File size: 4,341 Bytes
aa52d62
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.4302303791046143,
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l59-l/checkpoint-4500",
  "epoch": 0.8290346352247605,
  "eval_steps": 500,
  "global_step": 4500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09211495946941783,
      "grad_norm": 20.952665328979492,
      "learning_rate": 4.884856300663228e-09,
      "loss": 0.3952,
      "step": 500
    },
    {
      "epoch": 0.09211495946941783,
      "eval_loss": 1.4940427541732788,
      "eval_runtime": 73.9282,
      "eval_samples_per_second": 16.327,
      "eval_steps_per_second": 2.043,
      "step": 500
    },
    {
      "epoch": 0.18422991893883567,
      "grad_norm": 59.28666687011719,
      "learning_rate": 4.769712601326456e-09,
      "loss": 0.4562,
      "step": 1000
    },
    {
      "epoch": 0.18422991893883567,
      "eval_loss": 1.4853259325027466,
      "eval_runtime": 74.6533,
      "eval_samples_per_second": 16.168,
      "eval_steps_per_second": 2.023,
      "step": 1000
    },
    {
      "epoch": 0.2763448784082535,
      "grad_norm": 1.179814338684082,
      "learning_rate": 4.654568901989683e-09,
      "loss": 0.5131,
      "step": 1500
    },
    {
      "epoch": 0.2763448784082535,
      "eval_loss": 1.4757832288742065,
      "eval_runtime": 76.2866,
      "eval_samples_per_second": 15.822,
      "eval_steps_per_second": 1.979,
      "step": 1500
    },
    {
      "epoch": 0.36845983787767134,
      "grad_norm": 0.900991678237915,
      "learning_rate": 4.5394252026529105e-09,
      "loss": 0.4481,
      "step": 2000
    },
    {
      "epoch": 0.36845983787767134,
      "eval_loss": 1.4675536155700684,
      "eval_runtime": 75.9348,
      "eval_samples_per_second": 15.895,
      "eval_steps_per_second": 1.989,
      "step": 2000
    },
    {
      "epoch": 0.46057479734708917,
      "grad_norm": 346.93853759765625,
      "learning_rate": 4.424281503316139e-09,
      "loss": 0.4839,
      "step": 2500
    },
    {
      "epoch": 0.46057479734708917,
      "eval_loss": 1.4585391283035278,
      "eval_runtime": 76.7708,
      "eval_samples_per_second": 15.722,
      "eval_steps_per_second": 1.967,
      "step": 2500
    },
    {
      "epoch": 0.552689756816507,
      "grad_norm": 318.47515869140625,
      "learning_rate": 4.3091378039793666e-09,
      "loss": 0.4377,
      "step": 3000
    },
    {
      "epoch": 0.552689756816507,
      "eval_loss": 1.4507631063461304,
      "eval_runtime": 76.5424,
      "eval_samples_per_second": 15.769,
      "eval_steps_per_second": 1.973,
      "step": 3000
    },
    {
      "epoch": 0.6448047162859248,
      "grad_norm": 112.41814422607422,
      "learning_rate": 4.193994104642594e-09,
      "loss": 0.4231,
      "step": 3500
    },
    {
      "epoch": 0.6448047162859248,
      "eval_loss": 1.4432125091552734,
      "eval_runtime": 76.4812,
      "eval_samples_per_second": 15.782,
      "eval_steps_per_second": 1.974,
      "step": 3500
    },
    {
      "epoch": 0.7369196757553427,
      "grad_norm": 83.51781463623047,
      "learning_rate": 4.078850405305822e-09,
      "loss": 0.4369,
      "step": 4000
    },
    {
      "epoch": 0.7369196757553427,
      "eval_loss": 1.4365661144256592,
      "eval_runtime": 76.4405,
      "eval_samples_per_second": 15.79,
      "eval_steps_per_second": 1.975,
      "step": 4000
    },
    {
      "epoch": 0.8290346352247605,
      "grad_norm": 460.5648498535156,
      "learning_rate": 3.963706705969049e-09,
      "loss": 0.4082,
      "step": 4500
    },
    {
      "epoch": 0.8290346352247605,
      "eval_loss": 1.4302303791046143,
      "eval_runtime": 75.042,
      "eval_samples_per_second": 16.084,
      "eval_steps_per_second": 2.012,
      "step": 4500
    }
  ],
  "logging_steps": 500,
  "max_steps": 21712,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1619632097372520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}