Hugging Face's logo

nativemind
/
shridhar_8k_multimodal

PEFT
Safetensors
gpt2
multimodal
spiritual
multilingual
icaros
jiv-jago
thai
russian
spanish
hindi
meditation
yoga
freedome
love-destiny
shridhar
lora
Model card Files
xet
Community
shridhar_8k_multimodal
File size: 2,902 Bytes 
59b33ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_global_step": 100,
  "best_metric": 4.216272830963135,
  "best_model_checkpoint": "./shridhar_multilingual_retrained/checkpoint-100",
  "epoch": 9.094117647058823,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 22.509538650512695,
      "learning_rate": 9.000000000000001e-07,
      "loss": 4.445,
      "step": 10
    },
    {
      "epoch": 1.8470588235294119,
      "grad_norm": 17.885433197021484,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 4.6913,
      "step": 20
    },
    {
      "epoch": 2.7529411764705882,
      "grad_norm": 17.10190200805664,
      "learning_rate": 2.9e-06,
      "loss": 4.5176,
      "step": 30
    },
    {
      "epoch": 3.6588235294117646,
      "grad_norm": 17.561813354492188,
      "learning_rate": 3.900000000000001e-06,
      "loss": 4.2982,
      "step": 40
    },
    {
      "epoch": 4.564705882352941,
      "grad_norm": 16.954017639160156,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 3.9415,
      "step": 50
    },
    {
      "epoch": 4.564705882352941,
      "eval_loss": 4.784646511077881,
      "eval_runtime": 0.6453,
      "eval_samples_per_second": 15.497,
      "eval_steps_per_second": 15.497,
      "step": 50
    },
    {
      "epoch": 5.470588235294118,
      "grad_norm": 18.607324600219727,
      "learning_rate": 5.9e-06,
      "loss": 4.3359,
      "step": 60
    },
    {
      "epoch": 6.376470588235295,
      "grad_norm": 11.686802864074707,
      "learning_rate": 6.9e-06,
      "loss": 4.1427,
      "step": 70
    },
    {
      "epoch": 7.2823529411764705,
      "grad_norm": 13.75390625,
      "learning_rate": 7.9e-06,
      "loss": 3.7839,
      "step": 80
    },
    {
      "epoch": 8.188235294117646,
      "grad_norm": 12.081093788146973,
      "learning_rate": 8.900000000000001e-06,
      "loss": 3.94,
      "step": 90
    },
    {
      "epoch": 9.094117647058823,
      "grad_norm": 14.128493309020996,
      "learning_rate": 9.9e-06,
      "loss": 3.5581,
      "step": 100
    },
    {
      "epoch": 9.094117647058823,
      "eval_loss": 4.216272830963135,
      "eval_runtime": 0.5662,
      "eval_samples_per_second": 17.662,
      "eval_steps_per_second": 17.662,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 165,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 434550193717248.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}