Hugging Face's logo

Hanzalwi
/
bloom-1b-finetuned-aings-validation-automatic-try-4

PEFT
TensorBoard
Safetensors
bloom
Model card Files Metrics Community
bloom-1b-finetuned-aings-validation-automatic-try-4
File size: 3,569 Bytes 
f6ad367
2cbadc8
 
 
f6ad367
2cbadc8
f6ad367
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79d5000
 
 
 
 
 
 
 
 
 
 
 
 
 
baf348e
 
 
 
 
 
 
 
 
 
 
 
 
 
ec097cb
 
 
 
 
 
 
 
 
 
 
 
 
 
c68fe9b
 
 
 
 
 
 
 
 
 
 
 
 
 
6dffe39
 
 
 
 
 
 
 
 
 
 
 
 
 
140b209
 
 
 
 
 
 
 
 
 
 
 
 
 
edc4276
 
 
 
 
 
 
 
 
 
 
 
 
 
cc93e0e
 
 
 
 
 
 
 
 
 
 
 
 
 
2cbadc8
 
 
 
 
 
 
 
 
 
 
 
 
 
f6ad367
 
 
 
 
 
 
2cbadc8
f6ad367
 
 
 
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
 
{
  "best_metric": 0.9894721508026123,
  "best_model_checkpoint": "./outputs/checkpoint-1000",
  "epoch": 1.4204545454545454,
  "eval_steps": 100,
  "global_step": 1000,
  "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": 1.5808,
      "step": 100
    },
    {
      "epoch": 0.14,
      "eval_loss": 1.0812042951583862,
      "eval_runtime": 127.4925,
      "eval_samples_per_second": 11.703,
      "eval_steps_per_second": 1.467,
      "step": 100
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 1.2145,
      "step": 200
    },
    {
      "epoch": 0.28,
      "eval_loss": 1.0592867136001587,
      "eval_runtime": 124.4418,
      "eval_samples_per_second": 11.99,
      "eval_steps_per_second": 1.503,
      "step": 200
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 1.201,
      "step": 300
    },
    {
      "epoch": 0.43,
      "eval_loss": 1.0460368394851685,
      "eval_runtime": 124.1855,
      "eval_samples_per_second": 12.014,
      "eval_steps_per_second": 1.506,
      "step": 300
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 1.1833,
      "step": 400
    },
    {
      "epoch": 0.57,
      "eval_loss": 1.0355255603790283,
      "eval_runtime": 124.2488,
      "eval_samples_per_second": 12.008,
      "eval_steps_per_second": 1.505,
      "step": 400
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 1.1733,
      "step": 500
    },
    {
      "epoch": 0.71,
      "eval_loss": 1.0230828523635864,
      "eval_runtime": 124.322,
      "eval_samples_per_second": 12.001,
      "eval_steps_per_second": 1.504,
      "step": 500
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002,
      "loss": 1.1612,
      "step": 600
    },
    {
      "epoch": 0.85,
      "eval_loss": 1.0142004489898682,
      "eval_runtime": 124.2613,
      "eval_samples_per_second": 12.007,
      "eval_steps_per_second": 1.505,
      "step": 600
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 1.1492,
      "step": 700
    },
    {
      "epoch": 0.99,
      "eval_loss": 1.0080314874649048,
      "eval_runtime": 124.2662,
      "eval_samples_per_second": 12.006,
      "eval_steps_per_second": 1.505,
      "step": 700
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 1.1391,
      "step": 800
    },
    {
      "epoch": 1.14,
      "eval_loss": 1.0012787580490112,
      "eval_runtime": 124.3175,
      "eval_samples_per_second": 12.002,
      "eval_steps_per_second": 1.504,
      "step": 800
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0002,
      "loss": 1.1154,
      "step": 900
    },
    {
      "epoch": 1.28,
      "eval_loss": 0.9947501420974731,
      "eval_runtime": 124.3492,
      "eval_samples_per_second": 11.998,
      "eval_steps_per_second": 1.504,
      "step": 900
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0002,
      "loss": 1.1179,
      "step": 1000
    },
    {
      "epoch": 1.42,
      "eval_loss": 0.9894721508026123,
      "eval_runtime": 124.1464,
      "eval_samples_per_second": 12.018,
      "eval_steps_per_second": 1.506,
      "step": 1000
    }
  ],
  "logging_steps": 100,
  "max_steps": 2112,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 5.620616308242432e+16,
  "trial_name": null,
  "trial_params": null
}