Hugging Face's logo

trenden
/
50b8b445-5fe2-489e-b773-e08b8a013f3c

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
50b8b445-5fe2-489e-b773-e08b8a013f3c
File size: 3,211 Bytes 
cbafe6c
 
 
bfec626
cbafe6c
bfec626
cbafe6c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0d43cbd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26ed0ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bfec626
 
 
 
 
 
 
cbafe6c
 
 
 
 
 
 
 
 
 
 
 
 
 
bfec626
cbafe6c
 
 
 
bfec626
cbafe6c
 
 
 
 
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": 0.0006324910660636918,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.324910660636919e-05,
      "grad_norm": 12.095507621765137,
      "learning_rate": 2e-05,
      "loss": 8.0756,
      "step": 1
    },
    {
      "epoch": 6.324910660636919e-05,
      "eval_loss": 9.130346298217773,
      "eval_runtime": 226.4984,
      "eval_samples_per_second": 29.395,
      "eval_steps_per_second": 14.698,
      "step": 1
    },
    {
      "epoch": 0.00012649821321273838,
      "grad_norm": 15.04973316192627,
      "learning_rate": 4e-05,
      "loss": 7.2496,
      "step": 2
    },
    {
      "epoch": 0.00018974731981910754,
      "grad_norm": 14.547382354736328,
      "learning_rate": 6e-05,
      "loss": 8.5275,
      "step": 3
    },
    {
      "epoch": 0.00018974731981910754,
      "eval_loss": 9.00229549407959,
      "eval_runtime": 226.4272,
      "eval_samples_per_second": 29.405,
      "eval_steps_per_second": 14.702,
      "step": 3
    },
    {
      "epoch": 0.00025299642642547676,
      "grad_norm": 16.72240447998047,
      "learning_rate": 8e-05,
      "loss": 8.9993,
      "step": 4
    },
    {
      "epoch": 0.0003162455330318459,
      "grad_norm": 12.045751571655273,
      "learning_rate": 0.0001,
      "loss": 8.7741,
      "step": 5
    },
    {
      "epoch": 0.0003794946396382151,
      "grad_norm": 17.086132049560547,
      "learning_rate": 0.00012,
      "loss": 9.3432,
      "step": 6
    },
    {
      "epoch": 0.0003794946396382151,
      "eval_loss": 7.4766669273376465,
      "eval_runtime": 226.3391,
      "eval_samples_per_second": 29.416,
      "eval_steps_per_second": 14.708,
      "step": 6
    },
    {
      "epoch": 0.0004427437462445843,
      "grad_norm": 13.617958068847656,
      "learning_rate": 0.00014,
      "loss": 7.4227,
      "step": 7
    },
    {
      "epoch": 0.0005059928528509535,
      "grad_norm": 12.062705993652344,
      "learning_rate": 0.00016,
      "loss": 6.9968,
      "step": 8
    },
    {
      "epoch": 0.0005692419594573227,
      "grad_norm": 14.231619834899902,
      "learning_rate": 0.00018,
      "loss": 5.896,
      "step": 9
    },
    {
      "epoch": 0.0005692419594573227,
      "eval_loss": 6.201642990112305,
      "eval_runtime": 226.526,
      "eval_samples_per_second": 29.392,
      "eval_steps_per_second": 14.696,
      "step": 9
    },
    {
      "epoch": 0.0006324910660636918,
      "grad_norm": 15.345791816711426,
      "learning_rate": 0.0002,
      "loss": 5.3196,
      "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": 1911091416268800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}