Hugging Face's logo

mlfoundations-dev
/
stackoverflow_10000tasks_0p

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
stackoverflow_10000tasks_0p
File size: 2,977 Bytes 
a326ace
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
126
127
128
129
130
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 8.059077118463017,
      "learning_rate": 5e-06,
      "loss": 0.732,
      "step": 10
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.4614798499656616,
      "learning_rate": 5e-06,
      "loss": 0.6327,
      "step": 20
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 2.08216893424911,
      "learning_rate": 5e-06,
      "loss": 0.5881,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5583714842796326,
      "eval_runtime": 22.4257,
      "eval_samples_per_second": 39.642,
      "eval_steps_per_second": 0.624,
      "step": 33
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 1.5369606421179118,
      "learning_rate": 5e-06,
      "loss": 0.5367,
      "step": 40
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 1.208061629541289,
      "learning_rate": 5e-06,
      "loss": 0.5128,
      "step": 50
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.1652875666383131,
      "learning_rate": 5e-06,
      "loss": 0.4975,
      "step": 60
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5151528120040894,
      "eval_runtime": 22.6124,
      "eval_samples_per_second": 39.315,
      "eval_steps_per_second": 0.619,
      "step": 66
    },
    {
      "epoch": 2.121212121212121,
      "grad_norm": 1.405112627235947,
      "learning_rate": 5e-06,
      "loss": 0.4743,
      "step": 70
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 1.0655283861506202,
      "learning_rate": 5e-06,
      "loss": 0.4348,
      "step": 80
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 1.1549525346676852,
      "learning_rate": 5e-06,
      "loss": 0.4332,
      "step": 90
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5040238499641418,
      "eval_runtime": 21.7197,
      "eval_samples_per_second": 40.931,
      "eval_steps_per_second": 0.645,
      "step": 99
    },
    {
      "epoch": 3.0,
      "step": 99,
      "total_flos": 165619307642880.0,
      "train_loss": 0.5283013642436326,
      "train_runtime": 3529.0044,
      "train_samples_per_second": 14.355,
      "train_steps_per_second": 0.028
    }
  ],
  "logging_steps": 10,
  "max_steps": 99,
  "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": 165619307642880.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}