Hugging Face's logo

sqllama
/
alpaca-lora-dono

Model card Files Community
chrisdono commited on
Commit
a005e66
•
1 Parent(s): 68875ca

initial model

Browse files
Files changed (10) hide show
  1. adapter_config.json +18 -0
  2. adapter_model.bin +3 -0
  3. checkpoint-200/optimizer.pt +3 -0
  4. checkpoint-200/pytorch_model.bin +3 -0
  5. checkpoint-200/rng_state_0.pth +3 -0
  6. checkpoint-200/rng_state_1.pth +3 -0
  7. checkpoint-200/scaler.pt +3 -0
  8. checkpoint-200/scheduler.pt +3 -0
  9. checkpoint-200/trainer_state.json +144 -0
  10. checkpoint-200/training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "decapoda-research/llama-7b-hf",
3
+ "bias": "none",
4
+ "enable_lora": null,
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "lora_alpha": 16,
8
+ "lora_dropout": 0.05,
9
+ "merge_weights": false,
10
+ "modules_to_save": null,
11
+ "peft_type": "LORA",
12
+ "r": 8,
13
+ "target_modules": [
14
+ "q_proj",
15
+ "v_proj"
16
+ ],
17
+ "task_type": "CAUSAL_LM"
18
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3dd0dc366b732a0893ee36e96d7054e80e10f38dd427285a0b2dba6bb7c5f37
3
+ size 16822989
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a255d039eb3b513ae0eed95e385fc686871cdd30ec33e987ad7876e79c6d710
3
+ size 33661637
checkpoint-200/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:797362db1db8109eeac1ba2d4d7799e2cfd40cdbe32bb518699020cf366d027f
3
+ size 16822989
checkpoint-200/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc8e8654ce9eb5cd84ae277af1099500ed0f92cbd774c9e9366a711f14b7125
3
+ size 14583
checkpoint-200/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c44e028dc53964f5c4f5cbe8d5fb8ac19e6bc4b9bc8a408a8d3558c1fd4e3812
3
+ size 14583
checkpoint-200/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df38ef765efd726adcc50bd14c52fd9243ea375c4e974857564d9b4fc4c2a185
3
+ size 557
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbe336804acca841dde349e223d530cc282a2d586e05403d7a6bf0a86731c5c1
3
+ size 627
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9055714011192322,
3
+ "best_model_checkpoint": "./lora-alpaca/checkpoint-200",
4
+ "epoch": 0.5144694533762058,
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": 0.03,
12
+ "learning_rate": 2.9999999999999997e-05,
13
+ "loss": 1.8867,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.05,
18
+ "learning_rate": 5.6999999999999996e-05,
19
+ "loss": 1.8339,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.08,
24
+ "learning_rate": 8.699999999999999e-05,
25
+ "loss": 1.6664,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.1,
30
+ "learning_rate": 0.000117,
31
+ "loss": 1.3046,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.13,
36
+ "learning_rate": 0.000147,
37
+ "loss": 1.115,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.15,
42
+ "learning_rate": 0.00017399999999999997,
43
+ "loss": 1.0706,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.18,
48
+ "learning_rate": 0.000204,
49
+ "loss": 1.0269,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.21,
54
+ "learning_rate": 0.000234,
55
+ "loss": 1.0012,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.23,
60
+ "learning_rate": 0.00026399999999999997,
61
+ "loss": 0.9608,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.26,
66
+ "learning_rate": 0.000294,
67
+ "loss": 0.9563,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.28,
72
+ "learning_rate": 0.00029166666666666664,
73
+ "loss": 0.9512,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.31,
78
+ "learning_rate": 0.00028125,
79
+ "loss": 0.9505,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.33,
84
+ "learning_rate": 0.0002708333333333333,
85
+ "loss": 0.9326,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 0.36,
90
+ "learning_rate": 0.00026041666666666666,
91
+ "loss": 0.9229,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 0.39,
96
+ "learning_rate": 0.00025,
97
+ "loss": 0.918,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 0.41,
102
+ "learning_rate": 0.00023958333333333332,
103
+ "loss": 0.9128,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 0.44,
108
+ "learning_rate": 0.00022916666666666664,
109
+ "loss": 0.9021,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 0.46,
114
+ "learning_rate": 0.00021874999999999998,
115
+ "loss": 0.9115,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 0.49,
120
+ "learning_rate": 0.00020833333333333332,
121
+ "loss": 0.8915,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 0.51,
126
+ "learning_rate": 0.00019791666666666663,
127
+ "loss": 0.8993,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 0.51,
132
+ "eval_loss": 0.9055714011192322,
133
+ "eval_runtime": 179.4765,
134
+ "eval_samples_per_second": 11.144,
135
+ "eval_steps_per_second": 0.696,
136
+ "step": 200
137
+ }
138
+ ],
139
+ "max_steps": 388,
140
+ "num_train_epochs": 1,
141
+ "total_flos": 2.591511325704192e+17,
142
+ "trial_name": null,
143
+ "trial_params": null
144
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c96bac75926f7573110000cf035cf9751cd1e121a53b6c97d06ef30dd9ec07
3
+ size 3579