Hugging Face's logo

Hanzalwi
/
bloom-1b-finetuned-aings-validation-data

PEFT
TensorBoard
Safetensors
bloom
Model card Files Metrics Community
bloom-1b-finetuned-aings-validation-data
File size: 3,871 Bytes 
47b01f4
e818a32
 
 
47b01f4
e818a32
47b01f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e0803ad
 
 
 
 
 
 
 
 
 
 
 
 
 
b2ce0e7
 
 
 
 
 
 
 
 
 
 
 
 
 
3569b41
 
 
 
 
 
 
 
 
 
 
 
 
 
d3a2dcf
 
 
 
 
 
 
 
 
 
 
 
 
 
a14f1e8
 
 
 
 
 
 
 
 
 
 
 
 
 
5c6081e
 
 
 
 
 
 
 
 
 
 
 
 
 
b261436
 
 
 
 
 
 
 
 
 
 
 
 
 
78920ce
 
 
 
 
 
 
 
 
 
 
 
 
 
f195306
 
 
 
 
 
 
 
 
 
 
 
 
 
e818a32
 
 
 
 
 
 
 
 
 
 
 
 
 
47b01f4
 
 
 
 
 
 
e818a32
47b01f4
 
 
 
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
 
{
  "best_metric": 1.3373662233352661,
  "best_model_checkpoint": "./outputs/checkpoint-1100",
  "epoch": 1.4666666666666668,
  "eval_steps": 100,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0002,
      "loss": 1.3509,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.4751445055007935,
      "eval_runtime": 155.0414,
      "eval_samples_per_second": 12.448,
      "eval_steps_per_second": 1.561,
      "step": 100
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002,
      "loss": 1.2006,
      "step": 200
    },
    {
      "epoch": 0.27,
      "eval_loss": 1.441214680671692,
      "eval_runtime": 151.6424,
      "eval_samples_per_second": 12.727,
      "eval_steps_per_second": 1.596,
      "step": 200
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.1801,
      "step": 300
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.4250988960266113,
      "eval_runtime": 151.7377,
      "eval_samples_per_second": 12.719,
      "eval_steps_per_second": 1.595,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0002,
      "loss": 1.1655,
      "step": 400
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.4099382162094116,
      "eval_runtime": 151.5335,
      "eval_samples_per_second": 12.736,
      "eval_steps_per_second": 1.597,
      "step": 400
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.1486,
      "step": 500
    },
    {
      "epoch": 0.67,
      "eval_loss": 1.3928134441375732,
      "eval_runtime": 151.678,
      "eval_samples_per_second": 12.724,
      "eval_steps_per_second": 1.595,
      "step": 500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 1.1421,
      "step": 600
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.379417896270752,
      "eval_runtime": 151.6496,
      "eval_samples_per_second": 12.727,
      "eval_steps_per_second": 1.596,
      "step": 600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 1.1333,
      "step": 700
    },
    {
      "epoch": 0.93,
      "eval_loss": 1.3729456663131714,
      "eval_runtime": 151.5395,
      "eval_samples_per_second": 12.736,
      "eval_steps_per_second": 1.597,
      "step": 700
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 1.1179,
      "step": 800
    },
    {
      "epoch": 1.07,
      "eval_loss": 1.359381914138794,
      "eval_runtime": 151.6759,
      "eval_samples_per_second": 12.725,
      "eval_steps_per_second": 1.596,
      "step": 800
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0002,
      "loss": 1.1028,
      "step": 900
    },
    {
      "epoch": 1.2,
      "eval_loss": 1.3538635969161987,
      "eval_runtime": 151.6567,
      "eval_samples_per_second": 12.726,
      "eval_steps_per_second": 1.596,
      "step": 900
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 1.0936,
      "step": 1000
    },
    {
      "epoch": 1.33,
      "eval_loss": 1.3417681455612183,
      "eval_runtime": 151.5959,
      "eval_samples_per_second": 12.731,
      "eval_steps_per_second": 1.596,
      "step": 1000
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 1.1035,
      "step": 1100
    },
    {
      "epoch": 1.47,
      "eval_loss": 1.3373662233352661,
      "eval_runtime": 151.8187,
      "eval_samples_per_second": 12.713,
      "eval_steps_per_second": 1.594,
      "step": 1100
    }
  ],
  "logging_steps": 100,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 7.013163020838912e+16,
  "trial_name": null,
  "trial_params": null
}