Hugging Face's logo

eeeebbb2
/
1af61237-f42d-4174-80a9-320ae53bdb09

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
1af61237-f42d-4174-80a9-320ae53bdb09
File size: 2,672 Bytes 
cc14848
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.409090909090909,
  "eval_steps": 25,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 13.995810508728027,
      "learning_rate": 9.728616793536588e-05,
      "loss": 5.9656,
      "step": 1
    },
    {
      "epoch": 0.36363636363636365,
      "eval_loss": 4.640727519989014,
      "eval_runtime": 3.9673,
      "eval_samples_per_second": 12.603,
      "eval_steps_per_second": 3.277,
      "step": 1
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 9.464171409606934,
      "learning_rate": 8.947199994035401e-05,
      "loss": 4.3631,
      "step": 2
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 10.678471565246582,
      "learning_rate": 7.75e-05,
      "loss": 4.1543,
      "step": 3
    },
    {
      "epoch": 1.5,
      "grad_norm": 5.6354475021362305,
      "learning_rate": 6.281416799501188e-05,
      "loss": 2.4264,
      "step": 4
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 7.748903274536133,
      "learning_rate": 4.718583200498814e-05,
      "loss": 3.0526,
      "step": 5
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 6.438746452331543,
      "learning_rate": 3.250000000000001e-05,
      "loss": 2.2736,
      "step": 6
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 3.6028335094451904,
      "learning_rate": 2.0528000059645997e-05,
      "loss": 1.8927,
      "step": 7
    },
    {
      "epoch": 3.0454545454545454,
      "grad_norm": 4.209403991699219,
      "learning_rate": 1.2713832064634126e-05,
      "loss": 2.3577,
      "step": 8
    },
    {
      "epoch": 3.409090909090909,
      "grad_norm": 3.089271068572998,
      "learning_rate": 1e-05,
      "loss": 1.8169,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 9,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1114062820042342e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}