Hugging Face's logo

kostiantynk1205
/
2332d254-6cc4-46a3-a108-a67e87f80f9a

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
2332d254-6cc4-46a3-a108-a67e87f80f9a
File size: 3,161 Bytes 
a3e9c5f
 
 
8cb8b9d
a3e9c5f
8cb8b9d
a3e9c5f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff7367b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4fd6c66
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8cb8b9d
 
 
 
 
 
 
a3e9c5f
 
 
 
 
 
 
 
 
 
 
 
 
 
8cb8b9d
a3e9c5f
 
 
 
8cb8b9d
a3e9c5f
 
 
 
 
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": 0.003604902667627974,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003604902667627974,
      "grad_norm": 2.627377034514211e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0003604902667627974,
      "eval_loss": 11.5,
      "eval_runtime": 7.997,
      "eval_samples_per_second": 146.179,
      "eval_steps_per_second": 73.152,
      "step": 1
    },
    {
      "epoch": 0.0007209805335255948,
      "grad_norm": 1.59292158059543e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.0010814708002883922,
      "grad_norm": 2.913125354098156e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.0010814708002883922,
      "eval_loss": 11.5,
      "eval_runtime": 7.9318,
      "eval_samples_per_second": 147.382,
      "eval_steps_per_second": 73.754,
      "step": 3
    },
    {
      "epoch": 0.0014419610670511895,
      "grad_norm": 1.0232976819679607e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.001802451333813987,
      "grad_norm": 1.5346440704888664e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.0021629416005767843,
      "grad_norm": 1.547658939671237e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0021629416005767843,
      "eval_loss": 11.5,
      "eval_runtime": 8.0584,
      "eval_samples_per_second": 145.066,
      "eval_steps_per_second": 72.595,
      "step": 6
    },
    {
      "epoch": 0.0025234318673395817,
      "grad_norm": 1.8484262909623794e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.002883922134102379,
      "grad_norm": 2.8204764021211304e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.0032444124008651765,
      "grad_norm": 1.7167012629215606e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0032444124008651765,
      "eval_loss": 11.5,
      "eval_runtime": 8.0617,
      "eval_samples_per_second": 145.007,
      "eval_steps_per_second": 72.566,
      "step": 9
    },
    {
      "epoch": 0.003604902667627974,
      "grad_norm": 3.7309262552298605e-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": 373553971200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}