Hugging Face's logo

emdemor
/
question-generator-v2

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
question-generator-v2
File size: 4,256 Bytes 
65774c2
 
 
764c2d2
65774c2
764c2d2
65774c2
 
 
6306ca9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c8b6213
 
 
 
 
 
 
 
 
 
 
 
 
 
 
667756d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
be26ff5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4268b5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f8f02e5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7854460
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ad9e6aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
764c2d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6306ca9
 
65774c2
f98de7e
65774c2
 
 
 
 
 
 
 
 
6306ca9
65774c2
 
 
 
 
764c2d2
65774c2
 
 
 
 
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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9671179883945842,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09671179883945841,
      "grad_norm": 0.035103704780340195,
      "learning_rate": 0.00016025641025641028,
      "loss": 1.0483,
      "step": 50
    },
    {
      "epoch": 0.09671179883945841,
      "eval_loss": 0.9260319471359253,
      "eval_runtime": 60.9012,
      "eval_samples_per_second": 1.642,
      "eval_steps_per_second": 0.213,
      "step": 50
    },
    {
      "epoch": 0.19342359767891681,
      "grad_norm": 0.030684856697916985,
      "learning_rate": 0.00032051282051282057,
      "loss": 0.8577,
      "step": 100
    },
    {
      "epoch": 0.19342359767891681,
      "eval_loss": 0.820220410823822,
      "eval_runtime": 56.5241,
      "eval_samples_per_second": 1.769,
      "eval_steps_per_second": 0.23,
      "step": 100
    },
    {
      "epoch": 0.2901353965183752,
      "grad_norm": 0.02802114002406597,
      "learning_rate": 0.0004807692307692308,
      "loss": 0.7996,
      "step": 150
    },
    {
      "epoch": 0.2901353965183752,
      "eval_loss": 0.7894760370254517,
      "eval_runtime": 56.6018,
      "eval_samples_per_second": 1.767,
      "eval_steps_per_second": 0.23,
      "step": 150
    },
    {
      "epoch": 0.38684719535783363,
      "grad_norm": 0.03189089894294739,
      "learning_rate": 0.0004842293906810036,
      "loss": 0.7802,
      "step": 200
    },
    {
      "epoch": 0.38684719535783363,
      "eval_loss": 0.7783958315849304,
      "eval_runtime": 56.5799,
      "eval_samples_per_second": 1.767,
      "eval_steps_per_second": 0.23,
      "step": 200
    },
    {
      "epoch": 0.4835589941972921,
      "grad_norm": 0.03580320626497269,
      "learning_rate": 0.00046630824372759856,
      "loss": 0.7671,
      "step": 250
    },
    {
      "epoch": 0.4835589941972921,
      "eval_loss": 0.7721498012542725,
      "eval_runtime": 57.9466,
      "eval_samples_per_second": 1.726,
      "eval_steps_per_second": 0.224,
      "step": 250
    },
    {
      "epoch": 0.5802707930367504,
      "grad_norm": 0.034203894436359406,
      "learning_rate": 0.00044838709677419355,
      "loss": 0.761,
      "step": 300
    },
    {
      "epoch": 0.5802707930367504,
      "eval_loss": 0.7687731385231018,
      "eval_runtime": 60.6867,
      "eval_samples_per_second": 1.648,
      "eval_steps_per_second": 0.214,
      "step": 300
    },
    {
      "epoch": 0.6769825918762089,
      "grad_norm": 0.03307868540287018,
      "learning_rate": 0.00043046594982078853,
      "loss": 0.7587,
      "step": 350
    },
    {
      "epoch": 0.6769825918762089,
      "eval_loss": 0.766252338886261,
      "eval_runtime": 56.5991,
      "eval_samples_per_second": 1.767,
      "eval_steps_per_second": 0.23,
      "step": 350
    },
    {
      "epoch": 0.7736943907156673,
      "grad_norm": 0.03772694244980812,
      "learning_rate": 0.0004125448028673835,
      "loss": 0.7529,
      "step": 400
    },
    {
      "epoch": 0.7736943907156673,
      "eval_loss": 0.7637045383453369,
      "eval_runtime": 56.5561,
      "eval_samples_per_second": 1.768,
      "eval_steps_per_second": 0.23,
      "step": 400
    },
    {
      "epoch": 0.8704061895551257,
      "grad_norm": 0.04153395816683769,
      "learning_rate": 0.00039462365591397855,
      "loss": 0.7562,
      "step": 450
    },
    {
      "epoch": 0.8704061895551257,
      "eval_loss": 0.7616338133811951,
      "eval_runtime": 56.6718,
      "eval_samples_per_second": 1.765,
      "eval_steps_per_second": 0.229,
      "step": 450
    }
  ],
  "logging_steps": 50,
  "max_steps": 1551,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.844805825019904e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}