Hugging Face's logo

chauhoang
/
0d5df66a-fe13-409b-a177-c353c2baadb3

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
0d5df66a-fe13-409b-a177-c353c2baadb3
File size: 3,686 Bytes 
f443f54
 
 
5cb3ee8
7601301
5cb3ee8
f443f54
 
 
 
 
 
 
7601301
 
 
f443f54
7601301
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
932c83e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3791db8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5cb3ee8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f443f54
 
 
7601301
f443f54
 
7601301
f443f54
 
 
 
 
 
 
5cb3ee8
f443f54
 
 
 
5cb3ee8
f443f54
 
 
 
 
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": 0.18248175182481752,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036496350364963502,
      "eval_loss": 2.616699695587158,
      "eval_runtime": 6.3179,
      "eval_samples_per_second": 18.361,
      "eval_steps_per_second": 9.18,
      "step": 1
    },
    {
      "epoch": 0.01824817518248175,
      "grad_norm": 1.6743769645690918,
      "learning_rate": 5e-05,
      "loss": 2.5534,
      "step": 5
    },
    {
      "epoch": 0.0364963503649635,
      "grad_norm": 1.8287861347198486,
      "learning_rate": 0.0001,
      "loss": 2.3519,
      "step": 10
    },
    {
      "epoch": 0.0364963503649635,
      "eval_loss": 2.002800464630127,
      "eval_runtime": 6.3103,
      "eval_samples_per_second": 18.383,
      "eval_steps_per_second": 9.191,
      "step": 10
    },
    {
      "epoch": 0.05474452554744526,
      "grad_norm": 2.0079925060272217,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7359,
      "step": 15
    },
    {
      "epoch": 0.072992700729927,
      "grad_norm": 2.5511863231658936,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1344,
      "step": 20
    },
    {
      "epoch": 0.072992700729927,
      "eval_loss": 0.8217958807945251,
      "eval_runtime": 6.4298,
      "eval_samples_per_second": 18.041,
      "eval_steps_per_second": 9.021,
      "step": 20
    },
    {
      "epoch": 0.09124087591240876,
      "grad_norm": 2.521385908126831,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6589,
      "step": 25
    },
    {
      "epoch": 0.10948905109489052,
      "grad_norm": 2.6327896118164062,
      "learning_rate": 5e-05,
      "loss": 0.3088,
      "step": 30
    },
    {
      "epoch": 0.10948905109489052,
      "eval_loss": 0.17604775726795197,
      "eval_runtime": 6.5101,
      "eval_samples_per_second": 17.818,
      "eval_steps_per_second": 8.909,
      "step": 30
    },
    {
      "epoch": 0.12773722627737227,
      "grad_norm": 2.246385335922241,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1334,
      "step": 35
    },
    {
      "epoch": 0.145985401459854,
      "grad_norm": 1.123745322227478,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.064,
      "step": 40
    },
    {
      "epoch": 0.145985401459854,
      "eval_loss": 0.043108660727739334,
      "eval_runtime": 6.4968,
      "eval_samples_per_second": 17.855,
      "eval_steps_per_second": 8.927,
      "step": 40
    },
    {
      "epoch": 0.16423357664233576,
      "grad_norm": 1.209367036819458,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0385,
      "step": 45
    },
    {
      "epoch": 0.18248175182481752,
      "grad_norm": 0.65992271900177,
      "learning_rate": 0.0,
      "loss": 0.0407,
      "step": 50
    },
    {
      "epoch": 0.18248175182481752,
      "eval_loss": 0.03230349346995354,
      "eval_runtime": 6.4146,
      "eval_samples_per_second": 18.084,
      "eval_steps_per_second": 9.042,
      "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": 2500486653542400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}