
+      "epoch": 0.25626423690205014,
+      "grad_norm": 14.540772438049316,
+      "learning_rate": 1.9277578913114222e-05,
+      "loss": 0.1048,
+      "step": 450
+    },
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 10.503073692321777,
+      "learning_rate": 1.9196225187113572e-05,
+      "loss": 0.1224,
+      "step": 500
+    },
+    {
+      "epoch": 0.3132118451025057,
+      "grad_norm": 2.738131284713745,
+      "learning_rate": 1.911487146111292e-05,
+      "loss": 0.1025,
+      "step": 550
+    },
+    {
+      "epoch": 0.3416856492027335,
+      "grad_norm": 6.681102752685547,
+      "learning_rate": 1.903351773511227e-05,
+      "loss": 0.0869,
+      "step": 600
+    },
+    {
+      "epoch": 0.3701594533029613,
+      "grad_norm": 1.4330339431762695,
+      "learning_rate": 1.895216400911162e-05,
+      "loss": 0.052,
+      "step": 650
+    },
+    {
+      "epoch": 0.39863325740318906,
+      "grad_norm": 2.581470012664795,
+      "learning_rate": 1.8870810283110967e-05,
+      "loss": 0.0808,
+      "step": 700
+    },
+    {
+      "epoch": 0.4271070615034169,
+      "grad_norm": 5.825100898742676,
+      "learning_rate": 1.8789456557110317e-05,
+      "loss": 0.0716,
+      "step": 750
+    },
+    {
+      "epoch": 0.45558086560364464,
+      "grad_norm": 1.74166738986969,
+      "learning_rate": 1.8708102831109666e-05,
+      "loss": 0.0806,
+      "step": 800
+    },
+    {
+      "epoch": 0.48405466970387245,
+      "grad_norm": 7.3097405433654785,
+      "learning_rate": 1.8626749105109016e-05,
+      "loss": 0.0666,
+      "step": 850
+    },
+    {
+      "epoch": 0.5125284738041003,
+      "grad_norm": 2.220766067504883,
+      "learning_rate": 1.8545395379108362e-05,
+      "loss": 0.0768,
+      "step": 900
+    },
+    {
+      "epoch": 0.541002277904328,
+      "grad_norm": 4.0566511154174805,
+      "learning_rate": 1.8464041653107715e-05,
+      "loss": 0.0707,
+      "step": 950
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.2833240330219269,
+      "learning_rate": 1.8382687927107065e-05,
+      "loss": 0.0858,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5979498861047836,
+      "grad_norm": 21.131481170654297,
+      "learning_rate": 1.8301334201106415e-05,
+      "loss": 0.0595,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6264236902050114,
+      "grad_norm": 27.655433654785156,
+      "learning_rate": 1.821998047510576e-05,
+      "loss": 0.0466,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6548974943052391,
+      "grad_norm": 3.4721717834472656,
+      "learning_rate": 1.813862674910511e-05,
+      "loss": 0.0776,
+      "step": 1150
+    },
+    {
+      "epoch": 0.683371298405467,
+      "grad_norm": 2.4811441898345947,
+      "learning_rate": 1.805727302310446e-05,
+      "loss": 0.0647,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7118451025056948,
+      "grad_norm": 6.169066429138184,
+      "learning_rate": 1.797591929710381e-05,
+      "loss": 0.0724,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7403189066059226,
+      "grad_norm": 8.984748840332031,
+      "learning_rate": 1.7894565571103156e-05,
+      "loss": 0.0838,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7687927107061503,
+      "grad_norm": 5.944505214691162,
+      "learning_rate": 1.7813211845102506e-05,
+      "loss": 0.0683,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7972665148063781,
+      "grad_norm": 0.28812381625175476,
+      "learning_rate": 1.7731858119101856e-05,
+      "loss": 0.0614,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8257403189066059,
+      "grad_norm": 6.176011085510254,
+      "learning_rate": 1.7650504393101205e-05,
+      "loss": 0.0615,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8542141230068337,
+      "grad_norm": 2.5244405269622803,
+      "learning_rate": 1.7569150667100555e-05,
+      "loss": 0.0714,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8826879271070615,
+      "grad_norm": 3.3508074283599854,
+      "learning_rate": 1.7487796941099904e-05,
+      "loss": 0.0563,
+      "step": 1550
+    },
+    {
+      "epoch": 0.9111617312072893,
+      "grad_norm": 9.980842590332031,
+      "learning_rate": 1.7406443215099254e-05,
+      "loss": 0.0647,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9396355353075171,
+      "grad_norm": 3.6959774494171143,
+      "learning_rate": 1.7325089489098604e-05,
+      "loss": 0.0682,
+      "step": 1650
+    },
+    {
+      "epoch": 0.9681093394077449,
+      "grad_norm": 0.626620888710022,
+      "learning_rate": 1.724373576309795e-05,
+      "loss": 0.0499,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9965831435079726,
+      "grad_norm": 7.145672798156738,
+      "learning_rate": 1.71623820370973e-05,
+      "loss": 0.0569,
+      "step": 1750
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9242246437552389,
+      "eval_loss": 0.05600914731621742,
+      "eval_precision": 0.9206746826987308,
+      "eval_recall": 0.927802086839448,
+      "eval_runtime": 3.7538,
+      "eval_samples_per_second": 865.798,
+      "eval_steps_per_second": 108.425,
+      "step": 1756
+    },
+    {
+      "epoch": 1.0250569476082005,
+      "grad_norm": 4.280463695526123,
+      "learning_rate": 1.708102831109665e-05,
+      "loss": 0.0673,
+      "step": 1800
+    },
+    {
+      "epoch": 1.0535307517084282,
+      "grad_norm": 0.06692535430192947,
+      "learning_rate": 1.6999674585096e-05,
+      "loss": 0.0403,
+      "step": 1850
+    },
+    {
+      "epoch": 1.082004555808656,
+      "grad_norm": 0.03789375349879265,
+      "learning_rate": 1.691832085909535e-05,
+      "loss": 0.0496,
+      "step": 1900
+    },
+    {
+      "epoch": 1.1104783599088839,
+      "grad_norm": 3.698348045349121,
+      "learning_rate": 1.6836967133094698e-05,
+      "loss": 0.0381,
+      "step": 1950
+    },
+    {
+      "epoch": 1.1389521640091116,
+      "grad_norm": 2.753032684326172,
+      "learning_rate": 1.6755613407094048e-05,
+      "loss": 0.0432,
+      "step": 2000
+    },
+    {
+      "epoch": 1.1674259681093395,
+      "grad_norm": 0.06336130946874619,
+      "learning_rate": 1.6674259681093398e-05,
+      "loss": 0.0482,
+      "step": 2050
+    },
+    {
+      "epoch": 1.1958997722095672,
+      "grad_norm": 3.9503254890441895,
+      "learning_rate": 1.6592905955092744e-05,
+      "loss": 0.0436,
+      "step": 2100
+    },
+    {
+      "epoch": 1.224373576309795,
+      "grad_norm": 0.08679741621017456,
+      "learning_rate": 1.6511552229092093e-05,
+      "loss": 0.0346,
+      "step": 2150
+    },
+    {
+      "epoch": 1.2528473804100229,
+      "grad_norm": 2.1995127201080322,
+      "learning_rate": 1.6430198503091443e-05,
+      "loss": 0.0312,
+      "step": 2200
+    },
+    {
+      "epoch": 1.2813211845102506,
+      "grad_norm": 5.7709808349609375,
+      "learning_rate": 1.634884477709079e-05,
+      "loss": 0.032,
+      "step": 2250
+    },
+    {
+      "epoch": 1.3097949886104785,
+      "grad_norm": 0.2031829059123993,
+      "learning_rate": 1.626749105109014e-05,
+      "loss": 0.053,
+      "step": 2300
+    },
+    {
+      "epoch": 1.3382687927107062,
+      "grad_norm": 4.292157173156738,
+      "learning_rate": 1.6186137325089492e-05,
+      "loss": 0.0413,
+      "step": 2350
+    },
+    {
+      "epoch": 1.366742596810934,
+      "grad_norm": 0.07821401953697205,
+      "learning_rate": 1.6104783599088842e-05,
+      "loss": 0.0304,
+      "step": 2400
+    },
+    {
+      "epoch": 1.3952164009111616,
+      "grad_norm": 0.5930206179618835,
+      "learning_rate": 1.6023429873088188e-05,
+      "loss": 0.0525,
+      "step": 2450
+    },
+    {
+      "epoch": 1.4236902050113895,
+      "grad_norm": 1.6114712953567505,
+      "learning_rate": 1.5942076147087538e-05,
+      "loss": 0.0391,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4521640091116172,
+      "grad_norm": 0.28632065653800964,
+      "learning_rate": 1.5860722421086887e-05,
+      "loss": 0.0491,
+      "step": 2550
+    },
+    {
+      "epoch": 1.4806378132118452,
+      "grad_norm": 1.0017669200897217,
+      "learning_rate": 1.5779368695086237e-05,
+      "loss": 0.0395,
+      "step": 2600
+    },
+    {
+      "epoch": 1.5091116173120729,
+      "grad_norm": 0.03409272059798241,
+      "learning_rate": 1.5698014969085583e-05,
+      "loss": 0.0399,
+      "step": 2650
+    },
+    {
+      "epoch": 1.5375854214123006,
+      "grad_norm": 3.5108702182769775,
+      "learning_rate": 1.5616661243084933e-05,
+      "loss": 0.0424,
+      "step": 2700
+    },
+    {
+      "epoch": 1.5660592255125285,
+      "grad_norm": 3.5875349044799805,
+      "learning_rate": 1.5535307517084283e-05,
+      "loss": 0.0497,
+      "step": 2750
+    },
+    {
+      "epoch": 1.5945330296127562,
+      "grad_norm": 0.10498251020908356,
+      "learning_rate": 1.5453953791083632e-05,
+      "loss": 0.0461,
+      "step": 2800
+    },
+    {
+      "epoch": 1.6230068337129842,
+      "grad_norm": 7.618963718414307,
+      "learning_rate": 1.5374227139602996e-05,
+      "loss": 0.0394,
+      "step": 2850
+    },
+    {
+      "epoch": 1.6514806378132119,
+      "grad_norm": 3.3920793533325195,
+      "learning_rate": 1.5292873413602346e-05,
+      "loss": 0.0339,
+      "step": 2900
+    },
+    {
+      "epoch": 1.6799544419134396,
+      "grad_norm": 0.04736129939556122,
+      "learning_rate": 1.5211519687601692e-05,
+      "loss": 0.0358,
+      "step": 2950
+    },
+    {
+      "epoch": 1.7084282460136673,
+      "grad_norm": 0.17463508248329163,
+      "learning_rate": 1.5130165961601042e-05,
+      "loss": 0.034,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7369020501138952,
+      "grad_norm": 0.058148205280303955,
+      "learning_rate": 1.5048812235600392e-05,
+      "loss": 0.0317,
+      "step": 3050
+    },
+    {
+      "epoch": 1.7653758542141231,
+      "grad_norm": 3.5262815952301025,
+      "learning_rate": 1.4967458509599741e-05,
+      "loss": 0.0477,
+      "step": 3100
+    },
+    {
+      "epoch": 1.7938496583143508,
+      "grad_norm": 2.971937894821167,
+      "learning_rate": 1.488610478359909e-05,
+      "loss": 0.0364,
+      "step": 3150
+    },
+    {
+      "epoch": 1.8223234624145785,
+      "grad_norm": 0.05181724950671196,
+      "learning_rate": 1.4804751057598439e-05,
+      "loss": 0.0394,
+      "step": 3200
+    },
+    {
+      "epoch": 1.8507972665148062,
+      "grad_norm": 0.2712370455265045,
+      "learning_rate": 1.4723397331597789e-05,
+      "loss": 0.0456,
+      "step": 3250
+    },
+    {
+      "epoch": 1.8792710706150342,
+      "grad_norm": 1.608622431755066,
+      "learning_rate": 1.4642043605597138e-05,
+      "loss": 0.05,
+      "step": 3300
+    },
+    {
+      "epoch": 1.907744874715262,
+      "grad_norm": 5.2423529624938965,
+      "learning_rate": 1.4560689879596486e-05,
+      "loss": 0.0371,
+      "step": 3350
+    },
+    {
+      "epoch": 1.9362186788154898,
+      "grad_norm": 0.04786211624741554,
+      "learning_rate": 1.4479336153595836e-05,
+      "loss": 0.0329,
+      "step": 3400
+    },
+    {
+      "epoch": 1.9646924829157175,
+      "grad_norm": 0.5264931917190552,
+      "learning_rate": 1.4397982427595185e-05,
+      "loss": 0.0379,
+      "step": 3450
+    },
+    {
+      "epoch": 1.9931662870159452,
+      "grad_norm": 0.236006498336792,
+      "learning_rate": 1.4316628701594535e-05,
+      "loss": 0.0253,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9406438631790744,
+      "eval_loss": 0.05223705992102623,
+      "eval_precision": 0.9371867691279653,
+      "eval_recall": 0.9441265567149109,
+      "eval_runtime": 3.7109,
+      "eval_samples_per_second": 875.791,
+      "eval_steps_per_second": 109.676,
+      "step": 3512
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 12292,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 688219085312226.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-3512/training_args.bin b/checkpoint-3512/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5883d1e2ddb42c11dd6ad1fddc79d9ffe7a246f3
--- /dev/null
+++ b/checkpoint-3512/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e08f60c5260f286c88c6054e532ee0950cb5316081a3a51d07b57f6a266f71
+size 5368
diff --git a/checkpoint-5268/config.json b/checkpoint-5268/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f744ab25e17fedaffadd5fcb3ae10a7b9e4083bc
--- /dev/null
+++ b/checkpoint-5268/config.json
@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}
diff --git a/checkpoint-5268/model.safetensors b/checkpoint-5268/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6278018a10dbc950921e5aff5aa6d52d55d72631
--- /dev/null
+++ b/checkpoint-5268/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b786779ce4d72c2e34b9d4fc244b422821fb82aa9e9496830a4f8a217e8633f
+size 1109863956
diff --git a/checkpoint-5268/optimizer.pt b/checkpoint-5268/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6f47adbdea25d744f76f78fa72edb2103c8316c5
--- /dev/null
+++ b/checkpoint-5268/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d411b3ef7b4d64bdb57d539abb0b4f6f1d8c12b5b8383a2c868aac083b2256
+size 2219846202
diff --git a/checkpoint-5268/rng_state.pth b/checkpoint-5268/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..487bb1bad91d9f8e0bac712686bc5cb8b807c6a0
--- /dev/null
+++ b/checkpoint-5268/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773a0f008a7607f68cb3da99962235e5d2984b9344734097cf3b25025846c9bc
+size 14244
diff --git a/checkpoint-5268/scaler.pt b/checkpoint-5268/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..380b7d46ced03a6d1881df6ad74a8dbc8579698b
--- /dev/null
+++ b/checkpoint-5268/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a3533b1927eb7f3b5998624c4eb9b6aa2b02868d4fa466b42a5c27cecc77725
+size 988
diff --git a/checkpoint-5268/scheduler.pt b/checkpoint-5268/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..63eb71b1f0c4efc69d0ed226e84cf0db661e5459
--- /dev/null
+++ b/checkpoint-5268/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3242de081a409069272234d53e25d7d851ad8ccef68c36b808d8d26d28a55496
+size 1064
diff --git a/checkpoint-5268/special_tokens_map.json b/checkpoint-5268/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..d79c0fe029062eb03708803e72c3483296e2ea97
--- /dev/null
+++ b/checkpoint-5268/special_tokens_map.json
@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-5268/tokenizer.json b/checkpoint-5268/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..7126b1d228f6e5f725b6ee02a88b1118c725aeed
--- /dev/null
+++ b/checkpoint-5268/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734
diff --git a/checkpoint-5268/tokenizer_config.json b/checkpoint-5268/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d297107d53da62483767139822cf5ed3a6975e24
--- /dev/null
+++ b/checkpoint-5268/tokenizer_config.json
@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-5268/trainer_state.json b/checkpoint-5268/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..55e6b1c68f49b3a0394295fbe4b375ef114f56fe
--- /dev/null
+++ b/checkpoint-5268/trainer_state.json
@@ -0,0 +1,802 @@
+{
+  "best_global_step": 5268,
+  "best_metric": 0.9470420646891236,
+  "best_model_checkpoint": "C:\\Users\\Shara\\projects\\models\\run_16-lr_2e-05-acc_1-wd_0.01-bs_8-ep_7\\checkpoint-5268",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 5268,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02847380410022779,
+      "grad_norm": 4.8302321434021,
+      "learning_rate": 1.992840872111943e-05,
+      "loss": 0.9994,
+      "step": 50
+    },
+    {
+      "epoch": 0.05694760820045558,
+      "grad_norm": 3.4978649616241455,
+      "learning_rate": 1.9847054995118778e-05,
+      "loss": 0.3939,
+      "step": 100
+    },
+    {
+      "epoch": 0.08542141230068337,
+      "grad_norm": 8.353672981262207,
+      "learning_rate": 1.9765701269118128e-05,
+      "loss": 0.2882,
+      "step": 150
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "grad_norm": 9.822871208190918,
+      "learning_rate": 1.9684347543117477e-05,
+      "loss": 0.1728,
+      "step": 200
+    },
+    {
+      "epoch": 0.14236902050113895,
+      "grad_norm": 3.1411221027374268,
+      "learning_rate": 1.9602993817116827e-05,
+      "loss": 0.1251,
+      "step": 250
+    },
+    {
+      "epoch": 0.17084282460136674,
+      "grad_norm": 8.493424415588379,
+      "learning_rate": 1.9521640091116173e-05,
+      "loss": 0.1405,
+      "step": 300
+    },
+    {
+      "epoch": 0.19931662870159453,
+      "grad_norm": 4.757007122039795,
+      "learning_rate": 1.9440286365115523e-05,
+      "loss": 0.1431,
+      "step": 350
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "grad_norm": 4.339049816131592,
+      "learning_rate": 1.9358932639114873e-05,
+      "loss": 0.0912,
+      "step": 400
+    },
+    {
+      "epoch": 0.25626423690205014,
+      "grad_norm": 14.540772438049316,
+      "learning_rate": 1.9277578913114222e-05,
+      "loss": 0.1048,
+      "step": 450
+    },
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 10.503073692321777,
+      "learning_rate": 1.9196225187113572e-05,
+      "loss": 0.1224,
+      "step": 500
+    },
+    {
+      "epoch": 0.3132118451025057,
+      "grad_norm": 2.738131284713745,
+      "learning_rate": 1.911487146111292e-05,
+      "loss": 0.1025,
+      "step": 550
+    },
+    {
+      "epoch": 0.3416856492027335,
+      "grad_norm": 6.681102752685547,
+      "learning_rate": 1.903351773511227e-05,
+      "loss": 0.0869,
+      "step": 600
+    },
+    {
+      "epoch": 0.3701594533029613,
+      "grad_norm": 1.4330339431762695,
+      "learning_rate": 1.895216400911162e-05,
+      "loss": 0.052,
+      "step": 650
+    },
+    {
+      "epoch": 0.39863325740318906,
+      "grad_norm": 2.581470012664795,
+      "learning_rate": 1.8870810283110967e-05,
+      "loss": 0.0808,
+      "step": 700
+    },
+    {
+      "epoch": 0.4271070615034169,
+      "grad_norm": 5.825100898742676,
+      "learning_rate": 1.8789456557110317e-05,
+      "loss": 0.0716,
+      "step": 750
+    },
+    {
+      "epoch": 0.45558086560364464,
+      "grad_norm": 1.74166738986969,
+      "learning_rate": 1.8708102831109666e-05,
+      "loss": 0.0806,
+      "step": 800
+    },
+    {
+      "epoch": 0.48405466970387245,
+      "grad_norm": 7.3097405433654785,
+      "learning_rate": 1.8626749105109016e-05,
+      "loss": 0.0666,
+      "step": 850
+    },
+    {
+      "epoch": 0.5125284738041003,
+      "grad_norm": 2.220766067504883,
+      "learning_rate": 1.8545395379108362e-05,
+      "loss": 0.0768,
+      "step": 900
+    },
+    {
+      "epoch": 0.541002277904328,
+      "grad_norm": 4.0566511154174805,
+      "learning_rate": 1.8464041653107715e-05,
+      "loss": 0.0707,
+      "step": 950
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.2833240330219269,
+      "learning_rate": 1.8382687927107065e-05,
+      "loss": 0.0858,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5979498861047836,
+      "grad_norm": 21.131481170654297,
+      "learning_rate": 1.8301334201106415e-05,
+      "loss": 0.0595,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6264236902050114,
+      "grad_norm": 27.655433654785156,
+      "learning_rate": 1.821998047510576e-05,
+      "loss": 0.0466,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6548974943052391,
+      "grad_norm": 3.4721717834472656,
+      "learning_rate": 1.813862674910511e-05,
+      "loss": 0.0776,
+      "step": 1150
+    },
+    {
+      "epoch": 0.683371298405467,
+      "grad_norm": 2.4811441898345947,
+      "learning_rate": 1.805727302310446e-05,
+      "loss": 0.0647,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7118451025056948,
+      "grad_norm": 6.169066429138184,
+      "learning_rate": 1.797591929710381e-05,
+      "loss": 0.0724,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7403189066059226,
+      "grad_norm": 8.984748840332031,
+      "learning_rate": 1.7894565571103156e-05,
+      "loss": 0.0838,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7687927107061503,
+      "grad_norm": 5.944505214691162,
+      "learning_rate": 1.7813211845102506e-05,
+      "loss": 0.0683,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7972665148063781,
+      "grad_norm": 0.28812381625175476,
+      "learning_rate": 1.7731858119101856e-05,
+      "loss": 0.0614,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8257403189066059,
+      "grad_norm": 6.176011085510254,
+      "learning_rate": 1.7650504393101205e-05,
+      "loss": 0.0615,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8542141230068337,
+      "grad_norm": 2.5244405269622803,
+      "learning_rate": 1.7569150667100555e-05,
+      "loss": 0.0714,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8826879271070615,
+      "grad_norm": 3.3508074283599854,
+      "learning_rate": 1.7487796941099904e-05,
+      "loss": 0.0563,
+      "step": 1550
+    },
+    {
+      "epoch": 0.9111617312072893,
+      "grad_norm": 9.980842590332031,
+      "learning_rate": 1.7406443215099254e-05,
+      "loss": 0.0647,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9396355353075171,
+      "grad_norm": 3.6959774494171143,
+      "learning_rate": 1.7325089489098604e-05,
+      "loss": 0.0682,
+      "step": 1650
+    },
+    {
+      "epoch": 0.9681093394077449,
+      "grad_norm": 0.626620888710022,
+      "learning_rate": 1.724373576309795e-05,
+      "loss": 0.0499,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9965831435079726,
+      "grad_norm": 7.145672798156738,
+      "learning_rate": 1.71623820370973e-05,
+      "loss": 0.0569,
+      "step": 1750
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9242246437552389,
+      "eval_loss": 0.05600914731621742,
+      "eval_precision": 0.9206746826987308,
+      "eval_recall": 0.927802086839448,
+      "eval_runtime": 3.7538,
+      "eval_samples_per_second": 865.798,
+      "eval_steps_per_second": 108.425,
+      "step": 1756
+    },
+    {
+      "epoch": 1.0250569476082005,
+      "grad_norm": 4.280463695526123,
+      "learning_rate": 1.708102831109665e-05,
+      "loss": 0.0673,
+      "step": 1800
+    },
+    {
+      "epoch": 1.0535307517084282,
+      "grad_norm": 0.06692535430192947,
+      "learning_rate": 1.6999674585096e-05,
+      "loss": 0.0403,
+      "step": 1850
+    },
+    {
+      "epoch": 1.082004555808656,
+      "grad_norm": 0.03789375349879265,
+      "learning_rate": 1.691832085909535e-05,
+      "loss": 0.0496,
+      "step": 1900
+    },
+    {
+      "epoch": 1.1104783599088839,
+      "grad_norm": 3.698348045349121,
+      "learning_rate": 1.6836967133094698e-05,
+      "loss": 0.0381,
+      "step": 1950
+    },
+    {
+      "epoch": 1.1389521640091116,
+      "grad_norm": 2.753032684326172,
+      "learning_rate": 1.6755613407094048e-05,
+      "loss": 0.0432,
+      "step": 2000
+    },
+    {
+      "epoch": 1.1674259681093395,
+      "grad_norm": 0.06336130946874619,
+      "learning_rate": 1.6674259681093398e-05,
+      "loss": 0.0482,
+      "step": 2050
+    },
+    {
+      "epoch": 1.1958997722095672,
+      "grad_norm": 3.9503254890441895,
+      "learning_rate": 1.6592905955092744e-05,
+      "loss": 0.0436,
+      "step": 2100
+    },
+    {
+      "epoch": 1.224373576309795,
+      "grad_norm": 0.08679741621017456,
+      "learning_rate": 1.6511552229092093e-05,
+      "loss": 0.0346,
+      "step": 2150
+    },
+    {
+      "epoch": 1.2528473804100229,
+      "grad_norm": 2.1995127201080322,
+      "learning_rate": 1.6430198503091443e-05,
+      "loss": 0.0312,
+      "step": 2200
+    },
+    {
+      "epoch": 1.2813211845102506,
+      "grad_norm": 5.7709808349609375,
+      "learning_rate": 1.634884477709079e-05,
+      "loss": 0.032,
+      "step": 2250
+    },
+    {
+      "epoch": 1.3097949886104785,
+      "grad_norm": 0.2031829059123993,
+      "learning_rate": 1.626749105109014e-05,
+      "loss": 0.053,
+      "step": 2300
+    },
+    {
+      "epoch": 1.3382687927107062,
+      "grad_norm": 4.292157173156738,
+      "learning_rate": 1.6186137325089492e-05,
+      "loss": 0.0413,
+      "step": 2350
+    },
+    {
+      "epoch": 1.366742596810934,
+      "grad_norm": 0.07821401953697205,
+      "learning_rate": 1.6104783599088842e-05,
+      "loss": 0.0304,
+      "step": 2400
+    },
+    {
+      "epoch": 1.3952164009111616,
+      "grad_norm": 0.5930206179618835,
+      "learning_rate": 1.6023429873088188e-05,
+      "loss": 0.0525,
+      "step": 2450
+    },
+    {
+      "epoch": 1.4236902050113895,
+      "grad_norm": 1.6114712953567505,
+      "learning_rate": 1.5942076147087538e-05,
+      "loss": 0.0391,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4521640091116172,
+      "grad_norm": 0.28632065653800964,
+      "learning_rate": 1.5860722421086887e-05,
+      "loss": 0.0491,
+      "step": 2550
+    },
+    {
+      "epoch": 1.4806378132118452,
+      "grad_norm": 1.0017669200897217,
+      "learning_rate": 1.5779368695086237e-05,
+      "loss": 0.0395,
+      "step": 2600
+    },
+    {
+      "epoch": 1.5091116173120729,
+      "grad_norm": 0.03409272059798241,
+      "learning_rate": 1.5698014969085583e-05,
+      "loss": 0.0399,
+      "step": 2650
+    },
+    {
+      "epoch": 1.5375854214123006,
+      "grad_norm": 3.5108702182769775,
+      "learning_rate": 1.5616661243084933e-05,
+      "loss": 0.0424,
+      "step": 2700
+    },
+    {
+      "epoch": 1.5660592255125285,
+      "grad_norm": 3.5875349044799805,
+      "learning_rate": 1.5535307517084283e-05,
+      "loss": 0.0497,
+      "step": 2750
+    },
+    {
+      "epoch": 1.5945330296127562,
+      "grad_norm": 0.10498251020908356,
+      "learning_rate": 1.5453953791083632e-05,
+      "loss": 0.0461,
+      "step": 2800
+    },
+    {
+      "epoch": 1.6230068337129842,
+      "grad_norm": 7.618963718414307,
+      "learning_rate": 1.5374227139602996e-05,
+      "loss": 0.0394,
+      "step": 2850
+    },
+    {
+      "epoch": 1.6514806378132119,
+      "grad_norm": 3.3920793533325195,
+      "learning_rate": 1.5292873413602346e-05,
+      "loss": 0.0339,
+      "step": 2900
+    },
+    {
+      "epoch": 1.6799544419134396,
+      "grad_norm": 0.04736129939556122,
+      "learning_rate": 1.5211519687601692e-05,
+      "loss": 0.0358,
+      "step": 2950
+    },
+    {
+      "epoch": 1.7084282460136673,
+      "grad_norm": 0.17463508248329163,
+      "learning_rate": 1.5130165961601042e-05,
+      "loss": 0.034,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7369020501138952,
+      "grad_norm": 0.058148205280303955,
+      "learning_rate": 1.5048812235600392e-05,
+      "loss": 0.0317,
+      "step": 3050
+    },
+    {
+      "epoch": 1.7653758542141231,
+      "grad_norm": 3.5262815952301025,
+      "learning_rate": 1.4967458509599741e-05,
+      "loss": 0.0477,
+      "step": 3100
+    },
+    {
+      "epoch": 1.7938496583143508,
+      "grad_norm": 2.971937894821167,
+      "learning_rate": 1.488610478359909e-05,
+      "loss": 0.0364,
+      "step": 3150
+    },
+    {
+      "epoch": 1.8223234624145785,
+      "grad_norm": 0.05181724950671196,
+      "learning_rate": 1.4804751057598439e-05,
+      "loss": 0.0394,
+      "step": 3200
+    },
+    {
+      "epoch": 1.8507972665148062,
+      "grad_norm": 0.2712370455265045,
+      "learning_rate": 1.4723397331597789e-05,
+      "loss": 0.0456,
+      "step": 3250
+    },
+    {
+      "epoch": 1.8792710706150342,
+      "grad_norm": 1.608622431755066,
+      "learning_rate": 1.4642043605597138e-05,
+      "loss": 0.05,
+      "step": 3300
+    },
+    {
+      "epoch": 1.907744874715262,
+      "grad_norm": 5.2423529624938965,
+      "learning_rate": 1.4560689879596486e-05,
+      "loss": 0.0371,
+      "step": 3350
+    },
+    {
+      "epoch": 1.9362186788154898,
+      "grad_norm": 0.04786211624741554,
+      "learning_rate": 1.4479336153595836e-05,
+      "loss": 0.0329,
+      "step": 3400
+    },
+    {
+      "epoch": 1.9646924829157175,
+      "grad_norm": 0.5264931917190552,
+      "learning_rate": 1.4397982427595185e-05,
+      "loss": 0.0379,
+      "step": 3450
+    },
+    {
+      "epoch": 1.9931662870159452,
+      "grad_norm": 0.236006498336792,
+      "learning_rate": 1.4316628701594535e-05,
+      "loss": 0.0253,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9406438631790744,
+      "eval_loss": 0.05223705992102623,
+      "eval_precision": 0.9371867691279653,
+      "eval_recall": 0.9441265567149109,
+      "eval_runtime": 3.7109,
+      "eval_samples_per_second": 875.791,
+      "eval_steps_per_second": 109.676,
+      "step": 3512
+    },
+    {
+      "epoch": 2.021640091116173,
+      "grad_norm": 4.225963115692139,
+      "learning_rate": 1.4235274975593883e-05,
+      "loss": 0.0373,
+      "step": 3550
+    },
+    {
+      "epoch": 2.050113895216401,
+      "grad_norm": 0.15388111770153046,
+      "learning_rate": 1.4153921249593233e-05,
+      "loss": 0.0258,
+      "step": 3600
+    },
+    {
+      "epoch": 2.078587699316629,
+      "grad_norm": 6.3911895751953125,
+      "learning_rate": 1.4072567523592582e-05,
+      "loss": 0.0217,
+      "step": 3650
+    },
+    {
+      "epoch": 2.1070615034168565,
+      "grad_norm": 0.03075530007481575,
+      "learning_rate": 1.3991213797591932e-05,
+      "loss": 0.019,
+      "step": 3700
+    },
+    {
+      "epoch": 2.135535307517084,
+      "grad_norm": 0.16612432897090912,
+      "learning_rate": 1.3909860071591278e-05,
+      "loss": 0.0175,
+      "step": 3750
+    },
+    {
+      "epoch": 2.164009111617312,
+      "grad_norm": 0.14543022215366364,
+      "learning_rate": 1.382850634559063e-05,
+      "loss": 0.0289,
+      "step": 3800
+    },
+    {
+      "epoch": 2.19248291571754,
+      "grad_norm": 2.9880359172821045,
+      "learning_rate": 1.374715261958998e-05,
+      "loss": 0.0208,
+      "step": 3850
+    },
+    {
+      "epoch": 2.2209567198177678,
+      "grad_norm": 9.878133773803711,
+      "learning_rate": 1.3665798893589329e-05,
+      "loss": 0.021,
+      "step": 3900
+    },
+    {
+      "epoch": 2.2494305239179955,
+      "grad_norm": 9.684176445007324,
+      "learning_rate": 1.3584445167588675e-05,
+      "loss": 0.0267,
+      "step": 3950
+    },
+    {
+      "epoch": 2.277904328018223,
+      "grad_norm": 33.15859603881836,
+      "learning_rate": 1.3503091441588025e-05,
+      "loss": 0.0295,
+      "step": 4000
+    },
+    {
+      "epoch": 2.306378132118451,
+      "grad_norm": 2.559544086456299,
+      "learning_rate": 1.3421737715587374e-05,
+      "loss": 0.0292,
+      "step": 4050
+    },
+    {
+      "epoch": 2.334851936218679,
+      "grad_norm": 0.07091552764177322,
+      "learning_rate": 1.3340383989586724e-05,
+      "loss": 0.0262,
+      "step": 4100
+    },
+    {
+      "epoch": 2.3633257403189067,
+      "grad_norm": 1.8119585514068604,
+      "learning_rate": 1.3259030263586072e-05,
+      "loss": 0.03,
+      "step": 4150
+    },
+    {
+      "epoch": 2.3917995444191344,
+      "grad_norm": 0.1476636379957199,
+      "learning_rate": 1.3177676537585422e-05,
+      "loss": 0.0196,
+      "step": 4200
+    },
+    {
+      "epoch": 2.420273348519362,
+      "grad_norm": 0.04482650011777878,
+      "learning_rate": 1.3096322811584771e-05,
+      "loss": 0.0263,
+      "step": 4250
+    },
+    {
+      "epoch": 2.44874715261959,
+      "grad_norm": 0.09201560169458389,
+      "learning_rate": 1.3014969085584121e-05,
+      "loss": 0.0172,
+      "step": 4300
+    },
+    {
+      "epoch": 2.477220956719818,
+      "grad_norm": 0.02215876244008541,
+      "learning_rate": 1.2933615359583469e-05,
+      "loss": 0.0149,
+      "step": 4350
+    },
+    {
+      "epoch": 2.5056947608200457,
+      "grad_norm": 0.6993932127952576,
+      "learning_rate": 1.2852261633582819e-05,
+      "loss": 0.0331,
+      "step": 4400
+    },
+    {
+      "epoch": 2.5341685649202734,
+      "grad_norm": 0.030453965067863464,
+      "learning_rate": 1.2770907907582168e-05,
+      "loss": 0.0307,
+      "step": 4450
+    },
+    {
+      "epoch": 2.562642369020501,
+      "grad_norm": 0.22211593389511108,
+      "learning_rate": 1.2689554181581518e-05,
+      "loss": 0.0183,
+      "step": 4500
+    },
+    {
+      "epoch": 2.591116173120729,
+      "grad_norm": 1.2842738628387451,
+      "learning_rate": 1.2608200455580866e-05,
+      "loss": 0.0226,
+      "step": 4550
+    },
+    {
+      "epoch": 2.619589977220957,
+      "grad_norm": 3.9048423767089844,
+      "learning_rate": 1.2526846729580216e-05,
+      "loss": 0.0239,
+      "step": 4600
+    },
+    {
+      "epoch": 2.6480637813211843,
+      "grad_norm": 0.9887784719467163,
+      "learning_rate": 1.2445493003579565e-05,
+      "loss": 0.0271,
+      "step": 4650
+    },
+    {
+      "epoch": 2.6765375854214124,
+      "grad_norm": 4.759728908538818,
+      "learning_rate": 1.2364139277578915e-05,
+      "loss": 0.0201,
+      "step": 4700
+    },
+    {
+      "epoch": 2.70501138952164,
+      "grad_norm": 0.2671191096305847,
+      "learning_rate": 1.2282785551578263e-05,
+      "loss": 0.0212,
+      "step": 4750
+    },
+    {
+      "epoch": 2.733485193621868,
+      "grad_norm": 0.036626849323511124,
+      "learning_rate": 1.2201431825577612e-05,
+      "loss": 0.0155,
+      "step": 4800
+    },
+    {
+      "epoch": 2.7619589977220955,
+      "grad_norm": 6.877408027648926,
+      "learning_rate": 1.2120078099576962e-05,
+      "loss": 0.0266,
+      "step": 4850
+    },
+    {
+      "epoch": 2.7904328018223232,
+      "grad_norm": 4.725896835327148,
+      "learning_rate": 1.2038724373576312e-05,
+      "loss": 0.0163,
+      "step": 4900
+    },
+    {
+      "epoch": 2.8189066059225514,
+      "grad_norm": 0.11965059489011765,
+      "learning_rate": 1.195737064757566e-05,
+      "loss": 0.0246,
+      "step": 4950
+    },
+    {
+      "epoch": 2.847380410022779,
+      "grad_norm": 0.6634079813957214,
+      "learning_rate": 1.187601692157501e-05,
+      "loss": 0.0304,
+      "step": 5000
+    },
+    {
+      "epoch": 2.875854214123007,
+      "grad_norm": 3.952694892883301,
+      "learning_rate": 1.1794663195574359e-05,
+      "loss": 0.0183,
+      "step": 5050
+    },
+    {
+      "epoch": 2.9043280182232345,
+      "grad_norm": 19.788942337036133,
+      "learning_rate": 1.1713309469573709e-05,
+      "loss": 0.0193,
+      "step": 5100
+    },
+    {
+      "epoch": 2.932801822323462,
+      "grad_norm": 4.989261627197266,
+      "learning_rate": 1.1631955743573055e-05,
+      "loss": 0.023,
+      "step": 5150
+    },
+    {
+      "epoch": 2.9612756264236904,
+      "grad_norm": 9.020853996276855,
+      "learning_rate": 1.1550602017572406e-05,
+      "loss": 0.0231,
+      "step": 5200
+    },
+    {
+      "epoch": 2.989749430523918,
+      "grad_norm": 0.9151140451431274,
+      "learning_rate": 1.1469248291571756e-05,
+      "loss": 0.0314,
+      "step": 5250
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.9470420646891236,
+      "eval_loss": 0.04870199039578438,
+      "eval_precision": 0.943090787716956,
+      "eval_recall": 0.9510265903736116,
+      "eval_runtime": 3.7494,
+      "eval_samples_per_second": 866.805,
+      "eval_steps_per_second": 108.551,
+      "step": 5268
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 12292,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1034617415983686.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-5268/training_args.bin b/checkpoint-5268/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5883d1e2ddb42c11dd6ad1fddc79d9ffe7a246f3
--- /dev/null
+++ b/checkpoint-5268/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e08f60c5260f286c88c6054e532ee0950cb5316081a3a51d07b57f6a266f71
+size 5368
diff --git a/checkpoint-7024/config.json b/checkpoint-7024/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f744ab25e17fedaffadd5fcb3ae10a7b9e4083bc
--- /dev/null
+++ b/checkpoint-7024/config.json
@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}
diff --git a/checkpoint-7024/model.safetensors b/checkpoint-7024/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8b6cd3509a45ea182bbc7582fb59dabff55d943f
--- /dev/null
+++ b/checkpoint-7024/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6598e075d96ee3d6f97747af06fa07f2c3911ddaed25abfb7de1fd7721141c8
+size 1109863956
diff --git a/checkpoint-7024/optimizer.pt b/checkpoint-7024/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..76c231a740cac6d8eff8f04aac1274adcc676984
--- /dev/null
+++ b/checkpoint-7024/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a117e163d94c08fd1f1f9af39bd82f4b3716f00ac1182ace0c59a87904392071
+size 2219846202
diff --git a/checkpoint-7024/rng_state.pth b/checkpoint-7024/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0b6af7a7910ac3ba6f06785c64a3a3ee803a68ea
--- /dev/null
+++ b/checkpoint-7024/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812e0e72dade8665b357d04e5e8e4e32884d5be5e0a27b18a52cc0cb56ff2a99
+size 14244
diff --git a/checkpoint-7024/scaler.pt b/checkpoint-7024/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..369ecafb3ebf9577cec81398c91b2d5a39fe82e9
--- /dev/null
+++ b/checkpoint-7024/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9000913a2cd4b9138ab4ca6ca075392e853b97a40a57530ed47e619f75669ea
+size 988
diff --git a/checkpoint-7024/scheduler.pt b/checkpoint-7024/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2cac5bc5613e1621b097e0c3320bc4e2b82b52dc
--- /dev/null
+++ b/checkpoint-7024/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35960966f24baf5111ea581dacf8142ebf55786fd138b781b8da1cd15ea40080
+size 1064
diff --git a/checkpoint-7024/special_tokens_map.json b/checkpoint-7024/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..d79c0fe029062eb03708803e72c3483296e2ea97
--- /dev/null
+++ b/checkpoint-7024/special_tokens_map.json
@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-7024/tokenizer.json b/checkpoint-7024/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..7126b1d228f6e5f725b6ee02a88b1118c725aeed
--- /dev/null
+++ b/checkpoint-7024/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734
diff --git a/checkpoint-7024/tokenizer_config.json b/checkpoint-7024/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d297107d53da62483767139822cf5ed3a6975e24
--- /dev/null
+++ b/checkpoint-7024/tokenizer_config.json
@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-7024/trainer_state.json b/checkpoint-7024/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..26f3fc85eb672424322acb0b19f86e0cb3c15a84
--- /dev/null
+++ b/checkpoint-7024/trainer_state.json
@@ -0,0 +1,1058 @@
+{
+  "best_global_step": 7024,
+  "best_metric": 0.9525329748802823,
+  "best_model_checkpoint": "C:\\Users\\Shara\\projects\\models\\run_16-lr_2e-05-acc_1-wd_0.01-bs_8-ep_7\\checkpoint-7024",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 7024,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02847380410022779,
+      "grad_norm": 4.8302321434021,
+      "learning_rate": 1.992840872111943e-05,
+      "loss": 0.9994,
+      "step": 50
+    },
+    {
+      "epoch": 0.05694760820045558,
+      "grad_norm": 3.4978649616241455,
+      "learning_rate": 1.9847054995118778e-05,
+      "loss": 0.3939,
+      "step": 100
+    },
+    {
+      "epoch": 0.08542141230068337,
+      "grad_norm": 8.353672981262207,
+      "learning_rate": 1.9765701269118128e-05,
+      "loss": 0.2882,
+      "step": 150
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "grad_norm": 9.822871208190918,
+      "learning_rate": 1.9684347543117477e-05,
+      "loss": 0.1728,
+      "step": 200
+    },
+    {
+      "epoch": 0.14236902050113895,
+      "grad_norm": 3.1411221027374268,
+      "learning_rate": 1.9602993817116827e-05,
+      "loss": 0.1251,
+      "step": 250
+    },
+    {
+      "epoch": 0.17084282460136674,
+      "grad_norm": 8.493424415588379,
+      "learning_rate": 1.9521640091116173e-05,
+      "loss": 0.1405,
+      "step": 300
+    },
+    {
+      "epoch": 0.19931662870159453,
+      "grad_norm": 4.757007122039795,
+      "learning_rate": 1.9440286365115523e-05,
+      "loss": 0.1431,
+      "step": 350
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "grad_norm": 4.339049816131592,
+      "learning_rate": 1.9358932639114873e-05,
+      "loss": 0.0912,
+      "step": 400
+    },
+    {
+      "epoch": 0.25626423690205014,
+      "grad_norm": 14.540772438049316,
+      "learning_rate": 1.9277578913114222e-05,
+      "loss": 0.1048,
+      "step": 450
+    },
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 10.503073692321777,
+      "learning_rate": 1.9196225187113572e-05,
+      "loss": 0.1224,
+      "step": 500
+    },
+    {
+      "epoch": 0.3132118451025057,
+      "grad_norm": 2.738131284713745,
+      "learning_rate": 1.911487146111292e-05,
+      "loss": 0.1025,
+      "step": 550
+    },
+    {
+      "epoch": 0.3416856492027335,
+      "grad_norm": 6.681102752685547,
+      "learning_rate": 1.903351773511227e-05,
+      "loss": 0.0869,
+      "step": 600
+    },
+    {
+      "epoch": 0.3701594533029613,
+      "grad_norm": 1.4330339431762695,
+      "learning_rate": 1.895216400911162e-05,
+      "loss": 0.052,
+      "step": 650
+    },
+    {
+      "epoch": 0.39863325740318906,
+      "grad_norm": 2.581470012664795,
+      "learning_rate": 1.8870810283110967e-05,
+      "loss": 0.0808,
+      "step": 700
+    },
+    {
+      "epoch": 0.4271070615034169,
+      "grad_norm": 5.825100898742676,
+      "learning_rate": 1.8789456557110317e-05,
+      "loss": 0.0716,
+      "step": 750
+    },
+    {
+      "epoch": 0.45558086560364464,
+      "grad_norm": 1.74166738986969,
+      "learning_rate": 1.8708102831109666e-05,
+      "loss": 0.0806,
+      "step": 800
+    },
+    {
+      "epoch": 0.48405466970387245,
+      "grad_norm": 7.3097405433654785,
+      "learning_rate": 1.8626749105109016e-05,
+      "loss": 0.0666,
+      "step": 850
+    },
+    {
+      "epoch": 0.5125284738041003,
+      "grad_norm": 2.220766067504883,
+      "learning_rate": 1.8545395379108362e-05,
+      "loss": 0.0768,
+      "step": 900
+    },
+    {
+      "epoch": 0.541002277904328,
+      "grad_norm": 4.0566511154174805,
+      "learning_rate": 1.8464041653107715e-05,
+      "loss": 0.0707,
+      "step": 950
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.2833240330219269,
+      "learning_rate": 1.8382687927107065e-05,
+      "loss": 0.0858,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5979498861047836,
+      "grad_norm": 21.131481170654297,
+      "learning_rate": 1.8301334201106415e-05,
+      "loss": 0.0595,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6264236902050114,
+      "grad_norm": 27.655433654785156,
+      "learning_rate": 1.821998047510576e-05,
+      "loss": 0.0466,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6548974943052391,
+      "grad_norm": 3.4721717834472656,
+      "learning_rate": 1.813862674910511e-05,
+      "loss": 0.0776,
+      "step": 1150
+    },
+    {
+      "epoch": 0.683371298405467,
+      "grad_norm": 2.4811441898345947,
+      "learning_rate": 1.805727302310446e-05,
+      "loss": 0.0647,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7118451025056948,
+      "grad_norm": 6.169066429138184,
+      "learning_rate": 1.797591929710381e-05,
+      "loss": 0.0724,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7403189066059226,
+      "grad_norm": 8.984748840332031,
+      "learning_rate": 1.7894565571103156e-05,
+      "loss": 0.0838,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7687927107061503,
+      "grad_norm": 5.944505214691162,
+      "learning_rate": 1.7813211845102506e-05,
+      "loss": 0.0683,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7972665148063781,
+      "grad_norm": 0.28812381625175476,
+      "learning_rate": 1.7731858119101856e-05,
+      "loss": 0.0614,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8257403189066059,
+      "grad_norm": 6.176011085510254,
+      "learning_rate": 1.7650504393101205e-05,
+      "loss": 0.0615,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8542141230068337,
+      "grad_norm": 2.5244405269622803,
+      "learning_rate": 1.7569150667100555e-05,
+      "loss": 0.0714,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8826879271070615,
+      "grad_norm": 3.3508074283599854,
+      "learning_rate": 1.7487796941099904e-05,
+      "loss": 0.0563,
+      "step": 1550
+    },
+    {
+      "epoch": 0.9111617312072893,
+      "grad_norm": 9.980842590332031,
+      "learning_rate": 1.7406443215099254e-05,
+      "loss": 0.0647,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9396355353075171,
+      "grad_norm": 3.6959774494171143,
+      "learning_rate": 1.7325089489098604e-05,
+      "loss": 0.0682,
+      "step": 1650
+    },
+    {
+      "epoch": 0.9681093394077449,
+      "grad_norm": 0.626620888710022,
+      "learning_rate": 1.724373576309795e-05,
+      "loss": 0.0499,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9965831435079726,
+      "grad_norm": 7.145672798156738,
+      "learning_rate": 1.71623820370973e-05,
+      "loss": 0.0569,
+      "step": 1750
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9242246437552389,
+      "eval_loss": 0.05600914731621742,
+      "eval_precision": 0.9206746826987308,
+      "eval_recall": 0.927802086839448,
+      "eval_runtime": 3.7538,
+      "eval_samples_per_second": 865.798,
+      "eval_steps_per_second": 108.425,
+      "step": 1756
+    },
+    {
+      "epoch": 1.0250569476082005,
+      "grad_norm": 4.280463695526123,
+      "learning_rate": 1.708102831109665e-05,
+      "loss": 0.0673,
+      "step": 1800
+    },
+    {
+      "epoch": 1.0535307517084282,
+      "grad_norm": 0.06692535430192947,
+      "learning_rate": 1.6999674585096e-05,
+      "loss": 0.0403,
+      "step": 1850
+    },
+    {
+      "epoch": 1.082004555808656,
+      "grad_norm": 0.03789375349879265,
+      "learning_rate": 1.691832085909535e-05,
+      "loss": 0.0496,
+      "step": 1900
+    },
+    {
+      "epoch": 1.1104783599088839,
+      "grad_norm": 3.698348045349121,
+      "learning_rate": 1.6836967133094698e-05,
+      "loss": 0.0381,
+      "step": 1950
+    },
+    {
+      "epoch": 1.1389521640091116,
+      "grad_norm": 2.753032684326172,
+      "learning_rate": 1.6755613407094048e-05,
+      "loss": 0.0432,
+      "step": 2000
+    },
+    {
+      "epoch": 1.1674259681093395,
+      "grad_norm": 0.06336130946874619,
+      "learning_rate": 1.6674259681093398e-05,
+      "loss": 0.0482,
+      "step": 2050
+    },
+    {
+      "epoch": 1.1958997722095672,
+      "grad_norm": 3.9503254890441895,
+      "learning_rate": 1.6592905955092744e-05,
+      "loss": 0.0436,
+      "step": 2100
+    },
+    {
+      "epoch": 1.224373576309795,
+      "grad_norm": 0.08679741621017456,
+      "learning_rate": 1.6511552229092093e-05,
+      "loss": 0.0346,
+      "step": 2150
+    },
+    {
+      "epoch": 1.2528473804100229,
+      "grad_norm": 2.1995127201080322,
+      "learning_rate": 1.6430198503091443e-05,
+      "loss": 0.0312,
+      "step": 2200
+    },
+    {
+      "epoch": 1.2813211845102506,
+      "grad_norm": 5.7709808349609375,
+      "learning_rate": 1.634884477709079e-05,
+      "loss": 0.032,
+      "step": 2250
+    },
+    {
+      "epoch": 1.3097949886104785,
+      "grad_norm": 0.2031829059123993,
+      "learning_rate": 1.626749105109014e-05,
+      "loss": 0.053,
+      "step": 2300
+    },
+    {
+      "epoch": 1.3382687927107062,
+      "grad_norm": 4.292157173156738,
+      "learning_rate": 1.6186137325089492e-05,
+      "loss": 0.0413,
+      "step": 2350
+    },
+    {
+      "epoch": 1.366742596810934,
+      "grad_norm": 0.07821401953697205,
+      "learning_rate": 1.6104783599088842e-05,
+      "loss": 0.0304,
+      "step": 2400
+    },
+    {
+      "epoch": 1.3952164009111616,
+      "grad_norm": 0.5930206179618835,
+      "learning_rate": 1.6023429873088188e-05,
+      "loss": 0.0525,
+      "step": 2450
+    },
+    {
+      "epoch": 1.4236902050113895,
+      "grad_norm": 1.6114712953567505,
+      "learning_rate": 1.5942076147087538e-05,
+      "loss": 0.0391,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4521640091116172,
+      "grad_norm": 0.28632065653800964,
+      "learning_rate": 1.5860722421086887e-05,
+      "loss": 0.0491,
+      "step": 2550
+    },
+    {
+      "epoch": 1.4806378132118452,
+      "grad_norm": 1.0017669200897217,
+      "learning_rate": 1.5779368695086237e-05,
+      "loss": 0.0395,
+      "step": 2600
+    },
+    {
+      "epoch": 1.5091116173120729,
+      "grad_norm": 0.03409272059798241,
+      "learning_rate": 1.5698014969085583e-05,
+      "loss": 0.0399,
+      "step": 2650
+    },
+    {
+      "epoch": 1.5375854214123006,
+      "grad_norm": 3.5108702182769775,
+      "learning_rate": 1.5616661243084933e-05,
+      "loss": 0.0424,
+      "step": 2700
+    },
+    {
+      "epoch": 1.5660592255125285,
+      "grad_norm": 3.5875349044799805,
+      "learning_rate": 1.5535307517084283e-05,
+      "loss": 0.0497,
+      "step": 2750
+    },
+    {
+      "epoch": 1.5945330296127562,
+      "grad_norm": 0.10498251020908356,
+      "learning_rate": 1.5453953791083632e-05,
+      "loss": 0.0461,
+      "step": 2800
+    },
+    {
+      "epoch": 1.6230068337129842,
+      "grad_norm": 7.618963718414307,
+      "learning_rate": 1.5374227139602996e-05,
+      "loss": 0.0394,
+      "step": 2850
+    },
+    {
+      "epoch": 1.6514806378132119,
+      "grad_norm": 3.3920793533325195,
+      "learning_rate": 1.5292873413602346e-05,
+      "loss": 0.0339,
+      "step": 2900
+    },
+    {
+      "epoch": 1.6799544419134396,
+      "grad_norm": 0.04736129939556122,
+      "learning_rate": 1.5211519687601692e-05,
+      "loss": 0.0358,
+      "step": 2950
+    },
+    {
+      "epoch": 1.7084282460136673,
+      "grad_norm": 0.17463508248329163,
+      "learning_rate": 1.5130165961601042e-05,
+      "loss": 0.034,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7369020501138952,
+      "grad_norm": 0.058148205280303955,
+      "learning_rate": 1.5048812235600392e-05,
+      "loss": 0.0317,
+      "step": 3050
+    },
+    {
+      "epoch": 1.7653758542141231,
+      "grad_norm": 3.5262815952301025,
+      "learning_rate": 1.4967458509599741e-05,
+      "loss": 0.0477,
+      "step": 3100
+    },
+    {
+      "epoch": 1.7938496583143508,
+      "grad_norm": 2.971937894821167,
+      "learning_rate": 1.488610478359909e-05,
+      "loss": 0.0364,
+      "step": 3150
+    },
+    {
+      "epoch": 1.8223234624145785,
+      "grad_norm": 0.05181724950671196,
+      "learning_rate": 1.4804751057598439e-05,
+      "loss": 0.0394,
+      "step": 3200
+    },
+    {
+      "epoch": 1.8507972665148062,
+      "grad_norm": 0.2712370455265045,
+      "learning_rate": 1.4723397331597789e-05,
+      "loss": 0.0456,
+      "step": 3250
+    },
+    {
+      "epoch": 1.8792710706150342,
+      "grad_norm": 1.608622431755066,
+      "learning_rate": 1.4642043605597138e-05,
+      "loss": 0.05,
+      "step": 3300
+    },
+    {
+      "epoch": 1.907744874715262,
+      "grad_norm": 5.2423529624938965,
+      "learning_rate": 1.4560689879596486e-05,
+      "loss": 0.0371,
+      "step": 3350
+    },
+    {
+      "epoch": 1.9362186788154898,
+      "grad_norm": 0.04786211624741554,
+      "learning_rate": 1.4479336153595836e-05,
+      "loss": 0.0329,
+      "step": 3400
+    },
+    {
+      "epoch": 1.9646924829157175,
+      "grad_norm": 0.5264931917190552,
+      "learning_rate": 1.4397982427595185e-05,
+      "loss": 0.0379,
+      "step": 3450
+    },
+    {
+      "epoch": 1.9931662870159452,
+      "grad_norm": 0.236006498336792,
+      "learning_rate": 1.4316628701594535e-05,
+      "loss": 0.0253,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9406438631790744,
+      "eval_loss": 0.05223705992102623,
+      "eval_precision": 0.9371867691279653,
+      "eval_recall": 0.9441265567149109,
+      "eval_runtime": 3.7109,
+      "eval_samples_per_second": 875.791,
+      "eval_steps_per_second": 109.676,
+      "step": 3512
+    },
+    {
+      "epoch": 2.021640091116173,
+      "grad_norm": 4.225963115692139,
+      "learning_rate": 1.4235274975593883e-05,
+      "loss": 0.0373,
+      "step": 3550
+    },
+    {
+      "epoch": 2.050113895216401,
+      "grad_norm": 0.15388111770153046,
+      "learning_rate": 1.4153921249593233e-05,
+      "loss": 0.0258,
+      "step": 3600
+    },
+    {
+      "epoch": 2.078587699316629,
+      "grad_norm": 6.3911895751953125,
+      "learning_rate": 1.4072567523592582e-05,
+      "loss": 0.0217,
+      "step": 3650
+    },
+    {
+      "epoch": 2.1070615034168565,
+      "grad_norm": 0.03075530007481575,
+      "learning_rate": 1.3991213797591932e-05,
+      "loss": 0.019,
+      "step": 3700
+    },
+    {
+      "epoch": 2.135535307517084,
+      "grad_norm": 0.16612432897090912,
+      "learning_rate": 1.3909860071591278e-05,
+      "loss": 0.0175,
+      "step": 3750
+    },
+    {
+      "epoch": 2.164009111617312,
+      "grad_norm": 0.14543022215366364,
+      "learning_rate": 1.382850634559063e-05,
+      "loss": 0.0289,
+      "step": 3800
+    },
+    {
+      "epoch": 2.19248291571754,
+      "grad_norm": 2.9880359172821045,
+      "learning_rate": 1.374715261958998e-05,
+      "loss": 0.0208,
+      "step": 3850
+    },
+    {
+      "epoch": 2.2209567198177678,
+      "grad_norm": 9.878133773803711,
+      "learning_rate": 1.3665798893589329e-05,
+      "loss": 0.021,
+      "step": 3900
+    },
+    {
+      "epoch": 2.2494305239179955,
+      "grad_norm": 9.684176445007324,
+      "learning_rate": 1.3584445167588675e-05,
+      "loss": 0.0267,
+      "step": 3950
+    },
+    {
+      "epoch": 2.277904328018223,
+      "grad_norm": 33.15859603881836,
+      "learning_rate": 1.3503091441588025e-05,
+      "loss": 0.0295,
+      "step": 4000
+    },
+    {
+      "epoch": 2.306378132118451,
+      "grad_norm": 2.559544086456299,
+      "learning_rate": 1.3421737715587374e-05,
+      "loss": 0.0292,
+      "step": 4050
+    },
+    {
+      "epoch": 2.334851936218679,
+      "grad_norm": 0.07091552764177322,
+      "learning_rate": 1.3340383989586724e-05,
+      "loss": 0.0262,
+      "step": 4100
+    },
+    {
+      "epoch": 2.3633257403189067,
+      "grad_norm": 1.8119585514068604,
+      "learning_rate": 1.3259030263586072e-05,
+      "loss": 0.03,
+      "step": 4150
+    },
+    {
+      "epoch": 2.3917995444191344,
+      "grad_norm": 0.1476636379957199,
+      "learning_rate": 1.3177676537585422e-05,
+      "loss": 0.0196,
+      "step": 4200
+    },
+    {
+      "epoch": 2.420273348519362,
+      "grad_norm": 0.04482650011777878,
+      "learning_rate": 1.3096322811584771e-05,
+      "loss": 0.0263,
+      "step": 4250
+    },
+    {
+      "epoch": 2.44874715261959,
+      "grad_norm": 0.09201560169458389,
+      "learning_rate": 1.3014969085584121e-05,
+      "loss": 0.0172,
+      "step": 4300
+    },
+    {
+      "epoch": 2.477220956719818,
+      "grad_norm": 0.02215876244008541,
+      "learning_rate": 1.2933615359583469e-05,
+      "loss": 0.0149,
+      "step": 4350
+    },
+    {
+      "epoch": 2.5056947608200457,
+      "grad_norm": 0.6993932127952576,
+      "learning_rate": 1.2852261633582819e-05,
+      "loss": 0.0331,
+      "step": 4400
+    },
+    {
+      "epoch": 2.5341685649202734,
+      "grad_norm": 0.030453965067863464,
+      "learning_rate": 1.2770907907582168e-05,
+      "loss": 0.0307,
+      "step": 4450
+    },
+    {
+      "epoch": 2.562642369020501,
+      "grad_norm": 0.22211593389511108,
+      "learning_rate": 1.2689554181581518e-05,
+      "loss": 0.0183,
+      "step": 4500
+    },
+    {
+      "epoch": 2.591116173120729,
+      "grad_norm": 1.2842738628387451,
+      "learning_rate": 1.2608200455580866e-05,
+      "loss": 0.0226,
+      "step": 4550
+    },
+    {
+      "epoch": 2.619589977220957,
+      "grad_norm": 3.9048423767089844,
+      "learning_rate": 1.2526846729580216e-05,
+      "loss": 0.0239,
+      "step": 4600
+    },
+    {
+      "epoch": 2.6480637813211843,
+      "grad_norm": 0.9887784719467163,
+      "learning_rate": 1.2445493003579565e-05,
+      "loss": 0.0271,
+      "step": 4650
+    },
+    {
+      "epoch": 2.6765375854214124,
+      "grad_norm": 4.759728908538818,
+      "learning_rate": 1.2364139277578915e-05,
+      "loss": 0.0201,
+      "step": 4700
+    },
+    {
+      "epoch": 2.70501138952164,
+      "grad_norm": 0.2671191096305847,
+      "learning_rate": 1.2282785551578263e-05,
+      "loss": 0.0212,
+      "step": 4750
+    },
+    {
+      "epoch": 2.733485193621868,
+      "grad_norm": 0.036626849323511124,
+      "learning_rate": 1.2201431825577612e-05,
+      "loss": 0.0155,
+      "step": 4800
+    },
+    {
+      "epoch": 2.7619589977220955,
+      "grad_norm": 6.877408027648926,
+      "learning_rate": 1.2120078099576962e-05,
+      "loss": 0.0266,
+      "step": 4850
+    },
+    {
+      "epoch": 2.7904328018223232,
+      "grad_norm": 4.725896835327148,
+      "learning_rate": 1.2038724373576312e-05,
+      "loss": 0.0163,
+      "step": 4900
+    },
+    {
+      "epoch": 2.8189066059225514,
+      "grad_norm": 0.11965059489011765,
+      "learning_rate": 1.195737064757566e-05,
+      "loss": 0.0246,
+      "step": 4950
+    },
+    {
+      "epoch": 2.847380410022779,
+      "grad_norm": 0.6634079813957214,
+      "learning_rate": 1.187601692157501e-05,
+      "loss": 0.0304,
+      "step": 5000
+    },
+    {
+      "epoch": 2.875854214123007,
+      "grad_norm": 3.952694892883301,
+      "learning_rate": 1.1794663195574359e-05,
+      "loss": 0.0183,
+      "step": 5050
+    },
+    {
+      "epoch": 2.9043280182232345,
+      "grad_norm": 19.788942337036133,
+      "learning_rate": 1.1713309469573709e-05,
+      "loss": 0.0193,
+      "step": 5100
+    },
+    {
+      "epoch": 2.932801822323462,
+      "grad_norm": 4.989261627197266,
+      "learning_rate": 1.1631955743573055e-05,
+      "loss": 0.023,
+      "step": 5150
+    },
+    {
+      "epoch": 2.9612756264236904,
+      "grad_norm": 9.020853996276855,
+      "learning_rate": 1.1550602017572406e-05,
+      "loss": 0.0231,
+      "step": 5200
+    },
+    {
+      "epoch": 2.989749430523918,
+      "grad_norm": 0.9151140451431274,
+      "learning_rate": 1.1469248291571756e-05,
+      "loss": 0.0314,
+      "step": 5250
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.9470420646891236,
+      "eval_loss": 0.04870199039578438,
+      "eval_precision": 0.943090787716956,
+      "eval_recall": 0.9510265903736116,
+      "eval_runtime": 3.7494,
+      "eval_samples_per_second": 866.805,
+      "eval_steps_per_second": 108.551,
+      "step": 5268
+    },
+    {
+      "epoch": 3.0182232346241458,
+      "grad_norm": 8.62992000579834,
+      "learning_rate": 1.1387894565571106e-05,
+      "loss": 0.0194,
+      "step": 5300
+    },
+    {
+      "epoch": 3.0466970387243735,
+      "grad_norm": 0.5615554451942444,
+      "learning_rate": 1.1306540839570452e-05,
+      "loss": 0.0114,
+      "step": 5350
+    },
+    {
+      "epoch": 3.075170842824601,
+      "grad_norm": 2.5735936164855957,
+      "learning_rate": 1.1225187113569801e-05,
+      "loss": 0.0163,
+      "step": 5400
+    },
+    {
+      "epoch": 3.1036446469248293,
+      "grad_norm": 6.504094123840332,
+      "learning_rate": 1.1143833387569151e-05,
+      "loss": 0.0135,
+      "step": 5450
+    },
+    {
+      "epoch": 3.132118451025057,
+      "grad_norm": 14.477537155151367,
+      "learning_rate": 1.10624796615685e-05,
+      "loss": 0.0129,
+      "step": 5500
+    },
+    {
+      "epoch": 3.1605922551252847,
+      "grad_norm": 0.04929841682314873,
+      "learning_rate": 1.0981125935567849e-05,
+      "loss": 0.0263,
+      "step": 5550
+    },
+    {
+      "epoch": 3.1890660592255125,
+      "grad_norm": 0.08875144273042679,
+      "learning_rate": 1.0899772209567198e-05,
+      "loss": 0.0134,
+      "step": 5600
+    },
+    {
+      "epoch": 3.21753986332574,
+      "grad_norm": 0.6238455772399902,
+      "learning_rate": 1.0818418483566548e-05,
+      "loss": 0.0107,
+      "step": 5650
+    },
+    {
+      "epoch": 3.2460136674259683,
+      "grad_norm": 0.004948179703205824,
+      "learning_rate": 1.0737064757565898e-05,
+      "loss": 0.0167,
+      "step": 5700
+    },
+    {
+      "epoch": 3.274487471526196,
+      "grad_norm": 0.017031218856573105,
+      "learning_rate": 1.0655711031565246e-05,
+      "loss": 0.0085,
+      "step": 5750
+    },
+    {
+      "epoch": 3.3029612756264237,
+      "grad_norm": 2.9840469360351562,
+      "learning_rate": 1.0574357305564595e-05,
+      "loss": 0.0158,
+      "step": 5800
+    },
+    {
+      "epoch": 3.3314350797266514,
+      "grad_norm": 1.7477540969848633,
+      "learning_rate": 1.0493003579563945e-05,
+      "loss": 0.0157,
+      "step": 5850
+    },
+    {
+      "epoch": 3.359908883826879,
+      "grad_norm": 0.03963543102145195,
+      "learning_rate": 1.0411649853563295e-05,
+      "loss": 0.0201,
+      "step": 5900
+    },
+    {
+      "epoch": 3.3883826879271073,
+      "grad_norm": 0.16669808328151703,
+      "learning_rate": 1.0330296127562643e-05,
+      "loss": 0.0159,
+      "step": 5950
+    },
+    {
+      "epoch": 3.416856492027335,
+      "grad_norm": 0.01953568309545517,
+      "learning_rate": 1.0248942401561992e-05,
+      "loss": 0.0117,
+      "step": 6000
+    },
+    {
+      "epoch": 3.4453302961275627,
+      "grad_norm": 0.07708246260881424,
+      "learning_rate": 1.0167588675561342e-05,
+      "loss": 0.0117,
+      "step": 6050
+    },
+    {
+      "epoch": 3.4738041002277904,
+      "grad_norm": 2.423590898513794,
+      "learning_rate": 1.0086234949560691e-05,
+      "loss": 0.0111,
+      "step": 6100
+    },
+    {
+      "epoch": 3.502277904328018,
+      "grad_norm": 0.006337775848805904,
+      "learning_rate": 1.000488122356004e-05,
+      "loss": 0.0052,
+      "step": 6150
+    },
+    {
+      "epoch": 3.5307517084282463,
+      "grad_norm": 0.01373753696680069,
+      "learning_rate": 9.923527497559389e-06,
+      "loss": 0.009,
+      "step": 6200
+    },
+    {
+      "epoch": 3.559225512528474,
+      "grad_norm": 0.11260247975587845,
+      "learning_rate": 9.842173771558739e-06,
+      "loss": 0.0208,
+      "step": 6250
+    },
+    {
+      "epoch": 3.5876993166287017,
+      "grad_norm": 1.240822196006775,
+      "learning_rate": 9.760820045558087e-06,
+      "loss": 0.0157,
+      "step": 6300
+    },
+    {
+      "epoch": 3.6161731207289294,
+      "grad_norm": 0.05271293595433235,
+      "learning_rate": 9.679466319557436e-06,
+      "loss": 0.0175,
+      "step": 6350
+    },
+    {
+      "epoch": 3.644646924829157,
+      "grad_norm": 24.546663284301758,
+      "learning_rate": 9.598112593556786e-06,
+      "loss": 0.015,
+      "step": 6400
+    },
+    {
+      "epoch": 3.6731207289293852,
+      "grad_norm": 5.120173931121826,
+      "learning_rate": 9.516758867556136e-06,
+      "loss": 0.017,
+      "step": 6450
+    },
+    {
+      "epoch": 3.7015945330296125,
+      "grad_norm": 1.1922008991241455,
+      "learning_rate": 9.435405141555484e-06,
+      "loss": 0.0194,
+      "step": 6500
+    },
+    {
+      "epoch": 3.7300683371298406,
+      "grad_norm": 0.039439987391233444,
+      "learning_rate": 9.354051415554833e-06,
+      "loss": 0.0309,
+      "step": 6550
+    },
+    {
+      "epoch": 3.7585421412300684,
+      "grad_norm": 0.04055279493331909,
+      "learning_rate": 9.272697689554181e-06,
+      "loss": 0.0195,
+      "step": 6600
+    },
+    {
+      "epoch": 3.787015945330296,
+      "grad_norm": 0.5971085429191589,
+      "learning_rate": 9.191343963553533e-06,
+      "loss": 0.0156,
+      "step": 6650
+    },
+    {
+      "epoch": 3.8154897494305238,
+      "grad_norm": 0.2191866636276245,
+      "learning_rate": 9.10999023755288e-06,
+      "loss": 0.0174,
+      "step": 6700
+    },
+    {
+      "epoch": 3.8439635535307515,
+      "grad_norm": 0.033559828996658325,
+      "learning_rate": 9.02863651155223e-06,
+      "loss": 0.0149,
+      "step": 6750
+    },
+    {
+      "epoch": 3.8724373576309796,
+      "grad_norm": 3.7128634452819824,
+      "learning_rate": 8.947282785551578e-06,
+      "loss": 0.0221,
+      "step": 6800
+    },
+    {
+      "epoch": 3.9009111617312073,
+      "grad_norm": 0.08547580987215042,
+      "learning_rate": 8.865929059550928e-06,
+      "loss": 0.0153,
+      "step": 6850
+    },
+    {
+      "epoch": 3.929384965831435,
+      "grad_norm": 0.058124080300331116,
+      "learning_rate": 8.784575333550277e-06,
+      "loss": 0.0161,
+      "step": 6900
+    },
+    {
+      "epoch": 3.9578587699316627,
+      "grad_norm": 0.015579139813780785,
+      "learning_rate": 8.703221607549627e-06,
+      "loss": 0.011,
+      "step": 6950
+    },
+    {
+      "epoch": 3.9863325740318905,
+      "grad_norm": 0.12764935195446014,
+      "learning_rate": 8.621867881548975e-06,
+      "loss": 0.0166,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.9525329748802823,
+      "eval_loss": 0.04983380436897278,
+      "eval_precision": 0.9510149303808086,
+      "eval_recall": 0.9540558734432851,
+      "eval_runtime": 3.7495,
+      "eval_samples_per_second": 866.79,
+      "eval_steps_per_second": 108.549,
+      "step": 7024
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 12292,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1381501115682372.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-7024/training_args.bin b/checkpoint-7024/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5883d1e2ddb42c11dd6ad1fddc79d9ffe7a246f3
--- /dev/null
+++ b/checkpoint-7024/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e08f60c5260f286c88c6054e532ee0950cb5316081a3a51d07b57f6a266f71
+size 5368
diff --git a/checkpoint-8780/config.json b/checkpoint-8780/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f744ab25e17fedaffadd5fcb3ae10a7b9e4083bc
--- /dev/null
+++ b/checkpoint-8780/config.json
@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}
diff --git a/checkpoint-8780/model.safetensors b/checkpoint-8780/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..db41ce94478898eb99f37de35ed6a1e939782b7d
--- /dev/null
+++ b/checkpoint-8780/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d615235602767f4cfde51b1a188a54b5083d657570a6052102b84397d87dad48
+size 1109863956
diff --git a/checkpoint-8780/optimizer.pt b/checkpoint-8780/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9f1f397648a065b1410a62541096b5ea2ebde34e
--- /dev/null
+++ b/checkpoint-8780/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4274569bea9bc0a483b31f96a00b4d3062f2158c82027a814a4ac525cdd5e55e
+size 2219846202
diff --git a/checkpoint-8780/rng_state.pth b/checkpoint-8780/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..427922bb24fe67d1a43bf9a809f882bb59b71987
--- /dev/null
+++ b/checkpoint-8780/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d107323f4a2ea07f33aada80a6882ba4b85809248993851a21076ef56f91ddd
+size 14244
diff --git a/checkpoint-8780/scaler.pt b/checkpoint-8780/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bf937a7044c4e59d9b1e2b1257ff4802be72cc15
--- /dev/null
+++ b/checkpoint-8780/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f0698ad3d85f8bd4cbb53cb7a94efb3a21a83c224036fe2f15ec6148d3c6c6
+size 988
diff --git a/checkpoint-8780/scheduler.pt b/checkpoint-8780/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e2deded1f5ac35b82db5e1ec771d12adbd08c1da
--- /dev/null
+++ b/checkpoint-8780/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652940fd31d647532843bea47875013a7ecffe9de1753ce5cb1605324da74495
+size 1064
diff --git a/checkpoint-8780/special_tokens_map.json b/checkpoint-8780/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..d79c0fe029062eb03708803e72c3483296e2ea97
--- /dev/null
+++ b/checkpoint-8780/special_tokens_map.json
@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-8780/tokenizer.json b/checkpoint-8780/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..7126b1d228f6e5f725b6ee02a88b1118c725aeed
--- /dev/null
+++ b/checkpoint-8780/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734
diff --git a/checkpoint-8780/tokenizer_config.json b/checkpoint-8780/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d297107d53da62483767139822cf5ed3a6975e24
--- /dev/null
+++ b/checkpoint-8780/tokenizer_config.json
@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-8780/trainer_state.json b/checkpoint-8780/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..2bb81a9b70edce46c7d8e0ff48208c9929d12701
--- /dev/null
+++ b/checkpoint-8780/trainer_state.json
@@ -0,0 +1,1314 @@
+{
+  "best_global_step": 8780,
+  "best_metric": 0.9533444816053511,
+  "best_model_checkpoint": "C:\\Users\\Shara\\projects\\models\\run_16-lr_2e-05-acc_1-wd_0.01-bs_8-ep_7\\checkpoint-8780",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 8780,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02847380410022779,
+      "grad_norm": 4.8302321434021,
+      "learning_rate": 1.992840872111943e-05,
+      "loss": 0.9994,
+      "step": 50
+    },
+    {
+      "epoch": 0.05694760820045558,
+      "grad_norm": 3.4978649616241455,
+      "learning_rate": 1.9847054995118778e-05,
+      "loss": 0.3939,
+      "step": 100
+    },
+    {
+      "epoch": 0.08542141230068337,
+      "grad_norm": 8.353672981262207,
+      "learning_rate": 1.9765701269118128e-05,
+      "loss": 0.2882,
+      "step": 150
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "grad_norm": 9.822871208190918,
+      "learning_rate": 1.9684347543117477e-05,
+      "loss": 0.1728,
+      "step": 200
+    },
+    {
+      "epoch": 0.14236902050113895,
+      "grad_norm": 3.1411221027374268,
+      "learning_rate": 1.9602993817116827e-05,
+      "loss": 0.1251,
+      "step": 250
+    },
+    {
+      "epoch": 0.17084282460136674,
+      "grad_norm": 8.493424415588379,
+      "learning_rate": 1.9521640091116173e-05,
+      "loss": 0.1405,
+      "step": 300
+    },
+    {
+      "epoch": 0.19931662870159453,
+      "grad_norm": 4.757007122039795,
+      "learning_rate": 1.9440286365115523e-05,
+      "loss": 0.1431,
+      "step": 350
+    },
+    {
+      "epoch": 0.22779043280182232,
+      "grad_norm": 4.339049816131592,
+      "learning_rate": 1.9358932639114873e-05,
+      "loss": 0.0912,
+      "step": 400
+    },
+    {
+      "epoch": 0.25626423690205014,
+      "grad_norm": 14.540772438049316,
+      "learning_rate": 1.9277578913114222e-05,
+      "loss": 0.1048,
+      "step": 450
+    },
+    {
+      "epoch": 0.2847380410022779,
+      "grad_norm": 10.503073692321777,
+      "learning_rate": 1.9196225187113572e-05,
+      "loss": 0.1224,
+      "step": 500
+    },
+    {
+      "epoch": 0.3132118451025057,
+      "grad_norm": 2.738131284713745,
+      "learning_rate": 1.911487146111292e-05,
+      "loss": 0.1025,
+      "step": 550
+    },
+    {
+      "epoch": 0.3416856492027335,
+      "grad_norm": 6.681102752685547,
+      "learning_rate": 1.903351773511227e-05,
+      "loss": 0.0869,
+      "step": 600
+    },
+    {
+      "epoch": 0.3701594533029613,
+      "grad_norm": 1.4330339431762695,
+      "learning_rate": 1.895216400911162e-05,
+      "loss": 0.052,
+      "step": 650
+    },
+    {
+      "epoch": 0.39863325740318906,
+      "grad_norm": 2.581470012664795,
+      "learning_rate": 1.8870810283110967e-05,
+      "loss": 0.0808,
+      "step": 700
+    },
+    {
+      "epoch": 0.4271070615034169,
+      "grad_norm": 5.825100898742676,
+      "learning_rate": 1.8789456557110317e-05,
+      "loss": 0.0716,
+      "step": 750
+    },
+    {
+      "epoch": 0.45558086560364464,
+      "grad_norm": 1.74166738986969,
+      "learning_rate": 1.8708102831109666e-05,
+      "loss": 0.0806,
+      "step": 800
+    },
+    {
+      "epoch": 0.48405466970387245,
+      "grad_norm": 7.3097405433654785,
+      "learning_rate": 1.8626749105109016e-05,
+      "loss": 0.0666,
+      "step": 850
+    },
+    {
+      "epoch": 0.5125284738041003,
+      "grad_norm": 2.220766067504883,
+      "learning_rate": 1.8545395379108362e-05,
+      "loss": 0.0768,
+      "step": 900
+    },
+    {
+      "epoch": 0.541002277904328,
+      "grad_norm": 4.0566511154174805,
+      "learning_rate": 1.8464041653107715e-05,
+      "loss": 0.0707,
+      "step": 950
+    },
+    {
+      "epoch": 0.5694760820045558,
+      "grad_norm": 0.2833240330219269,
+      "learning_rate": 1.8382687927107065e-05,
+      "loss": 0.0858,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5979498861047836,
+      "grad_norm": 21.131481170654297,
+      "learning_rate": 1.8301334201106415e-05,
+      "loss": 0.0595,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6264236902050114,
+      "grad_norm": 27.655433654785156,
+      "learning_rate": 1.821998047510576e-05,
+      "loss": 0.0466,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6548974943052391,
+      "grad_norm": 3.4721717834472656,
+      "learning_rate": 1.813862674910511e-05,
+      "loss": 0.0776,
+      "step": 1150
+    },
+    {
+      "epoch": 0.683371298405467,
+      "grad_norm": 2.4811441898345947,
+      "learning_rate": 1.805727302310446e-05,
+      "loss": 0.0647,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7118451025056948,
+      "grad_norm": 6.169066429138184,
+      "learning_rate": 1.797591929710381e-05,
+      "loss": 0.0724,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7403189066059226,
+      "grad_norm": 8.984748840332031,
+      "learning_rate": 1.7894565571103156e-05,
+      "loss": 0.0838,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7687927107061503,
+      "grad_norm": 5.944505214691162,
+      "learning_rate": 1.7813211845102506e-05,
+      "loss": 0.0683,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7972665148063781,
+      "grad_norm": 0.28812381625175476,
+      "learning_rate": 1.7731858119101856e-05,
+      "loss": 0.0614,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8257403189066059,
+      "grad_norm": 6.176011085510254,
+      "learning_rate": 1.7650504393101205e-05,
+      "loss": 0.0615,
+      "step": 1450
+    },
+    {
+      "epoch": 0.8542141230068337,
+      "grad_norm": 2.5244405269622803,
+      "learning_rate": 1.7569150667100555e-05,
+      "loss": 0.0714,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8826879271070615,
+      "grad_norm": 3.3508074283599854,
+      "learning_rate": 1.7487796941099904e-05,
+      "loss": 0.0563,
+      "step": 1550
+    },
+    {
+      "epoch": 0.9111617312072893,
+      "grad_norm": 9.980842590332031,
+      "learning_rate": 1.7406443215099254e-05,
+      "loss": 0.0647,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9396355353075171,
+      "grad_norm": 3.6959774494171143,
+      "learning_rate": 1.7325089489098604e-05,
+      "loss": 0.0682,
+      "step": 1650
+    },
+    {
+      "epoch": 0.9681093394077449,
+      "grad_norm": 0.626620888710022,
+      "learning_rate": 1.724373576309795e-05,
+      "loss": 0.0499,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9965831435079726,
+      "grad_norm": 7.145672798156738,
+      "learning_rate": 1.71623820370973e-05,
+      "loss": 0.0569,
+      "step": 1750
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9242246437552389,
+      "eval_loss": 0.05600914731621742,
+      "eval_precision": 0.9206746826987308,
+      "eval_recall": 0.927802086839448,
+      "eval_runtime": 3.7538,
+      "eval_samples_per_second": 865.798,
+      "eval_steps_per_second": 108.425,
+      "step": 1756
+    },
+    {
+      "epoch": 1.0250569476082005,
+      "grad_norm": 4.280463695526123,
+      "learning_rate": 1.708102831109665e-05,
+      "loss": 0.0673,
+      "step": 1800
+    },
+    {
+      "epoch": 1.0535307517084282,
+      "grad_norm": 0.06692535430192947,
+      "learning_rate": 1.6999674585096e-05,
+      "loss": 0.0403,
+      "step": 1850
+    },
+    {
+      "epoch": 1.082004555808656,
+      "grad_norm": 0.03789375349879265,
+      "learning_rate": 1.691832085909535e-05,
+      "loss": 0.0496,
+      "step": 1900
+    },
+    {
+      "epoch": 1.1104783599088839,
+      "grad_norm": 3.698348045349121,
+      "learning_rate": 1.6836967133094698e-05,
+      "loss": 0.0381,
+      "step": 1950
+    },
+    {
+      "epoch": 1.1389521640091116,
+      "grad_norm": 2.753032684326172,
+      "learning_rate": 1.6755613407094048e-05,
+      "loss": 0.0432,
+      "step": 2000
+    },
+    {
+      "epoch": 1.1674259681093395,
+      "grad_norm": 0.06336130946874619,
+      "learning_rate": 1.6674259681093398e-05,
+      "loss": 0.0482,
+      "step": 2050
+    },
+    {
+      "epoch": 1.1958997722095672,
+      "grad_norm": 3.9503254890441895,
+      "learning_rate": 1.6592905955092744e-05,
+      "loss": 0.0436,
+      "step": 2100
+    },
+    {
+      "epoch": 1.224373576309795,
+      "grad_norm": 0.08679741621017456,
+      "learning_rate": 1.6511552229092093e-05,
+      "loss": 0.0346,
+      "step": 2150
+    },
+    {
+      "epoch": 1.2528473804100229,
+      "grad_norm": 2.1995127201080322,
+      "learning_rate": 1.6430198503091443e-05,
+      "loss": 0.0312,
+      "step": 2200
+    },
+    {
+      "epoch": 1.2813211845102506,
+      "grad_norm": 5.7709808349609375,
+      "learning_rate": 1.634884477709079e-05,
+      "loss": 0.032,
+      "step": 2250
+    },
+    {
+      "epoch": 1.3097949886104785,
+      "grad_norm": 0.2031829059123993,
+      "learning_rate": 1.626749105109014e-05,
+      "loss": 0.053,
+      "step": 2300
+    },
+    {
+      "epoch": 1.3382687927107062,
+      "grad_norm": 4.292157173156738,
+      "learning_rate": 1.6186137325089492e-05,
+      "loss": 0.0413,
+      "step": 2350
+    },
+    {
+      "epoch": 1.366742596810934,
+      "grad_norm": 0.07821401953697205,
+      "learning_rate": 1.6104783599088842e-05,
+      "loss": 0.0304,
+      "step": 2400
+    },
+    {
+      "epoch": 1.3952164009111616,
+      "grad_norm": 0.5930206179618835,
+      "learning_rate": 1.6023429873088188e-05,
+      "loss": 0.0525,
+      "step": 2450
+    },
+    {
+      "epoch": 1.4236902050113895,
+      "grad_norm": 1.6114712953567505,
+      "learning_rate": 1.5942076147087538e-05,
+      "loss": 0.0391,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4521640091116172,
+      "grad_norm": 0.28632065653800964,
+      "learning_rate": 1.5860722421086887e-05,
+      "loss": 0.0491,
+      "step": 2550
+    },
+    {
+      "epoch": 1.4806378132118452,
+      "grad_norm": 1.0017669200897217,
+      "learning_rate": 1.5779368695086237e-05,
+      "loss": 0.0395,
+      "step": 2600
+    },
+    {
+      "epoch": 1.5091116173120729,
+      "grad_norm": 0.03409272059798241,
+      "learning_rate": 1.5698014969085583e-05,
+      "loss": 0.0399,
+      "step": 2650
+    },
+    {
+      "epoch": 1.5375854214123006,
+      "grad_norm": 3.5108702182769775,
+      "learning_rate": 1.5616661243084933e-05,
+      "loss": 0.0424,
+      "step": 2700
+    },
+    {
+      "epoch": 1.5660592255125285,
+      "grad_norm": 3.5875349044799805,
+      "learning_rate": 1.5535307517084283e-05,
+      "loss": 0.0497,
+      "step": 2750
+    },
+    {
+      "epoch": 1.5945330296127562,
+      "grad_norm": 0.10498251020908356,
+      "learning_rate": 1.5453953791083632e-05,
+      "loss": 0.0461,
+      "step": 2800
+    },
+    {
+      "epoch": 1.6230068337129842,
+      "grad_norm": 7.618963718414307,
+      "learning_rate": 1.5374227139602996e-05,
+      "loss": 0.0394,
+      "step": 2850
+    },
+    {
+      "epoch": 1.6514806378132119,
+      "grad_norm": 3.3920793533325195,
+      "learning_rate": 1.5292873413602346e-05,
+      "loss": 0.0339,
+      "step": 2900
+    },
+    {
+      "epoch": 1.6799544419134396,
+      "grad_norm": 0.04736129939556122,
+      "learning_rate": 1.5211519687601692e-05,
+      "loss": 0.0358,
+      "step": 2950
+    },
+    {
+      "epoch": 1.7084282460136673,
+      "grad_norm": 0.17463508248329163,
+      "learning_rate": 1.5130165961601042e-05,
+      "loss": 0.034,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7369020501138952,
+      "grad_norm": 0.058148205280303955,
+      "learning_rate": 1.5048812235600392e-05,
+      "loss": 0.0317,
+      "step": 3050
+    },
+    {
+      "epoch": 1.7653758542141231,
+      "grad_norm": 3.5262815952301025,
+      "learning_rate": 1.4967458509599741e-05,
+      "loss": 0.0477,
+      "step": 3100
+    },
+    {
+      "epoch": 1.7938496583143508,
+      "grad_norm": 2.971937894821167,
+      "learning_rate": 1.488610478359909e-05,
+      "loss": 0.0364,
+      "step": 3150
+    },
+    {
+      "epoch": 1.8223234624145785,
+      "grad_norm": 0.05181724950671196,
+      "learning_rate": 1.4804751057598439e-05,
+      "loss": 0.0394,
+      "step": 3200
+    },
+    {
+      "epoch": 1.8507972665148062,
+      "grad_norm": 0.2712370455265045,
+      "learning_rate": 1.4723397331597789e-05,
+      "loss": 0.0456,
+      "step": 3250
+    },
+    {
+      "epoch": 1.8792710706150342,
+      "grad_norm": 1.608622431755066,
+      "learning_rate": 1.4642043605597138e-05,
+      "loss": 0.05,
+      "step": 3300
+    },
+    {
+      "epoch": 1.907744874715262,
+      "grad_norm": 5.2423529624938965,
+      "learning_rate": 1.4560689879596486e-05,
+      "loss": 0.0371,
+      "step": 3350
+    },
+    {
+      "epoch": 1.9362186788154898,
+      "grad_norm": 0.04786211624741554,
+      "learning_rate": 1.4479336153595836e-05,
+      "loss": 0.0329,
+      "step": 3400
+    },
+    {
+      "epoch": 1.9646924829157175,
+      "grad_norm": 0.5264931917190552,
+      "learning_rate": 1.4397982427595185e-05,
+      "loss": 0.0379,
+      "step": 3450
+    },
+    {
+      "epoch": 1.9931662870159452,
+      "grad_norm": 0.236006498336792,
+      "learning_rate": 1.4316628701594535e-05,
+      "loss": 0.0253,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9406438631790744,
+      "eval_loss": 0.05223705992102623,
+      "eval_precision": 0.9371867691279653,
+      "eval_recall": 0.9441265567149109,
+      "eval_runtime": 3.7109,
+      "eval_samples_per_second": 875.791,
+      "eval_steps_per_second": 109.676,
+      "step": 3512
+    },
+    {
+      "epoch": 2.021640091116173,
+      "grad_norm": 4.225963115692139,
+      "learning_rate": 1.4235274975593883e-05,
+      "loss": 0.0373,
+      "step": 3550
+    },
+    {
+      "epoch": 2.050113895216401,
+      "grad_norm": 0.15388111770153046,
+      "learning_rate": 1.4153921249593233e-05,
+      "loss": 0.0258,
+      "step": 3600
+    },
+    {
+      "epoch": 2.078587699316629,
+      "grad_norm": 6.3911895751953125,
+      "learning_rate": 1.4072567523592582e-05,
+      "loss": 0.0217,
+      "step": 3650
+    },
+    {
+      "epoch": 2.1070615034168565,
+      "grad_norm": 0.03075530007481575,
+      "learning_rate": 1.3991213797591932e-05,
+      "loss": 0.019,
+      "step": 3700
+    },
+    {
+      "epoch": 2.135535307517084,
+      "grad_norm": 0.16612432897090912,
+      "learning_rate": 1.3909860071591278e-05,
+      "loss": 0.0175,
+      "step": 3750
+    },
+    {
+      "epoch": 2.164009111617312,
+      "grad_norm": 0.14543022215366364,
+      "learning_rate": 1.382850634559063e-05,
+      "loss": 0.0289,
+      "step": 3800
+    },
+    {
+      "epoch": 2.19248291571754,
+      "grad_norm": 2.9880359172821045,
+      "learning_rate": 1.374715261958998e-05,
+      "loss": 0.0208,
+      "step": 3850
+    },
+    {
+      "epoch": 2.2209567198177678,
+      "grad_norm": 9.878133773803711,
+      "learning_rate": 1.3665798893589329e-05,
+      "loss": 0.021,
+      "step": 3900
+    },
+    {
+      "epoch": 2.2494305239179955,
+      "grad_norm": 9.684176445007324,
+      "learning_rate": 1.3584445167588675e-05,
+      "loss": 0.0267,
+      "step": 3950
+    },
+    {
+      "epoch": 2.277904328018223,
+      "grad_norm": 33.15859603881836,
+      "learning_rate": 1.3503091441588025e-05,
+      "loss": 0.0295,
+      "step": 4000
+    },
+    {
+      "epoch": 2.306378132118451,
+      "grad_norm": 2.559544086456299,
+      "learning_rate": 1.3421737715587374e-05,
+      "loss": 0.0292,
+      "step": 4050
+    },
+    {
+      "epoch": 2.334851936218679,
+      "grad_norm": 0.07091552764177322,
+      "learning_rate": 1.3340383989586724e-05,
+      "loss": 0.0262,
+      "step": 4100
+    },
+    {
+      "epoch": 2.3633257403189067,
+      "grad_norm": 1.8119585514068604,
+      "learning_rate": 1.3259030263586072e-05,
+      "loss": 0.03,
+      "step": 4150
+    },
+    {
+      "epoch": 2.3917995444191344,
+      "grad_norm": 0.1476636379957199,
+      "learning_rate": 1.3177676537585422e-05,
+      "loss": 0.0196,
+      "step": 4200
+    },
+    {
+      "epoch": 2.420273348519362,
+      "grad_norm": 0.04482650011777878,
+      "learning_rate": 1.3096322811584771e-05,
+      "loss": 0.0263,
+      "step": 4250
+    },
+    {
+      "epoch": 2.44874715261959,
+      "grad_norm": 0.09201560169458389,
+      "learning_rate": 1.3014969085584121e-05,
+      "loss": 0.0172,
+      "step": 4300
+    },
+    {
+      "epoch": 2.477220956719818,
+      "grad_norm": 0.02215876244008541,
+      "learning_rate": 1.2933615359583469e-05,
+      "loss": 0.0149,
+      "step": 4350
+    },
+    {
+      "epoch": 2.5056947608200457,
+      "grad_norm": 0.6993932127952576,
+      "learning_rate": 1.2852261633582819e-05,
+      "loss": 0.0331,
+      "step": 4400
+    },
+    {
+      "epoch": 2.5341685649202734,
+      "grad_norm": 0.030453965067863464,
+      "learning_rate": 1.2770907907582168e-05,
+      "loss": 0.0307,
+      "step": 4450
+    },
+    {
+      "epoch": 2.562642369020501,
+      "grad_norm": 0.22211593389511108,
+      "learning_rate": 1.2689554181581518e-05,
+      "loss": 0.0183,
+      "step": 4500
+    },
+    {
+      "epoch": 2.591116173120729,
+      "grad_norm": 1.2842738628387451,
+      "learning_rate": 1.2608200455580866e-05,
+      "loss": 0.0226,
+      "step": 4550
+    },
+    {
+      "epoch": 2.619589977220957,
+      "grad_norm": 3.9048423767089844,
+      "learning_rate": 1.2526846729580216e-05,
+      "loss": 0.0239,
+      "step": 4600
+    },
+    {
+      "epoch": 2.6480637813211843,
+      "grad_norm": 0.9887784719467163,
+      "learning_rate": 1.2445493003579565e-05,
+      "loss": 0.0271,
+      "step": 4650
+    },
+    {
+      "epoch": 2.6765375854214124,
+      "grad_norm": 4.759728908538818,
+      "learning_rate": 1.2364139277578915e-05,
+      "loss": 0.0201,
+      "step": 4700
+    },
+    {
+      "epoch": 2.70501138952164,
+      "grad_norm": 0.2671191096305847,
+      "learning_rate": 1.2282785551578263e-05,
+      "loss": 0.0212,
+      "step": 4750
+    },
+    {
+      "epoch": 2.733485193621868,
+      "grad_norm": 0.036626849323511124,
+      "learning_rate": 1.2201431825577612e-05,
+      "loss": 0.0155,
+      "step": 4800
+    },
+    {
+      "epoch": 2.7619589977220955,
+      "grad_norm": 6.877408027648926,
+      "learning_rate": 1.2120078099576962e-05,
+      "loss": 0.0266,
+      "step": 4850
+    },
+    {
+      "epoch": 2.7904328018223232,
+      "grad_norm": 4.725896835327148,
+      "learning_rate": 1.2038724373576312e-05,
+      "loss": 0.0163,
+      "step": 4900
+    },
+    {
+      "epoch": 2.8189066059225514,
+      "grad_norm": 0.11965059489011765,
+      "learning_rate": 1.195737064757566e-05,
+      "loss": 0.0246,
+      "step": 4950
+    },
+    {
+      "epoch": 2.847380410022779,
+      "grad_norm": 0.6634079813957214,
+      "learning_rate": 1.187601692157501e-05,
+      "loss": 0.0304,
+      "step": 5000
+    },
+    {
+      "epoch": 2.875854214123007,
+      "grad_norm": 3.952694892883301,
+      "learning_rate": 1.1794663195574359e-05,
+      "loss": 0.0183,
+      "step": 5050
+    },
+    {
+      "epoch": 2.9043280182232345,
+      "grad_norm": 19.788942337036133,
+      "learning_rate": 1.1713309469573709e-05,
+      "loss": 0.0193,
+      "step": 5100
+    },
+    {
+      "epoch": 2.932801822323462,
+      "grad_norm": 4.989261627197266,
+      "learning_rate": 1.1631955743573055e-05,
+      "loss": 0.023,
+      "step": 5150
+    },
+    {
+      "epoch": 2.9612756264236904,
+      "grad_norm": 9.020853996276855,
+      "learning_rate": 1.1550602017572406e-05,
+      "loss": 0.0231,
+      "step": 5200
+    },
+    {
+      "epoch": 2.989749430523918,
+      "grad_norm": 0.9151140451431274,
+      "learning_rate": 1.1469248291571756e-05,
+      "loss": 0.0314,
+      "step": 5250
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.9470420646891236,
+      "eval_loss": 0.04870199039578438,
+      "eval_precision": 0.943090787716956,
+      "eval_recall": 0.9510265903736116,
+      "eval_runtime": 3.7494,
+      "eval_samples_per_second": 866.805,
+      "eval_steps_per_second": 108.551,
+      "step": 5268
+    },
+    {
+      "epoch": 3.0182232346241458,
+      "grad_norm": 8.62992000579834,
+      "learning_rate": 1.1387894565571106e-05,
+      "loss": 0.0194,
+      "step": 5300
+    },
+    {
+      "epoch": 3.0466970387243735,
+      "grad_norm": 0.5615554451942444,
+      "learning_rate": 1.1306540839570452e-05,
+      "loss": 0.0114,
+      "step": 5350
+    },
+    {
+      "epoch": 3.075170842824601,
+      "grad_norm": 2.5735936164855957,
+      "learning_rate": 1.1225187113569801e-05,
+      "loss": 0.0163,
+      "step": 5400
+    },
+    {
+      "epoch": 3.1036446469248293,
+      "grad_norm": 6.504094123840332,
+      "learning_rate": 1.1143833387569151e-05,
+      "loss": 0.0135,
+      "step": 5450
+    },
+    {
+      "epoch": 3.132118451025057,
+      "grad_norm": 14.477537155151367,
+      "learning_rate": 1.10624796615685e-05,
+      "loss": 0.0129,
+      "step": 5500
+    },
+    {
+      "epoch": 3.1605922551252847,
+      "grad_norm": 0.04929841682314873,
+      "learning_rate": 1.0981125935567849e-05,
+      "loss": 0.0263,
+      "step": 5550
+    },
+    {
+      "epoch": 3.1890660592255125,
+      "grad_norm": 0.08875144273042679,
+      "learning_rate": 1.0899772209567198e-05,
+      "loss": 0.0134,
+      "step": 5600
+    },
+    {
+      "epoch": 3.21753986332574,
+      "grad_norm": 0.6238455772399902,
+      "learning_rate": 1.0818418483566548e-05,
+      "loss": 0.0107,
+      "step": 5650
+    },
+    {
+      "epoch": 3.2460136674259683,
+      "grad_norm": 0.004948179703205824,
+      "learning_rate": 1.0737064757565898e-05,
+      "loss": 0.0167,
+      "step": 5700
+    },
+    {
+      "epoch": 3.274487471526196,
+      "grad_norm": 0.017031218856573105,
+      "learning_rate": 1.0655711031565246e-05,
+      "loss": 0.0085,
+      "step": 5750
+    },
+    {
+      "epoch": 3.3029612756264237,
+      "grad_norm": 2.9840469360351562,
+      "learning_rate": 1.0574357305564595e-05,
+      "loss": 0.0158,
+      "step": 5800
+    },
+    {
+      "epoch": 3.3314350797266514,
+      "grad_norm": 1.7477540969848633,
+      "learning_rate": 1.0493003579563945e-05,
+      "loss": 0.0157,
+      "step": 5850
+    },
+    {
+      "epoch": 3.359908883826879,
+      "grad_norm": 0.03963543102145195,
+      "learning_rate": 1.0411649853563295e-05,
+      "loss": 0.0201,
+      "step": 5900
+    },
+    {
+      "epoch": 3.3883826879271073,
+      "grad_norm": 0.16669808328151703,
+      "learning_rate": 1.0330296127562643e-05,
+      "loss": 0.0159,
+      "step": 5950
+    },
+    {
+      "epoch": 3.416856492027335,
+      "grad_norm": 0.01953568309545517,
+      "learning_rate": 1.0248942401561992e-05,
+      "loss": 0.0117,
+      "step": 6000
+    },
+    {
+      "epoch": 3.4453302961275627,
+      "grad_norm": 0.07708246260881424,
+      "learning_rate": 1.0167588675561342e-05,
+      "loss": 0.0117,
+      "step": 6050
+    },
+    {
+      "epoch": 3.4738041002277904,
+      "grad_norm": 2.423590898513794,
+      "learning_rate": 1.0086234949560691e-05,
+      "loss": 0.0111,
+      "step": 6100
+    },
+    {
+      "epoch": 3.502277904328018,
+      "grad_norm": 0.006337775848805904,
+      "learning_rate": 1.000488122356004e-05,
+      "loss": 0.0052,
+      "step": 6150
+    },
+    {
+      "epoch": 3.5307517084282463,
+      "grad_norm": 0.01373753696680069,
+      "learning_rate": 9.923527497559389e-06,
+      "loss": 0.009,
+      "step": 6200
+    },
+    {
+      "epoch": 3.559225512528474,
+      "grad_norm": 0.11260247975587845,
+      "learning_rate": 9.842173771558739e-06,
+      "loss": 0.0208,
+      "step": 6250
+    },
+    {
+      "epoch": 3.5876993166287017,
+      "grad_norm": 1.240822196006775,
+      "learning_rate": 9.760820045558087e-06,
+      "loss": 0.0157,
+      "step": 6300
+    },
+    {
+      "epoch": 3.6161731207289294,
+      "grad_norm": 0.05271293595433235,
+      "learning_rate": 9.679466319557436e-06,
+      "loss": 0.0175,
+      "step": 6350
+    },
+    {
+      "epoch": 3.644646924829157,
+      "grad_norm": 24.546663284301758,
+      "learning_rate": 9.598112593556786e-06,
+      "loss": 0.015,
+      "step": 6400
+    },
+    {
+      "epoch": 3.6731207289293852,
+      "grad_norm": 5.120173931121826,
+      "learning_rate": 9.516758867556136e-06,
+      "loss": 0.017,
+      "step": 6450
+    },
+    {
+      "epoch": 3.7015945330296125,
+      "grad_norm": 1.1922008991241455,
+      "learning_rate": 9.435405141555484e-06,
+      "loss": 0.0194,
+      "step": 6500
+    },
+    {
+      "epoch": 3.7300683371298406,
+      "grad_norm": 0.039439987391233444,
+      "learning_rate": 9.354051415554833e-06,
+      "loss": 0.0309,
+      "step": 6550
+    },
+    {
+      "epoch": 3.7585421412300684,
+      "grad_norm": 0.04055279493331909,
+      "learning_rate": 9.272697689554181e-06,
+      "loss": 0.0195,
+      "step": 6600
+    },
+    {
+      "epoch": 3.787015945330296,
+      "grad_norm": 0.5971085429191589,
+      "learning_rate": 9.191343963553533e-06,
+      "loss": 0.0156,
+      "step": 6650
+    },
+    {
+      "epoch": 3.8154897494305238,
+      "grad_norm": 0.2191866636276245,
+      "learning_rate": 9.10999023755288e-06,
+      "loss": 0.0174,
+      "step": 6700
+    },
+    {
+      "epoch": 3.8439635535307515,
+      "grad_norm": 0.033559828996658325,
+      "learning_rate": 9.02863651155223e-06,
+      "loss": 0.0149,
+      "step": 6750
+    },
+    {
+      "epoch": 3.8724373576309796,
+      "grad_norm": 3.7128634452819824,
+      "learning_rate": 8.947282785551578e-06,
+      "loss": 0.0221,
+      "step": 6800
+    },
+    {
+      "epoch": 3.9009111617312073,
+      "grad_norm": 0.08547580987215042,
+      "learning_rate": 8.865929059550928e-06,
+      "loss": 0.0153,
+      "step": 6850
+    },
+    {
+      "epoch": 3.929384965831435,
+      "grad_norm": 0.058124080300331116,
+      "learning_rate": 8.784575333550277e-06,
+      "loss": 0.0161,
+      "step": 6900
+    },
+    {
+      "epoch": 3.9578587699316627,
+      "grad_norm": 0.015579139813780785,
+      "learning_rate": 8.703221607549627e-06,
+      "loss": 0.011,
+      "step": 6950
+    },
+    {
+      "epoch": 3.9863325740318905,
+      "grad_norm": 0.12764935195446014,
+      "learning_rate": 8.621867881548975e-06,
+      "loss": 0.0166,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.9525329748802823,
+      "eval_loss": 0.04983380436897278,
+      "eval_precision": 0.9510149303808086,
+      "eval_recall": 0.9540558734432851,
+      "eval_runtime": 3.7495,
+      "eval_samples_per_second": 866.79,
+      "eval_steps_per_second": 108.549,
+      "step": 7024
+    },
+    {
+      "epoch": 4.014806378132119,
+      "grad_norm": 0.04521024227142334,
+      "learning_rate": 8.540514155548325e-06,
+      "loss": 0.0102,
+      "step": 7050
+    },
+    {
+      "epoch": 4.043280182232346,
+      "grad_norm": 0.015535669401288033,
+      "learning_rate": 8.459160429547674e-06,
+      "loss": 0.0068,
+      "step": 7100
+    },
+    {
+      "epoch": 4.071753986332574,
+      "grad_norm": 12.566010475158691,
+      "learning_rate": 8.377806703547024e-06,
+      "loss": 0.0151,
+      "step": 7150
+    },
+    {
+      "epoch": 4.100227790432802,
+      "grad_norm": 0.027761396020650864,
+      "learning_rate": 8.296452977546372e-06,
+      "loss": 0.0053,
+      "step": 7200
+    },
+    {
+      "epoch": 4.128701594533029,
+      "grad_norm": 1.8846938610076904,
+      "learning_rate": 8.215099251545722e-06,
+      "loss": 0.0077,
+      "step": 7250
+    },
+    {
+      "epoch": 4.157175398633258,
+      "grad_norm": 0.005013479385524988,
+      "learning_rate": 8.13374552554507e-06,
+      "loss": 0.0073,
+      "step": 7300
+    },
+    {
+      "epoch": 4.185649202733485,
+      "grad_norm": 0.32696235179901123,
+      "learning_rate": 8.052391799544421e-06,
+      "loss": 0.0092,
+      "step": 7350
+    },
+    {
+      "epoch": 4.214123006833713,
+      "grad_norm": 0.014357910491526127,
+      "learning_rate": 7.971038073543769e-06,
+      "loss": 0.0164,
+      "step": 7400
+    },
+    {
+      "epoch": 4.242596810933941,
+      "grad_norm": 0.010845329612493515,
+      "learning_rate": 7.889684347543118e-06,
+      "loss": 0.0123,
+      "step": 7450
+    },
+    {
+      "epoch": 4.271070615034168,
+      "grad_norm": 0.6969354748725891,
+      "learning_rate": 7.808330621542466e-06,
+      "loss": 0.0103,
+      "step": 7500
+    },
+    {
+      "epoch": 4.2995444191343966,
+      "grad_norm": 0.3575742840766907,
+      "learning_rate": 7.726976895541816e-06,
+      "loss": 0.0161,
+      "step": 7550
+    },
+    {
+      "epoch": 4.328018223234624,
+      "grad_norm": 0.008076228201389313,
+      "learning_rate": 7.645623169541166e-06,
+      "loss": 0.0122,
+      "step": 7600
+    },
+    {
+      "epoch": 4.356492027334852,
+      "grad_norm": 0.029101597145199776,
+      "learning_rate": 7.564269443540515e-06,
+      "loss": 0.0071,
+      "step": 7650
+    },
+    {
+      "epoch": 4.38496583143508,
+      "grad_norm": 0.06841142475605011,
+      "learning_rate": 7.482915717539863e-06,
+      "loss": 0.0091,
+      "step": 7700
+    },
+    {
+      "epoch": 4.413439635535307,
+      "grad_norm": 0.04133535176515579,
+      "learning_rate": 7.401561991539213e-06,
+      "loss": 0.0073,
+      "step": 7750
+    },
+    {
+      "epoch": 4.4419134396355355,
+      "grad_norm": 0.03571132943034172,
+      "learning_rate": 7.320208265538562e-06,
+      "loss": 0.0131,
+      "step": 7800
+    },
+    {
+      "epoch": 4.470387243735763,
+      "grad_norm": 2.8286924362182617,
+      "learning_rate": 7.2388545395379114e-06,
+      "loss": 0.0043,
+      "step": 7850
+    },
+    {
+      "epoch": 4.498861047835991,
+      "grad_norm": 1.3785158395767212,
+      "learning_rate": 7.15750081353726e-06,
+      "loss": 0.0103,
+      "step": 7900
+    },
+    {
+      "epoch": 4.527334851936219,
+      "grad_norm": 0.05979786813259125,
+      "learning_rate": 7.07614708753661e-06,
+      "loss": 0.006,
+      "step": 7950
+    },
+    {
+      "epoch": 4.555808656036446,
+      "grad_norm": 1.3434393405914307,
+      "learning_rate": 6.994793361535959e-06,
+      "loss": 0.0148,
+      "step": 8000
+    },
+    {
+      "epoch": 4.5842824601366745,
+      "grad_norm": 0.019605603069067,
+      "learning_rate": 6.913439635535308e-06,
+      "loss": 0.0068,
+      "step": 8050
+    },
+    {
+      "epoch": 4.612756264236902,
+      "grad_norm": 0.0028891051188111305,
+      "learning_rate": 6.832085909534657e-06,
+      "loss": 0.0075,
+      "step": 8100
+    },
+    {
+      "epoch": 4.64123006833713,
+      "grad_norm": 0.014856363646686077,
+      "learning_rate": 6.750732183534007e-06,
+      "loss": 0.0073,
+      "step": 8150
+    },
+    {
+      "epoch": 4.669703872437358,
+      "grad_norm": 0.0037149768322706223,
+      "learning_rate": 6.669378457533356e-06,
+      "loss": 0.0066,
+      "step": 8200
+    },
+    {
+      "epoch": 4.698177676537585,
+      "grad_norm": 0.008534993045032024,
+      "learning_rate": 6.588024731532705e-06,
+      "loss": 0.0121,
+      "step": 8250
+    },
+    {
+      "epoch": 4.7266514806378135,
+      "grad_norm": 0.013920712284743786,
+      "learning_rate": 6.506671005532054e-06,
+      "loss": 0.013,
+      "step": 8300
+    },
+    {
+      "epoch": 4.755125284738041,
+      "grad_norm": 0.10121840238571167,
+      "learning_rate": 6.425317279531404e-06,
+      "loss": 0.0087,
+      "step": 8350
+    },
+    {
+      "epoch": 4.783599088838269,
+      "grad_norm": 0.07937771081924438,
+      "learning_rate": 6.343963553530752e-06,
+      "loss": 0.0086,
+      "step": 8400
+    },
+    {
+      "epoch": 4.812072892938497,
+      "grad_norm": 0.07674901187419891,
+      "learning_rate": 6.262609827530101e-06,
+      "loss": 0.0052,
+      "step": 8450
+    },
+    {
+      "epoch": 4.840546697038724,
+      "grad_norm": 0.06683178246021271,
+      "learning_rate": 6.18125610152945e-06,
+      "loss": 0.015,
+      "step": 8500
+    },
+    {
+      "epoch": 4.8690205011389525,
+      "grad_norm": 0.08861212432384491,
+      "learning_rate": 6.0999023755288e-06,
+      "loss": 0.0109,
+      "step": 8550
+    },
+    {
+      "epoch": 4.89749430523918,
+      "grad_norm": 0.006198623217642307,
+      "learning_rate": 6.018548649528149e-06,
+      "loss": 0.0181,
+      "step": 8600
+    },
+    {
+      "epoch": 4.925968109339408,
+      "grad_norm": 0.009029284119606018,
+      "learning_rate": 5.937194923527498e-06,
+      "loss": 0.0043,
+      "step": 8650
+    },
+    {
+      "epoch": 4.954441913439636,
+      "grad_norm": 1.1225602626800537,
+      "learning_rate": 5.855841197526847e-06,
+      "loss": 0.0121,
+      "step": 8700
+    },
+    {
+      "epoch": 4.982915717539863,
+      "grad_norm": 0.01218325924128294,
+      "learning_rate": 5.774487471526197e-06,
+      "loss": 0.0115,
+      "step": 8750
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.9533444816053511,
+      "eval_loss": 0.04722925275564194,
+      "eval_precision": 0.9473246925889,
+      "eval_recall": 0.9594412655671491,
+      "eval_runtime": 3.7358,
+      "eval_samples_per_second": 869.968,
+      "eval_steps_per_second": 108.947,
+      "step": 8780
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 12292,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1726265217515580.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-8780/training_args.bin b/checkpoint-8780/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5883d1e2ddb42c11dd6ad1fddc79d9ffe7a246f3
--- /dev/null
+++ b/checkpoint-8780/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e08f60c5260f286c88c6054e532ee0950cb5316081a3a51d07b57f6a266f71
+size 5368
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f744ab25e17fedaffadd5fcb3ae10a7b9e4083bc
--- /dev/null
+++ b/config.json
@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9138b6f1834a9abd518339bbab61b5b8559c4607
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3aa01fa5d49602728eca2190fb610b286d4348c8e470e053f83959dfd91049
+size 1109863956
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..d79c0fe029062eb03708803e72c3483296e2ea97
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..7126b1d228f6e5f725b6ee02a88b1118c725aeed
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d297107d53da62483767139822cf5ed3a6975e24
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..5883d1e2ddb42c11dd6ad1fddc79d9ffe7a246f3
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e08f60c5260f286c88c6054e532ee0950cb5316081a3a51d07b57f6a266f71
+size 5368
diff --git a/training_log.txt b/training_log.txt
new file mode 100644
index 0000000000000000000000000000000000000000..602c6d92b9b71a6668f77754a882b5cb41b8d37d
--- /dev/null
+++ b/training_log.txt
@@ -0,0 +1,18 @@
+Run 16 Hyperparameters:
+  Learning Rate: 2e-05
+  Gradient Accumulation Steps: 1
+  Weight Decay: 0.01
+  Batch Size: 8
+  Epochs: 7
+
+Evaluation Metrics:
+  Eval Loss: 0.052909377962350845
+  Eval Precision: 0.9515242378810594
+  Eval Recall: 0.9612924941097274
+  Eval F1: 0.9563834240267894
+
+Test Set Evaluation Results for Run 16:
+  Test Loss: 0.19122998416423798
+  Test Precision: 0.9052686671318911
+  Test Recall: 0.9187322946175638
+  Test F1: 0.9119507908611598