Hugging Face's logo

duyphu
/
7e2c0fde-811e-45f6-8099-77b73b8de88c

PEFT
Safetensors
mixtral
axolotl
Generated from Trainer
Model card Files Community
7e2c0fde-811e-45f6-8099-77b73b8de88c
File size: 2,780 Bytes 
d69ec8a
 
 
8222929
79129f7
8222929
d69ec8a
 
 
 
 
 
 
79129f7
 
 
d69ec8a
79129f7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3273e1f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8222929
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d69ec8a
 
 
79129f7
d69ec8a
 
79129f7
d69ec8a
 
 
 
 
 
 
79129f7
d69ec8a
 
 
 
8222929
d69ec8a
 
 
 
 
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": 0.049273531269740996,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012634238787113076,
      "eval_loss": 0.8878610730171204,
      "eval_runtime": 41.0395,
      "eval_samples_per_second": 8.139,
      "eval_steps_per_second": 4.069,
      "step": 1
    },
    {
      "epoch": 0.006317119393556538,
      "grad_norm": 0.5309655070304871,
      "learning_rate": 5e-05,
      "loss": 0.865,
      "step": 5
    },
    {
      "epoch": 0.012634238787113077,
      "grad_norm": 0.5345095992088318,
      "learning_rate": 0.0001,
      "loss": 0.8402,
      "step": 10
    },
    {
      "epoch": 0.012634238787113077,
      "eval_loss": 0.7144569754600525,
      "eval_runtime": 41.3875,
      "eval_samples_per_second": 8.07,
      "eval_steps_per_second": 4.035,
      "step": 10
    },
    {
      "epoch": 0.018951358180669616,
      "grad_norm": 0.6154476404190063,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.6647,
      "step": 15
    },
    {
      "epoch": 0.025268477574226154,
      "grad_norm": 0.5439320802688599,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6373,
      "step": 20
    },
    {
      "epoch": 0.025268477574226154,
      "eval_loss": 0.5970596075057983,
      "eval_runtime": 41.5592,
      "eval_samples_per_second": 8.037,
      "eval_steps_per_second": 4.018,
      "step": 20
    },
    {
      "epoch": 0.03158559696778269,
      "grad_norm": 0.4888911545276642,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.5915,
      "step": 25
    },
    {
      "epoch": 0.03790271636133923,
      "grad_norm": 0.5220611691474915,
      "learning_rate": 5e-05,
      "loss": 0.5889,
      "step": 30
    },
    {
      "epoch": 0.03790271636133923,
      "eval_loss": 0.5668606162071228,
      "eval_runtime": 41.6213,
      "eval_samples_per_second": 8.025,
      "eval_steps_per_second": 4.012,
      "step": 30
    },
    {
      "epoch": 0.04421983575489577,
      "grad_norm": 0.4219604730606079,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.569,
      "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": 1.2631125277016064e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}