Hugging Face's logo

mikhail-panzo
/
zlm_b128_le4_s4000

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
zlm_b128_le4_s4000
File size: 2,699 Bytes 
1f1c330
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 0.4566049873828888,
  "best_model_checkpoint": "mikhail-panzo/zlm_b128_le4_s4000/checkpoint-500",
  "epoch": 0.837696335078534,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08376963350785341,
      "grad_norm": 2.9717624187469482,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 1.0424,
      "step": 50
    },
    {
      "epoch": 0.16753926701570682,
      "grad_norm": 2.9720630645751953,
      "learning_rate": 4.950000000000001e-06,
      "loss": 0.8474,
      "step": 100
    },
    {
      "epoch": 0.2513089005235602,
      "grad_norm": 2.445929765701294,
      "learning_rate": 7.45e-06,
      "loss": 0.7336,
      "step": 150
    },
    {
      "epoch": 0.33507853403141363,
      "grad_norm": 5.502955913543701,
      "learning_rate": 9.950000000000001e-06,
      "loss": 0.6492,
      "step": 200
    },
    {
      "epoch": 0.418848167539267,
      "grad_norm": 2.3356130123138428,
      "learning_rate": 1.2450000000000001e-05,
      "loss": 0.6133,
      "step": 250
    },
    {
      "epoch": 0.5026178010471204,
      "grad_norm": 1.937270164489746,
      "learning_rate": 1.4950000000000001e-05,
      "loss": 0.5889,
      "step": 300
    },
    {
      "epoch": 0.5863874345549738,
      "grad_norm": 2.392244338989258,
      "learning_rate": 1.745e-05,
      "loss": 0.5694,
      "step": 350
    },
    {
      "epoch": 0.6701570680628273,
      "grad_norm": 7.3209919929504395,
      "learning_rate": 1.995e-05,
      "loss": 0.5477,
      "step": 400
    },
    {
      "epoch": 0.7539267015706806,
      "grad_norm": 3.415917158126831,
      "learning_rate": 2.245e-05,
      "loss": 0.5329,
      "step": 450
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": 3.0256705284118652,
      "learning_rate": 2.495e-05,
      "loss": 0.5173,
      "step": 500
    },
    {
      "epoch": 0.837696335078534,
      "eval_loss": 0.4566049873828888,
      "eval_runtime": 261.3511,
      "eval_samples_per_second": 32.481,
      "eval_steps_per_second": 4.063,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8963407491426432.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}