Hugging Face's logo

chauhoang
/
a8596733-36e5-6c1b-29d1-cff7d7dbb128

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
a8596733-36e5-6c1b-29d1-cff7d7dbb128
File size: 2,230 Bytes 
24e002d
 
 
3fdcb92
31ed02b
3fdcb92
24e002d
 
 
 
 
 
 
31ed02b
 
 
24e002d
31ed02b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3fdcb92
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24e002d
 
 
31ed02b
24e002d
 
31ed02b
24e002d
 
 
 
 
 
 
31ed02b
24e002d
 
 
 
3fdcb92
24e002d
 
 
 
 
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": 0.007347227128223242,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028258565877781704,
      "eval_loss": 1.151291847229004,
      "eval_runtime": 178.3855,
      "eval_samples_per_second": 8.353,
      "eval_steps_per_second": 4.176,
      "step": 1
    },
    {
      "epoch": 0.001412928293889085,
      "grad_norm": 6.91673469543457,
      "learning_rate": 5e-05,
      "loss": 4.7003,
      "step": 5
    },
    {
      "epoch": 0.00282585658777817,
      "grad_norm": 6.784793376922607,
      "learning_rate": 0.0001,
      "loss": 3.4863,
      "step": 10
    },
    {
      "epoch": 0.00282585658777817,
      "eval_loss": 0.638950526714325,
      "eval_runtime": 179.2534,
      "eval_samples_per_second": 8.312,
      "eval_steps_per_second": 4.156,
      "step": 10
    },
    {
      "epoch": 0.0042387848816672555,
      "grad_norm": 4.463286399841309,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0209,
      "step": 15
    },
    {
      "epoch": 0.00565171317555634,
      "grad_norm": 2.5350608825683594,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6406,
      "step": 20
    },
    {
      "epoch": 0.00565171317555634,
      "eval_loss": 0.3515169620513916,
      "eval_runtime": 179.1491,
      "eval_samples_per_second": 8.317,
      "eval_steps_per_second": 4.159,
      "step": 20
    },
    {
      "epoch": 0.007064641469445425,
      "grad_norm": 2.713797092437744,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3488,
      "step": 25
    }
  ],
  "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": 9113893355913216.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}