Commit
·
8f647d2
1
Parent(s):
371aab1
adding model finetuned on XNLI
Browse files- all_results.json +14 -0
- config.json +36 -0
- eval_results.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +625 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7730923694779116,
|
| 4 |
+
"eval_loss": 0.5570505857467651,
|
| 5 |
+
"eval_runtime": 0.7627,
|
| 6 |
+
"eval_samples": 2490,
|
| 7 |
+
"eval_samples_per_second": 3264.68,
|
| 8 |
+
"eval_steps_per_second": 102.267,
|
| 9 |
+
"train_loss": 0.5278426528443259,
|
| 10 |
+
"train_runtime": 4215.3344,
|
| 11 |
+
"train_samples": 392702,
|
| 12 |
+
"train_samples_per_second": 279.481,
|
| 13 |
+
"train_steps_per_second": 8.734
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "CenIA/distillbert-base-spanish-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"finetuning_task": "xnli",
|
| 11 |
+
"hidden_dim": 3072,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0,
|
| 20 |
+
"LABEL_1": 1,
|
| 21 |
+
"LABEL_2": 2
|
| 22 |
+
},
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "distilbert",
|
| 25 |
+
"n_heads": 12,
|
| 26 |
+
"n_layers": 6,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qa_dropout": 0.1,
|
| 30 |
+
"seq_classif_dropout": 0.2,
|
| 31 |
+
"sinusoidal_pos_embds": true,
|
| 32 |
+
"tie_weights_": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.12.5",
|
| 35 |
+
"vocab_size": 31002
|
| 36 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.7730923694779116,
|
| 4 |
+
"eval_loss": 0.5570505857467651,
|
| 5 |
+
"eval_runtime": 0.7627,
|
| 6 |
+
"eval_samples": 2490,
|
| 7 |
+
"eval_samples_per_second": 3264.68,
|
| 8 |
+
"eval_steps_per_second": 102.267
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdf0af97f00ec87b01344526e6341647aa2841b99c950f74fdb784929d8072b7
|
| 3 |
+
size 269337713
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "CenIA/distillbert-base-spanish-uncased", "tokenizer_class": "DistilBertTokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.5278426528443259,
|
| 4 |
+
"train_runtime": 4215.3344,
|
| 5 |
+
"train_samples": 392702,
|
| 6 |
+
"train_samples_per_second": 279.481,
|
| 7 |
+
"train_steps_per_second": 8.734
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,625 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5570505857467651,
|
| 3 |
+
"best_model_checkpoint": "/data/jcanete/all_results/xnli/distillbeto/epochs_3_bs_32_lr_5e-5/checkpoint-24000",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 36816,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 4.9323663624511086e-05,
|
| 13 |
+
"loss": 0.9001,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"learning_rate": 4.864461103867884e-05,
|
| 19 |
+
"loss": 0.8162,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.12,
|
| 24 |
+
"learning_rate": 4.7965558452846594e-05,
|
| 25 |
+
"loss": 0.7821,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.16,
|
| 30 |
+
"learning_rate": 4.728650586701434e-05,
|
| 31 |
+
"loss": 0.742,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.16,
|
| 36 |
+
"eval_accuracy": 0.7164658634538152,
|
| 37 |
+
"eval_loss": 0.689033567905426,
|
| 38 |
+
"eval_runtime": 0.7191,
|
| 39 |
+
"eval_samples_per_second": 3462.677,
|
| 40 |
+
"eval_steps_per_second": 108.469,
|
| 41 |
+
"step": 2000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.2,
|
| 45 |
+
"learning_rate": 4.660881138635376e-05,
|
| 46 |
+
"loss": 0.7456,
|
| 47 |
+
"step": 2500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.24,
|
| 51 |
+
"learning_rate": 4.5929758800521515e-05,
|
| 52 |
+
"loss": 0.7257,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.29,
|
| 57 |
+
"learning_rate": 4.525070621468927e-05,
|
| 58 |
+
"loss": 0.7183,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.33,
|
| 63 |
+
"learning_rate": 4.4571653628857017e-05,
|
| 64 |
+
"loss": 0.6993,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.33,
|
| 69 |
+
"eval_accuracy": 0.7176706827309237,
|
| 70 |
+
"eval_loss": 0.6759888529777527,
|
| 71 |
+
"eval_runtime": 0.7171,
|
| 72 |
+
"eval_samples_per_second": 3472.257,
|
| 73 |
+
"eval_steps_per_second": 108.77,
|
| 74 |
+
"step": 4000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.37,
|
| 78 |
+
"learning_rate": 4.389260104302477e-05,
|
| 79 |
+
"loss": 0.6877,
|
| 80 |
+
"step": 4500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.41,
|
| 84 |
+
"learning_rate": 4.3214906562364196e-05,
|
| 85 |
+
"loss": 0.6886,
|
| 86 |
+
"step": 5000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.45,
|
| 90 |
+
"learning_rate": 4.2535853976531944e-05,
|
| 91 |
+
"loss": 0.6822,
|
| 92 |
+
"step": 5500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.49,
|
| 96 |
+
"learning_rate": 4.18568013906997e-05,
|
| 97 |
+
"loss": 0.6738,
|
| 98 |
+
"step": 6000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.49,
|
| 102 |
+
"eval_accuracy": 0.7369477911646586,
|
| 103 |
+
"eval_loss": 0.6459766030311584,
|
| 104 |
+
"eval_runtime": 0.714,
|
| 105 |
+
"eval_samples_per_second": 3487.194,
|
| 106 |
+
"eval_steps_per_second": 109.237,
|
| 107 |
+
"step": 6000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.53,
|
| 111 |
+
"learning_rate": 4.117774880486745e-05,
|
| 112 |
+
"loss": 0.6721,
|
| 113 |
+
"step": 6500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.57,
|
| 117 |
+
"learning_rate": 4.049869621903521e-05,
|
| 118 |
+
"loss": 0.6681,
|
| 119 |
+
"step": 7000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.61,
|
| 123 |
+
"learning_rate": 3.981964363320296e-05,
|
| 124 |
+
"loss": 0.6638,
|
| 125 |
+
"step": 7500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.65,
|
| 129 |
+
"learning_rate": 3.914059104737071e-05,
|
| 130 |
+
"loss": 0.6511,
|
| 131 |
+
"step": 8000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.65,
|
| 135 |
+
"eval_accuracy": 0.7421686746987952,
|
| 136 |
+
"eval_loss": 0.6142069101333618,
|
| 137 |
+
"eval_runtime": 0.7168,
|
| 138 |
+
"eval_samples_per_second": 3473.794,
|
| 139 |
+
"eval_steps_per_second": 108.818,
|
| 140 |
+
"step": 8000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.69,
|
| 144 |
+
"learning_rate": 3.846153846153846e-05,
|
| 145 |
+
"loss": 0.6498,
|
| 146 |
+
"step": 8500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.73,
|
| 150 |
+
"learning_rate": 3.778384398087788e-05,
|
| 151 |
+
"loss": 0.6465,
|
| 152 |
+
"step": 9000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.77,
|
| 156 |
+
"learning_rate": 3.7106149500217294e-05,
|
| 157 |
+
"loss": 0.6422,
|
| 158 |
+
"step": 9500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.81,
|
| 162 |
+
"learning_rate": 3.642709691438505e-05,
|
| 163 |
+
"loss": 0.6377,
|
| 164 |
+
"step": 10000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.81,
|
| 168 |
+
"eval_accuracy": 0.736144578313253,
|
| 169 |
+
"eval_loss": 0.6204584240913391,
|
| 170 |
+
"eval_runtime": 0.7121,
|
| 171 |
+
"eval_samples_per_second": 3496.5,
|
| 172 |
+
"eval_steps_per_second": 109.529,
|
| 173 |
+
"step": 10000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.86,
|
| 177 |
+
"learning_rate": 3.57480443285528e-05,
|
| 178 |
+
"loss": 0.6408,
|
| 179 |
+
"step": 10500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.9,
|
| 183 |
+
"learning_rate": 3.5068991742720556e-05,
|
| 184 |
+
"loss": 0.6316,
|
| 185 |
+
"step": 11000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.94,
|
| 189 |
+
"learning_rate": 3.438993915688831e-05,
|
| 190 |
+
"loss": 0.6274,
|
| 191 |
+
"step": 11500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.98,
|
| 195 |
+
"learning_rate": 3.371224467622773e-05,
|
| 196 |
+
"loss": 0.6332,
|
| 197 |
+
"step": 12000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.98,
|
| 201 |
+
"eval_accuracy": 0.7602409638554217,
|
| 202 |
+
"eval_loss": 0.583670437335968,
|
| 203 |
+
"eval_runtime": 0.7748,
|
| 204 |
+
"eval_samples_per_second": 3213.841,
|
| 205 |
+
"eval_steps_per_second": 100.675,
|
| 206 |
+
"step": 12000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.02,
|
| 210 |
+
"learning_rate": 3.3033192090395484e-05,
|
| 211 |
+
"loss": 0.5784,
|
| 212 |
+
"step": 12500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.06,
|
| 216 |
+
"learning_rate": 3.235413950456324e-05,
|
| 217 |
+
"loss": 0.5255,
|
| 218 |
+
"step": 13000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.1,
|
| 222 |
+
"learning_rate": 3.167508691873099e-05,
|
| 223 |
+
"loss": 0.5146,
|
| 224 |
+
"step": 13500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.14,
|
| 228 |
+
"learning_rate": 3.0997392438070404e-05,
|
| 229 |
+
"loss": 0.5279,
|
| 230 |
+
"step": 14000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.14,
|
| 234 |
+
"eval_accuracy": 0.7594377510040161,
|
| 235 |
+
"eval_loss": 0.5976436138153076,
|
| 236 |
+
"eval_runtime": 0.7087,
|
| 237 |
+
"eval_samples_per_second": 3513.652,
|
| 238 |
+
"eval_steps_per_second": 110.066,
|
| 239 |
+
"step": 14000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.18,
|
| 243 |
+
"learning_rate": 3.031833985223816e-05,
|
| 244 |
+
"loss": 0.5312,
|
| 245 |
+
"step": 14500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.22,
|
| 249 |
+
"learning_rate": 2.9639287266405913e-05,
|
| 250 |
+
"loss": 0.5353,
|
| 251 |
+
"step": 15000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.26,
|
| 255 |
+
"learning_rate": 2.8960234680573667e-05,
|
| 256 |
+
"loss": 0.5151,
|
| 257 |
+
"step": 15500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.3,
|
| 261 |
+
"learning_rate": 2.828118209474142e-05,
|
| 262 |
+
"loss": 0.516,
|
| 263 |
+
"step": 16000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.3,
|
| 267 |
+
"eval_accuracy": 0.7686746987951807,
|
| 268 |
+
"eval_loss": 0.5902267098426819,
|
| 269 |
+
"eval_runtime": 0.7185,
|
| 270 |
+
"eval_samples_per_second": 3465.794,
|
| 271 |
+
"eval_steps_per_second": 108.567,
|
| 272 |
+
"step": 16000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.34,
|
| 276 |
+
"learning_rate": 2.7603487614080837e-05,
|
| 277 |
+
"loss": 0.5146,
|
| 278 |
+
"step": 16500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.39,
|
| 282 |
+
"learning_rate": 2.692443502824859e-05,
|
| 283 |
+
"loss": 0.5205,
|
| 284 |
+
"step": 17000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.43,
|
| 288 |
+
"learning_rate": 2.6245382442416345e-05,
|
| 289 |
+
"loss": 0.5209,
|
| 290 |
+
"step": 17500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.47,
|
| 294 |
+
"learning_rate": 2.5566329856584093e-05,
|
| 295 |
+
"loss": 0.5072,
|
| 296 |
+
"step": 18000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.47,
|
| 300 |
+
"eval_accuracy": 0.7622489959839357,
|
| 301 |
+
"eval_loss": 0.6036831736564636,
|
| 302 |
+
"eval_runtime": 0.7061,
|
| 303 |
+
"eval_samples_per_second": 3526.558,
|
| 304 |
+
"eval_steps_per_second": 110.47,
|
| 305 |
+
"step": 18000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.51,
|
| 309 |
+
"learning_rate": 2.488727727075185e-05,
|
| 310 |
+
"loss": 0.5105,
|
| 311 |
+
"step": 18500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.55,
|
| 315 |
+
"learning_rate": 2.4209582790091266e-05,
|
| 316 |
+
"loss": 0.5132,
|
| 317 |
+
"step": 19000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.59,
|
| 321 |
+
"learning_rate": 2.353053020425902e-05,
|
| 322 |
+
"loss": 0.5149,
|
| 323 |
+
"step": 19500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.63,
|
| 327 |
+
"learning_rate": 2.285147761842677e-05,
|
| 328 |
+
"loss": 0.5144,
|
| 329 |
+
"step": 20000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.63,
|
| 333 |
+
"eval_accuracy": 0.7622489959839357,
|
| 334 |
+
"eval_loss": 0.5975185632705688,
|
| 335 |
+
"eval_runtime": 0.7116,
|
| 336 |
+
"eval_samples_per_second": 3499.181,
|
| 337 |
+
"eval_steps_per_second": 109.613,
|
| 338 |
+
"step": 20000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.67,
|
| 342 |
+
"learning_rate": 2.2172425032594525e-05,
|
| 343 |
+
"loss": 0.5161,
|
| 344 |
+
"step": 20500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.71,
|
| 348 |
+
"learning_rate": 2.1493372446762276e-05,
|
| 349 |
+
"loss": 0.5122,
|
| 350 |
+
"step": 21000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.75,
|
| 354 |
+
"learning_rate": 2.081431986093003e-05,
|
| 355 |
+
"loss": 0.5052,
|
| 356 |
+
"step": 21500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.79,
|
| 360 |
+
"learning_rate": 2.0135267275097785e-05,
|
| 361 |
+
"loss": 0.502,
|
| 362 |
+
"step": 22000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.79,
|
| 366 |
+
"eval_accuracy": 0.7803212851405622,
|
| 367 |
+
"eval_loss": 0.5712254047393799,
|
| 368 |
+
"eval_runtime": 0.712,
|
| 369 |
+
"eval_samples_per_second": 3497.159,
|
| 370 |
+
"eval_steps_per_second": 109.55,
|
| 371 |
+
"step": 22000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.83,
|
| 375 |
+
"learning_rate": 1.94575727944372e-05,
|
| 376 |
+
"loss": 0.5084,
|
| 377 |
+
"step": 22500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.87,
|
| 381 |
+
"learning_rate": 1.8778520208604955e-05,
|
| 382 |
+
"loss": 0.5006,
|
| 383 |
+
"step": 23000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.91,
|
| 387 |
+
"learning_rate": 1.809946762277271e-05,
|
| 388 |
+
"loss": 0.498,
|
| 389 |
+
"step": 23500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.96,
|
| 393 |
+
"learning_rate": 1.7420415036940463e-05,
|
| 394 |
+
"loss": 0.4975,
|
| 395 |
+
"step": 24000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.96,
|
| 399 |
+
"eval_accuracy": 0.7730923694779116,
|
| 400 |
+
"eval_loss": 0.5570505857467651,
|
| 401 |
+
"eval_runtime": 0.7086,
|
| 402 |
+
"eval_samples_per_second": 3514.146,
|
| 403 |
+
"eval_steps_per_second": 110.082,
|
| 404 |
+
"step": 24000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.0,
|
| 408 |
+
"learning_rate": 1.6741362451108214e-05,
|
| 409 |
+
"loss": 0.506,
|
| 410 |
+
"step": 24500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.04,
|
| 414 |
+
"learning_rate": 1.6063667970447633e-05,
|
| 415 |
+
"loss": 0.4089,
|
| 416 |
+
"step": 25000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.08,
|
| 420 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 421 |
+
"loss": 0.3805,
|
| 422 |
+
"step": 25500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.12,
|
| 426 |
+
"learning_rate": 1.4705562798783138e-05,
|
| 427 |
+
"loss": 0.3925,
|
| 428 |
+
"step": 26000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.12,
|
| 432 |
+
"eval_accuracy": 0.7698795180722892,
|
| 433 |
+
"eval_loss": 0.6058809161186218,
|
| 434 |
+
"eval_runtime": 0.7123,
|
| 435 |
+
"eval_samples_per_second": 3495.574,
|
| 436 |
+
"eval_steps_per_second": 109.5,
|
| 437 |
+
"step": 26000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.16,
|
| 441 |
+
"learning_rate": 1.402651021295089e-05,
|
| 442 |
+
"loss": 0.3711,
|
| 443 |
+
"step": 26500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.2,
|
| 447 |
+
"learning_rate": 1.3347457627118645e-05,
|
| 448 |
+
"loss": 0.3735,
|
| 449 |
+
"step": 27000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.24,
|
| 453 |
+
"learning_rate": 1.2669763146458064e-05,
|
| 454 |
+
"loss": 0.3843,
|
| 455 |
+
"step": 27500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.28,
|
| 459 |
+
"learning_rate": 1.1990710560625816e-05,
|
| 460 |
+
"loss": 0.3771,
|
| 461 |
+
"step": 28000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.28,
|
| 465 |
+
"eval_accuracy": 0.7746987951807229,
|
| 466 |
+
"eval_loss": 0.6026178598403931,
|
| 467 |
+
"eval_runtime": 0.7183,
|
| 468 |
+
"eval_samples_per_second": 3466.55,
|
| 469 |
+
"eval_steps_per_second": 108.591,
|
| 470 |
+
"step": 28000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.32,
|
| 474 |
+
"learning_rate": 1.1311657974793569e-05,
|
| 475 |
+
"loss": 0.3781,
|
| 476 |
+
"step": 28500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.36,
|
| 480 |
+
"learning_rate": 1.0632605388961322e-05,
|
| 481 |
+
"loss": 0.3877,
|
| 482 |
+
"step": 29000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.4,
|
| 486 |
+
"learning_rate": 9.95491090830074e-06,
|
| 487 |
+
"loss": 0.3759,
|
| 488 |
+
"step": 29500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.44,
|
| 492 |
+
"learning_rate": 9.275858322468491e-06,
|
| 493 |
+
"loss": 0.3784,
|
| 494 |
+
"step": 30000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.44,
|
| 498 |
+
"eval_accuracy": 0.7855421686746988,
|
| 499 |
+
"eval_loss": 0.6055970788002014,
|
| 500 |
+
"eval_runtime": 0.7082,
|
| 501 |
+
"eval_samples_per_second": 3516.156,
|
| 502 |
+
"eval_steps_per_second": 110.145,
|
| 503 |
+
"step": 30000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.49,
|
| 507 |
+
"learning_rate": 8.596805736636245e-06,
|
| 508 |
+
"loss": 0.3774,
|
| 509 |
+
"step": 30500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.53,
|
| 513 |
+
"learning_rate": 7.917753150803998e-06,
|
| 514 |
+
"loss": 0.3783,
|
| 515 |
+
"step": 31000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.57,
|
| 519 |
+
"learning_rate": 7.240058670143417e-06,
|
| 520 |
+
"loss": 0.3732,
|
| 521 |
+
"step": 31500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.61,
|
| 525 |
+
"learning_rate": 6.561006084311169e-06,
|
| 526 |
+
"loss": 0.3863,
|
| 527 |
+
"step": 32000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.61,
|
| 531 |
+
"eval_accuracy": 0.7742971887550201,
|
| 532 |
+
"eval_loss": 0.5977765321731567,
|
| 533 |
+
"eval_runtime": 0.7194,
|
| 534 |
+
"eval_samples_per_second": 3461.392,
|
| 535 |
+
"eval_steps_per_second": 108.429,
|
| 536 |
+
"step": 32000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.65,
|
| 540 |
+
"learning_rate": 5.881953498478923e-06,
|
| 541 |
+
"loss": 0.3817,
|
| 542 |
+
"step": 32500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.69,
|
| 546 |
+
"learning_rate": 5.2029009126466755e-06,
|
| 547 |
+
"loss": 0.3748,
|
| 548 |
+
"step": 33000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.73,
|
| 552 |
+
"learning_rate": 4.525206431986093e-06,
|
| 553 |
+
"loss": 0.3746,
|
| 554 |
+
"step": 33500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.77,
|
| 558 |
+
"learning_rate": 3.846153846153847e-06,
|
| 559 |
+
"loss": 0.377,
|
| 560 |
+
"step": 34000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.77,
|
| 564 |
+
"eval_accuracy": 0.7755020080321285,
|
| 565 |
+
"eval_loss": 0.6021597385406494,
|
| 566 |
+
"eval_runtime": 0.71,
|
| 567 |
+
"eval_samples_per_second": 3507.063,
|
| 568 |
+
"eval_steps_per_second": 109.86,
|
| 569 |
+
"step": 34000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.81,
|
| 573 |
+
"learning_rate": 3.1671012603216e-06,
|
| 574 |
+
"loss": 0.3745,
|
| 575 |
+
"step": 34500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.85,
|
| 579 |
+
"learning_rate": 2.488048674489353e-06,
|
| 580 |
+
"loss": 0.3798,
|
| 581 |
+
"step": 35000
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.89,
|
| 585 |
+
"learning_rate": 1.8089960886571057e-06,
|
| 586 |
+
"loss": 0.3751,
|
| 587 |
+
"step": 35500
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 2.93,
|
| 591 |
+
"learning_rate": 1.1313016079965233e-06,
|
| 592 |
+
"loss": 0.3602,
|
| 593 |
+
"step": 36000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.93,
|
| 597 |
+
"eval_accuracy": 0.7742971887550201,
|
| 598 |
+
"eval_loss": 0.6019901633262634,
|
| 599 |
+
"eval_runtime": 0.7094,
|
| 600 |
+
"eval_samples_per_second": 3510.147,
|
| 601 |
+
"eval_steps_per_second": 109.956,
|
| 602 |
+
"step": 36000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.97,
|
| 606 |
+
"learning_rate": 4.522490221642764e-07,
|
| 607 |
+
"loss": 0.3712,
|
| 608 |
+
"step": 36500
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.0,
|
| 612 |
+
"step": 36816,
|
| 613 |
+
"total_flos": 2.996060719687747e+16,
|
| 614 |
+
"train_loss": 0.5278426528443259,
|
| 615 |
+
"train_runtime": 4215.3344,
|
| 616 |
+
"train_samples_per_second": 279.481,
|
| 617 |
+
"train_steps_per_second": 8.734
|
| 618 |
+
}
|
| 619 |
+
],
|
| 620 |
+
"max_steps": 36816,
|
| 621 |
+
"num_train_epochs": 3,
|
| 622 |
+
"total_flos": 2.996060719687747e+16,
|
| 623 |
+
"trial_name": null,
|
| 624 |
+
"trial_params": null
|
| 625 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:655e14be0ce5c2ee8212353c69a7d51621c2ef42be6247e3a3fc9c0b49baf52c
|
| 3 |
+
size 2863
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|