Hugging Face's logo

Ashmal
/
ClimateGPT13B_en

Text Generation
Transformers
PyTorch
llama
text-generation-inference
Model card Files
xet
 Community
1
Ashmal commited on
Commit
abb67b4
·
1 Parent(s): 5ed71d5

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +154 -0
trainer_state.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9991941982272361,
5
+ "global_step": 465,
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": 1.2313,
14
+ "step": 20
15
+ },
16
+ {
17
+ "epoch": 0.09,
18
+ "learning_rate": 2e-05,
19
+ "loss": 1.1365,
20
+ "step": 40
21
+ },
22
+ {
23
+ "epoch": 0.13,
24
+ "learning_rate": 2e-05,
25
+ "loss": 1.1187,
26
+ "step": 60
27
+ },
28
+ {
29
+ "epoch": 0.17,
30
+ "learning_rate": 2e-05,
31
+ "loss": 1.1067,
32
+ "step": 80
33
+ },
34
+ {
35
+ "epoch": 0.21,
36
+ "learning_rate": 2e-05,
37
+ "loss": 1.0958,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.26,
42
+ "learning_rate": 2e-05,
43
+ "loss": 1.0903,
44
+ "step": 120
45
+ },
46
+ {
47
+ "epoch": 0.3,
48
+ "learning_rate": 2e-05,
49
+ "loss": 1.0814,
50
+ "step": 140
51
+ },
52
+ {
53
+ "epoch": 0.34,
54
+ "learning_rate": 2e-05,
55
+ "loss": 1.0766,
56
+ "step": 160
57
+ },
58
+ {
59
+ "epoch": 0.39,
60
+ "learning_rate": 2e-05,
61
+ "loss": 1.0733,
62
+ "step": 180
63
+ },
64
+ {
65
+ "epoch": 0.43,
66
+ "learning_rate": 2e-05,
67
+ "loss": 1.0727,
68
+ "step": 200
69
+ },
70
+ {
71
+ "epoch": 0.47,
72
+ "learning_rate": 2e-05,
73
+ "loss": 1.0602,
74
+ "step": 220
75
+ },
76
+ {
77
+ "epoch": 0.52,
78
+ "learning_rate": 2e-05,
79
+ "loss": 1.0604,
80
+ "step": 240
81
+ },
82
+ {
83
+ "epoch": 0.56,
84
+ "learning_rate": 2e-05,
85
+ "loss": 1.058,
86
+ "step": 260
87
+ },
88
+ {
89
+ "epoch": 0.6,
90
+ "learning_rate": 2e-05,
91
+ "loss": 1.0519,
92
+ "step": 280
93
+ },
94
+ {
95
+ "epoch": 0.64,
96
+ "learning_rate": 2e-05,
97
+ "loss": 1.0468,
98
+ "step": 300
99
+ },
100
+ {
101
+ "epoch": 0.69,
102
+ "learning_rate": 2e-05,
103
+ "loss": 1.0466,
104
+ "step": 320
105
+ },
106
+ {
107
+ "epoch": 0.73,
108
+ "learning_rate": 2e-05,
109
+ "loss": 1.0425,
110
+ "step": 340
111
+ },
112
+ {
113
+ "epoch": 0.77,
114
+ "learning_rate": 2e-05,
115
+ "loss": 1.0432,
116
+ "step": 360
117
+ },
118
+ {
119
+ "epoch": 0.82,
120
+ "learning_rate": 2e-05,
121
+ "loss": 1.0399,
122
+ "step": 380
123
+ },
124
+ {
125
+ "epoch": 0.86,
126
+ "learning_rate": 2e-05,
127
+ "loss": 1.0364,
128
+ "step": 400
129
+ },
130
+ {
131
+ "epoch": 0.9,
132
+ "learning_rate": 2e-05,
133
+ "loss": 1.0309,
134
+ "step": 420
135
+ },
136
+ {
137
+ "epoch": 0.95,
138
+ "learning_rate": 2e-05,
139
+ "loss": 1.0274,
140
+ "step": 440
141
+ },
142
+ {
143
+ "epoch": 0.99,
144
+ "learning_rate": 2e-05,
145
+ "loss": 1.0269,
146
+ "step": 460
147
+ }
148
+ ],
149
+ "max_steps": 465,
150
+ "num_train_epochs": 1,
151
+ "total_flos": 3639334498467840.0,
152
+ "trial_name": null,
153
+ "trial_params": null
154
+ }