Hugging Face's logo

jssky
/
c097e8b9-c870-4487-abcb-4ecfbb127315

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
c097e8b9-c870-4487-abcb-4ecfbb127315
File size: 3,201 Bytes 
8f747ef
 
 
cddb0ab
8f747ef
cddb0ab
8f747ef
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b174f42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f22da12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cddb0ab
 
 
 
 
 
 
8f747ef
 
 
 
 
 
 
 
 
 
 
 
 
 
cddb0ab
8f747ef
 
 
 
cddb0ab
8f747ef
 
 
 
 
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": 0.03656307129798903,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003656307129798903,
      "grad_norm": 0.09328000247478485,
      "learning_rate": 2e-05,
      "loss": 10.3619,
      "step": 1
    },
    {
      "epoch": 0.003656307129798903,
      "eval_loss": 10.363189697265625,
      "eval_runtime": 0.5775,
      "eval_samples_per_second": 798.302,
      "eval_steps_per_second": 100.437,
      "step": 1
    },
    {
      "epoch": 0.007312614259597806,
      "grad_norm": 0.08740244060754776,
      "learning_rate": 4e-05,
      "loss": 10.36,
      "step": 2
    },
    {
      "epoch": 0.010968921389396709,
      "grad_norm": 0.08197702467441559,
      "learning_rate": 6e-05,
      "loss": 10.3704,
      "step": 3
    },
    {
      "epoch": 0.010968921389396709,
      "eval_loss": 10.363097190856934,
      "eval_runtime": 0.5623,
      "eval_samples_per_second": 819.818,
      "eval_steps_per_second": 103.144,
      "step": 3
    },
    {
      "epoch": 0.014625228519195612,
      "grad_norm": 0.06572431325912476,
      "learning_rate": 8e-05,
      "loss": 10.3638,
      "step": 4
    },
    {
      "epoch": 0.018281535648994516,
      "grad_norm": 0.0900840014219284,
      "learning_rate": 0.0001,
      "loss": 10.3618,
      "step": 5
    },
    {
      "epoch": 0.021937842778793418,
      "grad_norm": 0.0838831216096878,
      "learning_rate": 0.00012,
      "loss": 10.361,
      "step": 6
    },
    {
      "epoch": 0.021937842778793418,
      "eval_loss": 10.362741470336914,
      "eval_runtime": 0.5688,
      "eval_samples_per_second": 810.488,
      "eval_steps_per_second": 101.97,
      "step": 6
    },
    {
      "epoch": 0.025594149908592323,
      "grad_norm": 0.09633658081293106,
      "learning_rate": 0.00014,
      "loss": 10.3703,
      "step": 7
    },
    {
      "epoch": 0.029250457038391225,
      "grad_norm": 0.088631272315979,
      "learning_rate": 0.00016,
      "loss": 10.3625,
      "step": 8
    },
    {
      "epoch": 0.03290676416819013,
      "grad_norm": 0.09016067534685135,
      "learning_rate": 0.00018,
      "loss": 10.3623,
      "step": 9
    },
    {
      "epoch": 0.03290676416819013,
      "eval_loss": 10.3621187210083,
      "eval_runtime": 0.559,
      "eval_samples_per_second": 824.669,
      "eval_steps_per_second": 103.754,
      "step": 9
    },
    {
      "epoch": 0.03656307129798903,
      "grad_norm": 0.07421699911355972,
      "learning_rate": 0.0002,
      "loss": 10.363,
      "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": 4184195727360.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}