Hugging Face's logo

ClarenceDan
/
e0be9d66-e3f4-4901-8130-c2e25a1ba053

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e0be9d66-e3f4-4901-8130-c2e25a1ba053
File size: 3,214 Bytes 
deeb9aa
 
 
64b4689
deeb9aa
64b4689
deeb9aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1f244e7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e3301b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64b4689
 
 
 
 
 
 
deeb9aa
 
 
 
 
 
 
 
 
 
 
 
 
 
64b4689
deeb9aa
 
 
 
64b4689
deeb9aa
 
 
 
 
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": 8.432396423820676e-05,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.432396423820677e-06,
      "grad_norm": 0.43550553917884827,
      "learning_rate": 2e-05,
      "loss": 1.3887,
      "step": 1
    },
    {
      "epoch": 8.432396423820677e-06,
      "eval_loss": 1.1402034759521484,
      "eval_runtime": 2512.1721,
      "eval_samples_per_second": 19.876,
      "eval_steps_per_second": 9.938,
      "step": 1
    },
    {
      "epoch": 1.6864792847641354e-05,
      "grad_norm": 0.2166118025779724,
      "learning_rate": 4e-05,
      "loss": 1.0644,
      "step": 2
    },
    {
      "epoch": 2.529718927146203e-05,
      "grad_norm": 0.25337040424346924,
      "learning_rate": 6e-05,
      "loss": 0.7921,
      "step": 3
    },
    {
      "epoch": 2.529718927146203e-05,
      "eval_loss": 1.1398595571517944,
      "eval_runtime": 6028.2231,
      "eval_samples_per_second": 8.283,
      "eval_steps_per_second": 4.142,
      "step": 3
    },
    {
      "epoch": 3.372958569528271e-05,
      "grad_norm": 0.43934348225593567,
      "learning_rate": 8e-05,
      "loss": 1.2741,
      "step": 4
    },
    {
      "epoch": 4.216198211910338e-05,
      "grad_norm": 0.25466489791870117,
      "learning_rate": 0.0001,
      "loss": 0.8955,
      "step": 5
    },
    {
      "epoch": 5.059437854292406e-05,
      "grad_norm": 0.41991177201271057,
      "learning_rate": 0.00012,
      "loss": 1.2128,
      "step": 6
    },
    {
      "epoch": 5.059437854292406e-05,
      "eval_loss": 1.1368786096572876,
      "eval_runtime": 6918.8083,
      "eval_samples_per_second": 7.217,
      "eval_steps_per_second": 3.609,
      "step": 6
    },
    {
      "epoch": 5.9026774966744735e-05,
      "grad_norm": 0.38990527391433716,
      "learning_rate": 0.00014,
      "loss": 1.2169,
      "step": 7
    },
    {
      "epoch": 6.745917139056541e-05,
      "grad_norm": 0.304204523563385,
      "learning_rate": 0.00016,
      "loss": 1.0724,
      "step": 8
    },
    {
      "epoch": 7.58915678143861e-05,
      "grad_norm": 0.4411507844924927,
      "learning_rate": 0.00018,
      "loss": 1.2062,
      "step": 9
    },
    {
      "epoch": 7.58915678143861e-05,
      "eval_loss": 1.1268764734268188,
      "eval_runtime": 6915.961,
      "eval_samples_per_second": 7.22,
      "eval_steps_per_second": 3.61,
      "step": 9
    },
    {
      "epoch": 8.432396423820676e-05,
      "grad_norm": 0.3528674244880676,
      "learning_rate": 0.0002,
      "loss": 0.9766,
      "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": 1230072997478400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}