Hugging Face's logo

trenden
/
ce493822-9278-4761-9ac8-08bcf95a0724

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ce493822-9278-4761-9ac8-08bcf95a0724
File size: 3,207 Bytes 
80ccd40
 
 
805ef4b
80ccd40
805ef4b
80ccd40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0c62dc7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d1d9a5e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
805ef4b
 
 
 
 
 
 
80ccd40
 
 
 
 
 
 
 
 
 
 
 
 
 
805ef4b
80ccd40
 
 
 
805ef4b
80ccd40
 
 
 
 
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": 0.005858230814294083,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005858230814294083,
      "grad_norm": 9.5940523147583,
      "learning_rate": 2e-05,
      "loss": 15.9668,
      "step": 1
    },
    {
      "epoch": 0.0005858230814294083,
      "eval_loss": 16.182086944580078,
      "eval_runtime": 23.0092,
      "eval_samples_per_second": 31.248,
      "eval_steps_per_second": 15.646,
      "step": 1
    },
    {
      "epoch": 0.0011716461628588166,
      "grad_norm": 8.103241920471191,
      "learning_rate": 4e-05,
      "loss": 15.8215,
      "step": 2
    },
    {
      "epoch": 0.0017574692442882249,
      "grad_norm": 8.939263343811035,
      "learning_rate": 6e-05,
      "loss": 15.952,
      "step": 3
    },
    {
      "epoch": 0.0017574692442882249,
      "eval_loss": 16.123308181762695,
      "eval_runtime": 21.6338,
      "eval_samples_per_second": 33.235,
      "eval_steps_per_second": 16.641,
      "step": 3
    },
    {
      "epoch": 0.0023432923257176333,
      "grad_norm": 9.193857192993164,
      "learning_rate": 8e-05,
      "loss": 16.0648,
      "step": 4
    },
    {
      "epoch": 0.0029291154071470417,
      "grad_norm": 9.71928596496582,
      "learning_rate": 0.0001,
      "loss": 16.0317,
      "step": 5
    },
    {
      "epoch": 0.0035149384885764497,
      "grad_norm": 10.246051788330078,
      "learning_rate": 0.00012,
      "loss": 15.2528,
      "step": 6
    },
    {
      "epoch": 0.0035149384885764497,
      "eval_loss": 14.887479782104492,
      "eval_runtime": 21.7432,
      "eval_samples_per_second": 33.068,
      "eval_steps_per_second": 16.557,
      "step": 6
    },
    {
      "epoch": 0.004100761570005858,
      "grad_norm": 13.074706077575684,
      "learning_rate": 0.00014,
      "loss": 15.5862,
      "step": 7
    },
    {
      "epoch": 0.0046865846514352666,
      "grad_norm": 14.782737731933594,
      "learning_rate": 0.00016,
      "loss": 13.6667,
      "step": 8
    },
    {
      "epoch": 0.005272407732864675,
      "grad_norm": 14.997851371765137,
      "learning_rate": 0.00018,
      "loss": 12.6867,
      "step": 9
    },
    {
      "epoch": 0.005272407732864675,
      "eval_loss": 10.434623718261719,
      "eval_runtime": 21.7497,
      "eval_samples_per_second": 33.058,
      "eval_steps_per_second": 16.552,
      "step": 9
    },
    {
      "epoch": 0.005858230814294083,
      "grad_norm": 17.834928512573242,
      "learning_rate": 0.0002,
      "loss": 10.6756,
      "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
}