Hugging Face's logo

shibajustfor
/
657f2bbb-276d-41ed-8e70-4994c883be7f

PEFT
Safetensors
gptj
axolotl
Generated from Trainer
Model card Files Community
657f2bbb-276d-41ed-8e70-4994c883be7f
File size: 2,484 Bytes 
cb9e30b
 
 
0189033
cb9e30b
0189033
cb9e30b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c7e6865
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77c4204
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0189033
 
 
 
 
 
 
 
 
 
 
 
 
 
cb9e30b
 
 
 
 
 
 
 
 
 
 
 
 
 
0189033
cb9e30b
 
 
 
0189033
cb9e30b
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000865909573063285,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.73181914612657e-05,
      "eval_loss": 2.1214678287506104,
      "eval_runtime": 1102.6932,
      "eval_samples_per_second": 22.049,
      "eval_steps_per_second": 11.025,
      "step": 1
    },
    {
      "epoch": 0.000173181914612657,
      "grad_norm": 2.4697346687316895,
      "learning_rate": 0.00019396926207859084,
      "loss": 8.3142,
      "step": 10
    },
    {
      "epoch": 0.0002251364889964541,
      "eval_loss": 1.672813892364502,
      "eval_runtime": 1102.7354,
      "eval_samples_per_second": 22.048,
      "eval_steps_per_second": 11.024,
      "step": 13
    },
    {
      "epoch": 0.000346363829225314,
      "grad_norm": 2.826448678970337,
      "learning_rate": 0.00015000000000000001,
      "loss": 6.3914,
      "step": 20
    },
    {
      "epoch": 0.0004502729779929082,
      "eval_loss": 1.5376884937286377,
      "eval_runtime": 1102.0089,
      "eval_samples_per_second": 22.062,
      "eval_steps_per_second": 11.032,
      "step": 26
    },
    {
      "epoch": 0.000519545743837971,
      "grad_norm": 2.897918939590454,
      "learning_rate": 8.263518223330697e-05,
      "loss": 5.9956,
      "step": 30
    },
    {
      "epoch": 0.0006754094669893623,
      "eval_loss": 1.502578616142273,
      "eval_runtime": 1102.0929,
      "eval_samples_per_second": 22.061,
      "eval_steps_per_second": 11.031,
      "step": 39
    },
    {
      "epoch": 0.000692727658450628,
      "grad_norm": 5.3965325355529785,
      "learning_rate": 2.339555568810221e-05,
      "loss": 5.587,
      "step": 40
    },
    {
      "epoch": 0.000865909573063285,
      "grad_norm": 3.153414011001587,
      "learning_rate": 0.0,
      "loss": 5.9974,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0334801139984384e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}