Hugging Face's logo

MahmoudIbrahim
/
FalconMasr

Text Generation
Transformers
Safetensors
Arabic
falcon
finance
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
MahmoudIbrahim commited on
Commit
a1f2ec7
•
1 Parent(s): 88d7d3c

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +138 -0
trainer_state.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.34285714285714286,
5
+ "eval_steps": 500,
6
+ "global_step": 150,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.022857142857142857,
13
+ "grad_norm": 1.0595301389694214,
14
+ "learning_rate": 0.002,
15
+ "loss": 3.6082,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.045714285714285714,
20
+ "grad_norm": 0.2752091884613037,
21
+ "learning_rate": 0.002,
22
+ "loss": 1.5529,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06857142857142857,
27
+ "grad_norm": 0.17800529301166534,
28
+ "learning_rate": 0.002,
29
+ "loss": 1.0928,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.09142857142857143,
34
+ "grad_norm": 0.21639685332775116,
35
+ "learning_rate": 0.002,
36
+ "loss": 0.99,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.11428571428571428,
41
+ "grad_norm": 0.2555713951587677,
42
+ "learning_rate": 0.002,
43
+ "loss": 0.884,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.13714285714285715,
48
+ "grad_norm": 0.1835678517818451,
49
+ "learning_rate": 0.002,
50
+ "loss": 1.2252,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.16,
55
+ "grad_norm": 0.23407411575317383,
56
+ "learning_rate": 0.002,
57
+ "loss": 1.0325,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.18285714285714286,
62
+ "grad_norm": 0.20827867090702057,
63
+ "learning_rate": 0.002,
64
+ "loss": 0.9401,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.2057142857142857,
69
+ "grad_norm": 0.20146110653877258,
70
+ "learning_rate": 0.002,
71
+ "loss": 0.8852,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.22857142857142856,
76
+ "grad_norm": 0.2659783661365509,
77
+ "learning_rate": 0.002,
78
+ "loss": 0.8176,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.25142857142857145,
83
+ "grad_norm": 0.20099078118801117,
84
+ "learning_rate": 0.002,
85
+ "loss": 1.1806,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2742857142857143,
90
+ "grad_norm": 0.18531735241413116,
91
+ "learning_rate": 0.002,
92
+ "loss": 0.9712,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.29714285714285715,
97
+ "grad_norm": 0.19588737189769745,
98
+ "learning_rate": 0.002,
99
+ "loss": 0.918,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.32,
104
+ "grad_norm": 0.19109125435352325,
105
+ "learning_rate": 0.002,
106
+ "loss": 0.7857,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.34285714285714286,
111
+ "grad_norm": 0.2857687771320343,
112
+ "learning_rate": 0.002,
113
+ "loss": 0.7828,
114
+ "step": 150
115
+ }
116
+ ],
117
+ "logging_steps": 10,
118
+ "max_steps": 150,
119
+ "num_input_tokens_seen": 0,
120
+ "num_train_epochs": 1,
121
+ "save_steps": 10,
122
+ "stateful_callbacks": {
123
+ "TrainerControl": {
124
+ "args": {
125
+ "should_epoch_stop": false,
126
+ "should_evaluate": false,
127
+ "should_log": false,
128
+ "should_save": true,
129
+ "should_training_stop": true
130
+ },
131
+ "attributes": {}
132
+ }
133
+ },
134
+ "total_flos": 2.524734837978624e+16,
135
+ "train_batch_size": 4,
136
+ "trial_name": null,
137
+ "trial_params": null
138
+ }