Hugging Face's logo

kostiantynk-out
/
eaf98946-024c-406a-9686-f85c1fe8ba91

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
eaf98946-024c-406a-9686-f85c1fe8ba91
File size: 2,842 Bytes 
d55f14d
 
 
a05e8c3
d55f14d
a05e8c3
d55f14d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d2f8c25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a05e8c3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d55f14d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a05e8c3
d55f14d
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00011127768418775018,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2364187131972243e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 1.2364187131972243e-05,
      "eval_loss": NaN,
      "eval_runtime": 1204.0997,
      "eval_samples_per_second": 28.283,
      "eval_steps_per_second": 14.142,
      "step": 1
    },
    {
      "epoch": 2.4728374263944486e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 3.709256139591673e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 3.709256139591673e-05,
      "eval_loss": NaN,
      "eval_runtime": 1202.0061,
      "eval_samples_per_second": 28.332,
      "eval_steps_per_second": 14.166,
      "step": 3
    },
    {
      "epoch": 4.945674852788897e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 6.182093565986121e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 7.418512279183346e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 7.418512279183346e-05,
      "eval_loss": NaN,
      "eval_runtime": 1202.2099,
      "eval_samples_per_second": 28.327,
      "eval_steps_per_second": 14.164,
      "step": 6
    },
    {
      "epoch": 8.65493099238057e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 9.891349705577795e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00011127768418775018,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00011127768418775018,
      "eval_loss": NaN,
      "eval_runtime": 1202.2643,
      "eval_samples_per_second": 28.326,
      "eval_steps_per_second": 14.163,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1807480648630272.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}