Hugging Face's logo

ivangrapher
/
9a6774e5-dee4-41e0-be23-53a40cf6193d

PEFT
Safetensors
mixtral
axolotl
Generated from Trainer
Model card Files Community
9a6774e5-dee4-41e0-be23-53a40cf6193d
File size: 2,273 Bytes 
c62bdb4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0014534179545564654,
  "eval_steps": 5,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.689453030376436e-05,
      "eval_loss": NaN,
      "eval_runtime": 1116.6045,
      "eval_samples_per_second": 3.892,
      "eval_steps_per_second": 1.946,
      "step": 1
    },
    {
      "epoch": 0.00029068359091129306,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00048447265151882175,
      "eval_loss": NaN,
      "eval_runtime": 1117.3431,
      "eval_samples_per_second": 3.89,
      "eval_steps_per_second": 1.945,
      "step": 5
    },
    {
      "epoch": 0.0005813671818225861,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0008720507727338791,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0009689453030376435,
      "eval_loss": NaN,
      "eval_runtime": 1117.1294,
      "eval_samples_per_second": 3.89,
      "eval_steps_per_second": 1.945,
      "step": 10
    },
    {
      "epoch": 0.0011627343636451723,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0014534179545564654,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0014534179545564654,
      "eval_loss": NaN,
      "eval_runtime": 1116.3214,
      "eval_samples_per_second": 3.893,
      "eval_steps_per_second": 1.947,
      "step": 15
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.94858446749696e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}