Hugging Face's logo

kostiantynk-out
/
42be2544-d13d-4831-be16-bbb0f81b9ccd

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
42be2544-d13d-4831-be16-bbb0f81b9ccd
File size: 2,972 Bytes 
44da6e2
 
 
21ad56c
44da6e2
21ad56c
44da6e2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53166fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2bc92c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21ad56c
 
 
 
 
 
 
44da6e2
 
 
 
 
 
 
 
 
 
 
 
 
 
21ad56c
44da6e2
 
 
 
21ad56c
44da6e2
 
 
 
 
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": 0.0032131094867057595,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00032131094867057596,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00032131094867057596,
      "eval_loss": NaN,
      "eval_runtime": 50.984,
      "eval_samples_per_second": 25.714,
      "eval_steps_per_second": 12.867,
      "step": 1
    },
    {
      "epoch": 0.0006426218973411519,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0009639328460117278,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0009639328460117278,
      "eval_loss": NaN,
      "eval_runtime": 48.8915,
      "eval_samples_per_second": 26.814,
      "eval_steps_per_second": 13.417,
      "step": 3
    },
    {
      "epoch": 0.0012852437946823038,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0016065547433528797,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0019278656920234556,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0019278656920234556,
      "eval_loss": NaN,
      "eval_runtime": 49.3381,
      "eval_samples_per_second": 26.572,
      "eval_steps_per_second": 13.296,
      "step": 6
    },
    {
      "epoch": 0.0022491766406940315,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0025704875893646077,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.3096,
      "step": 8
    },
    {
      "epoch": 0.0028917985380351834,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0028917985380351834,
      "eval_loss": NaN,
      "eval_runtime": 48.9544,
      "eval_samples_per_second": 26.78,
      "eval_steps_per_second": 13.4,
      "step": 9
    },
    {
      "epoch": 0.0032131094867057595,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 2035917678182400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}