Upload folder using huggingface_hub
Browse files- config.json +40 -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 +1012 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaPrefixForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"finetuning_task": "boolq",
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "False",
|
| 16 |
+
"1": "True"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 4096,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"False": 0,
|
| 22 |
+
"True": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-05,
|
| 25 |
+
"max_position_embeddings": 514,
|
| 26 |
+
"model_type": "roberta",
|
| 27 |
+
"num_attention_heads": 16,
|
| 28 |
+
"num_hidden_layers": 24,
|
| 29 |
+
"pad_token_id": 1,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"pre_seq_len": 20,
|
| 32 |
+
"prefix_hidden_size": 512,
|
| 33 |
+
"prefix_projection": false,
|
| 34 |
+
"problem_type": "single_label_classification",
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.20.0",
|
| 37 |
+
"type_vocab_size": 1,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 50265
|
| 40 |
+
}
|
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:c667a11d63157f7ab09d1ac8272bd778b9e10eecdbcaa0e7554e163b668ba93b
|
| 3 |
+
size 7884444
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc9b09c26ff06d5701d05e37326376335e54c55f89a340c723a1582eb0a843cd
|
| 3 |
+
size 1425520118
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:870b197507cd604e5636ec0ecc874559905f369d8bd4f541cfc4bf16073c649b
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91d36a4970f9dcc7b4363d15f2ba63378db4e41b8fbbb1311313e6c526ac5ec3
|
| 3 |
+
size 1064
|
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-large",
|
| 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 +1,1012 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8354740061162079,
|
| 3 |
+
"best_model_checkpoint": "checkpoints/boolq-roberta/checkpoint-15930",
|
| 4 |
+
"epoch": 54.0,
|
| 5 |
+
"global_step": 15930,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.5525993883792049,
|
| 13 |
+
"eval_loss": 0.6860924959182739,
|
| 14 |
+
"eval_runtime": 9.8191,
|
| 15 |
+
"eval_samples_per_second": 333.024,
|
| 16 |
+
"eval_steps_per_second": 41.654,
|
| 17 |
+
"step": 295
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"best_epoch": 0,
|
| 21 |
+
"best_eval_accuracy": 0.5525993883792049,
|
| 22 |
+
"epoch": 1.0,
|
| 23 |
+
"step": 295
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.69,
|
| 27 |
+
"learning_rate": 0.0068813559322033905,
|
| 28 |
+
"loss": 0.768,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.6259938837920489,
|
| 34 |
+
"eval_loss": 0.6413273811340332,
|
| 35 |
+
"eval_runtime": 9.8093,
|
| 36 |
+
"eval_samples_per_second": 333.357,
|
| 37 |
+
"eval_steps_per_second": 41.695,
|
| 38 |
+
"step": 590
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"best_epoch": 1,
|
| 42 |
+
"best_eval_accuracy": 0.6259938837920489,
|
| 43 |
+
"epoch": 2.0,
|
| 44 |
+
"step": 590
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_accuracy": 0.7058103975535168,
|
| 49 |
+
"eval_loss": 0.7142531871795654,
|
| 50 |
+
"eval_runtime": 9.821,
|
| 51 |
+
"eval_samples_per_second": 332.961,
|
| 52 |
+
"eval_steps_per_second": 41.646,
|
| 53 |
+
"step": 885
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"best_epoch": 2,
|
| 57 |
+
"best_eval_accuracy": 0.7058103975535168,
|
| 58 |
+
"epoch": 3.0,
|
| 59 |
+
"step": 885
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.39,
|
| 63 |
+
"learning_rate": 0.00676271186440678,
|
| 64 |
+
"loss": 0.7341,
|
| 65 |
+
"step": 1000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 4.0,
|
| 69 |
+
"eval_accuracy": 0.7798165137614679,
|
| 70 |
+
"eval_loss": 0.4908980429172516,
|
| 71 |
+
"eval_runtime": 9.8251,
|
| 72 |
+
"eval_samples_per_second": 332.822,
|
| 73 |
+
"eval_steps_per_second": 41.628,
|
| 74 |
+
"step": 1180
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"best_epoch": 3,
|
| 78 |
+
"best_eval_accuracy": 0.7798165137614679,
|
| 79 |
+
"epoch": 4.0,
|
| 80 |
+
"step": 1180
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"eval_accuracy": 0.7865443425076453,
|
| 85 |
+
"eval_loss": 0.4921702444553375,
|
| 86 |
+
"eval_runtime": 9.8323,
|
| 87 |
+
"eval_samples_per_second": 332.579,
|
| 88 |
+
"eval_steps_per_second": 41.598,
|
| 89 |
+
"step": 1475
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"best_epoch": 4,
|
| 93 |
+
"best_eval_accuracy": 0.7865443425076453,
|
| 94 |
+
"epoch": 5.0,
|
| 95 |
+
"step": 1475
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 5.08,
|
| 99 |
+
"learning_rate": 0.00664406779661017,
|
| 100 |
+
"loss": 0.6102,
|
| 101 |
+
"step": 1500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 6.0,
|
| 105 |
+
"eval_accuracy": 0.791743119266055,
|
| 106 |
+
"eval_loss": 0.5190699696540833,
|
| 107 |
+
"eval_runtime": 9.8121,
|
| 108 |
+
"eval_samples_per_second": 333.263,
|
| 109 |
+
"eval_steps_per_second": 41.683,
|
| 110 |
+
"step": 1770
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"best_epoch": 5,
|
| 114 |
+
"best_eval_accuracy": 0.791743119266055,
|
| 115 |
+
"epoch": 6.0,
|
| 116 |
+
"step": 1770
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.78,
|
| 120 |
+
"learning_rate": 0.006525423728813559,
|
| 121 |
+
"loss": 0.5638,
|
| 122 |
+
"step": 2000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.0,
|
| 126 |
+
"eval_accuracy": 0.7602446483180428,
|
| 127 |
+
"eval_loss": 0.5134357810020447,
|
| 128 |
+
"eval_runtime": 9.8046,
|
| 129 |
+
"eval_samples_per_second": 333.516,
|
| 130 |
+
"eval_steps_per_second": 41.715,
|
| 131 |
+
"step": 2065
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"best_epoch": 5,
|
| 135 |
+
"best_eval_accuracy": 0.791743119266055,
|
| 136 |
+
"epoch": 7.0,
|
| 137 |
+
"step": 2065
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 8.0,
|
| 141 |
+
"eval_accuracy": 0.8048929663608563,
|
| 142 |
+
"eval_loss": 0.4786987006664276,
|
| 143 |
+
"eval_runtime": 9.8048,
|
| 144 |
+
"eval_samples_per_second": 333.508,
|
| 145 |
+
"eval_steps_per_second": 41.714,
|
| 146 |
+
"step": 2360
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"best_epoch": 7,
|
| 150 |
+
"best_eval_accuracy": 0.8048929663608563,
|
| 151 |
+
"epoch": 8.0,
|
| 152 |
+
"step": 2360
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 8.47,
|
| 156 |
+
"learning_rate": 0.006406779661016949,
|
| 157 |
+
"loss": 0.5123,
|
| 158 |
+
"step": 2500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 9.0,
|
| 162 |
+
"eval_accuracy": 0.8036697247706422,
|
| 163 |
+
"eval_loss": 0.4702308177947998,
|
| 164 |
+
"eval_runtime": 9.8236,
|
| 165 |
+
"eval_samples_per_second": 332.873,
|
| 166 |
+
"eval_steps_per_second": 41.635,
|
| 167 |
+
"step": 2655
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"best_epoch": 7,
|
| 171 |
+
"best_eval_accuracy": 0.8048929663608563,
|
| 172 |
+
"epoch": 9.0,
|
| 173 |
+
"step": 2655
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 10.0,
|
| 177 |
+
"eval_accuracy": 0.791743119266055,
|
| 178 |
+
"eval_loss": 0.5443930625915527,
|
| 179 |
+
"eval_runtime": 9.8027,
|
| 180 |
+
"eval_samples_per_second": 333.58,
|
| 181 |
+
"eval_steps_per_second": 41.723,
|
| 182 |
+
"step": 2950
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"best_epoch": 7,
|
| 186 |
+
"best_eval_accuracy": 0.8048929663608563,
|
| 187 |
+
"epoch": 10.0,
|
| 188 |
+
"step": 2950
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 10.17,
|
| 192 |
+
"learning_rate": 0.006288135593220339,
|
| 193 |
+
"loss": 0.5045,
|
| 194 |
+
"step": 3000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 11.0,
|
| 198 |
+
"eval_accuracy": 0.7871559633027523,
|
| 199 |
+
"eval_loss": 0.5409664511680603,
|
| 200 |
+
"eval_runtime": 9.8211,
|
| 201 |
+
"eval_samples_per_second": 332.955,
|
| 202 |
+
"eval_steps_per_second": 41.645,
|
| 203 |
+
"step": 3245
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"best_epoch": 7,
|
| 207 |
+
"best_eval_accuracy": 0.8048929663608563,
|
| 208 |
+
"epoch": 11.0,
|
| 209 |
+
"step": 3245
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 11.86,
|
| 213 |
+
"learning_rate": 0.006169491525423729,
|
| 214 |
+
"loss": 0.4583,
|
| 215 |
+
"step": 3500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 12.0,
|
| 219 |
+
"eval_accuracy": 0.8162079510703364,
|
| 220 |
+
"eval_loss": 0.460715115070343,
|
| 221 |
+
"eval_runtime": 9.8053,
|
| 222 |
+
"eval_samples_per_second": 333.493,
|
| 223 |
+
"eval_steps_per_second": 41.712,
|
| 224 |
+
"step": 3540
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"best_epoch": 11,
|
| 228 |
+
"best_eval_accuracy": 0.8162079510703364,
|
| 229 |
+
"epoch": 12.0,
|
| 230 |
+
"step": 3540
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 13.0,
|
| 234 |
+
"eval_accuracy": 0.8079510703363915,
|
| 235 |
+
"eval_loss": 0.5161741375923157,
|
| 236 |
+
"eval_runtime": 9.8021,
|
| 237 |
+
"eval_samples_per_second": 333.603,
|
| 238 |
+
"eval_steps_per_second": 41.726,
|
| 239 |
+
"step": 3835
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"best_epoch": 11,
|
| 243 |
+
"best_eval_accuracy": 0.8162079510703364,
|
| 244 |
+
"epoch": 13.0,
|
| 245 |
+
"step": 3835
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 13.56,
|
| 249 |
+
"learning_rate": 0.006050847457627119,
|
| 250 |
+
"loss": 0.4401,
|
| 251 |
+
"step": 4000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 14.0,
|
| 255 |
+
"eval_accuracy": 0.826605504587156,
|
| 256 |
+
"eval_loss": 0.5039022564888,
|
| 257 |
+
"eval_runtime": 9.7965,
|
| 258 |
+
"eval_samples_per_second": 333.792,
|
| 259 |
+
"eval_steps_per_second": 41.75,
|
| 260 |
+
"step": 4130
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"best_epoch": 13,
|
| 264 |
+
"best_eval_accuracy": 0.826605504587156,
|
| 265 |
+
"epoch": 14.0,
|
| 266 |
+
"step": 4130
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 15.0,
|
| 270 |
+
"eval_accuracy": 0.807645259938838,
|
| 271 |
+
"eval_loss": 0.4858939051628113,
|
| 272 |
+
"eval_runtime": 9.8364,
|
| 273 |
+
"eval_samples_per_second": 332.437,
|
| 274 |
+
"eval_steps_per_second": 41.58,
|
| 275 |
+
"step": 4425
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"best_epoch": 13,
|
| 279 |
+
"best_eval_accuracy": 0.826605504587156,
|
| 280 |
+
"epoch": 15.0,
|
| 281 |
+
"step": 4425
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 15.25,
|
| 285 |
+
"learning_rate": 0.005932203389830509,
|
| 286 |
+
"loss": 0.4317,
|
| 287 |
+
"step": 4500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 16.0,
|
| 291 |
+
"eval_accuracy": 0.8006116207951071,
|
| 292 |
+
"eval_loss": 0.5990845561027527,
|
| 293 |
+
"eval_runtime": 9.8097,
|
| 294 |
+
"eval_samples_per_second": 333.344,
|
| 295 |
+
"eval_steps_per_second": 41.694,
|
| 296 |
+
"step": 4720
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"best_epoch": 13,
|
| 300 |
+
"best_eval_accuracy": 0.826605504587156,
|
| 301 |
+
"epoch": 16.0,
|
| 302 |
+
"step": 4720
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 16.95,
|
| 306 |
+
"learning_rate": 0.005813559322033898,
|
| 307 |
+
"loss": 0.3821,
|
| 308 |
+
"step": 5000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 17.0,
|
| 312 |
+
"eval_accuracy": 0.8214067278287461,
|
| 313 |
+
"eval_loss": 0.6158734560012817,
|
| 314 |
+
"eval_runtime": 9.8135,
|
| 315 |
+
"eval_samples_per_second": 333.213,
|
| 316 |
+
"eval_steps_per_second": 41.677,
|
| 317 |
+
"step": 5015
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"best_epoch": 13,
|
| 321 |
+
"best_eval_accuracy": 0.826605504587156,
|
| 322 |
+
"epoch": 17.0,
|
| 323 |
+
"step": 5015
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 18.0,
|
| 327 |
+
"eval_accuracy": 0.8024464831804281,
|
| 328 |
+
"eval_loss": 0.6013011336326599,
|
| 329 |
+
"eval_runtime": 9.8051,
|
| 330 |
+
"eval_samples_per_second": 333.5,
|
| 331 |
+
"eval_steps_per_second": 41.713,
|
| 332 |
+
"step": 5310
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"best_epoch": 13,
|
| 336 |
+
"best_eval_accuracy": 0.826605504587156,
|
| 337 |
+
"epoch": 18.0,
|
| 338 |
+
"step": 5310
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 18.64,
|
| 342 |
+
"learning_rate": 0.005694915254237288,
|
| 343 |
+
"loss": 0.3534,
|
| 344 |
+
"step": 5500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 19.0,
|
| 348 |
+
"eval_accuracy": 0.8226299694189603,
|
| 349 |
+
"eval_loss": 0.5256037712097168,
|
| 350 |
+
"eval_runtime": 9.8062,
|
| 351 |
+
"eval_samples_per_second": 333.464,
|
| 352 |
+
"eval_steps_per_second": 41.708,
|
| 353 |
+
"step": 5605
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"best_epoch": 13,
|
| 357 |
+
"best_eval_accuracy": 0.826605504587156,
|
| 358 |
+
"epoch": 19.0,
|
| 359 |
+
"step": 5605
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 20.0,
|
| 363 |
+
"eval_accuracy": 0.8256880733944955,
|
| 364 |
+
"eval_loss": 0.6150120496749878,
|
| 365 |
+
"eval_runtime": 9.8251,
|
| 366 |
+
"eval_samples_per_second": 332.821,
|
| 367 |
+
"eval_steps_per_second": 41.628,
|
| 368 |
+
"step": 5900
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"best_epoch": 13,
|
| 372 |
+
"best_eval_accuracy": 0.826605504587156,
|
| 373 |
+
"epoch": 20.0,
|
| 374 |
+
"step": 5900
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 20.34,
|
| 378 |
+
"learning_rate": 0.005576271186440678,
|
| 379 |
+
"loss": 0.337,
|
| 380 |
+
"step": 6000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 21.0,
|
| 384 |
+
"eval_accuracy": 0.828440366972477,
|
| 385 |
+
"eval_loss": 0.5820947885513306,
|
| 386 |
+
"eval_runtime": 9.8077,
|
| 387 |
+
"eval_samples_per_second": 333.413,
|
| 388 |
+
"eval_steps_per_second": 41.702,
|
| 389 |
+
"step": 6195
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"best_epoch": 20,
|
| 393 |
+
"best_eval_accuracy": 0.828440366972477,
|
| 394 |
+
"epoch": 21.0,
|
| 395 |
+
"step": 6195
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 22.0,
|
| 399 |
+
"eval_accuracy": 0.82782874617737,
|
| 400 |
+
"eval_loss": 0.5438685417175293,
|
| 401 |
+
"eval_runtime": 9.8107,
|
| 402 |
+
"eval_samples_per_second": 333.309,
|
| 403 |
+
"eval_steps_per_second": 41.689,
|
| 404 |
+
"step": 6490
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"best_epoch": 20,
|
| 408 |
+
"best_eval_accuracy": 0.828440366972477,
|
| 409 |
+
"epoch": 22.0,
|
| 410 |
+
"step": 6490
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 22.03,
|
| 414 |
+
"learning_rate": 0.005457627118644068,
|
| 415 |
+
"loss": 0.3002,
|
| 416 |
+
"step": 6500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 23.0,
|
| 420 |
+
"eval_accuracy": 0.8302752293577982,
|
| 421 |
+
"eval_loss": 0.568505048751831,
|
| 422 |
+
"eval_runtime": 9.8907,
|
| 423 |
+
"eval_samples_per_second": 330.614,
|
| 424 |
+
"eval_steps_per_second": 41.352,
|
| 425 |
+
"step": 6785
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"best_epoch": 22,
|
| 429 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 430 |
+
"epoch": 23.0,
|
| 431 |
+
"step": 6785
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 23.73,
|
| 435 |
+
"learning_rate": 0.005338983050847458,
|
| 436 |
+
"loss": 0.2875,
|
| 437 |
+
"step": 7000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 24.0,
|
| 441 |
+
"eval_accuracy": 0.8125382262996942,
|
| 442 |
+
"eval_loss": 0.6513988375663757,
|
| 443 |
+
"eval_runtime": 9.8218,
|
| 444 |
+
"eval_samples_per_second": 332.932,
|
| 445 |
+
"eval_steps_per_second": 41.642,
|
| 446 |
+
"step": 7080
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"best_epoch": 22,
|
| 450 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 451 |
+
"epoch": 24.0,
|
| 452 |
+
"step": 7080
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 25.0,
|
| 456 |
+
"eval_accuracy": 0.8223241590214068,
|
| 457 |
+
"eval_loss": 0.6830200552940369,
|
| 458 |
+
"eval_runtime": 9.8098,
|
| 459 |
+
"eval_samples_per_second": 333.34,
|
| 460 |
+
"eval_steps_per_second": 41.693,
|
| 461 |
+
"step": 7375
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"best_epoch": 22,
|
| 465 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 466 |
+
"epoch": 25.0,
|
| 467 |
+
"step": 7375
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 25.42,
|
| 471 |
+
"learning_rate": 0.005220338983050848,
|
| 472 |
+
"loss": 0.2724,
|
| 473 |
+
"step": 7500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 26.0,
|
| 477 |
+
"eval_accuracy": 0.8207951070336391,
|
| 478 |
+
"eval_loss": 0.6568824052810669,
|
| 479 |
+
"eval_runtime": 9.8777,
|
| 480 |
+
"eval_samples_per_second": 331.049,
|
| 481 |
+
"eval_steps_per_second": 41.406,
|
| 482 |
+
"step": 7670
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"best_epoch": 22,
|
| 486 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 487 |
+
"epoch": 26.0,
|
| 488 |
+
"step": 7670
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 27.0,
|
| 492 |
+
"eval_accuracy": 0.8275229357798165,
|
| 493 |
+
"eval_loss": 0.6946196556091309,
|
| 494 |
+
"eval_runtime": 9.7866,
|
| 495 |
+
"eval_samples_per_second": 334.131,
|
| 496 |
+
"eval_steps_per_second": 41.792,
|
| 497 |
+
"step": 7965
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"best_epoch": 22,
|
| 501 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 502 |
+
"epoch": 27.0,
|
| 503 |
+
"step": 7965
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 27.12,
|
| 507 |
+
"learning_rate": 0.005101694915254237,
|
| 508 |
+
"loss": 0.2599,
|
| 509 |
+
"step": 8000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 28.0,
|
| 513 |
+
"eval_accuracy": 0.8229357798165138,
|
| 514 |
+
"eval_loss": 0.7936107516288757,
|
| 515 |
+
"eval_runtime": 9.8279,
|
| 516 |
+
"eval_samples_per_second": 332.727,
|
| 517 |
+
"eval_steps_per_second": 41.616,
|
| 518 |
+
"step": 8260
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"best_epoch": 22,
|
| 522 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 523 |
+
"epoch": 28.0,
|
| 524 |
+
"step": 8260
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 28.81,
|
| 528 |
+
"learning_rate": 0.004983050847457627,
|
| 529 |
+
"loss": 0.2504,
|
| 530 |
+
"step": 8500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 29.0,
|
| 534 |
+
"eval_accuracy": 0.8287461773700305,
|
| 535 |
+
"eval_loss": 0.6681709885597229,
|
| 536 |
+
"eval_runtime": 9.8102,
|
| 537 |
+
"eval_samples_per_second": 333.327,
|
| 538 |
+
"eval_steps_per_second": 41.691,
|
| 539 |
+
"step": 8555
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"best_epoch": 22,
|
| 543 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 544 |
+
"epoch": 29.0,
|
| 545 |
+
"step": 8555
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 30.0,
|
| 549 |
+
"eval_accuracy": 0.8226299694189603,
|
| 550 |
+
"eval_loss": 0.7363224029541016,
|
| 551 |
+
"eval_runtime": 9.8095,
|
| 552 |
+
"eval_samples_per_second": 333.349,
|
| 553 |
+
"eval_steps_per_second": 41.694,
|
| 554 |
+
"step": 8850
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"best_epoch": 22,
|
| 558 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 559 |
+
"epoch": 30.0,
|
| 560 |
+
"step": 8850
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 30.51,
|
| 564 |
+
"learning_rate": 0.004864406779661017,
|
| 565 |
+
"loss": 0.2333,
|
| 566 |
+
"step": 9000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 31.0,
|
| 570 |
+
"eval_accuracy": 0.8287461773700305,
|
| 571 |
+
"eval_loss": 0.6868186593055725,
|
| 572 |
+
"eval_runtime": 9.835,
|
| 573 |
+
"eval_samples_per_second": 332.487,
|
| 574 |
+
"eval_steps_per_second": 41.586,
|
| 575 |
+
"step": 9145
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"best_epoch": 22,
|
| 579 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 580 |
+
"epoch": 31.0,
|
| 581 |
+
"step": 9145
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 32.0,
|
| 585 |
+
"eval_accuracy": 0.8299694189602447,
|
| 586 |
+
"eval_loss": 0.7315894365310669,
|
| 587 |
+
"eval_runtime": 9.8164,
|
| 588 |
+
"eval_samples_per_second": 333.117,
|
| 589 |
+
"eval_steps_per_second": 41.665,
|
| 590 |
+
"step": 9440
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"best_epoch": 22,
|
| 594 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 595 |
+
"epoch": 32.0,
|
| 596 |
+
"step": 9440
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 32.2,
|
| 600 |
+
"learning_rate": 0.0047457627118644066,
|
| 601 |
+
"loss": 0.2116,
|
| 602 |
+
"step": 9500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 33.0,
|
| 606 |
+
"eval_accuracy": 0.8235474006116208,
|
| 607 |
+
"eval_loss": 0.7920485734939575,
|
| 608 |
+
"eval_runtime": 9.8087,
|
| 609 |
+
"eval_samples_per_second": 333.379,
|
| 610 |
+
"eval_steps_per_second": 41.698,
|
| 611 |
+
"step": 9735
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"best_epoch": 22,
|
| 615 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 616 |
+
"epoch": 33.0,
|
| 617 |
+
"step": 9735
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 33.9,
|
| 621 |
+
"learning_rate": 0.004627118644067797,
|
| 622 |
+
"loss": 0.2016,
|
| 623 |
+
"step": 10000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 34.0,
|
| 627 |
+
"eval_accuracy": 0.8302752293577982,
|
| 628 |
+
"eval_loss": 0.8122466802597046,
|
| 629 |
+
"eval_runtime": 9.8089,
|
| 630 |
+
"eval_samples_per_second": 333.371,
|
| 631 |
+
"eval_steps_per_second": 41.697,
|
| 632 |
+
"step": 10030
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"best_epoch": 22,
|
| 636 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 637 |
+
"epoch": 34.0,
|
| 638 |
+
"step": 10030
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 35.0,
|
| 642 |
+
"eval_accuracy": 0.8235474006116208,
|
| 643 |
+
"eval_loss": 0.8033488988876343,
|
| 644 |
+
"eval_runtime": 9.8046,
|
| 645 |
+
"eval_samples_per_second": 333.516,
|
| 646 |
+
"eval_steps_per_second": 41.715,
|
| 647 |
+
"step": 10325
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"best_epoch": 22,
|
| 651 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 652 |
+
"epoch": 35.0,
|
| 653 |
+
"step": 10325
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 35.59,
|
| 657 |
+
"learning_rate": 0.004508474576271186,
|
| 658 |
+
"loss": 0.2053,
|
| 659 |
+
"step": 10500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 36.0,
|
| 663 |
+
"eval_accuracy": 0.8275229357798165,
|
| 664 |
+
"eval_loss": 0.8479099273681641,
|
| 665 |
+
"eval_runtime": 9.8042,
|
| 666 |
+
"eval_samples_per_second": 333.529,
|
| 667 |
+
"eval_steps_per_second": 41.717,
|
| 668 |
+
"step": 10620
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"best_epoch": 22,
|
| 672 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 673 |
+
"epoch": 36.0,
|
| 674 |
+
"step": 10620
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 37.0,
|
| 678 |
+
"eval_accuracy": 0.826605504587156,
|
| 679 |
+
"eval_loss": 0.7674300074577332,
|
| 680 |
+
"eval_runtime": 9.8042,
|
| 681 |
+
"eval_samples_per_second": 333.532,
|
| 682 |
+
"eval_steps_per_second": 41.717,
|
| 683 |
+
"step": 10915
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"best_epoch": 22,
|
| 687 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 688 |
+
"epoch": 37.0,
|
| 689 |
+
"step": 10915
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 37.29,
|
| 693 |
+
"learning_rate": 0.004389830508474577,
|
| 694 |
+
"loss": 0.1784,
|
| 695 |
+
"step": 11000
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 38.0,
|
| 699 |
+
"eval_accuracy": 0.8302752293577982,
|
| 700 |
+
"eval_loss": 0.7334691882133484,
|
| 701 |
+
"eval_runtime": 9.8101,
|
| 702 |
+
"eval_samples_per_second": 333.331,
|
| 703 |
+
"eval_steps_per_second": 41.692,
|
| 704 |
+
"step": 11210
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"best_epoch": 22,
|
| 708 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 709 |
+
"epoch": 38.0,
|
| 710 |
+
"step": 11210
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 38.98,
|
| 714 |
+
"learning_rate": 0.004271186440677966,
|
| 715 |
+
"loss": 0.1742,
|
| 716 |
+
"step": 11500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 39.0,
|
| 720 |
+
"eval_accuracy": 0.8244648318042813,
|
| 721 |
+
"eval_loss": 0.8439134955406189,
|
| 722 |
+
"eval_runtime": 9.8448,
|
| 723 |
+
"eval_samples_per_second": 332.155,
|
| 724 |
+
"eval_steps_per_second": 41.545,
|
| 725 |
+
"step": 11505
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"best_epoch": 22,
|
| 729 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 730 |
+
"epoch": 39.0,
|
| 731 |
+
"step": 11505
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 40.0,
|
| 735 |
+
"eval_accuracy": 0.8269113149847095,
|
| 736 |
+
"eval_loss": 0.7226125597953796,
|
| 737 |
+
"eval_runtime": 9.7971,
|
| 738 |
+
"eval_samples_per_second": 333.772,
|
| 739 |
+
"eval_steps_per_second": 41.747,
|
| 740 |
+
"step": 11800
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"best_epoch": 22,
|
| 744 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 745 |
+
"epoch": 40.0,
|
| 746 |
+
"step": 11800
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 40.68,
|
| 750 |
+
"learning_rate": 0.0041525423728813555,
|
| 751 |
+
"loss": 0.1607,
|
| 752 |
+
"step": 12000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 41.0,
|
| 756 |
+
"eval_accuracy": 0.8262996941896025,
|
| 757 |
+
"eval_loss": 0.783122181892395,
|
| 758 |
+
"eval_runtime": 9.8034,
|
| 759 |
+
"eval_samples_per_second": 333.559,
|
| 760 |
+
"eval_steps_per_second": 41.72,
|
| 761 |
+
"step": 12095
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"best_epoch": 22,
|
| 765 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 766 |
+
"epoch": 41.0,
|
| 767 |
+
"step": 12095
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 42.0,
|
| 771 |
+
"eval_accuracy": 0.8204892966360856,
|
| 772 |
+
"eval_loss": 0.8774231672286987,
|
| 773 |
+
"eval_runtime": 9.8122,
|
| 774 |
+
"eval_samples_per_second": 333.26,
|
| 775 |
+
"eval_steps_per_second": 41.683,
|
| 776 |
+
"step": 12390
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"best_epoch": 22,
|
| 780 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 781 |
+
"epoch": 42.0,
|
| 782 |
+
"step": 12390
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 42.37,
|
| 786 |
+
"learning_rate": 0.004033898305084746,
|
| 787 |
+
"loss": 0.1482,
|
| 788 |
+
"step": 12500
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 43.0,
|
| 792 |
+
"eval_accuracy": 0.8201834862385321,
|
| 793 |
+
"eval_loss": 0.9140273928642273,
|
| 794 |
+
"eval_runtime": 9.8202,
|
| 795 |
+
"eval_samples_per_second": 332.988,
|
| 796 |
+
"eval_steps_per_second": 41.649,
|
| 797 |
+
"step": 12685
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"best_epoch": 22,
|
| 801 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 802 |
+
"epoch": 43.0,
|
| 803 |
+
"step": 12685
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 44.0,
|
| 807 |
+
"eval_accuracy": 0.8293577981651377,
|
| 808 |
+
"eval_loss": 1.0441981554031372,
|
| 809 |
+
"eval_runtime": 9.8317,
|
| 810 |
+
"eval_samples_per_second": 332.596,
|
| 811 |
+
"eval_steps_per_second": 41.6,
|
| 812 |
+
"step": 12980
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"best_epoch": 22,
|
| 816 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 817 |
+
"epoch": 44.0,
|
| 818 |
+
"step": 12980
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 44.07,
|
| 822 |
+
"learning_rate": 0.003915254237288135,
|
| 823 |
+
"loss": 0.1353,
|
| 824 |
+
"step": 13000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 45.0,
|
| 828 |
+
"eval_accuracy": 0.8204892966360856,
|
| 829 |
+
"eval_loss": 0.9284624457359314,
|
| 830 |
+
"eval_runtime": 9.8086,
|
| 831 |
+
"eval_samples_per_second": 333.381,
|
| 832 |
+
"eval_steps_per_second": 41.698,
|
| 833 |
+
"step": 13275
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"best_epoch": 22,
|
| 837 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 838 |
+
"epoch": 45.0,
|
| 839 |
+
"step": 13275
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 45.76,
|
| 843 |
+
"learning_rate": 0.0037966101694915256,
|
| 844 |
+
"loss": 0.1442,
|
| 845 |
+
"step": 13500
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 46.0,
|
| 849 |
+
"eval_accuracy": 0.8296636085626912,
|
| 850 |
+
"eval_loss": 0.9967836141586304,
|
| 851 |
+
"eval_runtime": 9.7985,
|
| 852 |
+
"eval_samples_per_second": 333.726,
|
| 853 |
+
"eval_steps_per_second": 41.741,
|
| 854 |
+
"step": 13570
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"best_epoch": 22,
|
| 858 |
+
"best_eval_accuracy": 0.8302752293577982,
|
| 859 |
+
"epoch": 46.0,
|
| 860 |
+
"step": 13570
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 47.0,
|
| 864 |
+
"eval_accuracy": 0.8333333333333334,
|
| 865 |
+
"eval_loss": 0.969611406326294,
|
| 866 |
+
"eval_runtime": 9.8112,
|
| 867 |
+
"eval_samples_per_second": 333.294,
|
| 868 |
+
"eval_steps_per_second": 41.687,
|
| 869 |
+
"step": 13865
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"best_epoch": 46,
|
| 873 |
+
"best_eval_accuracy": 0.8333333333333334,
|
| 874 |
+
"epoch": 47.0,
|
| 875 |
+
"step": 13865
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 47.46,
|
| 879 |
+
"learning_rate": 0.0036779661016949155,
|
| 880 |
+
"loss": 0.1308,
|
| 881 |
+
"step": 14000
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 48.0,
|
| 885 |
+
"eval_accuracy": 0.8333333333333334,
|
| 886 |
+
"eval_loss": 0.9742096662521362,
|
| 887 |
+
"eval_runtime": 9.8104,
|
| 888 |
+
"eval_samples_per_second": 333.319,
|
| 889 |
+
"eval_steps_per_second": 41.69,
|
| 890 |
+
"step": 14160
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"best_epoch": 46,
|
| 894 |
+
"best_eval_accuracy": 0.8333333333333334,
|
| 895 |
+
"epoch": 48.0,
|
| 896 |
+
"step": 14160
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 49.0,
|
| 900 |
+
"eval_accuracy": 0.8324159021406727,
|
| 901 |
+
"eval_loss": 0.9350805282592773,
|
| 902 |
+
"eval_runtime": 9.8421,
|
| 903 |
+
"eval_samples_per_second": 332.247,
|
| 904 |
+
"eval_steps_per_second": 41.556,
|
| 905 |
+
"step": 14455
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"best_epoch": 46,
|
| 909 |
+
"best_eval_accuracy": 0.8333333333333334,
|
| 910 |
+
"epoch": 49.0,
|
| 911 |
+
"step": 14455
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 49.15,
|
| 915 |
+
"learning_rate": 0.003559322033898305,
|
| 916 |
+
"loss": 0.12,
|
| 917 |
+
"step": 14500
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 50.0,
|
| 921 |
+
"eval_accuracy": 0.8232415902140673,
|
| 922 |
+
"eval_loss": 1.0194205045700073,
|
| 923 |
+
"eval_runtime": 9.8031,
|
| 924 |
+
"eval_samples_per_second": 333.567,
|
| 925 |
+
"eval_steps_per_second": 41.721,
|
| 926 |
+
"step": 14750
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"best_epoch": 46,
|
| 930 |
+
"best_eval_accuracy": 0.8333333333333334,
|
| 931 |
+
"epoch": 50.0,
|
| 932 |
+
"step": 14750
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 50.85,
|
| 936 |
+
"learning_rate": 0.0034406779661016952,
|
| 937 |
+
"loss": 0.1151,
|
| 938 |
+
"step": 15000
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 51.0,
|
| 942 |
+
"eval_accuracy": 0.8333333333333334,
|
| 943 |
+
"eval_loss": 1.0169928073883057,
|
| 944 |
+
"eval_runtime": 9.8124,
|
| 945 |
+
"eval_samples_per_second": 333.252,
|
| 946 |
+
"eval_steps_per_second": 41.682,
|
| 947 |
+
"step": 15045
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"best_epoch": 46,
|
| 951 |
+
"best_eval_accuracy": 0.8333333333333334,
|
| 952 |
+
"epoch": 51.0,
|
| 953 |
+
"step": 15045
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 52.0,
|
| 957 |
+
"eval_accuracy": 0.8324159021406727,
|
| 958 |
+
"eval_loss": 0.9195823073387146,
|
| 959 |
+
"eval_runtime": 9.8284,
|
| 960 |
+
"eval_samples_per_second": 332.708,
|
| 961 |
+
"eval_steps_per_second": 41.614,
|
| 962 |
+
"step": 15340
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"best_epoch": 46,
|
| 966 |
+
"best_eval_accuracy": 0.8333333333333334,
|
| 967 |
+
"epoch": 52.0,
|
| 968 |
+
"step": 15340
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 52.54,
|
| 972 |
+
"learning_rate": 0.003322033898305085,
|
| 973 |
+
"loss": 0.1081,
|
| 974 |
+
"step": 15500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 53.0,
|
| 978 |
+
"eval_accuracy": 0.8290519877675842,
|
| 979 |
+
"eval_loss": 0.9286013245582581,
|
| 980 |
+
"eval_runtime": 9.8253,
|
| 981 |
+
"eval_samples_per_second": 332.815,
|
| 982 |
+
"eval_steps_per_second": 41.627,
|
| 983 |
+
"step": 15635
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"best_epoch": 46,
|
| 987 |
+
"best_eval_accuracy": 0.8333333333333334,
|
| 988 |
+
"epoch": 53.0,
|
| 989 |
+
"step": 15635
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 54.0,
|
| 993 |
+
"eval_accuracy": 0.8354740061162079,
|
| 994 |
+
"eval_loss": 0.9297749400138855,
|
| 995 |
+
"eval_runtime": 9.8216,
|
| 996 |
+
"eval_samples_per_second": 332.938,
|
| 997 |
+
"eval_steps_per_second": 41.643,
|
| 998 |
+
"step": 15930
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"best_epoch": 53,
|
| 1002 |
+
"best_eval_accuracy": 0.8354740061162079,
|
| 1003 |
+
"epoch": 54.0,
|
| 1004 |
+
"step": 15930
|
| 1005 |
+
}
|
| 1006 |
+
],
|
| 1007 |
+
"max_steps": 29500,
|
| 1008 |
+
"num_train_epochs": 100,
|
| 1009 |
+
"total_flos": 1.1860177898825626e+17,
|
| 1010 |
+
"trial_name": null,
|
| 1011 |
+
"trial_params": null
|
| 1012 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66c0e325d7dfecc1f7f76622cd1dfa98f6b917729ba5a152a98dce3a273b9ee3
|
| 3 |
+
size 3768
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|