Upload 12 files
Browse files- config.json +60 -0
- generation_config.json +7 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +111 -0
- trainer_state.json +216 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-large",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 4096,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 1024,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "relu",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "relu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": false,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"n_positions": 512,
|
20 |
+
"num_decoder_layers": 24,
|
21 |
+
"num_heads": 16,
|
22 |
+
"num_layers": 24,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
+
"relative_attention_num_buckets": 32,
|
27 |
+
"task_specific_params": {
|
28 |
+
"summarization": {
|
29 |
+
"early_stopping": true,
|
30 |
+
"length_penalty": 2.0,
|
31 |
+
"max_length": 200,
|
32 |
+
"min_length": 30,
|
33 |
+
"no_repeat_ngram_size": 3,
|
34 |
+
"num_beams": 4,
|
35 |
+
"prefix": "summarize: "
|
36 |
+
},
|
37 |
+
"translation_en_to_de": {
|
38 |
+
"early_stopping": true,
|
39 |
+
"max_length": 300,
|
40 |
+
"num_beams": 4,
|
41 |
+
"prefix": "translate English to German: "
|
42 |
+
},
|
43 |
+
"translation_en_to_fr": {
|
44 |
+
"early_stopping": true,
|
45 |
+
"max_length": 300,
|
46 |
+
"num_beams": 4,
|
47 |
+
"prefix": "translate English to French: "
|
48 |
+
},
|
49 |
+
"translation_en_to_ro": {
|
50 |
+
"early_stopping": true,
|
51 |
+
"max_length": 300,
|
52 |
+
"num_beams": 4,
|
53 |
+
"prefix": "translate English to Romanian: "
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.31.0",
|
58 |
+
"use_cache": false,
|
59 |
+
"vocab_size": 32128
|
60 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.31.0"
|
7 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22d4e81bcdbae177c2bf498faaf54bb13e2fc0206506ccc634548e4844605dae
|
3 |
+
size 5901652619
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81ac302d36a72ee2d2a6066a3af38a32c7de5fc17c66069f485916aaacf61602
|
3 |
+
size 2950848513
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f421b962bac1131d9fdac9ac14532dde984b7171f28684e46375bff32f0fb237
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3a656775ee44121adc5b25a9532f7adfc38818aa7765b8bb73b97f4f0541457
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
107 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"clean_up_tokenization_spaces": true,
|
105 |
+
"eos_token": "</s>",
|
106 |
+
"extra_ids": 100,
|
107 |
+
"model_max_length": 512,
|
108 |
+
"pad_token": "<pad>",
|
109 |
+
"tokenizer_class": "T5Tokenizer",
|
110 |
+
"unk_token": "<unk>"
|
111 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,216 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4766906339372134,
|
3 |
+
"best_model_checkpoint": "trained_models/training_1696386400_imdb_t5-large/model/checkpoint-1250",
|
4 |
+
"epoch": 8.0,
|
5 |
+
"global_step": 10000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.4,
|
12 |
+
"learning_rate": 0.0002,
|
13 |
+
"loss": 2.2083,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.8,
|
18 |
+
"learning_rate": 0.0004,
|
19 |
+
"loss": 0.0893,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.0,
|
24 |
+
"eval_acc": 0.9126,
|
25 |
+
"eval_f1": 0.4766906339372134,
|
26 |
+
"eval_loss": 0.08332405984401703,
|
27 |
+
"eval_runtime": 2242.501,
|
28 |
+
"eval_samples_per_second": 11.148,
|
29 |
+
"eval_steps_per_second": 1.394,
|
30 |
+
"step": 1250
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.2,
|
34 |
+
"learning_rate": 0.0006,
|
35 |
+
"loss": 0.1071,
|
36 |
+
"step": 1500
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 1.6,
|
40 |
+
"learning_rate": 0.0008,
|
41 |
+
"loss": 0.1357,
|
42 |
+
"step": 2000
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 2.0,
|
46 |
+
"learning_rate": 0.001,
|
47 |
+
"loss": 0.1427,
|
48 |
+
"step": 2500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.0,
|
52 |
+
"eval_acc": 0.8804,
|
53 |
+
"eval_f1": 0.4681979775093732,
|
54 |
+
"eval_loss": 0.1213899627327919,
|
55 |
+
"eval_runtime": 2199.3043,
|
56 |
+
"eval_samples_per_second": 11.367,
|
57 |
+
"eval_steps_per_second": 1.421,
|
58 |
+
"step": 2500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 2.4,
|
62 |
+
"learning_rate": 0.0009777777777777777,
|
63 |
+
"loss": 0.1386,
|
64 |
+
"step": 3000
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 2.8,
|
68 |
+
"learning_rate": 0.0009555555555555556,
|
69 |
+
"loss": 0.1408,
|
70 |
+
"step": 3500
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 3.0,
|
74 |
+
"eval_acc": 0.90072,
|
75 |
+
"eval_f1": 0.47388185764694557,
|
76 |
+
"eval_loss": 0.10105577856302261,
|
77 |
+
"eval_runtime": 2213.3186,
|
78 |
+
"eval_samples_per_second": 11.295,
|
79 |
+
"eval_steps_per_second": 1.412,
|
80 |
+
"step": 3750
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 3.2,
|
84 |
+
"learning_rate": 0.0009333333333333333,
|
85 |
+
"loss": 0.1132,
|
86 |
+
"step": 4000
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 3.6,
|
90 |
+
"learning_rate": 0.0009111111111111111,
|
91 |
+
"loss": 0.1031,
|
92 |
+
"step": 4500
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 4.0,
|
96 |
+
"learning_rate": 0.0008888888888888888,
|
97 |
+
"loss": 0.1014,
|
98 |
+
"step": 5000
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 4.0,
|
102 |
+
"eval_acc": 0.87984,
|
103 |
+
"eval_f1": 0.4667470127189438,
|
104 |
+
"eval_loss": 0.10490511357784271,
|
105 |
+
"eval_runtime": 2197.6464,
|
106 |
+
"eval_samples_per_second": 11.376,
|
107 |
+
"eval_steps_per_second": 1.422,
|
108 |
+
"step": 5000
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 4.4,
|
112 |
+
"learning_rate": 0.0008666666666666667,
|
113 |
+
"loss": 0.0786,
|
114 |
+
"step": 5500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 4.8,
|
118 |
+
"learning_rate": 0.0008444444444444444,
|
119 |
+
"loss": 0.0884,
|
120 |
+
"step": 6000
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 5.0,
|
124 |
+
"eval_acc": 0.86384,
|
125 |
+
"eval_f1": 0.4614100111141227,
|
126 |
+
"eval_loss": 0.1329798400402069,
|
127 |
+
"eval_runtime": 2272.8013,
|
128 |
+
"eval_samples_per_second": 11.0,
|
129 |
+
"eval_steps_per_second": 1.375,
|
130 |
+
"step": 6250
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 5.2,
|
134 |
+
"learning_rate": 0.0008222222222222222,
|
135 |
+
"loss": 0.0797,
|
136 |
+
"step": 6500
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 5.6,
|
140 |
+
"learning_rate": 0.0008,
|
141 |
+
"loss": 0.078,
|
142 |
+
"step": 7000
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 6.0,
|
146 |
+
"learning_rate": 0.0007777777777777778,
|
147 |
+
"loss": 0.0787,
|
148 |
+
"step": 7500
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 6.0,
|
152 |
+
"eval_acc": 0.88716,
|
153 |
+
"eval_f1": 0.4692667461450598,
|
154 |
+
"eval_loss": 0.10306421667337418,
|
155 |
+
"eval_runtime": 2288.8555,
|
156 |
+
"eval_samples_per_second": 10.922,
|
157 |
+
"eval_steps_per_second": 1.365,
|
158 |
+
"step": 7500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 6.4,
|
162 |
+
"learning_rate": 0.0007555555555555555,
|
163 |
+
"loss": 0.0599,
|
164 |
+
"step": 8000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 6.8,
|
168 |
+
"learning_rate": 0.0007333333333333333,
|
169 |
+
"loss": 0.0662,
|
170 |
+
"step": 8500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 7.0,
|
174 |
+
"eval_acc": 0.8984,
|
175 |
+
"eval_f1": 0.4730434700951143,
|
176 |
+
"eval_loss": 0.10054909437894821,
|
177 |
+
"eval_runtime": 2312.3779,
|
178 |
+
"eval_samples_per_second": 10.811,
|
179 |
+
"eval_steps_per_second": 1.351,
|
180 |
+
"step": 8750
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 7.2,
|
184 |
+
"learning_rate": 0.0007111111111111111,
|
185 |
+
"loss": 0.057,
|
186 |
+
"step": 9000
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 7.6,
|
190 |
+
"learning_rate": 0.000688888888888889,
|
191 |
+
"loss": 0.0553,
|
192 |
+
"step": 9500
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 8.0,
|
196 |
+
"learning_rate": 0.0006666666666666666,
|
197 |
+
"loss": 0.0637,
|
198 |
+
"step": 10000
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 8.0,
|
202 |
+
"eval_acc": 0.903,
|
203 |
+
"eval_f1": 0.47421149544208796,
|
204 |
+
"eval_loss": 0.0991751179099083,
|
205 |
+
"eval_runtime": 2251.6698,
|
206 |
+
"eval_samples_per_second": 11.103,
|
207 |
+
"eval_steps_per_second": 1.388,
|
208 |
+
"step": 10000
|
209 |
+
}
|
210 |
+
],
|
211 |
+
"max_steps": 25000,
|
212 |
+
"num_train_epochs": 20,
|
213 |
+
"total_flos": 3.4640756736e+17,
|
214 |
+
"trial_name": null,
|
215 |
+
"trial_params": null
|
216 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ee3c5c959654c53ad12fd3ef78102777544b84e11a319325df0e5bf04fdc83b
|
3 |
+
size 4283
|