Hugging Face's logo

phungkhaccuong
/
95543050-c30c-43e1-a30c-c764cad05be3

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
95543050-c30c-43e1-a30c-c764cad05be3
File size: 3,703 Bytes 
dfa8b99
 
 
d73123b
668babc
d73123b
dfa8b99
 
 
 
 
 
 
668babc
 
 
dfa8b99
668babc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1bb7c3e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5db52c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d73123b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dfa8b99
 
 
668babc
dfa8b99
 
668babc
dfa8b99
 
 
 
 
 
 
d73123b
dfa8b99
 
 
 
d73123b
dfa8b99
 
 
 
 
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": 0.04193751310547285,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000838750262109457,
      "eval_loss": 1.2205588817596436,
      "eval_runtime": 33.6875,
      "eval_samples_per_second": 14.902,
      "eval_steps_per_second": 7.451,
      "step": 1
    },
    {
      "epoch": 0.004193751310547285,
      "grad_norm": 0.7135269641876221,
      "learning_rate": 5e-05,
      "loss": 1.1479,
      "step": 5
    },
    {
      "epoch": 0.00838750262109457,
      "grad_norm": 1.156472086906433,
      "learning_rate": 0.0001,
      "loss": 1.1771,
      "step": 10
    },
    {
      "epoch": 0.00838750262109457,
      "eval_loss": 1.0230368375778198,
      "eval_runtime": 33.9518,
      "eval_samples_per_second": 14.786,
      "eval_steps_per_second": 7.393,
      "step": 10
    },
    {
      "epoch": 0.012581253931641853,
      "grad_norm": 0.8804078698158264,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0332,
      "step": 15
    },
    {
      "epoch": 0.01677500524218914,
      "grad_norm": 0.9397221207618713,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8737,
      "step": 20
    },
    {
      "epoch": 0.01677500524218914,
      "eval_loss": 0.8285709619522095,
      "eval_runtime": 34.0574,
      "eval_samples_per_second": 14.74,
      "eval_steps_per_second": 7.37,
      "step": 20
    },
    {
      "epoch": 0.020968756552736424,
      "grad_norm": 0.714771032333374,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8035,
      "step": 25
    },
    {
      "epoch": 0.025162507863283706,
      "grad_norm": 0.6851562261581421,
      "learning_rate": 5e-05,
      "loss": 0.76,
      "step": 30
    },
    {
      "epoch": 0.025162507863283706,
      "eval_loss": 0.7844892740249634,
      "eval_runtime": 34.0815,
      "eval_samples_per_second": 14.729,
      "eval_steps_per_second": 7.365,
      "step": 30
    },
    {
      "epoch": 0.02935625917383099,
      "grad_norm": 0.6834311485290527,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7816,
      "step": 35
    },
    {
      "epoch": 0.03355001048437828,
      "grad_norm": 0.7540104985237122,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.7359,
      "step": 40
    },
    {
      "epoch": 0.03355001048437828,
      "eval_loss": 0.7644742131233215,
      "eval_runtime": 34.1728,
      "eval_samples_per_second": 14.69,
      "eval_steps_per_second": 7.345,
      "step": 40
    },
    {
      "epoch": 0.037743761794925564,
      "grad_norm": 0.6550795435905457,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7887,
      "step": 45
    },
    {
      "epoch": 0.04193751310547285,
      "grad_norm": 0.7117176651954651,
      "learning_rate": 0.0,
      "loss": 0.8369,
      "step": 50
    },
    {
      "epoch": 0.04193751310547285,
      "eval_loss": 0.7608298659324646,
      "eval_runtime": 34.1496,
      "eval_samples_per_second": 14.7,
      "eval_steps_per_second": 7.35,
      "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": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}