Hugging Face's logo

AlekseyKorshuk
/
6.7b-dalio-book-handwritten-io-constant-1e-6

Text Generation
Transformers
PyTorch
opt
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
6.7b-dalio-book-handwritten-io-constant-1e-6
File size: 3,723 Bytes 
b27f3cc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 56,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 1e-06,
      "loss": 2.5647,
      "step": 1
    },
    {
      "epoch": 0.11,
      "learning_rate": 1e-06,
      "loss": 2.6396,
      "step": 6
    },
    {
      "epoch": 0.11,
      "eval_accuracy": 0.29888098278902875,
      "eval_loss": 2.50390625,
      "eval_runtime": 65.6756,
      "eval_samples_per_second": 4.796,
      "eval_steps_per_second": 0.609,
      "step": 6
    },
    {
      "epoch": 0.21,
      "learning_rate": 1e-06,
      "loss": 2.5754,
      "step": 12
    },
    {
      "epoch": 0.21,
      "eval_accuracy": 0.29990877577084474,
      "eval_loss": 2.490234375,
      "eval_runtime": 66.3232,
      "eval_samples_per_second": 4.749,
      "eval_steps_per_second": 0.603,
      "step": 12
    },
    {
      "epoch": 0.32,
      "learning_rate": 1e-06,
      "loss": 2.5859,
      "step": 18
    },
    {
      "epoch": 0.32,
      "eval_accuracy": 0.3017940765067202,
      "eval_loss": 2.46484375,
      "eval_runtime": 66.3622,
      "eval_samples_per_second": 4.747,
      "eval_steps_per_second": 0.603,
      "step": 18
    },
    {
      "epoch": 0.43,
      "learning_rate": 1e-06,
      "loss": 2.5432,
      "step": 24
    },
    {
      "epoch": 0.43,
      "eval_accuracy": 0.30347868393845406,
      "eval_loss": 2.443359375,
      "eval_runtime": 66.0194,
      "eval_samples_per_second": 4.771,
      "eval_steps_per_second": 0.606,
      "step": 24
    },
    {
      "epoch": 0.54,
      "learning_rate": 1e-06,
      "loss": 2.472,
      "step": 30
    },
    {
      "epoch": 0.54,
      "eval_accuracy": 0.3053031685215593,
      "eval_loss": 2.423828125,
      "eval_runtime": 66.3343,
      "eval_samples_per_second": 4.749,
      "eval_steps_per_second": 0.603,
      "step": 30
    },
    {
      "epoch": 0.64,
      "learning_rate": 1e-06,
      "loss": 2.5184,
      "step": 36
    },
    {
      "epoch": 0.64,
      "eval_accuracy": 0.3064465121936386,
      "eval_loss": 2.408203125,
      "eval_runtime": 66.2869,
      "eval_samples_per_second": 4.752,
      "eval_steps_per_second": 0.603,
      "step": 36
    },
    {
      "epoch": 0.75,
      "learning_rate": 1e-06,
      "loss": 2.4524,
      "step": 42
    },
    {
      "epoch": 0.75,
      "eval_accuracy": 0.30782703886152163,
      "eval_loss": 2.392578125,
      "eval_runtime": 66.3104,
      "eval_samples_per_second": 4.75,
      "eval_steps_per_second": 0.603,
      "step": 42
    },
    {
      "epoch": 0.86,
      "learning_rate": 1e-06,
      "loss": 2.3876,
      "step": 48
    },
    {
      "epoch": 0.86,
      "eval_accuracy": 0.30921364714468164,
      "eval_loss": 2.37890625,
      "eval_runtime": 66.2891,
      "eval_samples_per_second": 4.752,
      "eval_steps_per_second": 0.603,
      "step": 48
    },
    {
      "epoch": 0.96,
      "learning_rate": 1e-06,
      "loss": 2.4456,
      "step": 54
    },
    {
      "epoch": 0.96,
      "eval_accuracy": 0.3103083378945448,
      "eval_loss": 2.36328125,
      "eval_runtime": 66.3214,
      "eval_samples_per_second": 4.75,
      "eval_steps_per_second": 0.603,
      "step": 54
    },
    {
      "epoch": 1.0,
      "step": 56,
      "total_flos": 3701894676480.0,
      "train_loss": 2.499117170061384,
      "train_runtime": 11859.1153,
      "train_samples_per_second": 0.037,
      "train_steps_per_second": 0.005
    }
  ],
  "max_steps": 56,
  "num_train_epochs": 1,
  "total_flos": 3701894676480.0,
  "trial_name": null,
  "trial_params": null
}