Hugging Face's logo

sn56z0
/
2c2e76c8-d646-414a-ab87-2a1939c2bdc0

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
2c2e76c8-d646-414a-ab87-2a1939c2bdc0
File size: 4,612 Bytes 
929501e
 
 
9a218fa
929501e
9a218fa
929501e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
427e12c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e727fdc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76a3ea6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9a218fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
929501e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9a218fa
929501e
 
 
 
 
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01944684528954192,
  "eval_steps": 9,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000432152117545376,
      "eval_loss": 2.312277317047119,
      "eval_runtime": 180.5436,
      "eval_samples_per_second": 86.345,
      "eval_steps_per_second": 2.703,
      "step": 1
    },
    {
      "epoch": 0.0012964563526361278,
      "grad_norm": 2.2848575115203857,
      "learning_rate": 3e-05,
      "loss": 2.362,
      "step": 3
    },
    {
      "epoch": 0.0025929127052722557,
      "grad_norm": 1.7597225904464722,
      "learning_rate": 6e-05,
      "loss": 2.1744,
      "step": 6
    },
    {
      "epoch": 0.0038893690579083835,
      "grad_norm": 1.3628700971603394,
      "learning_rate": 9e-05,
      "loss": 1.9805,
      "step": 9
    },
    {
      "epoch": 0.0038893690579083835,
      "eval_loss": 1.8443766832351685,
      "eval_runtime": 132.1231,
      "eval_samples_per_second": 117.988,
      "eval_steps_per_second": 3.694,
      "step": 9
    },
    {
      "epoch": 0.005185825410544511,
      "grad_norm": 1.3412178754806519,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.829,
      "step": 12
    },
    {
      "epoch": 0.00648228176318064,
      "grad_norm": 1.5588266849517822,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.7529,
      "step": 15
    },
    {
      "epoch": 0.007778738115816767,
      "grad_norm": 1.1395800113677979,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7135,
      "step": 18
    },
    {
      "epoch": 0.007778738115816767,
      "eval_loss": 1.6603822708129883,
      "eval_runtime": 132.0674,
      "eval_samples_per_second": 118.038,
      "eval_steps_per_second": 3.695,
      "step": 18
    },
    {
      "epoch": 0.009075194468452896,
      "grad_norm": 1.0279678106307983,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.6145,
      "step": 21
    },
    {
      "epoch": 0.010371650821089023,
      "grad_norm": 0.9357244372367859,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.6543,
      "step": 24
    },
    {
      "epoch": 0.011668107173725151,
      "grad_norm": 0.962315022945404,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.6006,
      "step": 27
    },
    {
      "epoch": 0.011668107173725151,
      "eval_loss": 1.5944404602050781,
      "eval_runtime": 132.0865,
      "eval_samples_per_second": 118.021,
      "eval_steps_per_second": 3.695,
      "step": 27
    },
    {
      "epoch": 0.01296456352636128,
      "grad_norm": 0.888576865196228,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.578,
      "step": 30
    },
    {
      "epoch": 0.014261019878997408,
      "grad_norm": 0.9320745468139648,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.5553,
      "step": 33
    },
    {
      "epoch": 0.015557476231633534,
      "grad_norm": 0.9765816330909729,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.5462,
      "step": 36
    },
    {
      "epoch": 0.015557476231633534,
      "eval_loss": 1.5527358055114746,
      "eval_runtime": 132.0946,
      "eval_samples_per_second": 118.014,
      "eval_steps_per_second": 3.694,
      "step": 36
    },
    {
      "epoch": 0.016853932584269662,
      "grad_norm": 0.9101667404174805,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.5658,
      "step": 39
    },
    {
      "epoch": 0.018150388936905792,
      "grad_norm": 0.9854418635368347,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.4873,
      "step": 42
    },
    {
      "epoch": 0.01944684528954192,
      "grad_norm": 1.0120340585708618,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5698,
      "step": 45
    },
    {
      "epoch": 0.01944684528954192,
      "eval_loss": 1.5253695249557495,
      "eval_runtime": 132.0927,
      "eval_samples_per_second": 118.016,
      "eval_steps_per_second": 3.694,
      "step": 45
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4235024213252506e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}