File size: 4,970 Bytes
e19f367
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_metric": 0.5339233038348082,
  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/canine/canine-base-finetuned-masakhaner-kin/checkpoint-1000",
  "epoch": 29.850746268656717,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.99,
      "eval_accuracy_score": 0.8626628725475513,
      "eval_f1": 0.2977635782747604,
      "eval_loss": 0.40653204917907715,
      "eval_precision": 0.24578059071729957,
      "eval_recall": 0.37763371150729336,
      "eval_runtime": 2.3533,
      "eval_samples_per_second": 128.333,
      "eval_steps_per_second": 16.148,
      "step": 200
    },
    {
      "epoch": 5.97,
      "eval_accuracy_score": 0.8854275872397783,
      "eval_f1": 0.3580729166666667,
      "eval_loss": 0.36062297224998474,
      "eval_precision": 0.2992383025027203,
      "eval_recall": 0.44570502431118314,
      "eval_runtime": 2.3498,
      "eval_samples_per_second": 128.522,
      "eval_steps_per_second": 16.172,
      "step": 400
    },
    {
      "epoch": 7.46,
      "learning_rate": 4.865771812080537e-05,
      "loss": 0.3324,
      "step": 500
    },
    {
      "epoch": 8.96,
      "eval_accuracy_score": 0.902201587539314,
      "eval_f1": 0.4444444444444445,
      "eval_loss": 0.3250875771045685,
      "eval_precision": 0.40052015604681407,
      "eval_recall": 0.4991896272285251,
      "eval_runtime": 2.3578,
      "eval_samples_per_second": 128.086,
      "eval_steps_per_second": 16.117,
      "step": 600
    },
    {
      "epoch": 11.94,
      "eval_accuracy_score": 0.9062453197543807,
      "eval_f1": 0.44697508896797156,
      "eval_loss": 0.35800644755363464,
      "eval_precision": 0.39847715736040606,
      "eval_recall": 0.5089141004862237,
      "eval_runtime": 2.3569,
      "eval_samples_per_second": 128.132,
      "eval_steps_per_second": 16.123,
      "step": 800
    },
    {
      "epoch": 14.93,
      "learning_rate": 4.697986577181208e-05,
      "loss": 0.0559,
      "step": 1000
    },
    {
      "epoch": 14.93,
      "eval_accuracy_score": 0.9155309270630523,
      "eval_f1": 0.5339233038348082,
      "eval_loss": 0.3548363149166107,
      "eval_precision": 0.489851150202977,
      "eval_recall": 0.586709886547812,
      "eval_runtime": 2.3472,
      "eval_samples_per_second": 128.664,
      "eval_steps_per_second": 16.19,
      "step": 1000
    },
    {
      "epoch": 17.91,
      "eval_accuracy_score": 0.9156806949228695,
      "eval_f1": 0.5113221329437545,
      "eval_loss": 0.39484161138534546,
      "eval_precision": 0.4654255319148936,
      "eval_recall": 0.5672609400324149,
      "eval_runtime": 2.3511,
      "eval_samples_per_second": 128.453,
      "eval_steps_per_second": 16.163,
      "step": 1200
    },
    {
      "epoch": 20.9,
      "eval_accuracy_score": 0.9123858020068893,
      "eval_f1": 0.4756446991404012,
      "eval_loss": 0.4212295711040497,
      "eval_precision": 0.42618741976893454,
      "eval_recall": 0.5380875202593193,
      "eval_runtime": 2.351,
      "eval_samples_per_second": 128.457,
      "eval_steps_per_second": 16.163,
      "step": 1400
    },
    {
      "epoch": 22.39,
      "learning_rate": 4.530201342281879e-05,
      "loss": 0.0133,
      "step": 1500
    },
    {
      "epoch": 23.88,
      "eval_accuracy_score": 0.9149318556237831,
      "eval_f1": 0.5033308660251665,
      "eval_loss": 0.42608439922332764,
      "eval_precision": 0.46321525885558584,
      "eval_recall": 0.5510534846029174,
      "eval_runtime": 2.3525,
      "eval_samples_per_second": 128.373,
      "eval_steps_per_second": 16.153,
      "step": 1600
    },
    {
      "epoch": 26.87,
      "eval_accuracy_score": 0.9161299985023214,
      "eval_f1": 0.53003003003003,
      "eval_loss": 0.4479231536388397,
      "eval_precision": 0.4937062937062937,
      "eval_recall": 0.5721231766612642,
      "eval_runtime": 2.3519,
      "eval_samples_per_second": 128.409,
      "eval_steps_per_second": 16.157,
      "step": 1800
    },
    {
      "epoch": 29.85,
      "learning_rate": 4.36241610738255e-05,
      "loss": 0.0058,
      "step": 2000
    },
    {
      "epoch": 29.85,
      "eval_accuracy_score": 0.918076980679946,
      "eval_f1": 0.5291887793783169,
      "eval_loss": 0.4661569595336914,
      "eval_precision": 0.49715099715099714,
      "eval_recall": 0.5656401944894651,
      "eval_runtime": 2.349,
      "eval_samples_per_second": 128.566,
      "eval_steps_per_second": 16.177,
      "step": 2000
    },
    {
      "epoch": 29.85,
      "step": 2000,
      "total_flos": 1.0376509207394304e+16,
      "train_loss": 0.10185246992111206,
      "train_runtime": 987.1722,
      "train_samples_per_second": 486.237,
      "train_steps_per_second": 15.195
    }
  ],
  "max_steps": 15000,
  "num_train_epochs": 224,
  "total_flos": 1.0376509207394304e+16,
  "trial_name": null,
  "trial_params": null
}