Hugging Face's logo

adammandic87
/
05f441bc-4409-4188-a62a-44e7d3d95c8a

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
05f441bc-4409-4188-a62a-44e7d3d95c8a
File size: 3,151 Bytes 
470d483
 
 
a435a15
470d483
a435a15
470d483
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1c4d778
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dff1755
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a435a15
 
 
 
 
 
 
470d483
 
 
 
 
 
 
 
 
 
 
 
 
 
a435a15
470d483
 
 
 
a435a15
470d483
 
 
 
 
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": 2.0399851564434357e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.0017543859649122807,
      "eval_loss": 11.5,
      "eval_runtime": 1.4089,
      "eval_samples_per_second": 170.347,
      "eval_steps_per_second": 85.173,
      "step": 1
    },
    {
      "epoch": 0.0035087719298245615,
      "grad_norm": 3.543835555319674e-05,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.005263157894736842,
      "grad_norm": 4.867135430686176e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.005263157894736842,
      "eval_loss": 11.5,
      "eval_runtime": 1.4045,
      "eval_samples_per_second": 170.879,
      "eval_steps_per_second": 85.44,
      "step": 3
    },
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 2.482670606696047e-05,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.008771929824561403,
      "grad_norm": 1.4282260053732898e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.010526315789473684,
      "grad_norm": 2.3083957785274833e-05,
      "learning_rate": 0.00012,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.010526315789473684,
      "eval_loss": 11.5,
      "eval_runtime": 1.4904,
      "eval_samples_per_second": 161.032,
      "eval_steps_per_second": 80.516,
      "step": 6
    },
    {
      "epoch": 0.012280701754385965,
      "grad_norm": 3.609339546528645e-05,
      "learning_rate": 0.00014,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 5.481456537381746e-05,
      "learning_rate": 0.00016,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.015789473684210527,
      "grad_norm": 6.254210165934637e-05,
      "learning_rate": 0.00018,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.015789473684210527,
      "eval_loss": 11.5,
      "eval_runtime": 1.4216,
      "eval_samples_per_second": 168.827,
      "eval_steps_per_second": 84.413,
      "step": 9
    },
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 5.912252890993841e-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
}