Hugging Face's logo

lesso03
/
0f4372e0-37f6-4fef-a7f4-12f15e411e0b

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
0f4372e0-37f6-4fef-a7f4-12f15e411e0b
File size: 2,982 Bytes 
cf60334
 
 
b261e20
cf60334
b261e20
cf60334
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fad286a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
141296d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b261e20
 
 
 
 
 
 
cf60334
 
 
 
 
 
 
 
 
 
 
 
 
 
b261e20
cf60334
 
 
 
b261e20
cf60334
 
 
 
 
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": 0.00013287138382224467,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3287138382224467e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 1.3287138382224467e-05,
      "eval_loss": NaN,
      "eval_runtime": 2053.2254,
      "eval_samples_per_second": 15.434,
      "eval_steps_per_second": 7.717,
      "step": 1
    },
    {
      "epoch": 2.6574276764448934e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 3.9861415146673396e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 3.9861415146673396e-05,
      "eval_loss": NaN,
      "eval_runtime": 2051.9717,
      "eval_samples_per_second": 15.443,
      "eval_steps_per_second": 7.722,
      "step": 3
    },
    {
      "epoch": 5.314855352889787e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 6.643569191112233e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 7.972283029334679e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 7.972283029334679e-05,
      "eval_loss": NaN,
      "eval_runtime": 2061.3982,
      "eval_samples_per_second": 15.373,
      "eval_steps_per_second": 7.687,
      "step": 6
    },
    {
      "epoch": 9.300996867557126e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00010629710705779574,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0001195842454400202,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0001195842454400202,
      "eval_loss": NaN,
      "eval_runtime": 2052.3295,
      "eval_samples_per_second": 15.441,
      "eval_steps_per_second": 7.72,
      "step": 9
    },
    {
      "epoch": 0.00013287138382224467,
      "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": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}