Hugging Face's logo

fedovtt
/
0b735ee6-e5d9-472d-be41-b2006ab23331

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
0b735ee6-e5d9-472d-be41-b2006ab23331
File size: 3,079 Bytes 
8adc8b1
 
 
43cd1a7
8adc8b1
43cd1a7
8adc8b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1cab39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43cd1a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8adc8b1
 
 
 
 
 
 
 
 
 
 
 
 
 
43cd1a7
8adc8b1
 
 
 
43cd1a7
8adc8b1
 
 
 
 
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": 0.0008232824270365949,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7442747567886496e-05,
      "eval_loss": NaN,
      "eval_runtime": 395.7204,
      "eval_samples_per_second": 38.772,
      "eval_steps_per_second": 19.387,
      "step": 1
    },
    {
      "epoch": 8.232824270365949e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00016465648540731897,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00021954198054309197,
      "eval_loss": NaN,
      "eval_runtime": 394.121,
      "eval_samples_per_second": 38.93,
      "eval_steps_per_second": 19.466,
      "step": 8
    },
    {
      "epoch": 0.00024698472811097847,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00032931297081463794,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00041164121351829747,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00043908396108618394,
      "eval_loss": NaN,
      "eval_runtime": 394.6269,
      "eval_samples_per_second": 38.88,
      "eval_steps_per_second": 19.441,
      "step": 16
    },
    {
      "epoch": 0.0004939694562219569,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0005762976989256164,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0006586259416292759,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0006586259416292759,
      "eval_loss": NaN,
      "eval_runtime": 393.8867,
      "eval_samples_per_second": 38.953,
      "eval_steps_per_second": 19.478,
      "step": 24
    },
    {
      "epoch": 0.0007409541843329355,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0008232824270365949,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1909376365363200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}