Muhammad Khalifa
commited on
Commit
•
ef20f9a
1
Parent(s):
d8ed1b7
first commit
Browse files- added_tokens.json +6 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +109 -0
- spiece.model +3 -0
- tokenizer_config.json +112 -0
- trainer_state.json +220 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<<": 32100,
|
3 |
+
">>": 32101,
|
4 |
+
"[CLS]": 32102,
|
5 |
+
"[SEP]": 32103
|
6 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed08219fa4b435aad8beae973823777a0d60fc050c6c907002530fddb3fc1787
|
3 |
+
size 3136877397
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:079c394b9cb260664e329f2b4816e7491246e0e9e0d68195b815302f1f211dda
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:089f904acfaab3e94abaec03f8ee431b6c4b483170ce8dea4718926b001f62eb
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"cls_token": "[CLS]",
|
105 |
+
"eos_token": "</s>",
|
106 |
+
"pad_token": "<pad>",
|
107 |
+
"sep_token": "[SEP]",
|
108 |
+
"unk_token": "<unk>"
|
109 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer_config.json
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"sp_model_kwargs": {},
|
110 |
+
"tokenizer_class": "T5Tokenizer",
|
111 |
+
"unk_token": "<unk>"
|
112 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.28675174713134766,
|
3 |
+
"best_model_checkpoint": "ckpts/discrim/contrastive_models/gen.llama-7b/flan_t5_large_coin_flip_100K_simcse_fixed_align/checkpoint-1500",
|
4 |
+
"epoch": 1.337196344996657,
|
5 |
+
"global_step": 1500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.04,
|
12 |
+
"learning_rate": 4.457652303120357e-06,
|
13 |
+
"loss": 0.9997,
|
14 |
+
"step": 50
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.09,
|
18 |
+
"learning_rate": 8.915304606240713e-06,
|
19 |
+
"loss": 0.9994,
|
20 |
+
"step": 100
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.13,
|
24 |
+
"learning_rate": 1.337295690936107e-05,
|
25 |
+
"loss": 0.9958,
|
26 |
+
"step": 150
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.18,
|
30 |
+
"learning_rate": 1.7830609212481426e-05,
|
31 |
+
"loss": 0.9517,
|
32 |
+
"step": 200
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.22,
|
36 |
+
"learning_rate": 2.2288261515601784e-05,
|
37 |
+
"loss": 0.7892,
|
38 |
+
"step": 250
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.27,
|
42 |
+
"learning_rate": 2.674591381872214e-05,
|
43 |
+
"loss": 0.7113,
|
44 |
+
"step": 300
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.31,
|
48 |
+
"learning_rate": 3.12035661218425e-05,
|
49 |
+
"loss": 0.6393,
|
50 |
+
"step": 350
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.36,
|
54 |
+
"learning_rate": 3.566121842496285e-05,
|
55 |
+
"loss": 0.6115,
|
56 |
+
"step": 400
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.4,
|
60 |
+
"learning_rate": 4.011887072808321e-05,
|
61 |
+
"loss": 0.5684,
|
62 |
+
"step": 450
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.45,
|
66 |
+
"learning_rate": 4.457652303120357e-05,
|
67 |
+
"loss": 0.4807,
|
68 |
+
"step": 500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.45,
|
72 |
+
"eval_loss": 0.39063507318496704,
|
73 |
+
"eval_runtime": 46.0326,
|
74 |
+
"eval_samples_per_second": 132.819,
|
75 |
+
"eval_steps_per_second": 16.619,
|
76 |
+
"step": 500
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.49,
|
80 |
+
"learning_rate": 4.903417533432392e-05,
|
81 |
+
"loss": 0.4024,
|
82 |
+
"step": 550
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.53,
|
86 |
+
"learning_rate": 5.349182763744428e-05,
|
87 |
+
"loss": 0.3846,
|
88 |
+
"step": 600
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.58,
|
92 |
+
"learning_rate": 5.794947994056464e-05,
|
93 |
+
"loss": 0.336,
|
94 |
+
"step": 650
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.62,
|
98 |
+
"learning_rate": 5.9999027964273596e-05,
|
99 |
+
"loss": 0.3333,
|
100 |
+
"step": 700
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.67,
|
104 |
+
"learning_rate": 5.9992094680623114e-05,
|
105 |
+
"loss": 0.3155,
|
106 |
+
"step": 750
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.71,
|
110 |
+
"learning_rate": 5.9978496329511386e-05,
|
111 |
+
"loss": 0.3047,
|
112 |
+
"step": 800
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.76,
|
116 |
+
"learning_rate": 5.995823593286565e-05,
|
117 |
+
"loss": 0.257,
|
118 |
+
"step": 850
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.8,
|
122 |
+
"learning_rate": 5.993131799310269e-05,
|
123 |
+
"loss": 0.2651,
|
124 |
+
"step": 900
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 0.85,
|
128 |
+
"learning_rate": 5.989774849212826e-05,
|
129 |
+
"loss": 0.2447,
|
130 |
+
"step": 950
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.89,
|
134 |
+
"learning_rate": 5.9857534890007815e-05,
|
135 |
+
"loss": 0.2189,
|
136 |
+
"step": 1000
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.89,
|
140 |
+
"eval_loss": 0.30103570222854614,
|
141 |
+
"eval_runtime": 46.0873,
|
142 |
+
"eval_samples_per_second": 132.661,
|
143 |
+
"eval_steps_per_second": 16.599,
|
144 |
+
"step": 1000
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.94,
|
148 |
+
"learning_rate": 5.981068612330859e-05,
|
149 |
+
"loss": 0.2223,
|
150 |
+
"step": 1050
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.98,
|
154 |
+
"learning_rate": 5.975721260311371e-05,
|
155 |
+
"loss": 0.21,
|
156 |
+
"step": 1100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.03,
|
160 |
+
"learning_rate": 5.969712621270851e-05,
|
161 |
+
"loss": 0.1952,
|
162 |
+
"step": 1150
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 1.07,
|
166 |
+
"learning_rate": 5.963044030493981e-05,
|
167 |
+
"loss": 0.2101,
|
168 |
+
"step": 1200
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 1.11,
|
172 |
+
"learning_rate": 5.955716969924848e-05,
|
173 |
+
"loss": 0.1969,
|
174 |
+
"step": 1250
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 1.16,
|
178 |
+
"learning_rate": 5.947733067837621e-05,
|
179 |
+
"loss": 0.1706,
|
180 |
+
"step": 1300
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 1.2,
|
184 |
+
"learning_rate": 5.939094098474696e-05,
|
185 |
+
"loss": 0.1491,
|
186 |
+
"step": 1350
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 1.25,
|
190 |
+
"learning_rate": 5.929801981652421e-05,
|
191 |
+
"loss": 0.1209,
|
192 |
+
"step": 1400
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 1.29,
|
196 |
+
"learning_rate": 5.9198587823344496e-05,
|
197 |
+
"loss": 0.1119,
|
198 |
+
"step": 1450
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.34,
|
202 |
+
"learning_rate": 5.909266710172858e-05,
|
203 |
+
"loss": 0.1188,
|
204 |
+
"step": 1500
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 1.34,
|
208 |
+
"eval_loss": 0.28675174713134766,
|
209 |
+
"eval_runtime": 46.0465,
|
210 |
+
"eval_samples_per_second": 132.779,
|
211 |
+
"eval_steps_per_second": 16.614,
|
212 |
+
"step": 1500
|
213 |
+
}
|
214 |
+
],
|
215 |
+
"max_steps": 11210,
|
216 |
+
"num_train_epochs": 10,
|
217 |
+
"total_flos": 0.0,
|
218 |
+
"trial_name": null,
|
219 |
+
"trial_params": null
|
220 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2161fc66d59a1d956a1e73f931ba2e6e2e476020cf5bf7cd03fbf16fd014517a
|
3 |
+
size 3835
|