Hugging Face's logo

duyphu
/
ee18d753-a67f-44fb-bd48-52c33d7962f4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ee18d753-a67f-44fb-bd48-52c33d7962f4
File size: 3,694 Bytes 
38c9f17
 
 
5c04bcc
bb075af
5c04bcc
38c9f17
 
 
 
 
 
 
bb075af
 
 
38c9f17
bb075af
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d84ac03
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71bda68
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5c04bcc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38c9f17
 
 
bb075af
38c9f17
 
bb075af
38c9f17
 
 
 
 
 
 
5c04bcc
38c9f17
 
 
 
5c04bcc
38c9f17
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5181347150259067,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010362694300518135,
      "eval_loss": 3.649900197982788,
      "eval_runtime": 0.7545,
      "eval_samples_per_second": 54.343,
      "eval_steps_per_second": 27.834,
      "step": 1
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 2.8373703956604004,
      "learning_rate": 5e-05,
      "loss": 3.5652,
      "step": 5
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 2.706880569458008,
      "learning_rate": 0.0001,
      "loss": 3.4354,
      "step": 10
    },
    {
      "epoch": 0.10362694300518134,
      "eval_loss": 3.3804771900177,
      "eval_runtime": 0.7498,
      "eval_samples_per_second": 54.684,
      "eval_steps_per_second": 28.009,
      "step": 10
    },
    {
      "epoch": 0.15544041450777202,
      "grad_norm": 1.4844454526901245,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.2829,
      "step": 15
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 1.2455134391784668,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.0929,
      "step": 20
    },
    {
      "epoch": 0.20725388601036268,
      "eval_loss": 3.0835258960723877,
      "eval_runtime": 0.7639,
      "eval_samples_per_second": 53.673,
      "eval_steps_per_second": 27.491,
      "step": 20
    },
    {
      "epoch": 0.25906735751295334,
      "grad_norm": 0.8904907703399658,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.0248,
      "step": 25
    },
    {
      "epoch": 0.31088082901554404,
      "grad_norm": 0.9830533266067505,
      "learning_rate": 5e-05,
      "loss": 2.9533,
      "step": 30
    },
    {
      "epoch": 0.31088082901554404,
      "eval_loss": 2.9466686248779297,
      "eval_runtime": 0.8016,
      "eval_samples_per_second": 51.146,
      "eval_steps_per_second": 26.197,
      "step": 30
    },
    {
      "epoch": 0.3626943005181347,
      "grad_norm": 1.1721653938293457,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.8659,
      "step": 35
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 1.0541706085205078,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.863,
      "step": 40
    },
    {
      "epoch": 0.41450777202072536,
      "eval_loss": 2.8699629306793213,
      "eval_runtime": 0.7571,
      "eval_samples_per_second": 54.151,
      "eval_steps_per_second": 27.736,
      "step": 40
    },
    {
      "epoch": 0.46632124352331605,
      "grad_norm": 0.825079619884491,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.7591,
      "step": 45
    },
    {
      "epoch": 0.5181347150259067,
      "grad_norm": 1.0289149284362793,
      "learning_rate": 0.0,
      "loss": 2.8184,
      "step": 50
    },
    {
      "epoch": 0.5181347150259067,
      "eval_loss": 2.857125759124756,
      "eval_runtime": 0.7555,
      "eval_samples_per_second": 54.266,
      "eval_steps_per_second": 27.795,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 171463252377600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}