Commit
·
15491e8
1
Parent(s):
0015138
Update from stanley
Browse files- config.json +36 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +1114 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "nielsr/coref-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": 0,
|
15 |
+
"1": 1
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"0": 0,
|
21 |
+
"1": 1
|
22 |
+
},
|
23 |
+
"layer_norm_eps": 1e-05,
|
24 |
+
"max_position_embeddings": 514,
|
25 |
+
"model_type": "roberta",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"output_past": true,
|
29 |
+
"pad_token_id": 1,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"problem_type": "single_label_classification",
|
32 |
+
"transformers_version": "4.7.0.dev0",
|
33 |
+
"type_vocab_size": 1,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 50265
|
36 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a654a221f3b62be51e7b468344336537979302360e53c8e9ec0cf5bd28cc29a4
|
3 |
+
size 997303505
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:445529a951dbec64729dadd80fcfad070579dedf14479eb9f59a0f200f8e22e8
|
3 |
+
size 498679241
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1180a76d2307c6fdb800471b14ba48cb7abd872146b8c3acf9b34005726e6231
|
3 |
+
size 14657
|
scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae86555af3ef2e545517454227fecdf997aae899fd7c048929f5ce3247cdf96a
|
3 |
+
size 559
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6763926a6e66250b48c8fb864dfaa1ed615df088edfe78edf0f4a6c9d4bef23
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": null, "name_or_path": "nielsr/coref-roberta-base"}
|
trainer_state.json
ADDED
@@ -0,0 +1,1114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.2722427248954773,
|
3 |
+
"best_model_checkpoint": "./ckpt/roberta/checkpoint-4000",
|
4 |
+
"epoch": 4.999781452611641,
|
5 |
+
"global_step": 17155,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"learning_rate": 4.971728359078986e-05,
|
13 |
+
"loss": 0.5548,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.06,
|
18 |
+
"learning_rate": 4.94258233751093e-05,
|
19 |
+
"loss": 0.324,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.09,
|
24 |
+
"learning_rate": 4.9134363159428745e-05,
|
25 |
+
"loss": 0.2765,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.12,
|
30 |
+
"learning_rate": 4.8842902943748184e-05,
|
31 |
+
"loss": 0.2655,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.15,
|
36 |
+
"learning_rate": 4.855144272806762e-05,
|
37 |
+
"loss": 0.26,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.17,
|
42 |
+
"learning_rate": 4.825998251238706e-05,
|
43 |
+
"loss": 0.2628,
|
44 |
+
"step": 600
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2,
|
48 |
+
"learning_rate": 4.79685222967065e-05,
|
49 |
+
"loss": 0.2509,
|
50 |
+
"step": 700
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.23,
|
54 |
+
"learning_rate": 4.767706208102594e-05,
|
55 |
+
"loss": 0.2694,
|
56 |
+
"step": 800
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.26,
|
60 |
+
"learning_rate": 4.738851646750219e-05,
|
61 |
+
"loss": 0.284,
|
62 |
+
"step": 900
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.29,
|
66 |
+
"learning_rate": 4.709705625182163e-05,
|
67 |
+
"loss": 0.2776,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.32,
|
72 |
+
"learning_rate": 4.6805596036141067e-05,
|
73 |
+
"loss": 0.253,
|
74 |
+
"step": 1100
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.35,
|
78 |
+
"learning_rate": 4.6514135820460505e-05,
|
79 |
+
"loss": 0.2577,
|
80 |
+
"step": 1200
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.38,
|
84 |
+
"learning_rate": 4.622267560477995e-05,
|
85 |
+
"loss": 0.2303,
|
86 |
+
"step": 1300
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.41,
|
90 |
+
"learning_rate": 4.593121538909939e-05,
|
91 |
+
"loss": 0.2214,
|
92 |
+
"step": 1400
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.44,
|
96 |
+
"learning_rate": 4.563975517341883e-05,
|
97 |
+
"loss": 0.2257,
|
98 |
+
"step": 1500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.47,
|
102 |
+
"learning_rate": 4.534829495773827e-05,
|
103 |
+
"loss": 0.2346,
|
104 |
+
"step": 1600
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.5,
|
108 |
+
"learning_rate": 4.505683474205771e-05,
|
109 |
+
"loss": 0.235,
|
110 |
+
"step": 1700
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.52,
|
114 |
+
"learning_rate": 4.476537452637715e-05,
|
115 |
+
"loss": 0.213,
|
116 |
+
"step": 1800
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.55,
|
120 |
+
"learning_rate": 4.447391431069659e-05,
|
121 |
+
"loss": 0.2286,
|
122 |
+
"step": 1900
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.58,
|
126 |
+
"learning_rate": 4.4182454095016036e-05,
|
127 |
+
"loss": 0.2234,
|
128 |
+
"step": 2000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.58,
|
132 |
+
"eval_accuracy": 0.9075907468795776,
|
133 |
+
"eval_loss": 0.29963451623916626,
|
134 |
+
"eval_runtime": 35.4657,
|
135 |
+
"eval_samples_per_second": 375.913,
|
136 |
+
"eval_steps_per_second": 47.003,
|
137 |
+
"step": 2000
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.61,
|
141 |
+
"learning_rate": 4.3890993879335475e-05,
|
142 |
+
"loss": 0.2158,
|
143 |
+
"step": 2100
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.64,
|
147 |
+
"learning_rate": 4.3599533663654914e-05,
|
148 |
+
"loss": 0.1989,
|
149 |
+
"step": 2200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.67,
|
153 |
+
"learning_rate": 4.330807344797435e-05,
|
154 |
+
"loss": 0.2229,
|
155 |
+
"step": 2300
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.7,
|
159 |
+
"learning_rate": 4.30166132322938e-05,
|
160 |
+
"loss": 0.2195,
|
161 |
+
"step": 2400
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.73,
|
165 |
+
"learning_rate": 4.272515301661324e-05,
|
166 |
+
"loss": 0.2054,
|
167 |
+
"step": 2500
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.76,
|
171 |
+
"learning_rate": 4.2433692800932676e-05,
|
172 |
+
"loss": 0.2046,
|
173 |
+
"step": 2600
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.79,
|
177 |
+
"learning_rate": 4.2142232585252115e-05,
|
178 |
+
"loss": 0.2019,
|
179 |
+
"step": 2700
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.82,
|
183 |
+
"learning_rate": 4.185077236957155e-05,
|
184 |
+
"loss": 0.2014,
|
185 |
+
"step": 2800
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.85,
|
189 |
+
"learning_rate": 4.155931215389099e-05,
|
190 |
+
"loss": 0.2043,
|
191 |
+
"step": 2900
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.87,
|
195 |
+
"learning_rate": 4.126785193821044e-05,
|
196 |
+
"loss": 0.1872,
|
197 |
+
"step": 3000
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 0.9,
|
201 |
+
"learning_rate": 4.0976391722529877e-05,
|
202 |
+
"loss": 0.1975,
|
203 |
+
"step": 3100
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.93,
|
207 |
+
"learning_rate": 4.0684931506849315e-05,
|
208 |
+
"loss": 0.1949,
|
209 |
+
"step": 3200
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.96,
|
213 |
+
"learning_rate": 4.0393471291168754e-05,
|
214 |
+
"loss": 0.2153,
|
215 |
+
"step": 3300
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.99,
|
219 |
+
"learning_rate": 4.01020110754882e-05,
|
220 |
+
"loss": 0.2092,
|
221 |
+
"step": 3400
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.02,
|
225 |
+
"learning_rate": 3.981055085980764e-05,
|
226 |
+
"loss": 0.2024,
|
227 |
+
"step": 3500
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.05,
|
231 |
+
"learning_rate": 3.952200524628388e-05,
|
232 |
+
"loss": 0.1814,
|
233 |
+
"step": 3600
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.08,
|
237 |
+
"learning_rate": 3.923054503060332e-05,
|
238 |
+
"loss": 0.1695,
|
239 |
+
"step": 3700
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.11,
|
243 |
+
"learning_rate": 3.8939084814922766e-05,
|
244 |
+
"loss": 0.1808,
|
245 |
+
"step": 3800
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 1.14,
|
249 |
+
"learning_rate": 3.8647624599242205e-05,
|
250 |
+
"loss": 0.161,
|
251 |
+
"step": 3900
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.17,
|
255 |
+
"learning_rate": 3.8356164383561644e-05,
|
256 |
+
"loss": 0.1851,
|
257 |
+
"step": 4000
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 1.17,
|
261 |
+
"eval_accuracy": 0.9154665470123291,
|
262 |
+
"eval_loss": 0.2722427248954773,
|
263 |
+
"eval_runtime": 35.4783,
|
264 |
+
"eval_samples_per_second": 375.779,
|
265 |
+
"eval_steps_per_second": 46.986,
|
266 |
+
"step": 4000
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.19,
|
270 |
+
"learning_rate": 3.806470416788109e-05,
|
271 |
+
"loss": 0.1787,
|
272 |
+
"step": 4100
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.22,
|
276 |
+
"learning_rate": 3.777324395220053e-05,
|
277 |
+
"loss": 0.1572,
|
278 |
+
"step": 4200
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.25,
|
282 |
+
"learning_rate": 3.748178373651997e-05,
|
283 |
+
"loss": 0.1825,
|
284 |
+
"step": 4300
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.28,
|
288 |
+
"learning_rate": 3.719032352083941e-05,
|
289 |
+
"loss": 0.1839,
|
290 |
+
"step": 4400
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.31,
|
294 |
+
"learning_rate": 3.689886330515885e-05,
|
295 |
+
"loss": 0.1584,
|
296 |
+
"step": 4500
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.34,
|
300 |
+
"learning_rate": 3.660740308947829e-05,
|
301 |
+
"loss": 0.1719,
|
302 |
+
"step": 4600
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.37,
|
306 |
+
"learning_rate": 3.631594287379773e-05,
|
307 |
+
"loss": 0.1792,
|
308 |
+
"step": 4700
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.4,
|
312 |
+
"learning_rate": 3.602448265811717e-05,
|
313 |
+
"loss": 0.1695,
|
314 |
+
"step": 4800
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.43,
|
318 |
+
"learning_rate": 3.5733022442436606e-05,
|
319 |
+
"loss": 0.1661,
|
320 |
+
"step": 4900
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.46,
|
324 |
+
"learning_rate": 3.5441562226756045e-05,
|
325 |
+
"loss": 0.1797,
|
326 |
+
"step": 5000
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.49,
|
330 |
+
"learning_rate": 3.515010201107549e-05,
|
331 |
+
"loss": 0.1666,
|
332 |
+
"step": 5100
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.52,
|
336 |
+
"learning_rate": 3.485864179539493e-05,
|
337 |
+
"loss": 0.1768,
|
338 |
+
"step": 5200
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.54,
|
342 |
+
"learning_rate": 3.456718157971437e-05,
|
343 |
+
"loss": 0.1662,
|
344 |
+
"step": 5300
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.57,
|
348 |
+
"learning_rate": 3.4275721364033814e-05,
|
349 |
+
"loss": 0.177,
|
350 |
+
"step": 5400
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.6,
|
354 |
+
"learning_rate": 3.398426114835325e-05,
|
355 |
+
"loss": 0.1734,
|
356 |
+
"step": 5500
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.63,
|
360 |
+
"learning_rate": 3.369280093267269e-05,
|
361 |
+
"loss": 0.1749,
|
362 |
+
"step": 5600
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.66,
|
366 |
+
"learning_rate": 3.340134071699213e-05,
|
367 |
+
"loss": 0.1767,
|
368 |
+
"step": 5700
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.69,
|
372 |
+
"learning_rate": 3.3109880501311576e-05,
|
373 |
+
"loss": 0.1541,
|
374 |
+
"step": 5800
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.72,
|
378 |
+
"learning_rate": 3.2818420285631015e-05,
|
379 |
+
"loss": 0.1706,
|
380 |
+
"step": 5900
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.75,
|
384 |
+
"learning_rate": 3.2526960069950453e-05,
|
385 |
+
"loss": 0.1757,
|
386 |
+
"step": 6000
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 1.75,
|
390 |
+
"eval_accuracy": 0.9202670454978943,
|
391 |
+
"eval_loss": 0.28923019766807556,
|
392 |
+
"eval_runtime": 35.505,
|
393 |
+
"eval_samples_per_second": 375.497,
|
394 |
+
"eval_steps_per_second": 46.951,
|
395 |
+
"step": 6000
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.78,
|
399 |
+
"learning_rate": 3.22354998542699e-05,
|
400 |
+
"loss": 0.1796,
|
401 |
+
"step": 6100
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.81,
|
405 |
+
"learning_rate": 3.194403963858934e-05,
|
406 |
+
"loss": 0.187,
|
407 |
+
"step": 6200
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 1.84,
|
411 |
+
"learning_rate": 3.165257942290878e-05,
|
412 |
+
"loss": 0.1651,
|
413 |
+
"step": 6300
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 1.87,
|
417 |
+
"learning_rate": 3.136403380938502e-05,
|
418 |
+
"loss": 0.1675,
|
419 |
+
"step": 6400
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.89,
|
423 |
+
"learning_rate": 3.1072573593704465e-05,
|
424 |
+
"loss": 0.1532,
|
425 |
+
"step": 6500
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 1.92,
|
429 |
+
"learning_rate": 3.0781113378023904e-05,
|
430 |
+
"loss": 0.1652,
|
431 |
+
"step": 6600
|
432 |
+
},
|
433 |
+
{
|
434 |
+
"epoch": 1.95,
|
435 |
+
"learning_rate": 3.048965316234334e-05,
|
436 |
+
"loss": 0.1657,
|
437 |
+
"step": 6700
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.98,
|
441 |
+
"learning_rate": 3.0198192946662785e-05,
|
442 |
+
"loss": 0.1477,
|
443 |
+
"step": 6800
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.01,
|
447 |
+
"learning_rate": 2.9906732730982224e-05,
|
448 |
+
"loss": 0.1589,
|
449 |
+
"step": 6900
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 2.04,
|
453 |
+
"learning_rate": 2.9615272515301663e-05,
|
454 |
+
"loss": 0.1383,
|
455 |
+
"step": 7000
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 2.07,
|
459 |
+
"learning_rate": 2.93238122996211e-05,
|
460 |
+
"loss": 0.1553,
|
461 |
+
"step": 7100
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 2.1,
|
465 |
+
"learning_rate": 2.9032352083940544e-05,
|
466 |
+
"loss": 0.1275,
|
467 |
+
"step": 7200
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 2.13,
|
471 |
+
"learning_rate": 2.8740891868259982e-05,
|
472 |
+
"loss": 0.1447,
|
473 |
+
"step": 7300
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 2.16,
|
477 |
+
"learning_rate": 2.844943165257942e-05,
|
478 |
+
"loss": 0.1399,
|
479 |
+
"step": 7400
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 2.19,
|
483 |
+
"learning_rate": 2.8157971436898867e-05,
|
484 |
+
"loss": 0.1383,
|
485 |
+
"step": 7500
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 2.22,
|
489 |
+
"learning_rate": 2.7866511221218306e-05,
|
490 |
+
"loss": 0.1453,
|
491 |
+
"step": 7600
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 2.24,
|
495 |
+
"learning_rate": 2.7575051005537744e-05,
|
496 |
+
"loss": 0.139,
|
497 |
+
"step": 7700
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 2.27,
|
501 |
+
"learning_rate": 2.728359078985719e-05,
|
502 |
+
"loss": 0.1262,
|
503 |
+
"step": 7800
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 2.3,
|
507 |
+
"learning_rate": 2.699213057417663e-05,
|
508 |
+
"loss": 0.1298,
|
509 |
+
"step": 7900
|
510 |
+
},
|
511 |
+
{
|
512 |
+
"epoch": 2.33,
|
513 |
+
"learning_rate": 2.6700670358496068e-05,
|
514 |
+
"loss": 0.1274,
|
515 |
+
"step": 8000
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 2.33,
|
519 |
+
"eval_accuracy": 0.9189168810844421,
|
520 |
+
"eval_loss": 0.35566407442092896,
|
521 |
+
"eval_runtime": 35.4775,
|
522 |
+
"eval_samples_per_second": 375.788,
|
523 |
+
"eval_steps_per_second": 46.988,
|
524 |
+
"step": 8000
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 2.36,
|
528 |
+
"learning_rate": 2.6409210142815503e-05,
|
529 |
+
"loss": 0.1338,
|
530 |
+
"step": 8100
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 2.39,
|
534 |
+
"learning_rate": 2.611774992713495e-05,
|
535 |
+
"loss": 0.133,
|
536 |
+
"step": 8200
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 2.42,
|
540 |
+
"learning_rate": 2.5826289711454387e-05,
|
541 |
+
"loss": 0.1295,
|
542 |
+
"step": 8300
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 2.45,
|
546 |
+
"learning_rate": 2.5534829495773826e-05,
|
547 |
+
"loss": 0.1493,
|
548 |
+
"step": 8400
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 2.48,
|
552 |
+
"learning_rate": 2.5243369280093272e-05,
|
553 |
+
"loss": 0.1317,
|
554 |
+
"step": 8500
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 2.51,
|
558 |
+
"learning_rate": 2.495190906441271e-05,
|
559 |
+
"loss": 0.1327,
|
560 |
+
"step": 8600
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 2.54,
|
564 |
+
"learning_rate": 2.466044884873215e-05,
|
565 |
+
"loss": 0.1458,
|
566 |
+
"step": 8700
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 2.56,
|
570 |
+
"learning_rate": 2.4371903235208396e-05,
|
571 |
+
"loss": 0.1321,
|
572 |
+
"step": 8800
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 2.59,
|
576 |
+
"learning_rate": 2.4080443019527835e-05,
|
577 |
+
"loss": 0.1325,
|
578 |
+
"step": 8900
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 2.62,
|
582 |
+
"learning_rate": 2.3788982803847277e-05,
|
583 |
+
"loss": 0.1427,
|
584 |
+
"step": 9000
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 2.65,
|
588 |
+
"learning_rate": 2.349752258816672e-05,
|
589 |
+
"loss": 0.1174,
|
590 |
+
"step": 9100
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 2.68,
|
594 |
+
"learning_rate": 2.3206062372486158e-05,
|
595 |
+
"loss": 0.1368,
|
596 |
+
"step": 9200
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 2.71,
|
600 |
+
"learning_rate": 2.2914602156805597e-05,
|
601 |
+
"loss": 0.1305,
|
602 |
+
"step": 9300
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 2.74,
|
606 |
+
"learning_rate": 2.2626056543281843e-05,
|
607 |
+
"loss": 0.1335,
|
608 |
+
"step": 9400
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 2.77,
|
612 |
+
"learning_rate": 2.2334596327601285e-05,
|
613 |
+
"loss": 0.1331,
|
614 |
+
"step": 9500
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 2.8,
|
618 |
+
"learning_rate": 2.2043136111920724e-05,
|
619 |
+
"loss": 0.1528,
|
620 |
+
"step": 9600
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 2.83,
|
624 |
+
"learning_rate": 2.1751675896240163e-05,
|
625 |
+
"loss": 0.1332,
|
626 |
+
"step": 9700
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 2.86,
|
630 |
+
"learning_rate": 2.1460215680559602e-05,
|
631 |
+
"loss": 0.1454,
|
632 |
+
"step": 9800
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 2.89,
|
636 |
+
"learning_rate": 2.1168755464879044e-05,
|
637 |
+
"loss": 0.1472,
|
638 |
+
"step": 9900
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 2.91,
|
642 |
+
"learning_rate": 2.0877295249198486e-05,
|
643 |
+
"loss": 0.1361,
|
644 |
+
"step": 10000
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 2.91,
|
648 |
+
"eval_accuracy": 0.9194419384002686,
|
649 |
+
"eval_loss": 0.2857810854911804,
|
650 |
+
"eval_runtime": 35.5011,
|
651 |
+
"eval_samples_per_second": 375.538,
|
652 |
+
"eval_steps_per_second": 46.956,
|
653 |
+
"step": 10000
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 2.94,
|
657 |
+
"learning_rate": 2.0585835033517925e-05,
|
658 |
+
"loss": 0.1261,
|
659 |
+
"step": 10100
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 2.97,
|
663 |
+
"learning_rate": 2.0294374817837367e-05,
|
664 |
+
"loss": 0.1416,
|
665 |
+
"step": 10200
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 3.0,
|
669 |
+
"learning_rate": 2.0002914602156806e-05,
|
670 |
+
"loss": 0.143,
|
671 |
+
"step": 10300
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 3.03,
|
675 |
+
"learning_rate": 1.9711454386476248e-05,
|
676 |
+
"loss": 0.1101,
|
677 |
+
"step": 10400
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 3.06,
|
681 |
+
"learning_rate": 1.9419994170795687e-05,
|
682 |
+
"loss": 0.1076,
|
683 |
+
"step": 10500
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 3.09,
|
687 |
+
"learning_rate": 1.9128533955115126e-05,
|
688 |
+
"loss": 0.0947,
|
689 |
+
"step": 10600
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 3.12,
|
693 |
+
"learning_rate": 1.8837073739434568e-05,
|
694 |
+
"loss": 0.1009,
|
695 |
+
"step": 10700
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 3.15,
|
699 |
+
"learning_rate": 1.8545613523754007e-05,
|
700 |
+
"loss": 0.1013,
|
701 |
+
"step": 10800
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 3.18,
|
705 |
+
"learning_rate": 1.825415330807345e-05,
|
706 |
+
"loss": 0.1108,
|
707 |
+
"step": 10900
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 3.21,
|
711 |
+
"learning_rate": 1.796269309239289e-05,
|
712 |
+
"loss": 0.1092,
|
713 |
+
"step": 11000
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 3.24,
|
717 |
+
"learning_rate": 1.767123287671233e-05,
|
718 |
+
"loss": 0.1184,
|
719 |
+
"step": 11100
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"epoch": 3.26,
|
723 |
+
"learning_rate": 1.7379772661031772e-05,
|
724 |
+
"loss": 0.0937,
|
725 |
+
"step": 11200
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 3.29,
|
729 |
+
"learning_rate": 1.708831244535121e-05,
|
730 |
+
"loss": 0.1137,
|
731 |
+
"step": 11300
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 3.32,
|
735 |
+
"learning_rate": 1.679685222967065e-05,
|
736 |
+
"loss": 0.0975,
|
737 |
+
"step": 11400
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 3.35,
|
741 |
+
"learning_rate": 1.6505392013990092e-05,
|
742 |
+
"loss": 0.1147,
|
743 |
+
"step": 11500
|
744 |
+
},
|
745 |
+
{
|
746 |
+
"epoch": 3.38,
|
747 |
+
"learning_rate": 1.621393179830953e-05,
|
748 |
+
"loss": 0.0951,
|
749 |
+
"step": 11600
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 3.41,
|
753 |
+
"learning_rate": 1.5922471582628973e-05,
|
754 |
+
"loss": 0.1167,
|
755 |
+
"step": 11700
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 3.44,
|
759 |
+
"learning_rate": 1.5633925969105216e-05,
|
760 |
+
"loss": 0.1264,
|
761 |
+
"step": 11800
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 3.47,
|
765 |
+
"learning_rate": 1.5342465753424658e-05,
|
766 |
+
"loss": 0.1105,
|
767 |
+
"step": 11900
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 3.5,
|
771 |
+
"learning_rate": 1.5051005537744099e-05,
|
772 |
+
"loss": 0.0935,
|
773 |
+
"step": 12000
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 3.5,
|
777 |
+
"eval_accuracy": 0.9215421676635742,
|
778 |
+
"eval_loss": 0.33558839559555054,
|
779 |
+
"eval_runtime": 35.5063,
|
780 |
+
"eval_samples_per_second": 375.483,
|
781 |
+
"eval_steps_per_second": 46.949,
|
782 |
+
"step": 12000
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 3.53,
|
786 |
+
"learning_rate": 1.4759545322063539e-05,
|
787 |
+
"loss": 0.1137,
|
788 |
+
"step": 12100
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 3.56,
|
792 |
+
"learning_rate": 1.4468085106382978e-05,
|
793 |
+
"loss": 0.0945,
|
794 |
+
"step": 12200
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 3.58,
|
798 |
+
"learning_rate": 1.417662489070242e-05,
|
799 |
+
"loss": 0.1118,
|
800 |
+
"step": 12300
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 3.61,
|
804 |
+
"learning_rate": 1.388516467502186e-05,
|
805 |
+
"loss": 0.1174,
|
806 |
+
"step": 12400
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 3.64,
|
810 |
+
"learning_rate": 1.35937044593413e-05,
|
811 |
+
"loss": 0.0992,
|
812 |
+
"step": 12500
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 3.67,
|
816 |
+
"learning_rate": 1.3302244243660742e-05,
|
817 |
+
"loss": 0.1068,
|
818 |
+
"step": 12600
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 3.7,
|
822 |
+
"learning_rate": 1.301078402798018e-05,
|
823 |
+
"loss": 0.1098,
|
824 |
+
"step": 12700
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 3.73,
|
828 |
+
"learning_rate": 1.2719323812299621e-05,
|
829 |
+
"loss": 0.1126,
|
830 |
+
"step": 12800
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 3.76,
|
834 |
+
"learning_rate": 1.2427863596619061e-05,
|
835 |
+
"loss": 0.1119,
|
836 |
+
"step": 12900
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 3.79,
|
840 |
+
"learning_rate": 1.2136403380938502e-05,
|
841 |
+
"loss": 0.0936,
|
842 |
+
"step": 13000
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 3.82,
|
846 |
+
"learning_rate": 1.1844943165257944e-05,
|
847 |
+
"loss": 0.0995,
|
848 |
+
"step": 13100
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 3.85,
|
852 |
+
"learning_rate": 1.1553482949577383e-05,
|
853 |
+
"loss": 0.1152,
|
854 |
+
"step": 13200
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 3.88,
|
858 |
+
"learning_rate": 1.126493733605363e-05,
|
859 |
+
"loss": 0.1191,
|
860 |
+
"step": 13300
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 3.91,
|
864 |
+
"learning_rate": 1.097347712037307e-05,
|
865 |
+
"loss": 0.1116,
|
866 |
+
"step": 13400
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 3.93,
|
870 |
+
"learning_rate": 1.068201690469251e-05,
|
871 |
+
"loss": 0.115,
|
872 |
+
"step": 13500
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 3.96,
|
876 |
+
"learning_rate": 1.039055668901195e-05,
|
877 |
+
"loss": 0.1026,
|
878 |
+
"step": 13600
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 3.99,
|
882 |
+
"learning_rate": 1.009909647333139e-05,
|
883 |
+
"loss": 0.0919,
|
884 |
+
"step": 13700
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 4.02,
|
888 |
+
"learning_rate": 9.80763625765083e-06,
|
889 |
+
"loss": 0.0885,
|
890 |
+
"step": 13800
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 4.05,
|
894 |
+
"learning_rate": 9.516176041970272e-06,
|
895 |
+
"loss": 0.0731,
|
896 |
+
"step": 13900
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 4.08,
|
900 |
+
"learning_rate": 9.224715826289713e-06,
|
901 |
+
"loss": 0.077,
|
902 |
+
"step": 14000
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 4.08,
|
906 |
+
"eval_accuracy": 0.9283678531646729,
|
907 |
+
"eval_loss": 0.3291896879673004,
|
908 |
+
"eval_runtime": 35.4606,
|
909 |
+
"eval_samples_per_second": 375.967,
|
910 |
+
"eval_steps_per_second": 47.01,
|
911 |
+
"step": 14000
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 4.11,
|
915 |
+
"learning_rate": 8.933255610609152e-06,
|
916 |
+
"loss": 0.0731,
|
917 |
+
"step": 14100
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 4.14,
|
921 |
+
"learning_rate": 8.641795394928592e-06,
|
922 |
+
"loss": 0.0821,
|
923 |
+
"step": 14200
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 4.17,
|
927 |
+
"learning_rate": 8.350335179248033e-06,
|
928 |
+
"loss": 0.0879,
|
929 |
+
"step": 14300
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 4.2,
|
933 |
+
"learning_rate": 8.058874963567475e-06,
|
934 |
+
"loss": 0.082,
|
935 |
+
"step": 14400
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 4.23,
|
939 |
+
"learning_rate": 7.767414747886914e-06,
|
940 |
+
"loss": 0.0851,
|
941 |
+
"step": 14500
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 4.26,
|
945 |
+
"learning_rate": 7.475954532206354e-06,
|
946 |
+
"loss": 0.0922,
|
947 |
+
"step": 14600
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 4.28,
|
951 |
+
"learning_rate": 7.1844943165257946e-06,
|
952 |
+
"loss": 0.0831,
|
953 |
+
"step": 14700
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 4.31,
|
957 |
+
"learning_rate": 6.893034100845234e-06,
|
958 |
+
"loss": 0.0817,
|
959 |
+
"step": 14800
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 4.34,
|
963 |
+
"learning_rate": 6.601573885164675e-06,
|
964 |
+
"loss": 0.0826,
|
965 |
+
"step": 14900
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 4.37,
|
969 |
+
"learning_rate": 6.310113669484116e-06,
|
970 |
+
"loss": 0.0926,
|
971 |
+
"step": 15000
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 4.4,
|
975 |
+
"learning_rate": 6.0186534538035565e-06,
|
976 |
+
"loss": 0.0829,
|
977 |
+
"step": 15100
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 4.43,
|
981 |
+
"learning_rate": 5.727193238122996e-06,
|
982 |
+
"loss": 0.0874,
|
983 |
+
"step": 15200
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 4.46,
|
987 |
+
"learning_rate": 5.435733022442437e-06,
|
988 |
+
"loss": 0.078,
|
989 |
+
"step": 15300
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 4.49,
|
993 |
+
"learning_rate": 5.144272806761877e-06,
|
994 |
+
"loss": 0.0964,
|
995 |
+
"step": 15400
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 4.52,
|
999 |
+
"learning_rate": 4.852812591081318e-06,
|
1000 |
+
"loss": 0.0759,
|
1001 |
+
"step": 15500
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 4.55,
|
1005 |
+
"learning_rate": 4.561352375400757e-06,
|
1006 |
+
"loss": 0.0996,
|
1007 |
+
"step": 15600
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 4.58,
|
1011 |
+
"learning_rate": 4.269892159720199e-06,
|
1012 |
+
"loss": 0.0835,
|
1013 |
+
"step": 15700
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 4.6,
|
1017 |
+
"learning_rate": 3.978431944039638e-06,
|
1018 |
+
"loss": 0.0869,
|
1019 |
+
"step": 15800
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 4.63,
|
1023 |
+
"learning_rate": 3.6869717283590797e-06,
|
1024 |
+
"loss": 0.0837,
|
1025 |
+
"step": 15900
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 4.66,
|
1029 |
+
"learning_rate": 3.3955115126785197e-06,
|
1030 |
+
"loss": 0.0687,
|
1031 |
+
"step": 16000
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 4.66,
|
1035 |
+
"eval_accuracy": 0.9291929006576538,
|
1036 |
+
"eval_loss": 0.31212949752807617,
|
1037 |
+
"eval_runtime": 35.4974,
|
1038 |
+
"eval_samples_per_second": 375.577,
|
1039 |
+
"eval_steps_per_second": 46.961,
|
1040 |
+
"step": 16000
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 4.69,
|
1044 |
+
"learning_rate": 3.1040512969979602e-06,
|
1045 |
+
"loss": 0.0854,
|
1046 |
+
"step": 16100
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 4.72,
|
1050 |
+
"learning_rate": 2.8125910813174003e-06,
|
1051 |
+
"loss": 0.0704,
|
1052 |
+
"step": 16200
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 4.75,
|
1056 |
+
"learning_rate": 2.521130865636841e-06,
|
1057 |
+
"loss": 0.0792,
|
1058 |
+
"step": 16300
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 4.78,
|
1062 |
+
"learning_rate": 2.2296706499562813e-06,
|
1063 |
+
"loss": 0.0777,
|
1064 |
+
"step": 16400
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 4.81,
|
1068 |
+
"learning_rate": 1.9382104342757214e-06,
|
1069 |
+
"loss": 0.0902,
|
1070 |
+
"step": 16500
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 4.84,
|
1074 |
+
"learning_rate": 1.6467502185951619e-06,
|
1075 |
+
"loss": 0.0801,
|
1076 |
+
"step": 16600
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 4.87,
|
1080 |
+
"learning_rate": 1.3552900029146024e-06,
|
1081 |
+
"loss": 0.0896,
|
1082 |
+
"step": 16700
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 4.9,
|
1086 |
+
"learning_rate": 1.0638297872340427e-06,
|
1087 |
+
"loss": 0.0772,
|
1088 |
+
"step": 16800
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 4.93,
|
1092 |
+
"learning_rate": 7.723695715534829e-07,
|
1093 |
+
"loss": 0.0716,
|
1094 |
+
"step": 16900
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 4.95,
|
1098 |
+
"learning_rate": 4.809093558729233e-07,
|
1099 |
+
"loss": 0.0658,
|
1100 |
+
"step": 17000
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 4.98,
|
1104 |
+
"learning_rate": 1.8944914019236375e-07,
|
1105 |
+
"loss": 0.0888,
|
1106 |
+
"step": 17100
|
1107 |
+
}
|
1108 |
+
],
|
1109 |
+
"max_steps": 17155,
|
1110 |
+
"num_train_epochs": 5,
|
1111 |
+
"total_flos": 5.255829891028992e+16,
|
1112 |
+
"trial_name": null,
|
1113 |
+
"trial_params": null
|
1114 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0829be1c69a925c00633e146afd48f57ecc0082809373a47b733231c787654bc
|
3 |
+
size 2479
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|