Hugging Face's logo

ClarenceDan
/
155f5e9a-7feb-4cf2-ac72-c4677e0ed94c

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
155f5e9a-7feb-4cf2-ac72-c4677e0ed94c
File size: 3,152 Bytes 
a1b954f
 
 
57093f3
a1b954f
57093f3
a1b954f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ac28e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b5e4c4a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57093f3
 
 
 
 
 
 
a1b954f
 
 
 
 
 
 
 
 
 
 
 
 
 
57093f3
a1b954f
 
 
 
57093f3
a1b954f
 
 
 
 
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": 0.017543859649122806,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017543859649122807,
      "grad_norm": 2.082876926579047e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0017543859649122807,
      "eval_loss": 11.5,
      "eval_runtime": 1.2716,
      "eval_samples_per_second": 188.744,
      "eval_steps_per_second": 94.372,
      "step": 1
    },
    {
      "epoch": 0.0035087719298245615,
      "grad_norm": 3.644842217909172e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.005263157894736842,
      "grad_norm": 5.134688035468571e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.005263157894736842,
      "eval_loss": 11.5,
      "eval_runtime": 1.2481,
      "eval_samples_per_second": 192.296,
      "eval_steps_per_second": 96.148,
      "step": 3
    },
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 2.7331225282978266e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.008771929824561403,
      "grad_norm": 1.5740233720862307e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.010526315789473684,
      "grad_norm": 2.3159351258073002e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.010526315789473684,
      "eval_loss": 11.5,
      "eval_runtime": 1.3373,
      "eval_samples_per_second": 179.47,
      "eval_steps_per_second": 89.735,
      "step": 6
    },
    {
      "epoch": 0.012280701754385965,
      "grad_norm": 3.5230528737884015e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 5.756669634138234e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.015789473684210527,
      "grad_norm": 5.9218640672042966e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.015789473684210527,
      "eval_loss": 11.5,
      "eval_runtime": 1.2659,
      "eval_samples_per_second": 189.59,
      "eval_steps_per_second": 94.795,
      "step": 9
    },
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 5.540232450584881e-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
}