Commit
•
2c7378d
1
Parent(s):
721a7c7
Upload 11 files
Browse files- config.json +45 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +431 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "NbAiLab/nb-bert-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2",
|
| 16 |
+
"3": "LABEL_3",
|
| 17 |
+
"4": "LABEL_4",
|
| 18 |
+
"5": "LABEL_5",
|
| 19 |
+
"6": "LABEL_6"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 4096,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"LABEL_0": 0,
|
| 25 |
+
"LABEL_1": 1,
|
| 26 |
+
"LABEL_2": 2,
|
| 27 |
+
"LABEL_3": 3,
|
| 28 |
+
"LABEL_4": 4,
|
| 29 |
+
"LABEL_5": 5,
|
| 30 |
+
"LABEL_6": 6
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"max_position_embeddings": 512,
|
| 34 |
+
"model_type": "bert",
|
| 35 |
+
"num_attention_heads": 16,
|
| 36 |
+
"num_hidden_layers": 24,
|
| 37 |
+
"pad_token_id": 0,
|
| 38 |
+
"position_embedding_type": "absolute",
|
| 39 |
+
"problem_type": "single_label_classification",
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.40.0",
|
| 42 |
+
"type_vocab_size": 2,
|
| 43 |
+
"use_cache": true,
|
| 44 |
+
"vocab_size": 50000
|
| 45 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77cb83eae223bcbc8342d37afaa3f167eccfe89eb7210f2e09ab50898176bd60
|
| 3 |
+
size 1420425204
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ee80e099b27b639b74f84d633fac0a8d8e83cb7ab6b889d5851bd636793654f
|
| 3 |
+
size 2841074157
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e5aa417b4f1b17cecb5dcf222fa3803ec44a2e98f52640f39c31b014e024933
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:146161a54404c69c61e07a330b5d04fb08e8df56104ee1a347f4c65ebc068516
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"501": {
|
| 4 |
+
"content": "[CLS]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"502": {
|
| 12 |
+
"content": "[MASK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"503": {
|
| 20 |
+
"content": "[PAD]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"504": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"505": {
|
| 36 |
+
"content": "[UNK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": false,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,431 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.547008547008547,
|
| 5 |
+
"eval_steps": 30,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.2564102564102564,
|
| 13 |
+
"eval_accuracy": 0.33653846153846156,
|
| 14 |
+
"eval_f1": 0.15795586527293845,
|
| 15 |
+
"eval_loss": 1.5857505798339844,
|
| 16 |
+
"eval_precision": 0.15263157894736842,
|
| 17 |
+
"eval_recall": 0.20117770428329435,
|
| 18 |
+
"eval_runtime": 8.6482,
|
| 19 |
+
"eval_samples_per_second": 12.026,
|
| 20 |
+
"eval_steps_per_second": 1.503,
|
| 21 |
+
"step": 30
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.5128205128205128,
|
| 25 |
+
"eval_accuracy": 0.46153846153846156,
|
| 26 |
+
"eval_f1": 0.2013725205214567,
|
| 27 |
+
"eval_loss": 1.4627048969268799,
|
| 28 |
+
"eval_precision": 0.25281954887218044,
|
| 29 |
+
"eval_recall": 0.2350972009357102,
|
| 30 |
+
"eval_runtime": 8.4187,
|
| 31 |
+
"eval_samples_per_second": 12.353,
|
| 32 |
+
"eval_steps_per_second": 1.544,
|
| 33 |
+
"step": 60
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.7692307692307693,
|
| 37 |
+
"eval_accuracy": 0.6153846153846154,
|
| 38 |
+
"eval_f1": 0.37538782821801686,
|
| 39 |
+
"eval_loss": 1.1772669553756714,
|
| 40 |
+
"eval_precision": 0.35533996281025143,
|
| 41 |
+
"eval_recall": 0.40736468500443657,
|
| 42 |
+
"eval_runtime": 7.8916,
|
| 43 |
+
"eval_samples_per_second": 13.179,
|
| 44 |
+
"eval_steps_per_second": 1.647,
|
| 45 |
+
"step": 90
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.0256410256410255,
|
| 49 |
+
"eval_accuracy": 0.6057692307692307,
|
| 50 |
+
"eval_f1": 0.36798810227453504,
|
| 51 |
+
"eval_loss": 1.1327857971191406,
|
| 52 |
+
"eval_precision": 0.38458852974982005,
|
| 53 |
+
"eval_recall": 0.37962410260546914,
|
| 54 |
+
"eval_runtime": 9.4477,
|
| 55 |
+
"eval_samples_per_second": 11.008,
|
| 56 |
+
"eval_steps_per_second": 1.376,
|
| 57 |
+
"step": 120
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.282051282051282,
|
| 61 |
+
"eval_accuracy": 0.6538461538461539,
|
| 62 |
+
"eval_f1": 0.41900575614861335,
|
| 63 |
+
"eval_loss": 1.0890244245529175,
|
| 64 |
+
"eval_precision": 0.5082160450387051,
|
| 65 |
+
"eval_recall": 0.43861238830182936,
|
| 66 |
+
"eval_runtime": 7.2525,
|
| 67 |
+
"eval_samples_per_second": 14.34,
|
| 68 |
+
"eval_steps_per_second": 1.792,
|
| 69 |
+
"step": 150
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.5384615384615383,
|
| 73 |
+
"eval_accuracy": 0.6057692307692307,
|
| 74 |
+
"eval_f1": 0.3925319620409576,
|
| 75 |
+
"eval_loss": 1.1820482015609741,
|
| 76 |
+
"eval_precision": 0.4949262737968994,
|
| 77 |
+
"eval_recall": 0.42246331997884795,
|
| 78 |
+
"eval_runtime": 7.3455,
|
| 79 |
+
"eval_samples_per_second": 14.158,
|
| 80 |
+
"eval_steps_per_second": 1.77,
|
| 81 |
+
"step": 180
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.7948717948717947,
|
| 85 |
+
"eval_accuracy": 0.6442307692307693,
|
| 86 |
+
"eval_f1": 0.42451081809572366,
|
| 87 |
+
"eval_loss": 1.0674420595169067,
|
| 88 |
+
"eval_precision": 0.42179487179487174,
|
| 89 |
+
"eval_recall": 0.4413065885115575,
|
| 90 |
+
"eval_runtime": 7.8787,
|
| 91 |
+
"eval_samples_per_second": 13.2,
|
| 92 |
+
"eval_steps_per_second": 1.65,
|
| 93 |
+
"step": 210
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.051282051282051,
|
| 97 |
+
"eval_accuracy": 0.6730769230769231,
|
| 98 |
+
"eval_f1": 0.45817680472411926,
|
| 99 |
+
"eval_loss": 1.0437394380569458,
|
| 100 |
+
"eval_precision": 0.4717732448710709,
|
| 101 |
+
"eval_recall": 0.46608498471852516,
|
| 102 |
+
"eval_runtime": 7.3406,
|
| 103 |
+
"eval_samples_per_second": 14.168,
|
| 104 |
+
"eval_steps_per_second": 1.771,
|
| 105 |
+
"step": 240
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.3076923076923075,
|
| 109 |
+
"eval_accuracy": 0.6634615384615384,
|
| 110 |
+
"eval_f1": 0.44733091369464534,
|
| 111 |
+
"eval_loss": 1.1606773138046265,
|
| 112 |
+
"eval_precision": 0.4613468768074031,
|
| 113 |
+
"eval_recall": 0.46812400849667934,
|
| 114 |
+
"eval_runtime": 7.0489,
|
| 115 |
+
"eval_samples_per_second": 14.754,
|
| 116 |
+
"eval_steps_per_second": 1.844,
|
| 117 |
+
"step": 270
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.564102564102564,
|
| 121 |
+
"eval_accuracy": 0.625,
|
| 122 |
+
"eval_f1": 0.4062809568796815,
|
| 123 |
+
"eval_loss": 1.2771650552749634,
|
| 124 |
+
"eval_precision": 0.41611170784103113,
|
| 125 |
+
"eval_recall": 0.4306409256719816,
|
| 126 |
+
"eval_runtime": 7.1782,
|
| 127 |
+
"eval_samples_per_second": 14.488,
|
| 128 |
+
"eval_steps_per_second": 1.811,
|
| 129 |
+
"step": 300
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.8205128205128203,
|
| 133 |
+
"eval_accuracy": 0.6153846153846154,
|
| 134 |
+
"eval_f1": 0.40669330669330667,
|
| 135 |
+
"eval_loss": 1.0749222040176392,
|
| 136 |
+
"eval_precision": 0.4599390919158361,
|
| 137 |
+
"eval_recall": 0.4225825244458785,
|
| 138 |
+
"eval_runtime": 7.4587,
|
| 139 |
+
"eval_samples_per_second": 13.943,
|
| 140 |
+
"eval_steps_per_second": 1.743,
|
| 141 |
+
"step": 330
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.076923076923077,
|
| 145 |
+
"eval_accuracy": 0.625,
|
| 146 |
+
"eval_f1": 0.42567364176740446,
|
| 147 |
+
"eval_loss": 1.1399219036102295,
|
| 148 |
+
"eval_precision": 0.46537455679332107,
|
| 149 |
+
"eval_recall": 0.45866383444023195,
|
| 150 |
+
"eval_runtime": 9.0954,
|
| 151 |
+
"eval_samples_per_second": 11.434,
|
| 152 |
+
"eval_steps_per_second": 1.429,
|
| 153 |
+
"step": 360
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 3.3333333333333335,
|
| 157 |
+
"eval_accuracy": 0.6538461538461539,
|
| 158 |
+
"eval_f1": 0.4619962083193933,
|
| 159 |
+
"eval_loss": 1.0954734086990356,
|
| 160 |
+
"eval_precision": 0.4735928232168834,
|
| 161 |
+
"eval_recall": 0.48448101243132297,
|
| 162 |
+
"eval_runtime": 8.1347,
|
| 163 |
+
"eval_samples_per_second": 12.785,
|
| 164 |
+
"eval_steps_per_second": 1.598,
|
| 165 |
+
"step": 390
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.58974358974359,
|
| 169 |
+
"eval_accuracy": 0.6346153846153846,
|
| 170 |
+
"eval_f1": 0.4427206780147956,
|
| 171 |
+
"eval_loss": 1.2177672386169434,
|
| 172 |
+
"eval_precision": 0.45063474537158743,
|
| 173 |
+
"eval_recall": 0.4697516424224498,
|
| 174 |
+
"eval_runtime": 7.1682,
|
| 175 |
+
"eval_samples_per_second": 14.509,
|
| 176 |
+
"eval_steps_per_second": 1.814,
|
| 177 |
+
"step": 420
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.8461538461538463,
|
| 181 |
+
"eval_accuracy": 0.625,
|
| 182 |
+
"eval_f1": 0.42804680076021545,
|
| 183 |
+
"eval_loss": 1.3288222551345825,
|
| 184 |
+
"eval_precision": 0.4205708300859973,
|
| 185 |
+
"eval_recall": 0.46260295949736946,
|
| 186 |
+
"eval_runtime": 7.5635,
|
| 187 |
+
"eval_samples_per_second": 13.75,
|
| 188 |
+
"eval_steps_per_second": 1.719,
|
| 189 |
+
"step": 450
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.102564102564102,
|
| 193 |
+
"eval_accuracy": 0.7019230769230769,
|
| 194 |
+
"eval_f1": 0.5106953307638845,
|
| 195 |
+
"eval_loss": 1.0881779193878174,
|
| 196 |
+
"eval_precision": 0.523184558376196,
|
| 197 |
+
"eval_recall": 0.5067507371855199,
|
| 198 |
+
"eval_runtime": 7.5106,
|
| 199 |
+
"eval_samples_per_second": 13.847,
|
| 200 |
+
"eval_steps_per_second": 1.731,
|
| 201 |
+
"step": 480
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.273504273504273,
|
| 205 |
+
"grad_norm": 7.013587474822998,
|
| 206 |
+
"learning_rate": 3.575498575498576e-05,
|
| 207 |
+
"loss": 0.9258,
|
| 208 |
+
"step": 500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 4.358974358974359,
|
| 212 |
+
"eval_accuracy": 0.7115384615384616,
|
| 213 |
+
"eval_f1": 0.49821801060849874,
|
| 214 |
+
"eval_loss": 1.1554274559020996,
|
| 215 |
+
"eval_precision": 0.49124649859943975,
|
| 216 |
+
"eval_recall": 0.5149140024916423,
|
| 217 |
+
"eval_runtime": 50.6521,
|
| 218 |
+
"eval_samples_per_second": 2.053,
|
| 219 |
+
"eval_steps_per_second": 0.257,
|
| 220 |
+
"step": 510
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.615384615384615,
|
| 224 |
+
"eval_accuracy": 0.6923076923076923,
|
| 225 |
+
"eval_f1": 0.49742827816559965,
|
| 226 |
+
"eval_loss": 1.4417259693145752,
|
| 227 |
+
"eval_precision": 0.5,
|
| 228 |
+
"eval_recall": 0.5011042097998619,
|
| 229 |
+
"eval_runtime": 103.6054,
|
| 230 |
+
"eval_samples_per_second": 1.004,
|
| 231 |
+
"eval_steps_per_second": 0.125,
|
| 232 |
+
"step": 540
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 4.871794871794872,
|
| 236 |
+
"eval_accuracy": 0.6923076923076923,
|
| 237 |
+
"eval_f1": 0.4863793250320917,
|
| 238 |
+
"eval_loss": 1.1507378816604614,
|
| 239 |
+
"eval_precision": 0.48549534756431306,
|
| 240 |
+
"eval_recall": 0.5111003558208527,
|
| 241 |
+
"eval_runtime": 75.6676,
|
| 242 |
+
"eval_samples_per_second": 1.374,
|
| 243 |
+
"eval_steps_per_second": 0.172,
|
| 244 |
+
"step": 570
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 5.128205128205128,
|
| 248 |
+
"eval_accuracy": 0.6634615384615384,
|
| 249 |
+
"eval_f1": 0.48039244705911377,
|
| 250 |
+
"eval_loss": 1.2641137838363647,
|
| 251 |
+
"eval_precision": 0.49331432177614126,
|
| 252 |
+
"eval_recall": 0.47660813996217727,
|
| 253 |
+
"eval_runtime": 42.9337,
|
| 254 |
+
"eval_samples_per_second": 2.422,
|
| 255 |
+
"eval_steps_per_second": 0.303,
|
| 256 |
+
"step": 600
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 5.384615384615385,
|
| 260 |
+
"eval_accuracy": 0.6923076923076923,
|
| 261 |
+
"eval_f1": 0.4878689679921483,
|
| 262 |
+
"eval_loss": 1.3560154438018799,
|
| 263 |
+
"eval_precision": 0.4848901098901099,
|
| 264 |
+
"eval_recall": 0.4981276832208509,
|
| 265 |
+
"eval_runtime": 8.8339,
|
| 266 |
+
"eval_samples_per_second": 11.773,
|
| 267 |
+
"eval_steps_per_second": 1.472,
|
| 268 |
+
"step": 630
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 5.641025641025641,
|
| 272 |
+
"eval_accuracy": 0.6923076923076923,
|
| 273 |
+
"eval_f1": 0.48765147825687144,
|
| 274 |
+
"eval_loss": 1.484885334968567,
|
| 275 |
+
"eval_precision": 0.4961309523809524,
|
| 276 |
+
"eval_recall": 0.49494501357855397,
|
| 277 |
+
"eval_runtime": 7.535,
|
| 278 |
+
"eval_samples_per_second": 13.802,
|
| 279 |
+
"eval_steps_per_second": 1.725,
|
| 280 |
+
"step": 660
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 5.897435897435898,
|
| 284 |
+
"eval_accuracy": 0.6923076923076923,
|
| 285 |
+
"eval_f1": 0.4755107161831651,
|
| 286 |
+
"eval_loss": 1.0820866823196411,
|
| 287 |
+
"eval_precision": 0.46649659863945575,
|
| 288 |
+
"eval_recall": 0.4995007752771728,
|
| 289 |
+
"eval_runtime": 7.4913,
|
| 290 |
+
"eval_samples_per_second": 13.883,
|
| 291 |
+
"eval_steps_per_second": 1.735,
|
| 292 |
+
"step": 690
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 6.153846153846154,
|
| 296 |
+
"eval_accuracy": 0.7115384615384616,
|
| 297 |
+
"eval_f1": 0.5779124103915706,
|
| 298 |
+
"eval_loss": 1.2979052066802979,
|
| 299 |
+
"eval_precision": 0.5928430383317601,
|
| 300 |
+
"eval_recall": 0.5695562546494223,
|
| 301 |
+
"eval_runtime": 7.5001,
|
| 302 |
+
"eval_samples_per_second": 13.866,
|
| 303 |
+
"eval_steps_per_second": 1.733,
|
| 304 |
+
"step": 720
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 6.410256410256411,
|
| 308 |
+
"eval_accuracy": 0.7115384615384616,
|
| 309 |
+
"eval_f1": 0.5007207127411731,
|
| 310 |
+
"eval_loss": 1.4726945161819458,
|
| 311 |
+
"eval_precision": 0.4985431235431235,
|
| 312 |
+
"eval_recall": 0.5046211897143573,
|
| 313 |
+
"eval_runtime": 7.4555,
|
| 314 |
+
"eval_samples_per_second": 13.949,
|
| 315 |
+
"eval_steps_per_second": 1.744,
|
| 316 |
+
"step": 750
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 6.666666666666667,
|
| 320 |
+
"eval_accuracy": 0.6826923076923077,
|
| 321 |
+
"eval_f1": 0.49164104194549385,
|
| 322 |
+
"eval_loss": 1.5962382555007935,
|
| 323 |
+
"eval_precision": 0.48890290995554153,
|
| 324 |
+
"eval_recall": 0.49645792440823505,
|
| 325 |
+
"eval_runtime": 7.8196,
|
| 326 |
+
"eval_samples_per_second": 13.3,
|
| 327 |
+
"eval_steps_per_second": 1.662,
|
| 328 |
+
"step": 780
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 6.923076923076923,
|
| 332 |
+
"eval_accuracy": 0.7211538461538461,
|
| 333 |
+
"eval_f1": 0.5234641383494542,
|
| 334 |
+
"eval_loss": 1.2745909690856934,
|
| 335 |
+
"eval_precision": 0.5273022215879359,
|
| 336 |
+
"eval_recall": 0.5242791714841405,
|
| 337 |
+
"eval_runtime": 7.0448,
|
| 338 |
+
"eval_samples_per_second": 14.763,
|
| 339 |
+
"eval_steps_per_second": 1.845,
|
| 340 |
+
"step": 810
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 7.17948717948718,
|
| 344 |
+
"eval_accuracy": 0.6538461538461539,
|
| 345 |
+
"eval_f1": 0.4674051433314255,
|
| 346 |
+
"eval_loss": 2.0724053382873535,
|
| 347 |
+
"eval_precision": 0.5055194805194805,
|
| 348 |
+
"eval_recall": 0.4713972018319845,
|
| 349 |
+
"eval_runtime": 8.5997,
|
| 350 |
+
"eval_samples_per_second": 12.093,
|
| 351 |
+
"eval_steps_per_second": 1.512,
|
| 352 |
+
"step": 840
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.435897435897436,
|
| 356 |
+
"eval_accuracy": 0.6826923076923077,
|
| 357 |
+
"eval_f1": 0.559112957131097,
|
| 358 |
+
"eval_loss": 1.8112683296203613,
|
| 359 |
+
"eval_precision": 0.6143772893772894,
|
| 360 |
+
"eval_recall": 0.5511665008559419,
|
| 361 |
+
"eval_runtime": 8.6462,
|
| 362 |
+
"eval_samples_per_second": 12.028,
|
| 363 |
+
"eval_steps_per_second": 1.504,
|
| 364 |
+
"step": 870
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 7.6923076923076925,
|
| 368 |
+
"eval_accuracy": 0.7307692307692307,
|
| 369 |
+
"eval_f1": 0.5986119673110736,
|
| 370 |
+
"eval_loss": 1.5658988952636719,
|
| 371 |
+
"eval_precision": 0.6397901095922239,
|
| 372 |
+
"eval_recall": 0.5927312163337008,
|
| 373 |
+
"eval_runtime": 8.5049,
|
| 374 |
+
"eval_samples_per_second": 12.228,
|
| 375 |
+
"eval_steps_per_second": 1.529,
|
| 376 |
+
"step": 900
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 7.948717948717949,
|
| 380 |
+
"eval_accuracy": 0.7019230769230769,
|
| 381 |
+
"eval_f1": 0.5792037287395081,
|
| 382 |
+
"eval_loss": 1.473520278930664,
|
| 383 |
+
"eval_precision": 0.5669774028567353,
|
| 384 |
+
"eval_recall": 0.619092432757029,
|
| 385 |
+
"eval_runtime": 8.1417,
|
| 386 |
+
"eval_samples_per_second": 12.774,
|
| 387 |
+
"eval_steps_per_second": 1.597,
|
| 388 |
+
"step": 930
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 8.205128205128204,
|
| 392 |
+
"eval_accuracy": 0.7019230769230769,
|
| 393 |
+
"eval_f1": 0.5951573832227319,
|
| 394 |
+
"eval_loss": 1.7524921894073486,
|
| 395 |
+
"eval_precision": 0.5870032223415682,
|
| 396 |
+
"eval_recall": 0.6328215607718713,
|
| 397 |
+
"eval_runtime": 6.8175,
|
| 398 |
+
"eval_samples_per_second": 15.255,
|
| 399 |
+
"eval_steps_per_second": 1.907,
|
| 400 |
+
"step": 960
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 8.461538461538462,
|
| 404 |
+
"eval_accuracy": 0.7115384615384616,
|
| 405 |
+
"eval_f1": 0.5830133910730354,
|
| 406 |
+
"eval_loss": 1.7076036930084229,
|
| 407 |
+
"eval_precision": 0.5997339127038376,
|
| 408 |
+
"eval_recall": 0.5719681284898676,
|
| 409 |
+
"eval_runtime": 7.3179,
|
| 410 |
+
"eval_samples_per_second": 14.212,
|
| 411 |
+
"eval_steps_per_second": 1.776,
|
| 412 |
+
"step": 990
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 8.547008547008547,
|
| 416 |
+
"grad_norm": 0.23315642774105072,
|
| 417 |
+
"learning_rate": 2.150997150997151e-05,
|
| 418 |
+
"loss": 0.2238,
|
| 419 |
+
"step": 1000
|
| 420 |
+
}
|
| 421 |
+
],
|
| 422 |
+
"logging_steps": 500,
|
| 423 |
+
"max_steps": 1755,
|
| 424 |
+
"num_input_tokens_seen": 0,
|
| 425 |
+
"num_train_epochs": 15,
|
| 426 |
+
"save_steps": 500,
|
| 427 |
+
"total_flos": 5649929338176000.0,
|
| 428 |
+
"train_batch_size": 8,
|
| 429 |
+
"trial_name": null,
|
| 430 |
+
"trial_params": null
|
| 431 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2571126580c83cf162ca39519a44ca8465173d240813184bd8fa877cb3ff5f6d
|
| 3 |
+
size 4984
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|