Hugging Face's logo

cwaud
/
3be6e87b-ccba-4d15-b744-b594459771ec2

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
3be6e87b-ccba-4d15-b744-b594459771ec2
File size: 2,959 Bytes 
002eb2d
 
 
fb2c40c
002eb2d
fb2c40c
002eb2d
 
 
 
 
 
 
 
 
 
 
 
 
 
3b3db91
 
 
002eb2d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3b3db91
 
 
002eb2d
43ad6f0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a5d5c4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fb2c40c
 
 
 
 
 
 
002eb2d
 
 
 
 
 
 
 
 
 
 
 
 
 
fb2c40c
002eb2d
 
 
 
fb2c40c
002eb2d
 
 
 
 
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": 0.0061823802163833074,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006182380216383308,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0006182380216383308,
      "eval_loss": NaN,
      "eval_runtime": 104.9278,
      "eval_samples_per_second": 6.49,
      "eval_steps_per_second": 3.25,
      "step": 1
    },
    {
      "epoch": 0.0012364760432766616,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0018547140649149924,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0018547140649149924,
      "eval_loss": NaN,
      "eval_runtime": 103.1072,
      "eval_samples_per_second": 6.605,
      "eval_steps_per_second": 3.307,
      "step": 3
    },
    {
      "epoch": 0.002472952086553323,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0030911901081916537,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0037094281298299847,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0037094281298299847,
      "eval_loss": NaN,
      "eval_runtime": 103.0207,
      "eval_samples_per_second": 6.61,
      "eval_steps_per_second": 3.31,
      "step": 6
    },
    {
      "epoch": 0.004327666151468315,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.004945904173106646,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0055641421947449764,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0055641421947449764,
      "eval_loss": NaN,
      "eval_runtime": 103.2654,
      "eval_samples_per_second": 6.595,
      "eval_steps_per_second": 3.302,
      "step": 9
    },
    {
      "epoch": 0.0061823802163833074,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 720954300825600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}