Hugging Face's logo

cwaud
/
34e3b6a4-97a8-4874-897d-209ff15538ee

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
34e3b6a4-97a8-4874-897d-209ff15538ee
File size: 2,352 Bytes 
8e0879b
 
 
db99cc5
8e0879b
db99cc5
8e0879b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
db99cc5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8e0879b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
db99cc5
8e0879b
 
 
 
 
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": 0.0009859097071026578,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016431828451710963,
      "grad_norm": 1.6920582056045532,
      "learning_rate": 2e-05,
      "loss": 1.9238,
      "step": 1
    },
    {
      "epoch": 0.00016431828451710963,
      "eval_loss": 1.8038899898529053,
      "eval_runtime": 188.5099,
      "eval_samples_per_second": 13.596,
      "eval_steps_per_second": 6.801,
      "step": 1
    },
    {
      "epoch": 0.00032863656903421926,
      "grad_norm": 1.5381139516830444,
      "learning_rate": 4e-05,
      "loss": 1.3894,
      "step": 2
    },
    {
      "epoch": 0.0004929548535513289,
      "grad_norm": 2.7109837532043457,
      "learning_rate": 6e-05,
      "loss": 1.9371,
      "step": 3
    },
    {
      "epoch": 0.0004929548535513289,
      "eval_loss": 1.794869065284729,
      "eval_runtime": 193.4515,
      "eval_samples_per_second": 13.249,
      "eval_steps_per_second": 6.627,
      "step": 3
    },
    {
      "epoch": 0.0006572731380684385,
      "grad_norm": 1.109828233718872,
      "learning_rate": 8e-05,
      "loss": 1.645,
      "step": 4
    },
    {
      "epoch": 0.0008215914225855482,
      "grad_norm": 1.2177774906158447,
      "learning_rate": 0.0001,
      "loss": 1.7819,
      "step": 5
    },
    {
      "epoch": 0.0009859097071026578,
      "grad_norm": 1.7350780963897705,
      "learning_rate": 0.00012,
      "loss": 1.7212,
      "step": 6
    },
    {
      "epoch": 0.0009859097071026578,
      "eval_loss": 1.7177189588546753,
      "eval_runtime": 194.4652,
      "eval_samples_per_second": 13.18,
      "eval_steps_per_second": 6.592,
      "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": 501714738216960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}