Hugging Face's logo

Teddysum
/
bllossom-polyglot-12.8b-lima-ko-adapter-4bit

Generated from Trainer
Model card Files Community
ybjeong commited on
Commit
bb196a0
•
1 Parent(s): 7659f0f

End of training

Browse files
Files changed (5) hide show
  1. README.md +32 -0
  2. all_results.json +7 -0
  3. completed +0 -0
  4. train_results.json +7 -0
  5. trainer_state.json +145 -0
README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: True
27
+ - bnb_4bit_compute_dtype: bfloat16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0.dev0
31
+
32
+ - PEFT 0.4.0.dev0
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.27,
3
+ "train_loss": 1.5663859701156617,
4
+ "train_runtime": 4414.9851,
5
+ "train_samples_per_second": 1.45,
6
+ "train_steps_per_second": 0.045
7
+ }
completed ADDED
File without changes
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.27,
3
+ "train_loss": 1.5663859701156617,
4
+ "train_runtime": 4414.9851,
5
+ "train_samples_per_second": 1.45,
6
+ "train_steps_per_second": 0.045
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.2745098039215685,
5
+ "global_step": 200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.31,
12
+ "learning_rate": 0.0002,
13
+ "loss": 2.0663,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.63,
18
+ "learning_rate": 0.0002,
19
+ "loss": 2.0741,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.94,
24
+ "learning_rate": 0.0002,
25
+ "loss": 1.9687,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 1.25,
30
+ "learning_rate": 0.0002,
31
+ "loss": 1.9634,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 1.57,
36
+ "learning_rate": 0.0002,
37
+ "loss": 1.8635,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 1.88,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.8845,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 2.2,
48
+ "learning_rate": 0.0002,
49
+ "loss": 1.7803,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 2.51,
54
+ "learning_rate": 0.0002,
55
+ "loss": 1.6615,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 2.82,
60
+ "learning_rate": 0.0002,
61
+ "loss": 1.7173,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 3.14,
66
+ "learning_rate": 0.0002,
67
+ "loss": 1.6624,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 3.45,
72
+ "learning_rate": 0.0002,
73
+ "loss": 1.3819,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 3.76,
78
+ "learning_rate": 0.0002,
79
+ "loss": 1.5122,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 4.08,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.5129,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 4.39,
90
+ "learning_rate": 0.0002,
91
+ "loss": 1.3089,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 4.71,
96
+ "learning_rate": 0.0002,
97
+ "loss": 1.2554,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 5.02,
102
+ "learning_rate": 0.0002,
103
+ "loss": 1.3004,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 5.33,
108
+ "learning_rate": 0.0002,
109
+ "loss": 1.1838,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 5.65,
114
+ "learning_rate": 0.0002,
115
+ "loss": 1.0549,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 5.96,
120
+ "learning_rate": 0.0002,
121
+ "loss": 1.1998,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 6.27,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.9754,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 6.27,
132
+ "step": 200,
133
+ "total_flos": 1.7550743484911616e+17,
134
+ "train_loss": 1.5663859701156617,
135
+ "train_runtime": 4414.9851,
136
+ "train_samples_per_second": 1.45,
137
+ "train_steps_per_second": 0.045
138
+ }
139
+ ],
140
+ "max_steps": 200,
141
+ "num_train_epochs": 7,
142
+ "total_flos": 1.7550743484911616e+17,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }