Upload 10 files
Browse files- config.json +30 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer_config.json +52 -0
- trainer_state.json +933 -0
- training_args.bin +3 -0
- vocab.txt +33 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ambrim/finetuned-epitope_attempt7_150M_200k_default_accuracy_more",
|
3 |
+
"architectures": [
|
4 |
+
"EsmForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_layer_norm_before": false,
|
9 |
+
"esmfold_config": null,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 640,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 2560,
|
15 |
+
"is_folding_model": false,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"mask_token_id": 32,
|
18 |
+
"max_position_embeddings": 1026,
|
19 |
+
"model_type": "esm",
|
20 |
+
"num_attention_heads": 20,
|
21 |
+
"num_hidden_layers": 30,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "rotary",
|
24 |
+
"token_dropout": true,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.36.0",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_list": null,
|
29 |
+
"vocab_size": 33
|
30 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86d3678ccad548f636d1644abbc8cade2bf13b3247d5899a1b43c1428cdc0838
|
3 |
+
size 593608020
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f06d96a8400cff776cdc7f4ce49159836b50ccae84a516166348a3acb84e461
|
3 |
+
size 1182240577
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c94c375fe5ad2903d244ca6b5cc2a1a6cba4c0c26196f3b9cbd9ddd170bb0b8
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:384bf607c3c150887ecedeb07e683fb1d492b749a22d9ccdebef895bf42a652b
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "<cls>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"mask_token": {
|
17 |
+
"content": "<mask>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"pad_token": {
|
24 |
+
"content": "<pad>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "<unk>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<cls>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<eos>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"32": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "<cls>",
|
46 |
+
"eos_token": "<eos>",
|
47 |
+
"mask_token": "<mask>",
|
48 |
+
"model_max_length": 1000000000000000019884624838656,
|
49 |
+
"pad_token": "<pad>",
|
50 |
+
"tokenizer_class": "EsmTokenizer",
|
51 |
+
"unk_token": "<unk>"
|
52 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,933 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9479369602362184,
|
3 |
+
"best_model_checkpoint": "finetuned-epitope_attempt7_150M_200k_default_accuracy_more-finetuned-epitope_attempt8_150M_200k_default_accuracy_mostest/checkpoint-6862",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 68620,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.07,
|
13 |
+
"learning_rate": 9.92713494607986e-05,
|
14 |
+
"loss": 0.0915,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.15,
|
19 |
+
"learning_rate": 9.854269892159721e-05,
|
20 |
+
"loss": 0.109,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.22,
|
25 |
+
"learning_rate": 9.781404838239581e-05,
|
26 |
+
"loss": 0.1101,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.29,
|
31 |
+
"learning_rate": 9.70853978431944e-05,
|
32 |
+
"loss": 0.121,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.36,
|
37 |
+
"learning_rate": 9.635674730399302e-05,
|
38 |
+
"loss": 0.1245,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.44,
|
43 |
+
"learning_rate": 9.562809676479161e-05,
|
44 |
+
"loss": 0.1231,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.51,
|
49 |
+
"learning_rate": 9.489944622559021e-05,
|
50 |
+
"loss": 0.1227,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.58,
|
55 |
+
"learning_rate": 9.417079568638881e-05,
|
56 |
+
"loss": 0.1291,
|
57 |
+
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.66,
|
61 |
+
"learning_rate": 9.34421451471874e-05,
|
62 |
+
"loss": 0.1283,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.73,
|
67 |
+
"learning_rate": 9.271349460798602e-05,
|
68 |
+
"loss": 0.1333,
|
69 |
+
"step": 5000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.8,
|
73 |
+
"learning_rate": 9.198484406878461e-05,
|
74 |
+
"loss": 0.1309,
|
75 |
+
"step": 5500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.87,
|
79 |
+
"learning_rate": 9.125619352958321e-05,
|
80 |
+
"loss": 0.146,
|
81 |
+
"step": 6000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.95,
|
85 |
+
"learning_rate": 9.052754299038182e-05,
|
86 |
+
"loss": 0.1353,
|
87 |
+
"step": 6500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 1.0,
|
91 |
+
"eval_accuracy": 0.9479369602362184,
|
92 |
+
"eval_loss": 0.13793735206127167,
|
93 |
+
"eval_runtime": 153.2159,
|
94 |
+
"eval_samples_per_second": 29.86,
|
95 |
+
"eval_steps_per_second": 4.98,
|
96 |
+
"step": 6862
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 1.02,
|
100 |
+
"learning_rate": 8.979889245118042e-05,
|
101 |
+
"loss": 0.1302,
|
102 |
+
"step": 7000
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 1.09,
|
106 |
+
"learning_rate": 8.907024191197903e-05,
|
107 |
+
"loss": 0.1158,
|
108 |
+
"step": 7500
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 1.17,
|
112 |
+
"learning_rate": 8.834159137277762e-05,
|
113 |
+
"loss": 0.1115,
|
114 |
+
"step": 8000
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.24,
|
118 |
+
"learning_rate": 8.761294083357622e-05,
|
119 |
+
"loss": 0.1123,
|
120 |
+
"step": 8500
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 1.31,
|
124 |
+
"learning_rate": 8.688429029437483e-05,
|
125 |
+
"loss": 0.1219,
|
126 |
+
"step": 9000
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 1.38,
|
130 |
+
"learning_rate": 8.615563975517343e-05,
|
131 |
+
"loss": 0.1192,
|
132 |
+
"step": 9500
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 1.46,
|
136 |
+
"learning_rate": 8.542698921597203e-05,
|
137 |
+
"loss": 0.124,
|
138 |
+
"step": 10000
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 1.53,
|
142 |
+
"learning_rate": 8.469833867677062e-05,
|
143 |
+
"loss": 0.1161,
|
144 |
+
"step": 10500
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 1.6,
|
148 |
+
"learning_rate": 8.396968813756922e-05,
|
149 |
+
"loss": 0.1168,
|
150 |
+
"step": 11000
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 1.68,
|
154 |
+
"learning_rate": 8.324103759836782e-05,
|
155 |
+
"loss": 0.1235,
|
156 |
+
"step": 11500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.75,
|
160 |
+
"learning_rate": 8.251238705916643e-05,
|
161 |
+
"loss": 0.1243,
|
162 |
+
"step": 12000
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 1.82,
|
166 |
+
"learning_rate": 8.178373651996502e-05,
|
167 |
+
"loss": 0.1258,
|
168 |
+
"step": 12500
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 1.89,
|
172 |
+
"learning_rate": 8.105508598076364e-05,
|
173 |
+
"loss": 0.1292,
|
174 |
+
"step": 13000
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.97,
|
178 |
+
"learning_rate": 8.032643544156223e-05,
|
179 |
+
"loss": 0.1243,
|
180 |
+
"step": 13500
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 2.0,
|
184 |
+
"eval_accuracy": 0.9455701299304663,
|
185 |
+
"eval_loss": 0.15209880471229553,
|
186 |
+
"eval_runtime": 153.336,
|
187 |
+
"eval_samples_per_second": 29.836,
|
188 |
+
"eval_steps_per_second": 4.976,
|
189 |
+
"step": 13724
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 2.04,
|
193 |
+
"learning_rate": 7.959778490236083e-05,
|
194 |
+
"loss": 0.1152,
|
195 |
+
"step": 14000
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 2.11,
|
199 |
+
"learning_rate": 7.886913436315944e-05,
|
200 |
+
"loss": 0.0952,
|
201 |
+
"step": 14500
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 2.19,
|
205 |
+
"learning_rate": 7.814048382395804e-05,
|
206 |
+
"loss": 0.0961,
|
207 |
+
"step": 15000
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 2.26,
|
211 |
+
"learning_rate": 7.741183328475663e-05,
|
212 |
+
"loss": 0.1019,
|
213 |
+
"step": 15500
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 2.33,
|
217 |
+
"learning_rate": 7.668318274555523e-05,
|
218 |
+
"loss": 0.1097,
|
219 |
+
"step": 16000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 2.4,
|
223 |
+
"learning_rate": 7.595453220635383e-05,
|
224 |
+
"loss": 0.1091,
|
225 |
+
"step": 16500
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 2.48,
|
229 |
+
"learning_rate": 7.522588166715244e-05,
|
230 |
+
"loss": 0.1067,
|
231 |
+
"step": 17000
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 2.55,
|
235 |
+
"learning_rate": 7.449723112795104e-05,
|
236 |
+
"loss": 0.1112,
|
237 |
+
"step": 17500
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 2.62,
|
241 |
+
"learning_rate": 7.376858058874963e-05,
|
242 |
+
"loss": 0.1119,
|
243 |
+
"step": 18000
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 2.7,
|
247 |
+
"learning_rate": 7.303993004954824e-05,
|
248 |
+
"loss": 0.1117,
|
249 |
+
"step": 18500
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 2.77,
|
253 |
+
"learning_rate": 7.231127951034684e-05,
|
254 |
+
"loss": 0.1112,
|
255 |
+
"step": 19000
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 2.84,
|
259 |
+
"learning_rate": 7.158262897114544e-05,
|
260 |
+
"loss": 0.1125,
|
261 |
+
"step": 19500
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.91,
|
265 |
+
"learning_rate": 7.085397843194405e-05,
|
266 |
+
"loss": 0.1134,
|
267 |
+
"step": 20000
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 2.99,
|
271 |
+
"learning_rate": 7.012532789274264e-05,
|
272 |
+
"loss": 0.1146,
|
273 |
+
"step": 20500
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 3.0,
|
277 |
+
"eval_accuracy": 0.9437319003298592,
|
278 |
+
"eval_loss": 0.1713561713695526,
|
279 |
+
"eval_runtime": 153.3707,
|
280 |
+
"eval_samples_per_second": 29.83,
|
281 |
+
"eval_steps_per_second": 4.975,
|
282 |
+
"step": 20586
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 3.06,
|
286 |
+
"learning_rate": 6.939667735354124e-05,
|
287 |
+
"loss": 0.0969,
|
288 |
+
"step": 21000
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 3.13,
|
292 |
+
"learning_rate": 6.866802681433985e-05,
|
293 |
+
"loss": 0.0846,
|
294 |
+
"step": 21500
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 3.21,
|
298 |
+
"learning_rate": 6.793937627513845e-05,
|
299 |
+
"loss": 0.0911,
|
300 |
+
"step": 22000
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 3.28,
|
304 |
+
"learning_rate": 6.721072573593705e-05,
|
305 |
+
"loss": 0.0915,
|
306 |
+
"step": 22500
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 3.35,
|
310 |
+
"learning_rate": 6.648207519673564e-05,
|
311 |
+
"loss": 0.093,
|
312 |
+
"step": 23000
|
313 |
+
},
|
314 |
+
{
|
315 |
+
"epoch": 3.42,
|
316 |
+
"learning_rate": 6.575342465753424e-05,
|
317 |
+
"loss": 0.095,
|
318 |
+
"step": 23500
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 3.5,
|
322 |
+
"learning_rate": 6.502477411833285e-05,
|
323 |
+
"loss": 0.1049,
|
324 |
+
"step": 24000
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 3.57,
|
328 |
+
"learning_rate": 6.429612357913145e-05,
|
329 |
+
"loss": 0.0957,
|
330 |
+
"step": 24500
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 3.64,
|
334 |
+
"learning_rate": 6.356747303993004e-05,
|
335 |
+
"loss": 0.0982,
|
336 |
+
"step": 25000
|
337 |
+
},
|
338 |
+
{
|
339 |
+
"epoch": 3.72,
|
340 |
+
"learning_rate": 6.283882250072866e-05,
|
341 |
+
"loss": 0.0996,
|
342 |
+
"step": 25500
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 3.79,
|
346 |
+
"learning_rate": 6.211017196152725e-05,
|
347 |
+
"loss": 0.1034,
|
348 |
+
"step": 26000
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"epoch": 3.86,
|
352 |
+
"learning_rate": 6.138152142232586e-05,
|
353 |
+
"loss": 0.0981,
|
354 |
+
"step": 26500
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 3.93,
|
358 |
+
"learning_rate": 6.065287088312446e-05,
|
359 |
+
"loss": 0.1001,
|
360 |
+
"step": 27000
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 4.0,
|
364 |
+
"eval_accuracy": 0.9392775102080849,
|
365 |
+
"eval_loss": 0.19221451878547668,
|
366 |
+
"eval_runtime": 153.3316,
|
367 |
+
"eval_samples_per_second": 29.837,
|
368 |
+
"eval_steps_per_second": 4.976,
|
369 |
+
"step": 27448
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 4.01,
|
373 |
+
"learning_rate": 5.992422034392306e-05,
|
374 |
+
"loss": 0.0978,
|
375 |
+
"step": 27500
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 4.08,
|
379 |
+
"learning_rate": 5.919556980472166e-05,
|
380 |
+
"loss": 0.0833,
|
381 |
+
"step": 28000
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 4.15,
|
385 |
+
"learning_rate": 5.846691926552026e-05,
|
386 |
+
"loss": 0.0839,
|
387 |
+
"step": 28500
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 4.23,
|
391 |
+
"learning_rate": 5.7738268726318855e-05,
|
392 |
+
"loss": 0.0789,
|
393 |
+
"step": 29000
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 4.3,
|
397 |
+
"learning_rate": 5.7009618187117465e-05,
|
398 |
+
"loss": 0.083,
|
399 |
+
"step": 29500
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 4.37,
|
403 |
+
"learning_rate": 5.628096764791606e-05,
|
404 |
+
"loss": 0.0897,
|
405 |
+
"step": 30000
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 4.44,
|
409 |
+
"learning_rate": 5.555231710871466e-05,
|
410 |
+
"loss": 0.0836,
|
411 |
+
"step": 30500
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 4.52,
|
415 |
+
"learning_rate": 5.482366656951326e-05,
|
416 |
+
"loss": 0.0863,
|
417 |
+
"step": 31000
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 4.59,
|
421 |
+
"learning_rate": 5.409501603031186e-05,
|
422 |
+
"loss": 0.0878,
|
423 |
+
"step": 31500
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 4.66,
|
427 |
+
"learning_rate": 5.336636549111047e-05,
|
428 |
+
"loss": 0.0861,
|
429 |
+
"step": 32000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 4.74,
|
433 |
+
"learning_rate": 5.263771495190907e-05,
|
434 |
+
"loss": 0.0955,
|
435 |
+
"step": 32500
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 4.81,
|
439 |
+
"learning_rate": 5.1909064412707665e-05,
|
440 |
+
"loss": 0.0874,
|
441 |
+
"step": 33000
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 4.88,
|
445 |
+
"learning_rate": 5.1180413873506275e-05,
|
446 |
+
"loss": 0.0926,
|
447 |
+
"step": 33500
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 4.95,
|
451 |
+
"learning_rate": 5.045176333430487e-05,
|
452 |
+
"loss": 0.0861,
|
453 |
+
"step": 34000
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 5.0,
|
457 |
+
"eval_accuracy": 0.9366432822800035,
|
458 |
+
"eval_loss": 0.23794159293174744,
|
459 |
+
"eval_runtime": 153.3625,
|
460 |
+
"eval_samples_per_second": 29.831,
|
461 |
+
"eval_steps_per_second": 4.975,
|
462 |
+
"step": 34310
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 5.03,
|
466 |
+
"learning_rate": 4.972311279510347e-05,
|
467 |
+
"loss": 0.0822,
|
468 |
+
"step": 34500
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 5.1,
|
472 |
+
"learning_rate": 4.899446225590207e-05,
|
473 |
+
"loss": 0.0734,
|
474 |
+
"step": 35000
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 5.17,
|
478 |
+
"learning_rate": 4.826581171670067e-05,
|
479 |
+
"loss": 0.0713,
|
480 |
+
"step": 35500
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 5.25,
|
484 |
+
"learning_rate": 4.7537161177499274e-05,
|
485 |
+
"loss": 0.0752,
|
486 |
+
"step": 36000
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 5.32,
|
490 |
+
"learning_rate": 4.680851063829788e-05,
|
491 |
+
"loss": 0.0718,
|
492 |
+
"step": 36500
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 5.39,
|
496 |
+
"learning_rate": 4.6079860099096475e-05,
|
497 |
+
"loss": 0.0772,
|
498 |
+
"step": 37000
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 5.46,
|
502 |
+
"learning_rate": 4.535120955989507e-05,
|
503 |
+
"loss": 0.0823,
|
504 |
+
"step": 37500
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 5.54,
|
508 |
+
"learning_rate": 4.4622559020693675e-05,
|
509 |
+
"loss": 0.075,
|
510 |
+
"step": 38000
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 5.61,
|
514 |
+
"learning_rate": 4.389390848149228e-05,
|
515 |
+
"loss": 0.0805,
|
516 |
+
"step": 38500
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 5.68,
|
520 |
+
"learning_rate": 4.316525794229088e-05,
|
521 |
+
"loss": 0.0825,
|
522 |
+
"step": 39000
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 5.76,
|
526 |
+
"learning_rate": 4.243660740308948e-05,
|
527 |
+
"loss": 0.0799,
|
528 |
+
"step": 39500
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 5.83,
|
532 |
+
"learning_rate": 4.1707956863888084e-05,
|
533 |
+
"loss": 0.0868,
|
534 |
+
"step": 40000
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 5.9,
|
538 |
+
"learning_rate": 4.097930632468668e-05,
|
539 |
+
"loss": 0.0832,
|
540 |
+
"step": 40500
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 5.97,
|
544 |
+
"learning_rate": 4.025065578548528e-05,
|
545 |
+
"loss": 0.0837,
|
546 |
+
"step": 41000
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 6.0,
|
550 |
+
"eval_accuracy": 0.9370614136971593,
|
551 |
+
"eval_loss": 0.23802441358566284,
|
552 |
+
"eval_runtime": 153.3499,
|
553 |
+
"eval_samples_per_second": 29.834,
|
554 |
+
"eval_steps_per_second": 4.976,
|
555 |
+
"step": 41172
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 6.05,
|
559 |
+
"learning_rate": 3.952200524628388e-05,
|
560 |
+
"loss": 0.0715,
|
561 |
+
"step": 41500
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 6.12,
|
565 |
+
"learning_rate": 3.8793354707082485e-05,
|
566 |
+
"loss": 0.0696,
|
567 |
+
"step": 42000
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 6.19,
|
571 |
+
"learning_rate": 3.806470416788109e-05,
|
572 |
+
"loss": 0.0647,
|
573 |
+
"step": 42500
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 6.27,
|
577 |
+
"learning_rate": 3.7336053628679686e-05,
|
578 |
+
"loss": 0.0662,
|
579 |
+
"step": 43000
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 6.34,
|
583 |
+
"learning_rate": 3.660740308947829e-05,
|
584 |
+
"loss": 0.0686,
|
585 |
+
"step": 43500
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 6.41,
|
589 |
+
"learning_rate": 3.587875255027689e-05,
|
590 |
+
"loss": 0.0684,
|
591 |
+
"step": 44000
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 6.48,
|
595 |
+
"learning_rate": 3.515010201107549e-05,
|
596 |
+
"loss": 0.0666,
|
597 |
+
"step": 44500
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 6.56,
|
601 |
+
"learning_rate": 3.442145147187409e-05,
|
602 |
+
"loss": 0.0684,
|
603 |
+
"step": 45000
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 6.63,
|
607 |
+
"learning_rate": 3.369280093267269e-05,
|
608 |
+
"loss": 0.0685,
|
609 |
+
"step": 45500
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 6.7,
|
613 |
+
"learning_rate": 3.2964150393471295e-05,
|
614 |
+
"loss": 0.0772,
|
615 |
+
"step": 46000
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 6.78,
|
619 |
+
"learning_rate": 3.22354998542699e-05,
|
620 |
+
"loss": 0.0746,
|
621 |
+
"step": 46500
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 6.85,
|
625 |
+
"learning_rate": 3.1506849315068496e-05,
|
626 |
+
"loss": 0.0707,
|
627 |
+
"step": 47000
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 6.92,
|
631 |
+
"learning_rate": 3.077819877586709e-05,
|
632 |
+
"loss": 0.0699,
|
633 |
+
"step": 47500
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 7.0,
|
637 |
+
"learning_rate": 3.0049548236665697e-05,
|
638 |
+
"loss": 0.0735,
|
639 |
+
"step": 48000
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 7.0,
|
643 |
+
"eval_accuracy": 0.9368017592492218,
|
644 |
+
"eval_loss": 0.2894147038459778,
|
645 |
+
"eval_runtime": 153.3728,
|
646 |
+
"eval_samples_per_second": 29.829,
|
647 |
+
"eval_steps_per_second": 4.975,
|
648 |
+
"step": 48034
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 7.07,
|
652 |
+
"learning_rate": 2.93208976974643e-05,
|
653 |
+
"loss": 0.0579,
|
654 |
+
"step": 48500
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 7.14,
|
658 |
+
"learning_rate": 2.8592247158262898e-05,
|
659 |
+
"loss": 0.0551,
|
660 |
+
"step": 49000
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 7.21,
|
664 |
+
"learning_rate": 2.7863596619061498e-05,
|
665 |
+
"loss": 0.0637,
|
666 |
+
"step": 49500
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 7.29,
|
670 |
+
"learning_rate": 2.7134946079860102e-05,
|
671 |
+
"loss": 0.0639,
|
672 |
+
"step": 50000
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 7.36,
|
676 |
+
"learning_rate": 2.64062955406587e-05,
|
677 |
+
"loss": 0.0601,
|
678 |
+
"step": 50500
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 7.43,
|
682 |
+
"learning_rate": 2.5677645001457303e-05,
|
683 |
+
"loss": 0.0653,
|
684 |
+
"step": 51000
|
685 |
+
},
|
686 |
+
{
|
687 |
+
"epoch": 7.51,
|
688 |
+
"learning_rate": 2.4948994462255903e-05,
|
689 |
+
"loss": 0.0594,
|
690 |
+
"step": 51500
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 7.58,
|
694 |
+
"learning_rate": 2.4220343923054503e-05,
|
695 |
+
"loss": 0.0642,
|
696 |
+
"step": 52000
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 7.65,
|
700 |
+
"learning_rate": 2.3491693383853107e-05,
|
701 |
+
"loss": 0.0612,
|
702 |
+
"step": 52500
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 7.72,
|
706 |
+
"learning_rate": 2.2763042844651704e-05,
|
707 |
+
"loss": 0.0695,
|
708 |
+
"step": 53000
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 7.8,
|
712 |
+
"learning_rate": 2.2034392305450308e-05,
|
713 |
+
"loss": 0.0614,
|
714 |
+
"step": 53500
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 7.87,
|
718 |
+
"learning_rate": 2.130574176624891e-05,
|
719 |
+
"loss": 0.0634,
|
720 |
+
"step": 54000
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 7.94,
|
724 |
+
"learning_rate": 2.057709122704751e-05,
|
725 |
+
"loss": 0.0623,
|
726 |
+
"step": 54500
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"epoch": 8.0,
|
730 |
+
"eval_accuracy": 0.9354890330840031,
|
731 |
+
"eval_loss": 0.30701231956481934,
|
732 |
+
"eval_runtime": 153.4064,
|
733 |
+
"eval_samples_per_second": 29.823,
|
734 |
+
"eval_steps_per_second": 4.974,
|
735 |
+
"step": 54896
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 8.02,
|
739 |
+
"learning_rate": 1.984844068784611e-05,
|
740 |
+
"loss": 0.0671,
|
741 |
+
"step": 55000
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 8.09,
|
745 |
+
"learning_rate": 1.9119790148644713e-05,
|
746 |
+
"loss": 0.0514,
|
747 |
+
"step": 55500
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 8.16,
|
751 |
+
"learning_rate": 1.839113960944331e-05,
|
752 |
+
"loss": 0.0537,
|
753 |
+
"step": 56000
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 8.23,
|
757 |
+
"learning_rate": 1.7662489070241914e-05,
|
758 |
+
"loss": 0.0543,
|
759 |
+
"step": 56500
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 8.31,
|
763 |
+
"learning_rate": 1.6933838531040514e-05,
|
764 |
+
"loss": 0.0553,
|
765 |
+
"step": 57000
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 8.38,
|
769 |
+
"learning_rate": 1.6205187991839114e-05,
|
770 |
+
"loss": 0.0558,
|
771 |
+
"step": 57500
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 8.45,
|
775 |
+
"learning_rate": 1.5476537452637715e-05,
|
776 |
+
"loss": 0.0545,
|
777 |
+
"step": 58000
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 8.53,
|
781 |
+
"learning_rate": 1.4747886913436319e-05,
|
782 |
+
"loss": 0.0593,
|
783 |
+
"step": 58500
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 8.6,
|
787 |
+
"learning_rate": 1.4019236374234917e-05,
|
788 |
+
"loss": 0.0601,
|
789 |
+
"step": 59000
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 8.67,
|
793 |
+
"learning_rate": 1.3290585835033518e-05,
|
794 |
+
"loss": 0.053,
|
795 |
+
"step": 59500
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 8.74,
|
799 |
+
"learning_rate": 1.256193529583212e-05,
|
800 |
+
"loss": 0.0552,
|
801 |
+
"step": 60000
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 8.82,
|
805 |
+
"learning_rate": 1.183328475663072e-05,
|
806 |
+
"loss": 0.0565,
|
807 |
+
"step": 60500
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 8.89,
|
811 |
+
"learning_rate": 1.1104634217429322e-05,
|
812 |
+
"loss": 0.0545,
|
813 |
+
"step": 61000
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 8.96,
|
817 |
+
"learning_rate": 1.0375983678227923e-05,
|
818 |
+
"loss": 0.0535,
|
819 |
+
"step": 61500
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 9.0,
|
823 |
+
"eval_accuracy": 0.9346114733196021,
|
824 |
+
"eval_loss": 0.3566416800022125,
|
825 |
+
"eval_runtime": 153.4241,
|
826 |
+
"eval_samples_per_second": 29.819,
|
827 |
+
"eval_steps_per_second": 4.973,
|
828 |
+
"step": 61758
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 9.04,
|
832 |
+
"learning_rate": 9.647333139026523e-06,
|
833 |
+
"loss": 0.0533,
|
834 |
+
"step": 62000
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 9.11,
|
838 |
+
"learning_rate": 8.918682599825125e-06,
|
839 |
+
"loss": 0.0496,
|
840 |
+
"step": 62500
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"epoch": 9.18,
|
844 |
+
"learning_rate": 8.190032060623726e-06,
|
845 |
+
"loss": 0.0455,
|
846 |
+
"step": 63000
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"epoch": 9.25,
|
850 |
+
"learning_rate": 7.461381521422327e-06,
|
851 |
+
"loss": 0.047,
|
852 |
+
"step": 63500
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 9.33,
|
856 |
+
"learning_rate": 6.732730982220928e-06,
|
857 |
+
"loss": 0.0467,
|
858 |
+
"step": 64000
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 9.4,
|
862 |
+
"learning_rate": 6.0040804430195285e-06,
|
863 |
+
"loss": 0.0466,
|
864 |
+
"step": 64500
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 9.47,
|
868 |
+
"learning_rate": 5.275429903818129e-06,
|
869 |
+
"loss": 0.0456,
|
870 |
+
"step": 65000
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 9.55,
|
874 |
+
"learning_rate": 4.54677936461673e-06,
|
875 |
+
"loss": 0.0516,
|
876 |
+
"step": 65500
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 9.62,
|
880 |
+
"learning_rate": 3.818128825415331e-06,
|
881 |
+
"loss": 0.0531,
|
882 |
+
"step": 66000
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 9.69,
|
886 |
+
"learning_rate": 3.0894782862139318e-06,
|
887 |
+
"loss": 0.0507,
|
888 |
+
"step": 66500
|
889 |
+
},
|
890 |
+
{
|
891 |
+
"epoch": 9.76,
|
892 |
+
"learning_rate": 2.360827747012533e-06,
|
893 |
+
"loss": 0.0501,
|
894 |
+
"step": 67000
|
895 |
+
},
|
896 |
+
{
|
897 |
+
"epoch": 9.84,
|
898 |
+
"learning_rate": 1.632177207811134e-06,
|
899 |
+
"loss": 0.0505,
|
900 |
+
"step": 67500
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 9.91,
|
904 |
+
"learning_rate": 9.035266686097348e-07,
|
905 |
+
"loss": 0.0491,
|
906 |
+
"step": 68000
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 9.98,
|
910 |
+
"learning_rate": 1.7487612940833577e-07,
|
911 |
+
"loss": 0.0483,
|
912 |
+
"step": 68500
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 10.0,
|
916 |
+
"eval_accuracy": 0.9332295747964836,
|
917 |
+
"eval_loss": 0.41370126605033875,
|
918 |
+
"eval_runtime": 153.4718,
|
919 |
+
"eval_samples_per_second": 29.81,
|
920 |
+
"eval_steps_per_second": 4.972,
|
921 |
+
"step": 68620
|
922 |
+
}
|
923 |
+
],
|
924 |
+
"logging_steps": 500,
|
925 |
+
"max_steps": 68620,
|
926 |
+
"num_input_tokens_seen": 0,
|
927 |
+
"num_train_epochs": 10,
|
928 |
+
"save_steps": 500,
|
929 |
+
"total_flos": 2.750401151541956e+17,
|
930 |
+
"train_batch_size": 6,
|
931 |
+
"trial_name": null,
|
932 |
+
"trial_params": null
|
933 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a935ff0efd6ea27ff3615bcbc28258efbb58fae131ee39f17cf7193886cc083
|
3 |
+
size 4920
|
vocab.txt
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<cls>
|
2 |
+
<pad>
|
3 |
+
<eos>
|
4 |
+
<unk>
|
5 |
+
L
|
6 |
+
A
|
7 |
+
G
|
8 |
+
V
|
9 |
+
S
|
10 |
+
E
|
11 |
+
R
|
12 |
+
T
|
13 |
+
I
|
14 |
+
D
|
15 |
+
P
|
16 |
+
K
|
17 |
+
Q
|
18 |
+
N
|
19 |
+
F
|
20 |
+
Y
|
21 |
+
M
|
22 |
+
H
|
23 |
+
W
|
24 |
+
C
|
25 |
+
X
|
26 |
+
B
|
27 |
+
U
|
28 |
+
Z
|
29 |
+
O
|
30 |
+
.
|
31 |
+
-
|
32 |
+
<null_1>
|
33 |
+
<mask>
|