Hugging Face's logo

tianzhechu
/
VIRL-L-Init

Safetensors
mllama
Model card Files Community
1
tianzhechu commited on
Commit
7a370e4
·
verified ·
1 Parent(s): 7f749c4

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +208 -0
trainer_state.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.625,
5
+ "eval_steps": 500,
6
+ "global_step": 25,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.025,
13
+ "grad_norm": 135.99700927734375,
14
+ "learning_rate": 0.0,
15
+ "loss": 1.8567,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.05,
20
+ "grad_norm": 132.19590759277344,
21
+ "learning_rate": 1e-06,
22
+ "loss": 1.6451,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.075,
27
+ "grad_norm": 126.63935852050781,
28
+ "learning_rate": 1e-06,
29
+ "loss": 1.6308,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.1,
34
+ "grad_norm": 132.1169891357422,
35
+ "learning_rate": 1e-06,
36
+ "loss": 1.1376,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.125,
41
+ "grad_norm": 111.94847869873047,
42
+ "learning_rate": 1e-06,
43
+ "loss": 0.9303,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.15,
48
+ "grad_norm": 47.188209533691406,
49
+ "learning_rate": 1e-06,
50
+ "loss": 0.5403,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.175,
55
+ "grad_norm": 32.26974868774414,
56
+ "learning_rate": 1e-06,
57
+ "loss": 0.4366,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.2,
62
+ "grad_norm": 26.274761199951172,
63
+ "learning_rate": 1e-06,
64
+ "loss": 0.3587,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.225,
69
+ "grad_norm": 26.633220672607422,
70
+ "learning_rate": 1e-06,
71
+ "loss": 0.3009,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.25,
76
+ "grad_norm": 19.493844985961914,
77
+ "learning_rate": 1e-06,
78
+ "loss": 0.091,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.275,
83
+ "grad_norm": 9.516935348510742,
84
+ "learning_rate": 1e-06,
85
+ "loss": 0.045,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.3,
90
+ "grad_norm": 5.694634914398193,
91
+ "learning_rate": 1e-06,
92
+ "loss": 0.0358,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.325,
97
+ "grad_norm": 3.269968271255493,
98
+ "learning_rate": 1e-06,
99
+ "loss": 0.0218,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.35,
104
+ "grad_norm": 2.6145660877227783,
105
+ "learning_rate": 1e-06,
106
+ "loss": 0.0161,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.375,
111
+ "grad_norm": 2.1988866329193115,
112
+ "learning_rate": 1e-06,
113
+ "loss": 0.0141,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.4,
118
+ "grad_norm": 1.8373610973358154,
119
+ "learning_rate": 1e-06,
120
+ "loss": 0.0061,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.425,
125
+ "grad_norm": 1.4379240274429321,
126
+ "learning_rate": 1e-06,
127
+ "loss": 0.0065,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.45,
132
+ "grad_norm": 1.604111671447754,
133
+ "learning_rate": 1e-06,
134
+ "loss": 0.0062,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.475,
139
+ "grad_norm": 2.3964450359344482,
140
+ "learning_rate": 1e-06,
141
+ "loss": 0.0062,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.5,
146
+ "grad_norm": 1.2232977151870728,
147
+ "learning_rate": 1e-06,
148
+ "loss": 0.0042,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.525,
153
+ "grad_norm": 2.4161126613616943,
154
+ "learning_rate": 1e-06,
155
+ "loss": 0.0044,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.55,
160
+ "grad_norm": 1.5427428483963013,
161
+ "learning_rate": 1e-06,
162
+ "loss": 0.0031,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.575,
167
+ "grad_norm": 0.6795447468757629,
168
+ "learning_rate": 1e-06,
169
+ "loss": 0.0008,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.6,
174
+ "grad_norm": 0.4597806930541992,
175
+ "learning_rate": 1e-06,
176
+ "loss": 0.0009,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.625,
181
+ "grad_norm": 1.3745927810668945,
182
+ "learning_rate": 1e-06,
183
+ "loss": 0.004,
184
+ "step": 25
185
+ }
186
+ ],
187
+ "logging_steps": 1.0,
188
+ "max_steps": 40,
189
+ "num_input_tokens_seen": 0,
190
+ "num_train_epochs": 1,
191
+ "save_steps": 5,
192
+ "stateful_callbacks": {
193
+ "TrainerControl": {
194
+ "args": {
195
+ "should_epoch_stop": false,
196
+ "should_evaluate": false,
197
+ "should_log": false,
198
+ "should_save": true,
199
+ "should_training_stop": false
200
+ },
201
+ "attributes": {}
202
+ }
203
+ },
204
+ "total_flos": 13389019086848.0,
205
+ "train_batch_size": 16,
206
+ "trial_name": null,
207
+ "trial_params": null
208
+ }