Hugging Face's logo

kk-aivio
/
4f83fc75-c47b-4ffc-9c5d-992d2de52d08

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files
xet
 Community
4f83fc75-c47b-4ffc-9c5d-992d2de52d08
File size: 2,344 Bytes
0aecb88
 
 
afdf379
0aecb88
afdf379
0aecb88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
afdf379
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0aecb88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
afdf379
0aecb88
 
 
 
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": 0.00199352105656616,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033225350942769335,
      "grad_norm": 1.0361193418502808,
      "learning_rate": 2e-05,
      "loss": 1.3271,
      "step": 1
    },
    {
      "epoch": 0.00033225350942769335,
      "eval_loss": 1.3564280271530151,
      "eval_runtime": 37.1559,
      "eval_samples_per_second": 34.126,
      "eval_steps_per_second": 17.063,
      "step": 1
    },
    {
      "epoch": 0.0006645070188553867,
      "grad_norm": 1.0444221496582031,
      "learning_rate": 4e-05,
      "loss": 1.2539,
      "step": 2
    },
    {
      "epoch": 0.00099676052828308,
      "grad_norm": 1.0711370706558228,
      "learning_rate": 6e-05,
      "loss": 1.2959,
      "step": 3
    },
    {
      "epoch": 0.00099676052828308,
      "eval_loss": 1.3421787023544312,
      "eval_runtime": 37.2185,
      "eval_samples_per_second": 34.069,
      "eval_steps_per_second": 17.035,
      "step": 3
    },
    {
      "epoch": 0.0013290140377107734,
      "grad_norm": 0.9208881258964539,
      "learning_rate": 8e-05,
      "loss": 1.1699,
      "step": 4
    },
    {
      "epoch": 0.0016612675471384666,
      "grad_norm": 1.0633083581924438,
      "learning_rate": 0.0001,
      "loss": 1.2754,
      "step": 5
    },
    {
      "epoch": 0.00199352105656616,
      "grad_norm": 1.0281527042388916,
      "learning_rate": 0.00012,
      "loss": 1.2609,
      "step": 6
    },
    {
      "epoch": 0.00199352105656616,
      "eval_loss": 1.1824383735656738,
      "eval_runtime": 37.281,
      "eval_samples_per_second": 34.012,
      "eval_steps_per_second": 17.006,
      "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": 300058398425088.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}