Hugging Face's logo

mlfoundations-dev
/
stackexchange_mathematica

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
stackexchange_mathematica
File size: 3,278 Bytes 
1b8db2d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
145
146
147
148
149
150
151
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 10.623923460343729,
      "learning_rate": 5e-06,
      "loss": 0.9372,
      "step": 10
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.793037918373031,
      "learning_rate": 5e-06,
      "loss": 0.8283,
      "step": 20
    },
    {
      "epoch": 0.75,
      "grad_norm": 3.7845451356616455,
      "learning_rate": 5e-06,
      "loss": 0.7811,
      "step": 30
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9164583944436338,
      "learning_rate": 5e-06,
      "loss": 0.7595,
      "step": 40
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7516233921051025,
      "eval_runtime": 27.7388,
      "eval_samples_per_second": 38.862,
      "eval_steps_per_second": 0.613,
      "step": 40
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.0460327419425848,
      "learning_rate": 5e-06,
      "loss": 0.7169,
      "step": 50
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.134555380206765,
      "learning_rate": 5e-06,
      "loss": 0.7105,
      "step": 60
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.834786450946659,
      "learning_rate": 5e-06,
      "loss": 0.6992,
      "step": 70
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8259020499128051,
      "learning_rate": 5e-06,
      "loss": 0.6946,
      "step": 80
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.7181093096733093,
      "eval_runtime": 27.9425,
      "eval_samples_per_second": 38.579,
      "eval_steps_per_second": 0.608,
      "step": 80
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.6752448107919039,
      "learning_rate": 5e-06,
      "loss": 0.651,
      "step": 90
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.763737793787202,
      "learning_rate": 5e-06,
      "loss": 0.6462,
      "step": 100
    },
    {
      "epoch": 2.75,
      "grad_norm": 1.0609101015318403,
      "learning_rate": 5e-06,
      "loss": 0.6444,
      "step": 110
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8435640146675477,
      "learning_rate": 5e-06,
      "loss": 0.6445,
      "step": 120
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7114487886428833,
      "eval_runtime": 26.8405,
      "eval_samples_per_second": 40.163,
      "eval_steps_per_second": 0.633,
      "step": 120
    },
    {
      "epoch": 3.0,
      "step": 120,
      "total_flos": 200795089797120.0,
      "train_loss": 0.7261142373085022,
      "train_runtime": 4198.995,
      "train_samples_per_second": 14.629,
      "train_steps_per_second": 0.029
    }
  ],
  "logging_steps": 10,
  "max_steps": 120,
  "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": 200795089797120.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}