Hugging Face's logo

VERSIL91
/
5918f97d-468f-4cb8-b202-9aed97eeaeaa

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
5918f97d-468f-4cb8-b202-9aed97eeaeaa
File size: 2,196 Bytes 
3d9716d
 
 
d6786b4
3d9716d
d6786b4
3d9716d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fb276d0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d6786b4
 
 
 
 
 
 
3d9716d
 
 
 
 
 
 
 
 
 
 
 
 
 
d6786b4
3d9716d
 
 
 
d6786b4
3d9716d
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006483717763765744,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012967435527531487,
      "grad_norm": 1.1431047916412354,
      "learning_rate": 1e-05,
      "loss": 1.7935,
      "step": 1
    },
    {
      "epoch": 0.00012967435527531487,
      "eval_loss": 1.8209973573684692,
      "eval_runtime": 521.3515,
      "eval_samples_per_second": 24.912,
      "eval_steps_per_second": 12.456,
      "step": 1
    },
    {
      "epoch": 0.00025934871055062974,
      "grad_norm": 1.130334496498108,
      "learning_rate": 2e-05,
      "loss": 1.6793,
      "step": 2
    },
    {
      "epoch": 0.00025934871055062974,
      "eval_loss": 1.8031895160675049,
      "eval_runtime": 450.2468,
      "eval_samples_per_second": 28.846,
      "eval_steps_per_second": 14.423,
      "step": 2
    },
    {
      "epoch": 0.0003890230658259446,
      "grad_norm": 1.1945505142211914,
      "learning_rate": 3e-05,
      "loss": 1.9287,
      "step": 3
    },
    {
      "epoch": 0.0005186974211012595,
      "grad_norm": 1.2244787216186523,
      "learning_rate": 4e-05,
      "loss": 1.6216,
      "step": 4
    },
    {
      "epoch": 0.0005186974211012595,
      "eval_loss": 1.7570958137512207,
      "eval_runtime": 505.6656,
      "eval_samples_per_second": 25.685,
      "eval_steps_per_second": 12.842,
      "step": 4
    },
    {
      "epoch": 0.0006483717763765744,
      "grad_norm": 1.231426477432251,
      "learning_rate": 5e-05,
      "loss": 1.6159,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5398833250959360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}