Hugging Face's logo

kostiantynk-out
/
bdba92b3-2db3-4711-a5aa-3784789d8456

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
bdba92b3-2db3-4711-a5aa-3784789d8456
File size: 3,176 Bytes 
eed0023
 
 
75bf968
eed0023
75bf968
eed0023
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a93ac38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75bf968
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eed0023
 
 
 
 
 
 
 
 
 
 
 
 
 
75bf968
eed0023
 
 
 
75bf968
eed0023
 
 
 
 
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": 0.0005055931239335145,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.055931239335145e-05,
      "grad_norm": 2.9395112505881116e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 5.055931239335145e-05,
      "eval_loss": 11.5,
      "eval_runtime": 51.474,
      "eval_samples_per_second": 161.79,
      "eval_steps_per_second": 80.895,
      "step": 1
    },
    {
      "epoch": 0.0001011186247867029,
      "grad_norm": 1.3729901183978654e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.00015167793718005436,
      "grad_norm": 1.920999784488231e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.00015167793718005436,
      "eval_loss": 11.5,
      "eval_runtime": 51.9288,
      "eval_samples_per_second": 160.373,
      "eval_steps_per_second": 80.187,
      "step": 3
    },
    {
      "epoch": 0.0002022372495734058,
      "grad_norm": 5.731997225666419e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.00025279656196675726,
      "grad_norm": 9.691962986835279e-06,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.00030335587436010873,
      "grad_norm": 1.898708796943538e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.00030335587436010873,
      "eval_loss": 11.5,
      "eval_runtime": 53.6365,
      "eval_samples_per_second": 155.267,
      "eval_steps_per_second": 77.634,
      "step": 6
    },
    {
      "epoch": 0.00035391518675346014,
      "grad_norm": 3.0670395062770694e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.0004044744991468116,
      "grad_norm": 1.8676053514354862e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.00045503381154016307,
      "grad_norm": 2.4990700694615953e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.00045503381154016307,
      "eval_loss": 11.5,
      "eval_runtime": 51.7209,
      "eval_samples_per_second": 161.018,
      "eval_steps_per_second": 80.509,
      "step": 9
    },
    {
      "epoch": 0.0005055931239335145,
      "grad_norm": 5.803050589747727e-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": 368573251584.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}