Hugging Face's logo

7flash
/
jan23-first

Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
mistral
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
jan23-first
File size: 2,786 Bytes 
6d7057d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.8248077630996704,
  "best_model_checkpoint": "./out/checkpoint-10",
  "epoch": 1.6521739130434783,
  "eval_steps": 2,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.9984,
      "step": 1
    },
    {
      "epoch": 0.17,
      "eval_loss": 1.09337317943573,
      "eval_runtime": 65.1601,
      "eval_samples_per_second": 1.535,
      "eval_steps_per_second": 0.767,
      "step": 1
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.9864,
      "step": 2
    },
    {
      "epoch": 0.35,
      "eval_loss": 1.0603257417678833,
      "eval_runtime": 66.8005,
      "eval_samples_per_second": 1.497,
      "eval_steps_per_second": 0.748,
      "step": 2
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.5e-06,
      "loss": 0.9692,
      "step": 3
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.9181,
      "step": 4
    },
    {
      "epoch": 0.7,
      "eval_loss": 0.9132175445556641,
      "eval_runtime": 65.6994,
      "eval_samples_per_second": 1.522,
      "eval_steps_per_second": 0.761,
      "step": 4
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.5e-06,
      "loss": 0.9237,
      "step": 5
    },
    {
      "epoch": 1.04,
      "learning_rate": 3e-06,
      "loss": 0.8843,
      "step": 6
    },
    {
      "epoch": 1.04,
      "eval_loss": 0.8623057007789612,
      "eval_runtime": 64.7101,
      "eval_samples_per_second": 1.545,
      "eval_steps_per_second": 0.773,
      "step": 6
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.5e-06,
      "loss": 0.8434,
      "step": 7
    },
    {
      "epoch": 1.3,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8513,
      "step": 8
    },
    {
      "epoch": 1.3,
      "eval_loss": 0.8309622406959534,
      "eval_runtime": 64.996,
      "eval_samples_per_second": 1.539,
      "eval_steps_per_second": 0.769,
      "step": 8
    },
    {
      "epoch": 1.48,
      "learning_rate": 4.5e-06,
      "loss": 0.8174,
      "step": 9
    },
    {
      "epoch": 1.65,
      "learning_rate": 5e-06,
      "loss": 0.7957,
      "step": 10
    },
    {
      "epoch": 1.65,
      "eval_loss": 0.8248077630996704,
      "eval_runtime": 65.0362,
      "eval_samples_per_second": 1.538,
      "eval_steps_per_second": 0.769,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 5,
  "total_flos": 2.796025320308736e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}