Hugging Face's logo

chauhoang
/
78162bad-ca18-b072-91a2-c6a11d0c1bf1

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files
xet
 Community
78162bad-ca18-b072-91a2-c6a11d0c1bf1
File size: 3,709 Bytes
3917225
 
 
e837ccf
73100ff
e837ccf
3917225
 
 
 
 
 
 
73100ff
 
 
3917225
73100ff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46b4531
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0a1c7f9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e837ccf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3917225
 
 
73100ff
3917225
 
73100ff
3917225
 
 
 
 
 
 
e837ccf
3917225
 
 
 
e837ccf
3917225
 
 
 
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": 0.016612675471384668,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033225350942769335,
      "eval_loss": 1.356743574142456,
      "eval_runtime": 69.6151,
      "eval_samples_per_second": 18.214,
      "eval_steps_per_second": 9.107,
      "step": 1
    },
    {
      "epoch": 0.0016612675471384666,
      "grad_norm": 1.057161569595337,
      "learning_rate": 5e-05,
      "loss": 1.2723,
      "step": 5
    },
    {
      "epoch": 0.003322535094276933,
      "grad_norm": 1.0211741924285889,
      "learning_rate": 0.0001,
      "loss": 1.2354,
      "step": 10
    },
    {
      "epoch": 0.003322535094276933,
      "eval_loss": 1.090079426765442,
      "eval_runtime": 69.432,
      "eval_samples_per_second": 18.262,
      "eval_steps_per_second": 9.131,
      "step": 10
    },
    {
      "epoch": 0.0049838026414154,
      "grad_norm": 1.071433424949646,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0207,
      "step": 15
    },
    {
      "epoch": 0.006645070188553866,
      "grad_norm": 1.2155852317810059,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.873,
      "step": 20
    },
    {
      "epoch": 0.006645070188553866,
      "eval_loss": 0.8100319504737854,
      "eval_runtime": 70.2598,
      "eval_samples_per_second": 18.047,
      "eval_steps_per_second": 9.024,
      "step": 20
    },
    {
      "epoch": 0.008306337735692334,
      "grad_norm": 1.0802018642425537,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.8331,
      "step": 25
    },
    {
      "epoch": 0.0099676052828308,
      "grad_norm": 0.9234360456466675,
      "learning_rate": 5e-05,
      "loss": 0.7435,
      "step": 30
    },
    {
      "epoch": 0.0099676052828308,
      "eval_loss": 0.7390913963317871,
      "eval_runtime": 69.6251,
      "eval_samples_per_second": 18.212,
      "eval_steps_per_second": 9.106,
      "step": 30
    },
    {
      "epoch": 0.011628872829969267,
      "grad_norm": 0.9415158629417419,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.7966,
      "step": 35
    },
    {
      "epoch": 0.013290140377107733,
      "grad_norm": 0.9960245490074158,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.755,
      "step": 40
    },
    {
      "epoch": 0.013290140377107733,
      "eval_loss": 0.7165237665176392,
      "eval_runtime": 70.0285,
      "eval_samples_per_second": 18.107,
      "eval_steps_per_second": 9.053,
      "step": 40
    },
    {
      "epoch": 0.0149514079242462,
      "grad_norm": 0.8190529942512512,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7666,
      "step": 45
    },
    {
      "epoch": 0.016612675471384668,
      "grad_norm": 0.927686870098114,
      "learning_rate": 0.0,
      "loss": 0.7215,
      "step": 50
    },
    {
      "epoch": 0.016612675471384668,
      "eval_loss": 0.7126367688179016,
      "eval_runtime": 69.167,
      "eval_samples_per_second": 18.332,
      "eval_steps_per_second": 9.166,
      "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
}