Hugging Face's logo

phungkhaccuong
/
95132b7d-e31b-cda3-fdda-2dc09cdb3598

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
95132b7d-e31b-cda3-fdda-2dc09cdb3598
File size: 2,782 Bytes 
0d0dd87
 
 
66776b0
eb133b2
66776b0
0d0dd87
 
 
 
 
 
 
eb133b2
 
 
0d0dd87
eb133b2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73d953f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66776b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d0dd87
 
 
eb133b2
0d0dd87
 
eb133b2
0d0dd87
 
 
 
 
 
 
eb133b2
0d0dd87
 
 
 
66776b0
0d0dd87
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05656272661348803,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014503263234227702,
      "eval_loss": 0.2840324938297272,
      "eval_runtime": 26.3496,
      "eval_samples_per_second": 11.044,
      "eval_steps_per_second": 5.541,
      "step": 1
    },
    {
      "epoch": 0.007251631617113851,
      "grad_norm": 7.322425842285156,
      "learning_rate": 5e-05,
      "loss": 0.9639,
      "step": 5
    },
    {
      "epoch": 0.014503263234227702,
      "grad_norm": 6.449563980102539,
      "learning_rate": 0.0001,
      "loss": 0.6865,
      "step": 10
    },
    {
      "epoch": 0.014503263234227702,
      "eval_loss": 0.18034805357456207,
      "eval_runtime": 26.6312,
      "eval_samples_per_second": 10.927,
      "eval_steps_per_second": 5.482,
      "step": 10
    },
    {
      "epoch": 0.021754894851341553,
      "grad_norm": 5.386337757110596,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.966,
      "step": 15
    },
    {
      "epoch": 0.029006526468455404,
      "grad_norm": 3.2059736251831055,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8909,
      "step": 20
    },
    {
      "epoch": 0.029006526468455404,
      "eval_loss": 0.16475515067577362,
      "eval_runtime": 26.6463,
      "eval_samples_per_second": 10.921,
      "eval_steps_per_second": 5.479,
      "step": 20
    },
    {
      "epoch": 0.03625815808556925,
      "grad_norm": 3.6938018798828125,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.5317,
      "step": 25
    },
    {
      "epoch": 0.043509789702683106,
      "grad_norm": 3.9650323390960693,
      "learning_rate": 5e-05,
      "loss": 0.807,
      "step": 30
    },
    {
      "epoch": 0.043509789702683106,
      "eval_loss": 0.15476326644420624,
      "eval_runtime": 26.8368,
      "eval_samples_per_second": 10.843,
      "eval_steps_per_second": 5.44,
      "step": 30
    },
    {
      "epoch": 0.050761421319796954,
      "grad_norm": 3.7301838397979736,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7523,
      "step": 35
    }
  ],
  "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": 9858767545958400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}