Hugging Face's logo

vdpappu
/
lora_psychology-2

Question Answering
PEFT
Safetensors
English
Model card Files Community
vdpappu commited on
Commit
cea8f9d
•
1 Parent(s): 78e03f6

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +173 -0
trainer_state.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.43605359317905,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1218026796589525,
13
+ "grad_norm": 0.567721962928772,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.6252,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.243605359317905,
20
+ "grad_norm": 0.7323570251464844,
21
+ "learning_rate": 1e-05,
22
+ "loss": 1.582,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.3654080389768575,
27
+ "grad_norm": 0.7963395118713379,
28
+ "learning_rate": 1.5e-05,
29
+ "loss": 1.4706,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.48721071863581,
34
+ "grad_norm": 0.6532277464866638,
35
+ "learning_rate": 2e-05,
36
+ "loss": 1.2949,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.6090133982947625,
41
+ "grad_norm": 0.7197393774986267,
42
+ "learning_rate": 2.5e-05,
43
+ "loss": 1.1536,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.730816077953715,
48
+ "grad_norm": 0.7984452247619629,
49
+ "learning_rate": 3e-05,
50
+ "loss": 1.0621,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.8526187576126675,
55
+ "grad_norm": 1.125217318534851,
56
+ "learning_rate": 3.5e-05,
57
+ "loss": 1.0322,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.97442143727162,
62
+ "grad_norm": 0.9447218179702759,
63
+ "learning_rate": 4e-05,
64
+ "loss": 1.0086,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 1.0962241169305724,
69
+ "grad_norm": 0.9581252932548523,
70
+ "learning_rate": 4.5e-05,
71
+ "loss": 0.9828,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 1.218026796589525,
76
+ "grad_norm": 1.0622270107269287,
77
+ "learning_rate": 5e-05,
78
+ "loss": 0.9694,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 1.3398294762484775,
83
+ "grad_norm": 1.1124155521392822,
84
+ "learning_rate": 4.877641290737884e-05,
85
+ "loss": 0.9658,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 1.46163215590743,
90
+ "grad_norm": 1.2832890748977661,
91
+ "learning_rate": 4.522542485937369e-05,
92
+ "loss": 0.9635,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 1.5834348355663823,
97
+ "grad_norm": 1.0713014602661133,
98
+ "learning_rate": 3.969463130731183e-05,
99
+ "loss": 0.9382,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 1.705237515225335,
104
+ "grad_norm": 1.0779744386672974,
105
+ "learning_rate": 3.272542485937369e-05,
106
+ "loss": 0.9457,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 1.8270401948842876,
111
+ "grad_norm": 1.0238535404205322,
112
+ "learning_rate": 2.5e-05,
113
+ "loss": 0.9462,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 1.94884287454324,
118
+ "grad_norm": 1.1264749765396118,
119
+ "learning_rate": 1.7274575140626318e-05,
120
+ "loss": 0.9315,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 2.0706455542021924,
125
+ "grad_norm": 1.1411375999450684,
126
+ "learning_rate": 1.0305368692688174e-05,
127
+ "loss": 0.9232,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 2.192448233861145,
132
+ "grad_norm": 1.1316472291946411,
133
+ "learning_rate": 4.7745751406263165e-06,
134
+ "loss": 0.9232,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 2.3142509135200973,
139
+ "grad_norm": 1.1166857481002808,
140
+ "learning_rate": 1.2235870926211619e-06,
141
+ "loss": 0.9241,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 2.43605359317905,
146
+ "grad_norm": 1.2450848817825317,
147
+ "learning_rate": 0.0,
148
+ "loss": 0.9213,
149
+ "step": 1000
150
+ }
151
+ ],
152
+ "logging_steps": 50,
153
+ "max_steps": 1000,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 3,
156
+ "save_steps": 100,
157
+ "stateful_callbacks": {
158
+ "TrainerControl": {
159
+ "args": {
160
+ "should_epoch_stop": false,
161
+ "should_evaluate": false,
162
+ "should_log": false,
163
+ "should_save": true,
164
+ "should_training_stop": true
165
+ },
166
+ "attributes": {}
167
+ }
168
+ },
169
+ "total_flos": 3.241676072477491e+16,
170
+ "train_batch_size": 12,
171
+ "trial_name": null,
172
+ "trial_params": null
173
+ }