Hugging Face's logo

ploppy2
/
Clinical-Reasoning-Test1

Text Generation
TensorBoard
Safetensors
English
medical
clinical-reasoning
diagnostic
education
fine-tuned
lora
sft
trl
conversational
Model card Files
xet
 Metrics Community
ploppy2 commited on
Commit
3a35e57
·
verified ·
1 Parent(s): f9312b3

Upload checkpoint-189/trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. checkpoint-189/trainer_state.json +159 -0
checkpoint-189/trainer_state.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.954990215264188,
5
+ "eval_steps": 500,
6
+ "global_step": 189,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.15655577299412915,
13
+ "grad_norm": 8.653885841369629,
14
+ "learning_rate": 1.5789473684210526e-05,
15
+ "loss": 22.3789,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.3131115459882583,
20
+ "grad_norm": 4.433068752288818,
21
+ "learning_rate": 2.9823529411764707e-05,
22
+ "loss": 20.8804,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.46966731898238745,
27
+ "grad_norm": 4.180165767669678,
28
+ "learning_rate": 2.8058823529411766e-05,
29
+ "loss": 19.2313,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.6262230919765166,
34
+ "grad_norm": 4.197498321533203,
35
+ "learning_rate": 2.6294117647058825e-05,
36
+ "loss": 18.3825,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.7827788649706457,
41
+ "grad_norm": 4.2604594230651855,
42
+ "learning_rate": 2.452941176470588e-05,
43
+ "loss": 17.0293,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.9393346379647749,
48
+ "grad_norm": 4.613166809082031,
49
+ "learning_rate": 2.276470588235294e-05,
50
+ "loss": 15.8548,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 1.0939334637964775,
55
+ "grad_norm": 4.805100917816162,
56
+ "learning_rate": 2.1e-05,
57
+ "loss": 15.2336,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 1.2504892367906066,
62
+ "grad_norm": 4.5222883224487305,
63
+ "learning_rate": 1.923529411764706e-05,
64
+ "loss": 15.19,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 1.4070450097847358,
69
+ "grad_norm": 5.12910795211792,
70
+ "learning_rate": 1.747058823529412e-05,
71
+ "loss": 15.0824,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 1.563600782778865,
76
+ "grad_norm": 5.300595283508301,
77
+ "learning_rate": 1.570588235294118e-05,
78
+ "loss": 14.5899,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 1.720156555772994,
83
+ "grad_norm": 5.652774333953857,
84
+ "learning_rate": 1.3941176470588236e-05,
85
+ "loss": 15.0659,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 1.8767123287671232,
90
+ "grad_norm": 5.436872959136963,
91
+ "learning_rate": 1.2176470588235294e-05,
92
+ "loss": 14.7455,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 2.031311154598826,
97
+ "grad_norm": 5.51776123046875,
98
+ "learning_rate": 1.0411764705882353e-05,
99
+ "loss": 14.5675,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 2.187866927592955,
104
+ "grad_norm": 5.708178997039795,
105
+ "learning_rate": 8.647058823529412e-06,
106
+ "loss": 14.0757,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 2.344422700587084,
111
+ "grad_norm": 5.40604829788208,
112
+ "learning_rate": 6.882352941176471e-06,
113
+ "loss": 13.899,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 2.5009784735812133,
118
+ "grad_norm": 5.536667823791504,
119
+ "learning_rate": 5.11764705882353e-06,
120
+ "loss": 14.1072,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 2.6575342465753424,
125
+ "grad_norm": 5.577488422393799,
126
+ "learning_rate": 3.3529411764705886e-06,
127
+ "loss": 14.3544,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 2.8140900195694716,
132
+ "grad_norm": 6.25947380065918,
133
+ "learning_rate": 1.5882352941176472e-06,
134
+ "loss": 13.7119,
135
+ "step": 180
136
+ }
137
+ ],
138
+ "logging_steps": 10,
139
+ "max_steps": 189,
140
+ "num_input_tokens_seen": 0,
141
+ "num_train_epochs": 3,
142
+ "save_steps": 500,
143
+ "stateful_callbacks": {
144
+ "TrainerControl": {
145
+ "args": {
146
+ "should_epoch_stop": false,
147
+ "should_evaluate": false,
148
+ "should_log": false,
149
+ "should_save": true,
150
+ "should_training_stop": true
151
+ },
152
+ "attributes": {}
153
+ }
154
+ },
155
+ "total_flos": 2.535639329417011e+16,
156
+ "train_batch_size": 1,
157
+ "trial_name": null,
158
+ "trial_params": null
159
+ }