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": 136.36,
+    "eval_accuracy_score": 0.9578587699316629,
+    "eval_f1": 0.7696879643387815,
+    "eval_loss": 0.3037085235118866,
+    "eval_precision": 0.7431850789096126,
+    "eval_recall": 0.7981510015408321,
+    "eval_runtime": 1.8072,
+    "eval_samples": 300,
+    "eval_samples_per_second": 166.001,
+    "eval_steps_per_second": 21.027,
+    "test_accuracy_score": 0.9565733896515312,
+    "test_f1": 0.7210372229192806,
+    "test_loss": 0.35158705711364746,
+    "test_precision": 0.7002437043054427,
+    "test_recall": 0.743103448275862,
+    "test_runtime": 3.6459,
+    "test_samples": 604,
+    "test_samples_per_second": 165.664,
+    "test_steps_per_second": 20.845,
+    "train_loss": 0.026613251682784823,
+    "train_runtime": 3020.8535,
+    "train_samples": 2109,
+    "train_samples_per_second": 158.895,
+    "train_steps_per_second": 4.965
+}

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 sha256:5b5441c57f8ac907b76deb024a4d086024e7a9eff1e28167bf6557ef92247ac7
+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 +1,673 @@
+{
+  "best_metric": 0.7696879643387815,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-swa/checkpoint-8000",
+  "epoch": 136.36363636363637,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.03,
+      "eval_accuracy_score": 0.9148633257403189,
+      "eval_f1": 0.4574540503744044,
+      "eval_loss": 0.247094064950943,
+      "eval_precision": 0.4097560975609756,
+      "eval_recall": 0.5177195685670262,
+      "eval_runtime": 1.8306,
+      "eval_samples_per_second": 163.885,
+      "eval_steps_per_second": 20.759,
+      "step": 200
+    },
+    {
+      "epoch": 6.06,
+      "eval_accuracy_score": 0.9370728929384966,
+      "eval_f1": 0.5889655172413792,
+      "eval_loss": 0.19638368487358093,
+      "eval_precision": 0.533083645443196,
+      "eval_recall": 0.6579352850539292,
+      "eval_runtime": 1.8217,
+      "eval_samples_per_second": 164.685,
+      "eval_steps_per_second": 20.86,
+      "step": 400
+    },
+    {
+      "epoch": 7.58,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.3448,
+      "step": 500
+    },
+    {
+      "epoch": 9.09,
+      "eval_accuracy_score": 0.9400626423690205,
+      "eval_f1": 0.6428571428571429,
+      "eval_loss": 0.19553665816783905,
+      "eval_precision": 0.5892169448010269,
+      "eval_recall": 0.7072419106317411,
+      "eval_runtime": 1.8313,
+      "eval_samples_per_second": 163.822,
+      "eval_steps_per_second": 20.751,
+      "step": 600
+    },
+    {
+      "epoch": 12.12,
+      "eval_accuracy_score": 0.945615034168565,
+      "eval_f1": 0.6884779516358465,
+      "eval_loss": 0.20538370311260223,
+      "eval_precision": 0.6393659180977543,
+      "eval_recall": 0.7457627118644068,
+      "eval_runtime": 1.8211,
+      "eval_samples_per_second": 164.736,
+      "eval_steps_per_second": 20.867,
+      "step": 800
+    },
+    {
+      "epoch": 15.15,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0881,
+      "step": 1000
+    },
+    {
+      "epoch": 15.15,
+      "eval_accuracy_score": 0.9533029612756264,
+      "eval_f1": 0.7061371841155235,
+      "eval_loss": 0.1924728900194168,
+      "eval_precision": 0.6644021739130435,
+      "eval_recall": 0.7534668721109399,
+      "eval_runtime": 1.8179,
+      "eval_samples_per_second": 165.026,
+      "eval_steps_per_second": 20.903,
+      "step": 1000
+    },
+    {
+      "epoch": 18.18,
+      "eval_accuracy_score": 0.9513097949886105,
+      "eval_f1": 0.7208121827411167,
+      "eval_loss": 0.20917125046253204,
+      "eval_precision": 0.6808219178082192,
+      "eval_recall": 0.765793528505393,
+      "eval_runtime": 1.8253,
+      "eval_samples_per_second": 164.358,
+      "eval_steps_per_second": 20.819,
+      "step": 1200
+    },
+    {
+      "epoch": 21.21,
+      "eval_accuracy_score": 0.9515945330296127,
+      "eval_f1": 0.7202295552367288,
+      "eval_loss": 0.22328592836856842,
+      "eval_precision": 0.6738255033557047,
+      "eval_recall": 0.773497688751926,
+      "eval_runtime": 1.8213,
+      "eval_samples_per_second": 164.719,
+      "eval_steps_per_second": 20.864,
+      "step": 1400
+    },
+    {
+      "epoch": 22.73,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0183,
+      "step": 1500
+    },
+    {
+      "epoch": 24.24,
+      "eval_accuracy_score": 0.9525911161731208,
+      "eval_f1": 0.7200577200577202,
+      "eval_loss": 0.22826075553894043,
+      "eval_precision": 0.6770691994572592,
+      "eval_recall": 0.7688751926040062,
+      "eval_runtime": 1.8217,
+      "eval_samples_per_second": 164.682,
+      "eval_steps_per_second": 20.86,
+      "step": 1600
+    },
+    {
+      "epoch": 27.27,
+      "eval_accuracy_score": 0.9530182232346242,
+      "eval_f1": 0.7344877344877345,
+      "eval_loss": 0.23747360706329346,
+      "eval_precision": 0.6906377204884667,
+      "eval_recall": 0.7842835130970724,
+      "eval_runtime": 1.8232,
+      "eval_samples_per_second": 164.543,
+      "eval_steps_per_second": 20.842,
+      "step": 1800
+    },
+    {
+      "epoch": 30.3,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.006,
+      "step": 2000
+    },
+    {
+      "epoch": 30.3,
+      "eval_accuracy_score": 0.9557232346241458,
+      "eval_f1": 0.7485549132947977,
+      "eval_loss": 0.23886878788471222,
+      "eval_precision": 0.7047619047619048,
+      "eval_recall": 0.7981510015408321,
+      "eval_runtime": 1.8593,
+      "eval_samples_per_second": 161.349,
+      "eval_steps_per_second": 20.437,
+      "step": 2000
+    },
+    {
+      "epoch": 33.33,
+      "eval_accuracy_score": 0.9558656036446469,
+      "eval_f1": 0.7386609071274299,
+      "eval_loss": 0.22935760021209717,
+      "eval_precision": 0.6932432432432433,
+      "eval_recall": 0.7904468412942989,
+      "eval_runtime": 1.8284,
+      "eval_samples_per_second": 164.075,
+      "eval_steps_per_second": 20.783,
+      "step": 2200
+    },
+    {
+      "epoch": 36.36,
+      "eval_accuracy_score": 0.9588553530751709,
+      "eval_f1": 0.7606038820992091,
+      "eval_loss": 0.22713881731033325,
+      "eval_precision": 0.7129380053908356,
+      "eval_recall": 0.8151001540832049,
+      "eval_runtime": 1.8307,
+      "eval_samples_per_second": 163.87,
+      "eval_steps_per_second": 20.757,
+      "step": 2400
+    },
+    {
+      "epoch": 37.88,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0041,
+      "step": 2500
+    },
+    {
+      "epoch": 39.39,
+      "eval_accuracy_score": 0.9557232346241458,
+      "eval_f1": 0.7356154406409323,
+      "eval_loss": 0.2489270567893982,
+      "eval_precision": 0.6975138121546961,
+      "eval_recall": 0.7781201848998459,
+      "eval_runtime": 1.8248,
+      "eval_samples_per_second": 164.405,
+      "eval_steps_per_second": 20.825,
+      "step": 2600
+    },
+    {
+      "epoch": 42.42,
+      "eval_accuracy_score": 0.9503132118451025,
+      "eval_f1": 0.7259786476868327,
+      "eval_loss": 0.30249449610710144,
+      "eval_precision": 0.6746031746031746,
+      "eval_recall": 0.785824345146379,
+      "eval_runtime": 1.813,
+      "eval_samples_per_second": 165.469,
+      "eval_steps_per_second": 20.959,
+      "step": 2800
+    },
+    {
+      "epoch": 45.45,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.0024,
+      "step": 3000
+    },
+    {
+      "epoch": 45.45,
+      "eval_accuracy_score": 0.9555808656036446,
+      "eval_f1": 0.7521739130434784,
+      "eval_loss": 0.25840774178504944,
+      "eval_precision": 0.7099863201094391,
+      "eval_recall": 0.7996918335901386,
+      "eval_runtime": 1.8125,
+      "eval_samples_per_second": 165.516,
+      "eval_steps_per_second": 20.965,
+      "step": 3000
+    },
+    {
+      "epoch": 48.48,
+      "eval_accuracy_score": 0.9533029612756264,
+      "eval_f1": 0.7311669128508125,
+      "eval_loss": 0.2636038661003113,
+      "eval_precision": 0.7021276595744681,
+      "eval_recall": 0.7627118644067796,
+      "eval_runtime": 1.8225,
+      "eval_samples_per_second": 164.607,
+      "eval_steps_per_second": 20.85,
+      "step": 3200
+    },
+    {
+      "epoch": 51.52,
+      "eval_accuracy_score": 0.9558656036446469,
+      "eval_f1": 0.7386609071274299,
+      "eval_loss": 0.2609228789806366,
+      "eval_precision": 0.6932432432432433,
+      "eval_recall": 0.7904468412942989,
+      "eval_runtime": 1.8187,
+      "eval_samples_per_second": 164.949,
+      "eval_steps_per_second": 20.894,
+      "step": 3400
+    },
+    {
+      "epoch": 53.03,
+      "learning_rate": 3.859060402684564e-05,
+      "loss": 0.0031,
+      "step": 3500
+    },
+    {
+      "epoch": 54.55,
+      "eval_accuracy_score": 0.9572892938496583,
+      "eval_f1": 0.7478134110787171,
+      "eval_loss": 0.2473631501197815,
+      "eval_precision": 0.7095435684647303,
+      "eval_recall": 0.7904468412942989,
+      "eval_runtime": 1.8173,
+      "eval_samples_per_second": 165.08,
+      "eval_steps_per_second": 20.91,
+      "step": 3600
+    },
+    {
+      "epoch": 57.58,
+      "eval_accuracy_score": 0.9547266514806378,
+      "eval_f1": 0.7534545454545455,
+      "eval_loss": 0.2842201292514801,
+      "eval_precision": 0.7134986225895317,
+      "eval_recall": 0.7981510015408321,
+      "eval_runtime": 1.8179,
+      "eval_samples_per_second": 165.029,
+      "eval_steps_per_second": 20.904,
+      "step": 3800
+    },
+    {
+      "epoch": 60.61,
+      "learning_rate": 3.6912751677852356e-05,
+      "loss": 0.0023,
+      "step": 4000
+    },
+    {
+      "epoch": 60.61,
+      "eval_accuracy_score": 0.9561503416856492,
+      "eval_f1": 0.7446964155084126,
+      "eval_loss": 0.2753300070762634,
+      "eval_precision": 0.7089136490250696,
+      "eval_recall": 0.7842835130970724,
+      "eval_runtime": 1.809,
+      "eval_samples_per_second": 165.841,
+      "eval_steps_per_second": 21.006,
+      "step": 4000
+    },
+    {
+      "epoch": 63.64,
+      "eval_accuracy_score": 0.9565774487471527,
+      "eval_f1": 0.7445887445887446,
+      "eval_loss": 0.26731398701667786,
+      "eval_precision": 0.7001356852103121,
+      "eval_recall": 0.7950693374422187,
+      "eval_runtime": 1.8118,
+      "eval_samples_per_second": 165.585,
+      "eval_steps_per_second": 20.974,
+      "step": 4200
+    },
+    {
+      "epoch": 66.67,
+      "eval_accuracy_score": 0.9592824601366743,
+      "eval_f1": 0.7662053896576839,
+      "eval_loss": 0.25669774413108826,
+      "eval_precision": 0.7265193370165746,
+      "eval_recall": 0.810477657935285,
+      "eval_runtime": 1.8165,
+      "eval_samples_per_second": 165.149,
+      "eval_steps_per_second": 20.919,
+      "step": 4400
+    },
+    {
+      "epoch": 68.18,
+      "learning_rate": 3.523489932885906e-05,
+      "loss": 0.0013,
+      "step": 4500
+    },
+    {
+      "epoch": 69.7,
+      "eval_accuracy_score": 0.9578587699316629,
+      "eval_f1": 0.7628865979381444,
+      "eval_loss": 0.26889553666114807,
+      "eval_precision": 0.7306064880112835,
+      "eval_recall": 0.7981510015408321,
+      "eval_runtime": 1.8209,
+      "eval_samples_per_second": 164.757,
+      "eval_steps_per_second": 20.869,
+      "step": 4600
+    },
+    {
+      "epoch": 72.73,
+      "eval_accuracy_score": 0.9541571753986332,
+      "eval_f1": 0.7272727272727272,
+      "eval_loss": 0.27668488025665283,
+      "eval_precision": 0.683853459972863,
+      "eval_recall": 0.7765793528505393,
+      "eval_runtime": 1.819,
+      "eval_samples_per_second": 164.922,
+      "eval_steps_per_second": 20.89,
+      "step": 4800
+    },
+    {
+      "epoch": 75.76,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 0.0017,
+      "step": 5000
+    },
+    {
+      "epoch": 75.76,
+      "eval_accuracy_score": 0.9611332574031891,
+      "eval_f1": 0.7647058823529411,
+      "eval_loss": 0.261895090341568,
+      "eval_precision": 0.7313642756680732,
+      "eval_recall": 0.8012326656394453,
+      "eval_runtime": 1.8166,
+      "eval_samples_per_second": 165.139,
+      "eval_steps_per_second": 20.918,
+      "step": 5000
+    },
+    {
+      "epoch": 78.79,
+      "eval_accuracy_score": 0.9565774487471527,
+      "eval_f1": 0.7635574837310196,
+      "eval_loss": 0.2799965441226959,
+      "eval_precision": 0.7193460490463215,
+      "eval_recall": 0.8135593220338984,
+      "eval_runtime": 1.8154,
+      "eval_samples_per_second": 165.252,
+      "eval_steps_per_second": 20.932,
+      "step": 5200
+    },
+    {
+      "epoch": 81.82,
+      "eval_accuracy_score": 0.9571469248291572,
+      "eval_f1": 0.7645756457564575,
+      "eval_loss": 0.2897091805934906,
+      "eval_precision": 0.7337110481586402,
+      "eval_recall": 0.7981510015408321,
+      "eval_runtime": 1.8225,
+      "eval_samples_per_second": 164.611,
+      "eval_steps_per_second": 20.851,
+      "step": 5400
+    },
+    {
+      "epoch": 83.33,
+      "learning_rate": 3.1879194630872485e-05,
+      "loss": 0.0013,
+      "step": 5500
+    },
+    {
+      "epoch": 84.85,
+      "eval_accuracy_score": 0.9582858769931663,
+      "eval_f1": 0.765925925925926,
+      "eval_loss": 0.28740614652633667,
+      "eval_precision": 0.7375178316690443,
+      "eval_recall": 0.7966101694915254,
+      "eval_runtime": 1.8149,
+      "eval_samples_per_second": 165.297,
+      "eval_steps_per_second": 20.938,
+      "step": 5600
+    },
+    {
+      "epoch": 87.88,
+      "eval_accuracy_score": 0.9567198177676538,
+      "eval_f1": 0.7501810282404056,
+      "eval_loss": 0.2884918749332428,
+      "eval_precision": 0.7076502732240437,
+      "eval_recall": 0.7981510015408321,
+      "eval_runtime": 1.8146,
+      "eval_samples_per_second": 165.322,
+      "eval_steps_per_second": 20.941,
+      "step": 5800
+    },
+    {
+      "epoch": 90.91,
+      "learning_rate": 3.02013422818792e-05,
+      "loss": 0.0014,
+      "step": 6000
+    },
+    {
+      "epoch": 90.91,
+      "eval_accuracy_score": 0.9524487471526196,
+      "eval_f1": 0.7301360057265569,
+      "eval_loss": 0.2914113402366638,
+      "eval_precision": 0.6818181818181818,
+      "eval_recall": 0.785824345146379,
+      "eval_runtime": 1.8206,
+      "eval_samples_per_second": 164.78,
+      "eval_steps_per_second": 20.872,
+      "step": 6000
+    },
+    {
+      "epoch": 93.94,
+      "eval_accuracy_score": 0.9501708428246014,
+      "eval_f1": 0.7317425885755603,
+      "eval_loss": 0.31541427969932556,
+      "eval_precision": 0.6893732970027248,
+      "eval_recall": 0.7796610169491526,
+      "eval_runtime": 1.8164,
+      "eval_samples_per_second": 165.165,
+      "eval_steps_per_second": 20.921,
+      "step": 6200
+    },
+    {
+      "epoch": 96.97,
+      "eval_accuracy_score": 0.9592824601366743,
+      "eval_f1": 0.7678571428571429,
+      "eval_loss": 0.26346713304519653,
+      "eval_precision": 0.7424460431654676,
+      "eval_recall": 0.7950693374422187,
+      "eval_runtime": 1.8177,
+      "eval_samples_per_second": 165.047,
+      "eval_steps_per_second": 20.906,
+      "step": 6400
+    },
+    {
+      "epoch": 98.48,
+      "learning_rate": 2.8523489932885905e-05,
+      "loss": 0.0012,
+      "step": 6500
+    },
+    {
+      "epoch": 100.0,
+      "eval_accuracy_score": 0.9578587699316629,
+      "eval_f1": 0.7687776141384388,
+      "eval_loss": 0.2713102400302887,
+      "eval_precision": 0.7362482369534555,
+      "eval_recall": 0.8043143297380585,
+      "eval_runtime": 1.8208,
+      "eval_samples_per_second": 164.767,
+      "eval_steps_per_second": 20.87,
+      "step": 6600
+    },
+    {
+      "epoch": 103.03,
+      "eval_accuracy_score": 0.9555808656036446,
+      "eval_f1": 0.7427745664739885,
+      "eval_loss": 0.2801496088504791,
+      "eval_precision": 0.6993197278911565,
+      "eval_recall": 0.7919876733436055,
+      "eval_runtime": 1.8128,
+      "eval_samples_per_second": 165.49,
+      "eval_steps_per_second": 20.962,
+      "step": 6800
+    },
+    {
+      "epoch": 106.06,
+      "learning_rate": 2.6845637583892618e-05,
+      "loss": 0.0006,
+      "step": 7000
+    },
+    {
+      "epoch": 106.06,
+      "eval_accuracy_score": 0.9574316628701595,
+      "eval_f1": 0.758169934640523,
+      "eval_loss": 0.28262782096862793,
+      "eval_precision": 0.717032967032967,
+      "eval_recall": 0.8043143297380585,
+      "eval_runtime": 1.815,
+      "eval_samples_per_second": 165.29,
+      "eval_steps_per_second": 20.937,
+      "step": 7000
+    },
+    {
+      "epoch": 109.09,
+      "eval_accuracy_score": 0.9567198177676538,
+      "eval_f1": 0.7523465703971118,
+      "eval_loss": 0.294379323720932,
+      "eval_precision": 0.7078804347826086,
+      "eval_recall": 0.802773497688752,
+      "eval_runtime": 1.8154,
+      "eval_samples_per_second": 165.256,
+      "eval_steps_per_second": 20.932,
+      "step": 7200
+    },
+    {
+      "epoch": 112.12,
+      "eval_accuracy_score": 0.9604214123006833,
+      "eval_f1": 0.7586715867158671,
+      "eval_loss": 0.27172133326530457,
+      "eval_precision": 0.7280453257790368,
+      "eval_recall": 0.7919876733436055,
+      "eval_runtime": 1.8173,
+      "eval_samples_per_second": 165.082,
+      "eval_steps_per_second": 20.91,
+      "step": 7400
+    },
+    {
+      "epoch": 113.64,
+      "learning_rate": 2.516778523489933e-05,
+      "loss": 0.0005,
+      "step": 7500
+    },
+    {
+      "epoch": 115.15,
+      "eval_accuracy_score": 0.9585706150341685,
+      "eval_f1": 0.765925925925926,
+      "eval_loss": 0.28619658946990967,
+      "eval_precision": 0.7375178316690443,
+      "eval_recall": 0.7966101694915254,
+      "eval_runtime": 1.8064,
+      "eval_samples_per_second": 166.079,
+      "eval_steps_per_second": 21.037,
+      "step": 7600
+    },
+    {
+      "epoch": 118.18,
+      "eval_accuracy_score": 0.9602790432801822,
+      "eval_f1": 0.7804878048780488,
+      "eval_loss": 0.2851082980632782,
+      "eval_precision": 0.75,
+      "eval_recall": 0.8135593220338984,
+      "eval_runtime": 1.8071,
+      "eval_samples_per_second": 166.013,
+      "eval_steps_per_second": 21.028,
+      "step": 7800
+    },
+    {
+      "epoch": 121.21,
+      "learning_rate": 2.348993288590604e-05,
+      "loss": 0.0005,
+      "step": 8000
+    },
+    {
+      "epoch": 121.21,
+      "eval_accuracy_score": 0.9578587699316629,
+      "eval_f1": 0.7696879643387815,
+      "eval_loss": 0.3037085235118866,
+      "eval_precision": 0.7431850789096126,
+      "eval_recall": 0.7981510015408321,
+      "eval_runtime": 1.8042,
+      "eval_samples_per_second": 166.279,
+      "eval_steps_per_second": 21.062,
+      "step": 8000
+    },
+    {
+      "epoch": 124.24,
+      "eval_accuracy_score": 0.9577164009111617,
+      "eval_f1": 0.7490747594374536,
+      "eval_loss": 0.2995525598526001,
+      "eval_precision": 0.7207977207977208,
+      "eval_recall": 0.7796610169491526,
+      "eval_runtime": 1.8078,
+      "eval_samples_per_second": 165.95,
+      "eval_steps_per_second": 21.02,
+      "step": 8200
+    },
+    {
+      "epoch": 127.27,
+      "eval_accuracy_score": 0.9567198177676538,
+      "eval_f1": 0.7512915129151292,
+      "eval_loss": 0.30669906735420227,
+      "eval_precision": 0.7209631728045326,
+      "eval_recall": 0.7842835130970724,
+      "eval_runtime": 1.8073,
+      "eval_samples_per_second": 165.994,
+      "eval_steps_per_second": 21.026,
+      "step": 8400
+    },
+    {
+      "epoch": 128.79,
+      "learning_rate": 2.181208053691275e-05,
+      "loss": 0.0007,
+      "step": 8500
+    },
+    {
+      "epoch": 130.3,
+      "eval_accuracy_score": 0.9607061503416856,
+      "eval_f1": 0.764792899408284,
+      "eval_loss": 0.27318519353866577,
+      "eval_precision": 0.7354196301564723,
+      "eval_recall": 0.7966101694915254,
+      "eval_runtime": 1.8004,
+      "eval_samples_per_second": 166.628,
+      "eval_steps_per_second": 21.106,
+      "step": 8600
+    },
+    {
+      "epoch": 133.33,
+      "eval_accuracy_score": 0.9567198177676538,
+      "eval_f1": 0.7402597402597403,
+      "eval_loss": 0.30070313811302185,
+      "eval_precision": 0.6960651289009498,
+      "eval_recall": 0.7904468412942989,
+      "eval_runtime": 1.8013,
+      "eval_samples_per_second": 166.549,
+      "eval_steps_per_second": 21.096,
+      "step": 8800
+    },
+    {
+      "epoch": 136.36,
+      "learning_rate": 2.013422818791946e-05,
+      "loss": 0.0006,
+      "step": 9000
+    },
+    {
+      "epoch": 136.36,
+      "eval_accuracy_score": 0.9592824601366743,
+      "eval_f1": 0.7628111273792093,
+      "eval_loss": 0.28866341710090637,
+      "eval_precision": 0.7266387726638772,
+      "eval_recall": 0.802773497688752,
+      "eval_runtime": 1.8039,
+      "eval_samples_per_second": 166.31,
+      "eval_steps_per_second": 21.066,
+      "step": 9000
+    },
+    {
+      "epoch": 136.36,
+      "step": 9000,
+      "total_flos": 4.722733803843994e+16,
+      "train_loss": 0.026613251682784823,
+      "train_runtime": 3020.8535,
+      "train_samples_per_second": 158.895,
+      "train_steps_per_second": 4.965
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 228,
+  "total_flos": 4.722733803843994e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3acece6691ce58eedf5b7e6e17accefb6c6479dc2128f2bc0ae56eab96514947
+size 3259