Hugging Face's logo

tuanna08go
/
2d06643f-2e4d-47cc-9ba9-ef5d1b12dac9

PEFT
Safetensors
falcon
axolotl
Generated from Trainer
custom_code
Model card Files Community
2d06643f-2e4d-47cc-9ba9-ef5d1b12dac9
File size: 2,797 Bytes 
14042a3
 
 
a6cfafc
dcf6fe9
a6cfafc
14042a3
 
 
 
 
 
 
dcf6fe9
 
 
14042a3
dcf6fe9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
677f16e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a6cfafc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14042a3
 
 
dcf6fe9
14042a3
 
dcf6fe9
14042a3
 
 
 
 
 
 
dcf6fe9
14042a3
 
 
 
a6cfafc
14042a3
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0021315260906991677,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.465451514613251e-05,
      "eval_loss": 3.0376367568969727,
      "eval_runtime": 692.0351,
      "eval_samples_per_second": 11.132,
      "eval_steps_per_second": 5.566,
      "step": 1
    },
    {
      "epoch": 0.00027327257573066255,
      "grad_norm": 9.199381828308105,
      "learning_rate": 5e-05,
      "loss": 13.2748,
      "step": 5
    },
    {
      "epoch": 0.0005465451514613251,
      "grad_norm": 10.021293640136719,
      "learning_rate": 0.0001,
      "loss": 12.8217,
      "step": 10
    },
    {
      "epoch": 0.0005465451514613251,
      "eval_loss": 2.7879865169525146,
      "eval_runtime": 693.1951,
      "eval_samples_per_second": 11.114,
      "eval_steps_per_second": 5.557,
      "step": 10
    },
    {
      "epoch": 0.0008198177271919876,
      "grad_norm": 4.444485664367676,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.9946,
      "step": 15
    },
    {
      "epoch": 0.0010930903029226502,
      "grad_norm": 6.395273685455322,
      "learning_rate": 8.535533905932738e-05,
      "loss": 9.5317,
      "step": 20
    },
    {
      "epoch": 0.0010930903029226502,
      "eval_loss": 2.2416298389434814,
      "eval_runtime": 695.2564,
      "eval_samples_per_second": 11.081,
      "eval_steps_per_second": 5.54,
      "step": 20
    },
    {
      "epoch": 0.0013663628786533127,
      "grad_norm": 7.272201061248779,
      "learning_rate": 6.91341716182545e-05,
      "loss": 8.8218,
      "step": 25
    },
    {
      "epoch": 0.0016396354543839753,
      "grad_norm": 7.44797945022583,
      "learning_rate": 5e-05,
      "loss": 8.5272,
      "step": 30
    },
    {
      "epoch": 0.0016396354543839753,
      "eval_loss": 2.082500696182251,
      "eval_runtime": 695.0217,
      "eval_samples_per_second": 11.085,
      "eval_steps_per_second": 5.542,
      "step": 30
    },
    {
      "epoch": 0.0019129080301146378,
      "grad_norm": 9.079113960266113,
      "learning_rate": 3.086582838174551e-05,
      "loss": 8.1588,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2328864478986240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}