Hugging Face's logo

kk-aivio
/
75f5f74e-6910-4e43-950f-a9adfe1ed987

PEFT
Safetensors
opt
axolotl
Generated from Trainer
Model card Files Community
75f5f74e-6910-4e43-950f-a9adfe1ed987
File size: 3,176 Bytes 
55551bc
 
 
020dd68
55551bc
020dd68
55551bc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fa0d636
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d917417
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
020dd68
 
 
 
 
 
 
55551bc
 
 
 
 
 
 
 
 
 
 
 
 
 
020dd68
55551bc
 
 
 
020dd68
55551bc
 
 
 
 
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": 0.07648183556405354,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0076481835564053535,
      "grad_norm": 21.02690315246582,
      "learning_rate": 2e-05,
      "loss": 9.822,
      "step": 1
    },
    {
      "epoch": 0.0076481835564053535,
      "eval_loss": 2.890343189239502,
      "eval_runtime": 1.8517,
      "eval_samples_per_second": 29.703,
      "eval_steps_per_second": 15.122,
      "step": 1
    },
    {
      "epoch": 0.015296367112810707,
      "grad_norm": 20.047754287719727,
      "learning_rate": 4e-05,
      "loss": 12.9937,
      "step": 2
    },
    {
      "epoch": 0.022944550669216062,
      "grad_norm": 22.70226287841797,
      "learning_rate": 6e-05,
      "loss": 11.7915,
      "step": 3
    },
    {
      "epoch": 0.022944550669216062,
      "eval_loss": 2.828831434249878,
      "eval_runtime": 0.91,
      "eval_samples_per_second": 60.437,
      "eval_steps_per_second": 30.768,
      "step": 3
    },
    {
      "epoch": 0.030592734225621414,
      "grad_norm": 29.1671085357666,
      "learning_rate": 8e-05,
      "loss": 11.1711,
      "step": 4
    },
    {
      "epoch": 0.03824091778202677,
      "grad_norm": 15.751770973205566,
      "learning_rate": 0.0001,
      "loss": 9.6744,
      "step": 5
    },
    {
      "epoch": 0.045889101338432124,
      "grad_norm": 18.53544807434082,
      "learning_rate": 0.00012,
      "loss": 11.195,
      "step": 6
    },
    {
      "epoch": 0.045889101338432124,
      "eval_loss": 2.4405295848846436,
      "eval_runtime": 1.0267,
      "eval_samples_per_second": 53.572,
      "eval_steps_per_second": 27.273,
      "step": 6
    },
    {
      "epoch": 0.05353728489483748,
      "grad_norm": 13.921692848205566,
      "learning_rate": 0.00014,
      "loss": 8.334,
      "step": 7
    },
    {
      "epoch": 0.06118546845124283,
      "grad_norm": 21.811330795288086,
      "learning_rate": 0.00016,
      "loss": 9.1286,
      "step": 8
    },
    {
      "epoch": 0.06883365200764818,
      "grad_norm": 17.255428314208984,
      "learning_rate": 0.00018,
      "loss": 6.7562,
      "step": 9
    },
    {
      "epoch": 0.06883365200764818,
      "eval_loss": 1.9071483612060547,
      "eval_runtime": 0.9102,
      "eval_samples_per_second": 60.427,
      "eval_steps_per_second": 30.763,
      "step": 9
    },
    {
      "epoch": 0.07648183556405354,
      "grad_norm": 23.9243106842041,
      "learning_rate": 0.0002,
      "loss": 7.9559,
      "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": 298765642629120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}