Hugging Face's logo

kostiantynk1205
/
eaecb7ee-786a-4adf-b086-5ee362db5050

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
eaecb7ee-786a-4adf-b086-5ee362db5050
File size: 2,492 Bytes 
116fb17
 
 
6f48098
116fb17
6f48098
116fb17
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0bfa2e0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5431bf8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f48098
 
 
 
 
 
 
 
 
 
 
 
 
 
116fb17
 
 
 
 
 
 
 
 
 
 
 
 
 
6f48098
116fb17
 
 
 
6f48098
116fb17
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0014044450686422527,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.8088901372845056e-05,
      "eval_loss": 0.7164075374603271,
      "eval_runtime": 964.0198,
      "eval_samples_per_second": 15.549,
      "eval_steps_per_second": 7.775,
      "step": 1
    },
    {
      "epoch": 0.00028088901372845055,
      "grad_norm": 0.7382564544677734,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.5811,
      "step": 10
    },
    {
      "epoch": 0.0003651557178469857,
      "eval_loss": 0.4477322995662689,
      "eval_runtime": 961.1483,
      "eval_samples_per_second": 15.596,
      "eval_steps_per_second": 7.798,
      "step": 13
    },
    {
      "epoch": 0.0005617780274569011,
      "grad_norm": 0.35799071192741394,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.3801,
      "step": 20
    },
    {
      "epoch": 0.0007303114356939714,
      "eval_loss": 0.3870624005794525,
      "eval_runtime": 962.4524,
      "eval_samples_per_second": 15.575,
      "eval_steps_per_second": 7.787,
      "step": 26
    },
    {
      "epoch": 0.0008426670411853516,
      "grad_norm": 0.37750139832496643,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.3475,
      "step": 30
    },
    {
      "epoch": 0.0010954671535409572,
      "eval_loss": 0.3713858127593994,
      "eval_runtime": 962.8376,
      "eval_samples_per_second": 15.569,
      "eval_steps_per_second": 7.784,
      "step": 39
    },
    {
      "epoch": 0.0011235560549138022,
      "grad_norm": 0.3937116861343384,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.3116,
      "step": 40
    },
    {
      "epoch": 0.0014044450686422527,
      "grad_norm": 0.3013254404067993,
      "learning_rate": 0.0,
      "loss": 0.3787,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.790074844872704e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}