Hugging Face's logo

sn56a6
/
59f3f484-30b0-4a8b-9d14-e271c3cb0a95

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
59f3f484-30b0-4a8b-9d14-e271c3cb0a95
File size: 3,158 Bytes 
76c0103
 
 
bfd9a7c
76c0103
bfd9a7c
76c0103
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3bb25ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6547a69
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bfd9a7c
 
 
 
 
 
 
76c0103
 
 
 
 
 
 
 
 
 
 
 
 
 
bfd9a7c
76c0103
 
 
 
bfd9a7c
76c0103
 
 
 
 
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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0321285140562249,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00321285140562249,
      "grad_norm": 10.668553352355957,
      "learning_rate": 2e-05,
      "loss": 5.299,
      "step": 1
    },
    {
      "epoch": 0.00321285140562249,
      "eval_loss": 5.279109477996826,
      "eval_runtime": 6.1635,
      "eval_samples_per_second": 85.016,
      "eval_steps_per_second": 10.708,
      "step": 1
    },
    {
      "epoch": 0.00642570281124498,
      "grad_norm": 10.448212623596191,
      "learning_rate": 4e-05,
      "loss": 4.6254,
      "step": 2
    },
    {
      "epoch": 0.00963855421686747,
      "grad_norm": 10.46432876586914,
      "learning_rate": 6e-05,
      "loss": 5.0187,
      "step": 3
    },
    {
      "epoch": 0.00963855421686747,
      "eval_loss": 4.949011325836182,
      "eval_runtime": 6.217,
      "eval_samples_per_second": 84.285,
      "eval_steps_per_second": 10.616,
      "step": 3
    },
    {
      "epoch": 0.01285140562248996,
      "grad_norm": 9.103033065795898,
      "learning_rate": 8e-05,
      "loss": 3.8705,
      "step": 4
    },
    {
      "epoch": 0.01606425702811245,
      "grad_norm": 9.697961807250977,
      "learning_rate": 0.0001,
      "loss": 4.6658,
      "step": 5
    },
    {
      "epoch": 0.01927710843373494,
      "grad_norm": 6.769638538360596,
      "learning_rate": 0.00012,
      "loss": 3.7274,
      "step": 6
    },
    {
      "epoch": 0.01927710843373494,
      "eval_loss": 3.3475189208984375,
      "eval_runtime": 6.2189,
      "eval_samples_per_second": 84.26,
      "eval_steps_per_second": 10.613,
      "step": 6
    },
    {
      "epoch": 0.02248995983935743,
      "grad_norm": 7.49973201751709,
      "learning_rate": 0.00014,
      "loss": 2.8421,
      "step": 7
    },
    {
      "epoch": 0.02570281124497992,
      "grad_norm": 7.562386512756348,
      "learning_rate": 0.00016,
      "loss": 2.1444,
      "step": 8
    },
    {
      "epoch": 0.02891566265060241,
      "grad_norm": 6.556207180023193,
      "learning_rate": 0.00018,
      "loss": 1.8961,
      "step": 9
    },
    {
      "epoch": 0.02891566265060241,
      "eval_loss": 2.141901731491089,
      "eval_runtime": 6.22,
      "eval_samples_per_second": 84.244,
      "eval_steps_per_second": 10.611,
      "step": 9
    },
    {
      "epoch": 0.0321285140562249,
      "grad_norm": 13.10632610321045,
      "learning_rate": 0.0002,
      "loss": 1.7408,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8265470012555264.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}