Hugging Face's logo

great0001
/
8fdb539a-222c-496a-af33-bc3b3d03b8d4

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
8fdb539a-222c-496a-af33-bc3b3d03b8d4
File size: 3,207 Bytes 
8ae037b
 
 
abc9f9b
8ae037b
abc9f9b
8ae037b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0c740f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93e3edd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
abc9f9b
 
 
 
 
 
 
8ae037b
 
 
 
 
 
 
 
 
 
 
 
 
 
abc9f9b
8ae037b
 
 
 
abc9f9b
8ae037b
 
 
 
 
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": 0.0010375865736297373,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010375865736297373,
      "grad_norm": 1.1354926824569702,
      "learning_rate": 2e-05,
      "loss": 2.1367,
      "step": 1
    },
    {
      "epoch": 0.00010375865736297373,
      "eval_loss": 2.0775890350341797,
      "eval_runtime": 82.2723,
      "eval_samples_per_second": 49.324,
      "eval_steps_per_second": 24.662,
      "step": 1
    },
    {
      "epoch": 0.00020751731472594745,
      "grad_norm": 1.1936341524124146,
      "learning_rate": 4e-05,
      "loss": 2.0164,
      "step": 2
    },
    {
      "epoch": 0.00031127597208892115,
      "grad_norm": 1.2371667623519897,
      "learning_rate": 6e-05,
      "loss": 2.1292,
      "step": 3
    },
    {
      "epoch": 0.00031127597208892115,
      "eval_loss": 2.074251413345337,
      "eval_runtime": 80.6,
      "eval_samples_per_second": 50.347,
      "eval_steps_per_second": 25.174,
      "step": 3
    },
    {
      "epoch": 0.0004150346294518949,
      "grad_norm": 1.0456353425979614,
      "learning_rate": 8e-05,
      "loss": 1.9339,
      "step": 4
    },
    {
      "epoch": 0.0005187932868148687,
      "grad_norm": 1.2975083589553833,
      "learning_rate": 0.0001,
      "loss": 2.0544,
      "step": 5
    },
    {
      "epoch": 0.0006225519441778423,
      "grad_norm": 1.0521240234375,
      "learning_rate": 0.00012,
      "loss": 2.1387,
      "step": 6
    },
    {
      "epoch": 0.0006225519441778423,
      "eval_loss": 2.0402276515960693,
      "eval_runtime": 80.8247,
      "eval_samples_per_second": 50.207,
      "eval_steps_per_second": 25.104,
      "step": 6
    },
    {
      "epoch": 0.000726310601540816,
      "grad_norm": 1.1553844213485718,
      "learning_rate": 0.00014,
      "loss": 1.9767,
      "step": 7
    },
    {
      "epoch": 0.0008300692589037898,
      "grad_norm": 1.0176719427108765,
      "learning_rate": 0.00016,
      "loss": 1.7407,
      "step": 8
    },
    {
      "epoch": 0.0009338279162667636,
      "grad_norm": 1.0879982709884644,
      "learning_rate": 0.00018,
      "loss": 1.8643,
      "step": 9
    },
    {
      "epoch": 0.0009338279162667636,
      "eval_loss": 1.9784159660339355,
      "eval_runtime": 81.6761,
      "eval_samples_per_second": 49.684,
      "eval_steps_per_second": 24.842,
      "step": 9
    },
    {
      "epoch": 0.0010375865736297373,
      "grad_norm": 0.9488828778266907,
      "learning_rate": 0.0002,
      "loss": 1.7424,
      "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": 126879383420928.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}