Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .ipynb_checkpoints/classification_report-checkpoint.json +1 -0
- .ipynb_checkpoints/confusion_matrix-checkpoint.png +0 -0
- .ipynb_checkpoints/metrics_all_fold-checkpoint.json +44 -0
- .ipynb_checkpoints/metrics_mean-checkpoint.json +8 -0
- .ipynb_checkpoints/metrics_visualisation-checkpoint.png +0 -0
- .ipynb_checkpoints/tracker_carbon_statistics-checkpoint.json +33 -0
- checkpoint-64160/config.json +58 -0
- checkpoint-64160/model.safetensors +3 -0
- checkpoint-64160/optimizer.pt +3 -0
- checkpoint-64160/rng_state.pth +3 -0
- checkpoint-64160/scheduler.pt +3 -0
- checkpoint-64160/trainer_state.json +787 -0
- checkpoint-64160/training_args.bin +3 -0
- classification_report.json +1 -0
- config.json +58 -0
- confusion_matrix.png +0 -0
- fold_results.json +67 -0
- metrics.json +1 -0
- metrics_all_fold.json +44 -0
- metrics_ci_bounds.json +26 -0
- metrics_mean.json +8 -0
- metrics_std.json +8 -0
- metrics_visualisation.png +0 -0
- model.safetensors +3 -0
- precision_recall_curve.png +0 -0
- roc_curve.png +0 -0
- tracker_carbon_statistics.json +33 -0
- train_data.csv +3 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
train_data.csv filter=lfs diff=lfs merge=lfs -text
|
.ipynb_checkpoints/classification_report-checkpoint.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"0": {"precision": 0.4512310606060606, "recall": 0.5982423101067169, "f1-score": 0.5144399460188934, "support": 1593}, "1": {"precision": 0.6656821221578243, "recall": 0.7571147873486721, "f1-score": 0.708460603184959, "support": 15777}, "2": {"precision": 0.6269629901735697, "recall": 0.6831782247573301, "f1-score": 0.6538645723589694, "support": 19986}, "3": {"precision": 0.8359839476813318, "recall": 0.8951221453011856, "f1-score": 0.8645429043538408, "support": 12567}, "4": {"precision": 0.6566014083987759, "recall": 0.7752818771494493, "f1-score": 0.7110232762406676, "support": 22971}, "5": {"precision": 0.8995719274529683, "recall": 0.7681442885771543, "f1-score": 0.8286794019215303, "support": 62375}, "6": {"precision": 0.38905382728798243, "recall": 0.6225986366453212, "f1-score": 0.47886876390212907, "support": 4841}, "7": {"precision": 0.66875, "recall": 0.722972972972973, "f1-score": 0.6948051948051949, "support": 148}, "8": {"precision": 0.525647288715193, "recall": 0.6926295461860316, "f1-score": 0.5976947646160256, "support": 3107}, "9": {"precision": 0.5018968133535661, "recall": 0.6988906497622821, "f1-score": 0.5842349304482226, "support": 1893}, "10": {"precision": 0.6903923138510809, "recall": 0.8541006339144216, "f1-score": 0.7635703533162137, "support": 10096}, "11": {"precision": 0.8630000486073981, "recall": 0.7264822619583453, "f1-score": 0.7888785212832135, "support": 48878}, "12": {"precision": 0.5558802045288532, "recall": 0.7013824884792627, "f1-score": 0.6202118989405053, "support": 1085}, "accuracy": 0.75498862734211, "macro avg": {"precision": 0.6408195348318926, "recall": 0.730472371012242, "f1-score": 0.6776365485684898, "support": 205317}, "weighted avg": {"precision": 0.7781716516906106, "recall": 0.75498862734211, "f1-score": 0.7611464074509748, "support": 205317}}
|
.ipynb_checkpoints/confusion_matrix-checkpoint.png
ADDED
|
.ipynb_checkpoints/metrics_all_fold-checkpoint.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"precision": [
|
| 3 |
+
0.5252250330421637,
|
| 4 |
+
0.6477779820843078,
|
| 5 |
+
0.7596557350071358,
|
| 6 |
+
0.8304325107329278,
|
| 7 |
+
0.8751116807965034
|
| 8 |
+
],
|
| 9 |
+
"recall": [
|
| 10 |
+
0.6374854712323833,
|
| 11 |
+
0.7320100191690904,
|
| 12 |
+
0.8487239873980083,
|
| 13 |
+
0.9023304419701069,
|
| 14 |
+
0.9294246408440382
|
| 15 |
+
],
|
| 16 |
+
"f1": [
|
| 17 |
+
0.5625255102511546,
|
| 18 |
+
0.6825079233694151,
|
| 19 |
+
0.7990700594736164,
|
| 20 |
+
0.8633227534621218,
|
| 21 |
+
0.9004263522213029
|
| 22 |
+
],
|
| 23 |
+
"auc": [
|
| 24 |
+
0.9322920483598879,
|
| 25 |
+
0.9640059936967966,
|
| 26 |
+
0.9824767677478932,
|
| 27 |
+
0.9898765599668817,
|
| 28 |
+
0.9935879555305066
|
| 29 |
+
],
|
| 30 |
+
"acc": [
|
| 31 |
+
0.7021595768515181,
|
| 32 |
+
0.7560309180438054,
|
| 33 |
+
0.8075366384663715,
|
| 34 |
+
0.8484587248011611,
|
| 35 |
+
0.8805797863791113
|
| 36 |
+
],
|
| 37 |
+
"mcc": [
|
| 38 |
+
0.6480230217467313,
|
| 39 |
+
0.7090463720401197,
|
| 40 |
+
0.769265197444783,
|
| 41 |
+
0.8177595473228007,
|
| 42 |
+
0.8560559464123465
|
| 43 |
+
]
|
| 44 |
+
}
|
.ipynb_checkpoints/metrics_mean-checkpoint.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"precision": 0.7276405883326078,
|
| 3 |
+
"recall": 0.8099949121227255,
|
| 4 |
+
"f1": 0.7615705197555221,
|
| 5 |
+
"auc": 0.9724478650603933,
|
| 6 |
+
"acc": 0.7989531289083935,
|
| 7 |
+
"mcc": 0.7600300169933563
|
| 8 |
+
}
|
.ipynb_checkpoints/metrics_visualisation-checkpoint.png
ADDED
|
.ipynb_checkpoints/tracker_carbon_statistics-checkpoint.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cloud_provider": "",
|
| 3 |
+
"cloud_region": "",
|
| 4 |
+
"codecarbon_version": "2.3.4",
|
| 5 |
+
"country_iso_code": "NOR",
|
| 6 |
+
"country_name": "Norway",
|
| 7 |
+
"cpu_count": 192,
|
| 8 |
+
"cpu_energy": 1.4828320130124364,
|
| 9 |
+
"cpu_model": "AMD EPYC 7642 48-Core Processor",
|
| 10 |
+
"cpu_power": 2.298767390462452,
|
| 11 |
+
"duration": 122739.22609949112,
|
| 12 |
+
"emissions": 1.1727223142964496,
|
| 13 |
+
"emissions_rate": 9.554584557555e-06,
|
| 14 |
+
"energy_consumed": 42.56705315050633,
|
| 15 |
+
"gpu_count": 4,
|
| 16 |
+
"gpu_energy": 28.207016370595046,
|
| 17 |
+
"gpu_model": "4 x NVIDIA GeForce RTX 3090",
|
| 18 |
+
"gpu_power": 594.0660961943797,
|
| 19 |
+
"latitude": 59.9016,
|
| 20 |
+
"longitude": 10.7343,
|
| 21 |
+
"on_cloud": "N",
|
| 22 |
+
"os": "Linux-4.18.0-513.18.1.el8_9.x86_64-x86_64-with-glibc2.28",
|
| 23 |
+
"project_name": "codecarbon",
|
| 24 |
+
"pue": 1.0,
|
| 25 |
+
"python_version": "3.10.8",
|
| 26 |
+
"ram_energy": 12.877204766898862,
|
| 27 |
+
"ram_power": 377.6938190460205,
|
| 28 |
+
"ram_total_size": 1007.1835174560547,
|
| 29 |
+
"region": "oslo county",
|
| 30 |
+
"run_id": "b1cb25e3-1153-48f7-ac38-ffb33c8612af",
|
| 31 |
+
"timestamp": "2024-04-06T05:49:45",
|
| 32 |
+
"tracking_mode": "machine"
|
| 33 |
+
}
|
checkpoint-64160/config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilroberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2",
|
| 17 |
+
"3": "LABEL_3",
|
| 18 |
+
"4": "LABEL_4",
|
| 19 |
+
"5": "LABEL_5",
|
| 20 |
+
"6": "LABEL_6",
|
| 21 |
+
"7": "LABEL_7",
|
| 22 |
+
"8": "LABEL_8",
|
| 23 |
+
"9": "LABEL_9",
|
| 24 |
+
"10": "LABEL_10",
|
| 25 |
+
"11": "LABEL_11",
|
| 26 |
+
"12": "LABEL_12"
|
| 27 |
+
},
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"intermediate_size": 3072,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"LABEL_0": 0,
|
| 32 |
+
"LABEL_1": 1,
|
| 33 |
+
"LABEL_10": 10,
|
| 34 |
+
"LABEL_11": 11,
|
| 35 |
+
"LABEL_12": 12,
|
| 36 |
+
"LABEL_2": 2,
|
| 37 |
+
"LABEL_3": 3,
|
| 38 |
+
"LABEL_4": 4,
|
| 39 |
+
"LABEL_5": 5,
|
| 40 |
+
"LABEL_6": 6,
|
| 41 |
+
"LABEL_7": 7,
|
| 42 |
+
"LABEL_8": 8,
|
| 43 |
+
"LABEL_9": 9
|
| 44 |
+
},
|
| 45 |
+
"layer_norm_eps": 1e-05,
|
| 46 |
+
"max_position_embeddings": 514,
|
| 47 |
+
"model_type": "roberta",
|
| 48 |
+
"num_attention_heads": 12,
|
| 49 |
+
"num_hidden_layers": 6,
|
| 50 |
+
"pad_token_id": 1,
|
| 51 |
+
"position_embedding_type": "absolute",
|
| 52 |
+
"problem_type": "single_label_classification",
|
| 53 |
+
"torch_dtype": "float32",
|
| 54 |
+
"transformers_version": "4.35.0",
|
| 55 |
+
"type_vocab_size": 1,
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"vocab_size": 50265
|
| 58 |
+
}
|
checkpoint-64160/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de7eb800b51ce22ced147cd56654217ad3ceaabf5f2d0979e852674cf0192e68
|
| 3 |
+
size 328526116
|
checkpoint-64160/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82e99b5121649c74af8ad5b2a1676da8094466a37284e8e46b33208f0e2f4fcc
|
| 3 |
+
size 657115194
|
checkpoint-64160/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32adb66e7042d9c56b2a7c1908dd0433eb478d0eb754841d816ad25f3c05bcfa
|
| 3 |
+
size 14244
|
checkpoint-64160/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:460b75ad97acd79d1005f8a377abd3bd678ddb6636ae52b8f85e00e1d6f6661d
|
| 3 |
+
size 1064
|
checkpoint-64160/trainer_state.json
ADDED
|
@@ -0,0 +1,787 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.999805182154685,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 64160,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 4.96e-05,
|
| 14 |
+
"loss": 0.3014,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.08,
|
| 19 |
+
"learning_rate": 4.999251109780014e-05,
|
| 20 |
+
"loss": 0.3397,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.12,
|
| 25 |
+
"learning_rate": 4.996980689833625e-05,
|
| 26 |
+
"loss": 0.3699,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.16,
|
| 31 |
+
"learning_rate": 4.993190073716137e-05,
|
| 32 |
+
"loss": 0.3544,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.19,
|
| 37 |
+
"learning_rate": 4.98789369907394e-05,
|
| 38 |
+
"loss": 0.3785,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.23,
|
| 43 |
+
"learning_rate": 4.98107356353746e-05,
|
| 44 |
+
"loss": 0.3816,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.27,
|
| 49 |
+
"learning_rate": 4.9727429163070526e-05,
|
| 50 |
+
"loss": 0.3734,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.31,
|
| 55 |
+
"learning_rate": 4.962927999970498e-05,
|
| 56 |
+
"loss": 0.4056,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.35,
|
| 61 |
+
"learning_rate": 4.9515954536416864e-05,
|
| 62 |
+
"loss": 0.3899,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.39,
|
| 67 |
+
"learning_rate": 4.9387703422975006e-05,
|
| 68 |
+
"loss": 0.3983,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.43,
|
| 73 |
+
"learning_rate": 4.924460474042041e-05,
|
| 74 |
+
"loss": 0.4079,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.47,
|
| 79 |
+
"learning_rate": 4.908674560919825e-05,
|
| 80 |
+
"loss": 0.3911,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.51,
|
| 85 |
+
"learning_rate": 4.891422213611778e-05,
|
| 86 |
+
"loss": 0.3979,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.55,
|
| 91 |
+
"learning_rate": 4.872713935584118e-05,
|
| 92 |
+
"loss": 0.4231,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.58,
|
| 97 |
+
"learning_rate": 4.8525611166936965e-05,
|
| 98 |
+
"loss": 0.4019,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.62,
|
| 103 |
+
"learning_rate": 4.831020617251396e-05,
|
| 104 |
+
"loss": 0.4206,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.66,
|
| 109 |
+
"learning_rate": 4.808019221131471e-05,
|
| 110 |
+
"loss": 0.4191,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.7,
|
| 115 |
+
"learning_rate": 4.783612671180332e-05,
|
| 116 |
+
"loss": 0.4093,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.74,
|
| 121 |
+
"learning_rate": 4.757815826441118e-05,
|
| 122 |
+
"loss": 0.4161,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.78,
|
| 127 |
+
"learning_rate": 4.7306443923875474e-05,
|
| 128 |
+
"loss": 0.4266,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.82,
|
| 133 |
+
"learning_rate": 4.70211491136221e-05,
|
| 134 |
+
"loss": 0.4193,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.86,
|
| 139 |
+
"learning_rate": 4.67224475250536e-05,
|
| 140 |
+
"loss": 0.4472,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.9,
|
| 145 |
+
"learning_rate": 4.641115793841016e-05,
|
| 146 |
+
"loss": 0.4171,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.94,
|
| 151 |
+
"learning_rate": 4.6086222280847177e-05,
|
| 152 |
+
"loss": 0.416,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.97,
|
| 157 |
+
"learning_rate": 4.574844904127774e-05,
|
| 158 |
+
"loss": 0.4367,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.01,
|
| 163 |
+
"learning_rate": 4.539804386069362e-05,
|
| 164 |
+
"loss": 0.3863,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.05,
|
| 169 |
+
"learning_rate": 4.503522007058594e-05,
|
| 170 |
+
"loss": 0.3266,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.09,
|
| 175 |
+
"learning_rate": 4.466172264679194e-05,
|
| 176 |
+
"loss": 0.323,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.13,
|
| 181 |
+
"learning_rate": 4.427477915319075e-05,
|
| 182 |
+
"loss": 0.3384,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.17,
|
| 187 |
+
"learning_rate": 4.38769098166774e-05,
|
| 188 |
+
"loss": 0.3314,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.21,
|
| 193 |
+
"learning_rate": 4.3466762279965556e-05,
|
| 194 |
+
"loss": 0.3227,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.25,
|
| 199 |
+
"learning_rate": 4.304537192450671e-05,
|
| 200 |
+
"loss": 0.3275,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.29,
|
| 205 |
+
"learning_rate": 4.261299529854229e-05,
|
| 206 |
+
"loss": 0.3421,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.32,
|
| 211 |
+
"learning_rate": 4.216989563890628e-05,
|
| 212 |
+
"loss": 0.3472,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.36,
|
| 217 |
+
"learning_rate": 4.1716342710762945e-05,
|
| 218 |
+
"loss": 0.3334,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.4,
|
| 223 |
+
"learning_rate": 4.125261264337015e-05,
|
| 224 |
+
"loss": 0.3344,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.44,
|
| 229 |
+
"learning_rate": 4.077898776196802e-05,
|
| 230 |
+
"loss": 0.3467,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.48,
|
| 235 |
+
"learning_rate": 4.029575641589549e-05,
|
| 236 |
+
"loss": 0.3322,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.52,
|
| 241 |
+
"learning_rate": 3.980321280303926e-05,
|
| 242 |
+
"loss": 0.3285,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.56,
|
| 247 |
+
"learning_rate": 3.9301656790722044e-05,
|
| 248 |
+
"loss": 0.3358,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.6,
|
| 253 |
+
"learning_rate": 3.879139373313927e-05,
|
| 254 |
+
"loss": 0.3312,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.64,
|
| 259 |
+
"learning_rate": 3.827377977489969e-05,
|
| 260 |
+
"loss": 0.3393,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.68,
|
| 265 |
+
"learning_rate": 3.774705554692486e-05,
|
| 266 |
+
"loss": 0.3407,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.71,
|
| 271 |
+
"learning_rate": 3.72125707362935e-05,
|
| 272 |
+
"loss": 0.3316,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.75,
|
| 277 |
+
"learning_rate": 3.667065074470612e-05,
|
| 278 |
+
"loss": 0.345,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.79,
|
| 283 |
+
"learning_rate": 3.6121625500503635e-05,
|
| 284 |
+
"loss": 0.3422,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.83,
|
| 289 |
+
"learning_rate": 3.556582925780241e-05,
|
| 290 |
+
"loss": 0.3361,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.87,
|
| 295 |
+
"learning_rate": 3.50047310436026e-05,
|
| 296 |
+
"loss": 0.3393,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.91,
|
| 301 |
+
"learning_rate": 3.443642368590404e-05,
|
| 302 |
+
"loss": 0.3396,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.95,
|
| 307 |
+
"learning_rate": 3.386237130373871e-05,
|
| 308 |
+
"loss": 0.3327,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.99,
|
| 313 |
+
"learning_rate": 3.328292338808862e-05,
|
| 314 |
+
"loss": 0.333,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.03,
|
| 319 |
+
"learning_rate": 3.269960649279959e-05,
|
| 320 |
+
"loss": 0.2806,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.07,
|
| 325 |
+
"learning_rate": 3.211043792460732e-05,
|
| 326 |
+
"loss": 0.2749,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.1,
|
| 331 |
+
"learning_rate": 3.151694042405613e-05,
|
| 332 |
+
"loss": 0.2526,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.14,
|
| 337 |
+
"learning_rate": 3.091947532058344e-05,
|
| 338 |
+
"loss": 0.2685,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.18,
|
| 343 |
+
"learning_rate": 3.0318406359157847e-05,
|
| 344 |
+
"loss": 0.2529,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.22,
|
| 349 |
+
"learning_rate": 2.9714099478826263e-05,
|
| 350 |
+
"loss": 0.278,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.26,
|
| 355 |
+
"learning_rate": 2.91069225899251e-05,
|
| 356 |
+
"loss": 0.2521,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.3,
|
| 361 |
+
"learning_rate": 2.8497245350091455e-05,
|
| 362 |
+
"loss": 0.2578,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.34,
|
| 367 |
+
"learning_rate": 2.7887889912889743e-05,
|
| 368 |
+
"loss": 0.2553,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.38,
|
| 373 |
+
"learning_rate": 2.727433309042916e-05,
|
| 374 |
+
"loss": 0.271,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.42,
|
| 379 |
+
"learning_rate": 2.6659391622716833e-05,
|
| 380 |
+
"loss": 0.2703,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.45,
|
| 385 |
+
"learning_rate": 2.6043439894572192e-05,
|
| 386 |
+
"loss": 0.2617,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.49,
|
| 391 |
+
"learning_rate": 2.5426852905875094e-05,
|
| 392 |
+
"loss": 0.2665,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.53,
|
| 397 |
+
"learning_rate": 2.481000604326075e-05,
|
| 398 |
+
"loss": 0.2657,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.57,
|
| 403 |
+
"learning_rate": 2.4193274851579207e-05,
|
| 404 |
+
"loss": 0.2523,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.61,
|
| 409 |
+
"learning_rate": 2.3577034805258435e-05,
|
| 410 |
+
"loss": 0.2588,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.65,
|
| 415 |
+
"learning_rate": 2.2962890713446218e-05,
|
| 416 |
+
"loss": 0.2693,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.69,
|
| 421 |
+
"learning_rate": 2.2348755101282832e-05,
|
| 422 |
+
"loss": 0.2661,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.73,
|
| 427 |
+
"learning_rate": 2.1736233603461655e-05,
|
| 428 |
+
"loss": 0.2701,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.77,
|
| 433 |
+
"learning_rate": 2.1125699131491166e-05,
|
| 434 |
+
"loss": 0.2441,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.81,
|
| 439 |
+
"learning_rate": 2.0517523387151202e-05,
|
| 440 |
+
"loss": 0.2726,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.84,
|
| 445 |
+
"learning_rate": 1.991207663619578e-05,
|
| 446 |
+
"loss": 0.2617,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.88,
|
| 451 |
+
"learning_rate": 1.9309727482930234e-05,
|
| 452 |
+
"loss": 0.2616,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.92,
|
| 457 |
+
"learning_rate": 1.871084264579985e-05,
|
| 458 |
+
"loss": 0.2477,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.96,
|
| 463 |
+
"learning_rate": 1.811697278347739e-05,
|
| 464 |
+
"loss": 0.2621,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.0,
|
| 469 |
+
"learning_rate": 1.752727665843023e-05,
|
| 470 |
+
"loss": 0.2715,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.04,
|
| 475 |
+
"learning_rate": 1.694094396397076e-05,
|
| 476 |
+
"loss": 0.1769,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.08,
|
| 481 |
+
"learning_rate": 1.6359517733617524e-05,
|
| 482 |
+
"loss": 0.1901,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.12,
|
| 487 |
+
"learning_rate": 1.5783351947652697e-05,
|
| 488 |
+
"loss": 0.1882,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.16,
|
| 493 |
+
"learning_rate": 1.5212797383727583e-05,
|
| 494 |
+
"loss": 0.1892,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 3.2,
|
| 499 |
+
"learning_rate": 1.464820140330438e-05,
|
| 500 |
+
"loss": 0.1975,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 3.23,
|
| 505 |
+
"learning_rate": 1.4089907740177721e-05,
|
| 506 |
+
"loss": 0.1962,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.27,
|
| 511 |
+
"learning_rate": 1.3538256291204832e-05,
|
| 512 |
+
"loss": 0.203,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 3.31,
|
| 517 |
+
"learning_rate": 1.299358290937165e-05,
|
| 518 |
+
"loss": 0.1915,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.35,
|
| 523 |
+
"learning_rate": 1.2457286413478578e-05,
|
| 524 |
+
"loss": 0.1956,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 3.39,
|
| 529 |
+
"learning_rate": 1.1928595581428234e-05,
|
| 530 |
+
"loss": 0.1994,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 3.43,
|
| 535 |
+
"learning_rate": 1.1406795555382551e-05,
|
| 536 |
+
"loss": 0.1952,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 3.47,
|
| 541 |
+
"learning_rate": 1.0893271259074697e-05,
|
| 542 |
+
"loss": 0.1925,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 3.51,
|
| 547 |
+
"learning_rate": 1.0388335333155925e-05,
|
| 548 |
+
"loss": 0.204,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.55,
|
| 553 |
+
"learning_rate": 9.893278190208626e-06,
|
| 554 |
+
"loss": 0.2031,
|
| 555 |
+
"step": 45500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.58,
|
| 559 |
+
"learning_rate": 9.406417131736153e-06,
|
| 560 |
+
"loss": 0.2004,
|
| 561 |
+
"step": 46000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.62,
|
| 565 |
+
"learning_rate": 8.929049660885956e-06,
|
| 566 |
+
"loss": 0.2028,
|
| 567 |
+
"step": 46500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 3.66,
|
| 571 |
+
"learning_rate": 8.46146640553685e-06,
|
| 572 |
+
"loss": 0.2008,
|
| 573 |
+
"step": 47000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.7,
|
| 577 |
+
"learning_rate": 8.003952036802789e-06,
|
| 578 |
+
"loss": 0.207,
|
| 579 |
+
"step": 47500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 3.74,
|
| 583 |
+
"learning_rate": 7.556785095721122e-06,
|
| 584 |
+
"loss": 0.2074,
|
| 585 |
+
"step": 48000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 3.78,
|
| 589 |
+
"learning_rate": 7.120237823672967e-06,
|
| 590 |
+
"loss": 0.1985,
|
| 591 |
+
"step": 48500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 3.82,
|
| 595 |
+
"learning_rate": 6.694575996638971e-06,
|
| 596 |
+
"loss": 0.204,
|
| 597 |
+
"step": 49000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.86,
|
| 601 |
+
"learning_rate": 6.280058763391209e-06,
|
| 602 |
+
"loss": 0.2105,
|
| 603 |
+
"step": 49500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 3.9,
|
| 607 |
+
"learning_rate": 5.876938487719819e-06,
|
| 608 |
+
"loss": 0.2021,
|
| 609 |
+
"step": 50000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 3.94,
|
| 613 |
+
"learning_rate": 5.485460594790515e-06,
|
| 614 |
+
"loss": 0.2113,
|
| 615 |
+
"step": 50500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 3.97,
|
| 619 |
+
"learning_rate": 5.105863421726345e-06,
|
| 620 |
+
"loss": 0.2028,
|
| 621 |
+
"step": 51000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 4.01,
|
| 625 |
+
"learning_rate": 4.739100805655252e-06,
|
| 626 |
+
"loss": 0.2007,
|
| 627 |
+
"step": 51500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 4.05,
|
| 631 |
+
"learning_rate": 4.383926120987686e-06,
|
| 632 |
+
"loss": 0.1636,
|
| 633 |
+
"step": 52000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 4.09,
|
| 637 |
+
"learning_rate": 4.041975366009893e-06,
|
| 638 |
+
"loss": 0.1694,
|
| 639 |
+
"step": 52500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 4.13,
|
| 643 |
+
"learning_rate": 3.7120862506114603e-06,
|
| 644 |
+
"loss": 0.163,
|
| 645 |
+
"step": 53000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 4.17,
|
| 649 |
+
"learning_rate": 3.3951575097582733e-06,
|
| 650 |
+
"loss": 0.166,
|
| 651 |
+
"step": 53500
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 4.21,
|
| 655 |
+
"learning_rate": 3.0913820940247336e-06,
|
| 656 |
+
"loss": 0.1608,
|
| 657 |
+
"step": 54000
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 4.25,
|
| 661 |
+
"learning_rate": 2.801512389873778e-06,
|
| 662 |
+
"loss": 0.1708,
|
| 663 |
+
"step": 54500
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 4.29,
|
| 667 |
+
"learning_rate": 2.5245631306097445e-06,
|
| 668 |
+
"loss": 0.1737,
|
| 669 |
+
"step": 55000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 4.32,
|
| 673 |
+
"learning_rate": 2.261297226291828e-06,
|
| 674 |
+
"loss": 0.1768,
|
| 675 |
+
"step": 55500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 4.36,
|
| 679 |
+
"learning_rate": 2.011874956821819e-06,
|
| 680 |
+
"loss": 0.1749,
|
| 681 |
+
"step": 56000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 4.4,
|
| 685 |
+
"learning_rate": 1.776448173906295e-06,
|
| 686 |
+
"loss": 0.1807,
|
| 687 |
+
"step": 56500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 4.44,
|
| 691 |
+
"learning_rate": 1.5555885830100786e-06,
|
| 692 |
+
"loss": 0.1736,
|
| 693 |
+
"step": 57000
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 4.48,
|
| 697 |
+
"learning_rate": 1.3485454827103923e-06,
|
| 698 |
+
"loss": 0.1841,
|
| 699 |
+
"step": 57500
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 4.52,
|
| 703 |
+
"learning_rate": 1.1559017130681137e-06,
|
| 704 |
+
"loss": 0.1662,
|
| 705 |
+
"step": 58000
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 4.56,
|
| 709 |
+
"learning_rate": 9.777745582585678e-07,
|
| 710 |
+
"loss": 0.1726,
|
| 711 |
+
"step": 58500
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 4.6,
|
| 715 |
+
"learning_rate": 8.14584805267532e-07,
|
| 716 |
+
"loss": 0.1717,
|
| 717 |
+
"step": 59000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 4.64,
|
| 721 |
+
"learning_rate": 6.657777723659553e-07,
|
| 722 |
+
"loss": 0.183,
|
| 723 |
+
"step": 59500
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 4.68,
|
| 727 |
+
"learning_rate": 5.317857484901683e-07,
|
| 728 |
+
"loss": 0.1848,
|
| 729 |
+
"step": 60000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 4.71,
|
| 733 |
+
"learning_rate": 4.1269030982635516e-07,
|
| 734 |
+
"loss": 0.1813,
|
| 735 |
+
"step": 60500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 4.75,
|
| 739 |
+
"learning_rate": 3.087572331968075e-07,
|
| 740 |
+
"loss": 0.1819,
|
| 741 |
+
"step": 61000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 4.79,
|
| 745 |
+
"learning_rate": 2.196332502277909e-07,
|
| 746 |
+
"loss": 0.1699,
|
| 747 |
+
"step": 61500
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 4.83,
|
| 751 |
+
"learning_rate": 1.4559589520299345e-07,
|
| 752 |
+
"loss": 0.185,
|
| 753 |
+
"step": 62000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 4.87,
|
| 757 |
+
"learning_rate": 8.669024308197716e-08,
|
| 758 |
+
"loss": 0.181,
|
| 759 |
+
"step": 62500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 4.91,
|
| 763 |
+
"learning_rate": 4.295215643555506e-08,
|
| 764 |
+
"loss": 0.1802,
|
| 765 |
+
"step": 63000
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 4.95,
|
| 769 |
+
"learning_rate": 1.4408263612167294e-08,
|
| 770 |
+
"loss": 0.1851,
|
| 771 |
+
"step": 63500
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 4.99,
|
| 775 |
+
"learning_rate": 1.0759425261658295e-09,
|
| 776 |
+
"loss": 0.174,
|
| 777 |
+
"step": 64000
|
| 778 |
+
}
|
| 779 |
+
],
|
| 780 |
+
"logging_steps": 500,
|
| 781 |
+
"max_steps": 64160,
|
| 782 |
+
"num_train_epochs": 5,
|
| 783 |
+
"save_steps": 500,
|
| 784 |
+
"total_flos": 5.44043806298026e+17,
|
| 785 |
+
"trial_name": null,
|
| 786 |
+
"trial_params": null
|
| 787 |
+
}
|
checkpoint-64160/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52bad78042ec9fbd7d6a45140e9e090b2c240f753885d6e0f1d68c4a58448480
|
| 3 |
+
size 4664
|
classification_report.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"0": {"precision": 0.8635346756152126, "recall": 0.9698492462311558, "f1-score": 0.9136094674556213, "support": 1592}, "1": {"precision": 0.8138346206269877, "recall": 0.9082842111935095, "f1-score": 0.8584693724726673, "support": 15777}, "2": {"precision": 0.7866246402631218, "recall": 0.8616031221855299, "f1-score": 0.8224084819829501, "support": 19986}, "3": {"precision": 0.9443112383014928, "recall": 0.9715126919710353, "f1-score": 0.9577188578600565, "support": 12567}, "4": {"precision": 0.7922296650717703, "recall": 0.9010448410970832, "f1-score": 0.8431408493736633, "support": 22970}, "5": {"precision": 0.9380160197165742, "recall": 0.85425250501002, "f1-score": 0.8941768753146502, "support": 62375}, "6": {"precision": 0.8526474467684191, "recall": 0.934724230530882, "f1-score": 0.8918013401655499, "support": 4841}, "7": {"precision": 0.9171974522292994, "recall": 0.9664429530201343, "f1-score": 0.9411764705882353, "support": 149}, "8": {"precision": 0.8802220274612913, "recall": 0.9700579523502898, "f1-score": 0.9229591055291775, "support": 3106}, "9": {"precision": 0.8821002386634845, "recall": 0.9762282091917591, "f1-score": 0.9267803410230692, "support": 1893}, "10": {"precision": 0.8882072880424831, "recall": 0.9607804298306427, "f1-score": 0.9230696036918978, "support": 10097}, "11": {"precision": 0.9141615677928527, "recall": 0.8436515405703998, "f1-score": 0.8774923924839869, "support": 48878}, "12": {"precision": 0.903364969801553, "recall": 0.9640883977900553, "f1-score": 0.932739420935412, "support": 1086}, "accuracy": 0.8805797863791113, "macro avg": {"precision": 0.8751116807965034, "recall": 0.9294246408440382, "f1-score": 0.9004263522213029, "support": 205317}, "weighted avg": {"precision": 0.8855053725516457, "recall": 0.8805797863791113, "f1-score": 0.8811442208186763, "support": 205317}}
|
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilroberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2",
|
| 17 |
+
"3": "LABEL_3",
|
| 18 |
+
"4": "LABEL_4",
|
| 19 |
+
"5": "LABEL_5",
|
| 20 |
+
"6": "LABEL_6",
|
| 21 |
+
"7": "LABEL_7",
|
| 22 |
+
"8": "LABEL_8",
|
| 23 |
+
"9": "LABEL_9",
|
| 24 |
+
"10": "LABEL_10",
|
| 25 |
+
"11": "LABEL_11",
|
| 26 |
+
"12": "LABEL_12"
|
| 27 |
+
},
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"intermediate_size": 3072,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"LABEL_0": 0,
|
| 32 |
+
"LABEL_1": 1,
|
| 33 |
+
"LABEL_10": 10,
|
| 34 |
+
"LABEL_11": 11,
|
| 35 |
+
"LABEL_12": 12,
|
| 36 |
+
"LABEL_2": 2,
|
| 37 |
+
"LABEL_3": 3,
|
| 38 |
+
"LABEL_4": 4,
|
| 39 |
+
"LABEL_5": 5,
|
| 40 |
+
"LABEL_6": 6,
|
| 41 |
+
"LABEL_7": 7,
|
| 42 |
+
"LABEL_8": 8,
|
| 43 |
+
"LABEL_9": 9
|
| 44 |
+
},
|
| 45 |
+
"layer_norm_eps": 1e-05,
|
| 46 |
+
"max_position_embeddings": 514,
|
| 47 |
+
"model_type": "roberta",
|
| 48 |
+
"num_attention_heads": 12,
|
| 49 |
+
"num_hidden_layers": 6,
|
| 50 |
+
"pad_token_id": 1,
|
| 51 |
+
"position_embedding_type": "absolute",
|
| 52 |
+
"problem_type": "single_label_classification",
|
| 53 |
+
"torch_dtype": "float32",
|
| 54 |
+
"transformers_version": "4.35.0",
|
| 55 |
+
"type_vocab_size": 1,
|
| 56 |
+
"use_cache": true,
|
| 57 |
+
"vocab_size": 50265
|
| 58 |
+
}
|
confusion_matrix.png
ADDED
|
fold_results.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"0": {
|
| 3 |
+
"eval_loss": 1.354443907737732,
|
| 4 |
+
"eval_precision": 0.5252250330421637,
|
| 5 |
+
"eval_recall": 0.6374854712323833,
|
| 6 |
+
"eval_acc": 0.7021595768515181,
|
| 7 |
+
"eval_mcc": 0.6480230217467313,
|
| 8 |
+
"eval_f1": 0.5625255102511546,
|
| 9 |
+
"eval_auc": 0.9322920483598879,
|
| 10 |
+
"eval_runtime": 374.7957,
|
| 11 |
+
"eval_samples_per_second": 547.813,
|
| 12 |
+
"eval_steps_per_second": 8.562,
|
| 13 |
+
"epoch": 5.0
|
| 14 |
+
},
|
| 15 |
+
"1": {
|
| 16 |
+
"eval_loss": 1.029205560684204,
|
| 17 |
+
"eval_precision": 0.6477779820843078,
|
| 18 |
+
"eval_recall": 0.7320100191690904,
|
| 19 |
+
"eval_acc": 0.7560309180438054,
|
| 20 |
+
"eval_mcc": 0.7090463720401197,
|
| 21 |
+
"eval_f1": 0.6825079233694151,
|
| 22 |
+
"eval_auc": 0.9640059936967966,
|
| 23 |
+
"eval_runtime": 381.5252,
|
| 24 |
+
"eval_samples_per_second": 538.148,
|
| 25 |
+
"eval_steps_per_second": 8.411,
|
| 26 |
+
"epoch": 5.0
|
| 27 |
+
},
|
| 28 |
+
"2": {
|
| 29 |
+
"eval_loss": 0.566839337348938,
|
| 30 |
+
"eval_precision": 0.7596557350071358,
|
| 31 |
+
"eval_recall": 0.8487239873980083,
|
| 32 |
+
"eval_acc": 0.8075366384663715,
|
| 33 |
+
"eval_mcc": 0.769265197444783,
|
| 34 |
+
"eval_f1": 0.7990700594736164,
|
| 35 |
+
"eval_auc": 0.9824767677478932,
|
| 36 |
+
"eval_runtime": 404.0601,
|
| 37 |
+
"eval_samples_per_second": 508.135,
|
| 38 |
+
"eval_steps_per_second": 7.942,
|
| 39 |
+
"epoch": 5.0
|
| 40 |
+
},
|
| 41 |
+
"3": {
|
| 42 |
+
"eval_loss": 0.3486688733100891,
|
| 43 |
+
"eval_precision": 0.8304325107329278,
|
| 44 |
+
"eval_recall": 0.9023304419701069,
|
| 45 |
+
"eval_acc": 0.8484587248011611,
|
| 46 |
+
"eval_mcc": 0.8177595473228007,
|
| 47 |
+
"eval_f1": 0.8633227534621218,
|
| 48 |
+
"eval_auc": 0.9898765599668817,
|
| 49 |
+
"eval_runtime": 415.4218,
|
| 50 |
+
"eval_samples_per_second": 494.237,
|
| 51 |
+
"eval_steps_per_second": 7.725,
|
| 52 |
+
"epoch": 5.0
|
| 53 |
+
},
|
| 54 |
+
"4": {
|
| 55 |
+
"eval_loss": 0.24775099754333496,
|
| 56 |
+
"eval_precision": 0.8751116807965034,
|
| 57 |
+
"eval_recall": 0.9294246408440382,
|
| 58 |
+
"eval_acc": 0.8805797863791113,
|
| 59 |
+
"eval_mcc": 0.8560559464123465,
|
| 60 |
+
"eval_f1": 0.9004263522213029,
|
| 61 |
+
"eval_auc": 0.9935879555305066,
|
| 62 |
+
"eval_runtime": 425.1886,
|
| 63 |
+
"eval_samples_per_second": 482.885,
|
| 64 |
+
"eval_steps_per_second": 7.547,
|
| 65 |
+
"epoch": 5.0
|
| 66 |
+
}
|
| 67 |
+
}
|
metrics.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"precision": 0.8751116807965034, "recall": 0.9294246408440382, "acc": 0.8805797863791113, "mcc": 0.8560559464123465, "f1": 0.9004263522213029, "auc": 0.9935879555305066}
|
metrics_all_fold.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"precision": [
|
| 3 |
+
0.5252250330421637,
|
| 4 |
+
0.6477779820843078,
|
| 5 |
+
0.7596557350071358,
|
| 6 |
+
0.8304325107329278,
|
| 7 |
+
0.8751116807965034
|
| 8 |
+
],
|
| 9 |
+
"recall": [
|
| 10 |
+
0.6374854712323833,
|
| 11 |
+
0.7320100191690904,
|
| 12 |
+
0.8487239873980083,
|
| 13 |
+
0.9023304419701069,
|
| 14 |
+
0.9294246408440382
|
| 15 |
+
],
|
| 16 |
+
"f1": [
|
| 17 |
+
0.5625255102511546,
|
| 18 |
+
0.6825079233694151,
|
| 19 |
+
0.7990700594736164,
|
| 20 |
+
0.8633227534621218,
|
| 21 |
+
0.9004263522213029
|
| 22 |
+
],
|
| 23 |
+
"auc": [
|
| 24 |
+
0.9322920483598879,
|
| 25 |
+
0.9640059936967966,
|
| 26 |
+
0.9824767677478932,
|
| 27 |
+
0.9898765599668817,
|
| 28 |
+
0.9935879555305066
|
| 29 |
+
],
|
| 30 |
+
"acc": [
|
| 31 |
+
0.7021595768515181,
|
| 32 |
+
0.7560309180438054,
|
| 33 |
+
0.8075366384663715,
|
| 34 |
+
0.8484587248011611,
|
| 35 |
+
0.8805797863791113
|
| 36 |
+
],
|
| 37 |
+
"mcc": [
|
| 38 |
+
0.6480230217467313,
|
| 39 |
+
0.7090463720401197,
|
| 40 |
+
0.769265197444783,
|
| 41 |
+
0.8177595473228007,
|
| 42 |
+
0.8560559464123465
|
| 43 |
+
]
|
| 44 |
+
}
|
metrics_ci_bounds.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"precision": {
|
| 3 |
+
"ci_lower": 0.5512882731246695,
|
| 4 |
+
"ci_upper": 0.9039929035405461
|
| 5 |
+
},
|
| 6 |
+
"recall": {
|
| 7 |
+
"ci_lower": 0.6577575859351843,
|
| 8 |
+
"ci_upper": 0.9622322383102666
|
| 9 |
+
},
|
| 10 |
+
"f1": {
|
| 11 |
+
"ci_lower": 0.5893967979379091,
|
| 12 |
+
"ci_upper": 0.9337442415731352
|
| 13 |
+
},
|
| 14 |
+
"auc": {
|
| 15 |
+
"ci_lower": 0.9411897505573044,
|
| 16 |
+
"ci_upper": 1.0037059795634822
|
| 17 |
+
},
|
| 18 |
+
"acc": {
|
| 19 |
+
"ci_lower": 0.7102834090359146,
|
| 20 |
+
"ci_upper": 0.8876228487808725
|
| 21 |
+
},
|
| 22 |
+
"mcc": {
|
| 23 |
+
"ci_lower": 0.6565466796150523,
|
| 24 |
+
"ci_upper": 0.8635133543716602
|
| 25 |
+
}
|
| 26 |
+
}
|
metrics_mean.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"precision": 0.7276405883326078,
|
| 3 |
+
"recall": 0.8099949121227255,
|
| 4 |
+
"f1": 0.7615705197555221,
|
| 5 |
+
"auc": 0.9724478650603933,
|
| 6 |
+
"acc": 0.7989531289083935,
|
| 7 |
+
"mcc": 0.7600300169933563
|
| 8 |
+
}
|
metrics_std.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"precision": 0.14202901546880273,
|
| 3 |
+
"recall": 0.12260750606264888,
|
| 4 |
+
"f1": 0.13866369812339366,
|
| 5 |
+
"auc": 0.025174374507361034,
|
| 6 |
+
"acc": 0.07141200840223409,
|
| 7 |
+
"mcc": 0.0833424642479821
|
| 8 |
+
}
|
metrics_visualisation.png
ADDED
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de7eb800b51ce22ced147cd56654217ad3ceaabf5f2d0979e852674cf0192e68
|
| 3 |
+
size 328526116
|
precision_recall_curve.png
ADDED
|
roc_curve.png
ADDED
|
tracker_carbon_statistics.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cloud_provider": "",
|
| 3 |
+
"cloud_region": "",
|
| 4 |
+
"codecarbon_version": "2.3.4",
|
| 5 |
+
"country_iso_code": "NOR",
|
| 6 |
+
"country_name": "Norway",
|
| 7 |
+
"cpu_count": 192,
|
| 8 |
+
"cpu_energy": 1.4828320130124364,
|
| 9 |
+
"cpu_model": "AMD EPYC 7642 48-Core Processor",
|
| 10 |
+
"cpu_power": 2.298767390462452,
|
| 11 |
+
"duration": 122739.22609949112,
|
| 12 |
+
"emissions": 1.1727223142964496,
|
| 13 |
+
"emissions_rate": 9.554584557555e-06,
|
| 14 |
+
"energy_consumed": 42.56705315050633,
|
| 15 |
+
"gpu_count": 4,
|
| 16 |
+
"gpu_energy": 28.207016370595046,
|
| 17 |
+
"gpu_model": "4 x NVIDIA GeForce RTX 3090",
|
| 18 |
+
"gpu_power": 594.0660961943797,
|
| 19 |
+
"latitude": 59.9016,
|
| 20 |
+
"longitude": 10.7343,
|
| 21 |
+
"on_cloud": "N",
|
| 22 |
+
"os": "Linux-4.18.0-513.18.1.el8_9.x86_64-x86_64-with-glibc2.28",
|
| 23 |
+
"project_name": "codecarbon",
|
| 24 |
+
"pue": 1.0,
|
| 25 |
+
"python_version": "3.10.8",
|
| 26 |
+
"ram_energy": 12.877204766898862,
|
| 27 |
+
"ram_power": 377.6938190460205,
|
| 28 |
+
"ram_total_size": 1007.1835174560547,
|
| 29 |
+
"region": "oslo county",
|
| 30 |
+
"run_id": "b1cb25e3-1153-48f7-ac38-ffb33c8612af",
|
| 31 |
+
"timestamp": "2024-04-06T05:49:45",
|
| 32 |
+
"tracking_mode": "machine"
|
| 33 |
+
}
|
train_data.csv
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a5a688ba507070666f174ff50c04e1264393fd1cad5d4300d9e6a52013c24b4
|
| 3 |
+
size 3932518235
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52bad78042ec9fbd7d6a45140e9e090b2c240f753885d6e0f1d68c4a58448480
|
| 3 |
+
size 4664
|