Upload with huggingface_hub

Browse files

Files changed (9) hide show

README.md +15 -0
all_results.json +26 -0
config.json +51 -0
pytorch_model.bin +3 -0
special_tokens_map.json +1 -0
test_predictions.txt +0 -0
tokenizer_config.json +1 -0
trainer_state.json +625 -0
training_args.bin +3 -0

README.md ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+    "epoch": 152.73,
+    "eval_accuracy_score": 0.8968824940047961,
+    "eval_f1": 0.3843843843843844,
+    "eval_loss": 0.8679910898208618,
+    "eval_precision": 0.378698224852071,
+    "eval_recall": 0.3902439024390244,
+    "eval_runtime": 1.9394,
+    "eval_samples": 250,
+    "eval_samples_per_second": 128.906,
+    "eval_steps_per_second": 16.5,
+    "test_accuracy_score": 0.8915436241610738,
+    "test_f1": 0.3150442477876106,
+    "test_loss": 0.9644748568534851,
+    "test_precision": 0.3111888111888112,
+    "test_recall": 0.31899641577060933,
+    "test_runtime": 3.8558,
+    "test_samples": 500,
+    "test_samples_per_second": 129.676,
+    "test_steps_per_second": 16.339,
+    "train_loss": 0.05317856186912173,
+    "train_runtime": 6259.9994,
+    "train_samples": 1750,
+    "train_samples_per_second": 76.677,
+    "train_steps_per_second": 2.396
+}

config.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cd05e5e32150fa76e3a10f196e240e2c8920b6539d643e132f53bac012030a3f
+size 528594737

special_tokens_map.json ADDED Viewed

	@@ -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}}

test_predictions.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,625 @@

+{
+  "best_metric": 0.3843843843843844,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-amh/checkpoint-7000",
+  "epoch": 152.72727272727272,
+  "global_step": 8400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.64,
+      "eval_accuracy_score": 0.8550492938982147,
+      "eval_f1": 0.18181818181818182,
+      "eval_loss": 0.5423177480697632,
+      "eval_precision": 0.25842696629213485,
+      "eval_recall": 0.1402439024390244,
+      "eval_runtime": 1.939,
+      "eval_samples_per_second": 128.935,
+      "eval_steps_per_second": 16.504,
+      "step": 200
+    },
+    {
+      "epoch": 7.27,
+      "eval_accuracy_score": 0.8651745270450306,
+      "eval_f1": 0.2825484764542936,
+      "eval_loss": 0.47274425625801086,
+      "eval_precision": 0.25888324873096447,
+      "eval_recall": 0.31097560975609756,
+      "eval_runtime": 1.9444,
+      "eval_samples_per_second": 128.574,
+      "eval_steps_per_second": 16.457,
+      "step": 400
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 4.865771812080537e-05,
+      "loss": 0.5536,
+      "step": 500
+    },
+    {
+      "epoch": 10.91,
+      "eval_accuracy_score": 0.8779642952304823,
+      "eval_f1": 0.31172413793103443,
+      "eval_loss": 0.4644899368286133,
+      "eval_precision": 0.28463476070528965,
+      "eval_recall": 0.3445121951219512,
+      "eval_runtime": 1.955,
+      "eval_samples_per_second": 127.88,
+      "eval_steps_per_second": 16.369,
+      "step": 600
+    },
+    {
+      "epoch": 14.55,
+      "eval_accuracy_score": 0.8763655742073009,
+      "eval_f1": 0.3186813186813187,
+      "eval_loss": 0.4930596649646759,
+      "eval_precision": 0.29,
+      "eval_recall": 0.35365853658536583,
+      "eval_runtime": 1.9394,
+      "eval_samples_per_second": 128.906,
+      "eval_steps_per_second": 16.5,
+      "step": 800
+    },
+    {
+      "epoch": 18.18,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.1937,
+      "step": 1000
+    },
+    {
+      "epoch": 18.18,
+      "eval_accuracy_score": 0.8840927258193445,
+      "eval_f1": 0.33570412517780934,
+      "eval_loss": 0.5170220732688904,
+      "eval_precision": 0.31466666666666665,
+      "eval_recall": 0.3597560975609756,
+      "eval_runtime": 1.9489,
+      "eval_samples_per_second": 128.275,
+      "eval_steps_per_second": 16.419,
+      "step": 1000
+    },
+    {
+      "epoch": 21.82,
+      "eval_accuracy_score": 0.8878230748734346,
+      "eval_f1": 0.33956834532374097,
+      "eval_loss": 0.5543549656867981,
+      "eval_precision": 0.3215258855585831,
+      "eval_recall": 0.3597560975609756,
+      "eval_runtime": 1.948,
+      "eval_samples_per_second": 128.334,
+      "eval_steps_per_second": 16.427,
+      "step": 1200
+    },
+    {
+      "epoch": 25.45,
+      "eval_accuracy_score": 0.8904876099120703,
+      "eval_f1": 0.36811594202898545,
+      "eval_loss": 0.5699805617332458,
+      "eval_precision": 0.35082872928176795,
+      "eval_recall": 0.3871951219512195,
+      "eval_runtime": 1.9374,
+      "eval_samples_per_second": 129.042,
+      "eval_steps_per_second": 16.517,
+      "step": 1400
+    },
+    {
+      "epoch": 27.27,
+      "learning_rate": 4.530201342281879e-05,
+      "loss": 0.0666,
+      "step": 1500
+    },
+    {
+      "epoch": 29.09,
+      "eval_accuracy_score": 0.8878230748734346,
+      "eval_f1": 0.358974358974359,
+      "eval_loss": 0.6034800410270691,
+      "eval_precision": 0.33689839572192515,
+      "eval_recall": 0.38414634146341464,
+      "eval_runtime": 1.9432,
+      "eval_samples_per_second": 128.651,
+      "eval_steps_per_second": 16.467,
+      "step": 1600
+    },
+    {
+      "epoch": 32.73,
+      "eval_accuracy_score": 0.8883559818811617,
+      "eval_f1": 0.3724137931034482,
+      "eval_loss": 0.6207764744758606,
+      "eval_precision": 0.34005037783375314,
+      "eval_recall": 0.4115853658536585,
+      "eval_runtime": 1.9449,
+      "eval_samples_per_second": 128.538,
+      "eval_steps_per_second": 16.453,
+      "step": 1800
+    },
+    {
+      "epoch": 36.36,
+      "learning_rate": 4.36241610738255e-05,
+      "loss": 0.0254,
+      "step": 2000
+    },
+    {
+      "epoch": 36.36,
+      "eval_accuracy_score": 0.8907540634159339,
+      "eval_f1": 0.35460992907801414,
+      "eval_loss": 0.6343292593955994,
+      "eval_precision": 0.33156498673740054,
+      "eval_recall": 0.38109756097560976,
+      "eval_runtime": 7.9566,
+      "eval_samples_per_second": 31.42,
+      "eval_steps_per_second": 4.022,
+      "step": 2000
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy_score": 0.8928856914468425,
+      "eval_f1": 0.3611111111111111,
+      "eval_loss": 0.6792951822280884,
+      "eval_precision": 0.365625,
+      "eval_recall": 0.3567073170731707,
+      "eval_runtime": 1.9365,
+      "eval_samples_per_second": 129.101,
+      "eval_steps_per_second": 16.525,
+      "step": 2200
+    },
+    {
+      "epoch": 43.64,
+      "eval_accuracy_score": 0.8920863309352518,
+      "eval_f1": 0.36465638148667606,
+      "eval_loss": 0.6779835224151611,
+      "eval_precision": 0.33766233766233766,
+      "eval_recall": 0.39634146341463417,
+      "eval_runtime": 1.9311,
+      "eval_samples_per_second": 129.461,
+      "eval_steps_per_second": 16.571,
+      "step": 2400
+    },
+    {
+      "epoch": 45.45,
+      "learning_rate": 4.194630872483222e-05,
+      "loss": 0.0133,
+      "step": 2500
+    },
+    {
+      "epoch": 47.27,
+      "eval_accuracy_score": 0.8920863309352518,
+      "eval_f1": 0.36775106082036774,
+      "eval_loss": 0.6805456876754761,
+      "eval_precision": 0.34300791556728233,
+      "eval_recall": 0.39634146341463417,
+      "eval_runtime": 1.9389,
+      "eval_samples_per_second": 128.941,
+      "eval_steps_per_second": 16.504,
+      "step": 2600
+    },
+    {
+      "epoch": 50.91,
+      "eval_accuracy_score": 0.8920863309352518,
+      "eval_f1": 0.34452554744525543,
+      "eval_loss": 0.7049936056137085,
+      "eval_precision": 0.33053221288515405,
+      "eval_recall": 0.3597560975609756,
+      "eval_runtime": 1.9347,
+      "eval_samples_per_second": 129.22,
+      "eval_steps_per_second": 16.54,
+      "step": 2800
+    },
+    {
+      "epoch": 54.55,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.0086,
+      "step": 3000
+    },
+    {
+      "epoch": 54.55,
+      "eval_accuracy_score": 0.8947508659738875,
+      "eval_f1": 0.362555720653789,
+      "eval_loss": 0.7268127799034119,
+      "eval_precision": 0.3536231884057971,
+      "eval_recall": 0.3719512195121951,
+      "eval_runtime": 1.9322,
+      "eval_samples_per_second": 129.384,
+      "eval_steps_per_second": 16.561,
+      "step": 3000
+    },
+    {
+      "epoch": 58.18,
+      "eval_accuracy_score": 0.8958166799893419,
+      "eval_f1": 0.3654970760233918,
+      "eval_loss": 0.7148891687393188,
+      "eval_precision": 0.351123595505618,
+      "eval_recall": 0.38109756097560976,
+      "eval_runtime": 1.9378,
+      "eval_samples_per_second": 129.014,
+      "eval_steps_per_second": 16.514,
+      "step": 3200
+    },
+    {
+      "epoch": 61.82,
+      "eval_accuracy_score": 0.8926192379429789,
+      "eval_f1": 0.3541364296081277,
+      "eval_loss": 0.7266244888305664,
+      "eval_precision": 0.3379501385041551,
+      "eval_recall": 0.3719512195121951,
+      "eval_runtime": 1.9376,
+      "eval_samples_per_second": 129.025,
+      "eval_steps_per_second": 16.515,
+      "step": 3400
+    },
+    {
+      "epoch": 63.64,
+      "learning_rate": 3.859060402684564e-05,
+      "loss": 0.0064,
+      "step": 3500
+    },
+    {
+      "epoch": 65.45,
+      "eval_accuracy_score": 0.8902211564082068,
+      "eval_f1": 0.37822349570200575,
+      "eval_loss": 0.746965229511261,
+      "eval_precision": 0.3567567567567568,
+      "eval_recall": 0.4024390243902439,
+      "eval_runtime": 1.934,
+      "eval_samples_per_second": 129.263,
+      "eval_steps_per_second": 16.546,
+      "step": 3600
+    },
+    {
+      "epoch": 69.09,
+      "eval_accuracy_score": 0.8992805755395683,
+      "eval_f1": 0.38730158730158737,
+      "eval_loss": 0.768635630607605,
+      "eval_precision": 0.40397350993377484,
+      "eval_recall": 0.3719512195121951,
+      "eval_runtime": 1.936,
+      "eval_samples_per_second": 129.13,
+      "eval_steps_per_second": 16.529,
+      "step": 3800
+    },
+    {
+      "epoch": 72.73,
+      "learning_rate": 3.6912751677852356e-05,
+      "loss": 0.0049,
+      "step": 4000
+    },
+    {
+      "epoch": 72.73,
+      "eval_accuracy_score": 0.8886224353850253,
+      "eval_f1": 0.3631284916201117,
+      "eval_loss": 0.7521090507507324,
+      "eval_precision": 0.33505154639175255,
+      "eval_recall": 0.39634146341463417,
+      "eval_runtime": 1.9329,
+      "eval_samples_per_second": 129.341,
+      "eval_steps_per_second": 16.556,
+      "step": 4000
+    },
+    {
+      "epoch": 76.36,
+      "eval_accuracy_score": 0.8966160405009326,
+      "eval_f1": 0.3831640058055153,
+      "eval_loss": 0.7643349170684814,
+      "eval_precision": 0.3656509695290859,
+      "eval_recall": 0.4024390243902439,
+      "eval_runtime": 1.9372,
+      "eval_samples_per_second": 129.05,
+      "eval_steps_per_second": 16.518,
+      "step": 4200
+    },
+    {
+      "epoch": 80.0,
+      "eval_accuracy_score": 0.8904876099120703,
+      "eval_f1": 0.35942028985507246,
+      "eval_loss": 0.7822825908660889,
+      "eval_precision": 0.3425414364640884,
+      "eval_recall": 0.3780487804878049,
+      "eval_runtime": 1.9392,
+      "eval_samples_per_second": 128.916,
+      "eval_steps_per_second": 16.501,
+      "step": 4400
+    },
+    {
+      "epoch": 81.82,
+      "learning_rate": 3.523489932885906e-05,
+      "loss": 0.0042,
+      "step": 4500
+    },
+    {
+      "epoch": 83.64,
+      "eval_accuracy_score": 0.8910205169197974,
+      "eval_f1": 0.36775106082036774,
+      "eval_loss": 0.7950363755226135,
+      "eval_precision": 0.34300791556728233,
+      "eval_recall": 0.39634146341463417,
+      "eval_runtime": 1.9356,
+      "eval_samples_per_second": 129.16,
+      "eval_steps_per_second": 16.533,
+      "step": 4600
+    },
+    {
+      "epoch": 87.27,
+      "eval_accuracy_score": 0.8958166799893419,
+      "eval_f1": 0.3740573152337858,
+      "eval_loss": 0.7768180966377258,
+      "eval_precision": 0.3701492537313433,
+      "eval_recall": 0.3780487804878049,
+      "eval_runtime": 1.9278,
+      "eval_samples_per_second": 129.685,
+      "eval_steps_per_second": 16.6,
+      "step": 4800
+    },
+    {
+      "epoch": 90.91,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 0.0034,
+      "step": 5000
+    },
+    {
+      "epoch": 90.91,
+      "eval_accuracy_score": 0.8854249933386624,
+      "eval_f1": 0.3408450704225352,
+      "eval_loss": 0.8097852468490601,
+      "eval_precision": 0.31675392670157065,
+      "eval_recall": 0.36890243902439024,
+      "eval_runtime": 1.9518,
+      "eval_samples_per_second": 128.087,
+      "eval_steps_per_second": 16.395,
+      "step": 5000
+    },
+    {
+      "epoch": 94.55,
+      "eval_accuracy_score": 0.8928856914468425,
+      "eval_f1": 0.3826086956521739,
+      "eval_loss": 0.8147957921028137,
+      "eval_precision": 0.36464088397790057,
+      "eval_recall": 0.4024390243902439,
+      "eval_runtime": 1.9329,
+      "eval_samples_per_second": 129.34,
+      "eval_steps_per_second": 16.555,
+      "step": 5200
+    },
+    {
+      "epoch": 98.18,
+      "eval_accuracy_score": 0.8939515054622968,
+      "eval_f1": 0.37125748502994016,
+      "eval_loss": 0.826421856880188,
+      "eval_precision": 0.36470588235294116,
+      "eval_recall": 0.3780487804878049,
+      "eval_runtime": 1.9341,
+      "eval_samples_per_second": 129.257,
+      "eval_steps_per_second": 16.545,
+      "step": 5400
+    },
+    {
+      "epoch": 100.0,
+      "learning_rate": 3.1879194630872485e-05,
+      "loss": 0.0025,
+      "step": 5500
+    },
+    {
+      "epoch": 101.82,
+      "eval_accuracy_score": 0.8936850519584333,
+      "eval_f1": 0.37181409295352325,
+      "eval_loss": 0.8357872366905212,
+      "eval_precision": 0.36578171091445427,
+      "eval_recall": 0.3780487804878049,
+      "eval_runtime": 1.9277,
+      "eval_samples_per_second": 129.688,
+      "eval_steps_per_second": 16.6,
+      "step": 5600
+    },
+    {
+      "epoch": 105.45,
+      "eval_accuracy_score": 0.8907540634159339,
+      "eval_f1": 0.36075036075036077,
+      "eval_loss": 0.8359671235084534,
+      "eval_precision": 0.3424657534246575,
+      "eval_recall": 0.38109756097560976,
+      "eval_runtime": 1.9329,
+      "eval_samples_per_second": 129.342,
+      "eval_steps_per_second": 16.556,
+      "step": 5800
+    },
+    {
+      "epoch": 109.09,
+      "learning_rate": 3.02013422818792e-05,
+      "loss": 0.0026,
+      "step": 6000
+    },
+    {
+      "epoch": 109.09,
+      "eval_accuracy_score": 0.894484412470024,
+      "eval_f1": 0.37037037037037046,
+      "eval_loss": 0.8180095553398132,
+      "eval_precision": 0.34759358288770054,
+      "eval_recall": 0.39634146341463417,
+      "eval_runtime": 1.9323,
+      "eval_samples_per_second": 129.378,
+      "eval_steps_per_second": 16.56,
+      "step": 6000
+    },
+    {
+      "epoch": 112.73,
+      "eval_accuracy_score": 0.8926192379429789,
+      "eval_f1": 0.3592814371257485,
+      "eval_loss": 0.8526071906089783,
+      "eval_precision": 0.35294117647058826,
+      "eval_recall": 0.36585365853658536,
+      "eval_runtime": 1.9299,
+      "eval_samples_per_second": 129.542,
+      "eval_steps_per_second": 16.581,
+      "step": 6200
+    },
+    {
+      "epoch": 116.36,
+      "eval_accuracy_score": 0.8950173194777511,
+      "eval_f1": 0.38135593220338987,
+      "eval_loss": 0.8284777998924255,
+      "eval_precision": 0.35526315789473684,
+      "eval_recall": 0.4115853658536585,
+      "eval_runtime": 1.9337,
+      "eval_samples_per_second": 129.288,
+      "eval_steps_per_second": 16.549,
+      "step": 6400
+    },
+    {
+      "epoch": 118.18,
+      "learning_rate": 2.8523489932885905e-05,
+      "loss": 0.0023,
+      "step": 6500
+    },
+    {
+      "epoch": 120.0,
+      "eval_accuracy_score": 0.8979483080202505,
+      "eval_f1": 0.3795620437956205,
+      "eval_loss": 0.8373560905456543,
+      "eval_precision": 0.3641456582633053,
+      "eval_recall": 0.39634146341463417,
+      "eval_runtime": 1.931,
+      "eval_samples_per_second": 129.468,
+      "eval_steps_per_second": 16.572,
+      "step": 6600
+    },
+    {
+      "epoch": 123.64,
+      "eval_accuracy_score": 0.896349586997069,
+      "eval_f1": 0.3813682678311499,
+      "eval_loss": 0.8431832194328308,
+      "eval_precision": 0.3649025069637883,
+      "eval_recall": 0.39939024390243905,
+      "eval_runtime": 1.9307,
+      "eval_samples_per_second": 129.485,
+      "eval_steps_per_second": 16.574,
+      "step": 6800
+    },
+    {
+      "epoch": 127.27,
+      "learning_rate": 2.6845637583892618e-05,
+      "loss": 0.0017,
+      "step": 7000
+    },
+    {
+      "epoch": 127.27,
+      "eval_accuracy_score": 0.8968824940047961,
+      "eval_f1": 0.3843843843843844,
+      "eval_loss": 0.8679910898208618,
+      "eval_precision": 0.378698224852071,
+      "eval_recall": 0.3902439024390244,
+      "eval_runtime": 1.9274,
+      "eval_samples_per_second": 129.711,
+      "eval_steps_per_second": 16.603,
+      "step": 7000
+    },
+    {
+      "epoch": 130.91,
+      "eval_accuracy_score": 0.8958166799893419,
+      "eval_f1": 0.38383838383838387,
+      "eval_loss": 0.8538209199905396,
+      "eval_precision": 0.3643835616438356,
+      "eval_recall": 0.4054878048780488,
+      "eval_runtime": 1.9333,
+      "eval_samples_per_second": 129.316,
+      "eval_steps_per_second": 16.552,
+      "step": 7200
+    },
+    {
+      "epoch": 134.55,
+      "eval_accuracy_score": 0.8995470290434319,
+      "eval_f1": 0.3894582723279649,
+      "eval_loss": 0.8490965366363525,
+      "eval_precision": 0.37464788732394366,
+      "eval_recall": 0.4054878048780488,
+      "eval_runtime": 1.9341,
+      "eval_samples_per_second": 129.26,
+      "eval_steps_per_second": 16.545,
+      "step": 7400
+    },
+    {
+      "epoch": 136.36,
+      "learning_rate": 2.516778523489933e-05,
+      "loss": 0.0016,
+      "step": 7500
+    },
+    {
+      "epoch": 138.18,
+      "eval_accuracy_score": 0.8966160405009326,
+      "eval_f1": 0.37223042836041353,
+      "eval_loss": 0.8647195100784302,
+      "eval_precision": 0.36103151862464183,
+      "eval_recall": 0.38414634146341464,
+      "eval_runtime": 1.9327,
+      "eval_samples_per_second": 129.354,
+      "eval_steps_per_second": 16.557,
+      "step": 7600
+    },
+    {
+      "epoch": 141.82,
+      "eval_accuracy_score": 0.8966160405009326,
+      "eval_f1": 0.37788018433179726,
+      "eval_loss": 0.8978907465934753,
+      "eval_precision": 0.38080495356037153,
+      "eval_recall": 0.375,
+      "eval_runtime": 1.9332,
+      "eval_samples_per_second": 129.318,
+      "eval_steps_per_second": 16.553,
+      "step": 7800
+    },
+    {
+      "epoch": 145.45,
+      "learning_rate": 2.348993288590604e-05,
+      "loss": 0.0017,
+      "step": 8000
+    },
+    {
+      "epoch": 145.45,
+      "eval_accuracy_score": 0.894484412470024,
+      "eval_f1": 0.3607038123167156,
+      "eval_loss": 0.8674683570861816,
+      "eval_precision": 0.3474576271186441,
+      "eval_recall": 0.375,
+      "eval_runtime": 1.9329,
+      "eval_samples_per_second": 129.337,
+      "eval_steps_per_second": 16.555,
+      "step": 8000
+    },
+    {
+      "epoch": 149.09,
+      "eval_accuracy_score": 0.8976818545163869,
+      "eval_f1": 0.37518037518037517,
+      "eval_loss": 0.8685262203216553,
+      "eval_precision": 0.3561643835616438,
+      "eval_recall": 0.39634146341463417,
+      "eval_runtime": 1.9309,
+      "eval_samples_per_second": 129.47,
+      "eval_steps_per_second": 16.572,
+      "step": 8200
+    },
+    {
+      "epoch": 152.73,
+      "eval_accuracy_score": 0.896349586997069,
+      "eval_f1": 0.38028169014084506,
+      "eval_loss": 0.816967785358429,
+      "eval_precision": 0.35340314136125656,
+      "eval_recall": 0.4115853658536585,
+      "eval_runtime": 1.9274,
+      "eval_samples_per_second": 129.712,
+      "eval_steps_per_second": 16.603,
+      "step": 8400
+    },
+    {
+      "epoch": 152.73,
+      "step": 8400,
+      "total_flos": 4.389177345306624e+16,
+      "train_loss": 0.05317856186912173,
+      "train_runtime": 6259.9994,
+      "train_samples_per_second": 76.677,
+      "train_steps_per_second": 2.396
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 273,
+  "total_flos": 4.389177345306624e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ac80bd956523b9fd0fc0d93123b23b58685d5a4215709dcaa36086d14d1a7fc1
+size 3259