Hugging Face's logo

dimasik87
/
4d203fd0-5ccd-4671-89b2-ae0d228f8de0

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
4d203fd0-5ccd-4671-89b2-ae0d228f8de0
File size: 3,079 Bytes
2701242
 
 
99e2e73
2701242
99e2e73
2701242
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d2d82ed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99e2e73
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2701242
 
 
 
 
 
 
 
 
 
 
 
 
 
99e2e73
2701242
 
 
 
99e2e73
2701242
 
 
 
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": 0.0012084105373398855,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.028035124466285e-05,
      "eval_loss": NaN,
      "eval_runtime": 40.5308,
      "eval_samples_per_second": 257.928,
      "eval_steps_per_second": 128.964,
      "step": 1
    },
    {
      "epoch": 0.00012084105373398856,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00024168210746797713,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0003222428099573028,
      "eval_loss": NaN,
      "eval_runtime": 39.2483,
      "eval_samples_per_second": 266.355,
      "eval_steps_per_second": 133.178,
      "step": 8
    },
    {
      "epoch": 0.0003625231612019657,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00048336421493595425,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0006042052686699428,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0006444856199146056,
      "eval_loss": NaN,
      "eval_runtime": 39.5041,
      "eval_samples_per_second": 264.631,
      "eval_steps_per_second": 132.315,
      "step": 16
    },
    {
      "epoch": 0.0007250463224039314,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0008458873761379199,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0009667284298719085,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0009667284298719085,
      "eval_loss": NaN,
      "eval_runtime": 39.5465,
      "eval_samples_per_second": 264.347,
      "eval_steps_per_second": 132.174,
      "step": 24
    },
    {
      "epoch": 0.0010875694836058971,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0012084105373398855,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1550057472000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}