chizhik
commited on
Commit
•
8cc346f
1
Parent(s):
42350de
updated model weights after stratified fine-tuning
Browse files- .DS_Store +0 -0
- config.json +65 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- trainer_state.json +588 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.DS_Store
DELETED
Binary file (6.15 kB)
|
|
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./Models/roberta-base-biomedical-clinical-es",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "LABEL_0",
|
16 |
+
"1": "LABEL_1",
|
17 |
+
"2": "LABEL_2",
|
18 |
+
"3": "LABEL_3",
|
19 |
+
"4": "LABEL_4",
|
20 |
+
"5": "LABEL_5",
|
21 |
+
"6": "LABEL_6",
|
22 |
+
"7": "LABEL_7",
|
23 |
+
"8": "LABEL_8",
|
24 |
+
"9": "LABEL_9",
|
25 |
+
"10": "LABEL_10",
|
26 |
+
"11": "LABEL_11",
|
27 |
+
"12": "LABEL_12",
|
28 |
+
"13": "LABEL_13",
|
29 |
+
"14": "LABEL_14",
|
30 |
+
"15": "LABEL_15"
|
31 |
+
},
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"intermediate_size": 3072,
|
34 |
+
"label2id": {
|
35 |
+
"LABEL_0": 0,
|
36 |
+
"LABEL_1": 1,
|
37 |
+
"LABEL_10": 10,
|
38 |
+
"LABEL_11": 11,
|
39 |
+
"LABEL_12": 12,
|
40 |
+
"LABEL_13": 13,
|
41 |
+
"LABEL_14": 14,
|
42 |
+
"LABEL_15": 15,
|
43 |
+
"LABEL_2": 2,
|
44 |
+
"LABEL_3": 3,
|
45 |
+
"LABEL_4": 4,
|
46 |
+
"LABEL_5": 5,
|
47 |
+
"LABEL_6": 6,
|
48 |
+
"LABEL_7": 7,
|
49 |
+
"LABEL_8": 8,
|
50 |
+
"LABEL_9": 9
|
51 |
+
},
|
52 |
+
"layer_norm_eps": 1e-05,
|
53 |
+
"max_position_embeddings": 514,
|
54 |
+
"model_type": "roberta",
|
55 |
+
"num_attention_heads": 12,
|
56 |
+
"num_hidden_layers": 12,
|
57 |
+
"pad_token_id": 1,
|
58 |
+
"position_embedding_type": "absolute",
|
59 |
+
"problem_type": "multi_label_classification",
|
60 |
+
"torch_dtype": "float32",
|
61 |
+
"transformers_version": "4.24.0",
|
62 |
+
"type_vocab_size": 1,
|
63 |
+
"use_cache": true,
|
64 |
+
"vocab_size": 52000
|
65 |
+
}
|
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:d5c5cbc732dc61f382394ca38be8c180004f09ebf568bf5f6c366f50c08d16a9
|
3 |
+
size 1008039837
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72d93baa2b2bd83e9ad3d5a6dee38be0e6fdc3537acb4f533d9871c48a5cffca
|
3 |
+
size 504033325
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c81a7f6b3c22226527f74224efa5bfd6812e7643711f3363571e33b7048a5d4
|
3 |
+
size 14567
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:501d80737344dcd2274196fc2df8440bccd24c52b8c2e1bc8bdc49a42cbf6651
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"cls_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"__type": "AddedToken",
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"errors": "replace",
|
28 |
+
"mask_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<mask>",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"max_len": 512,
|
37 |
+
"name_or_path": "Models/roberta-base-biomedical-clinical-es",
|
38 |
+
"pad_token": {
|
39 |
+
"__type": "AddedToken",
|
40 |
+
"content": "<pad>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": true,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"sep_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "</s>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"special_tokens_map_file": null,
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": {
|
58 |
+
"__type": "AddedToken",
|
59 |
+
"content": "<unk>",
|
60 |
+
"lstrip": false,
|
61 |
+
"normalized": true,
|
62 |
+
"rstrip": false,
|
63 |
+
"single_word": false
|
64 |
+
}
|
65 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,588 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7370102490601179,
|
3 |
+
"best_model_checkpoint": "./CARES/checkpoints/roberta-stratified/run-4/checkpoint-5112",
|
4 |
+
"epoch": 36.255319148936174,
|
5 |
+
"global_step": 5112,
|
6 |
+
"is_hyper_param_search": true,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.01,
|
12 |
+
"eval_loss": 0.3023780882358551,
|
13 |
+
"eval_macro_f1": 0.04276761517615176,
|
14 |
+
"eval_macro_precision": 0.03250514933058703,
|
15 |
+
"eval_macro_recall": 0.0625,
|
16 |
+
"eval_micro_f1": 0.4057854560064283,
|
17 |
+
"eval_micro_precision": 0.5200823892893924,
|
18 |
+
"eval_micro_recall": 0.3326745718050066,
|
19 |
+
"eval_runtime": 2.6706,
|
20 |
+
"eval_samples_per_second": 363.595,
|
21 |
+
"eval_steps_per_second": 22.842,
|
22 |
+
"step": 142
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.01,
|
26 |
+
"eval_loss": 0.2355797439813614,
|
27 |
+
"eval_macro_f1": 0.0478700416730977,
|
28 |
+
"eval_macro_precision": 0.10847007722007722,
|
29 |
+
"eval_macro_recall": 0.04781835896355593,
|
30 |
+
"eval_micro_f1": 0.3766552231486022,
|
31 |
+
"eval_micro_precision": 0.7370441458733206,
|
32 |
+
"eval_micro_recall": 0.25296442687747034,
|
33 |
+
"eval_runtime": 2.6743,
|
34 |
+
"eval_samples_per_second": 363.08,
|
35 |
+
"eval_steps_per_second": 22.809,
|
36 |
+
"step": 284
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.02,
|
40 |
+
"eval_loss": 0.20839156210422516,
|
41 |
+
"eval_macro_f1": 0.1270678623977507,
|
42 |
+
"eval_macro_precision": 0.15146020789583886,
|
43 |
+
"eval_macro_recall": 0.11056835837347367,
|
44 |
+
"eval_micro_f1": 0.5080789946140036,
|
45 |
+
"eval_micro_precision": 0.7971830985915493,
|
46 |
+
"eval_micro_recall": 0.37285902503293805,
|
47 |
+
"eval_runtime": 2.6737,
|
48 |
+
"eval_samples_per_second": 363.172,
|
49 |
+
"eval_steps_per_second": 22.815,
|
50 |
+
"step": 426
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 3.55,
|
54 |
+
"learning_rate": 4.760888771678367e-05,
|
55 |
+
"loss": 0.3067,
|
56 |
+
"step": 500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.03,
|
60 |
+
"eval_loss": 0.17458897829055786,
|
61 |
+
"eval_macro_f1": 0.2134043623340923,
|
62 |
+
"eval_macro_precision": 0.2555480902740095,
|
63 |
+
"eval_macro_recall": 0.1956241201896679,
|
64 |
+
"eval_micro_f1": 0.652869972666927,
|
65 |
+
"eval_micro_precision": 0.8015340364333653,
|
66 |
+
"eval_micro_recall": 0.5507246376811594,
|
67 |
+
"eval_runtime": 2.6714,
|
68 |
+
"eval_samples_per_second": 363.484,
|
69 |
+
"eval_steps_per_second": 22.835,
|
70 |
+
"step": 568
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 5.04,
|
74 |
+
"eval_loss": 0.1594998985528946,
|
75 |
+
"eval_macro_f1": 0.322947699403185,
|
76 |
+
"eval_macro_precision": 0.33082406427783345,
|
77 |
+
"eval_macro_recall": 0.31592054350156284,
|
78 |
+
"eval_micro_f1": 0.7086383601756956,
|
79 |
+
"eval_micro_precision": 0.7973640856672158,
|
80 |
+
"eval_micro_recall": 0.6376811594202898,
|
81 |
+
"eval_runtime": 2.6774,
|
82 |
+
"eval_samples_per_second": 362.663,
|
83 |
+
"eval_steps_per_second": 22.783,
|
84 |
+
"step": 710
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.04,
|
88 |
+
"eval_loss": 0.14328011870384216,
|
89 |
+
"eval_macro_f1": 0.35552541662372633,
|
90 |
+
"eval_macro_precision": 0.4154000509380286,
|
91 |
+
"eval_macro_recall": 0.3384352474665031,
|
92 |
+
"eval_micro_f1": 0.730332967435053,
|
93 |
+
"eval_micro_precision": 0.8213991769547325,
|
94 |
+
"eval_micro_recall": 0.6574440052700923,
|
95 |
+
"eval_runtime": 2.6759,
|
96 |
+
"eval_samples_per_second": 362.867,
|
97 |
+
"eval_steps_per_second": 22.796,
|
98 |
+
"step": 852
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.05,
|
102 |
+
"eval_loss": 0.1372288167476654,
|
103 |
+
"eval_macro_f1": 0.35769698646328396,
|
104 |
+
"eval_macro_precision": 0.45729587282684003,
|
105 |
+
"eval_macro_recall": 0.340956446807801,
|
106 |
+
"eval_micro_f1": 0.747014115092291,
|
107 |
+
"eval_micro_precision": 0.8289156626506025,
|
108 |
+
"eval_micro_recall": 0.6798418972332015,
|
109 |
+
"eval_runtime": 2.6665,
|
110 |
+
"eval_samples_per_second": 364.154,
|
111 |
+
"eval_steps_per_second": 22.877,
|
112 |
+
"step": 994
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 7.09,
|
116 |
+
"learning_rate": 4.585856096249015e-05,
|
117 |
+
"loss": 0.1366,
|
118 |
+
"step": 1000
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 8.06,
|
122 |
+
"eval_loss": 0.13587501645088196,
|
123 |
+
"eval_macro_f1": 0.4519999262177494,
|
124 |
+
"eval_macro_precision": 0.6383482484756009,
|
125 |
+
"eval_macro_recall": 0.4120606473790193,
|
126 |
+
"eval_micro_f1": 0.7476635514018692,
|
127 |
+
"eval_micro_precision": 0.8227848101265823,
|
128 |
+
"eval_micro_recall": 0.6851119894598156,
|
129 |
+
"eval_runtime": 2.6678,
|
130 |
+
"eval_samples_per_second": 363.976,
|
131 |
+
"eval_steps_per_second": 22.866,
|
132 |
+
"step": 1136
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 9.06,
|
136 |
+
"eval_loss": 0.1254434585571289,
|
137 |
+
"eval_macro_f1": 0.5752781473187552,
|
138 |
+
"eval_macro_precision": 0.6682540412600851,
|
139 |
+
"eval_macro_recall": 0.5248832453258128,
|
140 |
+
"eval_micro_f1": 0.7869884575026234,
|
141 |
+
"eval_micro_precision": 0.8389261744966443,
|
142 |
+
"eval_micro_recall": 0.741106719367589,
|
143 |
+
"eval_runtime": 2.6676,
|
144 |
+
"eval_samples_per_second": 364.002,
|
145 |
+
"eval_steps_per_second": 22.867,
|
146 |
+
"step": 1278
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 10.07,
|
150 |
+
"eval_loss": 0.12716087698936462,
|
151 |
+
"eval_macro_f1": 0.5783160913404322,
|
152 |
+
"eval_macro_precision": 0.6669120855288475,
|
153 |
+
"eval_macro_recall": 0.5333612306839322,
|
154 |
+
"eval_micro_f1": 0.7954701441317777,
|
155 |
+
"eval_micro_precision": 0.8302292263610315,
|
156 |
+
"eval_micro_recall": 0.7635046113306982,
|
157 |
+
"eval_runtime": 2.6683,
|
158 |
+
"eval_samples_per_second": 363.896,
|
159 |
+
"eval_steps_per_second": 22.861,
|
160 |
+
"step": 1420
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 10.64,
|
164 |
+
"learning_rate": 4.410823420819664e-05,
|
165 |
+
"loss": 0.0661,
|
166 |
+
"step": 1500
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 11.08,
|
170 |
+
"eval_loss": 0.12210354208946228,
|
171 |
+
"eval_macro_f1": 0.6129525814973475,
|
172 |
+
"eval_macro_precision": 0.694661979564102,
|
173 |
+
"eval_macro_recall": 0.5604968051311103,
|
174 |
+
"eval_micro_f1": 0.8090971743625087,
|
175 |
+
"eval_micro_precision": 0.8482658959537572,
|
176 |
+
"eval_micro_recall": 0.7733860342555995,
|
177 |
+
"eval_runtime": 2.6691,
|
178 |
+
"eval_samples_per_second": 363.79,
|
179 |
+
"eval_steps_per_second": 22.854,
|
180 |
+
"step": 1562
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 12.09,
|
184 |
+
"eval_loss": 0.13834641873836517,
|
185 |
+
"eval_macro_f1": 0.59964421079272,
|
186 |
+
"eval_macro_precision": 0.6259545070217613,
|
187 |
+
"eval_macro_recall": 0.5849130461175929,
|
188 |
+
"eval_micro_f1": 0.7874705287975748,
|
189 |
+
"eval_micro_precision": 0.8056512749827704,
|
190 |
+
"eval_micro_recall": 0.7700922266139657,
|
191 |
+
"eval_runtime": 2.6674,
|
192 |
+
"eval_samples_per_second": 364.02,
|
193 |
+
"eval_steps_per_second": 22.868,
|
194 |
+
"step": 1704
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 13.09,
|
198 |
+
"eval_loss": 0.13302326202392578,
|
199 |
+
"eval_macro_f1": 0.6249414362192053,
|
200 |
+
"eval_macro_precision": 0.6603169616331872,
|
201 |
+
"eval_macro_recall": 0.6008160113233191,
|
202 |
+
"eval_micro_f1": 0.8105579685933846,
|
203 |
+
"eval_micro_precision": 0.8223728813559322,
|
204 |
+
"eval_micro_recall": 0.7990777338603425,
|
205 |
+
"eval_runtime": 2.6684,
|
206 |
+
"eval_samples_per_second": 363.887,
|
207 |
+
"eval_steps_per_second": 22.86,
|
208 |
+
"step": 1846
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 14.1,
|
212 |
+
"eval_loss": 0.13799144327640533,
|
213 |
+
"eval_macro_f1": 0.6256821918613437,
|
214 |
+
"eval_macro_precision": 0.6740205274811021,
|
215 |
+
"eval_macro_recall": 0.5938987995613589,
|
216 |
+
"eval_micro_f1": 0.8119891008174386,
|
217 |
+
"eval_micro_precision": 0.840620592383639,
|
218 |
+
"eval_micro_recall": 0.7852437417654808,
|
219 |
+
"eval_runtime": 2.6691,
|
220 |
+
"eval_samples_per_second": 363.79,
|
221 |
+
"eval_steps_per_second": 22.854,
|
222 |
+
"step": 1988
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 14.18,
|
226 |
+
"learning_rate": 4.235790745390312e-05,
|
227 |
+
"loss": 0.0324,
|
228 |
+
"step": 2000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 15.11,
|
232 |
+
"eval_loss": 0.13957080245018005,
|
233 |
+
"eval_macro_f1": 0.6541379860188454,
|
234 |
+
"eval_macro_precision": 0.7002594602789083,
|
235 |
+
"eval_macro_recall": 0.6359217043250158,
|
236 |
+
"eval_micro_f1": 0.803843605036448,
|
237 |
+
"eval_micro_precision": 0.8086666666666666,
|
238 |
+
"eval_micro_recall": 0.7990777338603425,
|
239 |
+
"eval_runtime": 2.6709,
|
240 |
+
"eval_samples_per_second": 363.55,
|
241 |
+
"eval_steps_per_second": 22.839,
|
242 |
+
"step": 2130
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 16.11,
|
246 |
+
"eval_loss": 0.13600043952465057,
|
247 |
+
"eval_macro_f1": 0.6528569810495737,
|
248 |
+
"eval_macro_precision": 0.7119806310239326,
|
249 |
+
"eval_macro_recall": 0.6199612374678921,
|
250 |
+
"eval_micro_f1": 0.8169491525423729,
|
251 |
+
"eval_micro_precision": 0.8414804469273743,
|
252 |
+
"eval_micro_recall": 0.7938076416337286,
|
253 |
+
"eval_runtime": 2.6686,
|
254 |
+
"eval_samples_per_second": 363.864,
|
255 |
+
"eval_steps_per_second": 22.859,
|
256 |
+
"step": 2272
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 17.12,
|
260 |
+
"eval_loss": 0.1411595642566681,
|
261 |
+
"eval_macro_f1": 0.6780053870985077,
|
262 |
+
"eval_macro_precision": 0.7825949490722317,
|
263 |
+
"eval_macro_recall": 0.6371295063080809,
|
264 |
+
"eval_micro_f1": 0.8134328358208954,
|
265 |
+
"eval_micro_precision": 0.8384615384615385,
|
266 |
+
"eval_micro_recall": 0.7898550724637681,
|
267 |
+
"eval_runtime": 2.6685,
|
268 |
+
"eval_samples_per_second": 363.87,
|
269 |
+
"eval_steps_per_second": 22.859,
|
270 |
+
"step": 2414
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 17.73,
|
274 |
+
"learning_rate": 4.06075806996096e-05,
|
275 |
+
"loss": 0.0173,
|
276 |
+
"step": 2500
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 18.13,
|
280 |
+
"eval_loss": 0.14683738350868225,
|
281 |
+
"eval_macro_f1": 0.6538188838769178,
|
282 |
+
"eval_macro_precision": 0.7058131112592007,
|
283 |
+
"eval_macro_recall": 0.628120629850237,
|
284 |
+
"eval_micro_f1": 0.8044280442804428,
|
285 |
+
"eval_micro_precision": 0.8195488721804511,
|
286 |
+
"eval_micro_recall": 0.7898550724637681,
|
287 |
+
"eval_runtime": 2.6704,
|
288 |
+
"eval_samples_per_second": 363.611,
|
289 |
+
"eval_steps_per_second": 22.843,
|
290 |
+
"step": 2556
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 19.13,
|
294 |
+
"eval_loss": 0.14477181434631348,
|
295 |
+
"eval_macro_f1": 0.7213223353389469,
|
296 |
+
"eval_macro_precision": 0.7931053666626622,
|
297 |
+
"eval_macro_recall": 0.6989155005450692,
|
298 |
+
"eval_micro_f1": 0.8122731771692511,
|
299 |
+
"eval_micro_precision": 0.813615333773959,
|
300 |
+
"eval_micro_recall": 0.810935441370224,
|
301 |
+
"eval_runtime": 2.6682,
|
302 |
+
"eval_samples_per_second": 363.916,
|
303 |
+
"eval_steps_per_second": 22.862,
|
304 |
+
"step": 2698
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 20.14,
|
308 |
+
"eval_loss": 0.1553182750940323,
|
309 |
+
"eval_macro_f1": 0.6767777822180807,
|
310 |
+
"eval_macro_precision": 0.7296284296772766,
|
311 |
+
"eval_macro_recall": 0.6640188299255232,
|
312 |
+
"eval_micro_f1": 0.8082867477803354,
|
313 |
+
"eval_micro_precision": 0.8069599474720945,
|
314 |
+
"eval_micro_recall": 0.8096179183135704,
|
315 |
+
"eval_runtime": 2.6706,
|
316 |
+
"eval_samples_per_second": 363.587,
|
317 |
+
"eval_steps_per_second": 22.841,
|
318 |
+
"step": 2840
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 21.15,
|
322 |
+
"eval_loss": 0.14831620454788208,
|
323 |
+
"eval_macro_f1": 0.6951923518777028,
|
324 |
+
"eval_macro_precision": 0.8479068478364982,
|
325 |
+
"eval_macro_recall": 0.6493756779822191,
|
326 |
+
"eval_micro_f1": 0.8177506775067751,
|
327 |
+
"eval_micro_precision": 0.8417015341701534,
|
328 |
+
"eval_micro_recall": 0.7951251646903821,
|
329 |
+
"eval_runtime": 2.6679,
|
330 |
+
"eval_samples_per_second": 363.953,
|
331 |
+
"eval_steps_per_second": 22.864,
|
332 |
+
"step": 2982
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 21.28,
|
336 |
+
"learning_rate": 3.885725394531609e-05,
|
337 |
+
"loss": 0.0121,
|
338 |
+
"step": 3000
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 22.16,
|
342 |
+
"eval_loss": 0.1529681533575058,
|
343 |
+
"eval_macro_f1": 0.7215214471733791,
|
344 |
+
"eval_macro_precision": 0.840496134606828,
|
345 |
+
"eval_macro_recall": 0.6777226713039917,
|
346 |
+
"eval_micro_f1": 0.8099395567494962,
|
347 |
+
"eval_micro_precision": 0.826027397260274,
|
348 |
+
"eval_micro_recall": 0.7944664031620553,
|
349 |
+
"eval_runtime": 2.6724,
|
350 |
+
"eval_samples_per_second": 363.343,
|
351 |
+
"eval_steps_per_second": 22.826,
|
352 |
+
"step": 3124
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 23.16,
|
356 |
+
"eval_loss": 0.15208803117275238,
|
357 |
+
"eval_macro_f1": 0.7282532116551124,
|
358 |
+
"eval_macro_precision": 0.8178655579947314,
|
359 |
+
"eval_macro_recall": 0.702450635375965,
|
360 |
+
"eval_micro_f1": 0.8099009900990098,
|
361 |
+
"eval_micro_precision": 0.8115079365079365,
|
362 |
+
"eval_micro_recall": 0.808300395256917,
|
363 |
+
"eval_runtime": 2.6735,
|
364 |
+
"eval_samples_per_second": 363.196,
|
365 |
+
"eval_steps_per_second": 22.817,
|
366 |
+
"step": 3266
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 24.17,
|
370 |
+
"eval_loss": 0.17097046971321106,
|
371 |
+
"eval_macro_f1": 0.6781929633024913,
|
372 |
+
"eval_macro_precision": 0.7664743620916477,
|
373 |
+
"eval_macro_recall": 0.647287649907105,
|
374 |
+
"eval_micro_f1": 0.8018836192398252,
|
375 |
+
"eval_micro_precision": 0.8192439862542955,
|
376 |
+
"eval_micro_recall": 0.7852437417654808,
|
377 |
+
"eval_runtime": 2.6679,
|
378 |
+
"eval_samples_per_second": 363.956,
|
379 |
+
"eval_steps_per_second": 22.864,
|
380 |
+
"step": 3408
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 24.82,
|
384 |
+
"learning_rate": 3.710692719102257e-05,
|
385 |
+
"loss": 0.0086,
|
386 |
+
"step": 3500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 25.18,
|
390 |
+
"eval_loss": 0.16351111233234406,
|
391 |
+
"eval_macro_f1": 0.7009939961760294,
|
392 |
+
"eval_macro_precision": 0.8049793687947511,
|
393 |
+
"eval_macro_recall": 0.6631263784729529,
|
394 |
+
"eval_micro_f1": 0.8080672268907563,
|
395 |
+
"eval_micro_precision": 0.8249828414550446,
|
396 |
+
"eval_micro_recall": 0.7918313570487484,
|
397 |
+
"eval_runtime": 2.6758,
|
398 |
+
"eval_samples_per_second": 362.882,
|
399 |
+
"eval_steps_per_second": 22.797,
|
400 |
+
"step": 3550
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 26.18,
|
404 |
+
"eval_loss": 0.1703951209783554,
|
405 |
+
"eval_macro_f1": 0.728858993061112,
|
406 |
+
"eval_macro_precision": 0.8293166501604144,
|
407 |
+
"eval_macro_recall": 0.6848344575219967,
|
408 |
+
"eval_micro_f1": 0.8101945003353456,
|
409 |
+
"eval_micro_precision": 0.825136612021858,
|
410 |
+
"eval_micro_recall": 0.7957839262187089,
|
411 |
+
"eval_runtime": 2.6853,
|
412 |
+
"eval_samples_per_second": 361.599,
|
413 |
+
"eval_steps_per_second": 22.716,
|
414 |
+
"step": 3692
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 27.19,
|
418 |
+
"eval_loss": 0.1729104220867157,
|
419 |
+
"eval_macro_f1": 0.7246800474910258,
|
420 |
+
"eval_macro_precision": 0.8088443156400115,
|
421 |
+
"eval_macro_recall": 0.6938957592472167,
|
422 |
+
"eval_micro_f1": 0.8112827400940228,
|
423 |
+
"eval_micro_precision": 0.8273972602739726,
|
424 |
+
"eval_micro_recall": 0.7957839262187089,
|
425 |
+
"eval_runtime": 2.6704,
|
426 |
+
"eval_samples_per_second": 363.619,
|
427 |
+
"eval_steps_per_second": 22.843,
|
428 |
+
"step": 3834
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 28.2,
|
432 |
+
"eval_loss": 0.17421075701713562,
|
433 |
+
"eval_macro_f1": 0.721641920467399,
|
434 |
+
"eval_macro_precision": 0.7953793533738551,
|
435 |
+
"eval_macro_recall": 0.6939586213926427,
|
436 |
+
"eval_micro_f1": 0.8118745830553702,
|
437 |
+
"eval_micro_precision": 0.8222972972972973,
|
438 |
+
"eval_micro_recall": 0.8017127799736495,
|
439 |
+
"eval_runtime": 2.6674,
|
440 |
+
"eval_samples_per_second": 364.019,
|
441 |
+
"eval_steps_per_second": 22.868,
|
442 |
+
"step": 3976
|
443 |
+
},
|
444 |
+
{
|
445 |
+
"epoch": 28.37,
|
446 |
+
"learning_rate": 3.535660043672905e-05,
|
447 |
+
"loss": 0.0054,
|
448 |
+
"step": 4000
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 29.21,
|
452 |
+
"eval_loss": 0.17936377227306366,
|
453 |
+
"eval_macro_f1": 0.7165402537125084,
|
454 |
+
"eval_macro_precision": 0.7314012003015316,
|
455 |
+
"eval_macro_recall": 0.7193045979731636,
|
456 |
+
"eval_micro_f1": 0.8045826513911619,
|
457 |
+
"eval_micro_precision": 0.7996096291476903,
|
458 |
+
"eval_micro_recall": 0.8096179183135704,
|
459 |
+
"eval_runtime": 2.669,
|
460 |
+
"eval_samples_per_second": 363.809,
|
461 |
+
"eval_steps_per_second": 22.855,
|
462 |
+
"step": 4118
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 30.21,
|
466 |
+
"eval_loss": 0.184128999710083,
|
467 |
+
"eval_macro_f1": 0.7249069877656021,
|
468 |
+
"eval_macro_precision": 0.7920679958383108,
|
469 |
+
"eval_macro_recall": 0.6986794530201526,
|
470 |
+
"eval_micro_f1": 0.8046822742474916,
|
471 |
+
"eval_micro_precision": 0.8172554347826086,
|
472 |
+
"eval_micro_recall": 0.7924901185770751,
|
473 |
+
"eval_runtime": 2.6699,
|
474 |
+
"eval_samples_per_second": 363.687,
|
475 |
+
"eval_steps_per_second": 22.847,
|
476 |
+
"step": 4260
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 31.22,
|
480 |
+
"eval_loss": 0.18270088732242584,
|
481 |
+
"eval_macro_f1": 0.7341637485973148,
|
482 |
+
"eval_macro_precision": 0.8378115033399074,
|
483 |
+
"eval_macro_recall": 0.6892808840460984,
|
484 |
+
"eval_micro_f1": 0.8134680134680136,
|
485 |
+
"eval_micro_precision": 0.8319559228650137,
|
486 |
+
"eval_micro_recall": 0.7957839262187089,
|
487 |
+
"eval_runtime": 2.6693,
|
488 |
+
"eval_samples_per_second": 363.77,
|
489 |
+
"eval_steps_per_second": 22.853,
|
490 |
+
"step": 4402
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 31.91,
|
494 |
+
"learning_rate": 3.3606273682435536e-05,
|
495 |
+
"loss": 0.0035,
|
496 |
+
"step": 4500
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"epoch": 32.23,
|
500 |
+
"eval_loss": 0.18414482474327087,
|
501 |
+
"eval_macro_f1": 0.7314425663595913,
|
502 |
+
"eval_macro_precision": 0.8099477622958757,
|
503 |
+
"eval_macro_recall": 0.6986944147838622,
|
504 |
+
"eval_micro_f1": 0.8134003350083752,
|
505 |
+
"eval_micro_precision": 0.8275391956373551,
|
506 |
+
"eval_micro_recall": 0.7997364953886693,
|
507 |
+
"eval_runtime": 2.6686,
|
508 |
+
"eval_samples_per_second": 363.857,
|
509 |
+
"eval_steps_per_second": 22.858,
|
510 |
+
"step": 4544
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 33.23,
|
514 |
+
"eval_loss": 0.18519891798496246,
|
515 |
+
"eval_macro_f1": 0.7352936873025266,
|
516 |
+
"eval_macro_precision": 0.8265688293622399,
|
517 |
+
"eval_macro_recall": 0.6958315897622773,
|
518 |
+
"eval_micro_f1": 0.8212722988892629,
|
519 |
+
"eval_micro_precision": 0.8396421197522368,
|
520 |
+
"eval_micro_recall": 0.8036890645586298,
|
521 |
+
"eval_runtime": 2.6687,
|
522 |
+
"eval_samples_per_second": 363.853,
|
523 |
+
"eval_steps_per_second": 22.858,
|
524 |
+
"step": 4686
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 34.24,
|
528 |
+
"eval_loss": 0.1865757256746292,
|
529 |
+
"eval_macro_f1": 0.7207303759640109,
|
530 |
+
"eval_macro_precision": 0.7610227795725935,
|
531 |
+
"eval_macro_recall": 0.6996289765073358,
|
532 |
+
"eval_micro_f1": 0.8130245048674052,
|
533 |
+
"eval_micro_precision": 0.8288843258042436,
|
534 |
+
"eval_micro_recall": 0.7977602108036891,
|
535 |
+
"eval_runtime": 2.6701,
|
536 |
+
"eval_samples_per_second": 363.659,
|
537 |
+
"eval_steps_per_second": 22.846,
|
538 |
+
"step": 4828
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 35.25,
|
542 |
+
"eval_loss": 0.19158615171909332,
|
543 |
+
"eval_macro_f1": 0.7231833700345036,
|
544 |
+
"eval_macro_precision": 0.759857266859788,
|
545 |
+
"eval_macro_recall": 0.7038379676451936,
|
546 |
+
"eval_micro_f1": 0.8071928071928073,
|
547 |
+
"eval_micro_precision": 0.8161616161616162,
|
548 |
+
"eval_micro_recall": 0.7984189723320159,
|
549 |
+
"eval_runtime": 2.6696,
|
550 |
+
"eval_samples_per_second": 363.724,
|
551 |
+
"eval_steps_per_second": 22.85,
|
552 |
+
"step": 4970
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 35.46,
|
556 |
+
"learning_rate": 3.185594692814201e-05,
|
557 |
+
"loss": 0.0025,
|
558 |
+
"step": 5000
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 36.26,
|
562 |
+
"eval_loss": 0.18590226769447327,
|
563 |
+
"eval_macro_f1": 0.7370102490601179,
|
564 |
+
"eval_macro_precision": 0.8141501549264045,
|
565 |
+
"eval_macro_recall": 0.7143003391573518,
|
566 |
+
"eval_micro_f1": 0.8030253206182177,
|
567 |
+
"eval_micro_precision": 0.8017071569271176,
|
568 |
+
"eval_micro_recall": 0.8043478260869565,
|
569 |
+
"eval_runtime": 2.6693,
|
570 |
+
"eval_samples_per_second": 363.761,
|
571 |
+
"eval_steps_per_second": 22.852,
|
572 |
+
"step": 5112
|
573 |
+
}
|
574 |
+
],
|
575 |
+
"max_steps": 14100,
|
576 |
+
"num_train_epochs": 100,
|
577 |
+
"total_flos": 1.9741043739581184e+16,
|
578 |
+
"trial_name": null,
|
579 |
+
"trial_params": {
|
580 |
+
"adam_epsilon": 2.7636948844125687e-08,
|
581 |
+
"learning_rate": 4.7699904708006934e-05,
|
582 |
+
"per_device_eval_batch_size": 16,
|
583 |
+
"per_device_train_batch_size": 16,
|
584 |
+
"seed": 320,
|
585 |
+
"warmup_steps": 474,
|
586 |
+
"weight_decay": 0.08343382340090989
|
587 |
+
}
|
588 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad2c884e186c33efca82a69390d8020a7e0d5a1fa537e67f0f88b9f3eb3c34c9
|
3 |
+
size 3439
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|