Hugging Face's logo

AlexCuadron
/
Qwen-32B-8a4e8f3a

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
AlexCuadron commited on
Commit
e59e195
·
verified ·
1 Parent(s): e76eea7

Upload checkpoint-16/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-16/trainer_state.json +145 -0
checkpoint-16/trainer_state.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.8484848484848486,
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": 0.12121212121212122,
13
+ "grad_norm": 2.50050950050354,
14
+ "learning_rate": 2.5e-06,
15
+ "loss": 0.8407,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.24242424242424243,
20
+ "grad_norm": 2.2383944988250732,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.7878,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.36363636363636365,
27
+ "grad_norm": 2.1805531978607178,
28
+ "learning_rate": 7.500000000000001e-06,
29
+ "loss": 0.8026,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.48484848484848486,
34
+ "grad_norm": 2.0964150428771973,
35
+ "learning_rate": 1e-05,
36
+ "loss": 0.8133,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.6060606060606061,
41
+ "grad_norm": 1.5487000942230225,
42
+ "learning_rate": 9.968561049466214e-06,
43
+ "loss": 0.7608,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.7272727272727273,
48
+ "grad_norm": 1.7998461723327637,
49
+ "learning_rate": 9.874639560909118e-06,
50
+ "loss": 0.7272,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.8484848484848485,
55
+ "grad_norm": 1.9523899555206299,
56
+ "learning_rate": 9.719416651541839e-06,
57
+ "loss": 0.6923,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.9696969696969697,
62
+ "grad_norm": 4.303847312927246,
63
+ "learning_rate": 9.504844339512096e-06,
64
+ "loss": 0.6853,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 1.0,
69
+ "grad_norm": 4.303847312927246,
70
+ "learning_rate": 9.233620996141421e-06,
71
+ "loss": 0.6532,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 1.121212121212121,
76
+ "grad_norm": 2.6484241485595703,
77
+ "learning_rate": 8.90915741234015e-06,
78
+ "loss": 0.6334,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 1.2424242424242424,
83
+ "grad_norm": 1.0852004289627075,
84
+ "learning_rate": 8.535533905932739e-06,
85
+ "loss": 0.6171,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 1.3636363636363638,
90
+ "grad_norm": 87.41819763183594,
91
+ "learning_rate": 8.117449009293668e-06,
92
+ "loss": 0.5768,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 1.4848484848484849,
97
+ "grad_norm": 1.8918662071228027,
98
+ "learning_rate": 7.660160382576683e-06,
99
+ "loss": 0.5852,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 1.606060606060606,
104
+ "grad_norm": 1.3301656246185303,
105
+ "learning_rate": 7.169418695587791e-06,
106
+ "loss": 0.5752,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 1.7272727272727273,
111
+ "grad_norm": 0.9969548583030701,
112
+ "learning_rate": 6.651395309775837e-06,
113
+ "loss": 0.5949,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 1.8484848484848486,
118
+ "grad_norm": 0.9531848430633545,
119
+ "learning_rate": 6.112604669781572e-06,
120
+ "loss": 0.5568,
121
+ "step": 16
122
+ }
123
+ ],
124
+ "logging_steps": 1,
125
+ "max_steps": 32,
126
+ "num_input_tokens_seen": 0,
127
+ "num_train_epochs": 4,
128
+ "save_steps": 8,
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": false
137
+ },
138
+ "attributes": {}
139
+ }
140
+ },
141
+ "total_flos": 39941324668928.0,
142
+ "train_batch_size": 2,
143
+ "trial_name": null,
144
+ "trial_params": null
145
+ }