jprivera44 commited on
Commit
97ec993
·
verified ·
1 Parent(s): f05072e

Upload half_evil__pirate_ultrachat__lr10x/trainer_state.json with huggingface_hub

Browse files
half_evil__pirate_ultrachat__lr10x/trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 16,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0625,
13
+ "grad_norm": 0.899012565612793,
14
+ "learning_rate": 0.0002,
15
+ "loss": 1.5247,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.125,
20
+ "grad_norm": 0.8130273222923279,
21
+ "learning_rate": 0.0002,
22
+ "loss": 1.5775,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.1875,
27
+ "grad_norm": 0.40913769602775574,
28
+ "learning_rate": 0.0002,
29
+ "loss": 1.4811,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.25,
34
+ "grad_norm": 0.35765886306762695,
35
+ "learning_rate": 0.0002,
36
+ "loss": 1.372,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.3125,
41
+ "grad_norm": 0.297399640083313,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.3024,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.375,
48
+ "grad_norm": 0.41808706521987915,
49
+ "learning_rate": 0.0002,
50
+ "loss": 1.354,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.4375,
55
+ "grad_norm": 0.29261064529418945,
56
+ "learning_rate": 0.0002,
57
+ "loss": 1.3032,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.5,
62
+ "grad_norm": 0.2534007132053375,
63
+ "learning_rate": 0.0002,
64
+ "loss": 1.2594,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.5625,
69
+ "grad_norm": 0.26669755578041077,
70
+ "learning_rate": 0.0002,
71
+ "loss": 1.3107,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.625,
76
+ "grad_norm": 0.2550638020038605,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.2502,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.6875,
83
+ "grad_norm": 0.23848970234394073,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.2684,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.75,
90
+ "grad_norm": 0.2612243890762329,
91
+ "learning_rate": 0.0002,
92
+ "loss": 1.2572,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.8125,
97
+ "grad_norm": 0.24616308510303497,
98
+ "learning_rate": 0.0002,
99
+ "loss": 1.1975,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.875,
104
+ "grad_norm": 0.253064900636673,
105
+ "learning_rate": 0.0002,
106
+ "loss": 1.2118,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.9375,
111
+ "grad_norm": 0.2675933539867401,
112
+ "learning_rate": 0.0002,
113
+ "loss": 1.234,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.0,
118
+ "grad_norm": 0.23249714076519012,
119
+ "learning_rate": 0.0002,
120
+ "loss": 1.0601,
121
+ "step": 16
122
+ }
123
+ ],
124
+ "logging_steps": 1,
125
+ "max_steps": 16,
126
+ "num_input_tokens_seen": 0,
127
+ "num_train_epochs": 1,
128
+ "save_steps": 99999,
129
+ "stateful_callbacks": {
130
+ "TrainerControl": {
131
+ "args": {
132
+ "should_epoch_stop": false,
133
+ "should_evaluate": false,
134
+ "should_log": false,
135
+ "should_save": true,
136
+ "should_training_stop": true
137
+ },
138
+ "attributes": {}
139
+ }
140
+ },
141
+ "total_flos": 3.004429535228723e+16,
142
+ "train_batch_size": 8,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }