Hugging Face's logo

htahir1
/
peft-lora-zencoder15B-A100-40GB

PEFT
Safetensors
Model card Files Community
peft-lora-zencoder15B-A100-40GB
File size: 3,880 Bytes 
fc4465d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.8745,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019979028262377118,
      "loss": 0.8093,
      "step": 50
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019893981312363562,
      "loss": 0.7357,
      "step": 75
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019744105246469263,
      "loss": 0.7535,
      "step": 100
    },
    {
      "epoch": 0.1,
      "eval_loss": 0.4003306031227112,
      "eval_runtime": 1.7839,
      "eval_samples_per_second": 2.242,
      "eval_steps_per_second": 0.561,
      "step": 100
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001953038210948861,
      "loss": 0.7249,
      "step": 125
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019254212296427044,
      "loss": 0.7118,
      "step": 150
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00018917405376582145,
      "loss": 0.7467,
      "step": 175
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00018522168236559695,
      "loss": 0.6714,
      "step": 200
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.3684937059879303,
      "eval_runtime": 1.7853,
      "eval_samples_per_second": 2.24,
      "eval_steps_per_second": 0.56,
      "step": 200
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018071090619916093,
      "loss": 0.654,
      "step": 225
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00017567128158176953,
      "loss": 0.6392,
      "step": 250
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00017013583004418993,
      "loss": 0.5745,
      "step": 275
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.000164140821963114,
      "loss": 0.5364,
      "step": 300
    },
    {
      "epoch": 0.3,
      "eval_loss": 0.3665352761745453,
      "eval_runtime": 1.7852,
      "eval_samples_per_second": 2.241,
      "eval_steps_per_second": 0.56,
      "step": 300
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00015772553890390197,
      "loss": 0.5693,
      "step": 325
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00015093201623287631,
      "loss": 0.563,
      "step": 350
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00014380476768566824,
      "loss": 0.5478,
      "step": 375
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00013639049369634876,
      "loss": 0.5763,
      "step": 400
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.3363753855228424,
      "eval_runtime": 1.7851,
      "eval_samples_per_second": 2.241,
      "eval_steps_per_second": 0.56,
      "step": 400
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00012873777539848283,
      "loss": 0.4891,
      "step": 425
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00012089675630312754,
      "loss": 0.5331,
      "step": 450
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00011291881373954065,
      "loss": 0.5679,
      "step": 475
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010485622221144484,
      "loss": 0.5982,
      "step": 500
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.3186224400997162,
      "eval_runtime": 1.7828,
      "eval_samples_per_second": 2.244,
      "eval_steps_per_second": 0.561,
      "step": 500
    }
  ],
  "logging_steps": 25,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 100,
  "total_flos": 7.46753649278976e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}