File size: 5,140 Bytes
5c347ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
199
200
201
202
203
204
205
206
207
208
{
  "best_metric": 0.01156603079289198,
  "best_model_checkpoint": "verbnet_train_derived/checkpoint-2899875",
  "epoch": 11.0,
  "eval_steps": 500,
  "global_step": 2899875,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.0011935352813452482,
      "learning_rate": 1.9600150213371268e-05,
      "loss": 0.237,
      "step": 263625
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.0812821313738823,
      "eval_runtime": 657.1184,
      "eval_samples_per_second": 168.919,
      "eval_steps_per_second": 21.115,
      "step": 263625
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0008472450426779687,
      "learning_rate": 1.9200294357515412e-05,
      "loss": 0.0675,
      "step": 527250
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.04395299404859543,
      "eval_runtime": 635.1223,
      "eval_samples_per_second": 174.769,
      "eval_steps_per_second": 21.846,
      "step": 527250
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.0005161144654266536,
      "learning_rate": 1.8800440018966338e-05,
      "loss": 0.0402,
      "step": 790875
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.03021380864083767,
      "eval_runtime": 631.9338,
      "eval_samples_per_second": 175.651,
      "eval_steps_per_second": 21.956,
      "step": 790875
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3789523109153379e-05,
      "learning_rate": 1.8400591749644382e-05,
      "loss": 0.0269,
      "step": 1054500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.02329804003238678,
      "eval_runtime": 635.8959,
      "eval_samples_per_second": 174.557,
      "eval_steps_per_second": 21.82,
      "step": 1054500
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.8203951185569167e-05,
      "learning_rate": 1.8000737411095308e-05,
      "loss": 0.019,
      "step": 1318125
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.01786634884774685,
      "eval_runtime": 635.4082,
      "eval_samples_per_second": 174.691,
      "eval_steps_per_second": 21.836,
      "step": 1318125
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.00018590281251817942,
      "learning_rate": 1.7600884589853015e-05,
      "loss": 0.0144,
      "step": 1581750
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.016473863273859024,
      "eval_runtime": 633.0357,
      "eval_samples_per_second": 175.346,
      "eval_steps_per_second": 21.918,
      "step": 1581750
    },
    {
      "epoch": 7.0,
      "grad_norm": 4.66911842522677e-06,
      "learning_rate": 1.7201034803224278e-05,
      "loss": 0.0115,
      "step": 1845375
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.015895597636699677,
      "eval_runtime": 641.0505,
      "eval_samples_per_second": 173.153,
      "eval_steps_per_second": 21.644,
      "step": 1845375
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.0007661374402232468,
      "learning_rate": 1.6801183499288766e-05,
      "loss": 0.0093,
      "step": 2109000
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.014273108914494514,
      "eval_runtime": 643.6593,
      "eval_samples_per_second": 172.451,
      "eval_steps_per_second": 21.556,
      "step": 2109000
    },
    {
      "epoch": 9.0,
      "grad_norm": 8.322523353854194e-05,
      "learning_rate": 1.640133219535325e-05,
      "loss": 0.0078,
      "step": 2372625
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.014644059352576733,
      "eval_runtime": 650.6057,
      "eval_samples_per_second": 170.61,
      "eval_steps_per_second": 21.326,
      "step": 2372625
    },
    {
      "epoch": 10.0,
      "grad_norm": 5.2284158300608397e-05,
      "learning_rate": 1.6001473304883833e-05,
      "loss": 0.0067,
      "step": 2636250
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.012359824031591415,
      "eval_runtime": 641.3289,
      "eval_samples_per_second": 173.078,
      "eval_steps_per_second": 21.635,
      "step": 2636250
    },
    {
      "epoch": 11.0,
      "grad_norm": 3.8969083107076585e-06,
      "learning_rate": 1.5601615931721196e-05,
      "loss": 0.0058,
      "step": 2899875
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.01156603079289198,
      "eval_runtime": 652.3223,
      "eval_samples_per_second": 170.161,
      "eval_steps_per_second": 21.27,
      "step": 2899875
    }
  ],
  "logging_steps": 500,
  "max_steps": 13181250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.601008241480028e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}