Hugging Face's logo

duyphu
/
ade6d149-5430-4614-9b8f-0bebe06ee174

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
ade6d149-5430-4614-9b8f-0bebe06ee174
File size: 3,696 Bytes 
f6929a6
 
 
2f1027f
2e4e5cb
2f1027f
f6929a6
 
 
 
 
 
 
2e4e5cb
 
 
f6929a6
2e4e5cb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a510feb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
378d29d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2f1027f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f6929a6
 
 
2e4e5cb
f6929a6
 
2e4e5cb
f6929a6
 
 
 
 
 
 
2f1027f
f6929a6
 
 
 
2f1027f
f6929a6
 
 
 
 
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": 0.10922992900054615,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002184598580010923,
      "eval_loss": 7.941990852355957,
      "eval_runtime": 14.6223,
      "eval_samples_per_second": 13.199,
      "eval_steps_per_second": 6.634,
      "step": 1
    },
    {
      "epoch": 0.010922992900054615,
      "grad_norm": 25.455711364746094,
      "learning_rate": 5e-05,
      "loss": 7.9324,
      "step": 5
    },
    {
      "epoch": 0.02184598580010923,
      "grad_norm": 22.484371185302734,
      "learning_rate": 0.0001,
      "loss": 5.7697,
      "step": 10
    },
    {
      "epoch": 0.02184598580010923,
      "eval_loss": 3.301812171936035,
      "eval_runtime": 14.8432,
      "eval_samples_per_second": 13.003,
      "eval_steps_per_second": 6.535,
      "step": 10
    },
    {
      "epoch": 0.03276897870016385,
      "grad_norm": 17.777523040771484,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1332,
      "step": 15
    },
    {
      "epoch": 0.04369197160021846,
      "grad_norm": 9.074566841125488,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.9946,
      "step": 20
    },
    {
      "epoch": 0.04369197160021846,
      "eval_loss": 0.9706413149833679,
      "eval_runtime": 14.9005,
      "eval_samples_per_second": 12.953,
      "eval_steps_per_second": 6.51,
      "step": 20
    },
    {
      "epoch": 0.054614964500273075,
      "grad_norm": 16.745901107788086,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.95,
      "step": 25
    },
    {
      "epoch": 0.0655379574003277,
      "grad_norm": 9.343716621398926,
      "learning_rate": 5e-05,
      "loss": 0.8587,
      "step": 30
    },
    {
      "epoch": 0.0655379574003277,
      "eval_loss": 0.9797313213348389,
      "eval_runtime": 14.9045,
      "eval_samples_per_second": 12.949,
      "eval_steps_per_second": 6.508,
      "step": 30
    },
    {
      "epoch": 0.0764609503003823,
      "grad_norm": 5.940131664276123,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.8317,
      "step": 35
    },
    {
      "epoch": 0.08738394320043692,
      "grad_norm": 14.620291709899902,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.9143,
      "step": 40
    },
    {
      "epoch": 0.08738394320043692,
      "eval_loss": 0.8667392134666443,
      "eval_runtime": 15.046,
      "eval_samples_per_second": 12.827,
      "eval_steps_per_second": 6.447,
      "step": 40
    },
    {
      "epoch": 0.09830693610049153,
      "grad_norm": 21.33104133605957,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.8446,
      "step": 45
    },
    {
      "epoch": 0.10922992900054615,
      "grad_norm": 14.127695083618164,
      "learning_rate": 0.0,
      "loss": 0.8292,
      "step": 50
    },
    {
      "epoch": 0.10922992900054615,
      "eval_loss": 0.8796916604042053,
      "eval_runtime": 14.9708,
      "eval_samples_per_second": 12.892,
      "eval_steps_per_second": 6.479,
      "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": 9603234366750720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}