Hugging Face's logo

andrealexroom
/
AnswerMethod_v1.0.3.11_147

Safetensors
Model card Files
xet
Community
AnswerMethod_v1.0.3.11_147
File size: 3,451 Bytes 
3baf612
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.6896551724137931,
  "eval_steps": 21,
  "global_step": 147,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011494252873563218,
      "grad_norm": 0.14453125,
      "learning_rate": 0.0005,
      "loss": 0.6735,
      "step": 1
    },
    {
      "epoch": 0.2413793103448276,
      "grad_norm": 0.25390625,
      "learning_rate": 0.0005,
      "loss": 0.6075,
      "step": 21
    },
    {
      "epoch": 0.2413793103448276,
      "eval_loss": 0.5944878458976746,
      "eval_runtime": 243.3864,
      "eval_samples_per_second": 0.333,
      "eval_steps_per_second": 0.333,
      "step": 21
    },
    {
      "epoch": 0.4827586206896552,
      "grad_norm": 0.26953125,
      "learning_rate": 0.0005,
      "loss": 0.5843,
      "step": 42
    },
    {
      "epoch": 0.4827586206896552,
      "eval_loss": 0.5731382369995117,
      "eval_runtime": 242.7763,
      "eval_samples_per_second": 0.334,
      "eval_steps_per_second": 0.334,
      "step": 42
    },
    {
      "epoch": 0.7241379310344828,
      "grad_norm": 0.25390625,
      "learning_rate": 0.0005,
      "loss": 0.5643,
      "step": 63
    },
    {
      "epoch": 0.7241379310344828,
      "eval_loss": 0.5693779587745667,
      "eval_runtime": 242.4241,
      "eval_samples_per_second": 0.334,
      "eval_steps_per_second": 0.334,
      "step": 63
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 0.267578125,
      "learning_rate": 0.0005,
      "loss": 0.5705,
      "step": 84
    },
    {
      "epoch": 0.9655172413793104,
      "eval_loss": 0.563104510307312,
      "eval_runtime": 242.5946,
      "eval_samples_per_second": 0.334,
      "eval_steps_per_second": 0.334,
      "step": 84
    },
    {
      "epoch": 1.206896551724138,
      "grad_norm": 0.28125,
      "learning_rate": 0.0005,
      "loss": 0.4655,
      "step": 105
    },
    {
      "epoch": 1.206896551724138,
      "eval_loss": 0.5802934169769287,
      "eval_runtime": 242.4816,
      "eval_samples_per_second": 0.334,
      "eval_steps_per_second": 0.334,
      "step": 105
    },
    {
      "epoch": 1.4482758620689655,
      "grad_norm": 0.298828125,
      "learning_rate": 0.0005,
      "loss": 0.4694,
      "step": 126
    },
    {
      "epoch": 1.4482758620689655,
      "eval_loss": 0.5805184841156006,
      "eval_runtime": 242.4018,
      "eval_samples_per_second": 0.334,
      "eval_steps_per_second": 0.334,
      "step": 126
    },
    {
      "epoch": 1.6896551724137931,
      "grad_norm": 0.330078125,
      "learning_rate": 0.0005,
      "loss": 0.4568,
      "step": 147
    },
    {
      "epoch": 1.6896551724137931,
      "eval_loss": 0.5760032534599304,
      "eval_runtime": 242.3367,
      "eval_samples_per_second": 0.334,
      "eval_steps_per_second": 0.334,
      "step": 147
    }
  ],
  "logging_steps": 21,
  "max_steps": 261,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 21,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.46118484598825e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}