Hugging Face's logo

trenden
/
b1364d18-61b7-4fc3-a89c-16aaac1b3877

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
b1364d18-61b7-4fc3-a89c-16aaac1b3877
File size: 3,042 Bytes 
e1c3286
 
 
0f002e2
e1c3286
0f002e2
e1c3286
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
af99dc4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0f002e2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e1c3286
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0f002e2
e1c3286
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0028146989835809225,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003127443315089914,
      "grad_norm": 6.8922343254089355,
      "learning_rate": 2e-05,
      "loss": 19.7839,
      "step": 1
    },
    {
      "epoch": 0.0003127443315089914,
      "eval_loss": 17.957256317138672,
      "eval_runtime": 38.7574,
      "eval_samples_per_second": 34.755,
      "eval_steps_per_second": 17.39,
      "step": 1
    },
    {
      "epoch": 0.0006254886630179827,
      "grad_norm": 6.97463846206665,
      "learning_rate": 4e-05,
      "loss": 16.3235,
      "step": 2
    },
    {
      "epoch": 0.0009382329945269742,
      "grad_norm": 9.537607192993164,
      "learning_rate": 6e-05,
      "loss": 16.7324,
      "step": 3
    },
    {
      "epoch": 0.0009382329945269742,
      "eval_loss": 17.92792320251465,
      "eval_runtime": 37.2858,
      "eval_samples_per_second": 36.126,
      "eval_steps_per_second": 18.077,
      "step": 3
    },
    {
      "epoch": 0.0012509773260359655,
      "grad_norm": 6.914788722991943,
      "learning_rate": 8e-05,
      "loss": 18.15,
      "step": 4
    },
    {
      "epoch": 0.001563721657544957,
      "grad_norm": 8.019819259643555,
      "learning_rate": 0.0001,
      "loss": 16.1831,
      "step": 5
    },
    {
      "epoch": 0.0018764659890539485,
      "grad_norm": 7.5083723068237305,
      "learning_rate": 0.00012,
      "loss": 18.0949,
      "step": 6
    },
    {
      "epoch": 0.0018764659890539485,
      "eval_loss": 17.07736587524414,
      "eval_runtime": 37.4363,
      "eval_samples_per_second": 35.981,
      "eval_steps_per_second": 18.004,
      "step": 6
    },
    {
      "epoch": 0.00218921032056294,
      "grad_norm": 9.1001558303833,
      "learning_rate": 0.00014,
      "loss": 17.5335,
      "step": 7
    },
    {
      "epoch": 0.002501954652071931,
      "grad_norm": 15.724388122558594,
      "learning_rate": 0.00016,
      "loss": 15.0517,
      "step": 8
    },
    {
      "epoch": 0.0028146989835809225,
      "grad_norm": 15.608181953430176,
      "learning_rate": 0.00018,
      "loss": 13.1964,
      "step": 9
    },
    {
      "epoch": 0.0028146989835809225,
      "eval_loss": 13.878823280334473,
      "eval_runtime": 37.4374,
      "eval_samples_per_second": 35.98,
      "eval_steps_per_second": 18.003,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1568372441481216.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}