Hugging Face's logo

VERSIL91
/
969c8a3a-fae9-4a07-b934-44efb4f15885

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
969c8a3a-fae9-4a07-b934-44efb4f15885
File size: 2,996 Bytes 
f29ea17
 
 
40344a5
f29ea17
40344a5
f29ea17
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4f72f9c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b30710c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40344a5
 
 
 
 
 
 
f29ea17
 
 
 
 
 
 
 
 
 
 
 
 
 
40344a5
f29ea17
 
 
 
40344a5
f29ea17
 
 
 
 
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
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000780811556011029,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.80811556011029e-05,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 43349.4531,
      "step": 1
    },
    {
      "epoch": 7.80811556011029e-05,
      "eval_loss": NaN,
      "eval_runtime": 783.7756,
      "eval_samples_per_second": 27.521,
      "eval_steps_per_second": 13.76,
      "step": 1
    },
    {
      "epoch": 0.0001561623112022058,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00023424346680330868,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 5.8715,
      "step": 3
    },
    {
      "epoch": 0.00023424346680330868,
      "eval_loss": NaN,
      "eval_runtime": 697.1851,
      "eval_samples_per_second": 30.939,
      "eval_steps_per_second": 15.469,
      "step": 3
    },
    {
      "epoch": 0.0003123246224044116,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0003904057780055145,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00046848693360661736,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 34956.0312,
      "step": 6
    },
    {
      "epoch": 0.00046848693360661736,
      "eval_loss": NaN,
      "eval_runtime": 697.3582,
      "eval_samples_per_second": 30.931,
      "eval_steps_per_second": 15.466,
      "step": 6
    },
    {
      "epoch": 0.0005465680892077203,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0006246492448088232,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 253.8839,
      "step": 8
    },
    {
      "epoch": 0.0007027304004099261,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0007027304004099261,
      "eval_loss": NaN,
      "eval_runtime": 697.6516,
      "eval_samples_per_second": 30.918,
      "eval_steps_per_second": 15.459,
      "step": 9
    },
    {
      "epoch": 0.000780811556011029,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 2221.7275,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.073511477018624e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}