Hugging Face's logo

mlfoundations-dev
/
sky-t1-original-llama-instruct

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
sky-t1-original-llama-instruct
File size: 2,941 Bytes
0a7e1c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.1328805578866286,
      "learning_rate": 5e-06,
      "loss": 0.6261,
      "step": 10
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.5655437748332994,
      "learning_rate": 5e-06,
      "loss": 0.5229,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4255185947425879,
      "learning_rate": 5e-06,
      "loss": 0.4914,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.48239657282829285,
      "eval_runtime": 11.6513,
      "eval_samples_per_second": 69.349,
      "eval_steps_per_second": 1.116,
      "step": 30
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.4517651743600907,
      "learning_rate": 5e-06,
      "loss": 0.4487,
      "step": 40
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.3649131361498104,
      "learning_rate": 5e-06,
      "loss": 0.438,
      "step": 50
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3830225718161711,
      "learning_rate": 5e-06,
      "loss": 0.4301,
      "step": 60
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.45320141315460205,
      "eval_runtime": 11.8663,
      "eval_samples_per_second": 68.092,
      "eval_steps_per_second": 1.096,
      "step": 60
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.47711530562220955,
      "learning_rate": 5e-06,
      "loss": 0.3922,
      "step": 70
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.47041140445746077,
      "learning_rate": 5e-06,
      "loss": 0.3841,
      "step": 80
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.43944682743936286,
      "learning_rate": 5e-06,
      "loss": 0.3817,
      "step": 90
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.4424304664134979,
      "eval_runtime": 11.6409,
      "eval_samples_per_second": 69.41,
      "eval_steps_per_second": 1.117,
      "step": 90
    },
    {
      "epoch": 3.0,
      "step": 90,
      "total_flos": 150543972433920.0,
      "train_loss": 0.4572353945838081,
      "train_runtime": 2587.8961,
      "train_samples_per_second": 17.787,
      "train_steps_per_second": 0.035
    }
  ],
  "logging_steps": 10,
  "max_steps": 90,
  "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": 150543972433920.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}