Hugging Face's logo

andrealexroom
/
AnswerMethod_v1.0.3.13_88

Safetensors
Model card Files
xet
Community
AnswerMethod_v1.0.3.13_88
File size: 2,403 Bytes 
3039092
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9723756906077348,
  "eval_steps": 22,
  "global_step": 88,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011049723756906077,
      "grad_norm": 0.24585983157157898,
      "learning_rate": 0.0005,
      "loss": 0.7653,
      "step": 1
    },
    {
      "epoch": 0.2430939226519337,
      "grad_norm": 0.32683706283569336,
      "learning_rate": 0.0005,
      "loss": 0.6442,
      "step": 22
    },
    {
      "epoch": 0.2430939226519337,
      "eval_loss": 0.6002205014228821,
      "eval_runtime": 264.7454,
      "eval_samples_per_second": 0.317,
      "eval_steps_per_second": 0.317,
      "step": 22
    },
    {
      "epoch": 0.4861878453038674,
      "grad_norm": 0.2470276653766632,
      "learning_rate": 0.0005,
      "loss": 0.5889,
      "step": 44
    },
    {
      "epoch": 0.4861878453038674,
      "eval_loss": 0.5837110877037048,
      "eval_runtime": 264.3289,
      "eval_samples_per_second": 0.318,
      "eval_steps_per_second": 0.318,
      "step": 44
    },
    {
      "epoch": 0.7292817679558011,
      "grad_norm": 0.2570318579673767,
      "learning_rate": 0.0005,
      "loss": 0.5855,
      "step": 66
    },
    {
      "epoch": 0.7292817679558011,
      "eval_loss": 0.5752720832824707,
      "eval_runtime": 264.2764,
      "eval_samples_per_second": 0.318,
      "eval_steps_per_second": 0.318,
      "step": 66
    },
    {
      "epoch": 0.9723756906077348,
      "grad_norm": 0.25765955448150635,
      "learning_rate": 0.0005,
      "loss": 0.5533,
      "step": 88
    },
    {
      "epoch": 0.9723756906077348,
      "eval_loss": 0.5659109950065613,
      "eval_runtime": 264.6141,
      "eval_samples_per_second": 0.317,
      "eval_steps_per_second": 0.317,
      "step": 88
    }
  ],
  "logging_steps": 22,
  "max_steps": 270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 22,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.9250732494494515e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}