Hugging Face's logo

Ashmal
/
Clima_Vicuna_13B

PyTorch
llama
Model card Files Community
Ashmal commited on
Commit
191ac66
·
verified ·
1 Parent(s): 9b7656c

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +163 -0
trainer_state.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9992160961588712,
5
+ "global_step": 478,
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": 2e-05,
13
+ "loss": 1.2141,
14
+ "step": 20
15
+ },
16
+ {
17
+ "epoch": 0.08,
18
+ "learning_rate": 2e-05,
19
+ "loss": 1.1281,
20
+ "step": 40
21
+ },
22
+ {
23
+ "epoch": 0.13,
24
+ "learning_rate": 2e-05,
25
+ "loss": 1.1091,
26
+ "step": 60
27
+ },
28
+ {
29
+ "epoch": 0.17,
30
+ "learning_rate": 2e-05,
31
+ "loss": 1.0959,
32
+ "step": 80
33
+ },
34
+ {
35
+ "epoch": 0.21,
36
+ "learning_rate": 2e-05,
37
+ "loss": 1.0903,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.25,
42
+ "learning_rate": 2e-05,
43
+ "loss": 1.0811,
44
+ "step": 120
45
+ },
46
+ {
47
+ "epoch": 0.29,
48
+ "learning_rate": 2e-05,
49
+ "loss": 1.0693,
50
+ "step": 140
51
+ },
52
+ {
53
+ "epoch": 0.33,
54
+ "learning_rate": 2e-05,
55
+ "loss": 1.0702,
56
+ "step": 160
57
+ },
58
+ {
59
+ "epoch": 0.38,
60
+ "learning_rate": 2e-05,
61
+ "loss": 1.0631,
62
+ "step": 180
63
+ },
64
+ {
65
+ "epoch": 0.42,
66
+ "learning_rate": 2e-05,
67
+ "loss": 1.0627,
68
+ "step": 200
69
+ },
70
+ {
71
+ "epoch": 0.46,
72
+ "learning_rate": 2e-05,
73
+ "loss": 1.0575,
74
+ "step": 220
75
+ },
76
+ {
77
+ "epoch": 0.5,
78
+ "learning_rate": 2e-05,
79
+ "loss": 1.0518,
80
+ "step": 240
81
+ },
82
+ {
83
+ "epoch": 0.54,
84
+ "learning_rate": 2e-05,
85
+ "loss": 1.0492,
86
+ "step": 260
87
+ },
88
+ {
89
+ "epoch": 0.59,
90
+ "learning_rate": 2e-05,
91
+ "loss": 1.0476,
92
+ "step": 280
93
+ },
94
+ {
95
+ "epoch": 0.63,
96
+ "learning_rate": 2e-05,
97
+ "loss": 1.0422,
98
+ "step": 300
99
+ },
100
+ {
101
+ "epoch": 0.67,
102
+ "learning_rate": 2e-05,
103
+ "loss": 1.044,
104
+ "step": 320
105
+ },
106
+ {
107
+ "epoch": 0.71,
108
+ "learning_rate": 2e-05,
109
+ "loss": 1.0367,
110
+ "step": 340
111
+ },
112
+ {
113
+ "epoch": 0.75,
114
+ "learning_rate": 2e-05,
115
+ "loss": 1.0353,
116
+ "step": 360
117
+ },
118
+ {
119
+ "epoch": 0.79,
120
+ "learning_rate": 2e-05,
121
+ "loss": 1.0292,
122
+ "step": 380
123
+ },
124
+ {
125
+ "epoch": 0.84,
126
+ "learning_rate": 2e-05,
127
+ "loss": 1.0264,
128
+ "step": 400
129
+ },
130
+ {
131
+ "epoch": 0.88,
132
+ "learning_rate": 2e-05,
133
+ "loss": 1.0239,
134
+ "step": 420
135
+ },
136
+ {
137
+ "epoch": 0.92,
138
+ "learning_rate": 2e-05,
139
+ "loss": 1.0224,
140
+ "step": 440
141
+ },
142
+ {
143
+ "epoch": 0.96,
144
+ "learning_rate": 2e-05,
145
+ "loss": 1.018,
146
+ "step": 460
147
+ },
148
+ {
149
+ "epoch": 1.0,
150
+ "step": 478,
151
+ "total_flos": 3741093011128320.0,
152
+ "train_loss": 1.0616770588703235,
153
+ "train_runtime": 173276.7886,
154
+ "train_samples_per_second": 4.24,
155
+ "train_steps_per_second": 0.003
156
+ }
157
+ ],
158
+ "max_steps": 478,
159
+ "num_train_epochs": 1,
160
+ "total_flos": 3741093011128320.0,
161
+ "trial_name": null,
162
+ "trial_params": null
163
+ }