Hugging Face's logo

jssky
/
21f1e99d-c83f-4c16-8bcf-5b77dd6886fe

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
21f1e99d-c83f-4c16-8bcf-5b77dd6886fe
File size: 3,189 Bytes 
3c6f039
 
 
a3a83bd
3c6f039
a3a83bd
3c6f039
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6d0ca47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b98572d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a3a83bd
 
 
 
 
 
 
3c6f039
 
 
 
 
 
 
 
 
 
 
 
 
 
a3a83bd
3c6f039
 
 
 
a3a83bd
3c6f039
 
 
 
 
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": 0.0021448871253150303,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021448871253150302,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 11.14,
      "step": 1
    },
    {
      "epoch": 0.00021448871253150302,
      "eval_loss": 11.310040473937988,
      "eval_runtime": 238.0023,
      "eval_samples_per_second": 4.126,
      "eval_steps_per_second": 4.126,
      "step": 1
    },
    {
      "epoch": 0.00042897742506300604,
      "grad_norm": 63.52291488647461,
      "learning_rate": 2e-05,
      "loss": 11.7604,
      "step": 2
    },
    {
      "epoch": 0.0006434661375945091,
      "grad_norm": 71.64099884033203,
      "learning_rate": 4e-05,
      "loss": 13.3246,
      "step": 3
    },
    {
      "epoch": 0.0006434661375945091,
      "eval_loss": 8.893160820007324,
      "eval_runtime": 231.8354,
      "eval_samples_per_second": 4.236,
      "eval_steps_per_second": 4.236,
      "step": 3
    },
    {
      "epoch": 0.0008579548501260121,
      "grad_norm": 59.29423904418945,
      "learning_rate": 6e-05,
      "loss": 8.4669,
      "step": 4
    },
    {
      "epoch": 0.0010724435626575152,
      "grad_norm": 43.15823745727539,
      "learning_rate": 8e-05,
      "loss": 5.8545,
      "step": 5
    },
    {
      "epoch": 0.0012869322751890182,
      "grad_norm": 42.88001251220703,
      "learning_rate": 0.0001,
      "loss": 4.0161,
      "step": 6
    },
    {
      "epoch": 0.0012869322751890182,
      "eval_loss": 1.5954408645629883,
      "eval_runtime": 230.2213,
      "eval_samples_per_second": 4.265,
      "eval_steps_per_second": 4.265,
      "step": 6
    },
    {
      "epoch": 0.0015014209877205213,
      "grad_norm": 40.18137741088867,
      "learning_rate": 0.00012,
      "loss": 1.7633,
      "step": 7
    },
    {
      "epoch": 0.0017159097002520242,
      "grad_norm": 27.18015480041504,
      "learning_rate": 0.00014,
      "loss": 0.5389,
      "step": 8
    },
    {
      "epoch": 0.0019303984127835272,
      "grad_norm": 59.13418197631836,
      "learning_rate": 0.00016,
      "loss": 2.1024,
      "step": 9
    },
    {
      "epoch": 0.0019303984127835272,
      "eval_loss": 2.6004724502563477,
      "eval_runtime": 230.3217,
      "eval_samples_per_second": 4.264,
      "eval_steps_per_second": 4.264,
      "step": 9
    },
    {
      "epoch": 0.0021448871253150303,
      "grad_norm": 33.359867095947266,
      "learning_rate": 0.00018,
      "loss": 2.2976,
      "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": 7668943615426560.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}