Upload 11 files

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c0bb10949406cb6df26debebce6c9656292ed2b60159c6198cd5ac24eae851
+size 538970204

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f85619284e424f80785941a7c41bf6472c0b35bd3ed0af33e104d8e7f80402
+size 1078001210

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c40320c990f6d4f4b1a7f099cce71625488a96db8ee382390e1c67b6493ad17
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6bf7bee8311866377924a92ff23fd8566865c824dac56b32549b589e46b209
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,857 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.704444837967062,
+  "eval_steps": 1000,
+  "global_step": 38500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 11.598106384277344,
+      "learning_rate": 1.9873510587163855e-05,
+      "loss": 0.7232,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04,
+      "eval_LOC_f1": 0.6290546246963268,
+      "eval_ORG_f1": 0.5215345154455224,
+      "eval_PER_f1": 0.6879167213048609,
+      "eval_loss": 0.5066247582435608,
+      "eval_overall_accuracy": 0.8370397334429099,
+      "eval_overall_f1": 0.6156872111156381,
+      "eval_overall_precision": 0.6129916634028982,
+      "eval_overall_recall": 0.6184065701464736,
+      "eval_runtime": 273.4377,
+      "eval_samples_per_second": 240.274,
+      "eval_steps_per_second": 1.88,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 10.799552917480469,
+      "learning_rate": 1.974702117432771e-05,
+      "loss": 0.5027,
+      "step": 2000
+    },
+    {
+      "epoch": 0.09,
+      "eval_LOC_f1": 0.7183374430474798,
+      "eval_ORG_f1": 0.5772430933256492,
+      "eval_PER_f1": 0.7319963163818684,
+      "eval_loss": 0.4309352934360504,
+      "eval_overall_accuracy": 0.8618575027245279,
+      "eval_overall_f1": 0.6810770980734424,
+      "eval_overall_precision": 0.6907076628408085,
+      "eval_overall_recall": 0.6717113989783535,
+      "eval_runtime": 510.4367,
+      "eval_samples_per_second": 128.713,
+      "eval_steps_per_second": 1.007,
+      "step": 2000
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 6.027167797088623,
+      "learning_rate": 1.9620531761491565e-05,
+      "loss": 0.4459,
+      "step": 3000
+    },
+    {
+      "epoch": 0.13,
+      "eval_LOC_f1": 0.725799810401126,
+      "eval_ORG_f1": 0.6044215496887744,
+      "eval_PER_f1": 0.7564098621149212,
+      "eval_loss": 0.40737923979759216,
+      "eval_overall_accuracy": 0.867908783401521,
+      "eval_overall_f1": 0.7006346252072851,
+      "eval_overall_precision": 0.6948635032545487,
+      "eval_overall_recall": 0.706502413004826,
+      "eval_runtime": 385.809,
+      "eval_samples_per_second": 170.292,
+      "eval_steps_per_second": 1.332,
+      "step": 3000
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.919013023376465,
+      "learning_rate": 1.949404234865542e-05,
+      "loss": 0.4238,
+      "step": 4000
+    },
+    {
+      "epoch": 0.18,
+      "eval_LOC_f1": 0.7514409560614181,
+      "eval_ORG_f1": 0.6140201882946715,
+      "eval_PER_f1": 0.7751705876362154,
+      "eval_loss": 0.3706400394439697,
+      "eval_overall_accuracy": 0.8801371494589654,
+      "eval_overall_f1": 0.7200897664191354,
+      "eval_overall_precision": 0.711405652907357,
+      "eval_overall_recall": 0.7289885135325826,
+      "eval_runtime": 364.1549,
+      "eval_samples_per_second": 180.418,
+      "eval_steps_per_second": 1.411,
+      "step": 4000
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.984628677368164,
+      "learning_rate": 1.9367552935819272e-05,
+      "loss": 0.3889,
+      "step": 5000
+    },
+    {
+      "epoch": 0.22,
+      "eval_LOC_f1": 0.747598650693943,
+      "eval_ORG_f1": 0.6493777882131956,
+      "eval_PER_f1": 0.7714610460826736,
+      "eval_loss": 0.3741539716720581,
+      "eval_overall_accuracy": 0.8788552814154443,
+      "eval_overall_f1": 0.7267549997033853,
+      "eval_overall_precision": 0.7189698622570512,
+      "eval_overall_recall": 0.7347105805322722,
+      "eval_runtime": 381.1257,
+      "eval_samples_per_second": 172.384,
+      "eval_steps_per_second": 1.349,
+      "step": 5000
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 9.616731643676758,
+      "learning_rate": 1.924106352298313e-05,
+      "loss": 0.3741,
+      "step": 6000
+    },
+    {
+      "epoch": 0.27,
+      "eval_LOC_f1": 0.7834622535184133,
+      "eval_ORG_f1": 0.6557229099335325,
+      "eval_PER_f1": 0.7861336370240923,
+      "eval_loss": 0.34435510635375977,
+      "eval_overall_accuracy": 0.8897586038506661,
+      "eval_overall_f1": 0.7479976639412649,
+      "eval_overall_precision": 0.7372337801167668,
+      "eval_overall_recall": 0.7590805181610363,
+      "eval_runtime": 322.2713,
+      "eval_samples_per_second": 203.866,
+      "eval_steps_per_second": 1.595,
+      "step": 6000
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 23.724206924438477,
+      "learning_rate": 1.9114574110146982e-05,
+      "loss": 0.3565,
+      "step": 7000
+    },
+    {
+      "epoch": 0.31,
+      "eval_LOC_f1": 0.7660811273670305,
+      "eval_ORG_f1": 0.6701080291970803,
+      "eval_PER_f1": 0.8082118790158281,
+      "eval_loss": 0.3384684920310974,
+      "eval_overall_accuracy": 0.893588575444113,
+      "eval_overall_f1": 0.7513199894189224,
+      "eval_overall_precision": 0.7511583787634086,
+      "eval_overall_recall": 0.751481669630006,
+      "eval_runtime": 380.8076,
+      "eval_samples_per_second": 172.528,
+      "eval_steps_per_second": 1.35,
+      "step": 7000
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 12.36683177947998,
+      "learning_rate": 1.8988084697310836e-05,
+      "loss": 0.3438,
+      "step": 8000
+    },
+    {
+      "epoch": 0.35,
+      "eval_LOC_f1": 0.7931912766836788,
+      "eval_ORG_f1": 0.6588008889092534,
+      "eval_PER_f1": 0.801709206691627,
+      "eval_loss": 0.33696234226226807,
+      "eval_overall_accuracy": 0.8917491469101174,
+      "eval_overall_f1": 0.7552752293577981,
+      "eval_overall_precision": 0.7441655025063686,
+      "eval_overall_recall": 0.7667217001100669,
+      "eval_runtime": 319.19,
+      "eval_samples_per_second": 205.834,
+      "eval_steps_per_second": 1.61,
+      "step": 8000
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 11.394143104553223,
+      "learning_rate": 1.8861595284474693e-05,
+      "loss": 0.3371,
+      "step": 9000
+    },
+    {
+      "epoch": 0.4,
+      "eval_LOC_f1": 0.7949055775142732,
+      "eval_ORG_f1": 0.69052384904555,
+      "eval_PER_f1": 0.8017390414812541,
+      "eval_loss": 0.3417092263698578,
+      "eval_overall_accuracy": 0.8959111238156492,
+      "eval_overall_f1": 0.7671861870625006,
+      "eval_overall_precision": 0.7645921077527909,
+      "eval_overall_recall": 0.7697979284847458,
+      "eval_runtime": 381.3721,
+      "eval_samples_per_second": 172.273,
+      "eval_steps_per_second": 1.348,
+      "step": 9000
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.7753918170928955,
+      "learning_rate": 1.8735105871638546e-05,
+      "loss": 0.3352,
+      "step": 10000
+    },
+    {
+      "epoch": 0.44,
+      "eval_LOC_f1": 0.797682178676422,
+      "eval_ORG_f1": 0.6847098624696625,
+      "eval_PER_f1": 0.8165334907549915,
+      "eval_loss": 0.30863526463508606,
+      "eval_overall_accuracy": 0.8984957032855126,
+      "eval_overall_f1": 0.7713626684335284,
+      "eval_overall_precision": 0.7747418167842222,
+      "eval_overall_recall": 0.7680128693590721,
+      "eval_runtime": 353.766,
+      "eval_samples_per_second": 185.716,
+      "eval_steps_per_second": 1.453,
+      "step": 10000
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 4.4588704109191895,
+      "learning_rate": 1.86086164588024e-05,
+      "loss": 0.3294,
+      "step": 11000
+    },
+    {
+      "epoch": 0.49,
+      "eval_LOC_f1": 0.8038860433458362,
+      "eval_ORG_f1": 0.6876538381909779,
+      "eval_PER_f1": 0.8135372012007188,
+      "eval_loss": 0.3306277096271515,
+      "eval_overall_accuracy": 0.8961009474806305,
+      "eval_overall_f1": 0.7722079415779226,
+      "eval_overall_precision": 0.7585587302451574,
+      "eval_overall_recall": 0.7863573504924788,
+      "eval_runtime": 386.1174,
+      "eval_samples_per_second": 170.155,
+      "eval_steps_per_second": 1.331,
+      "step": 11000
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.8787571787834167,
+      "learning_rate": 1.8482127045966253e-05,
+      "loss": 0.3164,
+      "step": 12000
+    },
+    {
+      "epoch": 0.53,
+      "eval_LOC_f1": 0.7928661730178796,
+      "eval_ORG_f1": 0.6923009590976729,
+      "eval_PER_f1": 0.8189351776068096,
+      "eval_loss": 0.32749465107917786,
+      "eval_overall_accuracy": 0.8991314264615677,
+      "eval_overall_f1": 0.7738191399005043,
+      "eval_overall_precision": 0.7606578382394035,
+      "eval_overall_recall": 0.7874439082211497,
+      "eval_runtime": 369.9388,
+      "eval_samples_per_second": 177.597,
+      "eval_steps_per_second": 1.389,
+      "step": 12000
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 7.5162811279296875,
+      "learning_rate": 1.8355637633130106e-05,
+      "loss": 0.3248,
+      "step": 13000
+    },
+    {
+      "epoch": 0.58,
+      "eval_LOC_f1": 0.8073569920769398,
+      "eval_ORG_f1": 0.6888664253138371,
+      "eval_PER_f1": 0.813194105996661,
+      "eval_loss": 0.31697988510131836,
+      "eval_overall_accuracy": 0.9009842543130915,
+      "eval_overall_f1": 0.7742117470068326,
+      "eval_overall_precision": 0.7643891570738953,
+      "eval_overall_recall": 0.7842900685801372,
+      "eval_runtime": 387.7862,
+      "eval_samples_per_second": 169.423,
+      "eval_steps_per_second": 1.325,
+      "step": 13000
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 15.765552520751953,
+      "learning_rate": 1.8229148220293963e-05,
+      "loss": 0.3031,
+      "step": 14000
+    },
+    {
+      "epoch": 0.62,
+      "eval_LOC_f1": 0.8060124842017926,
+      "eval_ORG_f1": 0.7039925586720092,
+      "eval_PER_f1": 0.8251789914844223,
+      "eval_loss": 0.3116307258605957,
+      "eval_overall_accuracy": 0.9031675986636414,
+      "eval_overall_f1": 0.7825302431386867,
+      "eval_overall_precision": 0.7787194499951092,
+      "eval_overall_recall": 0.7863785172014789,
+      "eval_runtime": 393.4395,
+      "eval_samples_per_second": 166.989,
+      "eval_steps_per_second": 1.306,
+      "step": 14000
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 7.4173808097839355,
+      "learning_rate": 1.8102658807457817e-05,
+      "loss": 0.3215,
+      "step": 15000
+    },
+    {
+      "epoch": 0.66,
+      "eval_LOC_f1": 0.8202011293152209,
+      "eval_ORG_f1": 0.7058145261059131,
+      "eval_PER_f1": 0.831773061514806,
+      "eval_loss": 0.2920757532119751,
+      "eval_overall_accuracy": 0.9057320791572127,
+      "eval_overall_f1": 0.7904764259051951,
+      "eval_overall_precision": 0.791295187324571,
+      "eval_overall_recall": 0.7896593570964919,
+      "eval_runtime": 358.5756,
+      "eval_samples_per_second": 183.225,
+      "eval_steps_per_second": 1.433,
+      "step": 15000
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 2.693660259246826,
+      "learning_rate": 1.7976169394621674e-05,
+      "loss": 0.3004,
+      "step": 16000
+    },
+    {
+      "epoch": 0.71,
+      "eval_LOC_f1": 0.820160121404321,
+      "eval_ORG_f1": 0.7145462460731136,
+      "eval_PER_f1": 0.8352356233778416,
+      "eval_loss": 0.2958711087703705,
+      "eval_overall_accuracy": 0.9059717780596597,
+      "eval_overall_f1": 0.793620583311305,
+      "eval_overall_precision": 0.7928911988619157,
+      "eval_overall_recall": 0.7943513109248441,
+      "eval_runtime": 381.2154,
+      "eval_samples_per_second": 172.343,
+      "eval_steps_per_second": 1.348,
+      "step": 16000
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.5598666667938232,
+      "learning_rate": 1.7849679981785527e-05,
+      "loss": 0.2963,
+      "step": 17000
+    },
+    {
+      "epoch": 0.75,
+      "eval_LOC_f1": 0.8227697858804539,
+      "eval_ORG_f1": 0.7160294907475222,
+      "eval_PER_f1": 0.8368475991649269,
+      "eval_loss": 0.2975331246852875,
+      "eval_overall_accuracy": 0.9079280784187614,
+      "eval_overall_f1": 0.7966393323888228,
+      "eval_overall_precision": 0.7978373328992902,
+      "eval_overall_recall": 0.7954449242231818,
+      "eval_runtime": 335.9278,
+      "eval_samples_per_second": 195.578,
+      "eval_steps_per_second": 1.53,
+      "step": 17000
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.444880485534668,
+      "learning_rate": 1.772319056894938e-05,
+      "loss": 0.3037,
+      "step": 18000
+    },
+    {
+      "epoch": 0.8,
+      "eval_LOC_f1": 0.8179091806697487,
+      "eval_ORG_f1": 0.7172501033887172,
+      "eval_PER_f1": 0.8379966394973857,
+      "eval_loss": 0.29457131028175354,
+      "eval_overall_accuracy": 0.9080412282112209,
+      "eval_overall_f1": 0.7957346666573557,
+      "eval_overall_precision": 0.7876546623349693,
+      "eval_overall_recall": 0.8039821635198826,
+      "eval_runtime": 382.8523,
+      "eval_samples_per_second": 171.607,
+      "eval_steps_per_second": 1.343,
+      "step": 18000
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.651078701019287,
+      "learning_rate": 1.7596701156113234e-05,
+      "loss": 0.2893,
+      "step": 19000
+    },
+    {
+      "epoch": 0.84,
+      "eval_LOC_f1": 0.8096252541880508,
+      "eval_ORG_f1": 0.722521212121212,
+      "eval_PER_f1": 0.8371796558038832,
+      "eval_loss": 0.30927255749702454,
+      "eval_overall_accuracy": 0.90601644245142,
+      "eval_overall_f1": 0.7939453776936077,
+      "eval_overall_precision": 0.7907640837923529,
+      "eval_overall_recall": 0.797152372082522,
+      "eval_runtime": 321.3057,
+      "eval_samples_per_second": 204.478,
+      "eval_steps_per_second": 1.6,
+      "step": 19000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 7.439753532409668,
+      "learning_rate": 1.747021174327709e-05,
+      "loss": 0.2948,
+      "step": 20000
+    },
+    {
+      "epoch": 0.89,
+      "eval_LOC_f1": 0.82627274528115,
+      "eval_ORG_f1": 0.714928600160901,
+      "eval_PER_f1": 0.8321251892983341,
+      "eval_loss": 0.2865753769874573,
+      "eval_overall_accuracy": 0.9090692536282374,
+      "eval_overall_f1": 0.7971877602217748,
+      "eval_overall_precision": 0.7939824049383752,
+      "eval_overall_recall": 0.8004191008382017,
+      "eval_runtime": 380.5435,
+      "eval_samples_per_second": 172.648,
+      "eval_steps_per_second": 1.351,
+      "step": 20000
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 23.34659767150879,
+      "learning_rate": 1.7343722330440944e-05,
+      "loss": 0.2868,
+      "step": 21000
+    },
+    {
+      "epoch": 0.93,
+      "eval_LOC_f1": 0.8167083361060147,
+      "eval_ORG_f1": 0.727712241345968,
+      "eval_PER_f1": 0.840251831974404,
+      "eval_loss": 0.29932352900505066,
+      "eval_overall_accuracy": 0.9084059874105967,
+      "eval_overall_f1": 0.798865244242835,
+      "eval_overall_precision": 0.7950827119165264,
+      "eval_overall_recall": 0.8026839387012107,
+      "eval_runtime": 351.3256,
+      "eval_samples_per_second": 187.006,
+      "eval_steps_per_second": 1.463,
+      "step": 21000
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 10.305853843688965,
+      "learning_rate": 1.7217232917604798e-05,
+      "loss": 0.2977,
+      "step": 22000
+    },
+    {
+      "epoch": 0.97,
+      "eval_LOC_f1": 0.8263365865270175,
+      "eval_ORG_f1": 0.7257252830008247,
+      "eval_PER_f1": 0.8407604251839738,
+      "eval_loss": 0.2778206169605255,
+      "eval_overall_accuracy": 0.9105640219391492,
+      "eval_overall_f1": 0.8018860680855222,
+      "eval_overall_precision": 0.7934180537329926,
+      "eval_overall_recall": 0.8105367877402422,
+      "eval_runtime": 394.5686,
+      "eval_samples_per_second": 166.511,
+      "eval_steps_per_second": 1.303,
+      "step": 22000
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 11.687705993652344,
+      "learning_rate": 1.709074350476865e-05,
+      "loss": 0.2585,
+      "step": 23000
+    },
+    {
+      "epoch": 1.02,
+      "eval_LOC_f1": 0.8267493620904808,
+      "eval_ORG_f1": 0.7272141627126203,
+      "eval_PER_f1": 0.8396679597210218,
+      "eval_loss": 0.2966572642326355,
+      "eval_overall_accuracy": 0.9093171410025072,
+      "eval_overall_f1": 0.8032836474772869,
+      "eval_overall_precision": 0.7918766066838047,
+      "eval_overall_recall": 0.8150241300482601,
+      "eval_runtime": 380.5595,
+      "eval_samples_per_second": 172.641,
+      "eval_steps_per_second": 1.351,
+      "step": 23000
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 3.907621383666992,
+      "learning_rate": 1.6964254091932504e-05,
+      "loss": 0.2362,
+      "step": 24000
+    },
+    {
+      "epoch": 1.06,
+      "eval_LOC_f1": 0.8330133267755635,
+      "eval_ORG_f1": 0.7180792210666076,
+      "eval_PER_f1": 0.830729295671386,
+      "eval_loss": 0.3153696358203888,
+      "eval_overall_accuracy": 0.9078134398132433,
+      "eval_overall_f1": 0.7997513906153431,
+      "eval_overall_precision": 0.7873453202980789,
+      "eval_overall_recall": 0.8125546806649169,
+      "eval_runtime": 373.8915,
+      "eval_samples_per_second": 175.719,
+      "eval_steps_per_second": 1.375,
+      "step": 24000
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 8.853696823120117,
+      "learning_rate": 1.683776467909636e-05,
+      "loss": 0.2223,
+      "step": 25000
+    },
+    {
+      "epoch": 1.11,
+      "eval_LOC_f1": 0.827347355217957,
+      "eval_ORG_f1": 0.7285489531647101,
+      "eval_PER_f1": 0.8452979544031824,
+      "eval_loss": 0.29239869117736816,
+      "eval_overall_accuracy": 0.9101635312263651,
+      "eval_overall_f1": 0.8052130812290949,
+      "eval_overall_precision": 0.7913853365400993,
+      "eval_overall_recall": 0.8195326390652782,
+      "eval_runtime": 381.4229,
+      "eval_samples_per_second": 172.25,
+      "eval_steps_per_second": 1.348,
+      "step": 25000
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.670585572719574,
+      "learning_rate": 1.6711275266260215e-05,
+      "loss": 0.2339,
+      "step": 26000
+    },
+    {
+      "epoch": 1.15,
+      "eval_LOC_f1": 0.835739538961472,
+      "eval_ORG_f1": 0.7377061141106085,
+      "eval_PER_f1": 0.8477990752245738,
+      "eval_loss": 0.2966776490211487,
+      "eval_overall_accuracy": 0.9133503355784635,
+      "eval_overall_f1": 0.8116372709464219,
+      "eval_overall_precision": 0.8062829412297131,
+      "eval_overall_recall": 0.8170631896819349,
+      "eval_runtime": 348.6318,
+      "eval_samples_per_second": 188.451,
+      "eval_steps_per_second": 1.474,
+      "step": 26000
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 5.636080741882324,
+      "learning_rate": 1.658478585342407e-05,
+      "loss": 0.2318,
+      "step": 27000
+    },
+    {
+      "epoch": 1.2,
+      "eval_LOC_f1": 0.8379575082665046,
+      "eval_ORG_f1": 0.741773869167331,
+      "eval_PER_f1": 0.8468086407796683,
+      "eval_loss": 0.297035276889801,
+      "eval_overall_accuracy": 0.9143232749123089,
+      "eval_overall_f1": 0.8128532056457225,
+      "eval_overall_precision": 0.8019583070120025,
+      "eval_overall_recall": 0.8240482036519629,
+      "eval_runtime": 381.0554,
+      "eval_samples_per_second": 172.416,
+      "eval_steps_per_second": 1.349,
+      "step": 27000
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 11.75963306427002,
+      "learning_rate": 1.6458296440587925e-05,
+      "loss": 0.2261,
+      "step": 28000
+    },
+    {
+      "epoch": 1.24,
+      "eval_LOC_f1": 0.8355374639087424,
+      "eval_ORG_f1": 0.7354031739753795,
+      "eval_PER_f1": 0.8533292168364721,
+      "eval_loss": 0.28783518075942993,
+      "eval_overall_accuracy": 0.914816072034731,
+      "eval_overall_f1": 0.813075185134273,
+      "eval_overall_precision": 0.8123622174798036,
+      "eval_overall_recall": 0.8137894053565885,
+      "eval_runtime": 319.3665,
+      "eval_samples_per_second": 205.72,
+      "eval_steps_per_second": 1.609,
+      "step": 28000
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.3197329342365265,
+      "learning_rate": 1.633180702775178e-05,
+      "loss": 0.2209,
+      "step": 29000
+    },
+    {
+      "epoch": 1.28,
+      "eval_LOC_f1": 0.8348409410512713,
+      "eval_ORG_f1": 0.7400960885063363,
+      "eval_PER_f1": 0.852092035253628,
+      "eval_loss": 0.28716719150543213,
+      "eval_overall_accuracy": 0.9143351854167783,
+      "eval_overall_f1": 0.8130391159543484,
+      "eval_overall_precision": 0.8030238383615944,
+      "eval_overall_recall": 0.8233073688369599,
+      "eval_runtime": 381.0776,
+      "eval_samples_per_second": 172.406,
+      "eval_steps_per_second": 1.349,
+      "step": 29000
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 2.500840663909912,
+      "learning_rate": 1.6205317614915632e-05,
+      "loss": 0.2326,
+      "step": 30000
+    },
+    {
+      "epoch": 1.33,
+      "eval_LOC_f1": 0.835323589241317,
+      "eval_ORG_f1": 0.7427079308204821,
+      "eval_PER_f1": 0.8500763485649586,
+      "eval_loss": 0.28030699491500854,
+      "eval_overall_accuracy": 0.914723765625093,
+      "eval_overall_f1": 0.8127800899066888,
+      "eval_overall_precision": 0.8005707559436636,
+      "eval_overall_recall": 0.8253675951796348,
+      "eval_runtime": 325.8915,
+      "eval_samples_per_second": 201.601,
+      "eval_steps_per_second": 1.577,
+      "step": 30000
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.524834156036377,
+      "learning_rate": 1.607882820207949e-05,
+      "loss": 0.2198,
+      "step": 31000
+    },
+    {
+      "epoch": 1.37,
+      "eval_LOC_f1": 0.8371461143834315,
+      "eval_ORG_f1": 0.7432512590283674,
+      "eval_PER_f1": 0.8540951115999625,
+      "eval_loss": 0.28697240352630615,
+      "eval_overall_accuracy": 0.9156036541427712,
+      "eval_overall_f1": 0.8147560933208163,
+      "eval_overall_precision": 0.8031779980531677,
+      "eval_overall_recall": 0.8266728755679733,
+      "eval_runtime": 381.127,
+      "eval_samples_per_second": 172.383,
+      "eval_steps_per_second": 1.349,
+      "step": 31000
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 18.899179458618164,
+      "learning_rate": 1.5952338789243342e-05,
+      "loss": 0.221,
+      "step": 32000
+    },
+    {
+      "epoch": 1.42,
+      "eval_LOC_f1": 0.8441860465116279,
+      "eval_ORG_f1": 0.7411915135442319,
+      "eval_PER_f1": 0.8485990299434801,
+      "eval_loss": 0.28265270590782166,
+      "eval_overall_accuracy": 0.9150192950172404,
+      "eval_overall_f1": 0.8153681889236267,
+      "eval_overall_precision": 0.8065649592710203,
+      "eval_overall_recall": 0.8243657042869641,
+      "eval_runtime": 346.0172,
+      "eval_samples_per_second": 189.875,
+      "eval_steps_per_second": 1.485,
+      "step": 32000
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 9.521773338317871,
+      "learning_rate": 1.5825849376407196e-05,
+      "loss": 0.2319,
+      "step": 33000
+    },
+    {
+      "epoch": 1.46,
+      "eval_LOC_f1": 0.8391690707524869,
+      "eval_ORG_f1": 0.7463789877336044,
+      "eval_PER_f1": 0.8572165373824064,
+      "eval_loss": 0.27687233686447144,
+      "eval_overall_accuracy": 0.9169562408065793,
+      "eval_overall_f1": 0.8172862291713824,
+      "eval_overall_precision": 0.8068870201398582,
+      "eval_overall_recall": 0.8279569892473119,
+      "eval_runtime": 385.1918,
+      "eval_samples_per_second": 170.564,
+      "eval_steps_per_second": 1.334,
+      "step": 33000
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 4.6437883377075195,
+      "learning_rate": 1.569935996357105e-05,
+      "loss": 0.2284,
+      "step": 34000
+    },
+    {
+      "epoch": 1.51,
+      "eval_LOC_f1": 0.8413632604389053,
+      "eval_ORG_f1": 0.7468433377658009,
+      "eval_PER_f1": 0.8579245204510465,
+      "eval_loss": 0.2682867646217346,
+      "eval_overall_accuracy": 0.918707829370113,
+      "eval_overall_f1": 0.8187739611430496,
+      "eval_overall_precision": 0.8141108359780979,
+      "eval_overall_recall": 0.823490813648294,
+      "eval_runtime": 389.0432,
+      "eval_samples_per_second": 168.876,
+      "eval_steps_per_second": 1.321,
+      "step": 34000
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 8.055586814880371,
+      "learning_rate": 1.5572870550734906e-05,
+      "loss": 0.222,
+      "step": 35000
+    },
+    {
+      "epoch": 1.55,
+      "eval_LOC_f1": 0.8416752574836452,
+      "eval_ORG_f1": 0.7401676189600267,
+      "eval_PER_f1": 0.8485277320098252,
+      "eval_loss": 0.2882651388645172,
+      "eval_overall_accuracy": 0.9156967049589385,
+      "eval_overall_f1": 0.8135379092525155,
+      "eval_overall_precision": 0.7963817723503612,
+      "eval_overall_recall": 0.8314494962323258,
+      "eval_runtime": 364.9994,
+      "eval_samples_per_second": 180.0,
+      "eval_steps_per_second": 1.408,
+      "step": 35000
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 2.8561666011810303,
+      "learning_rate": 1.544638113789876e-05,
+      "loss": 0.2272,
+      "step": 36000
+    },
+    {
+      "epoch": 1.59,
+      "eval_LOC_f1": 0.843695144769584,
+      "eval_ORG_f1": 0.7492301387506587,
+      "eval_PER_f1": 0.8506844052649669,
+      "eval_loss": 0.2805135250091553,
+      "eval_overall_accuracy": 0.9165698938178527,
+      "eval_overall_f1": 0.8180830193920244,
+      "eval_overall_precision": 0.805384452359629,
+      "eval_overall_recall": 0.8311884401546581,
+      "eval_runtime": 381.2063,
+      "eval_samples_per_second": 172.348,
+      "eval_steps_per_second": 1.348,
+      "step": 36000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 3.3037211894989014,
+      "learning_rate": 1.5319891725062616e-05,
+      "loss": 0.2086,
+      "step": 37000
+    },
+    {
+      "epoch": 1.64,
+      "eval_LOC_f1": 0.8383752402995496,
+      "eval_ORG_f1": 0.7563655598566996,
+      "eval_PER_f1": 0.8609615664428694,
+      "eval_loss": 0.2780158519744873,
+      "eval_overall_accuracy": 0.9186519988804126,
+      "eval_overall_f1": 0.822004740154319,
+      "eval_overall_precision": 0.8205800667955704,
+      "eval_overall_recall": 0.8234343690909603,
+      "eval_runtime": 332.7363,
+      "eval_samples_per_second": 197.454,
+      "eval_steps_per_second": 1.545,
+      "step": 37000
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 3.0146262645721436,
+      "learning_rate": 1.5193402312226468e-05,
+      "loss": 0.2283,
+      "step": 38000
+    },
+    {
+      "epoch": 1.68,
+      "eval_LOC_f1": 0.8468252837536212,
+      "eval_ORG_f1": 0.7509236309217602,
+      "eval_PER_f1": 0.8619782260977246,
+      "eval_loss": 0.27215901017189026,
+      "eval_overall_accuracy": 0.9187383500378159,
+      "eval_overall_f1": 0.8234198288625827,
+      "eval_overall_precision": 0.8114117405301733,
+      "eval_overall_recall": 0.8357886715773432,
+      "eval_runtime": 305.4831,
+      "eval_samples_per_second": 215.069,
+      "eval_steps_per_second": 1.683,
+      "step": 38000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 158116,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 5313197707682040.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c3a5740e100dbfa14dbda8a5e3586aad084b4dc14da196be76e7c102216e95
+size 4856