Hugging Face's logo

fedovtt
/
0766bd24-e576-4a04-9f46-d0d8fa95d45d

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
Community
0766bd24-e576-4a04-9f46-d0d8fa95d45d
File size: 3,057 Bytes 
4cdfedc
 
 
fa21480
4cdfedc
fa21480
4cdfedc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f75b940
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fa21480
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4cdfedc
 
 
 
 
 
 
 
 
 
 
 
 
 
fa21480
4cdfedc
 
 
 
fa21480
4cdfedc
 
 
 
 
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": 0.014192785334121822,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004730928444707274,
      "eval_loss": NaN,
      "eval_runtime": 43.8525,
      "eval_samples_per_second": 20.295,
      "eval_steps_per_second": 10.148,
      "step": 1
    },
    {
      "epoch": 0.0014192785334121822,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0028385570668243644,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.003784742755765819,
      "eval_loss": NaN,
      "eval_runtime": 43.3023,
      "eval_samples_per_second": 20.553,
      "eval_steps_per_second": 10.277,
      "step": 8
    },
    {
      "epoch": 0.004257835600236547,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.005677114133648729,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.007096392667060911,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.007569485511531638,
      "eval_loss": NaN,
      "eval_runtime": 43.3451,
      "eval_samples_per_second": 20.533,
      "eval_steps_per_second": 10.266,
      "step": 16
    },
    {
      "epoch": 0.008515671200473094,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.009934949733885276,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.011354228267297458,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.011354228267297458,
      "eval_loss": NaN,
      "eval_runtime": 43.392,
      "eval_samples_per_second": 20.511,
      "eval_steps_per_second": 10.255,
      "step": 24
    },
    {
      "epoch": 0.01277350680070964,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.014192785334121822,
      "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": 4135709237575680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}