Hugging Face's logo

anish002
/
gemma-3-1b-it_checkpoint

PEFT
Safetensors
Model card Files Community
anish002 commited on
Commit
3c2d9dd
·
verified ·
1 Parent(s): 7ad7c3f

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +202 -0
trainer_state.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 10.0,
6
+ "eval_steps": 500,
7
+ "global_step": 12260,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.4078303425774878,
14
+ "grad_norm": 14.478927612304688,
15
+ "learning_rate": 0.00019993920556849446,
16
+ "loss": 0.8999,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.8156606851549756,
21
+ "grad_norm": 2.973954200744629,
22
+ "learning_rate": 0.00019860945509081267,
23
+ "loss": 0.376,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 1.2234910277324633,
28
+ "grad_norm": 0.7534143924713135,
29
+ "learning_rate": 0.0001955617290630555,
30
+ "loss": 0.2706,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.631321370309951,
35
+ "grad_norm": 0.533855140209198,
36
+ "learning_rate": 0.00019084912501825553,
37
+ "loss": 0.2597,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 2.039151712887439,
42
+ "grad_norm": 1.9753663539886475,
43
+ "learning_rate": 0.0001845537460216685,
44
+ "loss": 0.2481,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 2.4469820554649266,
49
+ "grad_norm": 2.5512447357177734,
50
+ "learning_rate": 0.00017678527026981862,
51
+ "loss": 0.1971,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 2.8548123980424145,
56
+ "grad_norm": 1.973365068435669,
57
+ "learning_rate": 0.000167679040275153,
58
+ "loss": 0.1924,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 3.262642740619902,
63
+ "grad_norm": 1.4714034795761108,
64
+ "learning_rate": 0.0001573937049265616,
65
+ "loss": 0.1546,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 3.6704730831973897,
70
+ "grad_norm": 0.18751826882362366,
71
+ "learning_rate": 0.00014610845550582294,
72
+ "loss": 0.156,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 4.078303425774878,
77
+ "grad_norm": 3.124044895172119,
78
+ "learning_rate": 0.00013401990381414286,
79
+ "loss": 0.1549,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 4.486133768352365,
84
+ "grad_norm": 0.6213807463645935,
85
+ "learning_rate": 0.00012133865679811696,
86
+ "loss": 0.1253,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 4.893964110929853,
91
+ "grad_norm": 1.664085030555725,
92
+ "learning_rate": 0.00010828564735203954,
93
+ "loss": 0.1266,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 5.301794453507341,
98
+ "grad_norm": 0.2742406725883484,
99
+ "learning_rate": 9.508828522138191e-05,
100
+ "loss": 0.1109,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 5.709624796084829,
105
+ "grad_norm": 0.24402563273906708,
106
+ "learning_rate": 8.19764950664627e-05,
107
+ "loss": 0.1081,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 6.117455138662317,
112
+ "grad_norm": 2.361426830291748,
113
+ "learning_rate": 6.91787107112304e-05,
114
+ "loss": 0.0916,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 6.525285481239804,
119
+ "grad_norm": 1.8119088411331177,
120
+ "learning_rate": 5.69178953654216e-05,
121
+ "loss": 0.0881,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 6.933115823817292,
126
+ "grad_norm": 1.1984834671020508,
127
+ "learning_rate": 4.540765715585027e-05,
128
+ "loss": 0.0828,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 7.3409461663947795,
133
+ "grad_norm": 0.19523586332798004,
134
+ "learning_rate": 3.484852764210548e-05,
135
+ "loss": 0.074,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 7.748776508972267,
140
+ "grad_norm": 0.11153391003608704,
141
+ "learning_rate": 2.542446815241867e-05,
142
+ "loss": 0.0721,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 8.156606851549755,
147
+ "grad_norm": 0.17387154698371887,
148
+ "learning_rate": 1.729966480637476e-05,
149
+ "loss": 0.0749,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 8.564437194127244,
154
+ "grad_norm": 0.8619000315666199,
155
+ "learning_rate": 1.0615668061633398e-05,
156
+ "loss": 0.0632,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 8.97226753670473,
161
+ "grad_norm": 0.3366154432296753,
162
+ "learning_rate": 5.488926619525248e-06,
163
+ "loss": 0.0658,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 9.380097879282218,
168
+ "grad_norm": 0.2561167776584625,
169
+ "learning_rate": 2.008758653860221e-06,
170
+ "loss": 0.0608,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 9.787928221859707,
175
+ "grad_norm": 0.24642044305801392,
176
+ "learning_rate": 2.3579570823278885e-07,
177
+ "loss": 0.0594,
178
+ "step": 12000
179
+ }
180
+ ],
181
+ "logging_steps": 500,
182
+ "max_steps": 12260,
183
+ "num_input_tokens_seen": 0,
184
+ "num_train_epochs": 10,
185
+ "save_steps": 2000,
186
+ "stateful_callbacks": {
187
+ "TrainerControl": {
188
+ "args": {
189
+ "should_epoch_stop": false,
190
+ "should_evaluate": false,
191
+ "should_log": false,
192
+ "should_save": true,
193
+ "should_training_stop": true
194
+ },
195
+ "attributes": {}
196
+ }
197
+ },
198
+ "total_flos": 1.03414156147584e+16,
199
+ "train_batch_size": 1,
200
+ "trial_name": null,
201
+ "trial_params": null
202
+ }