Commit
•
2240bd8
1
Parent(s):
713997d
Upload 12 files
Browse files- config.json +36 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +922 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "human-produced",
|
| 15 |
+
"1": "machine-generated"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"human-produced": 0,
|
| 21 |
+
"machine-generated": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-05,
|
| 24 |
+
"max_position_embeddings": 514,
|
| 25 |
+
"model_type": "roberta",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 1,
|
| 29 |
+
"position_embedding_type": "absolute",
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.26.1",
|
| 33 |
+
"type_vocab_size": 1,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 50265
|
| 36 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf3b1c9a1b4ae2ae04940a3d45196bcd5e7d0b84bdd8750d35868b56c2c0b87f
|
| 3 |
+
size 997344965
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65884bbeebba335c082512dee4b475947b08d83317a3c95f38550b5c85d0ef81
|
| 3 |
+
size 498662069
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb67e526eb3ee909ba650a3125bdfb951fa027b64d14c5d6847f72b90f3c71c3
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d94bffac577c2182cd3b6680df4b0ff46f4c0a0b7ff9c866be7458145e68e80
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
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 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"name_or_path": "roberta-base",
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"special_tokens_map_file": null,
|
| 13 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,922 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 2188,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 4.997714808043876e-05,
|
| 13 |
+
"loss": 0.701,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 4.9017367458866546e-05,
|
| 19 |
+
"loss": 0.5623,
|
| 20 |
+
"step": 43
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"eval_accuracy": 0.9112,
|
| 25 |
+
"eval_f1": 0.9178386380458919,
|
| 26 |
+
"eval_loss": 0.3157382309436798,
|
| 27 |
+
"eval_precision": 0.8539944903581267,
|
| 28 |
+
"eval_recall": 0.992,
|
| 29 |
+
"eval_runtime": 31.9687,
|
| 30 |
+
"eval_samples_per_second": 117.302,
|
| 31 |
+
"eval_steps_per_second": 14.671,
|
| 32 |
+
"step": 43
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.04,
|
| 36 |
+
"learning_rate": 4.8034734917733096e-05,
|
| 37 |
+
"loss": 0.4041,
|
| 38 |
+
"step": 86
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04,
|
| 42 |
+
"eval_accuracy": 0.9682666666666667,
|
| 43 |
+
"eval_f1": 0.9688563203349909,
|
| 44 |
+
"eval_loss": 0.10907813906669617,
|
| 45 |
+
"eval_precision": 0.9511819116135662,
|
| 46 |
+
"eval_recall": 0.9872,
|
| 47 |
+
"eval_runtime": 31.8725,
|
| 48 |
+
"eval_samples_per_second": 117.656,
|
| 49 |
+
"eval_steps_per_second": 14.715,
|
| 50 |
+
"step": 86
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.06,
|
| 54 |
+
"learning_rate": 4.705210237659964e-05,
|
| 55 |
+
"loss": 0.0811,
|
| 56 |
+
"step": 129
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"eval_accuracy": 0.9829333333333333,
|
| 61 |
+
"eval_f1": 0.9830777366472766,
|
| 62 |
+
"eval_loss": 0.11184453219175339,
|
| 63 |
+
"eval_precision": 0.9748295752490823,
|
| 64 |
+
"eval_recall": 0.9914666666666667,
|
| 65 |
+
"eval_runtime": 32.1826,
|
| 66 |
+
"eval_samples_per_second": 116.523,
|
| 67 |
+
"eval_steps_per_second": 14.573,
|
| 68 |
+
"step": 129
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.08,
|
| 72 |
+
"learning_rate": 4.606946983546618e-05,
|
| 73 |
+
"loss": 0.1455,
|
| 74 |
+
"step": 172
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.08,
|
| 78 |
+
"eval_accuracy": 0.9826666666666667,
|
| 79 |
+
"eval_f1": 0.9828360179561658,
|
| 80 |
+
"eval_loss": 0.08915094286203384,
|
| 81 |
+
"eval_precision": 0.9733263598326359,
|
| 82 |
+
"eval_recall": 0.9925333333333334,
|
| 83 |
+
"eval_runtime": 31.7933,
|
| 84 |
+
"eval_samples_per_second": 117.949,
|
| 85 |
+
"eval_steps_per_second": 14.752,
|
| 86 |
+
"step": 172
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1,
|
| 90 |
+
"learning_rate": 4.5086837294332726e-05,
|
| 91 |
+
"loss": 0.1159,
|
| 92 |
+
"step": 215
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.1,
|
| 96 |
+
"eval_accuracy": 0.9722666666666666,
|
| 97 |
+
"eval_f1": 0.9729448491155047,
|
| 98 |
+
"eval_loss": 0.15372106432914734,
|
| 99 |
+
"eval_precision": 0.9497206703910615,
|
| 100 |
+
"eval_recall": 0.9973333333333333,
|
| 101 |
+
"eval_runtime": 31.823,
|
| 102 |
+
"eval_samples_per_second": 117.839,
|
| 103 |
+
"eval_steps_per_second": 14.738,
|
| 104 |
+
"step": 215
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.12,
|
| 108 |
+
"learning_rate": 4.410420475319927e-05,
|
| 109 |
+
"loss": 0.1902,
|
| 110 |
+
"step": 258
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.12,
|
| 114 |
+
"eval_accuracy": 0.9765333333333334,
|
| 115 |
+
"eval_f1": 0.9769874476987447,
|
| 116 |
+
"eval_loss": 0.11824183911085129,
|
| 117 |
+
"eval_precision": 0.9584402257567983,
|
| 118 |
+
"eval_recall": 0.9962666666666666,
|
| 119 |
+
"eval_runtime": 31.879,
|
| 120 |
+
"eval_samples_per_second": 117.632,
|
| 121 |
+
"eval_steps_per_second": 14.712,
|
| 122 |
+
"step": 258
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14,
|
| 126 |
+
"learning_rate": 4.312157221206581e-05,
|
| 127 |
+
"loss": 0.0948,
|
| 128 |
+
"step": 301
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.14,
|
| 132 |
+
"eval_accuracy": 0.9917333333333334,
|
| 133 |
+
"eval_f1": 0.9917443408788282,
|
| 134 |
+
"eval_loss": 0.04853309690952301,
|
| 135 |
+
"eval_precision": 0.9904255319148936,
|
| 136 |
+
"eval_recall": 0.9930666666666667,
|
| 137 |
+
"eval_runtime": 32.1725,
|
| 138 |
+
"eval_samples_per_second": 116.559,
|
| 139 |
+
"eval_steps_per_second": 14.578,
|
| 140 |
+
"step": 301
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.16,
|
| 144 |
+
"learning_rate": 4.213893967093236e-05,
|
| 145 |
+
"loss": 0.0947,
|
| 146 |
+
"step": 344
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.16,
|
| 150 |
+
"eval_accuracy": 0.9589333333333333,
|
| 151 |
+
"eval_f1": 0.960431654676259,
|
| 152 |
+
"eval_loss": 0.21628336608409882,
|
| 153 |
+
"eval_precision": 0.9266236985622212,
|
| 154 |
+
"eval_recall": 0.9968,
|
| 155 |
+
"eval_runtime": 31.9931,
|
| 156 |
+
"eval_samples_per_second": 117.213,
|
| 157 |
+
"eval_steps_per_second": 14.659,
|
| 158 |
+
"step": 344
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.18,
|
| 162 |
+
"learning_rate": 4.1156307129798905e-05,
|
| 163 |
+
"loss": 0.1513,
|
| 164 |
+
"step": 387
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.18,
|
| 168 |
+
"eval_accuracy": 0.9885333333333334,
|
| 169 |
+
"eval_f1": 0.9884315308044122,
|
| 170 |
+
"eval_loss": 0.056088127195835114,
|
| 171 |
+
"eval_precision": 0.99728555917481,
|
| 172 |
+
"eval_recall": 0.9797333333333333,
|
| 173 |
+
"eval_runtime": 31.868,
|
| 174 |
+
"eval_samples_per_second": 117.673,
|
| 175 |
+
"eval_steps_per_second": 14.717,
|
| 176 |
+
"step": 387
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.2,
|
| 180 |
+
"learning_rate": 4.017367458866545e-05,
|
| 181 |
+
"loss": 0.2024,
|
| 182 |
+
"step": 430
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.2,
|
| 186 |
+
"eval_accuracy": 0.9770666666666666,
|
| 187 |
+
"eval_f1": 0.9774869109947643,
|
| 188 |
+
"eval_loss": 0.11541605740785599,
|
| 189 |
+
"eval_precision": 0.9598971722365038,
|
| 190 |
+
"eval_recall": 0.9957333333333334,
|
| 191 |
+
"eval_runtime": 31.7697,
|
| 192 |
+
"eval_samples_per_second": 118.037,
|
| 193 |
+
"eval_steps_per_second": 14.763,
|
| 194 |
+
"step": 430
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.22,
|
| 198 |
+
"learning_rate": 3.919104204753199e-05,
|
| 199 |
+
"loss": 0.0442,
|
| 200 |
+
"step": 473
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.22,
|
| 204 |
+
"eval_accuracy": 0.9872,
|
| 205 |
+
"eval_f1": 0.9871931696905016,
|
| 206 |
+
"eval_loss": 0.06453149765729904,
|
| 207 |
+
"eval_precision": 0.987720234917245,
|
| 208 |
+
"eval_recall": 0.9866666666666667,
|
| 209 |
+
"eval_runtime": 31.8692,
|
| 210 |
+
"eval_samples_per_second": 117.668,
|
| 211 |
+
"eval_steps_per_second": 14.716,
|
| 212 |
+
"step": 473
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.24,
|
| 216 |
+
"learning_rate": 3.820840950639854e-05,
|
| 217 |
+
"loss": 0.0859,
|
| 218 |
+
"step": 516
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.24,
|
| 222 |
+
"eval_accuracy": 0.9792,
|
| 223 |
+
"eval_f1": 0.9794736842105262,
|
| 224 |
+
"eval_loss": 0.11312653124332428,
|
| 225 |
+
"eval_precision": 0.9667532467532467,
|
| 226 |
+
"eval_recall": 0.9925333333333334,
|
| 227 |
+
"eval_runtime": 31.8306,
|
| 228 |
+
"eval_samples_per_second": 117.811,
|
| 229 |
+
"eval_steps_per_second": 14.734,
|
| 230 |
+
"step": 516
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.26,
|
| 234 |
+
"learning_rate": 3.7225776965265085e-05,
|
| 235 |
+
"loss": 0.0802,
|
| 236 |
+
"step": 559
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.26,
|
| 240 |
+
"eval_accuracy": 0.9866666666666667,
|
| 241 |
+
"eval_f1": 0.9867654843832716,
|
| 242 |
+
"eval_loss": 0.07340351492166519,
|
| 243 |
+
"eval_precision": 0.9795060430898581,
|
| 244 |
+
"eval_recall": 0.9941333333333333,
|
| 245 |
+
"eval_runtime": 31.9433,
|
| 246 |
+
"eval_samples_per_second": 117.396,
|
| 247 |
+
"eval_steps_per_second": 14.682,
|
| 248 |
+
"step": 559
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.28,
|
| 252 |
+
"learning_rate": 3.624314442413163e-05,
|
| 253 |
+
"loss": 0.0754,
|
| 254 |
+
"step": 602
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.28,
|
| 258 |
+
"eval_accuracy": 0.9909333333333333,
|
| 259 |
+
"eval_f1": 0.9909718534253851,
|
| 260 |
+
"eval_loss": 0.05534309148788452,
|
| 261 |
+
"eval_precision": 0.9867794817556849,
|
| 262 |
+
"eval_recall": 0.9952,
|
| 263 |
+
"eval_runtime": 31.9035,
|
| 264 |
+
"eval_samples_per_second": 117.542,
|
| 265 |
+
"eval_steps_per_second": 14.701,
|
| 266 |
+
"step": 602
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.29,
|
| 270 |
+
"learning_rate": 3.526051188299818e-05,
|
| 271 |
+
"loss": 0.0446,
|
| 272 |
+
"step": 645
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.29,
|
| 276 |
+
"eval_accuracy": 0.9802666666666666,
|
| 277 |
+
"eval_f1": 0.980546792849632,
|
| 278 |
+
"eval_loss": 0.10309968888759613,
|
| 279 |
+
"eval_precision": 0.966822187662001,
|
| 280 |
+
"eval_recall": 0.9946666666666667,
|
| 281 |
+
"eval_runtime": 31.8495,
|
| 282 |
+
"eval_samples_per_second": 117.741,
|
| 283 |
+
"eval_steps_per_second": 14.725,
|
| 284 |
+
"step": 645
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.31,
|
| 288 |
+
"learning_rate": 3.4277879341864715e-05,
|
| 289 |
+
"loss": 0.2247,
|
| 290 |
+
"step": 688
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.31,
|
| 294 |
+
"eval_accuracy": 0.9837333333333333,
|
| 295 |
+
"eval_f1": 0.9839262187088275,
|
| 296 |
+
"eval_loss": 0.05565320700407028,
|
| 297 |
+
"eval_precision": 0.9723958333333333,
|
| 298 |
+
"eval_recall": 0.9957333333333334,
|
| 299 |
+
"eval_runtime": 31.8106,
|
| 300 |
+
"eval_samples_per_second": 117.885,
|
| 301 |
+
"eval_steps_per_second": 14.744,
|
| 302 |
+
"step": 688
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.33,
|
| 306 |
+
"learning_rate": 3.329524680073126e-05,
|
| 307 |
+
"loss": 0.0198,
|
| 308 |
+
"step": 731
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.33,
|
| 312 |
+
"eval_accuracy": 0.972,
|
| 313 |
+
"eval_f1": 0.9726491273769211,
|
| 314 |
+
"eval_loss": 0.19524268805980682,
|
| 315 |
+
"eval_precision": 0.9506109979633401,
|
| 316 |
+
"eval_recall": 0.9957333333333334,
|
| 317 |
+
"eval_runtime": 31.8384,
|
| 318 |
+
"eval_samples_per_second": 117.782,
|
| 319 |
+
"eval_steps_per_second": 14.731,
|
| 320 |
+
"step": 731
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.35,
|
| 324 |
+
"learning_rate": 3.231261425959781e-05,
|
| 325 |
+
"loss": 0.144,
|
| 326 |
+
"step": 774
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.35,
|
| 330 |
+
"eval_accuracy": 0.9845333333333334,
|
| 331 |
+
"eval_f1": 0.984688489968321,
|
| 332 |
+
"eval_loss": 0.07750081270933151,
|
| 333 |
+
"eval_precision": 0.9749085206481966,
|
| 334 |
+
"eval_recall": 0.9946666666666667,
|
| 335 |
+
"eval_runtime": 31.9146,
|
| 336 |
+
"eval_samples_per_second": 117.501,
|
| 337 |
+
"eval_steps_per_second": 14.695,
|
| 338 |
+
"step": 774
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.37,
|
| 342 |
+
"learning_rate": 3.132998171846435e-05,
|
| 343 |
+
"loss": 0.1193,
|
| 344 |
+
"step": 817
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.37,
|
| 348 |
+
"eval_accuracy": 0.988,
|
| 349 |
+
"eval_f1": 0.9879194630872483,
|
| 350 |
+
"eval_loss": 0.04342731088399887,
|
| 351 |
+
"eval_precision": 0.9945945945945946,
|
| 352 |
+
"eval_recall": 0.9813333333333333,
|
| 353 |
+
"eval_runtime": 32.0746,
|
| 354 |
+
"eval_samples_per_second": 116.915,
|
| 355 |
+
"eval_steps_per_second": 14.622,
|
| 356 |
+
"step": 817
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.39,
|
| 360 |
+
"learning_rate": 3.03473491773309e-05,
|
| 361 |
+
"loss": 0.0813,
|
| 362 |
+
"step": 860
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.39,
|
| 366 |
+
"eval_accuracy": 0.9773333333333334,
|
| 367 |
+
"eval_f1": 0.9777661522364636,
|
| 368 |
+
"eval_loss": 0.13094328343868256,
|
| 369 |
+
"eval_precision": 0.9594455852156057,
|
| 370 |
+
"eval_recall": 0.9968,
|
| 371 |
+
"eval_runtime": 31.8439,
|
| 372 |
+
"eval_samples_per_second": 117.762,
|
| 373 |
+
"eval_steps_per_second": 14.728,
|
| 374 |
+
"step": 860
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.41,
|
| 378 |
+
"learning_rate": 2.9364716636197442e-05,
|
| 379 |
+
"loss": 0.1484,
|
| 380 |
+
"step": 903
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.41,
|
| 384 |
+
"eval_accuracy": 0.9893333333333333,
|
| 385 |
+
"eval_f1": 0.989406779661017,
|
| 386 |
+
"eval_loss": 0.04147784784436226,
|
| 387 |
+
"eval_precision": 0.9826407154129405,
|
| 388 |
+
"eval_recall": 0.9962666666666666,
|
| 389 |
+
"eval_runtime": 32.1496,
|
| 390 |
+
"eval_samples_per_second": 116.642,
|
| 391 |
+
"eval_steps_per_second": 14.588,
|
| 392 |
+
"step": 903
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.43,
|
| 396 |
+
"learning_rate": 2.838208409506399e-05,
|
| 397 |
+
"loss": 0.0575,
|
| 398 |
+
"step": 946
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.43,
|
| 402 |
+
"eval_accuracy": 0.9936,
|
| 403 |
+
"eval_f1": 0.9935897435897435,
|
| 404 |
+
"eval_loss": 0.0342133492231369,
|
| 405 |
+
"eval_precision": 0.9951845906902087,
|
| 406 |
+
"eval_recall": 0.992,
|
| 407 |
+
"eval_runtime": 31.8831,
|
| 408 |
+
"eval_samples_per_second": 117.617,
|
| 409 |
+
"eval_steps_per_second": 14.71,
|
| 410 |
+
"step": 946
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.45,
|
| 414 |
+
"learning_rate": 2.739945155393053e-05,
|
| 415 |
+
"loss": 0.0377,
|
| 416 |
+
"step": 989
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.45,
|
| 420 |
+
"eval_accuracy": 0.984,
|
| 421 |
+
"eval_f1": 0.9842022116903633,
|
| 422 |
+
"eval_loss": 0.08944225311279297,
|
| 423 |
+
"eval_precision": 0.9719188767550702,
|
| 424 |
+
"eval_recall": 0.9968,
|
| 425 |
+
"eval_runtime": 31.8105,
|
| 426 |
+
"eval_samples_per_second": 117.886,
|
| 427 |
+
"eval_steps_per_second": 14.744,
|
| 428 |
+
"step": 989
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.47,
|
| 432 |
+
"learning_rate": 2.641681901279708e-05,
|
| 433 |
+
"loss": 0.023,
|
| 434 |
+
"step": 1032
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.47,
|
| 438 |
+
"eval_accuracy": 0.9666666666666667,
|
| 439 |
+
"eval_f1": 0.9676752004137574,
|
| 440 |
+
"eval_loss": 0.2229950875043869,
|
| 441 |
+
"eval_precision": 0.9392570281124498,
|
| 442 |
+
"eval_recall": 0.9978666666666667,
|
| 443 |
+
"eval_runtime": 32.2928,
|
| 444 |
+
"eval_samples_per_second": 116.125,
|
| 445 |
+
"eval_steps_per_second": 14.523,
|
| 446 |
+
"step": 1032
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.49,
|
| 450 |
+
"learning_rate": 2.5434186471663625e-05,
|
| 451 |
+
"loss": 0.0147,
|
| 452 |
+
"step": 1075
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.49,
|
| 456 |
+
"eval_accuracy": 0.9922666666666666,
|
| 457 |
+
"eval_f1": 0.9922892847646902,
|
| 458 |
+
"eval_loss": 0.054798923432826996,
|
| 459 |
+
"eval_precision": 0.9893955461293743,
|
| 460 |
+
"eval_recall": 0.9952,
|
| 461 |
+
"eval_runtime": 31.9316,
|
| 462 |
+
"eval_samples_per_second": 117.439,
|
| 463 |
+
"eval_steps_per_second": 14.688,
|
| 464 |
+
"step": 1075
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.51,
|
| 468 |
+
"learning_rate": 2.4451553930530165e-05,
|
| 469 |
+
"loss": 0.0904,
|
| 470 |
+
"step": 1118
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.51,
|
| 474 |
+
"eval_accuracy": 0.9946666666666667,
|
| 475 |
+
"eval_f1": 0.9946638207043758,
|
| 476 |
+
"eval_loss": 0.029427310451865196,
|
| 477 |
+
"eval_precision": 0.9951948745328351,
|
| 478 |
+
"eval_recall": 0.9941333333333333,
|
| 479 |
+
"eval_runtime": 31.7699,
|
| 480 |
+
"eval_samples_per_second": 118.036,
|
| 481 |
+
"eval_steps_per_second": 14.762,
|
| 482 |
+
"step": 1118
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.53,
|
| 486 |
+
"learning_rate": 2.346892138939671e-05,
|
| 487 |
+
"loss": 0.0578,
|
| 488 |
+
"step": 1161
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.53,
|
| 492 |
+
"eval_accuracy": 0.9922666666666666,
|
| 493 |
+
"eval_f1": 0.992281075326058,
|
| 494 |
+
"eval_loss": 0.03940477967262268,
|
| 495 |
+
"eval_precision": 0.9904357066950054,
|
| 496 |
+
"eval_recall": 0.9941333333333333,
|
| 497 |
+
"eval_runtime": 31.7813,
|
| 498 |
+
"eval_samples_per_second": 117.994,
|
| 499 |
+
"eval_steps_per_second": 14.757,
|
| 500 |
+
"step": 1161
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.55,
|
| 504 |
+
"learning_rate": 2.2486288848263255e-05,
|
| 505 |
+
"loss": 0.0049,
|
| 506 |
+
"step": 1204
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.55,
|
| 510 |
+
"eval_accuracy": 0.9837333333333333,
|
| 511 |
+
"eval_f1": 0.9839515916863982,
|
| 512 |
+
"eval_loss": 0.10390568524599075,
|
| 513 |
+
"eval_precision": 0.9709241952232607,
|
| 514 |
+
"eval_recall": 0.9973333333333333,
|
| 515 |
+
"eval_runtime": 31.8349,
|
| 516 |
+
"eval_samples_per_second": 117.795,
|
| 517 |
+
"eval_steps_per_second": 14.732,
|
| 518 |
+
"step": 1204
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.57,
|
| 522 |
+
"learning_rate": 2.1503656307129798e-05,
|
| 523 |
+
"loss": 0.0008,
|
| 524 |
+
"step": 1247
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.57,
|
| 528 |
+
"eval_accuracy": 0.9930666666666667,
|
| 529 |
+
"eval_f1": 0.9930851063829788,
|
| 530 |
+
"eval_loss": 0.04775088652968407,
|
| 531 |
+
"eval_precision": 0.9904509283819629,
|
| 532 |
+
"eval_recall": 0.9957333333333334,
|
| 533 |
+
"eval_runtime": 31.8926,
|
| 534 |
+
"eval_samples_per_second": 117.582,
|
| 535 |
+
"eval_steps_per_second": 14.706,
|
| 536 |
+
"step": 1247
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.59,
|
| 540 |
+
"learning_rate": 2.0521023765996345e-05,
|
| 541 |
+
"loss": 0.0437,
|
| 542 |
+
"step": 1290
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.59,
|
| 546 |
+
"eval_accuracy": 0.9848,
|
| 547 |
+
"eval_f1": 0.9849802371541502,
|
| 548 |
+
"eval_loss": 0.10180956870317459,
|
| 549 |
+
"eval_precision": 0.9734375,
|
| 550 |
+
"eval_recall": 0.9968,
|
| 551 |
+
"eval_runtime": 31.9165,
|
| 552 |
+
"eval_samples_per_second": 117.494,
|
| 553 |
+
"eval_steps_per_second": 14.695,
|
| 554 |
+
"step": 1290
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.61,
|
| 558 |
+
"learning_rate": 1.953839122486289e-05,
|
| 559 |
+
"loss": 0.0482,
|
| 560 |
+
"step": 1333
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.61,
|
| 564 |
+
"eval_accuracy": 0.9952,
|
| 565 |
+
"eval_f1": 0.995187165775401,
|
| 566 |
+
"eval_loss": 0.03259880468249321,
|
| 567 |
+
"eval_precision": 0.9978552278820375,
|
| 568 |
+
"eval_recall": 0.9925333333333334,
|
| 569 |
+
"eval_runtime": 31.8461,
|
| 570 |
+
"eval_samples_per_second": 117.754,
|
| 571 |
+
"eval_steps_per_second": 14.727,
|
| 572 |
+
"step": 1333
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.63,
|
| 576 |
+
"learning_rate": 1.8555758683729435e-05,
|
| 577 |
+
"loss": 0.0513,
|
| 578 |
+
"step": 1376
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.63,
|
| 582 |
+
"eval_accuracy": 0.9941333333333333,
|
| 583 |
+
"eval_f1": 0.9941302027748132,
|
| 584 |
+
"eval_loss": 0.03475691378116608,
|
| 585 |
+
"eval_precision": 0.99466097170315,
|
| 586 |
+
"eval_recall": 0.9936,
|
| 587 |
+
"eval_runtime": 31.7619,
|
| 588 |
+
"eval_samples_per_second": 118.066,
|
| 589 |
+
"eval_steps_per_second": 14.766,
|
| 590 |
+
"step": 1376
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.65,
|
| 594 |
+
"learning_rate": 1.7573126142595978e-05,
|
| 595 |
+
"loss": 0.0184,
|
| 596 |
+
"step": 1419
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.65,
|
| 600 |
+
"eval_accuracy": 0.9888,
|
| 601 |
+
"eval_f1": 0.9888830068819482,
|
| 602 |
+
"eval_loss": 0.07543797791004181,
|
| 603 |
+
"eval_precision": 0.9816079873883342,
|
| 604 |
+
"eval_recall": 0.9962666666666666,
|
| 605 |
+
"eval_runtime": 31.8663,
|
| 606 |
+
"eval_samples_per_second": 117.679,
|
| 607 |
+
"eval_steps_per_second": 14.718,
|
| 608 |
+
"step": 1419
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.67,
|
| 612 |
+
"learning_rate": 1.659049360146252e-05,
|
| 613 |
+
"loss": 0.0327,
|
| 614 |
+
"step": 1462
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.67,
|
| 618 |
+
"eval_accuracy": 0.9914666666666667,
|
| 619 |
+
"eval_f1": 0.9914984059511159,
|
| 620 |
+
"eval_loss": 0.05370575934648514,
|
| 621 |
+
"eval_precision": 0.9878242456326098,
|
| 622 |
+
"eval_recall": 0.9952,
|
| 623 |
+
"eval_runtime": 31.7637,
|
| 624 |
+
"eval_samples_per_second": 118.059,
|
| 625 |
+
"eval_steps_per_second": 14.765,
|
| 626 |
+
"step": 1462
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.69,
|
| 630 |
+
"learning_rate": 1.5607861060329068e-05,
|
| 631 |
+
"loss": 0.0218,
|
| 632 |
+
"step": 1505
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.69,
|
| 636 |
+
"eval_accuracy": 0.988,
|
| 637 |
+
"eval_f1": 0.9880920878539297,
|
| 638 |
+
"eval_loss": 0.07749391347169876,
|
| 639 |
+
"eval_precision": 0.9805672268907563,
|
| 640 |
+
"eval_recall": 0.9957333333333334,
|
| 641 |
+
"eval_runtime": 32.0308,
|
| 642 |
+
"eval_samples_per_second": 117.075,
|
| 643 |
+
"eval_steps_per_second": 14.642,
|
| 644 |
+
"step": 1505
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.71,
|
| 648 |
+
"learning_rate": 1.4625228519195613e-05,
|
| 649 |
+
"loss": 0.0592,
|
| 650 |
+
"step": 1548
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.71,
|
| 654 |
+
"eval_accuracy": 0.9906666666666667,
|
| 655 |
+
"eval_f1": 0.9907137171663571,
|
| 656 |
+
"eval_loss": 0.05098994821310043,
|
| 657 |
+
"eval_precision": 0.9857444561774024,
|
| 658 |
+
"eval_recall": 0.9957333333333334,
|
| 659 |
+
"eval_runtime": 32.1011,
|
| 660 |
+
"eval_samples_per_second": 116.818,
|
| 661 |
+
"eval_steps_per_second": 14.61,
|
| 662 |
+
"step": 1548
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.73,
|
| 666 |
+
"learning_rate": 1.3642595978062158e-05,
|
| 667 |
+
"loss": 0.0506,
|
| 668 |
+
"step": 1591
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.73,
|
| 672 |
+
"eval_accuracy": 0.9928,
|
| 673 |
+
"eval_f1": 0.9928172386272945,
|
| 674 |
+
"eval_loss": 0.040217798203229904,
|
| 675 |
+
"eval_precision": 0.9904458598726115,
|
| 676 |
+
"eval_recall": 0.9952,
|
| 677 |
+
"eval_runtime": 32.4765,
|
| 678 |
+
"eval_samples_per_second": 115.468,
|
| 679 |
+
"eval_steps_per_second": 14.441,
|
| 680 |
+
"step": 1591
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.75,
|
| 684 |
+
"learning_rate": 1.2659963436928701e-05,
|
| 685 |
+
"loss": 0.0228,
|
| 686 |
+
"step": 1634
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.75,
|
| 690 |
+
"eval_accuracy": 0.9946666666666667,
|
| 691 |
+
"eval_f1": 0.9946695095948828,
|
| 692 |
+
"eval_loss": 0.031395528465509415,
|
| 693 |
+
"eval_precision": 0.9941395844432606,
|
| 694 |
+
"eval_recall": 0.9952,
|
| 695 |
+
"eval_runtime": 32.1532,
|
| 696 |
+
"eval_samples_per_second": 116.629,
|
| 697 |
+
"eval_steps_per_second": 14.586,
|
| 698 |
+
"step": 1634
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.77,
|
| 702 |
+
"learning_rate": 1.1677330895795248e-05,
|
| 703 |
+
"loss": 0.0297,
|
| 704 |
+
"step": 1677
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.77,
|
| 708 |
+
"eval_accuracy": 0.9928,
|
| 709 |
+
"eval_f1": 0.9928210582291943,
|
| 710 |
+
"eval_loss": 0.044785238802433014,
|
| 711 |
+
"eval_precision": 0.9899257688229056,
|
| 712 |
+
"eval_recall": 0.9957333333333334,
|
| 713 |
+
"eval_runtime": 32.1967,
|
| 714 |
+
"eval_samples_per_second": 116.472,
|
| 715 |
+
"eval_steps_per_second": 14.567,
|
| 716 |
+
"step": 1677
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.79,
|
| 720 |
+
"learning_rate": 1.0694698354661791e-05,
|
| 721 |
+
"loss": 0.0138,
|
| 722 |
+
"step": 1720
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.79,
|
| 726 |
+
"eval_accuracy": 0.9853333333333333,
|
| 727 |
+
"eval_f1": 0.9855072463768116,
|
| 728 |
+
"eval_loss": 0.09062495082616806,
|
| 729 |
+
"eval_precision": 0.9739583333333334,
|
| 730 |
+
"eval_recall": 0.9973333333333333,
|
| 731 |
+
"eval_runtime": 32.0852,
|
| 732 |
+
"eval_samples_per_second": 116.876,
|
| 733 |
+
"eval_steps_per_second": 14.617,
|
| 734 |
+
"step": 1720
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.81,
|
| 738 |
+
"learning_rate": 9.712065813528338e-06,
|
| 739 |
+
"loss": 0.0949,
|
| 740 |
+
"step": 1763
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.81,
|
| 744 |
+
"eval_accuracy": 0.9941333333333333,
|
| 745 |
+
"eval_f1": 0.994136460554371,
|
| 746 |
+
"eval_loss": 0.028302613645792007,
|
| 747 |
+
"eval_precision": 0.9936068193926478,
|
| 748 |
+
"eval_recall": 0.9946666666666667,
|
| 749 |
+
"eval_runtime": 32.2498,
|
| 750 |
+
"eval_samples_per_second": 116.28,
|
| 751 |
+
"eval_steps_per_second": 14.543,
|
| 752 |
+
"step": 1763
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.83,
|
| 756 |
+
"learning_rate": 8.729433272394881e-06,
|
| 757 |
+
"loss": 0.0614,
|
| 758 |
+
"step": 1806
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.83,
|
| 762 |
+
"eval_accuracy": 0.9941333333333333,
|
| 763 |
+
"eval_f1": 0.9941333333333333,
|
| 764 |
+
"eval_loss": 0.029561299830675125,
|
| 765 |
+
"eval_precision": 0.9941333333333333,
|
| 766 |
+
"eval_recall": 0.9941333333333333,
|
| 767 |
+
"eval_runtime": 32.2034,
|
| 768 |
+
"eval_samples_per_second": 116.447,
|
| 769 |
+
"eval_steps_per_second": 14.564,
|
| 770 |
+
"step": 1806
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.85,
|
| 774 |
+
"learning_rate": 7.746800731261426e-06,
|
| 775 |
+
"loss": 0.0012,
|
| 776 |
+
"step": 1849
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.85,
|
| 780 |
+
"eval_accuracy": 0.9936,
|
| 781 |
+
"eval_f1": 0.9936068193926478,
|
| 782 |
+
"eval_loss": 0.03323618695139885,
|
| 783 |
+
"eval_precision": 0.9925492283129325,
|
| 784 |
+
"eval_recall": 0.9946666666666667,
|
| 785 |
+
"eval_runtime": 32.2063,
|
| 786 |
+
"eval_samples_per_second": 116.437,
|
| 787 |
+
"eval_steps_per_second": 14.562,
|
| 788 |
+
"step": 1849
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.86,
|
| 792 |
+
"learning_rate": 6.764168190127972e-06,
|
| 793 |
+
"loss": 0.015,
|
| 794 |
+
"step": 1892
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.86,
|
| 798 |
+
"eval_accuracy": 0.9944,
|
| 799 |
+
"eval_f1": 0.9943955164131306,
|
| 800 |
+
"eval_loss": 0.03202632814645767,
|
| 801 |
+
"eval_precision": 0.9951923076923077,
|
| 802 |
+
"eval_recall": 0.9936,
|
| 803 |
+
"eval_runtime": 32.1602,
|
| 804 |
+
"eval_samples_per_second": 116.604,
|
| 805 |
+
"eval_steps_per_second": 14.583,
|
| 806 |
+
"step": 1892
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.88,
|
| 810 |
+
"learning_rate": 5.781535648994515e-06,
|
| 811 |
+
"loss": 0.0266,
|
| 812 |
+
"step": 1935
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.88,
|
| 816 |
+
"eval_accuracy": 0.9922666666666666,
|
| 817 |
+
"eval_f1": 0.9922933829391443,
|
| 818 |
+
"eval_loss": 0.042477842420339584,
|
| 819 |
+
"eval_precision": 0.9888771186440678,
|
| 820 |
+
"eval_recall": 0.9957333333333334,
|
| 821 |
+
"eval_runtime": 32.2356,
|
| 822 |
+
"eval_samples_per_second": 116.331,
|
| 823 |
+
"eval_steps_per_second": 14.549,
|
| 824 |
+
"step": 1935
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.9,
|
| 828 |
+
"learning_rate": 4.798903107861061e-06,
|
| 829 |
+
"loss": 0.0292,
|
| 830 |
+
"step": 1978
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.9,
|
| 834 |
+
"eval_accuracy": 0.9901333333333333,
|
| 835 |
+
"eval_f1": 0.9901934799893983,
|
| 836 |
+
"eval_loss": 0.04828348755836487,
|
| 837 |
+
"eval_precision": 0.9841938883034773,
|
| 838 |
+
"eval_recall": 0.9962666666666666,
|
| 839 |
+
"eval_runtime": 32.2496,
|
| 840 |
+
"eval_samples_per_second": 116.281,
|
| 841 |
+
"eval_steps_per_second": 14.543,
|
| 842 |
+
"step": 1978
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.92,
|
| 846 |
+
"learning_rate": 3.816270566727605e-06,
|
| 847 |
+
"loss": 0.0141,
|
| 848 |
+
"step": 2021
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.92,
|
| 852 |
+
"eval_accuracy": 0.9890666666666666,
|
| 853 |
+
"eval_f1": 0.9891505689335803,
|
| 854 |
+
"eval_loss": 0.052797310054302216,
|
| 855 |
+
"eval_precision": 0.9816176470588235,
|
| 856 |
+
"eval_recall": 0.9968,
|
| 857 |
+
"eval_runtime": 32.2638,
|
| 858 |
+
"eval_samples_per_second": 116.229,
|
| 859 |
+
"eval_steps_per_second": 14.536,
|
| 860 |
+
"step": 2021
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.94,
|
| 864 |
+
"learning_rate": 2.83363802559415e-06,
|
| 865 |
+
"loss": 0.0006,
|
| 866 |
+
"step": 2064
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.94,
|
| 870 |
+
"eval_accuracy": 0.9909333333333333,
|
| 871 |
+
"eval_f1": 0.9909862142099681,
|
| 872 |
+
"eval_loss": 0.04819910600781441,
|
| 873 |
+
"eval_precision": 0.985239852398524,
|
| 874 |
+
"eval_recall": 0.9968,
|
| 875 |
+
"eval_runtime": 32.596,
|
| 876 |
+
"eval_samples_per_second": 115.045,
|
| 877 |
+
"eval_steps_per_second": 14.388,
|
| 878 |
+
"step": 2064
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.96,
|
| 882 |
+
"learning_rate": 1.851005484460695e-06,
|
| 883 |
+
"loss": 0.0225,
|
| 884 |
+
"step": 2107
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.96,
|
| 888 |
+
"eval_accuracy": 0.9922666666666666,
|
| 889 |
+
"eval_f1": 0.9922933829391443,
|
| 890 |
+
"eval_loss": 0.03804012015461922,
|
| 891 |
+
"eval_precision": 0.9888771186440678,
|
| 892 |
+
"eval_recall": 0.9957333333333334,
|
| 893 |
+
"eval_runtime": 32.1606,
|
| 894 |
+
"eval_samples_per_second": 116.602,
|
| 895 |
+
"eval_steps_per_second": 14.583,
|
| 896 |
+
"step": 2107
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.98,
|
| 900 |
+
"learning_rate": 8.683729433272396e-07,
|
| 901 |
+
"loss": 0.0199,
|
| 902 |
+
"step": 2150
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.98,
|
| 906 |
+
"eval_accuracy": 0.9925333333333334,
|
| 907 |
+
"eval_f1": 0.9925492283129324,
|
| 908 |
+
"eval_loss": 0.036869850009679794,
|
| 909 |
+
"eval_precision": 0.9904407859798194,
|
| 910 |
+
"eval_recall": 0.9946666666666667,
|
| 911 |
+
"eval_runtime": 32.2379,
|
| 912 |
+
"eval_samples_per_second": 116.323,
|
| 913 |
+
"eval_steps_per_second": 14.548,
|
| 914 |
+
"step": 2150
|
| 915 |
+
}
|
| 916 |
+
],
|
| 917 |
+
"max_steps": 2188,
|
| 918 |
+
"num_train_epochs": 1,
|
| 919 |
+
"total_flos": 4604443468800000.0,
|
| 920 |
+
"trial_name": null,
|
| 921 |
+
"trial_params": null
|
| 922 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4abcbcb0e793c20ba879c1c33344ec0286718691f8480e70240e684b2ecc0883
|
| 3 |
+
size 3451
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|