Hugging Face's logo

tuanna08go
/
e81317ed-6a5e-4e44-8bb3-9bb30fa1efd1

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
e81317ed-6a5e-4e44-8bb3-9bb30fa1efd1
File size: 2,725 Bytes 
0a20ad3
 
 
70100d4
4f5e655
70100d4
0a20ad3
 
 
 
 
 
 
4f5e655
 
 
0a20ad3
4f5e655
 
 
 
 
 
 
 
 
 
 
 
 
 
 
00d2b91
 
 
 
 
 
 
 
 
 
 
 
 
 
 
341a10d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70100d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a20ad3
 
 
4f5e655
0a20ad3
 
4f5e655
0a20ad3
 
 
 
 
 
 
70100d4
0a20ad3
 
 
 
70100d4
0a20ad3
 
 
 
 
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": 0.040537116797567774,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008107423359513554,
      "eval_loss": NaN,
      "eval_runtime": 570.4037,
      "eval_samples_per_second": 14.569,
      "eval_steps_per_second": 1.822,
      "step": 1
    },
    {
      "epoch": 0.008107423359513555,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.008107423359513555,
      "eval_loss": NaN,
      "eval_runtime": 567.6362,
      "eval_samples_per_second": 14.64,
      "eval_steps_per_second": 1.83,
      "step": 10
    },
    {
      "epoch": 0.01621484671902711,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.01621484671902711,
      "eval_loss": NaN,
      "eval_runtime": 567.1332,
      "eval_samples_per_second": 14.653,
      "eval_steps_per_second": 1.832,
      "step": 20
    },
    {
      "epoch": 0.024322270078540664,
      "grad_norm": NaN,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.024322270078540664,
      "eval_loss": NaN,
      "eval_runtime": 566.1102,
      "eval_samples_per_second": 14.679,
      "eval_steps_per_second": 1.835,
      "step": 30
    },
    {
      "epoch": 0.03242969343805422,
      "grad_norm": NaN,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.03242969343805422,
      "eval_loss": NaN,
      "eval_runtime": 567.0942,
      "eval_samples_per_second": 14.654,
      "eval_steps_per_second": 1.832,
      "step": 40
    },
    {
      "epoch": 0.040537116797567774,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.040537116797567774,
      "eval_loss": NaN,
      "eval_runtime": 565.2586,
      "eval_samples_per_second": 14.701,
      "eval_steps_per_second": 1.838,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.464141918114939e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}