Upload folder using huggingface_hub
Browse files- config.json +42 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +400 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
| 3 |
+
"adapters": {
|
| 4 |
+
"adapters": {},
|
| 5 |
+
"config_map": {},
|
| 6 |
+
"fusion_config_map": {},
|
| 7 |
+
"fusions": {}
|
| 8 |
+
},
|
| 9 |
+
"architectures": [
|
| 10 |
+
"BertForSequenceClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_probs_dropout_prob": 0.12254664017551167,
|
| 13 |
+
"classifier_dropout": null,
|
| 14 |
+
"gradient_checkpointing": false,
|
| 15 |
+
"hidden_act": "gelu",
|
| 16 |
+
"hidden_dropout_prob": 0.09767216663102402,
|
| 17 |
+
"hidden_size": 768,
|
| 18 |
+
"id2label": {
|
| 19 |
+
"0": "right",
|
| 20 |
+
"1": "left"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"left": 1,
|
| 26 |
+
"right": 0
|
| 27 |
+
},
|
| 28 |
+
"layer_norm_eps": 1e-12,
|
| 29 |
+
"max_position_embeddings": 512,
|
| 30 |
+
"model_type": "bert",
|
| 31 |
+
"num_attention_heads": 12,
|
| 32 |
+
"num_hidden_layers": 12,
|
| 33 |
+
"output_past": true,
|
| 34 |
+
"pad_token_id": 1,
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.26.1",
|
| 39 |
+
"type_vocab_size": 2,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 31002
|
| 42 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b0d42934c6adcc6932fde9dde10c84e023f4f777488be65d7d6e55247290989
|
| 3 |
+
size 878937221
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c78038019e0564f6ed9a02b54d51c1ba25a1d7a14ee96dc53bbecdf47a82e835
|
| 3 |
+
size 439482485
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48b43e5d32e32af08a967d6b00b55ac9de2566e8afe2dee53092b67bdda7e824
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b074d794dc78d226b73c1c5bd5c2de265ec253feb15eebde071c24b606777f92
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1ad948fe02295e84ba3f25207af9671d9455bcbfa0ef083e143204df91d9429
|
| 3 |
+
size 627
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": "/home/lhurtado/.cache/huggingface/hub/models--dccuchile--bert-base-spanish-wwm-cased/snapshots/56a7647b957a4230fc3f80dafbe80f2ba9b0de73/special_tokens_map.json",
|
| 12 |
+
"strip_accents": false,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,400 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9818782216494845,
|
| 3 |
+
"best_model_checkpoint": "../models/PoliticES/ideology_binary/BETO/450_SEED_11/run-1/checkpoint-3180",
|
| 4 |
+
"epoch": 14.99647473560517,
|
| 5 |
+
"global_step": 3180,
|
| 6 |
+
"is_hyper_param_search": true,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.94,
|
| 12 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 13 |
+
"loss": 0.4738,
|
| 14 |
+
"step": 200
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.7511111111111111,
|
| 19 |
+
"eval_jaccard": 0.5818173817381738,
|
| 20 |
+
"eval_loss": 0.56746506690979,
|
| 21 |
+
"eval_macro_f1": 0.716113914924297,
|
| 22 |
+
"eval_macro_precision": 0.8270380109968922,
|
| 23 |
+
"eval_macro_recall": 0.7193362193362193,
|
| 24 |
+
"eval_micro_f1": 0.7511111111111111,
|
| 25 |
+
"eval_micro_precision": 0.7511111111111111,
|
| 26 |
+
"eval_micro_recall": 0.7511111111111111,
|
| 27 |
+
"eval_runtime": 3.8883,
|
| 28 |
+
"eval_samples_per_second": 387.83,
|
| 29 |
+
"eval_steps_per_second": 12.345,
|
| 30 |
+
"eval_weighted_f1": 0.7280749819754866,
|
| 31 |
+
"eval_weighted_precision": 0.8113889552952426,
|
| 32 |
+
"eval_weighted_recall": 0.7511111111111111,
|
| 33 |
+
"step": 212
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.88,
|
| 37 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 38 |
+
"loss": 0.3003,
|
| 39 |
+
"step": 400
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.0,
|
| 43 |
+
"eval_accuracy": 0.9422222222222222,
|
| 44 |
+
"eval_jaccard": 0.8905400934915497,
|
| 45 |
+
"eval_loss": 0.2769545614719391,
|
| 46 |
+
"eval_macro_f1": 0.9410294147295417,
|
| 47 |
+
"eval_macro_precision": 0.9443722592171513,
|
| 48 |
+
"eval_macro_recall": 0.9386724386724387,
|
| 49 |
+
"eval_micro_f1": 0.9422222222222222,
|
| 50 |
+
"eval_micro_precision": 0.9422222222222222,
|
| 51 |
+
"eval_micro_recall": 0.9422222222222222,
|
| 52 |
+
"eval_runtime": 3.8935,
|
| 53 |
+
"eval_samples_per_second": 387.316,
|
| 54 |
+
"eval_steps_per_second": 12.328,
|
| 55 |
+
"eval_weighted_f1": 0.9420358460514909,
|
| 56 |
+
"eval_weighted_precision": 0.9428033133019327,
|
| 57 |
+
"eval_weighted_recall": 0.9422222222222222,
|
| 58 |
+
"step": 424
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.83,
|
| 62 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 63 |
+
"loss": 0.1564,
|
| 64 |
+
"step": 600
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 3.0,
|
| 68 |
+
"eval_accuracy": 0.9333333333333333,
|
| 69 |
+
"eval_jaccard": 0.8754464285714286,
|
| 70 |
+
"eval_loss": 0.3916676938533783,
|
| 71 |
+
"eval_macro_f1": 0.9329945005856777,
|
| 72 |
+
"eval_macro_precision": 0.9322134387351779,
|
| 73 |
+
"eval_macro_recall": 0.9383116883116883,
|
| 74 |
+
"eval_micro_f1": 0.9333333333333333,
|
| 75 |
+
"eval_micro_precision": 0.9333333333333333,
|
| 76 |
+
"eval_micro_recall": 0.9333333333333333,
|
| 77 |
+
"eval_runtime": 3.9044,
|
| 78 |
+
"eval_samples_per_second": 386.23,
|
| 79 |
+
"eval_steps_per_second": 12.294,
|
| 80 |
+
"eval_weighted_f1": 0.9335662808473466,
|
| 81 |
+
"eval_weighted_precision": 0.9382608695652174,
|
| 82 |
+
"eval_weighted_recall": 0.9333333333333333,
|
| 83 |
+
"step": 636
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 3.77,
|
| 87 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 88 |
+
"loss": 0.0897,
|
| 89 |
+
"step": 800
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 4.0,
|
| 93 |
+
"eval_accuracy": 0.9422222222222222,
|
| 94 |
+
"eval_jaccard": 0.8902276505022765,
|
| 95 |
+
"eval_loss": 0.4636266231536865,
|
| 96 |
+
"eval_macro_f1": 0.9407042510490785,
|
| 97 |
+
"eval_macro_precision": 0.9481481481481482,
|
| 98 |
+
"eval_macro_recall": 0.9365079365079365,
|
| 99 |
+
"eval_micro_f1": 0.9422222222222222,
|
| 100 |
+
"eval_micro_precision": 0.9422222222222222,
|
| 101 |
+
"eval_micro_recall": 0.9422222222222222,
|
| 102 |
+
"eval_runtime": 3.8881,
|
| 103 |
+
"eval_samples_per_second": 387.847,
|
| 104 |
+
"eval_steps_per_second": 12.345,
|
| 105 |
+
"eval_weighted_f1": 0.9418427294289362,
|
| 106 |
+
"eval_weighted_precision": 0.9445925925925925,
|
| 107 |
+
"eval_weighted_recall": 0.9422222222222222,
|
| 108 |
+
"step": 848
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.71,
|
| 112 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 113 |
+
"loss": 0.0562,
|
| 114 |
+
"step": 1000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 5.0,
|
| 118 |
+
"eval_accuracy": 0.9422222222222222,
|
| 119 |
+
"eval_jaccard": 0.8902276505022765,
|
| 120 |
+
"eval_loss": 0.5073122978210449,
|
| 121 |
+
"eval_macro_f1": 0.9407042510490785,
|
| 122 |
+
"eval_macro_precision": 0.9481481481481482,
|
| 123 |
+
"eval_macro_recall": 0.9365079365079365,
|
| 124 |
+
"eval_micro_f1": 0.9422222222222222,
|
| 125 |
+
"eval_micro_precision": 0.9422222222222222,
|
| 126 |
+
"eval_micro_recall": 0.9422222222222222,
|
| 127 |
+
"eval_runtime": 3.9083,
|
| 128 |
+
"eval_samples_per_second": 385.848,
|
| 129 |
+
"eval_steps_per_second": 12.282,
|
| 130 |
+
"eval_weighted_f1": 0.9418427294289362,
|
| 131 |
+
"eval_weighted_precision": 0.9445925925925925,
|
| 132 |
+
"eval_weighted_recall": 0.9422222222222222,
|
| 133 |
+
"step": 1060
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 5.66,
|
| 137 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 138 |
+
"loss": 0.0804,
|
| 139 |
+
"step": 1200
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 6.0,
|
| 143 |
+
"eval_accuracy": 0.96,
|
| 144 |
+
"eval_jaccard": 0.9233056148355289,
|
| 145 |
+
"eval_loss": 0.6428035497665405,
|
| 146 |
+
"eval_macro_f1": 0.9596814335490294,
|
| 147 |
+
"eval_macro_precision": 0.9580624702711273,
|
| 148 |
+
"eval_macro_recall": 0.9632034632034632,
|
| 149 |
+
"eval_micro_f1": 0.96,
|
| 150 |
+
"eval_micro_precision": 0.96,
|
| 151 |
+
"eval_micro_recall": 0.96,
|
| 152 |
+
"eval_runtime": 3.9157,
|
| 153 |
+
"eval_samples_per_second": 385.112,
|
| 154 |
+
"eval_steps_per_second": 12.258,
|
| 155 |
+
"eval_weighted_f1": 0.9601114982578397,
|
| 156 |
+
"eval_weighted_precision": 0.9620865704772475,
|
| 157 |
+
"eval_weighted_recall": 0.96,
|
| 158 |
+
"step": 1272
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 6.6,
|
| 162 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 163 |
+
"loss": 0.0179,
|
| 164 |
+
"step": 1400
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 7.0,
|
| 168 |
+
"eval_accuracy": 0.9555555555555556,
|
| 169 |
+
"eval_jaccard": 0.9148573109738158,
|
| 170 |
+
"eval_loss": 0.630973756313324,
|
| 171 |
+
"eval_macro_f1": 0.9548047565482886,
|
| 172 |
+
"eval_macro_precision": 0.9559439432989691,
|
| 173 |
+
"eval_macro_recall": 0.9538239538239539,
|
| 174 |
+
"eval_micro_f1": 0.9555555555555556,
|
| 175 |
+
"eval_micro_precision": 0.9555555555555556,
|
| 176 |
+
"eval_micro_recall": 0.9555555555555556,
|
| 177 |
+
"eval_runtime": 3.9129,
|
| 178 |
+
"eval_samples_per_second": 385.393,
|
| 179 |
+
"eval_steps_per_second": 12.267,
|
| 180 |
+
"eval_weighted_f1": 0.9555037763136751,
|
| 181 |
+
"eval_weighted_precision": 0.9556056701030928,
|
| 182 |
+
"eval_weighted_recall": 0.9555555555555556,
|
| 183 |
+
"step": 1484
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 7.55,
|
| 187 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 188 |
+
"loss": 0.0454,
|
| 189 |
+
"step": 1600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 8.0,
|
| 193 |
+
"eval_accuracy": 0.9644444444444444,
|
| 194 |
+
"eval_jaccard": 0.9312917227959886,
|
| 195 |
+
"eval_loss": 0.5245578289031982,
|
| 196 |
+
"eval_macro_f1": 0.9638438052386309,
|
| 197 |
+
"eval_macro_precision": 0.9650048324742269,
|
| 198 |
+
"eval_macro_recall": 0.9628427128427128,
|
| 199 |
+
"eval_micro_f1": 0.9644444444444444,
|
| 200 |
+
"eval_micro_precision": 0.9644444444444444,
|
| 201 |
+
"eval_micro_recall": 0.9644444444444444,
|
| 202 |
+
"eval_runtime": 3.9143,
|
| 203 |
+
"eval_samples_per_second": 385.257,
|
| 204 |
+
"eval_steps_per_second": 12.263,
|
| 205 |
+
"eval_weighted_f1": 0.9644030210509401,
|
| 206 |
+
"eval_weighted_precision": 0.9645167525773195,
|
| 207 |
+
"eval_weighted_recall": 0.9644444444444444,
|
| 208 |
+
"step": 1696
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 8.49,
|
| 212 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 213 |
+
"loss": 0.0276,
|
| 214 |
+
"step": 1800
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 9.0,
|
| 218 |
+
"eval_accuracy": 0.9511111111111111,
|
| 219 |
+
"eval_jaccard": 0.9064495782911624,
|
| 220 |
+
"eval_loss": 0.645963728427887,
|
| 221 |
+
"eval_macro_f1": 0.9499686672461541,
|
| 222 |
+
"eval_macro_precision": 0.9552958483164433,
|
| 223 |
+
"eval_macro_recall": 0.9466089466089466,
|
| 224 |
+
"eval_micro_f1": 0.9511111111111111,
|
| 225 |
+
"eval_micro_precision": 0.9511111111111111,
|
| 226 |
+
"eval_micro_recall": 0.9511111111111111,
|
| 227 |
+
"eval_runtime": 3.8963,
|
| 228 |
+
"eval_samples_per_second": 387.03,
|
| 229 |
+
"eval_steps_per_second": 12.319,
|
| 230 |
+
"eval_weighted_f1": 0.9508759020800905,
|
| 231 |
+
"eval_weighted_precision": 0.9525400457665903,
|
| 232 |
+
"eval_weighted_recall": 0.9511111111111111,
|
| 233 |
+
"step": 1908
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 9.43,
|
| 237 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 238 |
+
"loss": 0.0244,
|
| 239 |
+
"step": 2000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 10.0,
|
| 243 |
+
"eval_accuracy": 0.9688888888888889,
|
| 244 |
+
"eval_jaccard": 0.9395812863729122,
|
| 245 |
+
"eval_loss": 0.5576620697975159,
|
| 246 |
+
"eval_macro_f1": 0.9683257918552036,
|
| 247 |
+
"eval_macro_precision": 0.970203488372093,
|
| 248 |
+
"eval_macro_recall": 0.9668109668109668,
|
| 249 |
+
"eval_micro_f1": 0.9688888888888889,
|
| 250 |
+
"eval_micro_precision": 0.9688888888888889,
|
| 251 |
+
"eval_micro_recall": 0.9688888888888889,
|
| 252 |
+
"eval_runtime": 3.8888,
|
| 253 |
+
"eval_samples_per_second": 387.781,
|
| 254 |
+
"eval_steps_per_second": 12.343,
|
| 255 |
+
"eval_weighted_f1": 0.9688325791855203,
|
| 256 |
+
"eval_weighted_precision": 0.9691279069767442,
|
| 257 |
+
"eval_weighted_recall": 0.9688888888888889,
|
| 258 |
+
"step": 2120
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 10.38,
|
| 262 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 263 |
+
"loss": 0.0144,
|
| 264 |
+
"step": 2200
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 11.0,
|
| 268 |
+
"eval_accuracy": 0.9688888888888889,
|
| 269 |
+
"eval_jaccard": 0.9397094904794161,
|
| 270 |
+
"eval_loss": 0.6369400024414062,
|
| 271 |
+
"eval_macro_f1": 0.9684678371939377,
|
| 272 |
+
"eval_macro_precision": 0.968,
|
| 273 |
+
"eval_macro_recall": 0.968975468975469,
|
| 274 |
+
"eval_micro_f1": 0.9688888888888889,
|
| 275 |
+
"eval_micro_precision": 0.9688888888888889,
|
| 276 |
+
"eval_micro_recall": 0.9688888888888889,
|
| 277 |
+
"eval_runtime": 3.8878,
|
| 278 |
+
"eval_samples_per_second": 387.876,
|
| 279 |
+
"eval_steps_per_second": 12.346,
|
| 280 |
+
"eval_weighted_f1": 0.9689050831848484,
|
| 281 |
+
"eval_weighted_precision": 0.9689599999999999,
|
| 282 |
+
"eval_weighted_recall": 0.9688888888888889,
|
| 283 |
+
"step": 2332
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 11.32,
|
| 287 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 288 |
+
"loss": 0.0113,
|
| 289 |
+
"step": 2400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 12.0,
|
| 293 |
+
"eval_accuracy": 0.9688888888888889,
|
| 294 |
+
"eval_jaccard": 0.9395812863729122,
|
| 295 |
+
"eval_loss": 0.6348240971565247,
|
| 296 |
+
"eval_macro_f1": 0.9683257918552036,
|
| 297 |
+
"eval_macro_precision": 0.970203488372093,
|
| 298 |
+
"eval_macro_recall": 0.9668109668109668,
|
| 299 |
+
"eval_micro_f1": 0.9688888888888889,
|
| 300 |
+
"eval_micro_precision": 0.9688888888888889,
|
| 301 |
+
"eval_micro_recall": 0.9688888888888889,
|
| 302 |
+
"eval_runtime": 3.8915,
|
| 303 |
+
"eval_samples_per_second": 387.511,
|
| 304 |
+
"eval_steps_per_second": 12.335,
|
| 305 |
+
"eval_weighted_f1": 0.9688325791855203,
|
| 306 |
+
"eval_weighted_precision": 0.9691279069767442,
|
| 307 |
+
"eval_weighted_recall": 0.9688888888888889,
|
| 308 |
+
"step": 2544
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 12.26,
|
| 312 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 313 |
+
"loss": 0.017,
|
| 314 |
+
"step": 2600
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 13.0,
|
| 318 |
+
"eval_accuracy": 0.9333333333333333,
|
| 319 |
+
"eval_jaccard": 0.8737588652482269,
|
| 320 |
+
"eval_loss": 0.6715770363807678,
|
| 321 |
+
"eval_macro_f1": 0.9309265058021734,
|
| 322 |
+
"eval_macro_precision": 0.9468085106382979,
|
| 323 |
+
"eval_macro_recall": 0.9242424242424243,
|
| 324 |
+
"eval_micro_f1": 0.9333333333333333,
|
| 325 |
+
"eval_micro_precision": 0.9333333333333333,
|
| 326 |
+
"eval_micro_recall": 0.9333333333333333,
|
| 327 |
+
"eval_runtime": 3.8914,
|
| 328 |
+
"eval_samples_per_second": 387.517,
|
| 329 |
+
"eval_steps_per_second": 12.335,
|
| 330 |
+
"eval_weighted_f1": 0.9324737520722048,
|
| 331 |
+
"eval_weighted_precision": 0.9404255319148935,
|
| 332 |
+
"eval_weighted_recall": 0.9333333333333333,
|
| 333 |
+
"step": 2756
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 13.21,
|
| 337 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 338 |
+
"loss": 0.0162,
|
| 339 |
+
"step": 2800
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 14.0,
|
| 343 |
+
"eval_accuracy": 0.9555555555555556,
|
| 344 |
+
"eval_jaccard": 0.9146445987882369,
|
| 345 |
+
"eval_loss": 0.6302870512008667,
|
| 346 |
+
"eval_macro_f1": 0.954578488372093,
|
| 347 |
+
"eval_macro_precision": 0.9589442815249267,
|
| 348 |
+
"eval_macro_recall": 0.9516594516594516,
|
| 349 |
+
"eval_micro_f1": 0.9555555555555556,
|
| 350 |
+
"eval_micro_precision": 0.9555555555555556,
|
| 351 |
+
"eval_micro_recall": 0.9555555555555556,
|
| 352 |
+
"eval_runtime": 3.8937,
|
| 353 |
+
"eval_samples_per_second": 387.288,
|
| 354 |
+
"eval_steps_per_second": 12.327,
|
| 355 |
+
"eval_weighted_f1": 0.9553779069767442,
|
| 356 |
+
"eval_weighted_precision": 0.9565982404692083,
|
| 357 |
+
"eval_weighted_recall": 0.9555555555555556,
|
| 358 |
+
"step": 2968
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 14.15,
|
| 362 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 363 |
+
"loss": 0.0134,
|
| 364 |
+
"step": 3000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 15.0,
|
| 368 |
+
"eval_accuracy": 0.9822222222222222,
|
| 369 |
+
"eval_jaccard": 0.964991452991453,
|
| 370 |
+
"eval_loss": 0.6276100277900696,
|
| 371 |
+
"eval_macro_f1": 0.9818782216494845,
|
| 372 |
+
"eval_macro_precision": 0.9846153846153847,
|
| 373 |
+
"eval_macro_recall": 0.9797979797979798,
|
| 374 |
+
"eval_micro_f1": 0.9822222222222222,
|
| 375 |
+
"eval_micro_precision": 0.9822222222222222,
|
| 376 |
+
"eval_micro_recall": 0.9822222222222222,
|
| 377 |
+
"eval_runtime": 3.8919,
|
| 378 |
+
"eval_samples_per_second": 387.474,
|
| 379 |
+
"eval_steps_per_second": 12.333,
|
| 380 |
+
"eval_weighted_f1": 0.9821778350515463,
|
| 381 |
+
"eval_weighted_precision": 0.9827692307692307,
|
| 382 |
+
"eval_weighted_recall": 0.9822222222222222,
|
| 383 |
+
"step": 3180
|
| 384 |
+
}
|
| 385 |
+
],
|
| 386 |
+
"max_steps": 4240,
|
| 387 |
+
"num_train_epochs": 20,
|
| 388 |
+
"total_flos": 4.724653668328427e+16,
|
| 389 |
+
"trial_name": null,
|
| 390 |
+
"trial_params": {
|
| 391 |
+
"attention_probs_dropout_prob": 0.12254664017551167,
|
| 392 |
+
"gradient_accumulation_steps": 4,
|
| 393 |
+
"hidden_dropout_prob": 0.09767216663102402,
|
| 394 |
+
"learning_rate": 2.7172184226965135e-05,
|
| 395 |
+
"lr_scheduler_type": "constant",
|
| 396 |
+
"num_train_epochs": 20,
|
| 397 |
+
"per_device_train_batch_size": 16,
|
| 398 |
+
"weight_decay": 0.004770259527907836
|
| 399 |
+
}
|
| 400 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ab52a9c26c37fd87431c66d4e04ba39612e66e1e5418d2ba771a3825defbc8d
|
| 3 |
+
size 3579
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|