Hugging Face's logo

tuantmdev
/
800686be-cd27-440c-8756-80855c8dbbf8

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
800686be-cd27-440c-8756-80855c8dbbf8
File size: 2,790 Bytes 
8b6f5b6
 
 
c52471a
1722a29
c52471a
8b6f5b6
 
 
 
 
 
 
1722a29
 
8b6f5b6
 
1722a29
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a26f7a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c52471a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b6f5b6
 
 
1722a29
8b6f5b6
 
1722a29
8b6f5b6
 
 
 
 
 
 
1722a29
8b6f5b6
 
 
 
c52471a
8b6f5b6
 
 
 
 
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": 0.004189719073964656,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010742869420422194,
      "eval_loss": 3.1173388957977295,
      "eval_runtime": 479.8029,
      "eval_samples_per_second": 8.17,
      "eval_steps_per_second": 4.085,
      "step": 1
    },
    {
      "epoch": 0.0005371434710211097,
      "grad_norm": 3.4544060230255127,
      "learning_rate": 5e-05,
      "loss": 2.8156,
      "step": 5
    },
    {
      "epoch": 0.0010742869420422194,
      "grad_norm": 3.225125551223755,
      "learning_rate": 0.0001,
      "loss": 2.5232,
      "step": 10
    },
    {
      "epoch": 0.0010742869420422194,
      "eval_loss": 2.313772439956665,
      "eval_runtime": 482.0841,
      "eval_samples_per_second": 8.131,
      "eval_steps_per_second": 4.066,
      "step": 10
    },
    {
      "epoch": 0.0016114304130633293,
      "grad_norm": 4.3110456466674805,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.6044,
      "step": 15
    },
    {
      "epoch": 0.002148573884084439,
      "grad_norm": 4.142456531524658,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1602,
      "step": 20
    },
    {
      "epoch": 0.002148573884084439,
      "eval_loss": 1.0064030885696411,
      "eval_runtime": 480.91,
      "eval_samples_per_second": 8.151,
      "eval_steps_per_second": 4.076,
      "step": 20
    },
    {
      "epoch": 0.0026857173551055485,
      "grad_norm": 4.778378963470459,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8835,
      "step": 25
    },
    {
      "epoch": 0.0032228608261266585,
      "grad_norm": 5.472487449645996,
      "learning_rate": 5e-05,
      "loss": 0.8802,
      "step": 30
    },
    {
      "epoch": 0.0032228608261266585,
      "eval_loss": 0.7272688150405884,
      "eval_runtime": 481.7044,
      "eval_samples_per_second": 8.138,
      "eval_steps_per_second": 4.069,
      "step": 30
    },
    {
      "epoch": 0.003760004297147768,
      "grad_norm": 4.021572113037109,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.6523,
      "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": 1.4426852391124992e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}