Hugging Face's logo

andrealexroom
/
AnswerMethod_v1.0.3.7_128

Safetensors
Model card Files
xet
Community
AnswerMethod_v1.0.3.7_128
File size: 3,629 Bytes 
e8969f9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 16,
  "global_step": 128,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015625,
      "grad_norm": 0.1416465789079666,
      "learning_rate": 0.0005,
      "loss": 0.6936,
      "step": 1
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.48029133677482605,
      "learning_rate": 0.0005,
      "loss": 0.6521,
      "step": 16
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.5866118669509888,
      "eval_runtime": 211.247,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 16
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.26290011405944824,
      "learning_rate": 0.0005,
      "loss": 0.5821,
      "step": 32
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.5616697072982788,
      "eval_runtime": 211.0712,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 32
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.2908053696155548,
      "learning_rate": 0.0005,
      "loss": 0.6006,
      "step": 48
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.5537130236625671,
      "eval_runtime": 211.1601,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 48
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2542905807495117,
      "learning_rate": 0.0005,
      "loss": 0.5708,
      "step": 64
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5481152534484863,
      "eval_runtime": 211.1765,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 64
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.44674304127693176,
      "learning_rate": 0.0005,
      "loss": 0.467,
      "step": 80
    },
    {
      "epoch": 1.25,
      "eval_loss": 0.5612103343009949,
      "eval_runtime": 211.1862,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 80
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.36239078640937805,
      "learning_rate": 0.0005,
      "loss": 0.4704,
      "step": 96
    },
    {
      "epoch": 1.5,
      "eval_loss": 0.564439594745636,
      "eval_runtime": 211.1729,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 96
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.4066231846809387,
      "learning_rate": 0.0005,
      "loss": 0.466,
      "step": 112
    },
    {
      "epoch": 1.75,
      "eval_loss": 0.5655233263969421,
      "eval_runtime": 211.1865,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 112
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3407813310623169,
      "learning_rate": 0.0005,
      "loss": 0.4697,
      "step": 128
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5586457252502441,
      "eval_runtime": 211.1864,
      "eval_samples_per_second": 0.303,
      "eval_steps_per_second": 0.303,
      "step": 128
    }
  ],
  "logging_steps": 16,
  "max_steps": 192,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 16,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.013060353710162e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}