Hugging Face's logo

VERSIL91
/
b3bb25f5-8ef1-4d74-8d98-1725f04ba352

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
b3bb25f5-8ef1-4d74-8d98-1725f04ba352
File size: 2,060 Bytes 
7a5113b
 
 
57ccc71
7a5113b
57ccc71
7a5113b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cfe5b21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57ccc71
 
 
 
 
 
 
7a5113b
 
 
 
 
 
 
 
 
 
 
 
 
 
57ccc71
7a5113b
 
 
 
57ccc71
7a5113b
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001766433350261653,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003532866700523306,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0003532866700523306,
      "eval_loss": NaN,
      "eval_runtime": 324.7041,
      "eval_samples_per_second": 14.684,
      "eval_steps_per_second": 7.342,
      "step": 1
    },
    {
      "epoch": 0.0007065733401046612,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0007065733401046612,
      "eval_loss": NaN,
      "eval_runtime": 190.2262,
      "eval_samples_per_second": 25.065,
      "eval_steps_per_second": 12.532,
      "step": 2
    },
    {
      "epoch": 0.0010598600101569917,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0014131466802093224,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0014131466802093224,
      "eval_loss": NaN,
      "eval_runtime": 193.0417,
      "eval_samples_per_second": 24.699,
      "eval_steps_per_second": 12.35,
      "step": 4
    },
    {
      "epoch": 0.001766433350261653,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 104.5392,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6923053606895616.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}