Hugging Face's logo

duyphu
/
7dc8f787-417b-4923-bab1-e07a509a483f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7dc8f787-417b-4923-bab1-e07a509a483f
File size: 2,794 Bytes 
cd75829
 
 
c877dc5
1d08e1e
c877dc5
cd75829
 
 
 
 
 
 
1d08e1e
 
 
cd75829
1d08e1e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f285198
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c877dc5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cd75829
 
 
1d08e1e
cd75829
 
1d08e1e
cd75829
 
 
 
 
 
 
1d08e1e
cd75829
 
 
 
c877dc5
cd75829
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009074357378441421,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.326758302164467e-05,
      "eval_loss": 5.18183708190918,
      "eval_runtime": 1103.9859,
      "eval_samples_per_second": 16.392,
      "eval_steps_per_second": 8.197,
      "step": 1
    },
    {
      "epoch": 0.00011633791510822335,
      "grad_norm": 3.286332368850708,
      "learning_rate": 5e-05,
      "loss": 5.2746,
      "step": 5
    },
    {
      "epoch": 0.0002326758302164467,
      "grad_norm": 4.80321741104126,
      "learning_rate": 0.0001,
      "loss": 4.9456,
      "step": 10
    },
    {
      "epoch": 0.0002326758302164467,
      "eval_loss": 4.540585517883301,
      "eval_runtime": 1107.4278,
      "eval_samples_per_second": 16.341,
      "eval_steps_per_second": 8.171,
      "step": 10
    },
    {
      "epoch": 0.00034901374532467005,
      "grad_norm": 4.00037956237793,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.947,
      "step": 15
    },
    {
      "epoch": 0.0004653516604328934,
      "grad_norm": 3.7681870460510254,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.3056,
      "step": 20
    },
    {
      "epoch": 0.0004653516604328934,
      "eval_loss": 2.6043853759765625,
      "eval_runtime": 1107.0056,
      "eval_samples_per_second": 16.348,
      "eval_steps_per_second": 8.174,
      "step": 20
    },
    {
      "epoch": 0.0005816895755411168,
      "grad_norm": 2.936751365661621,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.2767,
      "step": 25
    },
    {
      "epoch": 0.0006980274906493401,
      "grad_norm": 3.392641544342041,
      "learning_rate": 5e-05,
      "loss": 2.5175,
      "step": 30
    },
    {
      "epoch": 0.0006980274906493401,
      "eval_loss": 2.222399950027466,
      "eval_runtime": 1102.8097,
      "eval_samples_per_second": 16.41,
      "eval_steps_per_second": 8.205,
      "step": 30
    },
    {
      "epoch": 0.0008143654057575635,
      "grad_norm": 3.994202136993408,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.5334,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6632487266549760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}