File size: 4,268 Bytes
86bb489
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
170
171
{
  "best_metric": 0.926605504587156,
  "best_model_checkpoint": "electra-distilled-sst\\run-6\\checkpoint-2108",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 4743,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 17.92670440673828,
      "learning_rate": 2.010330074098376e-05,
      "loss": 1.6952,
      "step": 527
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8910550458715596,
      "eval_loss": 0.9234904050827026,
      "eval_runtime": 1.446,
      "eval_samples_per_second": 603.052,
      "eval_steps_per_second": 4.841,
      "step": 527
    },
    {
      "epoch": 2.0,
      "grad_norm": 43.87211990356445,
      "learning_rate": 1.759575125325375e-05,
      "loss": 0.8731,
      "step": 1054
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9059633027522935,
      "eval_loss": 0.770187258720398,
      "eval_runtime": 1.4489,
      "eval_samples_per_second": 601.851,
      "eval_steps_per_second": 4.831,
      "step": 1054
    },
    {
      "epoch": 3.0,
      "grad_norm": 13.310898780822754,
      "learning_rate": 1.508343456117444e-05,
      "loss": 0.6622,
      "step": 1581
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9139908256880734,
      "eval_loss": 0.7737818956375122,
      "eval_runtime": 1.4497,
      "eval_samples_per_second": 601.516,
      "eval_steps_per_second": 4.829,
      "step": 1581
    },
    {
      "epoch": 4.0,
      "grad_norm": 12.57313060760498,
      "learning_rate": 1.2571117869095134e-05,
      "loss": 0.5443,
      "step": 2108
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.926605504587156,
      "eval_loss": 0.7234447598457336,
      "eval_runtime": 1.451,
      "eval_samples_per_second": 600.977,
      "eval_steps_per_second": 4.824,
      "step": 2108
    },
    {
      "epoch": 5.0,
      "grad_norm": 28.64960289001465,
      "learning_rate": 1.0058801177015824e-05,
      "loss": 0.48,
      "step": 2635
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9174311926605505,
      "eval_loss": 0.7743226289749146,
      "eval_runtime": 1.4478,
      "eval_samples_per_second": 602.308,
      "eval_steps_per_second": 4.835,
      "step": 2635
    },
    {
      "epoch": 6.0,
      "grad_norm": 10.863966941833496,
      "learning_rate": 7.546484484936517e-06,
      "loss": 0.4283,
      "step": 3162
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9220183486238532,
      "eval_loss": 0.7562010288238525,
      "eval_runtime": 1.4492,
      "eval_samples_per_second": 601.691,
      "eval_steps_per_second": 4.83,
      "step": 3162
    },
    {
      "epoch": 7.0,
      "grad_norm": 25.16184425354004,
      "learning_rate": 5.038934997206505e-06,
      "loss": 0.3886,
      "step": 3689
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9197247706422018,
      "eval_loss": 0.7708072662353516,
      "eval_runtime": 1.4413,
      "eval_samples_per_second": 604.999,
      "eval_steps_per_second": 4.857,
      "step": 3689
    },
    {
      "epoch": 8.0,
      "grad_norm": 19.518695831298828,
      "learning_rate": 2.5266183051271976e-06,
      "loss": 0.373,
      "step": 4216
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9185779816513762,
      "eval_loss": 0.8256669640541077,
      "eval_runtime": 1.4454,
      "eval_samples_per_second": 603.301,
      "eval_steps_per_second": 4.843,
      "step": 4216
    },
    {
      "epoch": 9.0,
      "grad_norm": 73.0574951171875,
      "learning_rate": 1.4301613047889797e-08,
      "loss": 0.3533,
      "step": 4743
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9162844036697247,
      "eval_loss": 0.8148481845855713,
      "eval_runtime": 1.4457,
      "eval_samples_per_second": 603.149,
      "eval_steps_per_second": 4.842,
      "step": 4743
    }
  ],
  "logging_steps": 500,
  "max_steps": 4743,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 500,
  "total_flos": 1684816747339368.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.7277023096419001,
    "learning_rate": 2.261085022871377e-05,
    "num_train_epochs": 9,
    "temperature": 29
  }
}