Upload with huggingface_hub

README.md

@@ -0,0 +1,15 @@
+---
+license: apache-2.0
+tags:
+- canine
+- pretrained-on-english-language
+---
+
+### How to use
+
+Here is how to use this model:
+
+```python
+from transformers import CanineModel
+model = CanineModel.from_pretrained('mushfiqur11/<repo name>')
+```

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 6.53,
+    "eval_accuracy_score": 0.983046701339034,
+    "eval_f1": 0.8380823767724511,
+    "eval_loss": 0.062301117926836014,
+    "eval_precision": 0.8219867549668874,
+    "eval_recall": 0.8548209366391185,
+    "eval_runtime": 13.5993,
+    "eval_samples": 1721,
+    "eval_samples_per_second": 126.55,
+    "eval_steps_per_second": 15.883,
+    "test_accuracy_score": 0.9790823030920647,
+    "test_f1": 0.7231155778894472,
+    "test_loss": 0.08647164702415466,
+    "test_precision": 0.6918269230769231,
+    "test_recall": 0.7573684210526316,
+    "test_runtime": 13.5808,
+    "test_samples": 1721,
+    "test_samples_per_second": 126.723,
+    "test_steps_per_second": 15.905,
+    "train_loss": 0.06368145237798276,
+    "train_runtime": 5134.9469,
+    "train_samples": 45057,
+    "train_samples_per_second": 93.477,
+    "train_steps_per_second": 2.921
+}

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "google/canine-c",
+  "architectures": [
+    "CanineForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 57344,
+  "downsampling_rate": 4,
+  "eos_token_id": 57345,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-DATE",
+    "2": "I-DATE",
+    "3": "B-PER",
+    "4": "I-PER",
+    "5": "B-ORG",
+    "6": "I-ORG",
+    "7": "B-LOC",
+    "8": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DATE": 1,
+    "B-LOC": 7,
+    "B-ORG": 5,
+    "B-PER": 3,
+    "I-DATE": 2,
+    "I-LOC": 8,
+    "I-ORG": 6,
+    "I-PER": 4,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "local_transformer_stride": 128,
+  "max_position_embeddings": 16384,
+  "model_type": "canine",
+  "num_attention_heads": 12,
+  "num_hash_buckets": 16384,
+  "num_hash_functions": 8,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 16,
+  "upsampling_kernel_size": 4,
+  "use_cache": true
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc737e3e2b06d1e8cd028410716c68231eb432cbf727f9054b74978f185419cb
+size 528594737

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "\u0000", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "\u0000", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": "/home/mrahma45/.cache/huggingface/transformers/f8be97736b4765e3e8d559b4e7d4f1f531b1621150e5344b600684a27bc84e38.ab71f530366fe02e2834427e7b90198bfd0d573bc4279bfafdb2b95fe2b46dde", "name_or_path": "google/canine-c", "tokenizer_class": "CanineTokenizer"}

trainer_state.json

@@ -0,0 +1,685 @@
+{
+  "best_metric": 0.8380823767724511,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-zh/checkpoint-8000",
+  "epoch": 6.529453513129879,
+  "global_step": 9200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "eval_accuracy_score": 0.9129681035491316,
+      "eval_f1": 0.28297109094745726,
+      "eval_loss": 0.24658027291297913,
+      "eval_precision": 0.2293091655266758,
+      "eval_recall": 0.3694214876033058,
+      "eval_runtime": 13.6213,
+      "eval_samples_per_second": 126.346,
+      "eval_steps_per_second": 15.858,
+      "step": 200
+    },
+    {
+      "epoch": 0.28,
+      "eval_accuracy_score": 0.9404507407761931,
+      "eval_f1": 0.45835209365150836,
+      "eval_loss": 0.16537903249263763,
+      "eval_precision": 0.3875142748382185,
+      "eval_recall": 0.5608815426997246,
+      "eval_runtime": 13.6182,
+      "eval_samples_per_second": 126.375,
+      "eval_steps_per_second": 15.861,
+      "step": 400
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.311,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "eval_accuracy_score": 0.9547344798613105,
+      "eval_f1": 0.5599802127133318,
+      "eval_loss": 0.1292579174041748,
+      "eval_precision": 0.5080789946140036,
+      "eval_recall": 0.6236914600550965,
+      "eval_runtime": 13.6318,
+      "eval_samples_per_second": 126.249,
+      "eval_steps_per_second": 15.845,
+      "step": 600
+    },
+    {
+      "epoch": 0.57,
+      "eval_accuracy_score": 0.9593291003265159,
+      "eval_f1": 0.6071473041962396,
+      "eval_loss": 0.11427777260541916,
+      "eval_precision": 0.5539650079527381,
+      "eval_recall": 0.6716253443526171,
+      "eval_runtime": 13.6172,
+      "eval_samples_per_second": 126.385,
+      "eval_steps_per_second": 15.862,
+      "step": 800
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.129,
+      "step": 1000
+    },
+    {
+      "epoch": 0.71,
+      "eval_accuracy_score": 0.9607542835263712,
+      "eval_f1": 0.6353887399463807,
+      "eval_loss": 0.11220921576023102,
+      "eval_precision": 0.5697115384615384,
+      "eval_recall": 0.7181818181818181,
+      "eval_runtime": 13.6515,
+      "eval_samples_per_second": 126.067,
+      "eval_steps_per_second": 15.822,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "eval_accuracy_score": 0.9674547717047957,
+      "eval_f1": 0.6734111543450064,
+      "eval_loss": 0.09249622374773026,
+      "eval_precision": 0.6362745098039215,
+      "eval_recall": 0.7151515151515152,
+      "eval_runtime": 13.6224,
+      "eval_samples_per_second": 126.336,
+      "eval_steps_per_second": 15.856,
+      "step": 1200
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy_score": 0.9631473150186657,
+      "eval_f1": 0.6626785496276401,
+      "eval_loss": 0.10182885825634003,
+      "eval_precision": 0.5950449462837097,
+      "eval_recall": 0.7476584022038567,
+      "eval_runtime": 13.6109,
+      "eval_samples_per_second": 126.443,
+      "eval_steps_per_second": 15.87,
+      "step": 1400
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.1036,
+      "step": 1500
+    },
+    {
+      "epoch": 1.14,
+      "eval_accuracy_score": 0.9710921795730831,
+      "eval_f1": 0.6969853130636433,
+      "eval_loss": 0.082883320748806,
+      "eval_precision": 0.6546466602129719,
+      "eval_recall": 0.7451790633608816,
+      "eval_runtime": 13.6154,
+      "eval_samples_per_second": 126.401,
+      "eval_steps_per_second": 15.864,
+      "step": 1600
+    },
+    {
+      "epoch": 1.28,
+      "eval_accuracy_score": 0.9742722525339544,
+      "eval_f1": 0.7333952008484688,
+      "eval_loss": 0.07554662227630615,
+      "eval_precision": 0.7068745208280092,
+      "eval_recall": 0.7619834710743801,
+      "eval_runtime": 14.1365,
+      "eval_samples_per_second": 121.741,
+      "eval_steps_per_second": 15.28,
+      "step": 1800
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0836,
+      "step": 2000
+    },
+    {
+      "epoch": 1.42,
+      "eval_accuracy_score": 0.974740223136892,
+      "eval_f1": 0.732556617358293,
+      "eval_loss": 0.07343326508998871,
+      "eval_precision": 0.697929658268895,
+      "eval_recall": 0.7707988980716254,
+      "eval_runtime": 13.5903,
+      "eval_samples_per_second": 126.635,
+      "eval_steps_per_second": 15.894,
+      "step": 2000
+    },
+    {
+      "epoch": 1.56,
+      "eval_accuracy_score": 0.9732086829818236,
+      "eval_f1": 0.7319003033100355,
+      "eval_loss": 0.07696483284235,
+      "eval_precision": 0.7019984821654439,
+      "eval_recall": 0.7644628099173554,
+      "eval_runtime": 13.5905,
+      "eval_samples_per_second": 126.633,
+      "eval_steps_per_second": 15.893,
+      "step": 2200
+    },
+    {
+      "epoch": 1.7,
+      "eval_accuracy_score": 0.9746870446592855,
+      "eval_f1": 0.7546320804658551,
+      "eval_loss": 0.07449489831924438,
+      "eval_precision": 0.7261844116148752,
+      "eval_recall": 0.7853994490358127,
+      "eval_runtime": 13.5778,
+      "eval_samples_per_second": 126.751,
+      "eval_steps_per_second": 15.908,
+      "step": 2400
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0759,
+      "step": 2500
+    },
+    {
+      "epoch": 1.85,
+      "eval_accuracy_score": 0.9739850887548791,
+      "eval_f1": 0.7507269362939466,
+      "eval_loss": 0.07230275124311447,
+      "eval_precision": 0.7215447154471545,
+      "eval_recall": 0.7823691460055097,
+      "eval_runtime": 13.6116,
+      "eval_samples_per_second": 126.436,
+      "eval_steps_per_second": 15.869,
+      "step": 2600
+    },
+    {
+      "epoch": 1.99,
+      "eval_accuracy_score": 0.9774842325813896,
+      "eval_f1": 0.765840220385675,
+      "eval_loss": 0.06559152156114578,
+      "eval_precision": 0.7310293012772352,
+      "eval_recall": 0.8041322314049587,
+      "eval_runtime": 13.5735,
+      "eval_samples_per_second": 126.791,
+      "eval_steps_per_second": 15.913,
+      "step": 2800
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.0661,
+      "step": 3000
+    },
+    {
+      "epoch": 2.13,
+      "eval_accuracy_score": 0.9767397338948981,
+      "eval_f1": 0.766487478694113,
+      "eval_loss": 0.06845659017562866,
+      "eval_precision": 0.7312984738553916,
+      "eval_recall": 0.8052341597796143,
+      "eval_runtime": 13.5908,
+      "eval_samples_per_second": 126.63,
+      "eval_steps_per_second": 15.893,
+      "step": 3000
+    },
+    {
+      "epoch": 2.27,
+      "eval_accuracy_score": 0.9781861884857961,
+      "eval_f1": 0.786258521588023,
+      "eval_loss": 0.06672950088977814,
+      "eval_precision": 0.7636977408465334,
+      "eval_recall": 0.8101928374655647,
+      "eval_runtime": 13.5943,
+      "eval_samples_per_second": 126.597,
+      "eval_steps_per_second": 15.889,
+      "step": 3200
+    },
+    {
+      "epoch": 2.41,
+      "eval_accuracy_score": 0.978494623655914,
+      "eval_f1": 0.788430637386181,
+      "eval_loss": 0.06290964037179947,
+      "eval_precision": 0.7670661803022407,
+      "eval_recall": 0.8110192837465565,
+      "eval_runtime": 13.6234,
+      "eval_samples_per_second": 126.327,
+      "eval_steps_per_second": 15.855,
+      "step": 3400
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 3.859060402684564e-05,
+      "loss": 0.0557,
+      "step": 3500
+    },
+    {
+      "epoch": 2.56,
+      "eval_accuracy_score": 0.9771545260202291,
+      "eval_f1": 0.7819006940736786,
+      "eval_loss": 0.06865714490413666,
+      "eval_precision": 0.7584153288451579,
+      "eval_recall": 0.8068870523415977,
+      "eval_runtime": 13.6478,
+      "eval_samples_per_second": 126.101,
+      "eval_steps_per_second": 15.827,
+      "step": 3600
+    },
+    {
+      "epoch": 2.7,
+      "eval_accuracy_score": 0.9764100273337375,
+      "eval_f1": 0.7668036590216094,
+      "eval_loss": 0.06829773634672165,
+      "eval_precision": 0.7390748786097623,
+      "eval_recall": 0.7966942148760331,
+      "eval_runtime": 13.5949,
+      "eval_samples_per_second": 126.592,
+      "eval_steps_per_second": 15.888,
+      "step": 3800
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 3.6912751677852356e-05,
+      "loss": 0.053,
+      "step": 4000
+    },
+    {
+      "epoch": 2.84,
+      "eval_accuracy_score": 0.9786116163066484,
+      "eval_f1": 0.7864077669902914,
+      "eval_loss": 0.06425034999847412,
+      "eval_precision": 0.750751503006012,
+      "eval_recall": 0.8256198347107438,
+      "eval_runtime": 13.5943,
+      "eval_samples_per_second": 126.597,
+      "eval_steps_per_second": 15.889,
+      "step": 4000
+    },
+    {
+      "epoch": 2.98,
+      "eval_accuracy_score": 0.9795475575125235,
+      "eval_f1": 0.7989869368168488,
+      "eval_loss": 0.06154418736696243,
+      "eval_precision": 0.7740185950413223,
+      "eval_recall": 0.8256198347107438,
+      "eval_runtime": 13.6387,
+      "eval_samples_per_second": 126.185,
+      "eval_steps_per_second": 15.837,
+      "step": 4200
+    },
+    {
+      "epoch": 3.12,
+      "eval_accuracy_score": 0.9785797092200844,
+      "eval_f1": 0.7900653594771242,
+      "eval_loss": 0.0661051869392395,
+      "eval_precision": 0.7517412935323383,
+      "eval_recall": 0.8325068870523415,
+      "eval_runtime": 13.6158,
+      "eval_samples_per_second": 126.398,
+      "eval_steps_per_second": 15.864,
+      "step": 4400
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 3.523489932885906e-05,
+      "loss": 0.0438,
+      "step": 4500
+    },
+    {
+      "epoch": 3.26,
+      "eval_accuracy_score": 0.9797815428139923,
+      "eval_f1": 0.7966373098478784,
+      "eval_loss": 0.06480157375335693,
+      "eval_precision": 0.7725155279503105,
+      "eval_recall": 0.8223140495867769,
+      "eval_runtime": 13.6096,
+      "eval_samples_per_second": 126.455,
+      "eval_steps_per_second": 15.871,
+      "step": 4600
+    },
+    {
+      "epoch": 3.41,
+      "eval_accuracy_score": 0.9802920561990152,
+      "eval_f1": 0.7971303308090872,
+      "eval_loss": 0.0628492534160614,
+      "eval_precision": 0.7698229407236336,
+      "eval_recall": 0.8264462809917356,
+      "eval_runtime": 13.615,
+      "eval_samples_per_second": 126.404,
+      "eval_steps_per_second": 15.865,
+      "step": 4800
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 0.0387,
+      "step": 5000
+    },
+    {
+      "epoch": 3.55,
+      "eval_accuracy_score": 0.9815577039660509,
+      "eval_f1": 0.810593900481541,
+      "eval_loss": 0.06002389267086983,
+      "eval_precision": 0.7878315132605305,
+      "eval_recall": 0.8347107438016529,
+      "eval_runtime": 13.5792,
+      "eval_samples_per_second": 126.738,
+      "eval_steps_per_second": 15.907,
+      "step": 5000
+    },
+    {
+      "epoch": 3.69,
+      "eval_accuracy_score": 0.9817385107899131,
+      "eval_f1": 0.8027467348862258,
+      "eval_loss": 0.05803261324763298,
+      "eval_precision": 0.7850934948643666,
+      "eval_recall": 0.8212121212121212,
+      "eval_runtime": 13.5963,
+      "eval_samples_per_second": 126.578,
+      "eval_steps_per_second": 15.887,
+      "step": 5200
+    },
+    {
+      "epoch": 3.83,
+      "eval_accuracy_score": 0.9809940121034215,
+      "eval_f1": 0.7985592315901814,
+      "eval_loss": 0.05973115563392639,
+      "eval_precision": 0.7741852043455768,
+      "eval_recall": 0.8245179063360881,
+      "eval_runtime": 13.6439,
+      "eval_samples_per_second": 126.137,
+      "eval_steps_per_second": 15.831,
+      "step": 5400
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 3.1879194630872485e-05,
+      "loss": 0.0384,
+      "step": 5500
+    },
+    {
+      "epoch": 3.97,
+      "eval_accuracy_score": 0.9800155281154611,
+      "eval_f1": 0.811035221641891,
+      "eval_loss": 0.0613255649805069,
+      "eval_precision": 0.7891581965076883,
+      "eval_recall": 0.8341597796143251,
+      "eval_runtime": 13.6115,
+      "eval_samples_per_second": 126.437,
+      "eval_steps_per_second": 15.869,
+      "step": 5600
+    },
+    {
+      "epoch": 4.12,
+      "eval_accuracy_score": 0.9810046477989428,
+      "eval_f1": 0.8116173727684519,
+      "eval_loss": 0.062166035175323486,
+      "eval_precision": 0.7858617131062952,
+      "eval_recall": 0.8391184573002755,
+      "eval_runtime": 13.5983,
+      "eval_samples_per_second": 126.56,
+      "eval_steps_per_second": 15.884,
+      "step": 5800
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 3.02013422818792e-05,
+      "loss": 0.0306,
+      "step": 6000
+    },
+    {
+      "epoch": 4.26,
+      "eval_accuracy_score": 0.9821001244376376,
+      "eval_f1": 0.8187010227121796,
+      "eval_loss": 0.062430813908576965,
+      "eval_precision": 0.790459092074891,
+      "eval_recall": 0.8490358126721763,
+      "eval_runtime": 13.6088,
+      "eval_samples_per_second": 126.462,
+      "eval_steps_per_second": 15.872,
+      "step": 6000
+    },
+    {
+      "epoch": 4.4,
+      "eval_accuracy_score": 0.9816321538347,
+      "eval_f1": 0.8215152332165004,
+      "eval_loss": 0.06259527057409286,
+      "eval_precision": 0.8043822597676874,
+      "eval_recall": 0.8393939393939394,
+      "eval_runtime": 13.5727,
+      "eval_samples_per_second": 126.799,
+      "eval_steps_per_second": 15.914,
+      "step": 6200
+    },
+    {
+      "epoch": 4.54,
+      "eval_accuracy_score": 0.9820894887421163,
+      "eval_f1": 0.820450885668277,
+      "eval_loss": 0.060455016791820526,
+      "eval_precision": 0.7998430141287284,
+      "eval_recall": 0.8421487603305785,
+      "eval_runtime": 13.9612,
+      "eval_samples_per_second": 123.27,
+      "eval_steps_per_second": 15.471,
+      "step": 6400
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 2.8523489932885905e-05,
+      "loss": 0.0284,
+      "step": 6500
+    },
+    {
+      "epoch": 4.68,
+      "eval_accuracy_score": 0.9816959680078279,
+      "eval_f1": 0.8147754451235716,
+      "eval_loss": 0.06003221124410629,
+      "eval_precision": 0.7869609856262834,
+      "eval_recall": 0.8446280991735537,
+      "eval_runtime": 13.5502,
+      "eval_samples_per_second": 127.009,
+      "eval_steps_per_second": 15.941,
+      "step": 6600
+    },
+    {
+      "epoch": 4.83,
+      "eval_accuracy_score": 0.9806962126288249,
+      "eval_f1": 0.8067448294032407,
+      "eval_loss": 0.06309182196855545,
+      "eval_precision": 0.7730371118404443,
+      "eval_recall": 0.843526170798898,
+      "eval_runtime": 13.6187,
+      "eval_samples_per_second": 126.37,
+      "eval_steps_per_second": 15.861,
+      "step": 6800
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 2.6845637583892618e-05,
+      "loss": 0.0284,
+      "step": 7000
+    },
+    {
+      "epoch": 4.97,
+      "eval_accuracy_score": 0.9820150388734671,
+      "eval_f1": 0.8199058507061198,
+      "eval_loss": 0.06148926541209221,
+      "eval_precision": 0.8010512483574245,
+      "eval_recall": 0.8396694214876033,
+      "eval_runtime": 13.5967,
+      "eval_samples_per_second": 126.575,
+      "eval_steps_per_second": 15.886,
+      "step": 7000
+    },
+    {
+      "epoch": 5.11,
+      "eval_accuracy_score": 0.9822490241749359,
+      "eval_f1": 0.8229922105828633,
+      "eval_loss": 0.061297256499528885,
+      "eval_precision": 0.8029350104821803,
+      "eval_recall": 0.8440771349862259,
+      "eval_runtime": 13.5574,
+      "eval_samples_per_second": 126.941,
+      "eval_steps_per_second": 15.932,
+      "step": 7200
+    },
+    {
+      "epoch": 5.25,
+      "eval_accuracy_score": 0.9818767748316901,
+      "eval_f1": 0.8198608137044968,
+      "eval_loss": 0.06245254725217819,
+      "eval_precision": 0.7972410203019261,
+      "eval_recall": 0.843801652892562,
+      "eval_runtime": 13.5789,
+      "eval_samples_per_second": 126.741,
+      "eval_steps_per_second": 15.907,
+      "step": 7400
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 2.516778523489933e-05,
+      "loss": 0.0214,
+      "step": 7500
+    },
+    {
+      "epoch": 5.39,
+      "eval_accuracy_score": 0.9830041585569488,
+      "eval_f1": 0.8312735088662009,
+      "eval_loss": 0.061838824301958084,
+      "eval_precision": 0.8112218143681175,
+      "eval_recall": 0.8523415977961433,
+      "eval_runtime": 13.5752,
+      "eval_samples_per_second": 126.775,
+      "eval_steps_per_second": 15.911,
+      "step": 7600
+    },
+    {
+      "epoch": 5.54,
+      "eval_accuracy_score": 0.9833870435957159,
+      "eval_f1": 0.8350612629594723,
+      "eval_loss": 0.05837469547986984,
+      "eval_precision": 0.8166973926784303,
+      "eval_recall": 0.8542699724517906,
+      "eval_runtime": 13.5899,
+      "eval_samples_per_second": 126.638,
+      "eval_steps_per_second": 15.894,
+      "step": 7800
+    },
+    {
+      "epoch": 5.68,
+      "learning_rate": 2.348993288590604e-05,
+      "loss": 0.0207,
+      "step": 8000
+    },
+    {
+      "epoch": 5.68,
+      "eval_accuracy_score": 0.983046701339034,
+      "eval_f1": 0.8380823767724511,
+      "eval_loss": 0.062301117926836014,
+      "eval_precision": 0.8219867549668874,
+      "eval_recall": 0.8548209366391185,
+      "eval_runtime": 13.6129,
+      "eval_samples_per_second": 126.424,
+      "eval_steps_per_second": 15.867,
+      "step": 8000
+    },
+    {
+      "epoch": 5.82,
+      "eval_accuracy_score": 0.9830573370345553,
+      "eval_f1": 0.8395858545112277,
+      "eval_loss": 0.06179790198802948,
+      "eval_precision": 0.8200682952456002,
+      "eval_recall": 0.8600550964187328,
+      "eval_runtime": 13.5699,
+      "eval_samples_per_second": 126.824,
+      "eval_steps_per_second": 15.918,
+      "step": 8200
+    },
+    {
+      "epoch": 5.96,
+      "eval_accuracy_score": 0.9832913223360241,
+      "eval_f1": 0.832185770217362,
+      "eval_loss": 0.062014687806367874,
+      "eval_precision": 0.815991527667461,
+      "eval_recall": 0.8490358126721763,
+      "eval_runtime": 13.5558,
+      "eval_samples_per_second": 126.957,
+      "eval_steps_per_second": 15.934,
+      "step": 8400
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 2.181208053691275e-05,
+      "loss": 0.021,
+      "step": 8500
+    },
+    {
+      "epoch": 6.1,
+      "eval_accuracy_score": 0.9830041585569488,
+      "eval_f1": 0.8260577568838147,
+      "eval_loss": 0.0646287053823471,
+      "eval_precision": 0.8060288335517694,
+      "eval_recall": 0.8471074380165289,
+      "eval_runtime": 13.6088,
+      "eval_samples_per_second": 126.462,
+      "eval_steps_per_second": 15.872,
+      "step": 8600
+    },
+    {
+      "epoch": 6.25,
+      "eval_accuracy_score": 0.9833976792912372,
+      "eval_f1": 0.8323497854077254,
+      "eval_loss": 0.06417383998632431,
+      "eval_precision": 0.8110297961317303,
+      "eval_recall": 0.8548209366391185,
+      "eval_runtime": 13.585,
+      "eval_samples_per_second": 126.684,
+      "eval_steps_per_second": 15.9,
+      "step": 8800
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 2.013422818791946e-05,
+      "loss": 0.016,
+      "step": 9000
+    },
+    {
+      "epoch": 6.39,
+      "eval_accuracy_score": 0.9833870435957159,
+      "eval_f1": 0.8344495044200374,
+      "eval_loss": 0.062400706112384796,
+      "eval_precision": 0.8120437956204379,
+      "eval_recall": 0.8581267217630854,
+      "eval_runtime": 13.5776,
+      "eval_samples_per_second": 126.753,
+      "eval_steps_per_second": 15.909,
+      "step": 9000
+    },
+    {
+      "epoch": 6.53,
+      "eval_accuracy_score": 0.9841421779777288,
+      "eval_f1": 0.8372093023255813,
+      "eval_loss": 0.061586689203977585,
+      "eval_precision": 0.8130841121495327,
+      "eval_recall": 0.8628099173553719,
+      "eval_runtime": 13.5728,
+      "eval_samples_per_second": 126.797,
+      "eval_steps_per_second": 15.914,
+      "step": 9200
+    },
+    {
+      "epoch": 6.53,
+      "step": 9200,
+      "total_flos": 4.831477938761011e+16,
+      "train_loss": 0.06368145237798276,
+      "train_runtime": 5134.9469,
+      "train_samples_per_second": 93.477,
+      "train_steps_per_second": 2.921
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 11,
+  "total_flos": 4.831477938761011e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b64d3b432eb2c68d3667b90b45f088a364c3ef20dfdfb9ce6f7fdb74b14db04
+size 3259