Hugging Face's logo

VERSIL91
/
1cae8cbd-e6c5-43b7-a8dc-2531dc9f380e

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
1cae8cbd-e6c5-43b7-a8dc-2531dc9f380e
File size: 2,188 Bytes 
f5db359
 
 
de32323
f5db359
de32323
f5db359
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
108f06c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
de32323
 
 
 
 
 
 
f5db359
 
 
 
 
 
 
 
 
 
 
 
 
 
de32323
f5db359
 
 
 
de32323
f5db359
 
 
 
 
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": 0.000996189574876099,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019923791497521978,
      "grad_norm": 1.6526813507080078,
      "learning_rate": 1e-05,
      "loss": 2.2634,
      "step": 1
    },
    {
      "epoch": 0.00019923791497521978,
      "eval_loss": 2.703291416168213,
      "eval_runtime": 141.977,
      "eval_samples_per_second": 59.545,
      "eval_steps_per_second": 29.772,
      "step": 1
    },
    {
      "epoch": 0.00039847582995043956,
      "grad_norm": 1.9256006479263306,
      "learning_rate": 2e-05,
      "loss": 2.7682,
      "step": 2
    },
    {
      "epoch": 0.00039847582995043956,
      "eval_loss": 2.6866419315338135,
      "eval_runtime": 91.7448,
      "eval_samples_per_second": 92.147,
      "eval_steps_per_second": 46.073,
      "step": 2
    },
    {
      "epoch": 0.0005977137449256594,
      "grad_norm": 1.9943788051605225,
      "learning_rate": 3e-05,
      "loss": 2.7358,
      "step": 3
    },
    {
      "epoch": 0.0007969516599008791,
      "grad_norm": 1.673327088356018,
      "learning_rate": 4e-05,
      "loss": 2.2359,
      "step": 4
    },
    {
      "epoch": 0.0007969516599008791,
      "eval_loss": 2.6501004695892334,
      "eval_runtime": 92.615,
      "eval_samples_per_second": 91.281,
      "eval_steps_per_second": 45.641,
      "step": 4
    },
    {
      "epoch": 0.000996189574876099,
      "grad_norm": 2.082404851913452,
      "learning_rate": 5e-05,
      "loss": 2.7304,
      "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": 991192531599360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}