Hugging Face's logo

jssky
/
3f1228ab-8a91-48b8-8ea4-807689d90d3e

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
3f1228ab-8a91-48b8-8ea4-807689d90d3e
File size: 3,151 Bytes 
435958d
 
 
95af4e9
435958d
95af4e9
435958d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95df0b2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2acc88a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95af4e9
 
 
 
 
 
 
435958d
 
 
 
 
 
 
 
 
 
 
 
 
 
95af4e9
435958d
 
 
 
95af4e9
435958d
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00016234293321211728,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6234293321211728e-05,
      "grad_norm": 9.819344520568848,
      "learning_rate": 2e-05,
      "loss": 3.1041,
      "step": 1
    },
    {
      "epoch": 1.6234293321211728e-05,
      "eval_loss": NaN,
      "eval_runtime": 1684.6563,
      "eval_samples_per_second": 7.698,
      "eval_steps_per_second": 7.698,
      "step": 1
    },
    {
      "epoch": 3.2468586642423456e-05,
      "grad_norm": 11.458588600158691,
      "learning_rate": 4e-05,
      "loss": 3.7572,
      "step": 2
    },
    {
      "epoch": 4.8702879963635184e-05,
      "grad_norm": 11.369792938232422,
      "learning_rate": 6e-05,
      "loss": 2.8828,
      "step": 3
    },
    {
      "epoch": 4.8702879963635184e-05,
      "eval_loss": NaN,
      "eval_runtime": 1684.5918,
      "eval_samples_per_second": 7.698,
      "eval_steps_per_second": 7.698,
      "step": 3
    },
    {
      "epoch": 6.493717328484691e-05,
      "grad_norm": 9.130757331848145,
      "learning_rate": 8e-05,
      "loss": 3.286,
      "step": 4
    },
    {
      "epoch": 8.117146660605864e-05,
      "grad_norm": 9.889158248901367,
      "learning_rate": 0.0001,
      "loss": 2.3931,
      "step": 5
    },
    {
      "epoch": 9.740575992727037e-05,
      "grad_norm": 7.035650253295898,
      "learning_rate": 0.00012,
      "loss": 2.4323,
      "step": 6
    },
    {
      "epoch": 9.740575992727037e-05,
      "eval_loss": NaN,
      "eval_runtime": 1684.7423,
      "eval_samples_per_second": 7.697,
      "eval_steps_per_second": 7.697,
      "step": 6
    },
    {
      "epoch": 0.0001136400532484821,
      "grad_norm": 9.116958618164062,
      "learning_rate": 0.00014,
      "loss": 2.7834,
      "step": 7
    },
    {
      "epoch": 0.00012987434656969382,
      "grad_norm": 6.480123996734619,
      "learning_rate": 0.00016,
      "loss": 2.6653,
      "step": 8
    },
    {
      "epoch": 0.00014610863989090555,
      "grad_norm": 6.486927032470703,
      "learning_rate": 0.00018,
      "loss": 2.2272,
      "step": 9
    },
    {
      "epoch": 0.00014610863989090555,
      "eval_loss": NaN,
      "eval_runtime": 1684.8043,
      "eval_samples_per_second": 7.697,
      "eval_steps_per_second": 7.697,
      "step": 9
    },
    {
      "epoch": 0.00016234293321211728,
      "grad_norm": 5.726334571838379,
      "learning_rate": 0.0002,
      "loss": 2.212,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2010596581048320.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}