Hugging Face's logo

MahmoudIbrahim
/
Meta-LLama3-Instruct-Arabic

Text Generation
Transformers
Safetensors
Arabic
llama
finance
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
MahmoudIbrahim commited on
Commit
fcaf076
·
verified ·
1 Parent(s): 9634e8e

Upload trainer_state.json

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": 0.03076804738279297,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0015384023691396484,
13
+ "grad_norm": 1.1134390830993652,
14
+ "learning_rate": 0.00019487179487179487,
15
+ "loss": 1.9095,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.003076804738279297,
20
+ "grad_norm": 0.6254091858863831,
21
+ "learning_rate": 0.00018461538461538463,
22
+ "loss": 1.2605,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.004615207107418946,
27
+ "grad_norm": 0.7272558808326721,
28
+ "learning_rate": 0.00017435897435897436,
29
+ "loss": 1.1399,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.006153609476558594,
34
+ "grad_norm": 0.49501851201057434,
35
+ "learning_rate": 0.0001641025641025641,
36
+ "loss": 1.0796,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.007692011845698243,
41
+ "grad_norm": 0.6586689352989197,
42
+ "learning_rate": 0.00015384615384615385,
43
+ "loss": 1.1476,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.009230414214837892,
48
+ "grad_norm": 0.624894917011261,
49
+ "learning_rate": 0.0001435897435897436,
50
+ "loss": 1.0346,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.010768816583977539,
55
+ "grad_norm": 0.4778560400009155,
56
+ "learning_rate": 0.00013333333333333334,
57
+ "loss": 1.0532,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.012307218953117188,
62
+ "grad_norm": 0.5783376097679138,
63
+ "learning_rate": 0.0001230769230769231,
64
+ "loss": 1.0024,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.013845621322256836,
69
+ "grad_norm": 0.544222891330719,
70
+ "learning_rate": 0.00011282051282051283,
71
+ "loss": 1.0234,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.015384023691396485,
76
+ "grad_norm": 0.5201743245124817,
77
+ "learning_rate": 0.00010256410256410256,
78
+ "loss": 1.0451,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.016922426060536132,
83
+ "grad_norm": 0.5806599259376526,
84
+ "learning_rate": 9.230769230769232e-05,
85
+ "loss": 1.0226,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.018460828429675783,
90
+ "grad_norm": 0.5782334208488464,
91
+ "learning_rate": 8.205128205128205e-05,
92
+ "loss": 1.0224,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.01999923079881543,
97
+ "grad_norm": 0.5596034526824951,
98
+ "learning_rate": 7.17948717948718e-05,
99
+ "loss": 1.0013,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.021537633167955077,
104
+ "grad_norm": 0.5834138989448547,
105
+ "learning_rate": 6.153846153846155e-05,
106
+ "loss": 1.0763,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.023076035537094728,
111
+ "grad_norm": 0.45252805948257446,
112
+ "learning_rate": 5.128205128205128e-05,
113
+ "loss": 1.0192,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.024614437906234375,
118
+ "grad_norm": 0.5366165637969971,
119
+ "learning_rate": 4.1025641025641023e-05,
120
+ "loss": 0.962,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.026152840275374026,
125
+ "grad_norm": 0.5441515445709229,
126
+ "learning_rate": 3.0769230769230774e-05,
127
+ "loss": 1.0803,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.027691242644513673,
132
+ "grad_norm": 0.6809340119361877,
133
+ "learning_rate": 2.0512820512820512e-05,
134
+ "loss": 1.0303,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.02922964501365332,
139
+ "grad_norm": 0.45926156640052795,
140
+ "learning_rate": 1.0256410256410256e-05,
141
+ "loss": 1.0258,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.03076804738279297,
146
+ "grad_norm": 0.4480159878730774,
147
+ "learning_rate": 0.0,
148
+ "loss": 1.0755,
149
+ "step": 200
150
+ }
151
+ ],
152
+ "logging_steps": 10,
153
+ "max_steps": 200,
154
+ "num_input_tokens_seen": 0,
155
+ "num_train_epochs": 1,
156
+ "save_steps": 500,
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": 1.6066405922193408e+16,
170
+ "train_batch_size": 2,
171
+ "trial_name": null,
172
+ "trial_params": null
173
+ }