Hugging Face's logo

tuanna08go
/
34d41093-d500-4836-9a6e-21c22b3dc3cb

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
34d41093-d500-4836-9a6e-21c22b3dc3cb
File size: 3,700 Bytes 
61a507f
 
 
88eb040
196fbdd
88eb040
61a507f
 
 
 
 
 
 
196fbdd
 
 
61a507f
196fbdd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
deb5471
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cbfbe03
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88eb040
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61a507f
 
 
196fbdd
61a507f
 
196fbdd
61a507f
 
 
 
 
 
 
88eb040
61a507f
 
 
 
88eb040
61a507f
 
 
 
 
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": 0.11025358324145534,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002205071664829107,
      "eval_loss": 2.177356719970703,
      "eval_runtime": 9.5836,
      "eval_samples_per_second": 19.93,
      "eval_steps_per_second": 10.017,
      "step": 1
    },
    {
      "epoch": 0.011025358324145534,
      "grad_norm": 3.0545544624328613,
      "learning_rate": 5e-05,
      "loss": 2.1943,
      "step": 5
    },
    {
      "epoch": 0.022050716648291068,
      "grad_norm": 2.2579193115234375,
      "learning_rate": 0.0001,
      "loss": 2.2168,
      "step": 10
    },
    {
      "epoch": 0.022050716648291068,
      "eval_loss": 1.7749028205871582,
      "eval_runtime": 9.6049,
      "eval_samples_per_second": 19.886,
      "eval_steps_per_second": 9.995,
      "step": 10
    },
    {
      "epoch": 0.03307607497243661,
      "grad_norm": 2.798457622528076,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7471,
      "step": 15
    },
    {
      "epoch": 0.044101433296582136,
      "grad_norm": 2.5906262397766113,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.5741,
      "step": 20
    },
    {
      "epoch": 0.044101433296582136,
      "eval_loss": 1.4727933406829834,
      "eval_runtime": 9.6402,
      "eval_samples_per_second": 19.813,
      "eval_steps_per_second": 9.958,
      "step": 20
    },
    {
      "epoch": 0.05512679162072767,
      "grad_norm": 2.3336644172668457,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.4489,
      "step": 25
    },
    {
      "epoch": 0.06615214994487321,
      "grad_norm": 2.168654680252075,
      "learning_rate": 5e-05,
      "loss": 1.4988,
      "step": 30
    },
    {
      "epoch": 0.06615214994487321,
      "eval_loss": 1.4284926652908325,
      "eval_runtime": 9.9918,
      "eval_samples_per_second": 19.116,
      "eval_steps_per_second": 9.608,
      "step": 30
    },
    {
      "epoch": 0.07717750826901874,
      "grad_norm": 2.2377634048461914,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.3625,
      "step": 35
    },
    {
      "epoch": 0.08820286659316427,
      "grad_norm": 2.3646817207336426,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.401,
      "step": 40
    },
    {
      "epoch": 0.08820286659316427,
      "eval_loss": 1.4094713926315308,
      "eval_runtime": 9.8204,
      "eval_samples_per_second": 19.449,
      "eval_steps_per_second": 9.776,
      "step": 40
    },
    {
      "epoch": 0.09922822491730982,
      "grad_norm": 2.390453577041626,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.5494,
      "step": 45
    },
    {
      "epoch": 0.11025358324145534,
      "grad_norm": 2.1996264457702637,
      "learning_rate": 0.0,
      "loss": 1.3396,
      "step": 50
    },
    {
      "epoch": 0.11025358324145534,
      "eval_loss": 1.405466914176941,
      "eval_runtime": 9.8045,
      "eval_samples_per_second": 19.481,
      "eval_steps_per_second": 9.791,
      "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
}