Hugging Face's logo

mlfoundations-dev
/
stackexchange_crypto

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
stackexchange_crypto
File size: 3,366 Bytes 
ef77539
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9372937293729375,
  "eval_steps": 500,
  "global_step": 111,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.264026402640264,
      "grad_norm": 12.022938086535472,
      "learning_rate": 5e-06,
      "loss": 1.1583,
      "step": 10
    },
    {
      "epoch": 0.528052805280528,
      "grad_norm": 2.088240001039349,
      "learning_rate": 5e-06,
      "loss": 1.0448,
      "step": 20
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.3000719336915976,
      "learning_rate": 5e-06,
      "loss": 0.9949,
      "step": 30
    },
    {
      "epoch": 0.976897689768977,
      "eval_loss": 0.9789440631866455,
      "eval_runtime": 40.3765,
      "eval_samples_per_second": 25.213,
      "eval_steps_per_second": 0.396,
      "step": 37
    },
    {
      "epoch": 1.0594059405940595,
      "grad_norm": 0.9713352191576023,
      "learning_rate": 5e-06,
      "loss": 0.9862,
      "step": 40
    },
    {
      "epoch": 1.3234323432343233,
      "grad_norm": 0.9308222764215573,
      "learning_rate": 5e-06,
      "loss": 0.9269,
      "step": 50
    },
    {
      "epoch": 1.5874587458745875,
      "grad_norm": 0.7459606179464745,
      "learning_rate": 5e-06,
      "loss": 0.9154,
      "step": 60
    },
    {
      "epoch": 1.8514851485148514,
      "grad_norm": 1.2070339110976707,
      "learning_rate": 5e-06,
      "loss": 0.9063,
      "step": 70
    },
    {
      "epoch": 1.9834983498349836,
      "eval_loss": 0.9386385679244995,
      "eval_runtime": 40.383,
      "eval_samples_per_second": 25.209,
      "eval_steps_per_second": 0.396,
      "step": 75
    },
    {
      "epoch": 2.118811881188119,
      "grad_norm": 0.8653617914235142,
      "learning_rate": 5e-06,
      "loss": 0.9088,
      "step": 80
    },
    {
      "epoch": 2.382838283828383,
      "grad_norm": 0.7418041958945455,
      "learning_rate": 5e-06,
      "loss": 0.852,
      "step": 90
    },
    {
      "epoch": 2.6468646864686467,
      "grad_norm": 0.7211883671655479,
      "learning_rate": 5e-06,
      "loss": 0.8509,
      "step": 100
    },
    {
      "epoch": 2.910891089108911,
      "grad_norm": 0.9407139732490507,
      "learning_rate": 5e-06,
      "loss": 0.8472,
      "step": 110
    },
    {
      "epoch": 2.9372937293729375,
      "eval_loss": 0.9289506077766418,
      "eval_runtime": 39.7511,
      "eval_samples_per_second": 25.609,
      "eval_steps_per_second": 0.403,
      "step": 111
    },
    {
      "epoch": 2.9372937293729375,
      "step": 111,
      "total_flos": 185719754588160.0,
      "train_loss": 0.9437385083318831,
      "train_runtime": 6794.3487,
      "train_samples_per_second": 8.537,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 10,
  "max_steps": 111,
  "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": 185719754588160.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}