Upload folder using huggingface_hub
Browse files- checkpoint-best/config.json +30 -0
- checkpoint-best/model.safetensors +3 -0
- checkpoint-best/optimizer.pt +3 -0
- checkpoint-best/scheduler.pt +3 -0
- checkpoint-best/training_0.bin +3 -0
- checkpoint-best/training_1.bin +3 -0
- checkpoint-best/training_3.bin +3 -0
- checkpoint-best/training_4.bin +3 -0
- checkpoint-best/training_5.bin +3 -0
- checkpoint-best/training_6.bin +3 -0
- checkpoint-best/training_7.bin +3 -0
- checkpoint-last/config.json +30 -0
- checkpoint-last/idx_file.txt +1 -0
- checkpoint-last/model.safetensors +3 -0
- checkpoint-last/optimizer.pt +3 -0
- checkpoint-last/scheduler.pt +3 -0
- checkpoint-last/step_file.txt +1 -0
- config.json +30 -0
- eval_results.txt +248 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.json +0 -0
checkpoint-best/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/codebert-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 |
+
"finetuning_task": "codesearch",
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.49.0",
|
| 27 |
+
"type_vocab_size": 1,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 50265
|
| 30 |
+
}
|
checkpoint-best/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a1ab682ea4295024157ddc9e0b3ab2dba43d247343dc6e20e08e82ecac2dfd8
|
| 3 |
+
size 498612824
|
checkpoint-best/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba99d1c3ba0d69d50b8173f64f7462dd1ed76043c2e6f0ab3552ebe868aa52e0
|
| 3 |
+
size 997296075
|
checkpoint-best/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b7fe06310b357750986d24f03b00ab289eb730249c539587ac91e681738aa94
|
| 3 |
+
size 1465
|
checkpoint-best/training_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fd7c9bf2ecb52a8450a5bab5869f99f6049f24467b432ed2ab127059c2629e9
|
| 3 |
+
size 2623
|
checkpoint-best/training_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd569bf968060c4c179fd2bc1184500af2a2808ad15a9862addbab77593f3599
|
| 3 |
+
size 2623
|
checkpoint-best/training_3.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2caef9cd786a0855452a287fe329ebf9159bf9eeb360501ef26393d130d5394
|
| 3 |
+
size 2623
|
checkpoint-best/training_4.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ae9c34f8827c0410221c85d0e21036608f60304ebc77a2a065e135fc22fa5ce
|
| 3 |
+
size 2623
|
checkpoint-best/training_5.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e7a140f29ca90afa927476190c80de6e284a59aa8278c18d00f343aa86f90d0
|
| 3 |
+
size 2623
|
checkpoint-best/training_6.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0aab39363c53255d43dd459e71161b3889a322b5259aead56c92445d6f1acf6
|
| 3 |
+
size 2623
|
checkpoint-best/training_7.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e21f00a103ec7cafd9506199c20abce8b3ec9404c51ed13d566a2f84daf4efe7
|
| 3 |
+
size 2623
|
checkpoint-last/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/codebert-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 |
+
"finetuning_task": "codesearch",
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.49.0",
|
| 27 |
+
"type_vocab_size": 1,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 50265
|
| 30 |
+
}
|
checkpoint-last/idx_file.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
7
|
checkpoint-last/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a1ab682ea4295024157ddc9e0b3ab2dba43d247343dc6e20e08e82ecac2dfd8
|
| 3 |
+
size 498612824
|
checkpoint-last/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba99d1c3ba0d69d50b8173f64f7462dd1ed76043c2e6f0ab3552ebe868aa52e0
|
| 3 |
+
size 997296075
|
checkpoint-last/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b7fe06310b357750986d24f03b00ab289eb730249c539587ac91e681738aa94
|
| 3 |
+
size 1465
|
checkpoint-last/step_file.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
2736
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/codebert-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 |
+
"finetuning_task": "codesearch",
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-05,
|
| 17 |
+
"max_position_embeddings": 514,
|
| 18 |
+
"model_type": "roberta",
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_hidden_layers": 12,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"position_embedding_type": "absolute",
|
| 24 |
+
"problem_type": "single_label_classification",
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.49.0",
|
| 27 |
+
"type_vocab_size": 1,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 50265
|
| 30 |
+
}
|
eval_results.txt
ADDED
|
@@ -0,0 +1,248 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
evaluate 50
|
| 2 |
+
acc = 0.8008962868117798
|
| 3 |
+
acc_and_f1 = 0.7811081587550841
|
| 4 |
+
f1 = 0.7613200306983884
|
| 5 |
+
evaluate 100
|
| 6 |
+
acc = 0.9078104993597952
|
| 7 |
+
acc_and_f1 = 0.8906363568855216
|
| 8 |
+
f1 = 0.8734622144112478
|
| 9 |
+
evaluate 150
|
| 10 |
+
acc = 0.913572343149808
|
| 11 |
+
acc_and_f1 = 0.8901524104692771
|
| 12 |
+
f1 = 0.8667324777887463
|
| 13 |
+
evaluate 200
|
| 14 |
+
acc = 0.9379001280409731
|
| 15 |
+
acc_and_f1 = 0.926739446091853
|
| 16 |
+
f1 = 0.9155787641427328
|
| 17 |
+
evaluate 250
|
| 18 |
+
acc = 0.9430217669654289
|
| 19 |
+
acc_and_f1 = 0.9319553279271588
|
| 20 |
+
f1 = 0.9208888888888889
|
| 21 |
+
evaluate 300
|
| 22 |
+
acc = 0.9539052496798975
|
| 23 |
+
acc_and_f1 = 0.9438034535692306
|
| 24 |
+
f1 = 0.9337016574585635
|
| 25 |
+
evaluate 0
|
| 26 |
+
acc = 0.9551856594110115
|
| 27 |
+
acc_and_f1 = 0.9457166912719903
|
| 28 |
+
f1 = 0.936247723132969
|
| 29 |
+
evaluate 350
|
| 30 |
+
acc = 0.9545454545454546
|
| 31 |
+
acc_and_f1 = 0.9444327642755025
|
| 32 |
+
f1 = 0.9343200740055504
|
| 33 |
+
evaluate 400
|
| 34 |
+
acc = 0.9443021766965429
|
| 35 |
+
acc_and_f1 = 0.9335530404334533
|
| 36 |
+
f1 = 0.9228039041703638
|
| 37 |
+
evaluate 450
|
| 38 |
+
acc = 0.9539052496798975
|
| 39 |
+
acc_and_f1 = 0.9447522670581956
|
| 40 |
+
f1 = 0.9355992844364938
|
| 41 |
+
evaluate 500
|
| 42 |
+
acc = 0.9526248399487837
|
| 43 |
+
acc_and_f1 = 0.9436269076069006
|
| 44 |
+
f1 = 0.9346289752650176
|
| 45 |
+
evaluate 550
|
| 46 |
+
acc = 0.9571062740076824
|
| 47 |
+
acc_and_f1 = 0.9486156928572818
|
| 48 |
+
f1 = 0.9401251117068812
|
| 49 |
+
evaluate 600
|
| 50 |
+
acc = 0.9583866837387964
|
| 51 |
+
acc_and_f1 = 0.9497282466744752
|
| 52 |
+
f1 = 0.9410698096101541
|
| 53 |
+
evaluate 650
|
| 54 |
+
acc = 0.9583866837387964
|
| 55 |
+
acc_and_f1 = 0.9504577096854901
|
| 56 |
+
f1 = 0.9425287356321839
|
| 57 |
+
evaluate 1
|
| 58 |
+
acc = 0.9654289372599232
|
| 59 |
+
acc_and_f1 = 0.9582135611889453
|
| 60 |
+
f1 = 0.9509981851179673
|
| 61 |
+
evaluate 700
|
| 62 |
+
acc = 0.9667093469910372
|
| 63 |
+
acc_and_f1 = 0.9597612070708361
|
| 64 |
+
f1 = 0.9528130671506352
|
| 65 |
+
evaluate 750
|
| 66 |
+
acc = 0.9647887323943662
|
| 67 |
+
acc_and_f1 = 0.9576418909496583
|
| 68 |
+
f1 = 0.9504950495049505
|
| 69 |
+
evaluate 800
|
| 70 |
+
acc = 0.9590268886043534
|
| 71 |
+
acc_and_f1 = 0.9499385829343394
|
| 72 |
+
f1 = 0.9408502772643254
|
| 73 |
+
evaluate 850
|
| 74 |
+
acc = 0.9667093469910372
|
| 75 |
+
acc_and_f1 = 0.9596752563734785
|
| 76 |
+
f1 = 0.9526411657559198
|
| 77 |
+
evaluate 900
|
| 78 |
+
acc = 0.9526248399487837
|
| 79 |
+
acc_and_f1 = 0.9440824548175974
|
| 80 |
+
f1 = 0.9355400696864111
|
| 81 |
+
evaluate 950
|
| 82 |
+
acc = 0.970550576184379
|
| 83 |
+
acc_and_f1 = 0.9643661971830986
|
| 84 |
+
f1 = 0.9581818181818181
|
| 85 |
+
evaluate 1000
|
| 86 |
+
acc = 0.9660691421254801
|
| 87 |
+
acc_and_f1 = 0.9587003194557612
|
| 88 |
+
f1 = 0.9513314967860422
|
| 89 |
+
evaluate 2
|
| 90 |
+
acc = 0.9551856594110115
|
| 91 |
+
acc_and_f1 = 0.9470518174891009
|
| 92 |
+
f1 = 0.9389179755671903
|
| 93 |
+
evaluate 1050
|
| 94 |
+
acc = 0.9699103713188221
|
| 95 |
+
acc_and_f1 = 0.9636109531435164
|
| 96 |
+
f1 = 0.9573115349682108
|
| 97 |
+
evaluate 1100
|
| 98 |
+
acc = 0.9647887323943662
|
| 99 |
+
acc_and_f1 = 0.9573716182444989
|
| 100 |
+
f1 = 0.9499545040946314
|
| 101 |
+
evaluate 1150
|
| 102 |
+
acc = 0.9667093469910372
|
| 103 |
+
acc_and_f1 = 0.9600153557217304
|
| 104 |
+
f1 = 0.9533213644524237
|
| 105 |
+
evaluate 1200
|
| 106 |
+
acc = 0.9654289372599232
|
| 107 |
+
acc_and_f1 = 0.9583901443056373
|
| 108 |
+
f1 = 0.9513513513513514
|
| 109 |
+
evaluate 1250
|
| 110 |
+
acc = 0.9647887323943662
|
| 111 |
+
acc_and_f1 = 0.9571881333832509
|
| 112 |
+
f1 = 0.9495875343721356
|
| 113 |
+
evaluate 1300
|
| 114 |
+
acc = 0.9699103713188221
|
| 115 |
+
acc_and_f1 = 0.9636882173336192
|
| 116 |
+
f1 = 0.9574660633484163
|
| 117 |
+
evaluate 1350
|
| 118 |
+
acc = 0.9699103713188221
|
| 119 |
+
acc_and_f1 = 0.963764924162567
|
| 120 |
+
f1 = 0.957619477006312
|
| 121 |
+
evaluate 3
|
| 122 |
+
acc = 0.967989756722151
|
| 123 |
+
acc_and_f1 = 0.9612676056338028
|
| 124 |
+
f1 = 0.9545454545454546
|
| 125 |
+
evaluate 1400
|
| 126 |
+
acc = 0.971830985915493
|
| 127 |
+
acc_and_f1 = 0.9660956731379267
|
| 128 |
+
f1 = 0.9603603603603603
|
| 129 |
+
evaluate 1450
|
| 130 |
+
acc = 0.970550576184379
|
| 131 |
+
acc_and_f1 = 0.9644796280560232
|
| 132 |
+
f1 = 0.9584086799276673
|
| 133 |
+
evaluate 1500
|
| 134 |
+
acc = 0.970550576184379
|
| 135 |
+
acc_and_f1 = 0.9647028372871805
|
| 136 |
+
f1 = 0.9588550983899821
|
| 137 |
+
evaluate 1550
|
| 138 |
+
acc = 0.971190781049936
|
| 139 |
+
acc_and_f1 = 0.965524025672158
|
| 140 |
+
f1 = 0.9598572702943801
|
| 141 |
+
evaluate 1600
|
| 142 |
+
acc = 0.9737516005121639
|
| 143 |
+
acc_and_f1 = 0.9683906785247924
|
| 144 |
+
f1 = 0.9630297565374211
|
| 145 |
+
evaluate 1650
|
| 146 |
+
acc = 0.971190781049936
|
| 147 |
+
acc_and_f1 = 0.9654881519190699
|
| 148 |
+
f1 = 0.9597855227882037
|
| 149 |
+
evaluate 1700
|
| 150 |
+
acc = 0.967989756722151
|
| 151 |
+
acc_and_f1 = 0.9616335187904137
|
| 152 |
+
f1 = 0.9552772808586762
|
| 153 |
+
evaluate 4
|
| 154 |
+
acc = 0.9686299615877081
|
| 155 |
+
acc_and_f1 = 0.9621430350924967
|
| 156 |
+
f1 = 0.9556561085972851
|
| 157 |
+
evaluate 1750
|
| 158 |
+
acc = 0.9737516005121639
|
| 159 |
+
acc_and_f1 = 0.9682901248254383
|
| 160 |
+
f1 = 0.9628286491387126
|
| 161 |
+
evaluate 1800
|
| 162 |
+
acc = 0.971830985915493
|
| 163 |
+
acc_and_f1 = 0.9659517905983999
|
| 164 |
+
f1 = 0.9600725952813067
|
| 165 |
+
evaluate 1850
|
| 166 |
+
acc = 0.971830985915493
|
| 167 |
+
acc_and_f1 = 0.966202231309001
|
| 168 |
+
f1 = 0.9605734767025089
|
| 169 |
+
evaluate 1900
|
| 170 |
+
acc = 0.9699103713188221
|
| 171 |
+
acc_and_f1 = 0.9635721101362081
|
| 172 |
+
f1 = 0.9572338489535942
|
| 173 |
+
evaluate 1950
|
| 174 |
+
acc = 0.971190781049936
|
| 175 |
+
acc_and_f1 = 0.9651222331091354
|
| 176 |
+
f1 = 0.9590536851683349
|
| 177 |
+
evaluate 2000
|
| 178 |
+
acc = 0.971190781049936
|
| 179 |
+
acc_and_f1 = 0.9652701872729355
|
| 180 |
+
f1 = 0.959349593495935
|
| 181 |
+
evaluate 2050
|
| 182 |
+
acc = 0.971190781049936
|
| 183 |
+
acc_and_f1 = 0.965084907389143
|
| 184 |
+
f1 = 0.95897903372835
|
| 185 |
+
evaluate 5
|
| 186 |
+
acc = 0.970550576184379
|
| 187 |
+
acc_and_f1 = 0.9643281114073079
|
| 188 |
+
f1 = 0.9581056466302368
|
| 189 |
+
evaluate 2100
|
| 190 |
+
acc = 0.9737516005121639
|
| 191 |
+
acc_and_f1 = 0.9683572817375634
|
| 192 |
+
f1 = 0.9629629629629629
|
| 193 |
+
evaluate 2150
|
| 194 |
+
acc = 0.9737516005121639
|
| 195 |
+
acc_and_f1 = 0.9684239550715634
|
| 196 |
+
f1 = 0.963096309630963
|
| 197 |
+
evaluate 2200
|
| 198 |
+
acc = 0.9724711907810499
|
| 199 |
+
acc_and_f1 = 0.9667785818158643
|
| 200 |
+
f1 = 0.9610859728506788
|
| 201 |
+
evaluate 2250
|
| 202 |
+
acc = 0.9743918053777209
|
| 203 |
+
acc_and_f1 = 0.969145361172615
|
| 204 |
+
f1 = 0.9638989169675091
|
| 205 |
+
evaluate 2300
|
| 206 |
+
acc = 0.9743918053777209
|
| 207 |
+
acc_and_f1 = 0.9691778846708424
|
| 208 |
+
f1 = 0.963963963963964
|
| 209 |
+
evaluate 2350
|
| 210 |
+
acc = 0.9724711907810499
|
| 211 |
+
acc_and_f1 = 0.9667785818158643
|
| 212 |
+
f1 = 0.9610859728506788
|
| 213 |
+
evaluate 6
|
| 214 |
+
acc = 0.9731113956466069
|
| 215 |
+
acc_and_f1 = 0.9675339586928686
|
| 216 |
+
f1 = 0.9619565217391305
|
| 217 |
+
evaluate 2400
|
| 218 |
+
acc = 0.9737516005121639
|
| 219 |
+
acc_and_f1 = 0.968323764056987
|
| 220 |
+
f1 = 0.96289592760181
|
| 221 |
+
evaluate 2450
|
| 222 |
+
acc = 0.9737516005121639
|
| 223 |
+
acc_and_f1 = 0.9682901248254383
|
| 224 |
+
f1 = 0.9628286491387126
|
| 225 |
+
evaluate 2500
|
| 226 |
+
acc = 0.9731113956466069
|
| 227 |
+
acc_and_f1 = 0.9675683560511515
|
| 228 |
+
f1 = 0.9620253164556962
|
| 229 |
+
evaluate 2550
|
| 230 |
+
acc = 0.9731113956466069
|
| 231 |
+
acc_and_f1 = 0.9675683560511515
|
| 232 |
+
f1 = 0.9620253164556962
|
| 233 |
+
evaluate 2600
|
| 234 |
+
acc = 0.9731113956466069
|
| 235 |
+
acc_and_f1 = 0.9676026292312456
|
| 236 |
+
f1 = 0.9620938628158845
|
| 237 |
+
evaluate 2650
|
| 238 |
+
acc = 0.9737516005121639
|
| 239 |
+
acc_and_f1 = 0.9683906785247924
|
| 240 |
+
f1 = 0.9630297565374211
|
| 241 |
+
evaluate 2700
|
| 242 |
+
acc = 0.9737516005121639
|
| 243 |
+
acc_and_f1 = 0.9683906785247924
|
| 244 |
+
f1 = 0.9630297565374211
|
| 245 |
+
evaluate 7
|
| 246 |
+
acc = 0.9737516005121639
|
| 247 |
+
acc_and_f1 = 0.9683906785247924
|
| 248 |
+
f1 = 0.9630297565374211
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a1ab682ea4295024157ddc9e0b3ab2dba43d247343dc6e20e08e82ecac2dfd8
|
| 3 |
+
size 498612824
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"do_lower_case": false,
|
| 49 |
+
"eos_token": "</s>",
|
| 50 |
+
"errors": "replace",
|
| 51 |
+
"extra_special_tokens": {},
|
| 52 |
+
"mask_token": "<mask>",
|
| 53 |
+
"model_max_length": 512,
|
| 54 |
+
"pad_token": "<pad>",
|
| 55 |
+
"sep_token": "</s>",
|
| 56 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d99b7cfb9358e9fc1116aa488fa74b2c4dc3289ef9cb4a75fcf4e99025dfdb9c
|
| 3 |
+
size 2641
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|