File size: 4,977 Bytes
17ca29e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
{
  "best_global_step": 1920,
  "best_metric": 0.6441558441558441,
  "best_model_checkpoint": "/content/drive/MyDrive/project/MODELS/Surrogates/RoBERTa_LIAR/checkpoint-1920",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1920,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15625,
      "grad_norm": 1.4061976671218872,
      "learning_rate": 1.485e-05,
      "loss": 0.6982453918457031,
      "step": 100
    },
    {
      "epoch": 0.3125,
      "grad_norm": 2.2753427028656006,
      "learning_rate": 2.985e-05,
      "loss": 0.6896881866455078,
      "step": 200
    },
    {
      "epoch": 0.46875,
      "grad_norm": 6.735152721405029,
      "learning_rate": 2.8741525423728816e-05,
      "loss": 0.683045654296875,
      "step": 300
    },
    {
      "epoch": 0.625,
      "grad_norm": 1.8760987520217896,
      "learning_rate": 2.7470338983050847e-05,
      "loss": 0.6780765533447266,
      "step": 400
    },
    {
      "epoch": 0.78125,
      "grad_norm": 1.938730001449585,
      "learning_rate": 2.6199152542372882e-05,
      "loss": 0.6746772766113281,
      "step": 500
    },
    {
      "epoch": 0.9375,
      "grad_norm": 4.237790584564209,
      "learning_rate": 2.4927966101694917e-05,
      "loss": 0.6706379699707031,
      "step": 600
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6082554517133957,
      "eval_f1": 0.4830421377183967,
      "eval_loss": 0.6857937574386597,
      "eval_runtime": 9.9211,
      "eval_samples_per_second": 129.421,
      "eval_steps_per_second": 8.164,
      "step": 640
    },
    {
      "epoch": 1.09375,
      "grad_norm": 2.4777538776397705,
      "learning_rate": 2.365677966101695e-05,
      "loss": 0.6513714599609375,
      "step": 700
    },
    {
      "epoch": 1.25,
      "grad_norm": 4.130825996398926,
      "learning_rate": 2.2385593220338984e-05,
      "loss": 0.6446173858642578,
      "step": 800
    },
    {
      "epoch": 1.40625,
      "grad_norm": 5.078433513641357,
      "learning_rate": 2.111440677966102e-05,
      "loss": 0.6381737899780273,
      "step": 900
    },
    {
      "epoch": 1.5625,
      "grad_norm": 4.769000053405762,
      "learning_rate": 1.984322033898305e-05,
      "loss": 0.6448619842529297,
      "step": 1000
    },
    {
      "epoch": 1.71875,
      "grad_norm": 6.341429233551025,
      "learning_rate": 1.8572033898305086e-05,
      "loss": 0.6350166702270508,
      "step": 1100
    },
    {
      "epoch": 1.875,
      "grad_norm": 3.228231191635132,
      "learning_rate": 1.730084745762712e-05,
      "loss": 0.6343123626708984,
      "step": 1200
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6479750778816199,
      "eval_f1": 0.5727788279773157,
      "eval_loss": 0.651949405670166,
      "eval_runtime": 10.1237,
      "eval_samples_per_second": 126.832,
      "eval_steps_per_second": 8.001,
      "step": 1280
    },
    {
      "epoch": 2.03125,
      "grad_norm": 10.572697639465332,
      "learning_rate": 1.6029661016949153e-05,
      "loss": 0.6261093521118164,
      "step": 1300
    },
    {
      "epoch": 2.1875,
      "grad_norm": 7.916661739349365,
      "learning_rate": 1.4758474576271186e-05,
      "loss": 0.549117546081543,
      "step": 1400
    },
    {
      "epoch": 2.34375,
      "grad_norm": 17.981098175048828,
      "learning_rate": 1.348728813559322e-05,
      "loss": 0.5534476089477539,
      "step": 1500
    },
    {
      "epoch": 2.5,
      "grad_norm": 6.362517833709717,
      "learning_rate": 1.2216101694915255e-05,
      "loss": 0.5808805465698242,
      "step": 1600
    },
    {
      "epoch": 2.65625,
      "grad_norm": 11.875460624694824,
      "learning_rate": 1.0944915254237288e-05,
      "loss": 0.5447834014892579,
      "step": 1700
    },
    {
      "epoch": 2.8125,
      "grad_norm": 18.079544067382812,
      "learning_rate": 9.673728813559322e-06,
      "loss": 0.542778205871582,
      "step": 1800
    },
    {
      "epoch": 2.96875,
      "grad_norm": 5.842272758483887,
      "learning_rate": 8.402542372881357e-06,
      "loss": 0.5418962860107421,
      "step": 1900
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6799065420560748,
      "eval_f1": 0.6441558441558441,
      "eval_loss": 0.6514966487884521,
      "eval_runtime": 9.8829,
      "eval_samples_per_second": 129.921,
      "eval_steps_per_second": 8.196,
      "step": 1920
    }
  ],
  "logging_steps": 100,
  "max_steps": 2560,
  "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": 2020692905164800.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}