Hugging Face's logo

VERSIL91
/
8e55ad6c-33d0-4ed6-9efc-3aba7caa5184

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
8e55ad6c-33d0-4ed6-9efc-3aba7caa5184
File size: 2,359 Bytes 
8058322
 
 
8bfa0a4
8058322
8bfa0a4
8058322
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8bfa0a4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8058322
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8bfa0a4
8058322
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004620560531749508,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.700934219582514e-05,
      "grad_norm": 0.44221264123916626,
      "learning_rate": 1e-05,
      "loss": 0.918,
      "step": 1
    },
    {
      "epoch": 7.700934219582514e-05,
      "eval_loss": 1.0547187328338623,
      "eval_runtime": 980.5874,
      "eval_samples_per_second": 22.304,
      "eval_steps_per_second": 11.152,
      "step": 1
    },
    {
      "epoch": 0.00015401868439165027,
      "grad_norm": 0.40297988057136536,
      "learning_rate": 2e-05,
      "loss": 0.9651,
      "step": 2
    },
    {
      "epoch": 0.0002310280265874754,
      "grad_norm": 0.6582609415054321,
      "learning_rate": 3e-05,
      "loss": 1.003,
      "step": 3
    },
    {
      "epoch": 0.0002310280265874754,
      "eval_loss": 1.0451246500015259,
      "eval_runtime": 846.3252,
      "eval_samples_per_second": 25.842,
      "eval_steps_per_second": 12.922,
      "step": 3
    },
    {
      "epoch": 0.00030803736878330055,
      "grad_norm": 0.6603010892868042,
      "learning_rate": 4e-05,
      "loss": 1.0077,
      "step": 4
    },
    {
      "epoch": 0.00038504671097912567,
      "grad_norm": 0.45248380303382874,
      "learning_rate": 5e-05,
      "loss": 0.9375,
      "step": 5
    },
    {
      "epoch": 0.0004620560531749508,
      "grad_norm": 0.43786242604255676,
      "learning_rate": 6e-05,
      "loss": 0.8561,
      "step": 6
    },
    {
      "epoch": 0.0004620560531749508,
      "eval_loss": 1.0127555131912231,
      "eval_runtime": 848.2642,
      "eval_samples_per_second": 25.783,
      "eval_steps_per_second": 12.892,
      "step": 6
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7405479238041600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}