Hugging Face's logo

kostiantynk
/
7cd34c55-c52f-4c6f-9e34-37a2fc828f06

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7cd34c55-c52f-4c6f-9e34-37a2fc828f06
File size: 2,984 Bytes 
df8bbb0
 
 
53eaf05
df8bbb0
53eaf05
df8bbb0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b6b13af
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
856f1cb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53eaf05
 
 
 
 
 
 
df8bbb0
 
 
 
 
 
 
 
 
 
 
 
 
 
53eaf05
df8bbb0
 
 
 
53eaf05
df8bbb0
 
 
 
 
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": 0.00013869962169678183,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3869962169678183e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 1.3869962169678183e-05,
      "eval_loss": NaN,
      "eval_runtime": 581.7099,
      "eval_samples_per_second": 52.188,
      "eval_steps_per_second": 26.094,
      "step": 1
    },
    {
      "epoch": 2.7739924339356365e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 4.1609886509034544e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 4.1609886509034544e-05,
      "eval_loss": NaN,
      "eval_runtime": 577.9325,
      "eval_samples_per_second": 52.529,
      "eval_steps_per_second": 26.264,
      "step": 3
    },
    {
      "epoch": 5.547984867871273e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 6.934981084839092e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 8.321977301806909e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 8.321977301806909e-05,
      "eval_loss": NaN,
      "eval_runtime": 580.1344,
      "eval_samples_per_second": 52.329,
      "eval_steps_per_second": 26.165,
      "step": 6
    },
    {
      "epoch": 9.708973518774727e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00011095969735742546,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00012482965952710363,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00012482965952710363,
      "eval_loss": NaN,
      "eval_runtime": 580.9924,
      "eval_samples_per_second": 52.252,
      "eval_steps_per_second": 26.126,
      "step": 9
    },
    {
      "epoch": 0.00013869962169678183,
      "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": 316387255910400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}