Hugging Face's logo

Hanzalwi
/
bloom-1b-finetuned-aings-validation-automatic-try-3

PEFT
TensorBoard
Safetensors
bloom
Model card Files Metrics Community
bloom-1b-finetuned-aings-validation-automatic-try-3
File size: 3,239 Bytes 
f6f8270
71c7262
 
 
f6f8270
71c7262
f6f8270
 
 
 
 
 
 
990f638
f6f8270
 
 
 
990f638
 
 
 
f6f8270
7e0fe42
 
 
 
 
 
 
 
 
 
 
 
 
 
6ca75a1
 
 
 
 
 
 
 
 
 
 
 
 
 
a40b02a
 
 
 
 
 
 
 
 
 
 
 
 
 
cb7864f
 
 
 
 
 
 
 
 
 
 
 
 
 
1d7d2d6
 
 
 
 
 
 
 
 
 
 
 
 
 
6b2611d
 
 
 
 
 
 
 
 
 
 
 
 
 
7a65ebf
 
 
 
 
 
 
 
 
 
 
 
 
 
71c7262
 
 
 
 
 
 
 
 
 
 
 
 
 
f6f8270
 
 
 
 
 
 
71c7262
f6f8270
 
 
 
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
 
{
  "best_metric": 1.9468154907226562,
  "best_model_checkpoint": "./outputs/checkpoint-900",
  "epoch": 1.2784090909090908,
  "eval_steps": 100,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.4493,
      "step": 100
    },
    {
      "epoch": 0.14,
      "eval_loss": 2.11466121673584,
      "eval_runtime": 56.3914,
      "eval_samples_per_second": 26.458,
      "eval_steps_per_second": 3.316,
      "step": 100
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 2.253,
      "step": 200
    },
    {
      "epoch": 0.28,
      "eval_loss": 2.072767734527588,
      "eval_runtime": 54.1215,
      "eval_samples_per_second": 27.568,
      "eval_steps_per_second": 3.455,
      "step": 200
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 2.2227,
      "step": 300
    },
    {
      "epoch": 0.43,
      "eval_loss": 2.044309616088867,
      "eval_runtime": 54.0469,
      "eval_samples_per_second": 27.606,
      "eval_steps_per_second": 3.46,
      "step": 300
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 2.1901,
      "step": 400
    },
    {
      "epoch": 0.57,
      "eval_loss": 2.029090642929077,
      "eval_runtime": 54.0385,
      "eval_samples_per_second": 27.61,
      "eval_steps_per_second": 3.46,
      "step": 400
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 2.1699,
      "step": 500
    },
    {
      "epoch": 0.71,
      "eval_loss": 2.004894971847534,
      "eval_runtime": 54.1383,
      "eval_samples_per_second": 27.559,
      "eval_steps_per_second": 3.454,
      "step": 500
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 2.1541,
      "step": 600
    },
    {
      "epoch": 0.85,
      "eval_loss": 1.9869917631149292,
      "eval_runtime": 53.9116,
      "eval_samples_per_second": 27.675,
      "eval_steps_per_second": 3.469,
      "step": 600
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 2.133,
      "step": 700
    },
    {
      "epoch": 0.99,
      "eval_loss": 1.9750773906707764,
      "eval_runtime": 53.9551,
      "eval_samples_per_second": 27.653,
      "eval_steps_per_second": 3.466,
      "step": 700
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 2.1014,
      "step": 800
    },
    {
      "epoch": 1.14,
      "eval_loss": 1.960465431213379,
      "eval_runtime": 54.1302,
      "eval_samples_per_second": 27.563,
      "eval_steps_per_second": 3.455,
      "step": 800
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 2.0742,
      "step": 900
    },
    {
      "epoch": 1.28,
      "eval_loss": 1.9468154907226562,
      "eval_runtime": 75.283,
      "eval_samples_per_second": 19.819,
      "eval_steps_per_second": 2.484,
      "step": 900
    }
  ],
  "logging_steps": 100,
  "max_steps": 2112,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 2.739447726317568e+16,
  "trial_name": null,
  "trial_params": null
}