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": 119.4,
+    "eval_accuracy_score": 0.9705493924986793,
+    "eval_f1": 0.7951020408163265,
+    "eval_loss": 0.23545745015144348,
+    "eval_precision": 0.7867528271405493,
+    "eval_recall": 0.8036303630363036,
+    "eval_runtime": 2.4256,
+    "eval_samples": 306,
+    "eval_samples_per_second": 126.153,
+    "eval_steps_per_second": 16.078,
+    "test_accuracy_score": 0.9540281045336046,
+    "test_f1": 0.6339193381592555,
+    "test_loss": 0.36486369371414185,
+    "test_precision": 0.6039408866995074,
+    "test_recall": 0.6670293797606094,
+    "test_runtime": 4.735,
+    "test_samples": 600,
+    "test_samples_per_second": 126.716,
+    "test_steps_per_second": 15.84,
+    "train_loss": 0.029139109283685686,
+    "train_runtime": 3971.1585,
+    "train_samples": 2124,
+    "train_samples_per_second": 120.872,
+    "train_steps_per_second": 3.777
+}

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 sha256:7e8e0f0bc0f664d5f26447001c02b7e1092befcc5a6725d8fc51545c82da8e70
+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 +1,601 @@
+{
+  "best_metric": 0.7951020408163265,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-pcm/checkpoint-7000",
+  "epoch": 119.40298507462687,
+  "global_step": 8000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.99,
+      "eval_accuracy_score": 0.8950079239302694,
+      "eval_f1": 0.4056413700470114,
+      "eval_loss": 0.31147781014442444,
+      "eval_precision": 0.3420158550396376,
+      "eval_recall": 0.49834983498349833,
+      "eval_runtime": 2.4074,
+      "eval_samples_per_second": 127.107,
+      "eval_steps_per_second": 16.2,
+      "step": 200
+    },
+    {
+      "epoch": 5.97,
+      "eval_accuracy_score": 0.9330427892234548,
+      "eval_f1": 0.541019955654102,
+      "eval_loss": 0.22155305743217468,
+      "eval_precision": 0.4899598393574297,
+      "eval_recall": 0.6039603960396039,
+      "eval_runtime": 2.4071,
+      "eval_samples_per_second": 127.125,
+      "eval_steps_per_second": 16.202,
+      "step": 400
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.3727,
+      "step": 500
+    },
+    {
+      "epoch": 8.96,
+      "eval_accuracy_score": 0.9498151082937136,
+      "eval_f1": 0.6552238805970149,
+      "eval_loss": 0.18555797636508942,
+      "eval_precision": 0.5980926430517711,
+      "eval_recall": 0.7244224422442245,
+      "eval_runtime": 2.4132,
+      "eval_samples_per_second": 126.802,
+      "eval_steps_per_second": 16.161,
+      "step": 600
+    },
+    {
+      "epoch": 11.94,
+      "eval_accuracy_score": 0.95932382461701,
+      "eval_f1": 0.7168627450980393,
+      "eval_loss": 0.1749705672264099,
+      "eval_precision": 0.6831091180866966,
+      "eval_recall": 0.7541254125412541,
+      "eval_runtime": 2.408,
+      "eval_samples_per_second": 127.076,
+      "eval_steps_per_second": 16.196,
+      "step": 800
+    },
+    {
+      "epoch": 14.93,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.0555,
+      "step": 1000
+    },
+    {
+      "epoch": 14.93,
+      "eval_accuracy_score": 0.9578711040676176,
+      "eval_f1": 0.7334360554699538,
+      "eval_loss": 0.1944570541381836,
+      "eval_precision": 0.6878612716763006,
+      "eval_recall": 0.7854785478547854,
+      "eval_runtime": 2.4095,
+      "eval_samples_per_second": 127.0,
+      "eval_steps_per_second": 16.186,
+      "step": 1000
+    },
+    {
+      "epoch": 17.91,
+      "eval_accuracy_score": 0.9647385103011094,
+      "eval_f1": 0.7670364500792393,
+      "eval_loss": 0.18250040709972382,
+      "eval_precision": 0.7378048780487805,
+      "eval_recall": 0.7986798679867987,
+      "eval_runtime": 2.4111,
+      "eval_samples_per_second": 126.911,
+      "eval_steps_per_second": 16.175,
+      "step": 1200
+    },
+    {
+      "epoch": 20.9,
+      "eval_accuracy_score": 0.9630216587427364,
+      "eval_f1": 0.7384615384615385,
+      "eval_loss": 0.19533774256706238,
+      "eval_precision": 0.724960254372019,
+      "eval_recall": 0.7524752475247525,
+      "eval_runtime": 2.4014,
+      "eval_samples_per_second": 127.425,
+      "eval_steps_per_second": 16.24,
+      "step": 1400
+    },
+    {
+      "epoch": 22.39,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0105,
+      "step": 1500
+    },
+    {
+      "epoch": 23.88,
+      "eval_accuracy_score": 0.9644743792921289,
+      "eval_f1": 0.7389937106918238,
+      "eval_loss": 0.19444848597049713,
+      "eval_precision": 0.7057057057057057,
+      "eval_recall": 0.7755775577557755,
+      "eval_runtime": 2.4134,
+      "eval_samples_per_second": 126.79,
+      "eval_steps_per_second": 16.16,
+      "step": 1600
+    },
+    {
+      "epoch": 26.87,
+      "eval_accuracy_score": 0.963946117274168,
+      "eval_f1": 0.7565424266455195,
+      "eval_loss": 0.211569145321846,
+      "eval_precision": 0.7282442748091603,
+      "eval_recall": 0.7871287128712872,
+      "eval_runtime": 2.4076,
+      "eval_samples_per_second": 127.097,
+      "eval_steps_per_second": 16.199,
+      "step": 1800
+    },
+    {
+      "epoch": 29.85,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0055,
+      "step": 2000
+    },
+    {
+      "epoch": 29.85,
+      "eval_accuracy_score": 0.9611727416798732,
+      "eval_f1": 0.7248979591836734,
+      "eval_loss": 0.23255787789821625,
+      "eval_precision": 0.7172859450726979,
+      "eval_recall": 0.7326732673267327,
+      "eval_runtime": 2.4063,
+      "eval_samples_per_second": 127.167,
+      "eval_steps_per_second": 16.208,
+      "step": 2000
+    },
+    {
+      "epoch": 32.84,
+      "eval_accuracy_score": 0.9650026413100898,
+      "eval_f1": 0.7594339622641509,
+      "eval_loss": 0.21984447538852692,
+      "eval_precision": 0.7252252252252253,
+      "eval_recall": 0.7970297029702971,
+      "eval_runtime": 2.4107,
+      "eval_samples_per_second": 126.936,
+      "eval_steps_per_second": 16.178,
+      "step": 2200
+    },
+    {
+      "epoch": 35.82,
+      "eval_accuracy_score": 0.963946117274168,
+      "eval_f1": 0.7598736176935229,
+      "eval_loss": 0.2293044477701187,
+      "eval_precision": 0.7287878787878788,
+      "eval_recall": 0.7937293729372937,
+      "eval_runtime": 2.4114,
+      "eval_samples_per_second": 126.899,
+      "eval_steps_per_second": 16.173,
+      "step": 2400
+    },
+    {
+      "epoch": 37.31,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0038,
+      "step": 2500
+    },
+    {
+      "epoch": 38.81,
+      "eval_accuracy_score": 0.9643423137876387,
+      "eval_f1": 0.7497975708502024,
+      "eval_loss": 0.23353905975818634,
+      "eval_precision": 0.7360890302066773,
+      "eval_recall": 0.764026402640264,
+      "eval_runtime": 2.4071,
+      "eval_samples_per_second": 127.125,
+      "eval_steps_per_second": 16.202,
+      "step": 2600
+    },
+    {
+      "epoch": 41.79,
+      "eval_accuracy_score": 0.9655309033280507,
+      "eval_f1": 0.7648,
+      "eval_loss": 0.224817156791687,
+      "eval_precision": 0.7422360248447205,
+      "eval_recall": 0.7887788778877888,
+      "eval_runtime": 2.4046,
+      "eval_samples_per_second": 127.255,
+      "eval_steps_per_second": 16.219,
+      "step": 2800
+    },
+    {
+      "epoch": 44.78,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.0032,
+      "step": 3000
+    },
+    {
+      "epoch": 44.78,
+      "eval_accuracy_score": 0.95932382461701,
+      "eval_f1": 0.7264076130055511,
+      "eval_loss": 0.26162534952163696,
+      "eval_precision": 0.6992366412213741,
+      "eval_recall": 0.7557755775577558,
+      "eval_runtime": 2.3994,
+      "eval_samples_per_second": 127.53,
+      "eval_steps_per_second": 16.254,
+      "step": 3000
+    },
+    {
+      "epoch": 47.76,
+      "eval_accuracy_score": 0.9638140517696777,
+      "eval_f1": 0.7374392220421394,
+      "eval_loss": 0.2429530769586563,
+      "eval_precision": 0.7245222929936306,
+      "eval_recall": 0.7508250825082509,
+      "eval_runtime": 2.4056,
+      "eval_samples_per_second": 127.201,
+      "eval_steps_per_second": 16.212,
+      "step": 3200
+    },
+    {
+      "epoch": 50.75,
+      "eval_accuracy_score": 0.9646064447966192,
+      "eval_f1": 0.7631578947368421,
+      "eval_loss": 0.2461545169353485,
+      "eval_precision": 0.760655737704918,
+      "eval_recall": 0.7656765676567657,
+      "eval_runtime": 2.4169,
+      "eval_samples_per_second": 126.61,
+      "eval_steps_per_second": 16.137,
+      "step": 3400
+    },
+    {
+      "epoch": 52.24,
+      "learning_rate": 3.859060402684564e-05,
+      "loss": 0.0027,
+      "step": 3500
+    },
+    {
+      "epoch": 53.73,
+      "eval_accuracy_score": 0.9615689381933439,
+      "eval_f1": 0.7359870024370431,
+      "eval_loss": 0.25643840432167053,
+      "eval_precision": 0.7248,
+      "eval_recall": 0.7475247524752475,
+      "eval_runtime": 2.402,
+      "eval_samples_per_second": 127.392,
+      "eval_steps_per_second": 16.236,
+      "step": 3600
+    },
+    {
+      "epoch": 56.72,
+      "eval_accuracy_score": 0.96513470681458,
+      "eval_f1": 0.7636932707355242,
+      "eval_loss": 0.24773868918418884,
+      "eval_precision": 0.7261904761904762,
+      "eval_recall": 0.8052805280528053,
+      "eval_runtime": 2.406,
+      "eval_samples_per_second": 127.183,
+      "eval_steps_per_second": 16.21,
+      "step": 3800
+    },
+    {
+      "epoch": 59.7,
+      "learning_rate": 3.6912751677852356e-05,
+      "loss": 0.0019,
+      "step": 4000
+    },
+    {
+      "epoch": 59.7,
+      "eval_accuracy_score": 0.9615689381933439,
+      "eval_f1": 0.7295796986518637,
+      "eval_loss": 0.27105194330215454,
+      "eval_precision": 0.7022900763358778,
+      "eval_recall": 0.759075907590759,
+      "eval_runtime": 2.4067,
+      "eval_samples_per_second": 127.143,
+      "eval_steps_per_second": 16.204,
+      "step": 4000
+    },
+    {
+      "epoch": 62.69,
+      "eval_accuracy_score": 0.9620972002113048,
+      "eval_f1": 0.7459807073954984,
+      "eval_loss": 0.2745388150215149,
+      "eval_precision": 0.7272727272727273,
+      "eval_recall": 0.7656765676567657,
+      "eval_runtime": 2.4067,
+      "eval_samples_per_second": 127.143,
+      "eval_steps_per_second": 16.205,
+      "step": 4200
+    },
+    {
+      "epoch": 65.67,
+      "eval_accuracy_score": 0.9632857897517169,
+      "eval_f1": 0.7472353870458136,
+      "eval_loss": 0.26222512125968933,
+      "eval_precision": 0.7166666666666667,
+      "eval_recall": 0.7805280528052805,
+      "eval_runtime": 2.4079,
+      "eval_samples_per_second": 127.079,
+      "eval_steps_per_second": 16.196,
+      "step": 4400
+    },
+    {
+      "epoch": 67.16,
+      "learning_rate": 3.523489932885906e-05,
+      "loss": 0.0019,
+      "step": 4500
+    },
+    {
+      "epoch": 68.66,
+      "eval_accuracy_score": 0.9644743792921289,
+      "eval_f1": 0.7557677008750995,
+      "eval_loss": 0.25255098938941956,
+      "eval_precision": 0.7296466973886329,
+      "eval_recall": 0.7838283828382838,
+      "eval_runtime": 2.4095,
+      "eval_samples_per_second": 126.996,
+      "eval_steps_per_second": 16.186,
+      "step": 4600
+    },
+    {
+      "epoch": 71.64,
+      "eval_accuracy_score": 0.9657950343370312,
+      "eval_f1": 0.765079365079365,
+      "eval_loss": 0.2474120408296585,
+      "eval_precision": 0.7370030581039755,
+      "eval_recall": 0.7953795379537953,
+      "eval_runtime": 2.4085,
+      "eval_samples_per_second": 127.049,
+      "eval_steps_per_second": 16.192,
+      "step": 4800
+    },
+    {
+      "epoch": 74.63,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 0.0018,
+      "step": 5000
+    },
+    {
+      "epoch": 74.63,
+      "eval_accuracy_score": 0.9653988378235605,
+      "eval_f1": 0.7618296529968455,
+      "eval_loss": 0.2491973489522934,
+      "eval_precision": 0.729607250755287,
+      "eval_recall": 0.7970297029702971,
+      "eval_runtime": 2.4082,
+      "eval_samples_per_second": 127.066,
+      "eval_steps_per_second": 16.195,
+      "step": 5000
+    },
+    {
+      "epoch": 77.61,
+      "eval_accuracy_score": 0.963946117274168,
+      "eval_f1": 0.7564604541895067,
+      "eval_loss": 0.2652634084224701,
+      "eval_precision": 0.7198211624441133,
+      "eval_recall": 0.7970297029702971,
+      "eval_runtime": 2.4091,
+      "eval_samples_per_second": 127.02,
+      "eval_steps_per_second": 16.189,
+      "step": 5200
+    },
+    {
+      "epoch": 80.6,
+      "eval_accuracy_score": 0.963946117274168,
+      "eval_f1": 0.7577235772357722,
+      "eval_loss": 0.2766047418117523,
+      "eval_precision": 0.7467948717948718,
+      "eval_recall": 0.768976897689769,
+      "eval_runtime": 2.4127,
+      "eval_samples_per_second": 126.83,
+      "eval_steps_per_second": 16.165,
+      "step": 5400
+    },
+    {
+      "epoch": 82.09,
+      "learning_rate": 3.1879194630872485e-05,
+      "loss": 0.0012,
+      "step": 5500
+    },
+    {
+      "epoch": 83.58,
+      "eval_accuracy_score": 0.9627575277337559,
+      "eval_f1": 0.7384855581576891,
+      "eval_loss": 0.2791267931461334,
+      "eval_precision": 0.7007407407407408,
+      "eval_recall": 0.7805280528052805,
+      "eval_runtime": 2.4092,
+      "eval_samples_per_second": 127.015,
+      "eval_steps_per_second": 16.188,
+      "step": 5600
+    },
+    {
+      "epoch": 86.57,
+      "eval_accuracy_score": 0.9672477548864237,
+      "eval_f1": 0.7776000000000001,
+      "eval_loss": 0.24720582365989685,
+      "eval_precision": 0.7546583850931677,
+      "eval_recall": 0.801980198019802,
+      "eval_runtime": 2.4153,
+      "eval_samples_per_second": 126.694,
+      "eval_steps_per_second": 16.147,
+      "step": 5800
+    },
+    {
+      "epoch": 89.55,
+      "learning_rate": 3.02013422818792e-05,
+      "loss": 0.0013,
+      "step": 6000
+    },
+    {
+      "epoch": 89.55,
+      "eval_accuracy_score": 0.9664553618594823,
+      "eval_f1": 0.7794707297514034,
+      "eval_loss": 0.25364401936531067,
+      "eval_precision": 0.7581903276131046,
+      "eval_recall": 0.801980198019802,
+      "eval_runtime": 2.4087,
+      "eval_samples_per_second": 127.037,
+      "eval_steps_per_second": 16.191,
+      "step": 6000
+    },
+    {
+      "epoch": 92.54,
+      "eval_accuracy_score": 0.9676439513998943,
+      "eval_f1": 0.7832393231265109,
+      "eval_loss": 0.25377386808395386,
+      "eval_precision": 0.7653543307086614,
+      "eval_recall": 0.801980198019802,
+      "eval_runtime": 2.4146,
+      "eval_samples_per_second": 126.731,
+      "eval_steps_per_second": 16.152,
+      "step": 6200
+    },
+    {
+      "epoch": 95.52,
+      "eval_accuracy_score": 0.9689646064447967,
+      "eval_f1": 0.7859424920127794,
+      "eval_loss": 0.23607416450977325,
+      "eval_precision": 0.7616099071207431,
+      "eval_recall": 0.8118811881188119,
+      "eval_runtime": 2.4167,
+      "eval_samples_per_second": 126.62,
+      "eval_steps_per_second": 16.138,
+      "step": 6400
+    },
+    {
+      "epoch": 97.01,
+      "learning_rate": 2.8523489932885905e-05,
+      "loss": 0.0014,
+      "step": 6500
+    },
+    {
+      "epoch": 98.51,
+      "eval_accuracy_score": 0.9696249339672478,
+      "eval_f1": 0.784155214227971,
+      "eval_loss": 0.22985981404781342,
+      "eval_precision": 0.768621236133122,
+      "eval_recall": 0.8003300330033003,
+      "eval_runtime": 2.4152,
+      "eval_samples_per_second": 126.699,
+      "eval_steps_per_second": 16.148,
+      "step": 6600
+    },
+    {
+      "epoch": 101.49,
+      "eval_accuracy_score": 0.969228737453777,
+      "eval_f1": 0.7798537774167345,
+      "eval_loss": 0.2279633730649948,
+      "eval_precision": 0.768,
+      "eval_recall": 0.7920792079207921,
+      "eval_runtime": 2.4192,
+      "eval_samples_per_second": 126.488,
+      "eval_steps_per_second": 16.121,
+      "step": 6800
+    },
+    {
+      "epoch": 104.48,
+      "learning_rate": 2.6845637583892618e-05,
+      "loss": 0.001,
+      "step": 7000
+    },
+    {
+      "epoch": 104.48,
+      "eval_accuracy_score": 0.9705493924986793,
+      "eval_f1": 0.7951020408163265,
+      "eval_loss": 0.23545745015144348,
+      "eval_precision": 0.7867528271405493,
+      "eval_recall": 0.8036303630363036,
+      "eval_runtime": 2.41,
+      "eval_samples_per_second": 126.97,
+      "eval_steps_per_second": 16.182,
+      "step": 7000
+    },
+    {
+      "epoch": 107.46,
+      "eval_accuracy_score": 0.9688325409403064,
+      "eval_f1": 0.7739340305711988,
+      "eval_loss": 0.23859038949012756,
+      "eval_precision": 0.7551020408163265,
+      "eval_recall": 0.7937293729372937,
+      "eval_runtime": 2.4059,
+      "eval_samples_per_second": 127.189,
+      "eval_steps_per_second": 16.21,
+      "step": 7200
+    },
+    {
+      "epoch": 110.45,
+      "eval_accuracy_score": 0.9684363444268357,
+      "eval_f1": 0.7909967845659165,
+      "eval_loss": 0.2557569444179535,
+      "eval_precision": 0.7711598746081505,
+      "eval_recall": 0.8118811881188119,
+      "eval_runtime": 2.4083,
+      "eval_samples_per_second": 127.062,
+      "eval_steps_per_second": 16.194,
+      "step": 7400
+    },
+    {
+      "epoch": 111.94,
+      "learning_rate": 2.516778523489933e-05,
+      "loss": 0.0008,
+      "step": 7500
+    },
+    {
+      "epoch": 113.43,
+      "eval_accuracy_score": 0.9683042789223455,
+      "eval_f1": 0.7780429594272077,
+      "eval_loss": 0.2508944869041443,
+      "eval_precision": 0.7511520737327189,
+      "eval_recall": 0.806930693069307,
+      "eval_runtime": 2.4124,
+      "eval_samples_per_second": 126.846,
+      "eval_steps_per_second": 16.167,
+      "step": 7600
+    },
+    {
+      "epoch": 116.42,
+      "eval_accuracy_score": 0.9681722134178553,
+      "eval_f1": 0.7712206952303962,
+      "eval_loss": 0.2467135787010193,
+      "eval_precision": 0.7559429477020603,
+      "eval_recall": 0.7871287128712872,
+      "eval_runtime": 2.4114,
+      "eval_samples_per_second": 126.896,
+      "eval_steps_per_second": 16.173,
+      "step": 7800
+    },
+    {
+      "epoch": 119.4,
+      "learning_rate": 2.348993288590604e-05,
+      "loss": 0.0011,
+      "step": 8000
+    },
+    {
+      "epoch": 119.4,
+      "eval_accuracy_score": 0.966323296354992,
+      "eval_f1": 0.7704654895666132,
+      "eval_loss": 0.24946843087673187,
+      "eval_precision": 0.75,
+      "eval_recall": 0.7920792079207921,
+      "eval_runtime": 2.4125,
+      "eval_samples_per_second": 126.837,
+      "eval_steps_per_second": 16.166,
+      "step": 8000
+    },
+    {
+      "epoch": 119.4,
+      "step": 8000,
+      "total_flos": 4.164857671044096e+16,
+      "train_loss": 0.029139109283685686,
+      "train_runtime": 3971.1585,
+      "train_samples_per_second": 120.872,
+      "train_steps_per_second": 3.777
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 224,
+  "total_flos": 4.164857671044096e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:075bec07a6e14a0842c0efec93e592b23ca2d2f567dc848c4f855ee52696c7c5
+size 3259