Hugging Face's logo

andrealexroom
/
AnswerMethod_v1.0.3.8_105

Safetensors
Model card Files
xet
Community
AnswerMethod_v1.0.3.8_105
File size: 3,523 Bytes 
3afe3b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6693227091633465,
  "eval_steps": 15,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01593625498007968,
      "grad_norm": 0.15623033046722412,
      "learning_rate": 0.0005,
      "loss": 0.7895,
      "step": 1
    },
    {
      "epoch": 0.23904382470119523,
      "grad_norm": 0.4118459224700928,
      "learning_rate": 0.0005,
      "loss": 0.639,
      "step": 15
    },
    {
      "epoch": 0.23904382470119523,
      "eval_loss": 0.5786148309707642,
      "eval_runtime": 203.1738,
      "eval_samples_per_second": 0.305,
      "eval_steps_per_second": 0.305,
      "step": 15
    },
    {
      "epoch": 0.47808764940239046,
      "grad_norm": 0.28019416332244873,
      "learning_rate": 0.0005,
      "loss": 0.6105,
      "step": 30
    },
    {
      "epoch": 0.47808764940239046,
      "eval_loss": 0.5625983476638794,
      "eval_runtime": 203.0773,
      "eval_samples_per_second": 0.305,
      "eval_steps_per_second": 0.305,
      "step": 30
    },
    {
      "epoch": 0.7171314741035857,
      "grad_norm": 0.302608460187912,
      "learning_rate": 0.0005,
      "loss": 0.5912,
      "step": 45
    },
    {
      "epoch": 0.7171314741035857,
      "eval_loss": 0.5549846887588501,
      "eval_runtime": 203.1082,
      "eval_samples_per_second": 0.305,
      "eval_steps_per_second": 0.305,
      "step": 45
    },
    {
      "epoch": 0.9561752988047809,
      "grad_norm": 0.27707505226135254,
      "learning_rate": 0.0005,
      "loss": 0.5778,
      "step": 60
    },
    {
      "epoch": 0.9561752988047809,
      "eval_loss": 0.5472670197486877,
      "eval_runtime": 203.1439,
      "eval_samples_per_second": 0.305,
      "eval_steps_per_second": 0.305,
      "step": 60
    },
    {
      "epoch": 1.1912350597609562,
      "grad_norm": 0.28894054889678955,
      "learning_rate": 0.0005,
      "loss": 0.4824,
      "step": 75
    },
    {
      "epoch": 1.1912350597609562,
      "eval_loss": 0.5558595061302185,
      "eval_runtime": 202.9842,
      "eval_samples_per_second": 0.305,
      "eval_steps_per_second": 0.305,
      "step": 75
    },
    {
      "epoch": 1.4302788844621515,
      "grad_norm": 0.31184110045433044,
      "learning_rate": 0.0005,
      "loss": 0.4642,
      "step": 90
    },
    {
      "epoch": 1.4302788844621515,
      "eval_loss": 0.5655969977378845,
      "eval_runtime": 203.0879,
      "eval_samples_per_second": 0.305,
      "eval_steps_per_second": 0.305,
      "step": 90
    },
    {
      "epoch": 1.6693227091633465,
      "grad_norm": 0.33053600788116455,
      "learning_rate": 0.0005,
      "loss": 0.4727,
      "step": 105
    },
    {
      "epoch": 1.6693227091633465,
      "eval_loss": 0.5597427487373352,
      "eval_runtime": 203.0614,
      "eval_samples_per_second": 0.305,
      "eval_steps_per_second": 0.305,
      "step": 105
    }
  ],
  "logging_steps": 15,
  "max_steps": 248,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.9661979026785075e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}