Hugging Face's logo

tuanna08go
/
3a33c715-523a-4987-9e25-23b57afcd0dd

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
3a33c715-523a-4987-9e25-23b57afcd0dd
File size: 2,238 Bytes 
d2901a9
 
 
d5d3a69
4e15551
d5d3a69
d2901a9
 
 
 
 
 
 
4e15551
 
 
d2901a9
4e15551
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d5d3a69
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d2901a9
 
 
4e15551
d2901a9
 
4e15551
d2901a9
 
 
 
 
 
 
4e15551
d2901a9
 
 
 
d5d3a69
d2901a9
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02034428794992175,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000782472613458529,
      "eval_loss": 11.766357421875,
      "eval_runtime": 14.1981,
      "eval_samples_per_second": 37.963,
      "eval_steps_per_second": 19.017,
      "step": 1
    },
    {
      "epoch": 0.003912363067292645,
      "grad_norm": 0.05658465996384621,
      "learning_rate": 5e-05,
      "loss": 11.764,
      "step": 5
    },
    {
      "epoch": 0.00782472613458529,
      "grad_norm": 0.03729768842458725,
      "learning_rate": 0.0001,
      "loss": 11.7637,
      "step": 10
    },
    {
      "epoch": 0.00782472613458529,
      "eval_loss": 11.766192436218262,
      "eval_runtime": 13.477,
      "eval_samples_per_second": 39.994,
      "eval_steps_per_second": 20.034,
      "step": 10
    },
    {
      "epoch": 0.011737089201877934,
      "grad_norm": 0.04390498623251915,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.7714,
      "step": 15
    },
    {
      "epoch": 0.01564945226917058,
      "grad_norm": 0.04456234350800514,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.7622,
      "step": 20
    },
    {
      "epoch": 0.01564945226917058,
      "eval_loss": 11.765852928161621,
      "eval_runtime": 12.723,
      "eval_samples_per_second": 42.364,
      "eval_steps_per_second": 21.221,
      "step": 20
    },
    {
      "epoch": 0.019561815336463225,
      "grad_norm": 0.057392362505197525,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.7654,
      "step": 25
    }
  ],
  "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": 1320287993856.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}