Training in progress, step 1500, checkpoint
Browse files- checkpoint-1500/config.json +39 -0
- checkpoint-1500/merges.txt +0 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/pytorch_model.bin +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/special_tokens_map.json +15 -0
- checkpoint-1500/tokenizer.json +0 -0
- checkpoint-1500/tokenizer_config.json +57 -0
- checkpoint-1500/trainer_state.json +1894 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-1500/vocab.json +0 -0
checkpoint-1500/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSentimentClassification"
|
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": "text-classification",
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "0",
|
16 |
+
"1": "1",
|
17 |
+
"2": "2"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"0": 0,
|
23 |
+
"1": 1,
|
24 |
+
"2": 2
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-05,
|
27 |
+
"max_position_embeddings": 514,
|
28 |
+
"model_type": "roberta",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"problem_type": "single_label_classification",
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.34.1",
|
36 |
+
"type_vocab_size": 1,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50265
|
39 |
+
}
|
checkpoint-1500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8b6aa5bf4629e4d30b7b45269032b33612f885dc772e84d2d6e6b80fedfd0c7
|
3 |
+
size 997351674
|
checkpoint-1500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:524094ec85ab1f6c38ba79221c7ec78e8aae3d857ebf50abce7650c39315d832
|
3 |
+
size 498661166
|
checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a41b9419c0abbbb45323904ed06a3615c17806d67e5a893d89f675502ed03e13
|
3 |
+
size 14244
|
checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26f299d9dfb657287e200763a7dfe9c39f6622293b2dcf05e5c67bdd006e4e0b
|
3 |
+
size 1064
|
checkpoint-1500/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 |
+
}
|
checkpoint-1500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1500/tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,1894 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.514672686230249,
|
5 |
+
"eval_steps": 20,
|
6 |
+
"global_step": 1500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03,
|
13 |
+
"learning_rate": 5e-07,
|
14 |
+
"loss": 1.1046,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.06,
|
19 |
+
"learning_rate": 1e-06,
|
20 |
+
"loss": 1.0664,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.06,
|
25 |
+
"eval_accuracy": 0.44479243019924036,
|
26 |
+
"eval_combined_score": 0.3403229798934559,
|
27 |
+
"eval_f1": 0.2738667532127967,
|
28 |
+
"eval_loss": 1.065091609954834,
|
29 |
+
"eval_precision": 0.19784030596254612,
|
30 |
+
"eval_recall": 0.44479243019924036,
|
31 |
+
"eval_runtime": 49.6621,
|
32 |
+
"eval_samples_per_second": 604.364,
|
33 |
+
"eval_steps_per_second": 1.188,
|
34 |
+
"step": 20
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.09,
|
38 |
+
"learning_rate": 1.5e-06,
|
39 |
+
"loss": 1.0672,
|
40 |
+
"step": 30
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 0.12,
|
44 |
+
"learning_rate": 2e-06,
|
45 |
+
"loss": 1.0423,
|
46 |
+
"step": 40
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.12,
|
50 |
+
"eval_accuracy": 0.5033650962883988,
|
51 |
+
"eval_combined_score": 0.4633375988688383,
|
52 |
+
"eval_f1": 0.4137746858205889,
|
53 |
+
"eval_loss": 1.0188277959823608,
|
54 |
+
"eval_precision": 0.43284551707796665,
|
55 |
+
"eval_recall": 0.5033650962883988,
|
56 |
+
"eval_runtime": 49.1985,
|
57 |
+
"eval_samples_per_second": 610.06,
|
58 |
+
"eval_steps_per_second": 1.199,
|
59 |
+
"step": 40
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.15,
|
63 |
+
"learning_rate": 2.5e-06,
|
64 |
+
"loss": 1.027,
|
65 |
+
"step": 50
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.18,
|
69 |
+
"learning_rate": 3e-06,
|
70 |
+
"loss": 1.0137,
|
71 |
+
"step": 60
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.18,
|
75 |
+
"eval_accuracy": 0.5279203038581995,
|
76 |
+
"eval_combined_score": 0.48433586826626607,
|
77 |
+
"eval_f1": 0.4596383010419703,
|
78 |
+
"eval_loss": 0.9871189594268799,
|
79 |
+
"eval_precision": 0.421864564306695,
|
80 |
+
"eval_recall": 0.5279203038581995,
|
81 |
+
"eval_runtime": 49.0237,
|
82 |
+
"eval_samples_per_second": 612.235,
|
83 |
+
"eval_steps_per_second": 1.204,
|
84 |
+
"step": 60
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.21,
|
88 |
+
"learning_rate": 3.5e-06,
|
89 |
+
"loss": 1.0005,
|
90 |
+
"step": 70
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.24,
|
94 |
+
"learning_rate": 4e-06,
|
95 |
+
"loss": 1.0027,
|
96 |
+
"step": 80
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.24,
|
100 |
+
"eval_accuracy": 0.5308189511561271,
|
101 |
+
"eval_combined_score": 0.4866197693698143,
|
102 |
+
"eval_f1": 0.46528335920671143,
|
103 |
+
"eval_loss": 0.9888613224029541,
|
104 |
+
"eval_precision": 0.4195578159602916,
|
105 |
+
"eval_recall": 0.5308189511561271,
|
106 |
+
"eval_runtime": 49.518,
|
107 |
+
"eval_samples_per_second": 606.124,
|
108 |
+
"eval_steps_per_second": 1.191,
|
109 |
+
"step": 80
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.27,
|
113 |
+
"learning_rate": 4.5e-06,
|
114 |
+
"loss": 0.9937,
|
115 |
+
"step": 90
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.3,
|
119 |
+
"learning_rate": 5e-06,
|
120 |
+
"loss": 0.9914,
|
121 |
+
"step": 100
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.3,
|
125 |
+
"eval_accuracy": 0.5307856333710935,
|
126 |
+
"eval_combined_score": 0.48644275806230897,
|
127 |
+
"eval_f1": 0.4666072639999521,
|
128 |
+
"eval_loss": 0.9762536883354187,
|
129 |
+
"eval_precision": 0.4175925015070968,
|
130 |
+
"eval_recall": 0.5307856333710935,
|
131 |
+
"eval_runtime": 49.4629,
|
132 |
+
"eval_samples_per_second": 606.798,
|
133 |
+
"eval_steps_per_second": 1.193,
|
134 |
+
"step": 100
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.33,
|
138 |
+
"learning_rate": 5.5e-06,
|
139 |
+
"loss": 0.9884,
|
140 |
+
"step": 110
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.36,
|
144 |
+
"learning_rate": 6e-06,
|
145 |
+
"loss": 0.9826,
|
146 |
+
"step": 120
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.36,
|
150 |
+
"eval_accuracy": 0.5387819017791697,
|
151 |
+
"eval_combined_score": 0.4944622623129249,
|
152 |
+
"eval_f1": 0.47105988260831677,
|
153 |
+
"eval_loss": 0.9713281989097595,
|
154 |
+
"eval_precision": 0.4292253630850433,
|
155 |
+
"eval_recall": 0.5387819017791697,
|
156 |
+
"eval_runtime": 49.0682,
|
157 |
+
"eval_samples_per_second": 611.68,
|
158 |
+
"eval_steps_per_second": 1.202,
|
159 |
+
"step": 120
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.39,
|
163 |
+
"learning_rate": 6.5e-06,
|
164 |
+
"loss": 0.9882,
|
165 |
+
"step": 130
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.42,
|
169 |
+
"learning_rate": 7e-06,
|
170 |
+
"loss": 0.9788,
|
171 |
+
"step": 140
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.42,
|
175 |
+
"eval_accuracy": 0.5312520823615646,
|
176 |
+
"eval_combined_score": 0.48712844254868687,
|
177 |
+
"eval_f1": 0.4673598197970026,
|
178 |
+
"eval_loss": 0.9766249656677246,
|
179 |
+
"eval_precision": 0.41864978567461564,
|
180 |
+
"eval_recall": 0.5312520823615646,
|
181 |
+
"eval_runtime": 49.1859,
|
182 |
+
"eval_samples_per_second": 610.215,
|
183 |
+
"eval_steps_per_second": 1.2,
|
184 |
+
"step": 140
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.45,
|
188 |
+
"learning_rate": 7.5e-06,
|
189 |
+
"loss": 0.9854,
|
190 |
+
"step": 150
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 0.48,
|
194 |
+
"learning_rate": 8e-06,
|
195 |
+
"loss": 0.984,
|
196 |
+
"step": 160
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.48,
|
200 |
+
"eval_accuracy": 0.5398147531152129,
|
201 |
+
"eval_combined_score": 0.49477075635813,
|
202 |
+
"eval_f1": 0.4751263005883661,
|
203 |
+
"eval_loss": 0.9589501619338989,
|
204 |
+
"eval_precision": 0.4243272186137281,
|
205 |
+
"eval_recall": 0.5398147531152129,
|
206 |
+
"eval_runtime": 49.0847,
|
207 |
+
"eval_samples_per_second": 611.473,
|
208 |
+
"eval_steps_per_second": 1.202,
|
209 |
+
"step": 160
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.51,
|
213 |
+
"learning_rate": 8.500000000000002e-06,
|
214 |
+
"loss": 0.9795,
|
215 |
+
"step": 170
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.54,
|
219 |
+
"learning_rate": 9e-06,
|
220 |
+
"loss": 0.9694,
|
221 |
+
"step": 180
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.54,
|
225 |
+
"eval_accuracy": 0.5423469047777704,
|
226 |
+
"eval_combined_score": 0.49718028497336725,
|
227 |
+
"eval_f1": 0.4771728160733735,
|
228 |
+
"eval_loss": 0.953514814376831,
|
229 |
+
"eval_precision": 0.42685451426455484,
|
230 |
+
"eval_recall": 0.5423469047777704,
|
231 |
+
"eval_runtime": 49.0032,
|
232 |
+
"eval_samples_per_second": 612.491,
|
233 |
+
"eval_steps_per_second": 1.204,
|
234 |
+
"step": 180
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.57,
|
238 |
+
"learning_rate": 9.5e-06,
|
239 |
+
"loss": 0.9757,
|
240 |
+
"step": 190
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.6,
|
244 |
+
"learning_rate": 1e-05,
|
245 |
+
"loss": 0.9676,
|
246 |
+
"step": 200
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 0.6,
|
250 |
+
"eval_accuracy": 0.567201972412874,
|
251 |
+
"eval_combined_score": 0.5200447629299639,
|
252 |
+
"eval_f1": 0.49911443945569844,
|
253 |
+
"eval_loss": 0.9273685812950134,
|
254 |
+
"eval_precision": 0.44666066743840943,
|
255 |
+
"eval_recall": 0.567201972412874,
|
256 |
+
"eval_runtime": 49.1912,
|
257 |
+
"eval_samples_per_second": 610.15,
|
258 |
+
"eval_steps_per_second": 1.199,
|
259 |
+
"step": 200
|
260 |
+
},
|
261 |
+
{
|
262 |
+
"epoch": 0.63,
|
263 |
+
"learning_rate": 1.0500000000000001e-05,
|
264 |
+
"loss": 0.9708,
|
265 |
+
"step": 210
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.66,
|
269 |
+
"learning_rate": 1.1e-05,
|
270 |
+
"loss": 0.9753,
|
271 |
+
"step": 220
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.66,
|
275 |
+
"eval_accuracy": 0.573598987139335,
|
276 |
+
"eval_combined_score": 0.5278568904198743,
|
277 |
+
"eval_f1": 0.5026102591641352,
|
278 |
+
"eval_loss": 0.912590503692627,
|
279 |
+
"eval_precision": 0.4616193282366919,
|
280 |
+
"eval_recall": 0.573598987139335,
|
281 |
+
"eval_runtime": 49.2154,
|
282 |
+
"eval_samples_per_second": 609.849,
|
283 |
+
"eval_steps_per_second": 1.199,
|
284 |
+
"step": 220
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.69,
|
288 |
+
"learning_rate": 1.15e-05,
|
289 |
+
"loss": 0.9586,
|
290 |
+
"step": 230
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.72,
|
294 |
+
"learning_rate": 1.2e-05,
|
295 |
+
"loss": 0.9557,
|
296 |
+
"step": 240
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.72,
|
300 |
+
"eval_accuracy": 0.5759645498767242,
|
301 |
+
"eval_combined_score": 0.5280177627115059,
|
302 |
+
"eval_f1": 0.5069205876947673,
|
303 |
+
"eval_loss": 0.9052607417106628,
|
304 |
+
"eval_precision": 0.45322136339780783,
|
305 |
+
"eval_recall": 0.5759645498767242,
|
306 |
+
"eval_runtime": 49.1399,
|
307 |
+
"eval_samples_per_second": 610.787,
|
308 |
+
"eval_steps_per_second": 1.201,
|
309 |
+
"step": 240
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.75,
|
313 |
+
"learning_rate": 1.25e-05,
|
314 |
+
"loss": 0.9518,
|
315 |
+
"step": 250
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.78,
|
319 |
+
"learning_rate": 1.3e-05,
|
320 |
+
"loss": 0.9508,
|
321 |
+
"step": 260
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.78,
|
325 |
+
"eval_accuracy": 0.5766975411474645,
|
326 |
+
"eval_combined_score": 0.534067292009198,
|
327 |
+
"eval_f1": 0.5018221478654629,
|
328 |
+
"eval_loss": 0.9178985953330994,
|
329 |
+
"eval_precision": 0.4810519378764,
|
330 |
+
"eval_recall": 0.5766975411474645,
|
331 |
+
"eval_runtime": 49.2092,
|
332 |
+
"eval_samples_per_second": 609.927,
|
333 |
+
"eval_steps_per_second": 1.199,
|
334 |
+
"step": 260
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 0.81,
|
338 |
+
"learning_rate": 1.35e-05,
|
339 |
+
"loss": 0.9405,
|
340 |
+
"step": 270
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.84,
|
344 |
+
"learning_rate": 1.4e-05,
|
345 |
+
"loss": 0.9355,
|
346 |
+
"step": 280
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.84,
|
350 |
+
"eval_accuracy": 0.58915839275005,
|
351 |
+
"eval_combined_score": 0.5407092882328752,
|
352 |
+
"eval_f1": 0.5183161389995846,
|
353 |
+
"eval_loss": 0.8937407732009888,
|
354 |
+
"eval_precision": 0.46620422843181647,
|
355 |
+
"eval_recall": 0.58915839275005,
|
356 |
+
"eval_runtime": 49.2523,
|
357 |
+
"eval_samples_per_second": 609.393,
|
358 |
+
"eval_steps_per_second": 1.198,
|
359 |
+
"step": 280
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.87,
|
363 |
+
"learning_rate": 1.4500000000000002e-05,
|
364 |
+
"loss": 0.9235,
|
365 |
+
"step": 290
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 0.9,
|
369 |
+
"learning_rate": 1.5e-05,
|
370 |
+
"loss": 0.9,
|
371 |
+
"step": 300
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.9,
|
375 |
+
"eval_accuracy": 0.613013926834144,
|
376 |
+
"eval_combined_score": 0.5923759012239074,
|
377 |
+
"eval_f1": 0.5579282363395321,
|
378 |
+
"eval_loss": 0.8468813300132751,
|
379 |
+
"eval_precision": 0.5855475148878095,
|
380 |
+
"eval_recall": 0.613013926834144,
|
381 |
+
"eval_runtime": 49.1896,
|
382 |
+
"eval_samples_per_second": 610.17,
|
383 |
+
"eval_steps_per_second": 1.199,
|
384 |
+
"step": 300
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.93,
|
388 |
+
"learning_rate": 1.55e-05,
|
389 |
+
"loss": 0.8857,
|
390 |
+
"step": 310
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.96,
|
394 |
+
"learning_rate": 1.6e-05,
|
395 |
+
"loss": 0.993,
|
396 |
+
"step": 320
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"epoch": 0.96,
|
400 |
+
"eval_accuracy": 0.6046511627906976,
|
401 |
+
"eval_combined_score": 0.590510828847508,
|
402 |
+
"eval_f1": 0.5352474275558012,
|
403 |
+
"eval_loss": 0.8615403771400452,
|
404 |
+
"eval_precision": 0.6174935622528357,
|
405 |
+
"eval_recall": 0.6046511627906976,
|
406 |
+
"eval_runtime": 49.37,
|
407 |
+
"eval_samples_per_second": 607.94,
|
408 |
+
"eval_steps_per_second": 1.195,
|
409 |
+
"step": 320
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.99,
|
413 |
+
"learning_rate": 1.65e-05,
|
414 |
+
"loss": 0.8418,
|
415 |
+
"step": 330
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 1.02,
|
419 |
+
"learning_rate": 1.7000000000000003e-05,
|
420 |
+
"loss": 0.8527,
|
421 |
+
"step": 340
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 1.02,
|
425 |
+
"eval_accuracy": 0.6439328313453722,
|
426 |
+
"eval_combined_score": 0.6332615383344228,
|
427 |
+
"eval_f1": 0.6212200513859825,
|
428 |
+
"eval_loss": 0.7896137237548828,
|
429 |
+
"eval_precision": 0.6239604392609642,
|
430 |
+
"eval_recall": 0.6439328313453722,
|
431 |
+
"eval_runtime": 49.1146,
|
432 |
+
"eval_samples_per_second": 611.102,
|
433 |
+
"eval_steps_per_second": 1.201,
|
434 |
+
"step": 340
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 1.05,
|
438 |
+
"learning_rate": 1.7500000000000002e-05,
|
439 |
+
"loss": 0.8982,
|
440 |
+
"step": 350
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.08,
|
444 |
+
"learning_rate": 1.8e-05,
|
445 |
+
"loss": 0.966,
|
446 |
+
"step": 360
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 1.08,
|
450 |
+
"eval_accuracy": 0.5315852602119011,
|
451 |
+
"eval_combined_score": 0.5500800253024862,
|
452 |
+
"eval_f1": 0.4943799031015135,
|
453 |
+
"eval_loss": 1.0123510360717773,
|
454 |
+
"eval_precision": 0.642769677684629,
|
455 |
+
"eval_recall": 0.5315852602119011,
|
456 |
+
"eval_runtime": 49.1941,
|
457 |
+
"eval_samples_per_second": 610.114,
|
458 |
+
"eval_steps_per_second": 1.199,
|
459 |
+
"step": 360
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 1.11,
|
463 |
+
"learning_rate": 1.85e-05,
|
464 |
+
"loss": 0.9413,
|
465 |
+
"step": 370
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.14,
|
469 |
+
"learning_rate": 1.9e-05,
|
470 |
+
"loss": 0.8441,
|
471 |
+
"step": 380
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 1.14,
|
475 |
+
"eval_accuracy": 0.6488638635303525,
|
476 |
+
"eval_combined_score": 0.648329789222037,
|
477 |
+
"eval_f1": 0.6371420074616733,
|
478 |
+
"eval_loss": 0.791083574295044,
|
479 |
+
"eval_precision": 0.6584494223657698,
|
480 |
+
"eval_recall": 0.6488638635303525,
|
481 |
+
"eval_runtime": 49.3484,
|
482 |
+
"eval_samples_per_second": 608.207,
|
483 |
+
"eval_steps_per_second": 1.196,
|
484 |
+
"step": 380
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 1.17,
|
488 |
+
"learning_rate": 1.95e-05,
|
489 |
+
"loss": 0.8223,
|
490 |
+
"step": 390
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 1.2,
|
494 |
+
"learning_rate": 2e-05,
|
495 |
+
"loss": 0.8226,
|
496 |
+
"step": 400
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 1.2,
|
500 |
+
"eval_accuracy": 0.6699873392416872,
|
501 |
+
"eval_combined_score": 0.6621103162794577,
|
502 |
+
"eval_f1": 0.6459453754294268,
|
503 |
+
"eval_loss": 0.7472424507141113,
|
504 |
+
"eval_precision": 0.6625212112050299,
|
505 |
+
"eval_recall": 0.6699873392416872,
|
506 |
+
"eval_runtime": 49.3153,
|
507 |
+
"eval_samples_per_second": 608.614,
|
508 |
+
"eval_steps_per_second": 1.196,
|
509 |
+
"step": 400
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 1.23,
|
513 |
+
"learning_rate": 2.05e-05,
|
514 |
+
"loss": 0.7924,
|
515 |
+
"step": 410
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 1.26,
|
519 |
+
"learning_rate": 2.1000000000000002e-05,
|
520 |
+
"loss": 0.7948,
|
521 |
+
"step": 420
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.26,
|
525 |
+
"eval_accuracy": 0.6580595721996402,
|
526 |
+
"eval_combined_score": 0.6513132521613654,
|
527 |
+
"eval_f1": 0.6095365334747936,
|
528 |
+
"eval_loss": 0.7663838863372803,
|
529 |
+
"eval_precision": 0.6795973307713873,
|
530 |
+
"eval_recall": 0.6580595721996402,
|
531 |
+
"eval_runtime": 49.2143,
|
532 |
+
"eval_samples_per_second": 609.863,
|
533 |
+
"eval_steps_per_second": 1.199,
|
534 |
+
"step": 420
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 1.29,
|
538 |
+
"learning_rate": 2.1499999999999997e-05,
|
539 |
+
"loss": 0.776,
|
540 |
+
"step": 430
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 1.32,
|
544 |
+
"learning_rate": 2.2e-05,
|
545 |
+
"loss": 0.7428,
|
546 |
+
"step": 440
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 1.32,
|
550 |
+
"eval_accuracy": 0.6991737189311654,
|
551 |
+
"eval_combined_score": 0.6905198116505921,
|
552 |
+
"eval_f1": 0.653333567856404,
|
553 |
+
"eval_loss": 0.6993714570999146,
|
554 |
+
"eval_precision": 0.7103982408836337,
|
555 |
+
"eval_recall": 0.6991737189311654,
|
556 |
+
"eval_runtime": 49.1465,
|
557 |
+
"eval_samples_per_second": 610.704,
|
558 |
+
"eval_steps_per_second": 1.2,
|
559 |
+
"step": 440
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 1.35,
|
563 |
+
"learning_rate": 2.2499999999999998e-05,
|
564 |
+
"loss": 0.7512,
|
565 |
+
"step": 450
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 1.38,
|
569 |
+
"learning_rate": 2.3e-05,
|
570 |
+
"loss": 0.7109,
|
571 |
+
"step": 460
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 1.38,
|
575 |
+
"eval_accuracy": 0.7283600986206437,
|
576 |
+
"eval_combined_score": 0.7200537958840363,
|
577 |
+
"eval_f1": 0.6890059409106147,
|
578 |
+
"eval_loss": 0.6510820984840393,
|
579 |
+
"eval_precision": 0.7344890453842432,
|
580 |
+
"eval_recall": 0.7283600986206437,
|
581 |
+
"eval_runtime": 49.0446,
|
582 |
+
"eval_samples_per_second": 611.974,
|
583 |
+
"eval_steps_per_second": 1.203,
|
584 |
+
"step": 460
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 1.41,
|
588 |
+
"learning_rate": 2.3500000000000002e-05,
|
589 |
+
"loss": 0.701,
|
590 |
+
"step": 470
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 1.44,
|
594 |
+
"learning_rate": 2.4e-05,
|
595 |
+
"loss": 0.6882,
|
596 |
+
"step": 480
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 1.44,
|
600 |
+
"eval_accuracy": 0.7576797494502565,
|
601 |
+
"eval_combined_score": 0.7514829004826655,
|
602 |
+
"eval_f1": 0.7336051419487455,
|
603 |
+
"eval_loss": 0.5987845063209534,
|
604 |
+
"eval_precision": 0.7569669610814035,
|
605 |
+
"eval_recall": 0.7576797494502565,
|
606 |
+
"eval_runtime": 49.3939,
|
607 |
+
"eval_samples_per_second": 607.646,
|
608 |
+
"eval_steps_per_second": 1.194,
|
609 |
+
"step": 480
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 1.47,
|
613 |
+
"learning_rate": 2.4500000000000003e-05,
|
614 |
+
"loss": 0.651,
|
615 |
+
"step": 490
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 1.5,
|
619 |
+
"learning_rate": 2.5e-05,
|
620 |
+
"loss": 0.7296,
|
621 |
+
"step": 500
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 1.5,
|
625 |
+
"eval_accuracy": 0.7564136736189778,
|
626 |
+
"eval_combined_score": 0.7674838523650971,
|
627 |
+
"eval_f1": 0.766902713706533,
|
628 |
+
"eval_loss": 0.5992804765701294,
|
629 |
+
"eval_precision": 0.7902053485158999,
|
630 |
+
"eval_recall": 0.7564136736189778,
|
631 |
+
"eval_runtime": 49.1622,
|
632 |
+
"eval_samples_per_second": 610.509,
|
633 |
+
"eval_steps_per_second": 1.2,
|
634 |
+
"step": 500
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 1.53,
|
638 |
+
"learning_rate": 2.55e-05,
|
639 |
+
"loss": 0.5943,
|
640 |
+
"step": 510
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 1.57,
|
644 |
+
"learning_rate": 2.6e-05,
|
645 |
+
"loss": 0.5677,
|
646 |
+
"step": 520
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 1.57,
|
650 |
+
"eval_accuracy": 0.8125874591857133,
|
651 |
+
"eval_combined_score": 0.8104607682202668,
|
652 |
+
"eval_f1": 0.7941544044601274,
|
653 |
+
"eval_loss": 0.5067983865737915,
|
654 |
+
"eval_precision": 0.8225137500495135,
|
655 |
+
"eval_recall": 0.8125874591857133,
|
656 |
+
"eval_runtime": 49.0571,
|
657 |
+
"eval_samples_per_second": 611.817,
|
658 |
+
"eval_steps_per_second": 1.203,
|
659 |
+
"step": 520
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 1.6,
|
663 |
+
"learning_rate": 2.65e-05,
|
664 |
+
"loss": 0.5818,
|
665 |
+
"step": 530
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 1.63,
|
669 |
+
"learning_rate": 2.7e-05,
|
670 |
+
"loss": 0.5096,
|
671 |
+
"step": 540
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 1.63,
|
675 |
+
"eval_accuracy": 0.8520023988805224,
|
676 |
+
"eval_combined_score": 0.8500052190439381,
|
677 |
+
"eval_f1": 0.8448837390352126,
|
678 |
+
"eval_loss": 0.42726200819015503,
|
679 |
+
"eval_precision": 0.8511323393794948,
|
680 |
+
"eval_recall": 0.8520023988805224,
|
681 |
+
"eval_runtime": 49.0407,
|
682 |
+
"eval_samples_per_second": 612.023,
|
683 |
+
"eval_steps_per_second": 1.203,
|
684 |
+
"step": 540
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 1.66,
|
688 |
+
"learning_rate": 2.75e-05,
|
689 |
+
"loss": 0.462,
|
690 |
+
"step": 550
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 1.69,
|
694 |
+
"learning_rate": 2.8e-05,
|
695 |
+
"loss": 0.4452,
|
696 |
+
"step": 560
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 1.69,
|
700 |
+
"eval_accuracy": 0.8721929766109149,
|
701 |
+
"eval_combined_score": 0.8711433017214012,
|
702 |
+
"eval_f1": 0.8698654313719106,
|
703 |
+
"eval_loss": 0.37960025668144226,
|
704 |
+
"eval_precision": 0.8703218222918644,
|
705 |
+
"eval_recall": 0.8721929766109149,
|
706 |
+
"eval_runtime": 49.6519,
|
707 |
+
"eval_samples_per_second": 604.489,
|
708 |
+
"eval_steps_per_second": 1.188,
|
709 |
+
"step": 560
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 1.72,
|
713 |
+
"learning_rate": 2.85e-05,
|
714 |
+
"loss": 0.4267,
|
715 |
+
"step": 570
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 1.75,
|
719 |
+
"learning_rate": 2.9000000000000004e-05,
|
720 |
+
"loss": 0.3836,
|
721 |
+
"step": 580
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 1.75,
|
725 |
+
"eval_accuracy": 0.8756580262544146,
|
726 |
+
"eval_combined_score": 0.876232023467392,
|
727 |
+
"eval_f1": 0.8758457824110393,
|
728 |
+
"eval_loss": 0.3854842483997345,
|
729 |
+
"eval_precision": 0.8777662589496996,
|
730 |
+
"eval_recall": 0.8756580262544146,
|
731 |
+
"eval_runtime": 49.2229,
|
732 |
+
"eval_samples_per_second": 609.757,
|
733 |
+
"eval_steps_per_second": 1.199,
|
734 |
+
"step": 580
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 1.78,
|
738 |
+
"learning_rate": 2.95e-05,
|
739 |
+
"loss": 0.3828,
|
740 |
+
"step": 590
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 1.81,
|
744 |
+
"learning_rate": 3e-05,
|
745 |
+
"loss": 0.3783,
|
746 |
+
"step": 600
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 1.81,
|
750 |
+
"eval_accuracy": 0.8893849536882789,
|
751 |
+
"eval_combined_score": 0.8889004932680924,
|
752 |
+
"eval_f1": 0.8883136621852403,
|
753 |
+
"eval_loss": 0.35855188965797424,
|
754 |
+
"eval_precision": 0.8885184035105714,
|
755 |
+
"eval_recall": 0.8893849536882789,
|
756 |
+
"eval_runtime": 49.2611,
|
757 |
+
"eval_samples_per_second": 609.285,
|
758 |
+
"eval_steps_per_second": 1.198,
|
759 |
+
"step": 600
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 1.84,
|
763 |
+
"learning_rate": 3.05e-05,
|
764 |
+
"loss": 0.3466,
|
765 |
+
"step": 610
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 1.87,
|
769 |
+
"learning_rate": 3.1e-05,
|
770 |
+
"loss": 0.3496,
|
771 |
+
"step": 620
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 1.87,
|
775 |
+
"eval_accuracy": 0.8971813153861531,
|
776 |
+
"eval_combined_score": 0.8972621407363919,
|
777 |
+
"eval_f1": 0.8972738562660447,
|
778 |
+
"eval_loss": 0.321043998003006,
|
779 |
+
"eval_precision": 0.8974120759072168,
|
780 |
+
"eval_recall": 0.8971813153861531,
|
781 |
+
"eval_runtime": 49.4334,
|
782 |
+
"eval_samples_per_second": 607.16,
|
783 |
+
"eval_steps_per_second": 1.194,
|
784 |
+
"step": 620
|
785 |
+
},
|
786 |
+
{
|
787 |
+
"epoch": 1.9,
|
788 |
+
"learning_rate": 3.15e-05,
|
789 |
+
"loss": 0.3421,
|
790 |
+
"step": 630
|
791 |
+
},
|
792 |
+
{
|
793 |
+
"epoch": 1.93,
|
794 |
+
"learning_rate": 3.2e-05,
|
795 |
+
"loss": 0.3585,
|
796 |
+
"step": 640
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 1.93,
|
800 |
+
"eval_accuracy": 0.9035450123275804,
|
801 |
+
"eval_combined_score": 0.9033726098964578,
|
802 |
+
"eval_f1": 0.9030761902479666,
|
803 |
+
"eval_loss": 0.3006099760532379,
|
804 |
+
"eval_precision": 0.903324224682704,
|
805 |
+
"eval_recall": 0.9035450123275804,
|
806 |
+
"eval_runtime": 49.1842,
|
807 |
+
"eval_samples_per_second": 610.237,
|
808 |
+
"eval_steps_per_second": 1.2,
|
809 |
+
"step": 640
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 1.96,
|
813 |
+
"learning_rate": 3.2500000000000004e-05,
|
814 |
+
"loss": 0.3442,
|
815 |
+
"step": 650
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 1.99,
|
819 |
+
"learning_rate": 3.3e-05,
|
820 |
+
"loss": 0.345,
|
821 |
+
"step": 660
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 1.99,
|
825 |
+
"eval_accuracy": 0.9014126740854268,
|
826 |
+
"eval_combined_score": 0.9026415340332592,
|
827 |
+
"eval_f1": 0.9025066760774267,
|
828 |
+
"eval_loss": 0.30540063977241516,
|
829 |
+
"eval_precision": 0.9052341118847564,
|
830 |
+
"eval_recall": 0.9014126740854268,
|
831 |
+
"eval_runtime": 49.4063,
|
832 |
+
"eval_samples_per_second": 607.494,
|
833 |
+
"eval_steps_per_second": 1.194,
|
834 |
+
"step": 660
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 2.02,
|
838 |
+
"learning_rate": 3.35e-05,
|
839 |
+
"loss": 0.3246,
|
840 |
+
"step": 670
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 2.05,
|
844 |
+
"learning_rate": 3.4000000000000007e-05,
|
845 |
+
"loss": 0.3327,
|
846 |
+
"step": 680
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 2.05,
|
850 |
+
"eval_accuracy": 0.8912507496501633,
|
851 |
+
"eval_combined_score": 0.8911549520027604,
|
852 |
+
"eval_f1": 0.8866402874920362,
|
853 |
+
"eval_loss": 0.3174073100090027,
|
854 |
+
"eval_precision": 0.895478021218679,
|
855 |
+
"eval_recall": 0.8912507496501633,
|
856 |
+
"eval_runtime": 49.3463,
|
857 |
+
"eval_samples_per_second": 608.232,
|
858 |
+
"eval_steps_per_second": 1.196,
|
859 |
+
"step": 680
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 2.08,
|
863 |
+
"learning_rate": 3.4500000000000005e-05,
|
864 |
+
"loss": 0.3172,
|
865 |
+
"step": 690
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 2.11,
|
869 |
+
"learning_rate": 3.5000000000000004e-05,
|
870 |
+
"loss": 0.2962,
|
871 |
+
"step": 700
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 2.11,
|
875 |
+
"eval_accuracy": 0.9122076364363297,
|
876 |
+
"eval_combined_score": 0.9124808443428073,
|
877 |
+
"eval_f1": 0.9125293911738805,
|
878 |
+
"eval_loss": 0.2769884169101715,
|
879 |
+
"eval_precision": 0.9129787133246888,
|
880 |
+
"eval_recall": 0.9122076364363297,
|
881 |
+
"eval_runtime": 49.3634,
|
882 |
+
"eval_samples_per_second": 608.021,
|
883 |
+
"eval_steps_per_second": 1.195,
|
884 |
+
"step": 700
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 2.14,
|
888 |
+
"learning_rate": 3.5499999999999996e-05,
|
889 |
+
"loss": 0.287,
|
890 |
+
"step": 710
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 2.17,
|
894 |
+
"learning_rate": 3.6e-05,
|
895 |
+
"loss": 0.3032,
|
896 |
+
"step": 720
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 2.17,
|
900 |
+
"eval_accuracy": 0.9062437529153062,
|
901 |
+
"eval_combined_score": 0.9068222505646787,
|
902 |
+
"eval_f1": 0.9054896753410417,
|
903 |
+
"eval_loss": 0.2979203760623932,
|
904 |
+
"eval_precision": 0.9093118210870608,
|
905 |
+
"eval_recall": 0.9062437529153062,
|
906 |
+
"eval_runtime": 49.0419,
|
907 |
+
"eval_samples_per_second": 612.007,
|
908 |
+
"eval_steps_per_second": 1.203,
|
909 |
+
"step": 720
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 2.2,
|
913 |
+
"learning_rate": 3.65e-05,
|
914 |
+
"loss": 0.3017,
|
915 |
+
"step": 730
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 2.23,
|
919 |
+
"learning_rate": 3.7e-05,
|
920 |
+
"loss": 0.27,
|
921 |
+
"step": 740
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 2.23,
|
925 |
+
"eval_accuracy": 0.8997801026187779,
|
926 |
+
"eval_combined_score": 0.9003031124352014,
|
927 |
+
"eval_f1": 0.8971406374938125,
|
928 |
+
"eval_loss": 0.29734131693840027,
|
929 |
+
"eval_precision": 0.9045116070094374,
|
930 |
+
"eval_recall": 0.8997801026187779,
|
931 |
+
"eval_runtime": 49.1818,
|
932 |
+
"eval_samples_per_second": 610.267,
|
933 |
+
"eval_steps_per_second": 1.2,
|
934 |
+
"step": 740
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 2.26,
|
938 |
+
"learning_rate": 3.75e-05,
|
939 |
+
"loss": 0.3042,
|
940 |
+
"step": 750
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 2.29,
|
944 |
+
"learning_rate": 3.8e-05,
|
945 |
+
"loss": 0.2912,
|
946 |
+
"step": 760
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 2.29,
|
950 |
+
"eval_accuracy": 0.9221696541613914,
|
951 |
+
"eval_combined_score": 0.9221674217032323,
|
952 |
+
"eval_f1": 0.922071694968714,
|
953 |
+
"eval_loss": 0.24671417474746704,
|
954 |
+
"eval_precision": 0.9222586835214323,
|
955 |
+
"eval_recall": 0.9221696541613914,
|
956 |
+
"eval_runtime": 49.2126,
|
957 |
+
"eval_samples_per_second": 609.884,
|
958 |
+
"eval_steps_per_second": 1.199,
|
959 |
+
"step": 760
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 2.32,
|
963 |
+
"learning_rate": 3.85e-05,
|
964 |
+
"loss": 0.2609,
|
965 |
+
"step": 770
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 2.35,
|
969 |
+
"learning_rate": 3.9e-05,
|
970 |
+
"loss": 0.2412,
|
971 |
+
"step": 780
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 2.35,
|
975 |
+
"eval_accuracy": 0.9113080562404211,
|
976 |
+
"eval_combined_score": 0.9131963179862455,
|
977 |
+
"eval_f1": 0.9128361841568111,
|
978 |
+
"eval_loss": 0.2760636806488037,
|
979 |
+
"eval_precision": 0.917332975307328,
|
980 |
+
"eval_recall": 0.9113080562404211,
|
981 |
+
"eval_runtime": 49.2008,
|
982 |
+
"eval_samples_per_second": 610.031,
|
983 |
+
"eval_steps_per_second": 1.199,
|
984 |
+
"step": 780
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 2.38,
|
988 |
+
"learning_rate": 3.95e-05,
|
989 |
+
"loss": 0.2755,
|
990 |
+
"step": 790
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 2.41,
|
994 |
+
"learning_rate": 4e-05,
|
995 |
+
"loss": 0.2746,
|
996 |
+
"step": 800
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 2.41,
|
1000 |
+
"eval_accuracy": 0.9260011994402612,
|
1001 |
+
"eval_combined_score": 0.9259453001449679,
|
1002 |
+
"eval_f1": 0.9257439757889774,
|
1003 |
+
"eval_loss": 0.24102580547332764,
|
1004 |
+
"eval_precision": 0.9260348259103722,
|
1005 |
+
"eval_recall": 0.9260011994402612,
|
1006 |
+
"eval_runtime": 49.2957,
|
1007 |
+
"eval_samples_per_second": 608.856,
|
1008 |
+
"eval_steps_per_second": 1.197,
|
1009 |
+
"step": 800
|
1010 |
+
},
|
1011 |
+
{
|
1012 |
+
"epoch": 2.44,
|
1013 |
+
"learning_rate": 4.05e-05,
|
1014 |
+
"loss": 0.2563,
|
1015 |
+
"step": 810
|
1016 |
+
},
|
1017 |
+
{
|
1018 |
+
"epoch": 2.47,
|
1019 |
+
"learning_rate": 4.1e-05,
|
1020 |
+
"loss": 0.2637,
|
1021 |
+
"step": 820
|
1022 |
+
},
|
1023 |
+
{
|
1024 |
+
"epoch": 2.47,
|
1025 |
+
"eval_accuracy": 0.922103018591324,
|
1026 |
+
"eval_combined_score": 0.9220769784769673,
|
1027 |
+
"eval_f1": 0.9212994658547122,
|
1028 |
+
"eval_loss": 0.2446586638689041,
|
1029 |
+
"eval_precision": 0.9228024108705088,
|
1030 |
+
"eval_recall": 0.922103018591324,
|
1031 |
+
"eval_runtime": 48.9946,
|
1032 |
+
"eval_samples_per_second": 612.598,
|
1033 |
+
"eval_steps_per_second": 1.204,
|
1034 |
+
"step": 820
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 2.5,
|
1038 |
+
"learning_rate": 4.1500000000000006e-05,
|
1039 |
+
"loss": 0.2492,
|
1040 |
+
"step": 830
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 2.53,
|
1044 |
+
"learning_rate": 4.2000000000000004e-05,
|
1045 |
+
"loss": 0.2605,
|
1046 |
+
"step": 840
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 2.53,
|
1050 |
+
"eval_accuracy": 0.9237355900579729,
|
1051 |
+
"eval_combined_score": 0.9240135925879284,
|
1052 |
+
"eval_f1": 0.9231767824872119,
|
1053 |
+
"eval_loss": 0.2475174069404602,
|
1054 |
+
"eval_precision": 0.9254064077485559,
|
1055 |
+
"eval_recall": 0.9237355900579729,
|
1056 |
+
"eval_runtime": 49.3973,
|
1057 |
+
"eval_samples_per_second": 607.604,
|
1058 |
+
"eval_steps_per_second": 1.194,
|
1059 |
+
"step": 840
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 2.56,
|
1063 |
+
"learning_rate": 4.25e-05,
|
1064 |
+
"loss": 0.2393,
|
1065 |
+
"step": 850
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 2.59,
|
1069 |
+
"learning_rate": 4.2999999999999995e-05,
|
1070 |
+
"loss": 0.2517,
|
1071 |
+
"step": 860
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 2.59,
|
1075 |
+
"eval_accuracy": 0.9265342840007996,
|
1076 |
+
"eval_combined_score": 0.9265368337935618,
|
1077 |
+
"eval_f1": 0.9258759190762016,
|
1078 |
+
"eval_loss": 0.2590079605579376,
|
1079 |
+
"eval_precision": 0.927202848096446,
|
1080 |
+
"eval_recall": 0.9265342840007996,
|
1081 |
+
"eval_runtime": 48.961,
|
1082 |
+
"eval_samples_per_second": 613.019,
|
1083 |
+
"eval_steps_per_second": 1.205,
|
1084 |
+
"step": 860
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"epoch": 2.62,
|
1088 |
+
"learning_rate": 4.35e-05,
|
1089 |
+
"loss": 0.2515,
|
1090 |
+
"step": 870
|
1091 |
+
},
|
1092 |
+
{
|
1093 |
+
"epoch": 2.65,
|
1094 |
+
"learning_rate": 4.4e-05,
|
1095 |
+
"loss": 0.2453,
|
1096 |
+
"step": 880
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 2.65,
|
1100 |
+
"eval_accuracy": 0.930032651429333,
|
1101 |
+
"eval_combined_score": 0.9305237768064085,
|
1102 |
+
"eval_f1": 0.9305263249699511,
|
1103 |
+
"eval_loss": 0.22479340434074402,
|
1104 |
+
"eval_precision": 0.9315034793970168,
|
1105 |
+
"eval_recall": 0.930032651429333,
|
1106 |
+
"eval_runtime": 49.2223,
|
1107 |
+
"eval_samples_per_second": 609.764,
|
1108 |
+
"eval_steps_per_second": 1.199,
|
1109 |
+
"step": 880
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 2.68,
|
1113 |
+
"learning_rate": 4.45e-05,
|
1114 |
+
"loss": 0.2508,
|
1115 |
+
"step": 890
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 2.71,
|
1119 |
+
"learning_rate": 4.4999999999999996e-05,
|
1120 |
+
"loss": 0.2247,
|
1121 |
+
"step": 900
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 2.71,
|
1125 |
+
"eval_accuracy": 0.9273005930565736,
|
1126 |
+
"eval_combined_score": 0.9281516215920332,
|
1127 |
+
"eval_f1": 0.9280796047956419,
|
1128 |
+
"eval_loss": 0.22854498028755188,
|
1129 |
+
"eval_precision": 0.9299256954593439,
|
1130 |
+
"eval_recall": 0.9273005930565736,
|
1131 |
+
"eval_runtime": 49.2291,
|
1132 |
+
"eval_samples_per_second": 609.68,
|
1133 |
+
"eval_steps_per_second": 1.198,
|
1134 |
+
"step": 900
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 2.74,
|
1138 |
+
"learning_rate": 4.55e-05,
|
1139 |
+
"loss": 0.2322,
|
1140 |
+
"step": 910
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 2.77,
|
1144 |
+
"learning_rate": 4.6e-05,
|
1145 |
+
"loss": 0.2402,
|
1146 |
+
"step": 920
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 2.77,
|
1150 |
+
"eval_accuracy": 0.9306323715599387,
|
1151 |
+
"eval_combined_score": 0.9309955842160982,
|
1152 |
+
"eval_f1": 0.9310096138675644,
|
1153 |
+
"eval_loss": 0.23041337728500366,
|
1154 |
+
"eval_precision": 0.9317079798769508,
|
1155 |
+
"eval_recall": 0.9306323715599387,
|
1156 |
+
"eval_runtime": 49.1984,
|
1157 |
+
"eval_samples_per_second": 610.061,
|
1158 |
+
"eval_steps_per_second": 1.199,
|
1159 |
+
"step": 920
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 2.8,
|
1163 |
+
"learning_rate": 4.65e-05,
|
1164 |
+
"loss": 0.2271,
|
1165 |
+
"step": 930
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 2.83,
|
1169 |
+
"learning_rate": 4.7000000000000004e-05,
|
1170 |
+
"loss": 0.2033,
|
1171 |
+
"step": 940
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 2.83,
|
1175 |
+
"eval_accuracy": 0.9318651296061837,
|
1176 |
+
"eval_combined_score": 0.9319597345286359,
|
1177 |
+
"eval_f1": 0.9316097686956853,
|
1178 |
+
"eval_loss": 0.22282446920871735,
|
1179 |
+
"eval_precision": 0.9324989102064907,
|
1180 |
+
"eval_recall": 0.9318651296061837,
|
1181 |
+
"eval_runtime": 49.2383,
|
1182 |
+
"eval_samples_per_second": 609.566,
|
1183 |
+
"eval_steps_per_second": 1.198,
|
1184 |
+
"step": 940
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 2.86,
|
1188 |
+
"learning_rate": 4.75e-05,
|
1189 |
+
"loss": 0.2296,
|
1190 |
+
"step": 950
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 2.89,
|
1194 |
+
"learning_rate": 4.8e-05,
|
1195 |
+
"loss": 0.2315,
|
1196 |
+
"step": 960
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 2.89,
|
1200 |
+
"eval_accuracy": 0.9270673685613381,
|
1201 |
+
"eval_combined_score": 0.928342902973598,
|
1202 |
+
"eval_f1": 0.9281145494229922,
|
1203 |
+
"eval_loss": 0.22748184204101562,
|
1204 |
+
"eval_precision": 0.9311223253487236,
|
1205 |
+
"eval_recall": 0.9270673685613381,
|
1206 |
+
"eval_runtime": 49.2362,
|
1207 |
+
"eval_samples_per_second": 609.592,
|
1208 |
+
"eval_steps_per_second": 1.198,
|
1209 |
+
"step": 960
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 2.92,
|
1213 |
+
"learning_rate": 4.85e-05,
|
1214 |
+
"loss": 0.2223,
|
1215 |
+
"step": 970
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 2.95,
|
1219 |
+
"learning_rate": 4.9000000000000005e-05,
|
1220 |
+
"loss": 0.2231,
|
1221 |
+
"step": 980
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 2.95,
|
1225 |
+
"eval_accuracy": 0.9342973279136403,
|
1226 |
+
"eval_combined_score": 0.9345308601987949,
|
1227 |
+
"eval_f1": 0.9344884304469883,
|
1228 |
+
"eval_loss": 0.21153467893600464,
|
1229 |
+
"eval_precision": 0.9350403545209113,
|
1230 |
+
"eval_recall": 0.9342973279136403,
|
1231 |
+
"eval_runtime": 49.0355,
|
1232 |
+
"eval_samples_per_second": 612.087,
|
1233 |
+
"eval_steps_per_second": 1.203,
|
1234 |
+
"step": 980
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 2.98,
|
1238 |
+
"learning_rate": 4.9500000000000004e-05,
|
1239 |
+
"loss": 0.2282,
|
1240 |
+
"step": 990
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"epoch": 3.01,
|
1244 |
+
"learning_rate": 5e-05,
|
1245 |
+
"loss": 0.2061,
|
1246 |
+
"step": 1000
|
1247 |
+
},
|
1248 |
+
{
|
1249 |
+
"epoch": 3.01,
|
1250 |
+
"eval_accuracy": 0.9355300859598854,
|
1251 |
+
"eval_combined_score": 0.9356749651327266,
|
1252 |
+
"eval_f1": 0.9355579422022496,
|
1253 |
+
"eval_loss": 0.21559903025627136,
|
1254 |
+
"eval_precision": 0.936081746408886,
|
1255 |
+
"eval_recall": 0.9355300859598854,
|
1256 |
+
"eval_runtime": 49.063,
|
1257 |
+
"eval_samples_per_second": 611.744,
|
1258 |
+
"eval_steps_per_second": 1.203,
|
1259 |
+
"step": 1000
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"epoch": 3.04,
|
1263 |
+
"learning_rate": 5.05e-05,
|
1264 |
+
"loss": 0.2043,
|
1265 |
+
"step": 1010
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 3.07,
|
1269 |
+
"learning_rate": 5.1e-05,
|
1270 |
+
"loss": 0.238,
|
1271 |
+
"step": 1020
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 3.07,
|
1275 |
+
"eval_accuracy": 0.9251682548144199,
|
1276 |
+
"eval_combined_score": 0.9264968648076566,
|
1277 |
+
"eval_f1": 0.9262304286538198,
|
1278 |
+
"eval_loss": 0.23586203157901764,
|
1279 |
+
"eval_precision": 0.9294205209479667,
|
1280 |
+
"eval_recall": 0.9251682548144199,
|
1281 |
+
"eval_runtime": 49.1761,
|
1282 |
+
"eval_samples_per_second": 610.337,
|
1283 |
+
"eval_steps_per_second": 1.2,
|
1284 |
+
"step": 1020
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 3.1,
|
1288 |
+
"learning_rate": 5.15e-05,
|
1289 |
+
"loss": 0.2052,
|
1290 |
+
"step": 1030
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 3.13,
|
1294 |
+
"learning_rate": 5.2e-05,
|
1295 |
+
"loss": 0.1959,
|
1296 |
+
"step": 1040
|
1297 |
+
},
|
1298 |
+
{
|
1299 |
+
"epoch": 3.13,
|
1300 |
+
"eval_accuracy": 0.9342640101286066,
|
1301 |
+
"eval_combined_score": 0.9344882418668942,
|
1302 |
+
"eval_f1": 0.9342944371065101,
|
1303 |
+
"eval_loss": 0.20517703890800476,
|
1304 |
+
"eval_precision": 0.9351305101038535,
|
1305 |
+
"eval_recall": 0.9342640101286066,
|
1306 |
+
"eval_runtime": 49.0279,
|
1307 |
+
"eval_samples_per_second": 612.182,
|
1308 |
+
"eval_steps_per_second": 1.203,
|
1309 |
+
"step": 1040
|
1310 |
+
},
|
1311 |
+
{
|
1312 |
+
"epoch": 3.16,
|
1313 |
+
"learning_rate": 5.25e-05,
|
1314 |
+
"loss": 0.2001,
|
1315 |
+
"step": 1050
|
1316 |
+
},
|
1317 |
+
{
|
1318 |
+
"epoch": 3.19,
|
1319 |
+
"learning_rate": 5.3e-05,
|
1320 |
+
"loss": 0.2013,
|
1321 |
+
"step": 1060
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 3.19,
|
1325 |
+
"eval_accuracy": 0.9337309255680682,
|
1326 |
+
"eval_combined_score": 0.9339696079631046,
|
1327 |
+
"eval_f1": 0.9335629951059575,
|
1328 |
+
"eval_loss": 0.21142832934856415,
|
1329 |
+
"eval_precision": 0.934853585610324,
|
1330 |
+
"eval_recall": 0.9337309255680682,
|
1331 |
+
"eval_runtime": 49.2873,
|
1332 |
+
"eval_samples_per_second": 608.96,
|
1333 |
+
"eval_steps_per_second": 1.197,
|
1334 |
+
"step": 1060
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 3.22,
|
1338 |
+
"learning_rate": 5.35e-05,
|
1339 |
+
"loss": 0.2047,
|
1340 |
+
"step": 1070
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 3.25,
|
1344 |
+
"learning_rate": 5.4e-05,
|
1345 |
+
"loss": 0.2055,
|
1346 |
+
"step": 1080
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 3.25,
|
1350 |
+
"eval_accuracy": 0.9353634970347171,
|
1351 |
+
"eval_combined_score": 0.9355549475589314,
|
1352 |
+
"eval_f1": 0.9353965410744636,
|
1353 |
+
"eval_loss": 0.19850768148899078,
|
1354 |
+
"eval_precision": 0.936096255091828,
|
1355 |
+
"eval_recall": 0.9353634970347171,
|
1356 |
+
"eval_runtime": 49.2971,
|
1357 |
+
"eval_samples_per_second": 608.839,
|
1358 |
+
"eval_steps_per_second": 1.197,
|
1359 |
+
"step": 1080
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 3.28,
|
1363 |
+
"learning_rate": 5.45e-05,
|
1364 |
+
"loss": 0.1785,
|
1365 |
+
"step": 1090
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 3.31,
|
1369 |
+
"learning_rate": 5.5e-05,
|
1370 |
+
"loss": 0.1851,
|
1371 |
+
"step": 1100
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 3.31,
|
1375 |
+
"eval_accuracy": 0.934030785633371,
|
1376 |
+
"eval_combined_score": 0.9342491522296387,
|
1377 |
+
"eval_f1": 0.9337587906840622,
|
1378 |
+
"eval_loss": 0.20976577699184418,
|
1379 |
+
"eval_precision": 0.9351762469677505,
|
1380 |
+
"eval_recall": 0.934030785633371,
|
1381 |
+
"eval_runtime": 49.3513,
|
1382 |
+
"eval_samples_per_second": 608.171,
|
1383 |
+
"eval_steps_per_second": 1.196,
|
1384 |
+
"step": 1100
|
1385 |
+
},
|
1386 |
+
{
|
1387 |
+
"epoch": 3.34,
|
1388 |
+
"learning_rate": 5.55e-05,
|
1389 |
+
"loss": 0.2021,
|
1390 |
+
"step": 1110
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 3.37,
|
1394 |
+
"learning_rate": 5.6e-05,
|
1395 |
+
"loss": 0.2091,
|
1396 |
+
"step": 1120
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 3.37,
|
1400 |
+
"eval_accuracy": 0.9349970013993469,
|
1401 |
+
"eval_combined_score": 0.9350402563461946,
|
1402 |
+
"eval_f1": 0.9346837244814421,
|
1403 |
+
"eval_loss": 0.20015399158000946,
|
1404 |
+
"eval_precision": 0.9354832981046425,
|
1405 |
+
"eval_recall": 0.9349970013993469,
|
1406 |
+
"eval_runtime": 49.0442,
|
1407 |
+
"eval_samples_per_second": 611.979,
|
1408 |
+
"eval_steps_per_second": 1.203,
|
1409 |
+
"step": 1120
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 3.4,
|
1413 |
+
"learning_rate": 5.6500000000000005e-05,
|
1414 |
+
"loss": 0.1921,
|
1415 |
+
"step": 1130
|
1416 |
+
},
|
1417 |
+
{
|
1418 |
+
"epoch": 3.43,
|
1419 |
+
"learning_rate": 5.7e-05,
|
1420 |
+
"loss": 0.1933,
|
1421 |
+
"step": 1140
|
1422 |
+
},
|
1423 |
+
{
|
1424 |
+
"epoch": 3.43,
|
1425 |
+
"eval_accuracy": 0.9367295262210968,
|
1426 |
+
"eval_combined_score": 0.9370493307806007,
|
1427 |
+
"eval_f1": 0.9370521574768956,
|
1428 |
+
"eval_loss": 0.2045455276966095,
|
1429 |
+
"eval_precision": 0.9376861132033139,
|
1430 |
+
"eval_recall": 0.9367295262210968,
|
1431 |
+
"eval_runtime": 49.275,
|
1432 |
+
"eval_samples_per_second": 609.112,
|
1433 |
+
"eval_steps_per_second": 1.197,
|
1434 |
+
"step": 1140
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 3.46,
|
1438 |
+
"learning_rate": 5.75e-05,
|
1439 |
+
"loss": 0.1872,
|
1440 |
+
"step": 1150
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 3.49,
|
1444 |
+
"learning_rate": 5.800000000000001e-05,
|
1445 |
+
"loss": 0.2011,
|
1446 |
+
"step": 1160
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"epoch": 3.49,
|
1450 |
+
"eval_accuracy": 0.9349636836143134,
|
1451 |
+
"eval_combined_score": 0.9349395692420557,
|
1452 |
+
"eval_f1": 0.9344939564813404,
|
1453 |
+
"eval_loss": 0.20722946524620056,
|
1454 |
+
"eval_precision": 0.9353369532582558,
|
1455 |
+
"eval_recall": 0.9349636836143134,
|
1456 |
+
"eval_runtime": 49.14,
|
1457 |
+
"eval_samples_per_second": 610.786,
|
1458 |
+
"eval_steps_per_second": 1.201,
|
1459 |
+
"step": 1160
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 3.52,
|
1463 |
+
"learning_rate": 5.8500000000000006e-05,
|
1464 |
+
"loss": 0.1807,
|
1465 |
+
"step": 1170
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 3.55,
|
1469 |
+
"learning_rate": 5.9e-05,
|
1470 |
+
"loss": 0.2085,
|
1471 |
+
"step": 1180
|
1472 |
+
},
|
1473 |
+
{
|
1474 |
+
"epoch": 3.55,
|
1475 |
+
"eval_accuracy": 0.9327313920170587,
|
1476 |
+
"eval_combined_score": 0.933838750818189,
|
1477 |
+
"eval_f1": 0.933658760865571,
|
1478 |
+
"eval_loss": 0.2123931348323822,
|
1479 |
+
"eval_precision": 0.9362334583730675,
|
1480 |
+
"eval_recall": 0.9327313920170587,
|
1481 |
+
"eval_runtime": 49.1943,
|
1482 |
+
"eval_samples_per_second": 610.111,
|
1483 |
+
"eval_steps_per_second": 1.199,
|
1484 |
+
"step": 1180
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"epoch": 3.58,
|
1488 |
+
"learning_rate": 5.9499999999999996e-05,
|
1489 |
+
"loss": 0.1888,
|
1490 |
+
"step": 1190
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 3.61,
|
1494 |
+
"learning_rate": 6e-05,
|
1495 |
+
"loss": 0.1991,
|
1496 |
+
"step": 1200
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 3.61,
|
1500 |
+
"eval_accuracy": 0.9395615379489571,
|
1501 |
+
"eval_combined_score": 0.9398781089093659,
|
1502 |
+
"eval_f1": 0.9398246745836987,
|
1503 |
+
"eval_loss": 0.187956303358078,
|
1504 |
+
"eval_precision": 0.9405646851558505,
|
1505 |
+
"eval_recall": 0.9395615379489571,
|
1506 |
+
"eval_runtime": 49.0546,
|
1507 |
+
"eval_samples_per_second": 611.849,
|
1508 |
+
"eval_steps_per_second": 1.203,
|
1509 |
+
"step": 1200
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 3.64,
|
1513 |
+
"learning_rate": 6.05e-05,
|
1514 |
+
"loss": 0.184,
|
1515 |
+
"step": 1210
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 3.67,
|
1519 |
+
"learning_rate": 6.1e-05,
|
1520 |
+
"loss": 0.1972,
|
1521 |
+
"step": 1220
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 3.67,
|
1525 |
+
"eval_accuracy": 0.9347304591190778,
|
1526 |
+
"eval_combined_score": 0.9347275548603768,
|
1527 |
+
"eval_f1": 0.9343894894257468,
|
1528 |
+
"eval_loss": 0.2123294323682785,
|
1529 |
+
"eval_precision": 0.9350598117776048,
|
1530 |
+
"eval_recall": 0.9347304591190778,
|
1531 |
+
"eval_runtime": 49.1469,
|
1532 |
+
"eval_samples_per_second": 610.7,
|
1533 |
+
"eval_steps_per_second": 1.2,
|
1534 |
+
"step": 1220
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"epoch": 3.7,
|
1538 |
+
"learning_rate": 6.15e-05,
|
1539 |
+
"loss": 0.2081,
|
1540 |
+
"step": 1230
|
1541 |
+
},
|
1542 |
+
{
|
1543 |
+
"epoch": 3.73,
|
1544 |
+
"learning_rate": 6.2e-05,
|
1545 |
+
"loss": 0.1905,
|
1546 |
+
"step": 1240
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 3.73,
|
1550 |
+
"eval_accuracy": 0.9350636369694143,
|
1551 |
+
"eval_combined_score": 0.9355463954135541,
|
1552 |
+
"eval_f1": 0.9352086535253742,
|
1553 |
+
"eval_loss": 0.20560528337955475,
|
1554 |
+
"eval_precision": 0.936849654190014,
|
1555 |
+
"eval_recall": 0.9350636369694143,
|
1556 |
+
"eval_runtime": 48.922,
|
1557 |
+
"eval_samples_per_second": 613.507,
|
1558 |
+
"eval_steps_per_second": 1.206,
|
1559 |
+
"step": 1240
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 3.76,
|
1563 |
+
"learning_rate": 6.25e-05,
|
1564 |
+
"loss": 0.1887,
|
1565 |
+
"step": 1250
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"epoch": 3.79,
|
1569 |
+
"learning_rate": 6.3e-05,
|
1570 |
+
"loss": 0.1974,
|
1571 |
+
"step": 1260
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 3.79,
|
1575 |
+
"eval_accuracy": 0.9284667155327514,
|
1576 |
+
"eval_combined_score": 0.9289254664345794,
|
1577 |
+
"eval_f1": 0.9279749557741453,
|
1578 |
+
"eval_loss": 0.24318872392177582,
|
1579 |
+
"eval_precision": 0.9307934788986695,
|
1580 |
+
"eval_recall": 0.9284667155327514,
|
1581 |
+
"eval_runtime": 48.8771,
|
1582 |
+
"eval_samples_per_second": 614.07,
|
1583 |
+
"eval_steps_per_second": 1.207,
|
1584 |
+
"step": 1260
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 3.82,
|
1588 |
+
"learning_rate": 6.35e-05,
|
1589 |
+
"loss": 0.2053,
|
1590 |
+
"step": 1270
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"epoch": 3.85,
|
1594 |
+
"learning_rate": 6.4e-05,
|
1595 |
+
"loss": 0.1831,
|
1596 |
+
"step": 1280
|
1597 |
+
},
|
1598 |
+
{
|
1599 |
+
"epoch": 3.85,
|
1600 |
+
"eval_accuracy": 0.9392283600986207,
|
1601 |
+
"eval_combined_score": 0.9394177419543435,
|
1602 |
+
"eval_f1": 0.9390156020685934,
|
1603 |
+
"eval_loss": 0.18808111548423767,
|
1604 |
+
"eval_precision": 0.9401986455515388,
|
1605 |
+
"eval_recall": 0.9392283600986207,
|
1606 |
+
"eval_runtime": 48.9948,
|
1607 |
+
"eval_samples_per_second": 612.596,
|
1608 |
+
"eval_steps_per_second": 1.204,
|
1609 |
+
"step": 1280
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 3.88,
|
1613 |
+
"learning_rate": 6.450000000000001e-05,
|
1614 |
+
"loss": 0.1957,
|
1615 |
+
"step": 1290
|
1616 |
+
},
|
1617 |
+
{
|
1618 |
+
"epoch": 3.91,
|
1619 |
+
"learning_rate": 6.500000000000001e-05,
|
1620 |
+
"loss": 0.1883,
|
1621 |
+
"step": 1300
|
1622 |
+
},
|
1623 |
+
{
|
1624 |
+
"epoch": 3.91,
|
1625 |
+
"eval_accuracy": 0.941294062770707,
|
1626 |
+
"eval_combined_score": 0.941598262073596,
|
1627 |
+
"eval_f1": 0.9414926633381392,
|
1628 |
+
"eval_loss": 0.19479438662528992,
|
1629 |
+
"eval_precision": 0.9423122594148309,
|
1630 |
+
"eval_recall": 0.941294062770707,
|
1631 |
+
"eval_runtime": 48.9175,
|
1632 |
+
"eval_samples_per_second": 613.564,
|
1633 |
+
"eval_steps_per_second": 1.206,
|
1634 |
+
"step": 1300
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 3.94,
|
1638 |
+
"learning_rate": 6.55e-05,
|
1639 |
+
"loss": 0.1965,
|
1640 |
+
"step": 1310
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 3.97,
|
1644 |
+
"learning_rate": 6.6e-05,
|
1645 |
+
"loss": 0.2023,
|
1646 |
+
"step": 1320
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"epoch": 3.97,
|
1650 |
+
"eval_accuracy": 0.9335310188578664,
|
1651 |
+
"eval_combined_score": 0.9345550947345727,
|
1652 |
+
"eval_f1": 0.9343029810913681,
|
1653 |
+
"eval_loss": 0.20408588647842407,
|
1654 |
+
"eval_precision": 0.9368553601311899,
|
1655 |
+
"eval_recall": 0.9335310188578664,
|
1656 |
+
"eval_runtime": 49.2214,
|
1657 |
+
"eval_samples_per_second": 609.775,
|
1658 |
+
"eval_steps_per_second": 1.199,
|
1659 |
+
"step": 1320
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 4.0,
|
1663 |
+
"learning_rate": 6.65e-05,
|
1664 |
+
"loss": 0.1907,
|
1665 |
+
"step": 1330
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 4.03,
|
1669 |
+
"learning_rate": 6.7e-05,
|
1670 |
+
"loss": 0.1694,
|
1671 |
+
"step": 1340
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 4.03,
|
1675 |
+
"eval_accuracy": 0.9360298527353902,
|
1676 |
+
"eval_combined_score": 0.9363142224274822,
|
1677 |
+
"eval_f1": 0.9359863994713908,
|
1678 |
+
"eval_loss": 0.20074895024299622,
|
1679 |
+
"eval_precision": 0.9372107847677573,
|
1680 |
+
"eval_recall": 0.9360298527353902,
|
1681 |
+
"eval_runtime": 49.0756,
|
1682 |
+
"eval_samples_per_second": 611.587,
|
1683 |
+
"eval_steps_per_second": 1.202,
|
1684 |
+
"step": 1340
|
1685 |
+
},
|
1686 |
+
{
|
1687 |
+
"epoch": 4.06,
|
1688 |
+
"learning_rate": 6.75e-05,
|
1689 |
+
"loss": 0.1678,
|
1690 |
+
"step": 1350
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 4.09,
|
1694 |
+
"learning_rate": 6.800000000000001e-05,
|
1695 |
+
"loss": 0.1727,
|
1696 |
+
"step": 1360
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 4.09,
|
1700 |
+
"eval_accuracy": 0.9410941560605051,
|
1701 |
+
"eval_combined_score": 0.9414479845953316,
|
1702 |
+
"eval_f1": 0.9413537047900903,
|
1703 |
+
"eval_loss": 0.19899074733257294,
|
1704 |
+
"eval_precision": 0.9422499214702263,
|
1705 |
+
"eval_recall": 0.9410941560605051,
|
1706 |
+
"eval_runtime": 48.939,
|
1707 |
+
"eval_samples_per_second": 613.294,
|
1708 |
+
"eval_steps_per_second": 1.206,
|
1709 |
+
"step": 1360
|
1710 |
+
},
|
1711 |
+
{
|
1712 |
+
"epoch": 4.12,
|
1713 |
+
"learning_rate": 6.850000000000001e-05,
|
1714 |
+
"loss": 0.1671,
|
1715 |
+
"step": 1370
|
1716 |
+
},
|
1717 |
+
{
|
1718 |
+
"epoch": 4.15,
|
1719 |
+
"learning_rate": 6.900000000000001e-05,
|
1720 |
+
"loss": 0.1666,
|
1721 |
+
"step": 1380
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 4.15,
|
1725 |
+
"eval_accuracy": 0.9396948090890918,
|
1726 |
+
"eval_combined_score": 0.9399064543181681,
|
1727 |
+
"eval_f1": 0.9399187035532075,
|
1728 |
+
"eval_loss": 0.1951565146446228,
|
1729 |
+
"eval_precision": 0.9403174955412814,
|
1730 |
+
"eval_recall": 0.9396948090890918,
|
1731 |
+
"eval_runtime": 49.1438,
|
1732 |
+
"eval_samples_per_second": 610.738,
|
1733 |
+
"eval_steps_per_second": 1.201,
|
1734 |
+
"step": 1380
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 4.18,
|
1738 |
+
"learning_rate": 6.950000000000001e-05,
|
1739 |
+
"loss": 0.1534,
|
1740 |
+
"step": 1390
|
1741 |
+
},
|
1742 |
+
{
|
1743 |
+
"epoch": 4.21,
|
1744 |
+
"learning_rate": 7.000000000000001e-05,
|
1745 |
+
"loss": 0.2011,
|
1746 |
+
"step": 1400
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 4.21,
|
1750 |
+
"eval_accuracy": 0.9384287332578131,
|
1751 |
+
"eval_combined_score": 0.9389423434978216,
|
1752 |
+
"eval_f1": 0.9388320598028991,
|
1753 |
+
"eval_loss": 0.19526319205760956,
|
1754 |
+
"eval_precision": 0.9400798476727612,
|
1755 |
+
"eval_recall": 0.9384287332578131,
|
1756 |
+
"eval_runtime": 48.9255,
|
1757 |
+
"eval_samples_per_second": 613.463,
|
1758 |
+
"eval_steps_per_second": 1.206,
|
1759 |
+
"step": 1400
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 4.24,
|
1763 |
+
"learning_rate": 7.049999999999999e-05,
|
1764 |
+
"loss": 0.1604,
|
1765 |
+
"step": 1410
|
1766 |
+
},
|
1767 |
+
{
|
1768 |
+
"epoch": 4.27,
|
1769 |
+
"learning_rate": 7.099999999999999e-05,
|
1770 |
+
"loss": 0.1798,
|
1771 |
+
"step": 1420
|
1772 |
+
},
|
1773 |
+
{
|
1774 |
+
"epoch": 4.27,
|
1775 |
+
"eval_accuracy": 0.9324981675218231,
|
1776 |
+
"eval_combined_score": 0.9328057540278043,
|
1777 |
+
"eval_f1": 0.9317552726797775,
|
1778 |
+
"eval_loss": 0.2032395899295807,
|
1779 |
+
"eval_precision": 0.9344714083877934,
|
1780 |
+
"eval_recall": 0.9324981675218231,
|
1781 |
+
"eval_runtime": 48.9309,
|
1782 |
+
"eval_samples_per_second": 613.396,
|
1783 |
+
"eval_steps_per_second": 1.206,
|
1784 |
+
"step": 1420
|
1785 |
+
},
|
1786 |
+
{
|
1787 |
+
"epoch": 4.3,
|
1788 |
+
"learning_rate": 7.149999999999999e-05,
|
1789 |
+
"loss": 0.1574,
|
1790 |
+
"step": 1430
|
1791 |
+
},
|
1792 |
+
{
|
1793 |
+
"epoch": 4.33,
|
1794 |
+
"learning_rate": 7.2e-05,
|
1795 |
+
"loss": 0.1808,
|
1796 |
+
"step": 1440
|
1797 |
+
},
|
1798 |
+
{
|
1799 |
+
"epoch": 4.33,
|
1800 |
+
"eval_accuracy": 0.9307656427000733,
|
1801 |
+
"eval_combined_score": 0.9322843963954361,
|
1802 |
+
"eval_f1": 0.9319394065463472,
|
1803 |
+
"eval_loss": 0.20845866203308105,
|
1804 |
+
"eval_precision": 0.9356668936352504,
|
1805 |
+
"eval_recall": 0.9307656427000733,
|
1806 |
+
"eval_runtime": 48.972,
|
1807 |
+
"eval_samples_per_second": 612.88,
|
1808 |
+
"eval_steps_per_second": 1.205,
|
1809 |
+
"step": 1440
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 4.36,
|
1813 |
+
"learning_rate": 7.25e-05,
|
1814 |
+
"loss": 0.1781,
|
1815 |
+
"step": 1450
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 4.39,
|
1819 |
+
"learning_rate": 7.3e-05,
|
1820 |
+
"loss": 0.1552,
|
1821 |
+
"step": 1460
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 4.39,
|
1825 |
+
"eval_accuracy": 0.937096021856467,
|
1826 |
+
"eval_combined_score": 0.9377356315073376,
|
1827 |
+
"eval_f1": 0.9376720069592002,
|
1828 |
+
"eval_loss": 0.2010466307401657,
|
1829 |
+
"eval_precision": 0.9390784753572167,
|
1830 |
+
"eval_recall": 0.937096021856467,
|
1831 |
+
"eval_runtime": 49.0946,
|
1832 |
+
"eval_samples_per_second": 611.35,
|
1833 |
+
"eval_steps_per_second": 1.202,
|
1834 |
+
"step": 1460
|
1835 |
+
},
|
1836 |
+
{
|
1837 |
+
"epoch": 4.42,
|
1838 |
+
"learning_rate": 7.35e-05,
|
1839 |
+
"loss": 0.1686,
|
1840 |
+
"step": 1470
|
1841 |
+
},
|
1842 |
+
{
|
1843 |
+
"epoch": 4.45,
|
1844 |
+
"learning_rate": 7.4e-05,
|
1845 |
+
"loss": 0.1608,
|
1846 |
+
"step": 1480
|
1847 |
+
},
|
1848 |
+
{
|
1849 |
+
"epoch": 4.45,
|
1850 |
+
"eval_accuracy": 0.9341973745585394,
|
1851 |
+
"eval_combined_score": 0.9351371759134793,
|
1852 |
+
"eval_f1": 0.9349095822764671,
|
1853 |
+
"eval_loss": 0.2090441733598709,
|
1854 |
+
"eval_precision": 0.9372443722603717,
|
1855 |
+
"eval_recall": 0.9341973745585394,
|
1856 |
+
"eval_runtime": 49.1134,
|
1857 |
+
"eval_samples_per_second": 611.116,
|
1858 |
+
"eval_steps_per_second": 1.201,
|
1859 |
+
"step": 1480
|
1860 |
+
},
|
1861 |
+
{
|
1862 |
+
"epoch": 4.48,
|
1863 |
+
"learning_rate": 7.45e-05,
|
1864 |
+
"loss": 0.1745,
|
1865 |
+
"step": 1490
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 4.51,
|
1869 |
+
"learning_rate": 7.5e-05,
|
1870 |
+
"loss": 0.1683,
|
1871 |
+
"step": 1500
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 4.51,
|
1875 |
+
"eval_accuracy": 0.9373625641367362,
|
1876 |
+
"eval_combined_score": 0.9375629630953092,
|
1877 |
+
"eval_f1": 0.9370996834102538,
|
1878 |
+
"eval_loss": 0.20049959421157837,
|
1879 |
+
"eval_precision": 0.9384270406975105,
|
1880 |
+
"eval_recall": 0.9373625641367362,
|
1881 |
+
"eval_runtime": 49.1089,
|
1882 |
+
"eval_samples_per_second": 611.173,
|
1883 |
+
"eval_steps_per_second": 1.201,
|
1884 |
+
"step": 1500
|
1885 |
+
}
|
1886 |
+
],
|
1887 |
+
"logging_steps": 10,
|
1888 |
+
"max_steps": 1660,
|
1889 |
+
"num_train_epochs": 5,
|
1890 |
+
"save_steps": 100,
|
1891 |
+
"total_flos": 2.020626851857367e+17,
|
1892 |
+
"trial_name": null,
|
1893 |
+
"trial_params": null
|
1894 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae98e7de1b05a570517ae68653e3c31b639a52c739d05197601f467f38b01c66
|
3 |
+
size 4536
|
checkpoint-1500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|