Hugging Face's logo

Bmcbob76
/
echo-titlehound-lora

Text Generation
PEFT
Safetensors
lora
title-examination
oil-gas
texas
landman
legal
mineral-rights
conversational
Model card Files
xet
Community
Bmcbob76 commited on
Commit
87f2640
·
verified ·
1 Parent(s): 3803e29

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +189 -0
trainer_state.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.3913894324853229,
5
+ "eval_steps": 100,
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": 0.019569471624266144,
13
+ "grad_norm": 0.6461917161941528,
14
+ "learning_rate": 2.5974025974025972e-05,
15
+ "loss": 1.9953,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.03913894324853229,
20
+ "grad_norm": 0.35114091634750366,
21
+ "learning_rate": 5.1948051948051944e-05,
22
+ "loss": 1.923,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.05870841487279843,
27
+ "grad_norm": 0.41224125027656555,
28
+ "learning_rate": 7.792207792207793e-05,
29
+ "loss": 1.8037,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.07827788649706457,
34
+ "grad_norm": 0.4727496802806854,
35
+ "learning_rate": 0.00010389610389610389,
36
+ "loss": 1.597,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.09784735812133072,
41
+ "grad_norm": 0.5965492129325867,
42
+ "learning_rate": 0.00012987012987012987,
43
+ "loss": 1.3375,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.11741682974559686,
48
+ "grad_norm": 0.820002555847168,
49
+ "learning_rate": 0.00015584415584415587,
50
+ "loss": 1.0652,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.136986301369863,
55
+ "grad_norm": 0.6552278399467468,
56
+ "learning_rate": 0.00018181818181818183,
57
+ "loss": 0.7861,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.15655577299412915,
62
+ "grad_norm": 0.7231012582778931,
63
+ "learning_rate": 0.0001999979049808708,
64
+ "loss": 0.7016,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.1761252446183953,
69
+ "grad_norm": 0.723237156867981,
70
+ "learning_rate": 0.00019996066263830531,
71
+ "loss": 0.5777,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.19569471624266144,
76
+ "grad_norm": 0.5118690729141235,
77
+ "learning_rate": 0.00019987688427197897,
78
+ "loss": 0.5553,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.19569471624266144,
83
+ "eval_loss": 0.5386264324188232,
84
+ "eval_runtime": 2488.1393,
85
+ "eval_samples_per_second": 0.083,
86
+ "eval_steps_per_second": 0.083,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 0.21526418786692758,
91
+ "grad_norm": 0.650175929069519,
92
+ "learning_rate": 0.0001997466088843548,
93
+ "loss": 0.5231,
94
+ "step": 110
95
+ },
96
+ {
97
+ "epoch": 0.23483365949119372,
98
+ "grad_norm": 0.4600216746330261,
99
+ "learning_rate": 0.00019956989712427577,
100
+ "loss": 0.4945,
101
+ "step": 120
102
+ },
103
+ {
104
+ "epoch": 0.25440313111545987,
105
+ "grad_norm": 0.5527154207229614,
106
+ "learning_rate": 0.0001993468312587303,
107
+ "loss": 0.4671,
108
+ "step": 130
109
+ },
110
+ {
111
+ "epoch": 0.273972602739726,
112
+ "grad_norm": 0.46538111567497253,
113
+ "learning_rate": 0.00019907751513455302,
114
+ "loss": 0.5276,
115
+ "step": 140
116
+ },
117
+ {
118
+ "epoch": 0.29354207436399216,
119
+ "grad_norm": 0.4237975776195526,
120
+ "learning_rate": 0.00019876207413008015,
121
+ "loss": 0.5122,
122
+ "step": 150
123
+ },
124
+ {
125
+ "epoch": 0.3131115459882583,
126
+ "grad_norm": 0.40869906544685364,
127
+ "learning_rate": 0.00019840065509677988,
128
+ "loss": 0.4781,
129
+ "step": 160
130
+ },
131
+ {
132
+ "epoch": 0.33268101761252444,
133
+ "grad_norm": 0.47258374094963074,
134
+ "learning_rate": 0.00019799342629088702,
135
+ "loss": 0.5291,
136
+ "step": 170
137
+ },
138
+ {
139
+ "epoch": 0.3522504892367906,
140
+ "grad_norm": 1.2339996099472046,
141
+ "learning_rate": 0.00019754057729507227,
142
+ "loss": 0.483,
143
+ "step": 180
144
+ },
145
+ {
146
+ "epoch": 0.37181996086105673,
147
+ "grad_norm": 0.32413920760154724,
148
+ "learning_rate": 0.0001970423189301833,
149
+ "loss": 0.4802,
150
+ "step": 190
151
+ },
152
+ {
153
+ "epoch": 0.3913894324853229,
154
+ "grad_norm": 0.3887979984283447,
155
+ "learning_rate": 0.00019649888315709843,
156
+ "loss": 0.5053,
157
+ "step": 200
158
+ },
159
+ {
160
+ "epoch": 0.3913894324853229,
161
+ "eval_loss": 0.47472819685935974,
162
+ "eval_runtime": 2489.5517,
163
+ "eval_samples_per_second": 0.083,
164
+ "eval_steps_per_second": 0.083,
165
+ "step": 200
166
+ }
167
+ ],
168
+ "logging_steps": 10,
169
+ "max_steps": 1533,
170
+ "num_input_tokens_seen": 0,
171
+ "num_train_epochs": 3,
172
+ "save_steps": 100,
173
+ "stateful_callbacks": {
174
+ "TrainerControl": {
175
+ "args": {
176
+ "should_epoch_stop": false,
177
+ "should_evaluate": false,
178
+ "should_log": false,
179
+ "should_save": true,
180
+ "should_training_stop": false
181
+ },
182
+ "attributes": {}
183
+ }
184
+ },
185
+ "total_flos": 3.4803114049536e+16,
186
+ "train_batch_size": 1,
187
+ "trial_name": null,
188
+ "trial_params": null
189
+ }