Hugging Face's logo

chauhoang
/
119c6de8-4d74-4658-80c6-2b3c1d5aab09

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
119c6de8-4d74-4658-80c6-2b3c1d5aab09
File size: 3,711 Bytes 
43ef7b5
 
 
f37899f
408f5ee
f37899f
43ef7b5
 
 
 
 
 
 
408f5ee
 
 
43ef7b5
408f5ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d90837f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ca342d0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f37899f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43ef7b5
 
 
408f5ee
43ef7b5
 
408f5ee
43ef7b5
 
 
 
 
 
 
f37899f
43ef7b5
 
 
 
f37899f
43ef7b5
 
 
 
 
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": 0.08837825894829872,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017675651789659744,
      "eval_loss": 1.5736385583877563,
      "eval_runtime": 18.5113,
      "eval_samples_per_second": 12.911,
      "eval_steps_per_second": 6.483,
      "step": 1
    },
    {
      "epoch": 0.008837825894829872,
      "grad_norm": 1.6883810758590698,
      "learning_rate": 5e-05,
      "loss": 1.4734,
      "step": 5
    },
    {
      "epoch": 0.017675651789659744,
      "grad_norm": 1.110305666923523,
      "learning_rate": 0.0001,
      "loss": 1.4599,
      "step": 10
    },
    {
      "epoch": 0.017675651789659744,
      "eval_loss": 1.436456561088562,
      "eval_runtime": 18.9204,
      "eval_samples_per_second": 12.632,
      "eval_steps_per_second": 6.342,
      "step": 10
    },
    {
      "epoch": 0.026513477684489615,
      "grad_norm": 1.0780854225158691,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.3273,
      "step": 15
    },
    {
      "epoch": 0.03535130357931949,
      "grad_norm": 1.3645310401916504,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.2836,
      "step": 20
    },
    {
      "epoch": 0.03535130357931949,
      "eval_loss": 1.2428770065307617,
      "eval_runtime": 18.9823,
      "eval_samples_per_second": 12.591,
      "eval_steps_per_second": 6.322,
      "step": 20
    },
    {
      "epoch": 0.04418912947414936,
      "grad_norm": 0.8436744213104248,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2168,
      "step": 25
    },
    {
      "epoch": 0.05302695536897923,
      "grad_norm": 0.8301315307617188,
      "learning_rate": 5e-05,
      "loss": 1.2328,
      "step": 30
    },
    {
      "epoch": 0.05302695536897923,
      "eval_loss": 1.2236849069595337,
      "eval_runtime": 18.9713,
      "eval_samples_per_second": 12.598,
      "eval_steps_per_second": 6.325,
      "step": 30
    },
    {
      "epoch": 0.0618647812638091,
      "grad_norm": 0.879909336566925,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.2017,
      "step": 35
    },
    {
      "epoch": 0.07070260715863898,
      "grad_norm": 1.6775568723678589,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.1638,
      "step": 40
    },
    {
      "epoch": 0.07070260715863898,
      "eval_loss": 1.2111330032348633,
      "eval_runtime": 19.0169,
      "eval_samples_per_second": 12.568,
      "eval_steps_per_second": 6.31,
      "step": 40
    },
    {
      "epoch": 0.07954043305346885,
      "grad_norm": 0.7706012725830078,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.0841,
      "step": 45
    },
    {
      "epoch": 0.08837825894829872,
      "grad_norm": 0.9315032362937927,
      "learning_rate": 0.0,
      "loss": 1.2157,
      "step": 50
    },
    {
      "epoch": 0.08837825894829872,
      "eval_loss": 1.2092931270599365,
      "eval_runtime": 18.9727,
      "eval_samples_per_second": 12.597,
      "eval_steps_per_second": 6.325,
      "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": 1.1051146382671872e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}