Hugging Face's logo

kostiantynk1205
/
07c314aa-7f69-4443-b58d-c116a485cc31

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
07c314aa-7f69-4443-b58d-c116a485cc31
File size: 3,176 Bytes 
eff2ed6
 
 
4c8dc7d
eff2ed6
4c8dc7d
eff2ed6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e61c2ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e34f87f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4c8dc7d
 
 
 
 
 
 
eff2ed6
 
 
 
 
 
 
 
 
 
 
 
 
 
4c8dc7d
eff2ed6
 
 
 
4c8dc7d
eff2ed6
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006520286240565961,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.520286240565961e-05,
      "grad_norm": 4.0287657611770555e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 6.520286240565961e-05,
      "eval_loss": 11.5,
      "eval_runtime": 36.5202,
      "eval_samples_per_second": 176.834,
      "eval_steps_per_second": 88.417,
      "step": 1
    },
    {
      "epoch": 0.00013040572481131922,
      "grad_norm": 1.8807237211149186e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.00019560858721697882,
      "grad_norm": 3.044315417355392e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.00019560858721697882,
      "eval_loss": 11.5,
      "eval_runtime": 36.5784,
      "eval_samples_per_second": 176.552,
      "eval_steps_per_second": 88.276,
      "step": 3
    },
    {
      "epoch": 0.00026081144962263844,
      "grad_norm": 3.73293187294621e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.00032601431202829807,
      "grad_norm": 2.4770373784122057e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.00039121717443395764,
      "grad_norm": 2.662832775968127e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.00039121717443395764,
      "eval_loss": 11.5,
      "eval_runtime": 36.5527,
      "eval_samples_per_second": 176.676,
      "eval_steps_per_second": 88.338,
      "step": 6
    },
    {
      "epoch": 0.00045642003683961726,
      "grad_norm": 2.7896492611034773e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0005216228992452769,
      "grad_norm": 1.936236731125973e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0005868257616509365,
      "grad_norm": 2.1733101675636135e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0005868257616509365,
      "eval_loss": 11.5,
      "eval_runtime": 36.231,
      "eval_samples_per_second": 178.245,
      "eval_steps_per_second": 89.122,
      "step": 9
    },
    {
      "epoch": 0.0006520286240565961,
      "grad_norm": 4.696622272604145e-05,
      "learning_rate": 0.0002,
      "loss": 46.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 199228784640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}