Hugging Face's logo

tuantmdev
/
9d784aae-a730-41c2-93b9-30769642fbe4

PEFT
Safetensors
mixtral
axolotl
Generated from Trainer
Model card Files Community
9d784aae-a730-41c2-93b9-30769642fbe4
File size: 2,675 Bytes 
3f0b413
 
 
ba38dd8
3f0b413
ba38dd8
3f0b413
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ee46175
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ad3fe52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b06d46f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ba38dd8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3f0b413
 
 
 
 
 
 
 
 
 
 
 
 
 
ba38dd8
3f0b413
 
 
 
ba38dd8
3f0b413
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4547392354696604,
  "eval_steps": 40,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002273696177348302,
      "eval_loss": NaN,
      "eval_runtime": 89.7585,
      "eval_samples_per_second": 8.255,
      "eval_steps_per_second": 4.133,
      "step": 1
    },
    {
      "epoch": 0.09094784709393207,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.09094784709393207,
      "eval_loss": NaN,
      "eval_runtime": 88.4448,
      "eval_samples_per_second": 8.378,
      "eval_steps_per_second": 4.195,
      "step": 40
    },
    {
      "epoch": 0.18189569418786414,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.18189569418786414,
      "eval_loss": NaN,
      "eval_runtime": 88.3357,
      "eval_samples_per_second": 8.388,
      "eval_steps_per_second": 4.2,
      "step": 80
    },
    {
      "epoch": 0.2728435412817962,
      "grad_norm": NaN,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.2728435412817962,
      "eval_loss": NaN,
      "eval_runtime": 88.487,
      "eval_samples_per_second": 8.374,
      "eval_steps_per_second": 4.193,
      "step": 120
    },
    {
      "epoch": 0.3637913883757283,
      "grad_norm": NaN,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.3637913883757283,
      "eval_loss": NaN,
      "eval_runtime": 88.4091,
      "eval_samples_per_second": 8.381,
      "eval_steps_per_second": 4.196,
      "step": 160
    },
    {
      "epoch": 0.4547392354696604,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.4547392354696604,
      "eval_loss": NaN,
      "eval_runtime": 88.3863,
      "eval_samples_per_second": 8.384,
      "eval_steps_per_second": 4.197,
      "step": 200
    }
  ],
  "logging_steps": 40,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8735810005211546e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}