Upload 7 files
Browse files- config.json +33 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- trainer_state.json +1036 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "NEGATIVE",
|
| 13 |
+
"1": "POSITIVE"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"NEGATIVE": 0,
|
| 18 |
+
"POSITIVE": 1
|
| 19 |
+
},
|
| 20 |
+
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "distilbert",
|
| 22 |
+
"n_heads": 12,
|
| 23 |
+
"n_layers": 6,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"problem_type": "single_label_classification",
|
| 26 |
+
"qa_dropout": 0.1,
|
| 27 |
+
"seq_classif_dropout": 0.2,
|
| 28 |
+
"sinusoidal_pos_embds": false,
|
| 29 |
+
"tie_weights_": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.28.1",
|
| 32 |
+
"vocab_size": 30522
|
| 33 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5953f81e3a65d865ba17b3722fefc988408cbb0cff88779e5a5eb813dc12c26
|
| 3 |
+
size 267855533
|
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 12 |
+
"unk_token": "[UNK]"
|
| 13 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1036 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5703100562095642,
|
| 3 |
+
"best_model_checkpoint": "my_awesome_model/checkpoint-10000",
|
| 4 |
+
"epoch": 0.9983028850953379,
|
| 5 |
+
"global_step": 10000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"eval_accuracy": 0.5599324704558244,
|
| 13 |
+
"eval_loss": 0.6817283630371094,
|
| 14 |
+
"eval_runtime": 87.555,
|
| 15 |
+
"eval_samples_per_second": 385.621,
|
| 16 |
+
"eval_steps_per_second": 24.111,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02,
|
| 21 |
+
"eval_accuracy": 0.6039155288333383,
|
| 22 |
+
"eval_loss": 0.6646063923835754,
|
| 23 |
+
"eval_runtime": 98.0865,
|
| 24 |
+
"eval_samples_per_second": 344.217,
|
| 25 |
+
"eval_steps_per_second": 21.522,
|
| 26 |
+
"step": 200
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.03,
|
| 30 |
+
"eval_accuracy": 0.6300684180908095,
|
| 31 |
+
"eval_loss": 0.6491487622261047,
|
| 32 |
+
"eval_runtime": 112.999,
|
| 33 |
+
"eval_samples_per_second": 298.79,
|
| 34 |
+
"eval_steps_per_second": 18.682,
|
| 35 |
+
"step": 300
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.04,
|
| 39 |
+
"eval_accuracy": 0.5918609128335752,
|
| 40 |
+
"eval_loss": 0.6735296249389648,
|
| 41 |
+
"eval_runtime": 122.3302,
|
| 42 |
+
"eval_samples_per_second": 275.999,
|
| 43 |
+
"eval_steps_per_second": 17.257,
|
| 44 |
+
"step": 400
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.05,
|
| 48 |
+
"learning_rate": 1.9001697114904664e-05,
|
| 49 |
+
"loss": 0.6666,
|
| 50 |
+
"step": 500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.05,
|
| 54 |
+
"eval_accuracy": 0.6279951426117347,
|
| 55 |
+
"eval_loss": 0.6454014778137207,
|
| 56 |
+
"eval_runtime": 125.5195,
|
| 57 |
+
"eval_samples_per_second": 268.986,
|
| 58 |
+
"eval_steps_per_second": 16.818,
|
| 59 |
+
"step": 500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06,
|
| 63 |
+
"eval_accuracy": 0.6282024701596423,
|
| 64 |
+
"eval_loss": 0.643072247505188,
|
| 65 |
+
"eval_runtime": 134.8724,
|
| 66 |
+
"eval_samples_per_second": 250.333,
|
| 67 |
+
"eval_steps_per_second": 15.652,
|
| 68 |
+
"step": 600
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.07,
|
| 72 |
+
"eval_accuracy": 0.6378283920267749,
|
| 73 |
+
"eval_loss": 0.6360176205635071,
|
| 74 |
+
"eval_runtime": 135.5933,
|
| 75 |
+
"eval_samples_per_second": 249.002,
|
| 76 |
+
"eval_steps_per_second": 15.569,
|
| 77 |
+
"step": 700
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.08,
|
| 81 |
+
"eval_accuracy": 0.6515120101886681,
|
| 82 |
+
"eval_loss": 0.6259913444519043,
|
| 83 |
+
"eval_runtime": 135.7915,
|
| 84 |
+
"eval_samples_per_second": 248.639,
|
| 85 |
+
"eval_steps_per_second": 15.546,
|
| 86 |
+
"step": 800
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.09,
|
| 90 |
+
"eval_accuracy": 0.6522524657169091,
|
| 91 |
+
"eval_loss": 0.6238675713539124,
|
| 92 |
+
"eval_runtime": 145.4218,
|
| 93 |
+
"eval_samples_per_second": 232.173,
|
| 94 |
+
"eval_steps_per_second": 14.516,
|
| 95 |
+
"step": 900
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.1,
|
| 99 |
+
"learning_rate": 1.8003394229809327e-05,
|
| 100 |
+
"loss": 0.6365,
|
| 101 |
+
"step": 1000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.1,
|
| 105 |
+
"eval_accuracy": 0.6556881793679472,
|
| 106 |
+
"eval_loss": 0.6250938177108765,
|
| 107 |
+
"eval_runtime": 142.1467,
|
| 108 |
+
"eval_samples_per_second": 237.522,
|
| 109 |
+
"eval_steps_per_second": 14.851,
|
| 110 |
+
"step": 1000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.11,
|
| 114 |
+
"eval_accuracy": 0.6417676154370169,
|
| 115 |
+
"eval_loss": 0.6320825815200806,
|
| 116 |
+
"eval_runtime": 144.5395,
|
| 117 |
+
"eval_samples_per_second": 233.59,
|
| 118 |
+
"eval_steps_per_second": 14.605,
|
| 119 |
+
"step": 1100
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.12,
|
| 123 |
+
"eval_accuracy": 0.656517489559577,
|
| 124 |
+
"eval_loss": 0.6173945665359497,
|
| 125 |
+
"eval_runtime": 145.4484,
|
| 126 |
+
"eval_samples_per_second": 232.13,
|
| 127 |
+
"eval_steps_per_second": 14.514,
|
| 128 |
+
"step": 1200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.13,
|
| 132 |
+
"eval_accuracy": 0.6573171815300773,
|
| 133 |
+
"eval_loss": 0.6152162551879883,
|
| 134 |
+
"eval_runtime": 148.4944,
|
| 135 |
+
"eval_samples_per_second": 227.369,
|
| 136 |
+
"eval_steps_per_second": 14.216,
|
| 137 |
+
"step": 1300
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.14,
|
| 141 |
+
"eval_accuracy": 0.6613156413825786,
|
| 142 |
+
"eval_loss": 0.6118360757827759,
|
| 143 |
+
"eval_runtime": 147.9224,
|
| 144 |
+
"eval_samples_per_second": 228.248,
|
| 145 |
+
"eval_steps_per_second": 14.271,
|
| 146 |
+
"step": 1400
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.15,
|
| 150 |
+
"learning_rate": 1.700509134471399e-05,
|
| 151 |
+
"loss": 0.6256,
|
| 152 |
+
"step": 1500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.15,
|
| 156 |
+
"eval_accuracy": 0.6628557888813198,
|
| 157 |
+
"eval_loss": 0.6129273176193237,
|
| 158 |
+
"eval_runtime": 144.8646,
|
| 159 |
+
"eval_samples_per_second": 233.066,
|
| 160 |
+
"eval_steps_per_second": 14.572,
|
| 161 |
+
"step": 1500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.16,
|
| 165 |
+
"eval_accuracy": 0.6606048040754672,
|
| 166 |
+
"eval_loss": 0.6123291254043579,
|
| 167 |
+
"eval_runtime": 147.7984,
|
| 168 |
+
"eval_samples_per_second": 228.44,
|
| 169 |
+
"eval_steps_per_second": 14.283,
|
| 170 |
+
"step": 1600
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.17,
|
| 174 |
+
"eval_accuracy": 0.6520451381690016,
|
| 175 |
+
"eval_loss": 0.6141842603683472,
|
| 176 |
+
"eval_runtime": 146.6547,
|
| 177 |
+
"eval_samples_per_second": 230.221,
|
| 178 |
+
"eval_steps_per_second": 14.394,
|
| 179 |
+
"step": 1700
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.18,
|
| 183 |
+
"eval_accuracy": 0.6619968604685602,
|
| 184 |
+
"eval_loss": 0.6088994145393372,
|
| 185 |
+
"eval_runtime": 144.5506,
|
| 186 |
+
"eval_samples_per_second": 233.572,
|
| 187 |
+
"eval_steps_per_second": 14.604,
|
| 188 |
+
"step": 1800
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.19,
|
| 192 |
+
"eval_accuracy": 0.6693125610875811,
|
| 193 |
+
"eval_loss": 0.6045596599578857,
|
| 194 |
+
"eval_runtime": 149.624,
|
| 195 |
+
"eval_samples_per_second": 225.652,
|
| 196 |
+
"eval_steps_per_second": 14.109,
|
| 197 |
+
"step": 1900
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.2,
|
| 201 |
+
"learning_rate": 1.600678845961865e-05,
|
| 202 |
+
"loss": 0.6206,
|
| 203 |
+
"step": 2000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.2,
|
| 207 |
+
"eval_accuracy": 0.6670911945028581,
|
| 208 |
+
"eval_loss": 0.6107525825500488,
|
| 209 |
+
"eval_runtime": 150.716,
|
| 210 |
+
"eval_samples_per_second": 224.017,
|
| 211 |
+
"eval_steps_per_second": 14.006,
|
| 212 |
+
"step": 2000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.21,
|
| 216 |
+
"eval_accuracy": 0.6699937801735628,
|
| 217 |
+
"eval_loss": 0.6015494465827942,
|
| 218 |
+
"eval_runtime": 145.7183,
|
| 219 |
+
"eval_samples_per_second": 231.7,
|
| 220 |
+
"eval_steps_per_second": 14.487,
|
| 221 |
+
"step": 2100
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.22,
|
| 225 |
+
"eval_accuracy": 0.67514735065012,
|
| 226 |
+
"eval_loss": 0.6029151678085327,
|
| 227 |
+
"eval_runtime": 146.7946,
|
| 228 |
+
"eval_samples_per_second": 230.002,
|
| 229 |
+
"eval_steps_per_second": 14.381,
|
| 230 |
+
"step": 2200
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.23,
|
| 234 |
+
"eval_accuracy": 0.6646032639279685,
|
| 235 |
+
"eval_loss": 0.611104428768158,
|
| 236 |
+
"eval_runtime": 148.7299,
|
| 237 |
+
"eval_samples_per_second": 227.009,
|
| 238 |
+
"eval_steps_per_second": 14.194,
|
| 239 |
+
"step": 2300
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.24,
|
| 243 |
+
"eval_accuracy": 0.6710304179131001,
|
| 244 |
+
"eval_loss": 0.598213791847229,
|
| 245 |
+
"eval_runtime": 148.4521,
|
| 246 |
+
"eval_samples_per_second": 227.434,
|
| 247 |
+
"eval_steps_per_second": 14.22,
|
| 248 |
+
"step": 2400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.25,
|
| 252 |
+
"learning_rate": 1.5008485574523313e-05,
|
| 253 |
+
"loss": 0.611,
|
| 254 |
+
"step": 2500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.25,
|
| 258 |
+
"eval_accuracy": 0.666528448301395,
|
| 259 |
+
"eval_loss": 0.6279574632644653,
|
| 260 |
+
"eval_runtime": 146.8286,
|
| 261 |
+
"eval_samples_per_second": 229.948,
|
| 262 |
+
"eval_steps_per_second": 14.377,
|
| 263 |
+
"step": 2500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.26,
|
| 267 |
+
"eval_accuracy": 0.6672392856085063,
|
| 268 |
+
"eval_loss": 0.607886791229248,
|
| 269 |
+
"eval_runtime": 152.0709,
|
| 270 |
+
"eval_samples_per_second": 222.021,
|
| 271 |
+
"eval_steps_per_second": 13.882,
|
| 272 |
+
"step": 2600
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.27,
|
| 276 |
+
"eval_accuracy": 0.67185972810473,
|
| 277 |
+
"eval_loss": 0.5957935452461243,
|
| 278 |
+
"eval_runtime": 151.6655,
|
| 279 |
+
"eval_samples_per_second": 222.615,
|
| 280 |
+
"eval_steps_per_second": 13.919,
|
| 281 |
+
"step": 2700
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.28,
|
| 285 |
+
"eval_accuracy": 0.6712377454610076,
|
| 286 |
+
"eval_loss": 0.6077716946601868,
|
| 287 |
+
"eval_runtime": 153.1917,
|
| 288 |
+
"eval_samples_per_second": 220.397,
|
| 289 |
+
"eval_steps_per_second": 13.78,
|
| 290 |
+
"step": 2800
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.29,
|
| 294 |
+
"eval_accuracy": 0.6713858365666558,
|
| 295 |
+
"eval_loss": 0.5977779626846313,
|
| 296 |
+
"eval_runtime": 148.182,
|
| 297 |
+
"eval_samples_per_second": 227.848,
|
| 298 |
+
"eval_steps_per_second": 14.246,
|
| 299 |
+
"step": 2900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.3,
|
| 303 |
+
"learning_rate": 1.4010182689427974e-05,
|
| 304 |
+
"loss": 0.6131,
|
| 305 |
+
"step": 3000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.3,
|
| 309 |
+
"eval_accuracy": 0.6731333116133045,
|
| 310 |
+
"eval_loss": 0.5991169810295105,
|
| 311 |
+
"eval_runtime": 148.2187,
|
| 312 |
+
"eval_samples_per_second": 227.792,
|
| 313 |
+
"eval_steps_per_second": 14.242,
|
| 314 |
+
"step": 3000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.31,
|
| 318 |
+
"eval_accuracy": 0.6711785090187483,
|
| 319 |
+
"eval_loss": 0.6033596396446228,
|
| 320 |
+
"eval_runtime": 147.6774,
|
| 321 |
+
"eval_samples_per_second": 228.627,
|
| 322 |
+
"eval_steps_per_second": 14.295,
|
| 323 |
+
"step": 3100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.32,
|
| 327 |
+
"eval_accuracy": 0.6733110209400823,
|
| 328 |
+
"eval_loss": 0.5941784977912903,
|
| 329 |
+
"eval_runtime": 146.1758,
|
| 330 |
+
"eval_samples_per_second": 230.975,
|
| 331 |
+
"eval_steps_per_second": 14.442,
|
| 332 |
+
"step": 3200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.33,
|
| 336 |
+
"eval_accuracy": 0.6770132985812872,
|
| 337 |
+
"eval_loss": 0.5986897945404053,
|
| 338 |
+
"eval_runtime": 132.6551,
|
| 339 |
+
"eval_samples_per_second": 254.517,
|
| 340 |
+
"eval_steps_per_second": 15.913,
|
| 341 |
+
"step": 3300
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.34,
|
| 345 |
+
"eval_accuracy": 0.6789681011758434,
|
| 346 |
+
"eval_loss": 0.5917928218841553,
|
| 347 |
+
"eval_runtime": 126.761,
|
| 348 |
+
"eval_samples_per_second": 266.352,
|
| 349 |
+
"eval_steps_per_second": 16.653,
|
| 350 |
+
"step": 3400
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.35,
|
| 354 |
+
"learning_rate": 1.3011879804332637e-05,
|
| 355 |
+
"loss": 0.6037,
|
| 356 |
+
"step": 3500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.35,
|
| 360 |
+
"eval_accuracy": 0.6815448864141219,
|
| 361 |
+
"eval_loss": 0.591849148273468,
|
| 362 |
+
"eval_runtime": 127.1262,
|
| 363 |
+
"eval_samples_per_second": 265.586,
|
| 364 |
+
"eval_steps_per_second": 16.606,
|
| 365 |
+
"step": 3500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.36,
|
| 369 |
+
"eval_accuracy": 0.6831738885762522,
|
| 370 |
+
"eval_loss": 0.5918092131614685,
|
| 371 |
+
"eval_runtime": 123.6609,
|
| 372 |
+
"eval_samples_per_second": 273.029,
|
| 373 |
+
"eval_steps_per_second": 17.071,
|
| 374 |
+
"step": 3600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.37,
|
| 378 |
+
"eval_accuracy": 0.6806563397802328,
|
| 379 |
+
"eval_loss": 0.5881184935569763,
|
| 380 |
+
"eval_runtime": 123.6786,
|
| 381 |
+
"eval_samples_per_second": 272.99,
|
| 382 |
+
"eval_steps_per_second": 17.068,
|
| 383 |
+
"step": 3700
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.38,
|
| 387 |
+
"eval_accuracy": 0.6733998756034713,
|
| 388 |
+
"eval_loss": 0.6080012321472168,
|
| 389 |
+
"eval_runtime": 123.437,
|
| 390 |
+
"eval_samples_per_second": 273.524,
|
| 391 |
+
"eval_steps_per_second": 17.102,
|
| 392 |
+
"step": 3800
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.39,
|
| 396 |
+
"eval_accuracy": 0.6735479667091194,
|
| 397 |
+
"eval_loss": 0.6100932359695435,
|
| 398 |
+
"eval_runtime": 118.7243,
|
| 399 |
+
"eval_samples_per_second": 284.382,
|
| 400 |
+
"eval_steps_per_second": 17.781,
|
| 401 |
+
"step": 3900
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.4,
|
| 405 |
+
"learning_rate": 1.2013576919237297e-05,
|
| 406 |
+
"loss": 0.596,
|
| 407 |
+
"step": 4000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.4,
|
| 411 |
+
"eval_accuracy": 0.6837662529988449,
|
| 412 |
+
"eval_loss": 0.5860297679901123,
|
| 413 |
+
"eval_runtime": 120.6458,
|
| 414 |
+
"eval_samples_per_second": 279.852,
|
| 415 |
+
"eval_steps_per_second": 17.498,
|
| 416 |
+
"step": 4000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.41,
|
| 420 |
+
"eval_accuracy": 0.683588543672067,
|
| 421 |
+
"eval_loss": 0.5865428447723389,
|
| 422 |
+
"eval_runtime": 119.5342,
|
| 423 |
+
"eval_samples_per_second": 282.455,
|
| 424 |
+
"eval_steps_per_second": 17.66,
|
| 425 |
+
"step": 4100
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.42,
|
| 429 |
+
"eval_accuracy": 0.6822261055001037,
|
| 430 |
+
"eval_loss": 0.5836812257766724,
|
| 431 |
+
"eval_runtime": 119.7355,
|
| 432 |
+
"eval_samples_per_second": 281.98,
|
| 433 |
+
"eval_steps_per_second": 17.631,
|
| 434 |
+
"step": 4200
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.43,
|
| 438 |
+
"eval_accuracy": 0.6840328169890116,
|
| 439 |
+
"eval_loss": 0.5837206840515137,
|
| 440 |
+
"eval_runtime": 120.8178,
|
| 441 |
+
"eval_samples_per_second": 279.454,
|
| 442 |
+
"eval_steps_per_second": 17.473,
|
| 443 |
+
"step": 4300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.44,
|
| 447 |
+
"eval_accuracy": 0.6855137280454936,
|
| 448 |
+
"eval_loss": 0.5865352153778076,
|
| 449 |
+
"eval_runtime": 122.1434,
|
| 450 |
+
"eval_samples_per_second": 276.421,
|
| 451 |
+
"eval_steps_per_second": 17.283,
|
| 452 |
+
"step": 4400
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.45,
|
| 456 |
+
"learning_rate": 1.101527403414196e-05,
|
| 457 |
+
"loss": 0.5948,
|
| 458 |
+
"step": 4500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.45,
|
| 462 |
+
"eval_accuracy": 0.6864022746793828,
|
| 463 |
+
"eval_loss": 0.5826652646064758,
|
| 464 |
+
"eval_runtime": 121.7629,
|
| 465 |
+
"eval_samples_per_second": 277.285,
|
| 466 |
+
"eval_steps_per_second": 17.337,
|
| 467 |
+
"step": 4500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.46,
|
| 471 |
+
"eval_accuracy": 0.6799751206942511,
|
| 472 |
+
"eval_loss": 0.5849358439445496,
|
| 473 |
+
"eval_runtime": 118.4911,
|
| 474 |
+
"eval_samples_per_second": 284.941,
|
| 475 |
+
"eval_steps_per_second": 17.816,
|
| 476 |
+
"step": 4600
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.47,
|
| 480 |
+
"eval_accuracy": 0.6880608950626426,
|
| 481 |
+
"eval_loss": 0.584037721157074,
|
| 482 |
+
"eval_runtime": 121.4782,
|
| 483 |
+
"eval_samples_per_second": 277.935,
|
| 484 |
+
"eval_steps_per_second": 17.378,
|
| 485 |
+
"step": 4700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.48,
|
| 489 |
+
"eval_accuracy": 0.6825815241536594,
|
| 490 |
+
"eval_loss": 0.5843004584312439,
|
| 491 |
+
"eval_runtime": 120.7083,
|
| 492 |
+
"eval_samples_per_second": 279.707,
|
| 493 |
+
"eval_steps_per_second": 17.488,
|
| 494 |
+
"step": 4800
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.49,
|
| 498 |
+
"eval_accuracy": 0.6855729644877528,
|
| 499 |
+
"eval_loss": 0.5819188356399536,
|
| 500 |
+
"eval_runtime": 119.2894,
|
| 501 |
+
"eval_samples_per_second": 283.034,
|
| 502 |
+
"eval_steps_per_second": 17.696,
|
| 503 |
+
"step": 4900
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.5,
|
| 507 |
+
"learning_rate": 1.0016971149046621e-05,
|
| 508 |
+
"loss": 0.5862,
|
| 509 |
+
"step": 5000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.5,
|
| 513 |
+
"eval_accuracy": 0.6876462399668276,
|
| 514 |
+
"eval_loss": 0.5809924602508545,
|
| 515 |
+
"eval_runtime": 118.4258,
|
| 516 |
+
"eval_samples_per_second": 285.098,
|
| 517 |
+
"eval_steps_per_second": 17.826,
|
| 518 |
+
"step": 5000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.51,
|
| 522 |
+
"eval_accuracy": 0.67268903829636,
|
| 523 |
+
"eval_loss": 0.5965932607650757,
|
| 524 |
+
"eval_runtime": 120.9456,
|
| 525 |
+
"eval_samples_per_second": 279.158,
|
| 526 |
+
"eval_steps_per_second": 17.454,
|
| 527 |
+
"step": 5100
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.52,
|
| 531 |
+
"eval_accuracy": 0.6881793679471611,
|
| 532 |
+
"eval_loss": 0.582930862903595,
|
| 533 |
+
"eval_runtime": 121.936,
|
| 534 |
+
"eval_samples_per_second": 276.891,
|
| 535 |
+
"eval_steps_per_second": 17.312,
|
| 536 |
+
"step": 5200
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.53,
|
| 540 |
+
"eval_accuracy": 0.6695198886354885,
|
| 541 |
+
"eval_loss": 0.5954956412315369,
|
| 542 |
+
"eval_runtime": 120.2241,
|
| 543 |
+
"eval_samples_per_second": 280.834,
|
| 544 |
+
"eval_steps_per_second": 17.559,
|
| 545 |
+
"step": 5300
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.54,
|
| 549 |
+
"eval_accuracy": 0.6855433462666233,
|
| 550 |
+
"eval_loss": 0.5801506638526917,
|
| 551 |
+
"eval_runtime": 123.0327,
|
| 552 |
+
"eval_samples_per_second": 274.423,
|
| 553 |
+
"eval_steps_per_second": 17.158,
|
| 554 |
+
"step": 5400
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.55,
|
| 558 |
+
"learning_rate": 9.018668263951284e-06,
|
| 559 |
+
"loss": 0.5868,
|
| 560 |
+
"step": 5500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.55,
|
| 564 |
+
"eval_accuracy": 0.6835589254509374,
|
| 565 |
+
"eval_loss": 0.5841577649116516,
|
| 566 |
+
"eval_runtime": 122.0071,
|
| 567 |
+
"eval_samples_per_second": 276.73,
|
| 568 |
+
"eval_steps_per_second": 17.302,
|
| 569 |
+
"step": 5500
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.56,
|
| 573 |
+
"eval_accuracy": 0.6864318929005124,
|
| 574 |
+
"eval_loss": 0.5806400775909424,
|
| 575 |
+
"eval_runtime": 121.8556,
|
| 576 |
+
"eval_samples_per_second": 277.074,
|
| 577 |
+
"eval_steps_per_second": 17.324,
|
| 578 |
+
"step": 5600
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.57,
|
| 582 |
+
"eval_accuracy": 0.6876462399668276,
|
| 583 |
+
"eval_loss": 0.582034170627594,
|
| 584 |
+
"eval_runtime": 121.9909,
|
| 585 |
+
"eval_samples_per_second": 276.767,
|
| 586 |
+
"eval_steps_per_second": 17.305,
|
| 587 |
+
"step": 5700
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.58,
|
| 591 |
+
"eval_accuracy": 0.6849213636229008,
|
| 592 |
+
"eval_loss": 0.5870340466499329,
|
| 593 |
+
"eval_runtime": 123.4237,
|
| 594 |
+
"eval_samples_per_second": 273.554,
|
| 595 |
+
"eval_steps_per_second": 17.104,
|
| 596 |
+
"step": 5800
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.59,
|
| 600 |
+
"eval_accuracy": 0.6870538755442348,
|
| 601 |
+
"eval_loss": 0.579352080821991,
|
| 602 |
+
"eval_runtime": 123.7102,
|
| 603 |
+
"eval_samples_per_second": 272.92,
|
| 604 |
+
"eval_steps_per_second": 17.064,
|
| 605 |
+
"step": 5900
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.6,
|
| 609 |
+
"learning_rate": 8.020365378855946e-06,
|
| 610 |
+
"loss": 0.5868,
|
| 611 |
+
"step": 6000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.6,
|
| 615 |
+
"eval_accuracy": 0.6886828777063649,
|
| 616 |
+
"eval_loss": 0.5769456624984741,
|
| 617 |
+
"eval_runtime": 121.7224,
|
| 618 |
+
"eval_samples_per_second": 277.377,
|
| 619 |
+
"eval_steps_per_second": 17.343,
|
| 620 |
+
"step": 6000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.61,
|
| 624 |
+
"eval_accuracy": 0.6878239492936055,
|
| 625 |
+
"eval_loss": 0.5787535309791565,
|
| 626 |
+
"eval_runtime": 118.515,
|
| 627 |
+
"eval_samples_per_second": 284.884,
|
| 628 |
+
"eval_steps_per_second": 17.812,
|
| 629 |
+
"step": 6100
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.62,
|
| 633 |
+
"eval_accuracy": 0.6861653289103457,
|
| 634 |
+
"eval_loss": 0.5844166278839111,
|
| 635 |
+
"eval_runtime": 119.9114,
|
| 636 |
+
"eval_samples_per_second": 281.566,
|
| 637 |
+
"eval_steps_per_second": 17.605,
|
| 638 |
+
"step": 6200
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.63,
|
| 642 |
+
"eval_accuracy": 0.6863430382371235,
|
| 643 |
+
"eval_loss": 0.5797388553619385,
|
| 644 |
+
"eval_runtime": 121.613,
|
| 645 |
+
"eval_samples_per_second": 277.627,
|
| 646 |
+
"eval_steps_per_second": 17.358,
|
| 647 |
+
"step": 6300
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.64,
|
| 651 |
+
"eval_accuracy": 0.6922370642419217,
|
| 652 |
+
"eval_loss": 0.5815860033035278,
|
| 653 |
+
"eval_runtime": 121.9323,
|
| 654 |
+
"eval_samples_per_second": 276.9,
|
| 655 |
+
"eval_steps_per_second": 17.313,
|
| 656 |
+
"step": 6400
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.65,
|
| 660 |
+
"learning_rate": 7.022062493760607e-06,
|
| 661 |
+
"loss": 0.5872,
|
| 662 |
+
"step": 6500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.65,
|
| 666 |
+
"eval_accuracy": 0.6891863874655688,
|
| 667 |
+
"eval_loss": 0.5755571126937866,
|
| 668 |
+
"eval_runtime": 120.5961,
|
| 669 |
+
"eval_samples_per_second": 279.968,
|
| 670 |
+
"eval_steps_per_second": 17.505,
|
| 671 |
+
"step": 6500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.66,
|
| 675 |
+
"eval_accuracy": 0.6912892811657732,
|
| 676 |
+
"eval_loss": 0.5765994191169739,
|
| 677 |
+
"eval_runtime": 118.5726,
|
| 678 |
+
"eval_samples_per_second": 284.745,
|
| 679 |
+
"eval_steps_per_second": 17.803,
|
| 680 |
+
"step": 6600
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.67,
|
| 684 |
+
"eval_accuracy": 0.6933033202025887,
|
| 685 |
+
"eval_loss": 0.5784236192703247,
|
| 686 |
+
"eval_runtime": 120.5154,
|
| 687 |
+
"eval_samples_per_second": 280.155,
|
| 688 |
+
"eval_steps_per_second": 17.516,
|
| 689 |
+
"step": 6700
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.68,
|
| 693 |
+
"eval_accuracy": 0.6937475935195332,
|
| 694 |
+
"eval_loss": 0.5751758813858032,
|
| 695 |
+
"eval_runtime": 121.1939,
|
| 696 |
+
"eval_samples_per_second": 278.587,
|
| 697 |
+
"eval_steps_per_second": 17.418,
|
| 698 |
+
"step": 6800
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.69,
|
| 702 |
+
"eval_accuracy": 0.6900453158783284,
|
| 703 |
+
"eval_loss": 0.5770964622497559,
|
| 704 |
+
"eval_runtime": 122.265,
|
| 705 |
+
"eval_samples_per_second": 276.146,
|
| 706 |
+
"eval_steps_per_second": 17.266,
|
| 707 |
+
"step": 6900
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.7,
|
| 711 |
+
"learning_rate": 6.02375960866527e-06,
|
| 712 |
+
"loss": 0.584,
|
| 713 |
+
"step": 7000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.7,
|
| 717 |
+
"eval_accuracy": 0.691466990492551,
|
| 718 |
+
"eval_loss": 0.5755699872970581,
|
| 719 |
+
"eval_runtime": 120.2886,
|
| 720 |
+
"eval_samples_per_second": 280.683,
|
| 721 |
+
"eval_steps_per_second": 17.549,
|
| 722 |
+
"step": 7000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.71,
|
| 726 |
+
"eval_accuracy": 0.6928294286645144,
|
| 727 |
+
"eval_loss": 0.5778803825378418,
|
| 728 |
+
"eval_runtime": 119.22,
|
| 729 |
+
"eval_samples_per_second": 283.199,
|
| 730 |
+
"eval_steps_per_second": 17.707,
|
| 731 |
+
"step": 7100
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.72,
|
| 735 |
+
"eval_accuracy": 0.691052335396736,
|
| 736 |
+
"eval_loss": 0.5816224813461304,
|
| 737 |
+
"eval_runtime": 121.6119,
|
| 738 |
+
"eval_samples_per_second": 277.629,
|
| 739 |
+
"eval_steps_per_second": 17.359,
|
| 740 |
+
"step": 7200
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.73,
|
| 744 |
+
"eval_accuracy": 0.6899268429938098,
|
| 745 |
+
"eval_loss": 0.5753040313720703,
|
| 746 |
+
"eval_runtime": 122.0359,
|
| 747 |
+
"eval_samples_per_second": 276.665,
|
| 748 |
+
"eval_steps_per_second": 17.298,
|
| 749 |
+
"step": 7300
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.74,
|
| 753 |
+
"eval_accuracy": 0.6927109557799959,
|
| 754 |
+
"eval_loss": 0.578673779964447,
|
| 755 |
+
"eval_runtime": 120.6028,
|
| 756 |
+
"eval_samples_per_second": 279.952,
|
| 757 |
+
"eval_steps_per_second": 17.504,
|
| 758 |
+
"step": 7400
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.75,
|
| 762 |
+
"learning_rate": 5.0254567235699314e-06,
|
| 763 |
+
"loss": 0.5812,
|
| 764 |
+
"step": 7500
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.75,
|
| 768 |
+
"eval_accuracy": 0.6879720403992536,
|
| 769 |
+
"eval_loss": 0.5793206691741943,
|
| 770 |
+
"eval_runtime": 121.5038,
|
| 771 |
+
"eval_samples_per_second": 277.876,
|
| 772 |
+
"eval_steps_per_second": 17.374,
|
| 773 |
+
"step": 7500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.76,
|
| 777 |
+
"eval_accuracy": 0.6891567692444391,
|
| 778 |
+
"eval_loss": 0.5748796463012695,
|
| 779 |
+
"eval_runtime": 120.9422,
|
| 780 |
+
"eval_samples_per_second": 279.166,
|
| 781 |
+
"eval_steps_per_second": 17.455,
|
| 782 |
+
"step": 7600
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.77,
|
| 786 |
+
"eval_accuracy": 0.6884459319373278,
|
| 787 |
+
"eval_loss": 0.5827967524528503,
|
| 788 |
+
"eval_runtime": 120.4061,
|
| 789 |
+
"eval_samples_per_second": 280.409,
|
| 790 |
+
"eval_steps_per_second": 17.532,
|
| 791 |
+
"step": 7700
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.78,
|
| 795 |
+
"eval_accuracy": 0.6921482095785327,
|
| 796 |
+
"eval_loss": 0.5722939372062683,
|
| 797 |
+
"eval_runtime": 120.2444,
|
| 798 |
+
"eval_samples_per_second": 280.787,
|
| 799 |
+
"eval_steps_per_second": 17.556,
|
| 800 |
+
"step": 7800
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.79,
|
| 804 |
+
"eval_accuracy": 0.6930071379912922,
|
| 805 |
+
"eval_loss": 0.5720646381378174,
|
| 806 |
+
"eval_runtime": 120.4878,
|
| 807 |
+
"eval_samples_per_second": 280.219,
|
| 808 |
+
"eval_steps_per_second": 17.52,
|
| 809 |
+
"step": 7900
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.8,
|
| 813 |
+
"learning_rate": 4.027153838474593e-06,
|
| 814 |
+
"loss": 0.5754,
|
| 815 |
+
"step": 8000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.8,
|
| 819 |
+
"eval_accuracy": 0.6890382963599206,
|
| 820 |
+
"eval_loss": 0.5755317211151123,
|
| 821 |
+
"eval_runtime": 121.8943,
|
| 822 |
+
"eval_samples_per_second": 276.986,
|
| 823 |
+
"eval_steps_per_second": 17.318,
|
| 824 |
+
"step": 8000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.81,
|
| 828 |
+
"eval_accuracy": 0.6926813375588662,
|
| 829 |
+
"eval_loss": 0.580621063709259,
|
| 830 |
+
"eval_runtime": 120.5342,
|
| 831 |
+
"eval_samples_per_second": 280.111,
|
| 832 |
+
"eval_steps_per_second": 17.514,
|
| 833 |
+
"step": 8100
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.82,
|
| 837 |
+
"eval_accuracy": 0.6944880490477742,
|
| 838 |
+
"eval_loss": 0.5727642178535461,
|
| 839 |
+
"eval_runtime": 121.4458,
|
| 840 |
+
"eval_samples_per_second": 278.009,
|
| 841 |
+
"eval_steps_per_second": 17.382,
|
| 842 |
+
"step": 8200
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.83,
|
| 846 |
+
"eval_accuracy": 0.6914966087136807,
|
| 847 |
+
"eval_loss": 0.5764381885528564,
|
| 848 |
+
"eval_runtime": 119.5977,
|
| 849 |
+
"eval_samples_per_second": 282.305,
|
| 850 |
+
"eval_steps_per_second": 17.651,
|
| 851 |
+
"step": 8300
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.84,
|
| 855 |
+
"eval_accuracy": 0.693925302846311,
|
| 856 |
+
"eval_loss": 0.5707160830497742,
|
| 857 |
+
"eval_runtime": 119.8766,
|
| 858 |
+
"eval_samples_per_second": 281.648,
|
| 859 |
+
"eval_steps_per_second": 17.61,
|
| 860 |
+
"step": 8400
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.85,
|
| 864 |
+
"learning_rate": 3.0288509533792554e-06,
|
| 865 |
+
"loss": 0.5743,
|
| 866 |
+
"step": 8500
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.85,
|
| 870 |
+
"eval_accuracy": 0.6939845392885703,
|
| 871 |
+
"eval_loss": 0.5710459351539612,
|
| 872 |
+
"eval_runtime": 121.7301,
|
| 873 |
+
"eval_samples_per_second": 277.36,
|
| 874 |
+
"eval_steps_per_second": 17.342,
|
| 875 |
+
"step": 8500
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.86,
|
| 879 |
+
"eval_accuracy": 0.6937475935195332,
|
| 880 |
+
"eval_loss": 0.5757591128349304,
|
| 881 |
+
"eval_runtime": 121.0195,
|
| 882 |
+
"eval_samples_per_second": 278.988,
|
| 883 |
+
"eval_steps_per_second": 17.443,
|
| 884 |
+
"step": 8600
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.87,
|
| 888 |
+
"eval_accuracy": 0.6917039362615881,
|
| 889 |
+
"eval_loss": 0.574606716632843,
|
| 890 |
+
"eval_runtime": 124.4692,
|
| 891 |
+
"eval_samples_per_second": 271.256,
|
| 892 |
+
"eval_steps_per_second": 16.96,
|
| 893 |
+
"step": 8700
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.88,
|
| 897 |
+
"eval_accuracy": 0.6962355240944229,
|
| 898 |
+
"eval_loss": 0.5732554197311401,
|
| 899 |
+
"eval_runtime": 120.9096,
|
| 900 |
+
"eval_samples_per_second": 279.242,
|
| 901 |
+
"eval_steps_per_second": 17.459,
|
| 902 |
+
"step": 8800
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.89,
|
| 906 |
+
"eval_accuracy": 0.6945769037111631,
|
| 907 |
+
"eval_loss": 0.5710918307304382,
|
| 908 |
+
"eval_runtime": 119.8896,
|
| 909 |
+
"eval_samples_per_second": 281.617,
|
| 910 |
+
"eval_steps_per_second": 17.608,
|
| 911 |
+
"step": 8900
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 0.9,
|
| 915 |
+
"learning_rate": 2.0305480682839176e-06,
|
| 916 |
+
"loss": 0.5664,
|
| 917 |
+
"step": 9000
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 0.9,
|
| 921 |
+
"eval_accuracy": 0.6929775197701626,
|
| 922 |
+
"eval_loss": 0.57152259349823,
|
| 923 |
+
"eval_runtime": 120.0446,
|
| 924 |
+
"eval_samples_per_second": 281.254,
|
| 925 |
+
"eval_steps_per_second": 17.585,
|
| 926 |
+
"step": 9000
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.91,
|
| 930 |
+
"eval_accuracy": 0.6967686520747564,
|
| 931 |
+
"eval_loss": 0.5711397528648376,
|
| 932 |
+
"eval_runtime": 119.8872,
|
| 933 |
+
"eval_samples_per_second": 281.623,
|
| 934 |
+
"eval_steps_per_second": 17.608,
|
| 935 |
+
"step": 9100
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.92,
|
| 939 |
+
"eval_accuracy": 0.6950211770281077,
|
| 940 |
+
"eval_loss": 0.5720114707946777,
|
| 941 |
+
"eval_runtime": 119.8996,
|
| 942 |
+
"eval_samples_per_second": 281.594,
|
| 943 |
+
"eval_steps_per_second": 17.606,
|
| 944 |
+
"step": 9200
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.93,
|
| 948 |
+
"eval_accuracy": 0.6930663744335516,
|
| 949 |
+
"eval_loss": 0.5728961825370789,
|
| 950 |
+
"eval_runtime": 121.5387,
|
| 951 |
+
"eval_samples_per_second": 277.796,
|
| 952 |
+
"eval_steps_per_second": 17.369,
|
| 953 |
+
"step": 9300
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.94,
|
| 957 |
+
"eval_accuracy": 0.6957912507774783,
|
| 958 |
+
"eval_loss": 0.5721818804740906,
|
| 959 |
+
"eval_runtime": 121.3258,
|
| 960 |
+
"eval_samples_per_second": 278.284,
|
| 961 |
+
"eval_steps_per_second": 17.399,
|
| 962 |
+
"step": 9400
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.95,
|
| 966 |
+
"learning_rate": 1.0322451831885795e-06,
|
| 967 |
+
"loss": 0.5659,
|
| 968 |
+
"step": 9500
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.95,
|
| 972 |
+
"eval_accuracy": 0.6956727778929598,
|
| 973 |
+
"eval_loss": 0.5728616118431091,
|
| 974 |
+
"eval_runtime": 122.9243,
|
| 975 |
+
"eval_samples_per_second": 274.665,
|
| 976 |
+
"eval_steps_per_second": 17.173,
|
| 977 |
+
"step": 9500
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.96,
|
| 981 |
+
"eval_accuracy": 0.695406213902793,
|
| 982 |
+
"eval_loss": 0.571672797203064,
|
| 983 |
+
"eval_runtime": 117.4658,
|
| 984 |
+
"eval_samples_per_second": 287.428,
|
| 985 |
+
"eval_steps_per_second": 17.971,
|
| 986 |
+
"step": 9600
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.97,
|
| 990 |
+
"eval_accuracy": 0.6966205609691082,
|
| 991 |
+
"eval_loss": 0.569725513458252,
|
| 992 |
+
"eval_runtime": 122.1907,
|
| 993 |
+
"eval_samples_per_second": 276.314,
|
| 994 |
+
"eval_steps_per_second": 17.276,
|
| 995 |
+
"step": 9700
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.98,
|
| 999 |
+
"eval_accuracy": 0.6969759796226639,
|
| 1000 |
+
"eval_loss": 0.5699070692062378,
|
| 1001 |
+
"eval_runtime": 119.8449,
|
| 1002 |
+
"eval_samples_per_second": 281.722,
|
| 1003 |
+
"eval_steps_per_second": 17.614,
|
| 1004 |
+
"step": 9800
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.99,
|
| 1008 |
+
"eval_accuracy": 0.6957616325563487,
|
| 1009 |
+
"eval_loss": 0.5702488422393799,
|
| 1010 |
+
"eval_runtime": 121.0927,
|
| 1011 |
+
"eval_samples_per_second": 278.82,
|
| 1012 |
+
"eval_steps_per_second": 17.433,
|
| 1013 |
+
"step": 9900
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.0,
|
| 1017 |
+
"learning_rate": 3.394229809324149e-08,
|
| 1018 |
+
"loss": 0.5699,
|
| 1019 |
+
"step": 10000
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.0,
|
| 1023 |
+
"eval_accuracy": 0.6955839232295709,
|
| 1024 |
+
"eval_loss": 0.5703100562095642,
|
| 1025 |
+
"eval_runtime": 120.0243,
|
| 1026 |
+
"eval_samples_per_second": 281.301,
|
| 1027 |
+
"eval_steps_per_second": 17.588,
|
| 1028 |
+
"step": 10000
|
| 1029 |
+
}
|
| 1030 |
+
],
|
| 1031 |
+
"max_steps": 10017,
|
| 1032 |
+
"num_train_epochs": 1,
|
| 1033 |
+
"total_flos": 7221381585213888.0,
|
| 1034 |
+
"trial_name": null,
|
| 1035 |
+
"trial_params": null
|
| 1036 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|