Hugging Face's logo

ivangrapher
/
fea6a7f6-5768-46b2-8073-ff96f567f2c9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
fea6a7f6-5768-46b2-8073-ff96f567f2c9
File size: 3,307 Bytes
58950bc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.0011183493164089804,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.727831054696601e-05,
      "eval_loss": 9.17426586151123,
      "eval_runtime": 1670.2712,
      "eval_samples_per_second": 6.762,
      "eval_steps_per_second": 3.381,
      "step": 1
    },
    {
      "epoch": 0.00011183493164089804,
      "grad_norm": 8.672355651855469,
      "learning_rate": 6e-05,
      "loss": 10.7953,
      "step": 3
    },
    {
      "epoch": 0.00022366986328179608,
      "grad_norm": 6.415405750274658,
      "learning_rate": 0.00012,
      "loss": 5.7534,
      "step": 6
    },
    {
      "epoch": 0.00029822648437572807,
      "eval_loss": 4.07205057144165,
      "eval_runtime": 1681.9115,
      "eval_samples_per_second": 6.716,
      "eval_steps_per_second": 3.358,
      "step": 8
    },
    {
      "epoch": 0.0003355047949226941,
      "grad_norm": 14.511173248291016,
      "learning_rate": 0.00018,
      "loss": 4.8316,
      "step": 9
    },
    {
      "epoch": 0.00044733972656359216,
      "grad_norm": 12.734044075012207,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.8366,
      "step": 12
    },
    {
      "epoch": 0.0005591746582044902,
      "grad_norm": 8.869030952453613,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.2011,
      "step": 15
    },
    {
      "epoch": 0.0005964529687514561,
      "eval_loss": 1.5937066078186035,
      "eval_runtime": 1682.2165,
      "eval_samples_per_second": 6.714,
      "eval_steps_per_second": 3.357,
      "step": 16
    },
    {
      "epoch": 0.0006710095898453882,
      "grad_norm": 8.932065963745117,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.3685,
      "step": 18
    },
    {
      "epoch": 0.0007828445214862862,
      "grad_norm": 8.256165504455566,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.404,
      "step": 21
    },
    {
      "epoch": 0.0008946794531271843,
      "grad_norm": 4.563572883605957,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.0567,
      "step": 24
    },
    {
      "epoch": 0.0008946794531271843,
      "eval_loss": 1.3930147886276245,
      "eval_runtime": 1680.4632,
      "eval_samples_per_second": 6.721,
      "eval_steps_per_second": 3.361,
      "step": 24
    },
    {
      "epoch": 0.0010065143847680822,
      "grad_norm": 8.776552200317383,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.5312,
      "step": 27
    },
    {
      "epoch": 0.0011183493164089804,
      "grad_norm": 6.855684757232666,
      "learning_rate": 0.0,
      "loss": 1.1873,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2577036887392256e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}