Hugging Face's logo

OEvortex
/
HelpingAI-unvelite

Text Generation
Transformers
PyTorch
Safetensors
English
Hindi
llama
HelpingAI
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
1
Abhaykoul commited on
Commit
4dd8b3d
•
1 Parent(s): a9cb5a6

Upload 2 files

Browse files
Files changed (2) hide show
  1. trainer_state.json +179 -0
  2. training_args (1).bin +3 -0
trainer_state.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.00012304421224634436,
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": 0.0,
13
+ "learning_rate": 2e-05,
14
+ "loss": 1.3413,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.5983,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.0,
25
+ "learning_rate": 6e-05,
26
+ "loss": 1.5431,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.0,
31
+ "learning_rate": 8e-05,
32
+ "loss": 1.7992,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.0,
37
+ "learning_rate": 0.0001,
38
+ "loss": 1.2091,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.0,
43
+ "learning_rate": 0.00012,
44
+ "loss": 2.7719,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.0,
49
+ "learning_rate": 0.00012,
50
+ "loss": 3.317,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.0,
55
+ "learning_rate": 0.00014,
56
+ "loss": 1.1447,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.0,
61
+ "learning_rate": 0.00016,
62
+ "loss": 1.4177,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.0,
67
+ "learning_rate": 0.00018,
68
+ "loss": 1.851,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.0,
73
+ "learning_rate": 0.0002,
74
+ "loss": 1.9526,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.0,
79
+ "learning_rate": 0.00019781476007338058,
80
+ "loss": 1.7479,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.0,
85
+ "learning_rate": 0.0001913545457642601,
86
+ "loss": 1.3683,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.0,
91
+ "learning_rate": 0.00018090169943749476,
92
+ "loss": 0.527,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.0,
97
+ "learning_rate": 0.00016691306063588583,
98
+ "loss": 2.01,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.0,
103
+ "learning_rate": 0.00015000000000000001,
104
+ "loss": 1.2848,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.0,
109
+ "learning_rate": 0.00013090169943749476,
110
+ "loss": 1.2189,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.0,
115
+ "learning_rate": 0.00011045284632676536,
116
+ "loss": 1.4882,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.0,
121
+ "learning_rate": 8.954715367323468e-05,
122
+ "loss": 0.5045,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.0,
127
+ "learning_rate": 6.909830056250527e-05,
128
+ "loss": 1.454,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.0,
133
+ "learning_rate": 5.000000000000002e-05,
134
+ "loss": 1.2887,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.0,
139
+ "learning_rate": 3.308693936411421e-05,
140
+ "loss": 0.8272,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.0,
145
+ "learning_rate": 1.9098300562505266e-05,
146
+ "loss": 1.6697,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.0,
151
+ "learning_rate": 8.645454235739903e-06,
152
+ "loss": 1.6019,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.0,
157
+ "learning_rate": 2.1852399266194314e-06,
158
+ "loss": 1.0745,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.0,
163
+ "eval_loss": NaN,
164
+ "eval_runtime": 4150.2492,
165
+ "eval_samples_per_second": 11.575,
166
+ "eval_steps_per_second": 11.575,
167
+ "step": 25
168
+ }
169
+ ],
170
+ "logging_steps": 1,
171
+ "max_steps": 25,
172
+ "num_input_tokens_seen": 0,
173
+ "num_train_epochs": 1,
174
+ "save_steps": 500,
175
+ "total_flos": 183123718963200.0,
176
+ "train_batch_size": 1,
177
+ "trial_name": null,
178
+ "trial_params": null
179
+ }
training_args (1).bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35287ef26a7dfcc015e0237824a0fa49982706609ab72610ad14222df433fe99
3
+ size 4859