Hugging Face's logo

alexlawtengyi
/
final_model_travel

PEFT
TensorBoard
Safetensors
mistral
Model card Files Metrics Community
alexlawtengyi commited on
Commit
e154418
·
verified ·
1 Parent(s): 4292162

Upload checkpoint-200/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-200/trainer_state.json +173 -0
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.7976071784646062,
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": 0.03988035892323031,
13
+ "grad_norm": 16.628543853759766,
14
+ "learning_rate": 0.00012,
15
+ "loss": 2.1274,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.07976071784646062,
20
+ "grad_norm": 12.371907234191895,
21
+ "learning_rate": 0.00019950829025450114,
22
+ "loss": 0.7722,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.11964107676969092,
27
+ "grad_norm": 9.106270790100098,
28
+ "learning_rate": 0.00019652089102773488,
29
+ "loss": 0.4456,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.15952143569292124,
34
+ "grad_norm": 5.712669372558594,
35
+ "learning_rate": 0.00019090065350491626,
36
+ "loss": 0.3662,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.19940179461615154,
41
+ "grad_norm": 2.922630548477173,
42
+ "learning_rate": 0.00018280088311480201,
43
+ "loss": 0.2983,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.23928215353938184,
48
+ "grad_norm": 5.451596260070801,
49
+ "learning_rate": 0.00017244252047910892,
50
+ "loss": 0.3034,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.27916251246261214,
55
+ "grad_norm": 3.604940414428711,
56
+ "learning_rate": 0.00016010811472830252,
57
+ "loss": 0.2754,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.3190428713858425,
62
+ "grad_norm": 2.805121660232544,
63
+ "learning_rate": 0.0001461341162978688,
64
+ "loss": 0.2659,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.3589232303090728,
69
+ "grad_norm": 3.4018733501434326,
70
+ "learning_rate": 0.00013090169943749476,
71
+ "loss": 0.2767,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.3988035892323031,
76
+ "grad_norm": 3.0557034015655518,
77
+ "learning_rate": 0.0001148263647711842,
78
+ "loss": 0.286,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.4386839481555334,
83
+ "grad_norm": 4.8394036293029785,
84
+ "learning_rate": 9.834660552336415e-05,
85
+ "loss": 0.2604,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.4785643070787637,
90
+ "grad_norm": 6.2420759201049805,
91
+ "learning_rate": 8.191194656678904e-05,
92
+ "loss": 0.2447,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.518444666001994,
97
+ "grad_norm": 3.427865505218506,
98
+ "learning_rate": 6.59706825558357e-05,
99
+ "loss": 0.282,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.5583250249252243,
104
+ "grad_norm": 5.478673934936523,
105
+ "learning_rate": 5.095764961694922e-05,
106
+ "loss": 0.2314,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.5982053838484547,
111
+ "grad_norm": 1.9072978496551514,
112
+ "learning_rate": 3.7282364152646297e-05,
113
+ "loss": 0.2284,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.638085742771685,
118
+ "grad_norm": 2.6893632411956787,
119
+ "learning_rate": 2.5317852301584643e-05,
120
+ "loss": 0.2232,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.6779661016949152,
125
+ "grad_norm": 2.540834665298462,
126
+ "learning_rate": 1.5390474757906446e-05,
127
+ "loss": 0.2421,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.7178464606181456,
132
+ "grad_norm": 2.5203776359558105,
133
+ "learning_rate": 7.771024502261526e-06,
134
+ "loss": 0.2265,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.7577268195413759,
139
+ "grad_norm": 2.1481897830963135,
140
+ "learning_rate": 2.667340275199426e-06,
141
+ "loss": 0.2287,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.7976071784646062,
146
+ "grad_norm": 2.8947484493255615,
147
+ "learning_rate": 2.1863727812254653e-07,
148
+ "loss": 0.2406,
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": 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": 2868052066295808.0,
170
+ "train_batch_size": 1,
171
+ "trial_name": null,
172
+ "trial_params": null
173
+ }