Hugging Face's logo

joboffer
/
7f85054d-2929-4128-bf45-727e456e1f13

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
7f85054d-2929-4128-bf45-727e456e1f13
File size: 3,120 Bytes 
2bf134c
0950a65
 
 
2bf134c
0950a65
2bf134c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0950a65
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2bf134c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0950a65
2bf134c
 
 
 
 
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
 
{
  "best_metric": 0.7788602709770203,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0035234529839242457,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001761726491962123,
      "eval_loss": 1.2554974555969238,
      "eval_runtime": 773.1604,
      "eval_samples_per_second": 3.093,
      "eval_steps_per_second": 1.547,
      "step": 1
    },
    {
      "epoch": 0.0005285179475886368,
      "grad_norm": 1.7705259323120117,
      "learning_rate": 6e-05,
      "loss": 4.7927,
      "step": 3
    },
    {
      "epoch": 0.0008808632459810614,
      "eval_loss": 1.1834067106246948,
      "eval_runtime": 780.6272,
      "eval_samples_per_second": 3.063,
      "eval_steps_per_second": 1.532,
      "step": 5
    },
    {
      "epoch": 0.0010570358951772737,
      "grad_norm": 2.296821117401123,
      "learning_rate": 9.96057350657239e-05,
      "loss": 5.1837,
      "step": 6
    },
    {
      "epoch": 0.0015855538427659106,
      "grad_norm": 1.795020341873169,
      "learning_rate": 9.381533400219318e-05,
      "loss": 4.4933,
      "step": 9
    },
    {
      "epoch": 0.0017617264919621229,
      "eval_loss": 0.9860424995422363,
      "eval_runtime": 780.0353,
      "eval_samples_per_second": 3.065,
      "eval_steps_per_second": 1.533,
      "step": 10
    },
    {
      "epoch": 0.0021140717903545474,
      "grad_norm": 1.7132139205932617,
      "learning_rate": 8.18711994874345e-05,
      "loss": 3.8929,
      "step": 12
    },
    {
      "epoch": 0.0026425897379431843,
      "grad_norm": 1.8616305589675903,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.6906,
      "step": 15
    },
    {
      "epoch": 0.0026425897379431843,
      "eval_loss": 0.8647217750549316,
      "eval_runtime": 777.3119,
      "eval_samples_per_second": 3.076,
      "eval_steps_per_second": 1.539,
      "step": 15
    },
    {
      "epoch": 0.0031711076855318212,
      "grad_norm": 1.8421508073806763,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 3.2375,
      "step": 18
    },
    {
      "epoch": 0.0035234529839242457,
      "eval_loss": 0.7788602709770203,
      "eval_runtime": 781.0425,
      "eval_samples_per_second": 3.061,
      "eval_steps_per_second": 1.531,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.28688285138944e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}