Hugging Face's logo

kayrab
/
doktor-llama-3-cosmos-8b-lora

Question Answering
Transformers
Safetensors
Turkish
unsloth
llama
trl
sft
turkish
Model card Files Community
kayrab commited on
Commit
82f0c07
·
verified ·
1 Parent(s): 9a07f74

log formatlandı

Browse files
Files changed (1) hide show
  1. training_log.json +146 -1
training_log.json CHANGED
@@ -1 +1,146 @@
1
- [{"loss": 1.8184, "grad_norm": 0.774284303188324, "learning_rate": 8.923190911336132e-05, "epoch": 0.2218976306523778, "step": 451}, {"eval_loss": 1.749639630317688, "eval_runtime": 1083.3199, "eval_samples_per_second": 26.684, "eval_steps_per_second": 6.671, "epoch": 0.2218976306523778, "step": 451}, {"loss": 1.7064, "grad_norm": 0.7226008772850037, "learning_rate": 7.809335638429242e-05, "epoch": 0.4437952613047556, "step": 902}, {"eval_loss": 1.6820720434188843, "eval_runtime": 1087.8354, "eval_samples_per_second": 26.573, "eval_steps_per_second": 6.643, "epoch": 0.4437952613047556, "step": 902}, {"loss": 1.6623, "grad_norm": 0.7210889458656311, "learning_rate": 6.695480365522352e-05, "epoch": 0.6656928919571334, "step": 1353}, {"eval_loss": 1.6484241485595703, "eval_runtime": 1084.0066, "eval_samples_per_second": 26.667, "eval_steps_per_second": 6.667, "epoch": 0.6656928919571334, "step": 1353}, {"loss": 1.6362, "grad_norm": 0.7425829172134399, "learning_rate": 5.581625092615461e-05, "epoch": 0.8875905226095112, "step": 1804}, {"eval_loss": 1.6261749267578125, "eval_runtime": 1085.6726, "eval_samples_per_second": 26.626, "eval_steps_per_second": 6.657, "epoch": 0.8875905226095112, "step": 1804}, {"loss": 1.5914, "grad_norm": 0.7476176023483276, "learning_rate": 4.4677698197085704e-05, "epoch": 1.109488153261889, "step": 2255}, {"eval_loss": 1.6124544143676758, "eval_runtime": 1084.6953, "eval_samples_per_second": 26.65, "eval_steps_per_second": 6.663, "epoch": 1.109488153261889, "step": 2255}, {"loss": 1.5557, "grad_norm": 0.7473255395889282, "learning_rate": 3.3539145468016795e-05, "epoch": 1.3313857839142669, "step": 2706}, {"eval_loss": 1.6011990308761597, "eval_runtime": 1084.5737, "eval_samples_per_second": 26.653, "eval_steps_per_second": 6.663, "epoch": 1.3313857839142669, "step": 2706}, {"loss": 1.5468, "grad_norm": 0.750347375869751, "learning_rate": 2.240059273894789e-05, "epoch": 1.5532834145666445, "step": 3157}, {"eval_loss": 1.592125415802002, "eval_runtime": 1086.1382, "eval_samples_per_second": 26.614, "eval_steps_per_second": 6.654, "epoch": 1.5532834145666445, "step": 3157}, {"loss": 1.539, "grad_norm": 0.7452530860900879, "learning_rate": 1.1262040009878982e-05, "epoch": 1.7751810452190224, "step": 3608}, {"eval_loss": 1.5855711698532104, "eval_runtime": 1084.064, "eval_samples_per_second": 26.665, "eval_steps_per_second": 6.667, "epoch": 1.7751810452190224, "step": 3608}, {"loss": 1.5373, "grad_norm": 0.7762174606323242, "learning_rate": 1.2348728081007656e-07, "epoch": 1.9970786758714003, "step": 4059}, {"eval_loss": 1.5827687978744507, "eval_runtime": 1086.4478, "eval_samples_per_second": 26.607, "eval_steps_per_second": 6.652, "epoch": 1.9970786758714003, "step": 4059}, {"train_runtime": 69830.4547, "train_samples_per_second": 7.451, "train_steps_per_second": 0.058, "total_flos": 9.47865607059515e+18, "train_loss": 1.5162640926171476, "epoch": 1.9995387382954841, "step": 4064}]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "loss": 1.8184,
4
+ "grad_norm": 0.774284303188324,
5
+ "learning_rate": 8.923190911336132e-05,
6
+ "epoch": 0.2218976306523778,
7
+ "step": 451
8
+ },
9
+ {
10
+ "eval_loss": 1.749639630317688,
11
+ "eval_runtime": 1083.3199,
12
+ "eval_samples_per_second": 26.684,
13
+ "eval_steps_per_second": 6.671,
14
+ "epoch": 0.2218976306523778,
15
+ "step": 451
16
+ },
17
+ {
18
+ "loss": 1.7064,
19
+ "grad_norm": 0.7226008772850037,
20
+ "learning_rate": 7.809335638429242e-05,
21
+ "epoch": 0.4437952613047556,
22
+ "step": 902
23
+ },
24
+ {
25
+ "eval_loss": 1.6820720434188843,
26
+ "eval_runtime": 1087.8354,
27
+ "eval_samples_per_second": 26.573,
28
+ "eval_steps_per_second": 6.643,
29
+ "epoch": 0.4437952613047556,
30
+ "step": 902
31
+ },
32
+ {
33
+ "loss": 1.6623,
34
+ "grad_norm": 0.7210889458656311,
35
+ "learning_rate": 6.695480365522352e-05,
36
+ "epoch": 0.6656928919571334,
37
+ "step": 1353
38
+ },
39
+ {
40
+ "eval_loss": 1.6484241485595703,
41
+ "eval_runtime": 1084.0066,
42
+ "eval_samples_per_second": 26.667,
43
+ "eval_steps_per_second": 6.667,
44
+ "epoch": 0.6656928919571334,
45
+ "step": 1353
46
+ },
47
+ {
48
+ "loss": 1.6362,
49
+ "grad_norm": 0.7425829172134399,
50
+ "learning_rate": 5.581625092615461e-05,
51
+ "epoch": 0.8875905226095112,
52
+ "step": 1804
53
+ },
54
+ {
55
+ "eval_loss": 1.6261749267578125,
56
+ "eval_runtime": 1085.6726,
57
+ "eval_samples_per_second": 26.626,
58
+ "eval_steps_per_second": 6.657,
59
+ "epoch": 0.8875905226095112,
60
+ "step": 1804
61
+ },
62
+ {
63
+ "loss": 1.5914,
64
+ "grad_norm": 0.7476176023483276,
65
+ "learning_rate": 4.4677698197085704e-05,
66
+ "epoch": 1.109488153261889,
67
+ "step": 2255
68
+ },
69
+ {
70
+ "eval_loss": 1.6124544143676758,
71
+ "eval_runtime": 1084.6953,
72
+ "eval_samples_per_second": 26.65,
73
+ "eval_steps_per_second": 6.663,
74
+ "epoch": 1.109488153261889,
75
+ "step": 2255
76
+ },
77
+ {
78
+ "loss": 1.5557,
79
+ "grad_norm": 0.7473255395889282,
80
+ "learning_rate": 3.3539145468016795e-05,
81
+ "epoch": 1.3313857839142669,
82
+ "step": 2706
83
+ },
84
+ {
85
+ "eval_loss": 1.6011990308761597,
86
+ "eval_runtime": 1084.5737,
87
+ "eval_samples_per_second": 26.653,
88
+ "eval_steps_per_second": 6.663,
89
+ "epoch": 1.3313857839142669,
90
+ "step": 2706
91
+ },
92
+ {
93
+ "loss": 1.5468,
94
+ "grad_norm": 0.750347375869751,
95
+ "learning_rate": 2.240059273894789e-05,
96
+ "epoch": 1.5532834145666445,
97
+ "step": 3157
98
+ },
99
+ {
100
+ "eval_loss": 1.592125415802002,
101
+ "eval_runtime": 1086.1382,
102
+ "eval_samples_per_second": 26.614,
103
+ "eval_steps_per_second": 6.654,
104
+ "epoch": 1.5532834145666445,
105
+ "step": 3157
106
+ },
107
+ {
108
+ "loss": 1.539,
109
+ "grad_norm": 0.7452530860900879,
110
+ "learning_rate": 1.1262040009878982e-05,
111
+ "epoch": 1.7751810452190224,
112
+ "step": 3608
113
+ },
114
+ {
115
+ "eval_loss": 1.5855711698532104,
116
+ "eval_runtime": 1084.064,
117
+ "eval_samples_per_second": 26.665,
118
+ "eval_steps_per_second": 6.667,
119
+ "epoch": 1.7751810452190224,
120
+ "step": 3608
121
+ },
122
+ {
123
+ "loss": 1.5373,
124
+ "grad_norm": 0.7762174606323242,
125
+ "learning_rate": 1.2348728081007656e-07,
126
+ "epoch": 1.9970786758714003,
127
+ "step": 4059
128
+ },
129
+ {
130
+ "eval_loss": 1.5827687978744507,
131
+ "eval_runtime": 1086.4478,
132
+ "eval_samples_per_second": 26.607,
133
+ "eval_steps_per_second": 6.652,
134
+ "epoch": 1.9970786758714003,
135
+ "step": 4059
136
+ },
137
+ {
138
+ "train_runtime": 69830.4547,
139
+ "train_samples_per_second": 7.451,
140
+ "train_steps_per_second": 0.058,
141
+ "total_flos": 9.47865607059515e+18,
142
+ "train_loss": 1.5162640926171476,
143
+ "epoch": 1.9995387382954841,
144
+ "step": 4064
145
+ }
146
+ ]