Commit
•
19d383d
1
Parent(s):
ce0094f
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 sha256:486e5e4769d3c92716600b6a095f8dc24bd7a275447755d1f09ab8e6402a66e2
|
| 3 |
+
size 997344965
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:149770c2c20e9c68fc91076f4c54d71bbb4483287408f1513a749d00dd140142
|
| 3 |
+
size 498662069
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ef13ebee760fa9462ec40b69f70c0ec528d43ffa79815160f0dbdd5ca853387
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69cba08054b3bf2fbdc80fa4968315fe57d8a157dcab8404be1077c8de4d7657
|
| 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": 2625,
|
| 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": 4.998095238095239e-05,
|
| 13 |
+
"loss": 0.7271,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 4.900952380952381e-05,
|
| 19 |
+
"loss": 0.2895,
|
| 20 |
+
"step": 52
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"eval_accuracy": 0.9933333333333333,
|
| 25 |
+
"eval_f1": 0.9933451641526175,
|
| 26 |
+
"eval_loss": 0.02848968468606472,
|
| 27 |
+
"eval_precision": 0.991585473870682,
|
| 28 |
+
"eval_recall": 0.9951111111111111,
|
| 29 |
+
"eval_runtime": 53.465,
|
| 30 |
+
"eval_samples_per_second": 84.167,
|
| 31 |
+
"eval_steps_per_second": 10.53,
|
| 32 |
+
"step": 52
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.04,
|
| 36 |
+
"learning_rate": 4.8019047619047617e-05,
|
| 37 |
+
"loss": 0.0128,
|
| 38 |
+
"step": 104
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04,
|
| 42 |
+
"eval_accuracy": 0.9951111111111111,
|
| 43 |
+
"eval_f1": 0.9950914770191879,
|
| 44 |
+
"eval_loss": 0.03895995765924454,
|
| 45 |
+
"eval_precision": 0.9991039426523297,
|
| 46 |
+
"eval_recall": 0.9911111111111112,
|
| 47 |
+
"eval_runtime": 52.7075,
|
| 48 |
+
"eval_samples_per_second": 85.377,
|
| 49 |
+
"eval_steps_per_second": 10.682,
|
| 50 |
+
"step": 104
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.06,
|
| 54 |
+
"learning_rate": 4.702857142857143e-05,
|
| 55 |
+
"loss": 0.0362,
|
| 56 |
+
"step": 156
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"eval_accuracy": 0.9928888888888889,
|
| 61 |
+
"eval_f1": 0.9929203539823008,
|
| 62 |
+
"eval_loss": 0.046059854328632355,
|
| 63 |
+
"eval_precision": 0.9885462555066079,
|
| 64 |
+
"eval_recall": 0.9973333333333333,
|
| 65 |
+
"eval_runtime": 52.6732,
|
| 66 |
+
"eval_samples_per_second": 85.432,
|
| 67 |
+
"eval_steps_per_second": 10.689,
|
| 68 |
+
"step": 156
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.08,
|
| 72 |
+
"learning_rate": 4.6038095238095244e-05,
|
| 73 |
+
"loss": 0.0746,
|
| 74 |
+
"step": 208
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.08,
|
| 78 |
+
"eval_accuracy": 0.994,
|
| 79 |
+
"eval_f1": 0.9939718687206966,
|
| 80 |
+
"eval_loss": 0.037436459213495255,
|
| 81 |
+
"eval_precision": 0.9986541049798116,
|
| 82 |
+
"eval_recall": 0.9893333333333333,
|
| 83 |
+
"eval_runtime": 54.0208,
|
| 84 |
+
"eval_samples_per_second": 83.301,
|
| 85 |
+
"eval_steps_per_second": 10.422,
|
| 86 |
+
"step": 208
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1,
|
| 90 |
+
"learning_rate": 4.504761904761905e-05,
|
| 91 |
+
"loss": 0.065,
|
| 92 |
+
"step": 260
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.1,
|
| 96 |
+
"eval_accuracy": 0.9964444444444445,
|
| 97 |
+
"eval_f1": 0.9964349376114082,
|
| 98 |
+
"eval_loss": 0.015599595382809639,
|
| 99 |
+
"eval_precision": 0.9991063449508489,
|
| 100 |
+
"eval_recall": 0.9937777777777778,
|
| 101 |
+
"eval_runtime": 52.5898,
|
| 102 |
+
"eval_samples_per_second": 85.568,
|
| 103 |
+
"eval_steps_per_second": 10.706,
|
| 104 |
+
"step": 260
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.12,
|
| 108 |
+
"learning_rate": 4.405714285714286e-05,
|
| 109 |
+
"loss": 0.018,
|
| 110 |
+
"step": 312
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.12,
|
| 114 |
+
"eval_accuracy": 0.9977777777777778,
|
| 115 |
+
"eval_f1": 0.9977787649933363,
|
| 116 |
+
"eval_loss": 0.013370415195822716,
|
| 117 |
+
"eval_precision": 0.9973357015985791,
|
| 118 |
+
"eval_recall": 0.9982222222222222,
|
| 119 |
+
"eval_runtime": 52.6939,
|
| 120 |
+
"eval_samples_per_second": 85.399,
|
| 121 |
+
"eval_steps_per_second": 10.684,
|
| 122 |
+
"step": 312
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14,
|
| 126 |
+
"learning_rate": 4.3066666666666665e-05,
|
| 127 |
+
"loss": 0.0021,
|
| 128 |
+
"step": 364
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.14,
|
| 132 |
+
"eval_accuracy": 0.9968888888888889,
|
| 133 |
+
"eval_f1": 0.9968819599109132,
|
| 134 |
+
"eval_loss": 0.026465779170393944,
|
| 135 |
+
"eval_precision": 0.9991071428571429,
|
| 136 |
+
"eval_recall": 0.9946666666666667,
|
| 137 |
+
"eval_runtime": 52.8294,
|
| 138 |
+
"eval_samples_per_second": 85.18,
|
| 139 |
+
"eval_steps_per_second": 10.657,
|
| 140 |
+
"step": 364
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.16,
|
| 144 |
+
"learning_rate": 4.207619047619048e-05,
|
| 145 |
+
"loss": 0.0385,
|
| 146 |
+
"step": 416
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.16,
|
| 150 |
+
"eval_accuracy": 0.9968888888888889,
|
| 151 |
+
"eval_f1": 0.9968791796700847,
|
| 152 |
+
"eval_loss": 0.019380465149879456,
|
| 153 |
+
"eval_precision": 1.0,
|
| 154 |
+
"eval_recall": 0.9937777777777778,
|
| 155 |
+
"eval_runtime": 53.1835,
|
| 156 |
+
"eval_samples_per_second": 84.613,
|
| 157 |
+
"eval_steps_per_second": 10.586,
|
| 158 |
+
"step": 416
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.18,
|
| 162 |
+
"learning_rate": 4.1085714285714286e-05,
|
| 163 |
+
"loss": 0.0158,
|
| 164 |
+
"step": 468
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.18,
|
| 168 |
+
"eval_accuracy": 0.9926666666666667,
|
| 169 |
+
"eval_f1": 0.9926124916051041,
|
| 170 |
+
"eval_loss": 0.05080940201878548,
|
| 171 |
+
"eval_precision": 1.0,
|
| 172 |
+
"eval_recall": 0.9853333333333333,
|
| 173 |
+
"eval_runtime": 53.8229,
|
| 174 |
+
"eval_samples_per_second": 83.608,
|
| 175 |
+
"eval_steps_per_second": 10.46,
|
| 176 |
+
"step": 468
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.2,
|
| 180 |
+
"learning_rate": 4.00952380952381e-05,
|
| 181 |
+
"loss": 0.0483,
|
| 182 |
+
"step": 520
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.2,
|
| 186 |
+
"eval_accuracy": 0.9926666666666667,
|
| 187 |
+
"eval_f1": 0.9926974994467802,
|
| 188 |
+
"eval_loss": 0.03643398359417915,
|
| 189 |
+
"eval_precision": 0.988541207580432,
|
| 190 |
+
"eval_recall": 0.9968888888888889,
|
| 191 |
+
"eval_runtime": 53.9013,
|
| 192 |
+
"eval_samples_per_second": 83.486,
|
| 193 |
+
"eval_steps_per_second": 10.445,
|
| 194 |
+
"step": 520
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.22,
|
| 198 |
+
"learning_rate": 3.910476190476191e-05,
|
| 199 |
+
"loss": 0.0008,
|
| 200 |
+
"step": 572
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.22,
|
| 204 |
+
"eval_accuracy": 0.9968888888888889,
|
| 205 |
+
"eval_f1": 0.9968791796700847,
|
| 206 |
+
"eval_loss": 0.02641967684030533,
|
| 207 |
+
"eval_precision": 1.0,
|
| 208 |
+
"eval_recall": 0.9937777777777778,
|
| 209 |
+
"eval_runtime": 52.853,
|
| 210 |
+
"eval_samples_per_second": 85.142,
|
| 211 |
+
"eval_steps_per_second": 10.652,
|
| 212 |
+
"step": 572
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.24,
|
| 216 |
+
"learning_rate": 3.8114285714285714e-05,
|
| 217 |
+
"loss": 0.0445,
|
| 218 |
+
"step": 624
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.24,
|
| 222 |
+
"eval_accuracy": 0.9937777777777778,
|
| 223 |
+
"eval_f1": 0.9937998228520815,
|
| 224 |
+
"eval_loss": 0.04403863102197647,
|
| 225 |
+
"eval_precision": 0.9902912621359223,
|
| 226 |
+
"eval_recall": 0.9973333333333333,
|
| 227 |
+
"eval_runtime": 52.6526,
|
| 228 |
+
"eval_samples_per_second": 85.466,
|
| 229 |
+
"eval_steps_per_second": 10.693,
|
| 230 |
+
"step": 624
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.26,
|
| 234 |
+
"learning_rate": 3.712380952380953e-05,
|
| 235 |
+
"loss": 0.0659,
|
| 236 |
+
"step": 676
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.26,
|
| 240 |
+
"eval_accuracy": 0.9977777777777778,
|
| 241 |
+
"eval_f1": 0.9977738201246661,
|
| 242 |
+
"eval_loss": 0.0159127339720726,
|
| 243 |
+
"eval_precision": 0.9995539696699376,
|
| 244 |
+
"eval_recall": 0.996,
|
| 245 |
+
"eval_runtime": 52.8265,
|
| 246 |
+
"eval_samples_per_second": 85.184,
|
| 247 |
+
"eval_steps_per_second": 10.658,
|
| 248 |
+
"step": 676
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.28,
|
| 252 |
+
"learning_rate": 3.6133333333333335e-05,
|
| 253 |
+
"loss": 0.0002,
|
| 254 |
+
"step": 728
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.28,
|
| 258 |
+
"eval_accuracy": 0.9977777777777778,
|
| 259 |
+
"eval_f1": 0.9977738201246661,
|
| 260 |
+
"eval_loss": 0.019492752850055695,
|
| 261 |
+
"eval_precision": 0.9995539696699376,
|
| 262 |
+
"eval_recall": 0.996,
|
| 263 |
+
"eval_runtime": 52.6759,
|
| 264 |
+
"eval_samples_per_second": 85.428,
|
| 265 |
+
"eval_steps_per_second": 10.688,
|
| 266 |
+
"step": 728
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.3,
|
| 270 |
+
"learning_rate": 3.514285714285714e-05,
|
| 271 |
+
"loss": 0.0001,
|
| 272 |
+
"step": 780
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.3,
|
| 276 |
+
"eval_accuracy": 0.9977777777777778,
|
| 277 |
+
"eval_f1": 0.9977738201246661,
|
| 278 |
+
"eval_loss": 0.020457539707422256,
|
| 279 |
+
"eval_precision": 0.9995539696699376,
|
| 280 |
+
"eval_recall": 0.996,
|
| 281 |
+
"eval_runtime": 53.9153,
|
| 282 |
+
"eval_samples_per_second": 83.464,
|
| 283 |
+
"eval_steps_per_second": 10.442,
|
| 284 |
+
"step": 780
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.32,
|
| 288 |
+
"learning_rate": 3.415238095238095e-05,
|
| 289 |
+
"loss": 0.0376,
|
| 290 |
+
"step": 832
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.32,
|
| 294 |
+
"eval_accuracy": 0.9975555555555555,
|
| 295 |
+
"eval_f1": 0.9975506568692942,
|
| 296 |
+
"eval_loss": 0.017426395788788795,
|
| 297 |
+
"eval_precision": 0.999553770638108,
|
| 298 |
+
"eval_recall": 0.9955555555555555,
|
| 299 |
+
"eval_runtime": 52.8865,
|
| 300 |
+
"eval_samples_per_second": 85.088,
|
| 301 |
+
"eval_steps_per_second": 10.645,
|
| 302 |
+
"step": 832
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.34,
|
| 306 |
+
"learning_rate": 3.316190476190476e-05,
|
| 307 |
+
"loss": 0.0003,
|
| 308 |
+
"step": 884
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.34,
|
| 312 |
+
"eval_accuracy": 0.9915555555555555,
|
| 313 |
+
"eval_f1": 0.9916114790286976,
|
| 314 |
+
"eval_loss": 0.07331586629152298,
|
| 315 |
+
"eval_precision": 0.9850877192982456,
|
| 316 |
+
"eval_recall": 0.9982222222222222,
|
| 317 |
+
"eval_runtime": 52.7607,
|
| 318 |
+
"eval_samples_per_second": 85.291,
|
| 319 |
+
"eval_steps_per_second": 10.671,
|
| 320 |
+
"step": 884
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.36,
|
| 324 |
+
"learning_rate": 3.217142857142858e-05,
|
| 325 |
+
"loss": 0.0386,
|
| 326 |
+
"step": 936
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.36,
|
| 330 |
+
"eval_accuracy": 0.9977777777777778,
|
| 331 |
+
"eval_f1": 0.997774810858923,
|
| 332 |
+
"eval_loss": 0.01634088158607483,
|
| 333 |
+
"eval_precision": 0.9991087344028521,
|
| 334 |
+
"eval_recall": 0.9964444444444445,
|
| 335 |
+
"eval_runtime": 52.7493,
|
| 336 |
+
"eval_samples_per_second": 85.309,
|
| 337 |
+
"eval_steps_per_second": 10.673,
|
| 338 |
+
"step": 936
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.38,
|
| 342 |
+
"learning_rate": 3.1180952380952384e-05,
|
| 343 |
+
"loss": 0.0189,
|
| 344 |
+
"step": 988
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.38,
|
| 348 |
+
"eval_accuracy": 0.996,
|
| 349 |
+
"eval_f1": 0.9960035523978685,
|
| 350 |
+
"eval_loss": 0.017804233357310295,
|
| 351 |
+
"eval_precision": 0.9951197870452528,
|
| 352 |
+
"eval_recall": 0.9968888888888889,
|
| 353 |
+
"eval_runtime": 53.7392,
|
| 354 |
+
"eval_samples_per_second": 83.738,
|
| 355 |
+
"eval_steps_per_second": 10.477,
|
| 356 |
+
"step": 988
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.4,
|
| 360 |
+
"learning_rate": 3.019047619047619e-05,
|
| 361 |
+
"loss": 0.0087,
|
| 362 |
+
"step": 1040
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.4,
|
| 366 |
+
"eval_accuracy": 0.9962222222222222,
|
| 367 |
+
"eval_f1": 0.9962230615418795,
|
| 368 |
+
"eval_loss": 0.027117114514112473,
|
| 369 |
+
"eval_precision": 0.9960017769880053,
|
| 370 |
+
"eval_recall": 0.9964444444444445,
|
| 371 |
+
"eval_runtime": 52.7187,
|
| 372 |
+
"eval_samples_per_second": 85.359,
|
| 373 |
+
"eval_steps_per_second": 10.679,
|
| 374 |
+
"step": 1040
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.42,
|
| 378 |
+
"learning_rate": 2.9199999999999998e-05,
|
| 379 |
+
"loss": 0.0003,
|
| 380 |
+
"step": 1092
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.42,
|
| 384 |
+
"eval_accuracy": 0.9942222222222222,
|
| 385 |
+
"eval_f1": 0.994188645507376,
|
| 386 |
+
"eval_loss": 0.04296413064002991,
|
| 387 |
+
"eval_precision": 1.0,
|
| 388 |
+
"eval_recall": 0.9884444444444445,
|
| 389 |
+
"eval_runtime": 53.6263,
|
| 390 |
+
"eval_samples_per_second": 83.914,
|
| 391 |
+
"eval_steps_per_second": 10.499,
|
| 392 |
+
"step": 1092
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.44,
|
| 396 |
+
"learning_rate": 2.8209523809523812e-05,
|
| 397 |
+
"loss": 0.0783,
|
| 398 |
+
"step": 1144
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.44,
|
| 402 |
+
"eval_accuracy": 0.9737777777777777,
|
| 403 |
+
"eval_f1": 0.9744367417677643,
|
| 404 |
+
"eval_loss": 0.18719656765460968,
|
| 405 |
+
"eval_precision": 0.9505494505494505,
|
| 406 |
+
"eval_recall": 0.9995555555555555,
|
| 407 |
+
"eval_runtime": 54.0229,
|
| 408 |
+
"eval_samples_per_second": 83.298,
|
| 409 |
+
"eval_steps_per_second": 10.422,
|
| 410 |
+
"step": 1144
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.46,
|
| 414 |
+
"learning_rate": 2.7219047619047623e-05,
|
| 415 |
+
"loss": 0.0383,
|
| 416 |
+
"step": 1196
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.46,
|
| 420 |
+
"eval_accuracy": 0.9971111111111111,
|
| 421 |
+
"eval_f1": 0.9971104689931096,
|
| 422 |
+
"eval_loss": 0.020702555775642395,
|
| 423 |
+
"eval_precision": 0.997332147621165,
|
| 424 |
+
"eval_recall": 0.9968888888888889,
|
| 425 |
+
"eval_runtime": 52.7011,
|
| 426 |
+
"eval_samples_per_second": 85.387,
|
| 427 |
+
"eval_steps_per_second": 10.683,
|
| 428 |
+
"step": 1196
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.48,
|
| 432 |
+
"learning_rate": 2.622857142857143e-05,
|
| 433 |
+
"loss": 0.0674,
|
| 434 |
+
"step": 1248
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.48,
|
| 438 |
+
"eval_accuracy": 0.9973333333333333,
|
| 439 |
+
"eval_f1": 0.9973262032085561,
|
| 440 |
+
"eval_loss": 0.01964743435382843,
|
| 441 |
+
"eval_precision": 1.0,
|
| 442 |
+
"eval_recall": 0.9946666666666667,
|
| 443 |
+
"eval_runtime": 52.7411,
|
| 444 |
+
"eval_samples_per_second": 85.322,
|
| 445 |
+
"eval_steps_per_second": 10.675,
|
| 446 |
+
"step": 1248
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.5,
|
| 450 |
+
"learning_rate": 2.523809523809524e-05,
|
| 451 |
+
"loss": 0.0619,
|
| 452 |
+
"step": 1300
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.5,
|
| 456 |
+
"eval_accuracy": 0.9973333333333333,
|
| 457 |
+
"eval_f1": 0.9973273942093541,
|
| 458 |
+
"eval_loss": 0.021862877532839775,
|
| 459 |
+
"eval_precision": 0.9995535714285714,
|
| 460 |
+
"eval_recall": 0.9951111111111111,
|
| 461 |
+
"eval_runtime": 52.7015,
|
| 462 |
+
"eval_samples_per_second": 85.387,
|
| 463 |
+
"eval_steps_per_second": 10.683,
|
| 464 |
+
"step": 1300
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.52,
|
| 468 |
+
"learning_rate": 2.424761904761905e-05,
|
| 469 |
+
"loss": 0.0208,
|
| 470 |
+
"step": 1352
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.52,
|
| 474 |
+
"eval_accuracy": 0.9973333333333333,
|
| 475 |
+
"eval_f1": 0.9973297730307076,
|
| 476 |
+
"eval_loss": 0.01971598155796528,
|
| 477 |
+
"eval_precision": 0.9986631016042781,
|
| 478 |
+
"eval_recall": 0.996,
|
| 479 |
+
"eval_runtime": 53.8268,
|
| 480 |
+
"eval_samples_per_second": 83.602,
|
| 481 |
+
"eval_steps_per_second": 10.459,
|
| 482 |
+
"step": 1352
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.53,
|
| 486 |
+
"learning_rate": 2.3257142857142858e-05,
|
| 487 |
+
"loss": 0.0407,
|
| 488 |
+
"step": 1404
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.53,
|
| 492 |
+
"eval_accuracy": 0.9973333333333333,
|
| 493 |
+
"eval_f1": 0.9973309608540925,
|
| 494 |
+
"eval_loss": 0.01426586601883173,
|
| 495 |
+
"eval_precision": 0.9982190560997328,
|
| 496 |
+
"eval_recall": 0.9964444444444445,
|
| 497 |
+
"eval_runtime": 53.9464,
|
| 498 |
+
"eval_samples_per_second": 83.416,
|
| 499 |
+
"eval_steps_per_second": 10.436,
|
| 500 |
+
"step": 1404
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.55,
|
| 504 |
+
"learning_rate": 2.2266666666666668e-05,
|
| 505 |
+
"loss": 0.0003,
|
| 506 |
+
"step": 1456
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.55,
|
| 510 |
+
"eval_accuracy": 0.9973333333333333,
|
| 511 |
+
"eval_f1": 0.9973309608540925,
|
| 512 |
+
"eval_loss": 0.01685367338359356,
|
| 513 |
+
"eval_precision": 0.9982190560997328,
|
| 514 |
+
"eval_recall": 0.9964444444444445,
|
| 515 |
+
"eval_runtime": 54.279,
|
| 516 |
+
"eval_samples_per_second": 82.905,
|
| 517 |
+
"eval_steps_per_second": 10.372,
|
| 518 |
+
"step": 1456
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.57,
|
| 522 |
+
"learning_rate": 2.127619047619048e-05,
|
| 523 |
+
"loss": 0.0185,
|
| 524 |
+
"step": 1508
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.57,
|
| 528 |
+
"eval_accuracy": 0.9973333333333333,
|
| 529 |
+
"eval_f1": 0.9973273942093541,
|
| 530 |
+
"eval_loss": 0.018773263320326805,
|
| 531 |
+
"eval_precision": 0.9995535714285714,
|
| 532 |
+
"eval_recall": 0.9951111111111111,
|
| 533 |
+
"eval_runtime": 54.1737,
|
| 534 |
+
"eval_samples_per_second": 83.066,
|
| 535 |
+
"eval_steps_per_second": 10.393,
|
| 536 |
+
"step": 1508
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.59,
|
| 540 |
+
"learning_rate": 2.0285714285714286e-05,
|
| 541 |
+
"loss": 0.0334,
|
| 542 |
+
"step": 1560
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.59,
|
| 546 |
+
"eval_accuracy": 0.9977777777777778,
|
| 547 |
+
"eval_f1": 0.9977738201246661,
|
| 548 |
+
"eval_loss": 0.015659423545002937,
|
| 549 |
+
"eval_precision": 0.9995539696699376,
|
| 550 |
+
"eval_recall": 0.996,
|
| 551 |
+
"eval_runtime": 54.2691,
|
| 552 |
+
"eval_samples_per_second": 82.92,
|
| 553 |
+
"eval_steps_per_second": 10.374,
|
| 554 |
+
"step": 1560
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.61,
|
| 558 |
+
"learning_rate": 1.9295238095238096e-05,
|
| 559 |
+
"loss": 0.0374,
|
| 560 |
+
"step": 1612
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.61,
|
| 564 |
+
"eval_accuracy": 0.9913333333333333,
|
| 565 |
+
"eval_f1": 0.9913774043776254,
|
| 566 |
+
"eval_loss": 0.06105850636959076,
|
| 567 |
+
"eval_precision": 0.9863616366036075,
|
| 568 |
+
"eval_recall": 0.9964444444444445,
|
| 569 |
+
"eval_runtime": 53.9747,
|
| 570 |
+
"eval_samples_per_second": 83.372,
|
| 571 |
+
"eval_steps_per_second": 10.431,
|
| 572 |
+
"step": 1612
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.63,
|
| 576 |
+
"learning_rate": 1.8304761904761906e-05,
|
| 577 |
+
"loss": 0.0332,
|
| 578 |
+
"step": 1664
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.63,
|
| 582 |
+
"eval_accuracy": 0.9977777777777778,
|
| 583 |
+
"eval_f1": 0.9977728285077951,
|
| 584 |
+
"eval_loss": 0.017448944970965385,
|
| 585 |
+
"eval_precision": 1.0,
|
| 586 |
+
"eval_recall": 0.9955555555555555,
|
| 587 |
+
"eval_runtime": 52.8918,
|
| 588 |
+
"eval_samples_per_second": 85.079,
|
| 589 |
+
"eval_steps_per_second": 10.644,
|
| 590 |
+
"step": 1664
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.65,
|
| 594 |
+
"learning_rate": 1.7314285714285717e-05,
|
| 595 |
+
"loss": 0.0003,
|
| 596 |
+
"step": 1716
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.65,
|
| 600 |
+
"eval_accuracy": 0.9977777777777778,
|
| 601 |
+
"eval_f1": 0.9977728285077951,
|
| 602 |
+
"eval_loss": 0.018406476825475693,
|
| 603 |
+
"eval_precision": 1.0,
|
| 604 |
+
"eval_recall": 0.9955555555555555,
|
| 605 |
+
"eval_runtime": 53.9635,
|
| 606 |
+
"eval_samples_per_second": 83.39,
|
| 607 |
+
"eval_steps_per_second": 10.433,
|
| 608 |
+
"step": 1716
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.67,
|
| 612 |
+
"learning_rate": 1.6323809523809524e-05,
|
| 613 |
+
"loss": 0.0542,
|
| 614 |
+
"step": 1768
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.67,
|
| 618 |
+
"eval_accuracy": 0.9975555555555555,
|
| 619 |
+
"eval_f1": 0.9975517471622524,
|
| 620 |
+
"eval_loss": 0.013020477257668972,
|
| 621 |
+
"eval_precision": 0.9991083370485956,
|
| 622 |
+
"eval_recall": 0.996,
|
| 623 |
+
"eval_runtime": 53.3551,
|
| 624 |
+
"eval_samples_per_second": 84.341,
|
| 625 |
+
"eval_steps_per_second": 10.552,
|
| 626 |
+
"step": 1768
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.69,
|
| 630 |
+
"learning_rate": 1.5333333333333334e-05,
|
| 631 |
+
"loss": 0.0354,
|
| 632 |
+
"step": 1820
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.69,
|
| 636 |
+
"eval_accuracy": 0.9973333333333333,
|
| 637 |
+
"eval_f1": 0.997332147621165,
|
| 638 |
+
"eval_loss": 0.013979670591652393,
|
| 639 |
+
"eval_precision": 0.9977758007117438,
|
| 640 |
+
"eval_recall": 0.9968888888888889,
|
| 641 |
+
"eval_runtime": 53.9647,
|
| 642 |
+
"eval_samples_per_second": 83.388,
|
| 643 |
+
"eval_steps_per_second": 10.433,
|
| 644 |
+
"step": 1820
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.71,
|
| 648 |
+
"learning_rate": 1.4342857142857143e-05,
|
| 649 |
+
"loss": 0.0003,
|
| 650 |
+
"step": 1872
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.71,
|
| 654 |
+
"eval_accuracy": 0.9975555555555555,
|
| 655 |
+
"eval_f1": 0.9975517471622524,
|
| 656 |
+
"eval_loss": 0.016862161457538605,
|
| 657 |
+
"eval_precision": 0.9991083370485956,
|
| 658 |
+
"eval_recall": 0.996,
|
| 659 |
+
"eval_runtime": 52.8464,
|
| 660 |
+
"eval_samples_per_second": 85.152,
|
| 661 |
+
"eval_steps_per_second": 10.654,
|
| 662 |
+
"step": 1872
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.73,
|
| 666 |
+
"learning_rate": 1.3352380952380952e-05,
|
| 667 |
+
"loss": 0.0052,
|
| 668 |
+
"step": 1924
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.73,
|
| 672 |
+
"eval_accuracy": 0.9977777777777778,
|
| 673 |
+
"eval_f1": 0.9977738201246661,
|
| 674 |
+
"eval_loss": 0.01669122278690338,
|
| 675 |
+
"eval_precision": 0.9995539696699376,
|
| 676 |
+
"eval_recall": 0.996,
|
| 677 |
+
"eval_runtime": 52.8849,
|
| 678 |
+
"eval_samples_per_second": 85.09,
|
| 679 |
+
"eval_steps_per_second": 10.646,
|
| 680 |
+
"step": 1924
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.75,
|
| 684 |
+
"learning_rate": 1.2361904761904762e-05,
|
| 685 |
+
"loss": 0.0001,
|
| 686 |
+
"step": 1976
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.75,
|
| 690 |
+
"eval_accuracy": 0.9977777777777778,
|
| 691 |
+
"eval_f1": 0.9977738201246661,
|
| 692 |
+
"eval_loss": 0.016820691525936127,
|
| 693 |
+
"eval_precision": 0.9995539696699376,
|
| 694 |
+
"eval_recall": 0.996,
|
| 695 |
+
"eval_runtime": 53.752,
|
| 696 |
+
"eval_samples_per_second": 83.718,
|
| 697 |
+
"eval_steps_per_second": 10.474,
|
| 698 |
+
"step": 1976
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.77,
|
| 702 |
+
"learning_rate": 1.1371428571428571e-05,
|
| 703 |
+
"loss": 0.0001,
|
| 704 |
+
"step": 2028
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.77,
|
| 708 |
+
"eval_accuracy": 0.9977777777777778,
|
| 709 |
+
"eval_f1": 0.9977738201246661,
|
| 710 |
+
"eval_loss": 0.017111966386437416,
|
| 711 |
+
"eval_precision": 0.9995539696699376,
|
| 712 |
+
"eval_recall": 0.996,
|
| 713 |
+
"eval_runtime": 53.4254,
|
| 714 |
+
"eval_samples_per_second": 84.23,
|
| 715 |
+
"eval_steps_per_second": 10.538,
|
| 716 |
+
"step": 2028
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.79,
|
| 720 |
+
"learning_rate": 1.0380952380952382e-05,
|
| 721 |
+
"loss": 0.0001,
|
| 722 |
+
"step": 2080
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.79,
|
| 726 |
+
"eval_accuracy": 0.9977777777777778,
|
| 727 |
+
"eval_f1": 0.9977738201246661,
|
| 728 |
+
"eval_loss": 0.017430588603019714,
|
| 729 |
+
"eval_precision": 0.9995539696699376,
|
| 730 |
+
"eval_recall": 0.996,
|
| 731 |
+
"eval_runtime": 54.0709,
|
| 732 |
+
"eval_samples_per_second": 83.224,
|
| 733 |
+
"eval_steps_per_second": 10.412,
|
| 734 |
+
"step": 2080
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.81,
|
| 738 |
+
"learning_rate": 9.39047619047619e-06,
|
| 739 |
+
"loss": 0.0545,
|
| 740 |
+
"step": 2132
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.81,
|
| 744 |
+
"eval_accuracy": 0.9973333333333333,
|
| 745 |
+
"eval_f1": 0.997335701598579,
|
| 746 |
+
"eval_loss": 0.016096895560622215,
|
| 747 |
+
"eval_precision": 0.9964507542147294,
|
| 748 |
+
"eval_recall": 0.9982222222222222,
|
| 749 |
+
"eval_runtime": 52.7688,
|
| 750 |
+
"eval_samples_per_second": 85.278,
|
| 751 |
+
"eval_steps_per_second": 10.669,
|
| 752 |
+
"step": 2132
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.83,
|
| 756 |
+
"learning_rate": 8.400000000000001e-06,
|
| 757 |
+
"loss": 0.0006,
|
| 758 |
+
"step": 2184
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.83,
|
| 762 |
+
"eval_accuracy": 0.9977777777777778,
|
| 763 |
+
"eval_f1": 0.997774810858923,
|
| 764 |
+
"eval_loss": 0.013929061591625214,
|
| 765 |
+
"eval_precision": 0.9991087344028521,
|
| 766 |
+
"eval_recall": 0.9964444444444445,
|
| 767 |
+
"eval_runtime": 54.6395,
|
| 768 |
+
"eval_samples_per_second": 82.358,
|
| 769 |
+
"eval_steps_per_second": 10.304,
|
| 770 |
+
"step": 2184
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.85,
|
| 774 |
+
"learning_rate": 7.40952380952381e-06,
|
| 775 |
+
"loss": 0.0208,
|
| 776 |
+
"step": 2236
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.85,
|
| 780 |
+
"eval_accuracy": 0.998,
|
| 781 |
+
"eval_f1": 0.9979959919839679,
|
| 782 |
+
"eval_loss": 0.015503444708883762,
|
| 783 |
+
"eval_precision": 1.0,
|
| 784 |
+
"eval_recall": 0.996,
|
| 785 |
+
"eval_runtime": 52.9508,
|
| 786 |
+
"eval_samples_per_second": 84.984,
|
| 787 |
+
"eval_steps_per_second": 10.633,
|
| 788 |
+
"step": 2236
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.87,
|
| 792 |
+
"learning_rate": 6.419047619047619e-06,
|
| 793 |
+
"loss": 0.0204,
|
| 794 |
+
"step": 2288
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.87,
|
| 798 |
+
"eval_accuracy": 0.998,
|
| 799 |
+
"eval_f1": 0.9979959919839679,
|
| 800 |
+
"eval_loss": 0.014153528958559036,
|
| 801 |
+
"eval_precision": 1.0,
|
| 802 |
+
"eval_recall": 0.996,
|
| 803 |
+
"eval_runtime": 52.7536,
|
| 804 |
+
"eval_samples_per_second": 85.302,
|
| 805 |
+
"eval_steps_per_second": 10.672,
|
| 806 |
+
"step": 2288
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.89,
|
| 810 |
+
"learning_rate": 5.428571428571429e-06,
|
| 811 |
+
"loss": 0.0129,
|
| 812 |
+
"step": 2340
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.89,
|
| 816 |
+
"eval_accuracy": 0.998,
|
| 817 |
+
"eval_f1": 0.997996884041843,
|
| 818 |
+
"eval_loss": 0.012016250751912594,
|
| 819 |
+
"eval_precision": 0.9995541685242978,
|
| 820 |
+
"eval_recall": 0.9964444444444445,
|
| 821 |
+
"eval_runtime": 52.656,
|
| 822 |
+
"eval_samples_per_second": 85.46,
|
| 823 |
+
"eval_steps_per_second": 10.692,
|
| 824 |
+
"step": 2340
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.91,
|
| 828 |
+
"learning_rate": 4.4380952380952385e-06,
|
| 829 |
+
"loss": 0.0157,
|
| 830 |
+
"step": 2392
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.91,
|
| 834 |
+
"eval_accuracy": 0.9975555555555555,
|
| 835 |
+
"eval_f1": 0.9975528364849834,
|
| 836 |
+
"eval_loss": 0.012594416737556458,
|
| 837 |
+
"eval_precision": 0.9986636971046771,
|
| 838 |
+
"eval_recall": 0.9964444444444445,
|
| 839 |
+
"eval_runtime": 53.7606,
|
| 840 |
+
"eval_samples_per_second": 83.704,
|
| 841 |
+
"eval_steps_per_second": 10.472,
|
| 842 |
+
"step": 2392
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.93,
|
| 846 |
+
"learning_rate": 3.4476190476190472e-06,
|
| 847 |
+
"loss": 0.0147,
|
| 848 |
+
"step": 2444
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.93,
|
| 852 |
+
"eval_accuracy": 0.9973333333333333,
|
| 853 |
+
"eval_f1": 0.9973309608540925,
|
| 854 |
+
"eval_loss": 0.011972985230386257,
|
| 855 |
+
"eval_precision": 0.9982190560997328,
|
| 856 |
+
"eval_recall": 0.9964444444444445,
|
| 857 |
+
"eval_runtime": 52.7147,
|
| 858 |
+
"eval_samples_per_second": 85.365,
|
| 859 |
+
"eval_steps_per_second": 10.68,
|
| 860 |
+
"step": 2444
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.95,
|
| 864 |
+
"learning_rate": 2.4571428571428573e-06,
|
| 865 |
+
"loss": 0.0115,
|
| 866 |
+
"step": 2496
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.95,
|
| 870 |
+
"eval_accuracy": 0.9973333333333333,
|
| 871 |
+
"eval_f1": 0.9973309608540925,
|
| 872 |
+
"eval_loss": 0.01194427628070116,
|
| 873 |
+
"eval_precision": 0.9982190560997328,
|
| 874 |
+
"eval_recall": 0.9964444444444445,
|
| 875 |
+
"eval_runtime": 55.506,
|
| 876 |
+
"eval_samples_per_second": 81.072,
|
| 877 |
+
"eval_steps_per_second": 10.143,
|
| 878 |
+
"step": 2496
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.97,
|
| 882 |
+
"learning_rate": 1.4666666666666667e-06,
|
| 883 |
+
"loss": 0.0002,
|
| 884 |
+
"step": 2548
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.97,
|
| 888 |
+
"eval_accuracy": 0.9973333333333333,
|
| 889 |
+
"eval_f1": 0.9973309608540925,
|
| 890 |
+
"eval_loss": 0.011756585910916328,
|
| 891 |
+
"eval_precision": 0.9982190560997328,
|
| 892 |
+
"eval_recall": 0.9964444444444445,
|
| 893 |
+
"eval_runtime": 54.1036,
|
| 894 |
+
"eval_samples_per_second": 83.174,
|
| 895 |
+
"eval_steps_per_second": 10.406,
|
| 896 |
+
"step": 2548
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.99,
|
| 900 |
+
"learning_rate": 4.761904761904763e-07,
|
| 901 |
+
"loss": 0.0125,
|
| 902 |
+
"step": 2600
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.99,
|
| 906 |
+
"eval_accuracy": 0.9973333333333333,
|
| 907 |
+
"eval_f1": 0.9973309608540925,
|
| 908 |
+
"eval_loss": 0.011715704575181007,
|
| 909 |
+
"eval_precision": 0.9982190560997328,
|
| 910 |
+
"eval_recall": 0.9964444444444445,
|
| 911 |
+
"eval_runtime": 54.017,
|
| 912 |
+
"eval_samples_per_second": 83.307,
|
| 913 |
+
"eval_steps_per_second": 10.423,
|
| 914 |
+
"step": 2600
|
| 915 |
+
}
|
| 916 |
+
],
|
| 917 |
+
"max_steps": 2625,
|
| 918 |
+
"num_train_epochs": 1,
|
| 919 |
+
"total_flos": 5525332162560000.0,
|
| 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 sha256:8c3e7a9d6c2c726d8a736284261a68e49532bbf68d6d2f70b83f862c50a42565
|
| 3 |
+
size 3451
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|