Hugging Face's logo

kk-aivio
/
daf1bd6a-e5be-4d9a-8927-aca9dfd696dd

PEFT
Safetensors
olmo
axolotl
Generated from Trainer
Model card Files Community
daf1bd6a-e5be-4d9a-8927-aca9dfd696dd
File size: 3,234 Bytes 
106ec0f
 
 
b5c5773
106ec0f
b5c5773
106ec0f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0eb2ef3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2e3e350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b5c5773
 
 
 
 
 
 
106ec0f
 
 
 
 
 
 
 
 
 
 
 
 
 
b5c5773
106ec0f
 
 
 
b5c5773
106ec0f
 
 
 
 
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": 0.00035324767077317084,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.532476707731709e-05,
      "grad_norm": 0.20259849727153778,
      "learning_rate": 2e-05,
      "loss": 10.8416,
      "step": 1
    },
    {
      "epoch": 3.532476707731709e-05,
      "eval_loss": 10.84003734588623,
      "eval_runtime": 77.2252,
      "eval_samples_per_second": 154.354,
      "eval_steps_per_second": 77.177,
      "step": 1
    },
    {
      "epoch": 7.064953415463417e-05,
      "grad_norm": 0.18833394348621368,
      "learning_rate": 4e-05,
      "loss": 10.8483,
      "step": 2
    },
    {
      "epoch": 0.00010597430123195125,
      "grad_norm": 0.28344565629959106,
      "learning_rate": 6e-05,
      "loss": 10.8258,
      "step": 3
    },
    {
      "epoch": 0.00010597430123195125,
      "eval_loss": 10.83998966217041,
      "eval_runtime": 50.2893,
      "eval_samples_per_second": 237.029,
      "eval_steps_per_second": 118.514,
      "step": 3
    },
    {
      "epoch": 0.00014129906830926835,
      "grad_norm": 0.250560462474823,
      "learning_rate": 8e-05,
      "loss": 10.8422,
      "step": 4
    },
    {
      "epoch": 0.00017662383538658542,
      "grad_norm": 0.14231401681900024,
      "learning_rate": 0.0001,
      "loss": 10.8284,
      "step": 5
    },
    {
      "epoch": 0.0002119486024639025,
      "grad_norm": 0.14842887222766876,
      "learning_rate": 0.00012,
      "loss": 10.8331,
      "step": 6
    },
    {
      "epoch": 0.0002119486024639025,
      "eval_loss": 10.839518547058105,
      "eval_runtime": 67.283,
      "eval_samples_per_second": 177.162,
      "eval_steps_per_second": 88.581,
      "step": 6
    },
    {
      "epoch": 0.00024727336954121957,
      "grad_norm": 0.1853141486644745,
      "learning_rate": 0.00014,
      "loss": 10.8397,
      "step": 7
    },
    {
      "epoch": 0.0002825981366185367,
      "grad_norm": 0.14467550814151764,
      "learning_rate": 0.00016,
      "loss": 10.8336,
      "step": 8
    },
    {
      "epoch": 0.00031792290369585377,
      "grad_norm": 0.22408948838710785,
      "learning_rate": 0.00018,
      "loss": 10.8251,
      "step": 9
    },
    {
      "epoch": 0.00031792290369585377,
      "eval_loss": 10.838693618774414,
      "eval_runtime": 48.3628,
      "eval_samples_per_second": 246.47,
      "eval_steps_per_second": 123.235,
      "step": 9
    },
    {
      "epoch": 0.00035324767077317084,
      "grad_norm": 0.1886138767004013,
      "learning_rate": 0.0002,
      "loss": 10.8247,
      "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": 820295761920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}