Hugging Face's logo

dimasik1987
/
2e725caa-495f-458a-8cb9-93dc90a8af13

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
2e725caa-495f-458a-8cb9-93dc90a8af13
File size: 3,275 Bytes 
ff9d33a
 
 
e0e96f6
ff9d33a
e0e96f6
ff9d33a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ebb7b57
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e0e96f6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff9d33a
 
 
 
 
 
 
 
 
 
 
 
 
 
e0e96f6
ff9d33a
 
 
 
e0e96f6
ff9d33a
 
 
 
 
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
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029607698001480384,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009869232667160128,
      "eval_loss": 1.1808140277862549,
      "eval_runtime": 47.629,
      "eval_samples_per_second": 8.965,
      "eval_steps_per_second": 4.493,
      "step": 1
    },
    {
      "epoch": 0.0029607698001480384,
      "grad_norm": 3.3512725830078125,
      "learning_rate": 6e-05,
      "loss": 4.7998,
      "step": 3
    },
    {
      "epoch": 0.005921539600296077,
      "grad_norm": 4.269518852233887,
      "learning_rate": 0.00012,
      "loss": 4.8916,
      "step": 6
    },
    {
      "epoch": 0.007895386133728102,
      "eval_loss": 0.9780867099761963,
      "eval_runtime": 48.086,
      "eval_samples_per_second": 8.88,
      "eval_steps_per_second": 4.45,
      "step": 8
    },
    {
      "epoch": 0.008882309400444115,
      "grad_norm": 5.373497486114502,
      "learning_rate": 0.00018,
      "loss": 4.2661,
      "step": 9
    },
    {
      "epoch": 0.011843079200592153,
      "grad_norm": 4.902787685394287,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.7163,
      "step": 12
    },
    {
      "epoch": 0.014803849000740192,
      "grad_norm": 4.044931411743164,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.9925,
      "step": 15
    },
    {
      "epoch": 0.015790772267456205,
      "eval_loss": 0.642095685005188,
      "eval_runtime": 48.5408,
      "eval_samples_per_second": 8.797,
      "eval_steps_per_second": 4.409,
      "step": 16
    },
    {
      "epoch": 0.01776461880088823,
      "grad_norm": 5.7240214347839355,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.5394,
      "step": 18
    },
    {
      "epoch": 0.02072538860103627,
      "grad_norm": 3.553171157836914,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.8476,
      "step": 21
    },
    {
      "epoch": 0.023686158401184307,
      "grad_norm": 7.226178169250488,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.0504,
      "step": 24
    },
    {
      "epoch": 0.023686158401184307,
      "eval_loss": 0.5628054738044739,
      "eval_runtime": 48.9279,
      "eval_samples_per_second": 8.727,
      "eval_steps_per_second": 4.374,
      "step": 24
    },
    {
      "epoch": 0.026646928201332347,
      "grad_norm": 5.056282043457031,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.0441,
      "step": 27
    },
    {
      "epoch": 0.029607698001480384,
      "grad_norm": 3.949553966522217,
      "learning_rate": 0.0,
      "loss": 2.3592,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9801873028546560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}