Hugging Face's logo

leixa
/
734ac95e-5bed-4ddb-b101-d50ed38eac5f

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
734ac95e-5bed-4ddb-b101-d50ed38eac5f
File size: 2,944 Bytes 
fe9c46c
 
 
37863cf
fe9c46c
37863cf
fe9c46c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f88fe11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
119d29e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37863cf
 
 
 
 
 
 
 
 
 
 
 
 
 
fe9c46c
 
 
 
 
 
 
 
 
 
 
 
 
 
37863cf
fe9c46c
 
 
 
37863cf
fe9c46c
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0120481927710843,
  "eval_steps": 11,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024096385542168676,
      "eval_loss": 2.2396206855773926,
      "eval_runtime": 0.819,
      "eval_samples_per_second": 21.977,
      "eval_steps_per_second": 10.988,
      "step": 1
    },
    {
      "epoch": 0.12048192771084337,
      "grad_norm": 2.930671453475952,
      "learning_rate": 5e-05,
      "loss": 8.4169,
      "step": 5
    },
    {
      "epoch": 0.24096385542168675,
      "grad_norm": 5.1463799476623535,
      "learning_rate": 0.0001,
      "loss": 9.684,
      "step": 10
    },
    {
      "epoch": 0.26506024096385544,
      "eval_loss": 2.027172088623047,
      "eval_runtime": 0.8116,
      "eval_samples_per_second": 22.179,
      "eval_steps_per_second": 11.09,
      "step": 11
    },
    {
      "epoch": 0.3614457831325301,
      "grad_norm": 4.772299289703369,
      "learning_rate": 9.409606321741775e-05,
      "loss": 8.0285,
      "step": 15
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 5.042806148529053,
      "learning_rate": 7.777851165098012e-05,
      "loss": 8.0437,
      "step": 20
    },
    {
      "epoch": 0.5301204819277109,
      "eval_loss": 1.8765888214111328,
      "eval_runtime": 0.8213,
      "eval_samples_per_second": 21.917,
      "eval_steps_per_second": 10.958,
      "step": 22
    },
    {
      "epoch": 0.6024096385542169,
      "grad_norm": 3.4582600593566895,
      "learning_rate": 5.490085701647805e-05,
      "loss": 7.4872,
      "step": 25
    },
    {
      "epoch": 0.7228915662650602,
      "grad_norm": 7.964458465576172,
      "learning_rate": 3.086582838174551e-05,
      "loss": 8.2409,
      "step": 30
    },
    {
      "epoch": 0.7951807228915663,
      "eval_loss": 1.8038959503173828,
      "eval_runtime": 0.8269,
      "eval_samples_per_second": 21.768,
      "eval_steps_per_second": 10.884,
      "step": 33
    },
    {
      "epoch": 0.8433734939759037,
      "grad_norm": 4.781399726867676,
      "learning_rate": 1.134947733186315e-05,
      "loss": 7.6683,
      "step": 35
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 7.088382720947266,
      "learning_rate": 9.607359798384785e-07,
      "loss": 7.8901,
      "step": 40
    }
  ],
  "logging_steps": 5,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 11,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5974486312550400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}