Commit
•
61bb5f5
1
Parent(s):
0d4bef0
First model version
Browse files- .gitattributes +1 -0
- config.json +42 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +3 -0
- tokenizer_config.json +12 -0
- trainer_state.json +922 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bigscience/bloomz-1b7",
|
| 3 |
+
"apply_residual_connection_post_layernorm": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BloomForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attention_softmax_in_fp32": true,
|
| 9 |
+
"bias_dropout_fusion": true,
|
| 10 |
+
"bos_token_id": 1,
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "human-produced",
|
| 16 |
+
"1": "machine-generated"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"human-produced": 0,
|
| 21 |
+
"machine-generated": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_epsilon": 1e-05,
|
| 24 |
+
"masked_softmax_fusion": true,
|
| 25 |
+
"model_type": "bloom",
|
| 26 |
+
"n_head": 16,
|
| 27 |
+
"n_inner": null,
|
| 28 |
+
"n_layer": 24,
|
| 29 |
+
"offset_alibi": 100,
|
| 30 |
+
"pad_token_id": 3,
|
| 31 |
+
"pretraining_tp": 2,
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"seq_length": 4096,
|
| 34 |
+
"skip_bias_add": true,
|
| 35 |
+
"skip_bias_add_qkv": false,
|
| 36 |
+
"slow_but_exact": false,
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.26.1",
|
| 39 |
+
"unk_token_id": 0,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 250880
|
| 42 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7140019f432f10b2acacdb9902d8dcf655e4a11067ba8ca5a796ab595c16629f
|
| 3 |
+
size 13779559309
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba6b6db6c53180ba9d603febc8ceb0dcb3ac2d98bd3bb45e354f3e5eb6a39880
|
| 3 |
+
size 6889753481
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d944d6907131fce4941c1b98753b6c6304e9268438faa750202a7ed282544a4
|
| 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 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa18280d17cb2240255ae226f2e8ce87bc72ae3fb9f7044d0238395b4d8b7a33
|
| 3 |
+
size 14500707
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 6 |
+
"name_or_path": "bigscience/bloomz-1b7",
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"padding_side": "left",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
+
"tokenizer_class": "BloomTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
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": 0.0837,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 4.900952380952381e-05,
|
| 19 |
+
"loss": 3.1832,
|
| 20 |
+
"step": 52
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"eval_accuracy": 0.5,
|
| 25 |
+
"eval_f1": 0.0,
|
| 26 |
+
"eval_loss": 1.1445605754852295,
|
| 27 |
+
"eval_precision": 0.0,
|
| 28 |
+
"eval_recall": 0.0,
|
| 29 |
+
"eval_runtime": 367.3994,
|
| 30 |
+
"eval_samples_per_second": 12.248,
|
| 31 |
+
"eval_steps_per_second": 1.532,
|
| 32 |
+
"step": 52
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.04,
|
| 36 |
+
"learning_rate": 4.8019047619047617e-05,
|
| 37 |
+
"loss": 0.5495,
|
| 38 |
+
"step": 104
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04,
|
| 42 |
+
"eval_accuracy": 0.9688888888888889,
|
| 43 |
+
"eval_f1": 0.9681528662420383,
|
| 44 |
+
"eval_loss": 0.3199825882911682,
|
| 45 |
+
"eval_precision": 0.9916123019571296,
|
| 46 |
+
"eval_recall": 0.9457777777777778,
|
| 47 |
+
"eval_runtime": 366.8654,
|
| 48 |
+
"eval_samples_per_second": 12.266,
|
| 49 |
+
"eval_steps_per_second": 1.535,
|
| 50 |
+
"step": 104
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.06,
|
| 54 |
+
"learning_rate": 4.702857142857143e-05,
|
| 55 |
+
"loss": 0.5137,
|
| 56 |
+
"step": 156
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"eval_accuracy": 0.9622222222222222,
|
| 61 |
+
"eval_f1": 0.9608114338404794,
|
| 62 |
+
"eval_loss": 0.14260223507881165,
|
| 63 |
+
"eval_precision": 0.9980842911877394,
|
| 64 |
+
"eval_recall": 0.9262222222222222,
|
| 65 |
+
"eval_runtime": 366.5855,
|
| 66 |
+
"eval_samples_per_second": 12.275,
|
| 67 |
+
"eval_steps_per_second": 1.536,
|
| 68 |
+
"step": 156
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.08,
|
| 72 |
+
"learning_rate": 4.6038095238095244e-05,
|
| 73 |
+
"loss": 0.8596,
|
| 74 |
+
"step": 208
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.08,
|
| 78 |
+
"eval_accuracy": 0.5,
|
| 79 |
+
"eval_f1": 0.6666666666666666,
|
| 80 |
+
"eval_loss": 1.3752027750015259,
|
| 81 |
+
"eval_precision": 0.5,
|
| 82 |
+
"eval_recall": 1.0,
|
| 83 |
+
"eval_runtime": 366.5836,
|
| 84 |
+
"eval_samples_per_second": 12.276,
|
| 85 |
+
"eval_steps_per_second": 1.536,
|
| 86 |
+
"step": 208
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1,
|
| 90 |
+
"learning_rate": 4.504761904761905e-05,
|
| 91 |
+
"loss": 0.5534,
|
| 92 |
+
"step": 260
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.1,
|
| 96 |
+
"eval_accuracy": 0.9573333333333334,
|
| 97 |
+
"eval_f1": 0.9563239308462239,
|
| 98 |
+
"eval_loss": 0.4955243170261383,
|
| 99 |
+
"eval_precision": 0.9794967381174278,
|
| 100 |
+
"eval_recall": 0.9342222222222222,
|
| 101 |
+
"eval_runtime": 366.7821,
|
| 102 |
+
"eval_samples_per_second": 12.269,
|
| 103 |
+
"eval_steps_per_second": 1.535,
|
| 104 |
+
"step": 260
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.12,
|
| 108 |
+
"learning_rate": 4.405714285714286e-05,
|
| 109 |
+
"loss": 0.2591,
|
| 110 |
+
"step": 312
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.12,
|
| 114 |
+
"eval_accuracy": 0.9713333333333334,
|
| 115 |
+
"eval_f1": 0.9705142857142858,
|
| 116 |
+
"eval_loss": 0.19041332602500916,
|
| 117 |
+
"eval_precision": 0.9990588235294118,
|
| 118 |
+
"eval_recall": 0.9435555555555556,
|
| 119 |
+
"eval_runtime": 366.5597,
|
| 120 |
+
"eval_samples_per_second": 12.276,
|
| 121 |
+
"eval_steps_per_second": 1.536,
|
| 122 |
+
"step": 312
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14,
|
| 126 |
+
"learning_rate": 4.3066666666666665e-05,
|
| 127 |
+
"loss": 0.1978,
|
| 128 |
+
"step": 364
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.14,
|
| 132 |
+
"eval_accuracy": 0.9668888888888889,
|
| 133 |
+
"eval_f1": 0.9657864523536166,
|
| 134 |
+
"eval_loss": 0.16762977838516235,
|
| 135 |
+
"eval_precision": 0.9990498812351544,
|
| 136 |
+
"eval_recall": 0.9346666666666666,
|
| 137 |
+
"eval_runtime": 366.5739,
|
| 138 |
+
"eval_samples_per_second": 12.276,
|
| 139 |
+
"eval_steps_per_second": 1.536,
|
| 140 |
+
"step": 364
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.16,
|
| 144 |
+
"learning_rate": 4.207619047619048e-05,
|
| 145 |
+
"loss": 0.1662,
|
| 146 |
+
"step": 416
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.16,
|
| 150 |
+
"eval_accuracy": 0.9686666666666667,
|
| 151 |
+
"eval_f1": 0.9676531314521679,
|
| 152 |
+
"eval_loss": 0.20070703327655792,
|
| 153 |
+
"eval_precision": 1.0,
|
| 154 |
+
"eval_recall": 0.9373333333333334,
|
| 155 |
+
"eval_runtime": 366.9725,
|
| 156 |
+
"eval_samples_per_second": 12.262,
|
| 157 |
+
"eval_steps_per_second": 1.534,
|
| 158 |
+
"step": 416
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.18,
|
| 162 |
+
"learning_rate": 4.1085714285714286e-05,
|
| 163 |
+
"loss": 0.3206,
|
| 164 |
+
"step": 468
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.18,
|
| 168 |
+
"eval_accuracy": 0.968,
|
| 169 |
+
"eval_f1": 0.9669421487603307,
|
| 170 |
+
"eval_loss": 0.18063302338123322,
|
| 171 |
+
"eval_precision": 1.0,
|
| 172 |
+
"eval_recall": 0.936,
|
| 173 |
+
"eval_runtime": 371.3928,
|
| 174 |
+
"eval_samples_per_second": 12.117,
|
| 175 |
+
"eval_steps_per_second": 1.516,
|
| 176 |
+
"step": 468
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.2,
|
| 180 |
+
"learning_rate": 4.00952380952381e-05,
|
| 181 |
+
"loss": 0.2036,
|
| 182 |
+
"step": 520
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.2,
|
| 186 |
+
"eval_accuracy": 0.9628888888888889,
|
| 187 |
+
"eval_f1": 0.9625308503477674,
|
| 188 |
+
"eval_loss": 0.5867714881896973,
|
| 189 |
+
"eval_precision": 0.9719075668328047,
|
| 190 |
+
"eval_recall": 0.9533333333333334,
|
| 191 |
+
"eval_runtime": 366.8218,
|
| 192 |
+
"eval_samples_per_second": 12.268,
|
| 193 |
+
"eval_steps_per_second": 1.535,
|
| 194 |
+
"step": 520
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.22,
|
| 198 |
+
"learning_rate": 3.910476190476191e-05,
|
| 199 |
+
"loss": 0.4246,
|
| 200 |
+
"step": 572
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.22,
|
| 204 |
+
"eval_accuracy": 0.9682222222222222,
|
| 205 |
+
"eval_f1": 0.9675663415740532,
|
| 206 |
+
"eval_loss": 0.14041858911514282,
|
| 207 |
+
"eval_precision": 0.9879573876794813,
|
| 208 |
+
"eval_recall": 0.948,
|
| 209 |
+
"eval_runtime": 366.7155,
|
| 210 |
+
"eval_samples_per_second": 12.271,
|
| 211 |
+
"eval_steps_per_second": 1.535,
|
| 212 |
+
"step": 572
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.24,
|
| 216 |
+
"learning_rate": 3.8114285714285714e-05,
|
| 217 |
+
"loss": 0.1938,
|
| 218 |
+
"step": 624
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.24,
|
| 222 |
+
"eval_accuracy": 0.9688888888888889,
|
| 223 |
+
"eval_f1": 0.9679046309032554,
|
| 224 |
+
"eval_loss": 0.12066192179918289,
|
| 225 |
+
"eval_precision": 0.9995265151515151,
|
| 226 |
+
"eval_recall": 0.9382222222222222,
|
| 227 |
+
"eval_runtime": 367.3124,
|
| 228 |
+
"eval_samples_per_second": 12.251,
|
| 229 |
+
"eval_steps_per_second": 1.533,
|
| 230 |
+
"step": 624
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.26,
|
| 234 |
+
"learning_rate": 3.712380952380953e-05,
|
| 235 |
+
"loss": 0.1131,
|
| 236 |
+
"step": 676
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.26,
|
| 240 |
+
"eval_accuracy": 0.9702222222222222,
|
| 241 |
+
"eval_f1": 0.9693363844393592,
|
| 242 |
+
"eval_loss": 0.15112678706645966,
|
| 243 |
+
"eval_precision": 0.9990566037735849,
|
| 244 |
+
"eval_recall": 0.9413333333333334,
|
| 245 |
+
"eval_runtime": 366.4976,
|
| 246 |
+
"eval_samples_per_second": 12.278,
|
| 247 |
+
"eval_steps_per_second": 1.536,
|
| 248 |
+
"step": 676
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.28,
|
| 252 |
+
"learning_rate": 3.6133333333333335e-05,
|
| 253 |
+
"loss": 0.1786,
|
| 254 |
+
"step": 728
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.28,
|
| 258 |
+
"eval_accuracy": 0.9717777777777777,
|
| 259 |
+
"eval_f1": 0.9710376282782212,
|
| 260 |
+
"eval_loss": 0.1380281001329422,
|
| 261 |
+
"eval_precision": 0.9971896955503513,
|
| 262 |
+
"eval_recall": 0.9462222222222222,
|
| 263 |
+
"eval_runtime": 366.0457,
|
| 264 |
+
"eval_samples_per_second": 12.294,
|
| 265 |
+
"eval_steps_per_second": 1.538,
|
| 266 |
+
"step": 728
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.3,
|
| 270 |
+
"learning_rate": 3.514285714285714e-05,
|
| 271 |
+
"loss": 0.1303,
|
| 272 |
+
"step": 780
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.3,
|
| 276 |
+
"eval_accuracy": 0.9717777777777777,
|
| 277 |
+
"eval_f1": 0.9709846927119031,
|
| 278 |
+
"eval_loss": 0.14563770592212677,
|
| 279 |
+
"eval_precision": 0.999059708509638,
|
| 280 |
+
"eval_recall": 0.9444444444444444,
|
| 281 |
+
"eval_runtime": 366.3569,
|
| 282 |
+
"eval_samples_per_second": 12.283,
|
| 283 |
+
"eval_steps_per_second": 1.537,
|
| 284 |
+
"step": 780
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.32,
|
| 288 |
+
"learning_rate": 3.415238095238095e-05,
|
| 289 |
+
"loss": 0.1851,
|
| 290 |
+
"step": 832
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.32,
|
| 294 |
+
"eval_accuracy": 0.9711111111111111,
|
| 295 |
+
"eval_f1": 0.970360237118103,
|
| 296 |
+
"eval_loss": 0.20535722374916077,
|
| 297 |
+
"eval_precision": 0.9962546816479401,
|
| 298 |
+
"eval_recall": 0.9457777777777778,
|
| 299 |
+
"eval_runtime": 366.4431,
|
| 300 |
+
"eval_samples_per_second": 12.28,
|
| 301 |
+
"eval_steps_per_second": 1.536,
|
| 302 |
+
"step": 832
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.34,
|
| 306 |
+
"learning_rate": 3.316190476190476e-05,
|
| 307 |
+
"loss": 0.1857,
|
| 308 |
+
"step": 884
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.34,
|
| 312 |
+
"eval_accuracy": 0.9722222222222222,
|
| 313 |
+
"eval_f1": 0.9714807209673739,
|
| 314 |
+
"eval_loss": 0.12345914542675018,
|
| 315 |
+
"eval_precision": 0.9981247069854665,
|
| 316 |
+
"eval_recall": 0.9462222222222222,
|
| 317 |
+
"eval_runtime": 366.3331,
|
| 318 |
+
"eval_samples_per_second": 12.284,
|
| 319 |
+
"eval_steps_per_second": 1.537,
|
| 320 |
+
"step": 884
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.36,
|
| 324 |
+
"learning_rate": 3.217142857142858e-05,
|
| 325 |
+
"loss": 0.2037,
|
| 326 |
+
"step": 936
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.36,
|
| 330 |
+
"eval_accuracy": 0.9548888888888889,
|
| 331 |
+
"eval_f1": 0.9527797162130728,
|
| 332 |
+
"eval_loss": 0.19388167560100555,
|
| 333 |
+
"eval_precision": 0.9995119570522206,
|
| 334 |
+
"eval_recall": 0.9102222222222223,
|
| 335 |
+
"eval_runtime": 368.1148,
|
| 336 |
+
"eval_samples_per_second": 12.224,
|
| 337 |
+
"eval_steps_per_second": 1.529,
|
| 338 |
+
"step": 936
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.38,
|
| 342 |
+
"learning_rate": 3.1180952380952384e-05,
|
| 343 |
+
"loss": 0.133,
|
| 344 |
+
"step": 988
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.38,
|
| 348 |
+
"eval_accuracy": 0.9591111111111111,
|
| 349 |
+
"eval_f1": 0.9585772174696083,
|
| 350 |
+
"eval_loss": 0.2834174335002899,
|
| 351 |
+
"eval_precision": 0.9712591240875912,
|
| 352 |
+
"eval_recall": 0.9462222222222222,
|
| 353 |
+
"eval_runtime": 366.4123,
|
| 354 |
+
"eval_samples_per_second": 12.281,
|
| 355 |
+
"eval_steps_per_second": 1.537,
|
| 356 |
+
"step": 988
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.4,
|
| 360 |
+
"learning_rate": 3.019047619047619e-05,
|
| 361 |
+
"loss": 0.105,
|
| 362 |
+
"step": 1040
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.4,
|
| 366 |
+
"eval_accuracy": 0.9693333333333334,
|
| 367 |
+
"eval_f1": 0.9684065934065934,
|
| 368 |
+
"eval_loss": 0.13286447525024414,
|
| 369 |
+
"eval_precision": 0.9985835694050992,
|
| 370 |
+
"eval_recall": 0.94,
|
| 371 |
+
"eval_runtime": 372.0042,
|
| 372 |
+
"eval_samples_per_second": 12.097,
|
| 373 |
+
"eval_steps_per_second": 1.513,
|
| 374 |
+
"step": 1040
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.42,
|
| 378 |
+
"learning_rate": 2.9199999999999998e-05,
|
| 379 |
+
"loss": 0.2736,
|
| 380 |
+
"step": 1092
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.42,
|
| 384 |
+
"eval_accuracy": 0.9504444444444444,
|
| 385 |
+
"eval_f1": 0.9502343226958269,
|
| 386 |
+
"eval_loss": 0.2549838125705719,
|
| 387 |
+
"eval_precision": 0.9542805916629314,
|
| 388 |
+
"eval_recall": 0.9462222222222222,
|
| 389 |
+
"eval_runtime": 366.5595,
|
| 390 |
+
"eval_samples_per_second": 12.276,
|
| 391 |
+
"eval_steps_per_second": 1.536,
|
| 392 |
+
"step": 1092
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.44,
|
| 396 |
+
"learning_rate": 2.8209523809523812e-05,
|
| 397 |
+
"loss": 0.2565,
|
| 398 |
+
"step": 1144
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.44,
|
| 402 |
+
"eval_accuracy": 0.9693333333333334,
|
| 403 |
+
"eval_f1": 0.9683921209344939,
|
| 404 |
+
"eval_loss": 0.16569776833057404,
|
| 405 |
+
"eval_precision": 0.999054820415879,
|
| 406 |
+
"eval_recall": 0.9395555555555556,
|
| 407 |
+
"eval_runtime": 366.5097,
|
| 408 |
+
"eval_samples_per_second": 12.278,
|
| 409 |
+
"eval_steps_per_second": 1.536,
|
| 410 |
+
"step": 1144
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.46,
|
| 414 |
+
"learning_rate": 2.7219047619047623e-05,
|
| 415 |
+
"loss": 0.0888,
|
| 416 |
+
"step": 1196
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.46,
|
| 420 |
+
"eval_accuracy": 0.9717777777777777,
|
| 421 |
+
"eval_f1": 0.9709979447362412,
|
| 422 |
+
"eval_loss": 0.14255712926387787,
|
| 423 |
+
"eval_precision": 0.9985908877407234,
|
| 424 |
+
"eval_recall": 0.9448888888888889,
|
| 425 |
+
"eval_runtime": 366.3675,
|
| 426 |
+
"eval_samples_per_second": 12.283,
|
| 427 |
+
"eval_steps_per_second": 1.537,
|
| 428 |
+
"step": 1196
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.48,
|
| 432 |
+
"learning_rate": 2.622857142857143e-05,
|
| 433 |
+
"loss": 0.1704,
|
| 434 |
+
"step": 1248
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.48,
|
| 438 |
+
"eval_accuracy": 0.9717777777777777,
|
| 439 |
+
"eval_f1": 0.9709714285714286,
|
| 440 |
+
"eval_loss": 0.13756924867630005,
|
| 441 |
+
"eval_precision": 0.9995294117647059,
|
| 442 |
+
"eval_recall": 0.944,
|
| 443 |
+
"eval_runtime": 366.5849,
|
| 444 |
+
"eval_samples_per_second": 12.275,
|
| 445 |
+
"eval_steps_per_second": 1.536,
|
| 446 |
+
"step": 1248
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.5,
|
| 450 |
+
"learning_rate": 2.523809523809524e-05,
|
| 451 |
+
"loss": 0.0877,
|
| 452 |
+
"step": 1300
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.5,
|
| 456 |
+
"eval_accuracy": 0.9715555555555555,
|
| 457 |
+
"eval_f1": 0.9707895937927886,
|
| 458 |
+
"eval_loss": 0.12067598104476929,
|
| 459 |
+
"eval_precision": 0.9976547842401501,
|
| 460 |
+
"eval_recall": 0.9453333333333334,
|
| 461 |
+
"eval_runtime": 366.3594,
|
| 462 |
+
"eval_samples_per_second": 12.283,
|
| 463 |
+
"eval_steps_per_second": 1.537,
|
| 464 |
+
"step": 1300
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.52,
|
| 468 |
+
"learning_rate": 2.424761904761905e-05,
|
| 469 |
+
"loss": 0.1013,
|
| 470 |
+
"step": 1352
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.52,
|
| 474 |
+
"eval_accuracy": 0.9711111111111111,
|
| 475 |
+
"eval_f1": 0.9702653247941445,
|
| 476 |
+
"eval_loss": 0.10261368751525879,
|
| 477 |
+
"eval_precision": 0.9995287464655985,
|
| 478 |
+
"eval_recall": 0.9426666666666667,
|
| 479 |
+
"eval_runtime": 367.9823,
|
| 480 |
+
"eval_samples_per_second": 12.229,
|
| 481 |
+
"eval_steps_per_second": 1.53,
|
| 482 |
+
"step": 1352
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.53,
|
| 486 |
+
"learning_rate": 2.3257142857142858e-05,
|
| 487 |
+
"loss": 0.1281,
|
| 488 |
+
"step": 1404
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.53,
|
| 492 |
+
"eval_accuracy": 0.9697777777777777,
|
| 493 |
+
"eval_f1": 0.968878718535469,
|
| 494 |
+
"eval_loss": 0.19041745364665985,
|
| 495 |
+
"eval_precision": 0.9985849056603774,
|
| 496 |
+
"eval_recall": 0.9408888888888889,
|
| 497 |
+
"eval_runtime": 368.2198,
|
| 498 |
+
"eval_samples_per_second": 12.221,
|
| 499 |
+
"eval_steps_per_second": 1.529,
|
| 500 |
+
"step": 1404
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.55,
|
| 504 |
+
"learning_rate": 2.2266666666666668e-05,
|
| 505 |
+
"loss": 0.1385,
|
| 506 |
+
"step": 1456
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.55,
|
| 510 |
+
"eval_accuracy": 0.9704444444444444,
|
| 511 |
+
"eval_f1": 0.9695443095946874,
|
| 512 |
+
"eval_loss": 0.1330152004957199,
|
| 513 |
+
"eval_precision": 1.0,
|
| 514 |
+
"eval_recall": 0.9408888888888889,
|
| 515 |
+
"eval_runtime": 366.4259,
|
| 516 |
+
"eval_samples_per_second": 12.281,
|
| 517 |
+
"eval_steps_per_second": 1.536,
|
| 518 |
+
"step": 1456
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.57,
|
| 522 |
+
"learning_rate": 2.127619047619048e-05,
|
| 523 |
+
"loss": 0.0947,
|
| 524 |
+
"step": 1508
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.57,
|
| 528 |
+
"eval_accuracy": 0.9722222222222222,
|
| 529 |
+
"eval_f1": 0.9714285714285714,
|
| 530 |
+
"eval_loss": 0.16506431996822357,
|
| 531 |
+
"eval_precision": 1.0,
|
| 532 |
+
"eval_recall": 0.9444444444444444,
|
| 533 |
+
"eval_runtime": 366.4491,
|
| 534 |
+
"eval_samples_per_second": 12.28,
|
| 535 |
+
"eval_steps_per_second": 1.536,
|
| 536 |
+
"step": 1508
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.59,
|
| 540 |
+
"learning_rate": 2.0285714285714286e-05,
|
| 541 |
+
"loss": 0.1062,
|
| 542 |
+
"step": 1560
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.59,
|
| 546 |
+
"eval_accuracy": 0.9728888888888889,
|
| 547 |
+
"eval_f1": 0.9721333942439471,
|
| 548 |
+
"eval_loss": 0.08876548707485199,
|
| 549 |
+
"eval_precision": 1.0,
|
| 550 |
+
"eval_recall": 0.9457777777777778,
|
| 551 |
+
"eval_runtime": 366.4995,
|
| 552 |
+
"eval_samples_per_second": 12.278,
|
| 553 |
+
"eval_steps_per_second": 1.536,
|
| 554 |
+
"step": 1560
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.61,
|
| 558 |
+
"learning_rate": 1.9295238095238096e-05,
|
| 559 |
+
"loss": 0.0974,
|
| 560 |
+
"step": 1612
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.61,
|
| 564 |
+
"eval_accuracy": 0.9726666666666667,
|
| 565 |
+
"eval_f1": 0.9719113952957296,
|
| 566 |
+
"eval_loss": 0.1103716641664505,
|
| 567 |
+
"eval_precision": 0.9995302959135745,
|
| 568 |
+
"eval_recall": 0.9457777777777778,
|
| 569 |
+
"eval_runtime": 367.3196,
|
| 570 |
+
"eval_samples_per_second": 12.251,
|
| 571 |
+
"eval_steps_per_second": 1.533,
|
| 572 |
+
"step": 1612
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.63,
|
| 576 |
+
"learning_rate": 1.8304761904761906e-05,
|
| 577 |
+
"loss": 0.1549,
|
| 578 |
+
"step": 1664
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.63,
|
| 582 |
+
"eval_accuracy": 0.9362222222222222,
|
| 583 |
+
"eval_f1": 0.9375951293759512,
|
| 584 |
+
"eval_loss": 1.4429972171783447,
|
| 585 |
+
"eval_precision": 0.9178373776074925,
|
| 586 |
+
"eval_recall": 0.9582222222222222,
|
| 587 |
+
"eval_runtime": 366.4448,
|
| 588 |
+
"eval_samples_per_second": 12.28,
|
| 589 |
+
"eval_steps_per_second": 1.536,
|
| 590 |
+
"step": 1664
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.65,
|
| 594 |
+
"learning_rate": 1.7314285714285717e-05,
|
| 595 |
+
"loss": 0.1223,
|
| 596 |
+
"step": 1716
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.65,
|
| 600 |
+
"eval_accuracy": 0.9717777777777777,
|
| 601 |
+
"eval_f1": 0.9710244125028521,
|
| 602 |
+
"eval_loss": 0.07695630192756653,
|
| 603 |
+
"eval_precision": 0.9976558837318331,
|
| 604 |
+
"eval_recall": 0.9457777777777778,
|
| 605 |
+
"eval_runtime": 366.6321,
|
| 606 |
+
"eval_samples_per_second": 12.274,
|
| 607 |
+
"eval_steps_per_second": 1.536,
|
| 608 |
+
"step": 1716
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.67,
|
| 612 |
+
"learning_rate": 1.6323809523809524e-05,
|
| 613 |
+
"loss": 0.0686,
|
| 614 |
+
"step": 1768
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.67,
|
| 618 |
+
"eval_accuracy": 0.9704444444444444,
|
| 619 |
+
"eval_f1": 0.9697107720337054,
|
| 620 |
+
"eval_loss": 0.15851092338562012,
|
| 621 |
+
"eval_precision": 0.9943951424567959,
|
| 622 |
+
"eval_recall": 0.9462222222222222,
|
| 623 |
+
"eval_runtime": 366.4624,
|
| 624 |
+
"eval_samples_per_second": 12.28,
|
| 625 |
+
"eval_steps_per_second": 1.536,
|
| 626 |
+
"step": 1768
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.69,
|
| 630 |
+
"learning_rate": 1.5333333333333334e-05,
|
| 631 |
+
"loss": 0.156,
|
| 632 |
+
"step": 1820
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.69,
|
| 636 |
+
"eval_accuracy": 0.9646666666666667,
|
| 637 |
+
"eval_f1": 0.9633724948168625,
|
| 638 |
+
"eval_loss": 0.2488366961479187,
|
| 639 |
+
"eval_precision": 1.0,
|
| 640 |
+
"eval_recall": 0.9293333333333333,
|
| 641 |
+
"eval_runtime": 369.4407,
|
| 642 |
+
"eval_samples_per_second": 12.181,
|
| 643 |
+
"eval_steps_per_second": 1.524,
|
| 644 |
+
"step": 1820
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.71,
|
| 648 |
+
"learning_rate": 1.4342857142857143e-05,
|
| 649 |
+
"loss": 0.1607,
|
| 650 |
+
"step": 1872
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.71,
|
| 654 |
+
"eval_accuracy": 0.9726666666666667,
|
| 655 |
+
"eval_f1": 0.971898560657985,
|
| 656 |
+
"eval_loss": 0.10330852121114731,
|
| 657 |
+
"eval_precision": 1.0,
|
| 658 |
+
"eval_recall": 0.9453333333333334,
|
| 659 |
+
"eval_runtime": 367.7786,
|
| 660 |
+
"eval_samples_per_second": 12.236,
|
| 661 |
+
"eval_steps_per_second": 1.531,
|
| 662 |
+
"step": 1872
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.73,
|
| 666 |
+
"learning_rate": 1.3352380952380952e-05,
|
| 667 |
+
"loss": 0.0813,
|
| 668 |
+
"step": 1924
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.73,
|
| 672 |
+
"eval_accuracy": 0.9726666666666667,
|
| 673 |
+
"eval_f1": 0.971898560657985,
|
| 674 |
+
"eval_loss": 0.11011069267988205,
|
| 675 |
+
"eval_precision": 1.0,
|
| 676 |
+
"eval_recall": 0.9453333333333334,
|
| 677 |
+
"eval_runtime": 366.3291,
|
| 678 |
+
"eval_samples_per_second": 12.284,
|
| 679 |
+
"eval_steps_per_second": 1.537,
|
| 680 |
+
"step": 1924
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.75,
|
| 684 |
+
"learning_rate": 1.2361904761904762e-05,
|
| 685 |
+
"loss": 0.0902,
|
| 686 |
+
"step": 1976
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.75,
|
| 690 |
+
"eval_accuracy": 0.9726666666666667,
|
| 691 |
+
"eval_f1": 0.971898560657985,
|
| 692 |
+
"eval_loss": 0.09210823476314545,
|
| 693 |
+
"eval_precision": 1.0,
|
| 694 |
+
"eval_recall": 0.9453333333333334,
|
| 695 |
+
"eval_runtime": 366.51,
|
| 696 |
+
"eval_samples_per_second": 12.278,
|
| 697 |
+
"eval_steps_per_second": 1.536,
|
| 698 |
+
"step": 1976
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.77,
|
| 702 |
+
"learning_rate": 1.1371428571428571e-05,
|
| 703 |
+
"loss": 0.1138,
|
| 704 |
+
"step": 2028
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.77,
|
| 708 |
+
"eval_accuracy": 0.9728888888888889,
|
| 709 |
+
"eval_f1": 0.9721333942439471,
|
| 710 |
+
"eval_loss": 0.12518948316574097,
|
| 711 |
+
"eval_precision": 1.0,
|
| 712 |
+
"eval_recall": 0.9457777777777778,
|
| 713 |
+
"eval_runtime": 367.2547,
|
| 714 |
+
"eval_samples_per_second": 12.253,
|
| 715 |
+
"eval_steps_per_second": 1.533,
|
| 716 |
+
"step": 2028
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.79,
|
| 720 |
+
"learning_rate": 1.0380952380952382e-05,
|
| 721 |
+
"loss": 0.1131,
|
| 722 |
+
"step": 2080
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.79,
|
| 726 |
+
"eval_accuracy": 0.9728888888888889,
|
| 727 |
+
"eval_f1": 0.9721333942439471,
|
| 728 |
+
"eval_loss": 0.07795156538486481,
|
| 729 |
+
"eval_precision": 1.0,
|
| 730 |
+
"eval_recall": 0.9457777777777778,
|
| 731 |
+
"eval_runtime": 366.7002,
|
| 732 |
+
"eval_samples_per_second": 12.272,
|
| 733 |
+
"eval_steps_per_second": 1.535,
|
| 734 |
+
"step": 2080
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.81,
|
| 738 |
+
"learning_rate": 9.39047619047619e-06,
|
| 739 |
+
"loss": 0.1169,
|
| 740 |
+
"step": 2132
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.81,
|
| 744 |
+
"eval_accuracy": 0.9728888888888889,
|
| 745 |
+
"eval_f1": 0.9721333942439471,
|
| 746 |
+
"eval_loss": 0.0857003927230835,
|
| 747 |
+
"eval_precision": 1.0,
|
| 748 |
+
"eval_recall": 0.9457777777777778,
|
| 749 |
+
"eval_runtime": 366.5193,
|
| 750 |
+
"eval_samples_per_second": 12.278,
|
| 751 |
+
"eval_steps_per_second": 1.536,
|
| 752 |
+
"step": 2132
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.83,
|
| 756 |
+
"learning_rate": 8.400000000000001e-06,
|
| 757 |
+
"loss": 0.0624,
|
| 758 |
+
"step": 2184
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.83,
|
| 762 |
+
"eval_accuracy": 0.9728888888888889,
|
| 763 |
+
"eval_f1": 0.9721333942439471,
|
| 764 |
+
"eval_loss": 0.11906697601079941,
|
| 765 |
+
"eval_precision": 1.0,
|
| 766 |
+
"eval_recall": 0.9457777777777778,
|
| 767 |
+
"eval_runtime": 366.4052,
|
| 768 |
+
"eval_samples_per_second": 12.281,
|
| 769 |
+
"eval_steps_per_second": 1.537,
|
| 770 |
+
"step": 2184
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.85,
|
| 774 |
+
"learning_rate": 7.40952380952381e-06,
|
| 775 |
+
"loss": 0.0936,
|
| 776 |
+
"step": 2236
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.85,
|
| 780 |
+
"eval_accuracy": 0.9728888888888889,
|
| 781 |
+
"eval_f1": 0.9721333942439471,
|
| 782 |
+
"eval_loss": 0.1168401688337326,
|
| 783 |
+
"eval_precision": 1.0,
|
| 784 |
+
"eval_recall": 0.9457777777777778,
|
| 785 |
+
"eval_runtime": 368.3489,
|
| 786 |
+
"eval_samples_per_second": 12.217,
|
| 787 |
+
"eval_steps_per_second": 1.528,
|
| 788 |
+
"step": 2236
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.87,
|
| 792 |
+
"learning_rate": 6.419047619047619e-06,
|
| 793 |
+
"loss": 0.1124,
|
| 794 |
+
"step": 2288
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.87,
|
| 798 |
+
"eval_accuracy": 0.9728888888888889,
|
| 799 |
+
"eval_f1": 0.9721333942439471,
|
| 800 |
+
"eval_loss": 0.08958863466978073,
|
| 801 |
+
"eval_precision": 1.0,
|
| 802 |
+
"eval_recall": 0.9457777777777778,
|
| 803 |
+
"eval_runtime": 367.9579,
|
| 804 |
+
"eval_samples_per_second": 12.23,
|
| 805 |
+
"eval_steps_per_second": 1.53,
|
| 806 |
+
"step": 2288
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.89,
|
| 810 |
+
"learning_rate": 5.428571428571429e-06,
|
| 811 |
+
"loss": 0.0519,
|
| 812 |
+
"step": 2340
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.89,
|
| 816 |
+
"eval_accuracy": 0.9728888888888889,
|
| 817 |
+
"eval_f1": 0.9721333942439471,
|
| 818 |
+
"eval_loss": 0.10539975017309189,
|
| 819 |
+
"eval_precision": 1.0,
|
| 820 |
+
"eval_recall": 0.9457777777777778,
|
| 821 |
+
"eval_runtime": 367.9097,
|
| 822 |
+
"eval_samples_per_second": 12.231,
|
| 823 |
+
"eval_steps_per_second": 1.53,
|
| 824 |
+
"step": 2340
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.91,
|
| 828 |
+
"learning_rate": 4.4380952380952385e-06,
|
| 829 |
+
"loss": 0.1278,
|
| 830 |
+
"step": 2392
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.91,
|
| 834 |
+
"eval_accuracy": 0.9728888888888889,
|
| 835 |
+
"eval_f1": 0.9721333942439471,
|
| 836 |
+
"eval_loss": 0.11540067195892334,
|
| 837 |
+
"eval_precision": 1.0,
|
| 838 |
+
"eval_recall": 0.9457777777777778,
|
| 839 |
+
"eval_runtime": 367.0779,
|
| 840 |
+
"eval_samples_per_second": 12.259,
|
| 841 |
+
"eval_steps_per_second": 1.534,
|
| 842 |
+
"step": 2392
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.93,
|
| 846 |
+
"learning_rate": 3.4476190476190472e-06,
|
| 847 |
+
"loss": 0.1412,
|
| 848 |
+
"step": 2444
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.93,
|
| 852 |
+
"eval_accuracy": 0.9728888888888889,
|
| 853 |
+
"eval_f1": 0.9721333942439471,
|
| 854 |
+
"eval_loss": 0.09740398824214935,
|
| 855 |
+
"eval_precision": 1.0,
|
| 856 |
+
"eval_recall": 0.9457777777777778,
|
| 857 |
+
"eval_runtime": 366.6614,
|
| 858 |
+
"eval_samples_per_second": 12.273,
|
| 859 |
+
"eval_steps_per_second": 1.535,
|
| 860 |
+
"step": 2444
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.95,
|
| 864 |
+
"learning_rate": 2.4571428571428573e-06,
|
| 865 |
+
"loss": 0.0472,
|
| 866 |
+
"step": 2496
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.95,
|
| 870 |
+
"eval_accuracy": 0.9728888888888889,
|
| 871 |
+
"eval_f1": 0.9721333942439471,
|
| 872 |
+
"eval_loss": 0.11149758845567703,
|
| 873 |
+
"eval_precision": 1.0,
|
| 874 |
+
"eval_recall": 0.9457777777777778,
|
| 875 |
+
"eval_runtime": 366.4328,
|
| 876 |
+
"eval_samples_per_second": 12.281,
|
| 877 |
+
"eval_steps_per_second": 1.536,
|
| 878 |
+
"step": 2496
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.97,
|
| 882 |
+
"learning_rate": 1.4666666666666667e-06,
|
| 883 |
+
"loss": 0.128,
|
| 884 |
+
"step": 2548
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.97,
|
| 888 |
+
"eval_accuracy": 0.9728888888888889,
|
| 889 |
+
"eval_f1": 0.9721333942439471,
|
| 890 |
+
"eval_loss": 0.09608805179595947,
|
| 891 |
+
"eval_precision": 1.0,
|
| 892 |
+
"eval_recall": 0.9457777777777778,
|
| 893 |
+
"eval_runtime": 367.1973,
|
| 894 |
+
"eval_samples_per_second": 12.255,
|
| 895 |
+
"eval_steps_per_second": 1.533,
|
| 896 |
+
"step": 2548
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.99,
|
| 900 |
+
"learning_rate": 4.761904761904763e-07,
|
| 901 |
+
"loss": 0.0462,
|
| 902 |
+
"step": 2600
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.99,
|
| 906 |
+
"eval_accuracy": 0.9728888888888889,
|
| 907 |
+
"eval_f1": 0.9721333942439471,
|
| 908 |
+
"eval_loss": 0.10537552833557129,
|
| 909 |
+
"eval_precision": 1.0,
|
| 910 |
+
"eval_recall": 0.9457777777777778,
|
| 911 |
+
"eval_runtime": 366.8901,
|
| 912 |
+
"eval_samples_per_second": 12.265,
|
| 913 |
+
"eval_steps_per_second": 1.535,
|
| 914 |
+
"step": 2600
|
| 915 |
+
}
|
| 916 |
+
],
|
| 917 |
+
"max_steps": 2625,
|
| 918 |
+
"num_train_epochs": 1,
|
| 919 |
+
"total_flos": 7.7969900961792e+16,
|
| 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:b9443f755ec9b57a1d1994658f6a2270fb3a503721d2936b3ce3ee27a38266ed
|
| 3 |
+
size 3451
|