Hugging Face's logo

mlfoundations-dev
/
evol_tt_1s

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
evol_tt_1s
File size: 2,895 Bytes
aa9b0d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9871244635193133,
  "eval_steps": 500,
  "global_step": 87,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.34334763948497854,
      "grad_norm": 1.8007573016175122,
      "learning_rate": 5e-06,
      "loss": 1.2432,
      "step": 10
    },
    {
      "epoch": 0.6866952789699571,
      "grad_norm": 1.542700646142592,
      "learning_rate": 5e-06,
      "loss": 1.1372,
      "step": 20
    },
    {
      "epoch": 0.9957081545064378,
      "eval_loss": 1.0878669023513794,
      "eval_runtime": 32.8832,
      "eval_samples_per_second": 23.842,
      "eval_steps_per_second": 0.395,
      "step": 29
    },
    {
      "epoch": 1.0300429184549356,
      "grad_norm": 2.765314152692575,
      "learning_rate": 5e-06,
      "loss": 1.1935,
      "step": 30
    },
    {
      "epoch": 1.3733905579399142,
      "grad_norm": 0.8946628026156727,
      "learning_rate": 5e-06,
      "loss": 1.0502,
      "step": 40
    },
    {
      "epoch": 1.7167381974248928,
      "grad_norm": 0.7633278799134907,
      "learning_rate": 5e-06,
      "loss": 1.0329,
      "step": 50
    },
    {
      "epoch": 1.9914163090128756,
      "eval_loss": 1.0472540855407715,
      "eval_runtime": 33.0231,
      "eval_samples_per_second": 23.741,
      "eval_steps_per_second": 0.394,
      "step": 58
    },
    {
      "epoch": 2.060085836909871,
      "grad_norm": 0.8772200864505999,
      "learning_rate": 5e-06,
      "loss": 1.0996,
      "step": 60
    },
    {
      "epoch": 2.40343347639485,
      "grad_norm": 0.7789437536890554,
      "learning_rate": 5e-06,
      "loss": 0.964,
      "step": 70
    },
    {
      "epoch": 2.7467811158798283,
      "grad_norm": 0.9813046326799254,
      "learning_rate": 5e-06,
      "loss": 0.9598,
      "step": 80
    },
    {
      "epoch": 2.9871244635193133,
      "eval_loss": 1.036589503288269,
      "eval_runtime": 31.9958,
      "eval_samples_per_second": 24.503,
      "eval_steps_per_second": 0.406,
      "step": 87
    },
    {
      "epoch": 2.9871244635193133,
      "step": 87,
      "total_flos": 145518860697600.0,
      "train_loss": 1.0745980438144727,
      "train_runtime": 5447.9996,
      "train_samples_per_second": 8.198,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 10,
  "max_steps": 87,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 145518860697600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}