File size: 5,716 Bytes
dc7b6cc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
{
  "best_metric": 0.7038731575012207,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.045625641610585146,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001825025664423406,
      "grad_norm": 1.3225451707839966,
      "learning_rate": 5e-05,
      "loss": 0.97,
      "step": 1
    },
    {
      "epoch": 0.001825025664423406,
      "eval_loss": 2.524681568145752,
      "eval_runtime": 2.6698,
      "eval_samples_per_second": 18.728,
      "eval_steps_per_second": 4.869,
      "step": 1
    },
    {
      "epoch": 0.003650051328846812,
      "grad_norm": 1.6591840982437134,
      "learning_rate": 0.0001,
      "loss": 1.308,
      "step": 2
    },
    {
      "epoch": 0.0054750769932702175,
      "grad_norm": 1.876944899559021,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.4438,
      "step": 3
    },
    {
      "epoch": 0.007300102657693624,
      "grad_norm": 2.3761868476867676,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.353,
      "step": 4
    },
    {
      "epoch": 0.009125128322117029,
      "grad_norm": 2.066288709640503,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.1193,
      "step": 5
    },
    {
      "epoch": 0.010950153986540435,
      "grad_norm": 2.1301584243774414,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.1276,
      "step": 6
    },
    {
      "epoch": 0.012775179650963841,
      "grad_norm": 1.1909555196762085,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.9841,
      "step": 7
    },
    {
      "epoch": 0.014600205315387247,
      "grad_norm": 1.662056565284729,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.9273,
      "step": 8
    },
    {
      "epoch": 0.016425230979810655,
      "grad_norm": 0.961665689945221,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.0642,
      "step": 9
    },
    {
      "epoch": 0.018250256644234058,
      "grad_norm": 0.9523164629936218,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.0873,
      "step": 10
    },
    {
      "epoch": 0.020075282308657464,
      "grad_norm": 1.3972877264022827,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.3219,
      "step": 11
    },
    {
      "epoch": 0.02190030797308087,
      "grad_norm": 0.9584366083145142,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.1643,
      "step": 12
    },
    {
      "epoch": 0.023725333637504276,
      "grad_norm": 1.5735657215118408,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.5538,
      "step": 13
    },
    {
      "epoch": 0.025550359301927682,
      "grad_norm": 1.2523537874221802,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.3921,
      "step": 14
    },
    {
      "epoch": 0.02737538496635109,
      "grad_norm": 0.676099956035614,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.5625,
      "step": 15
    },
    {
      "epoch": 0.029200410630774495,
      "grad_norm": 0.852027952671051,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.7331,
      "step": 16
    },
    {
      "epoch": 0.0310254362951979,
      "grad_norm": 0.8262453675270081,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.8157,
      "step": 17
    },
    {
      "epoch": 0.03285046195962131,
      "grad_norm": 0.7066594958305359,
      "learning_rate": 7.75e-05,
      "loss": 0.7801,
      "step": 18
    },
    {
      "epoch": 0.03467548762404472,
      "grad_norm": 0.5954535007476807,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.7334,
      "step": 19
    },
    {
      "epoch": 0.036500513288468116,
      "grad_norm": 0.5671157836914062,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.662,
      "step": 20
    },
    {
      "epoch": 0.03832553895289152,
      "grad_norm": 0.6849473714828491,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.8301,
      "step": 21
    },
    {
      "epoch": 0.04015056461731493,
      "grad_norm": 0.7973899841308594,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.8623,
      "step": 22
    },
    {
      "epoch": 0.041975590281738334,
      "grad_norm": 0.8184006214141846,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.0401,
      "step": 23
    },
    {
      "epoch": 0.04380061594616174,
      "grad_norm": 0.9607341289520264,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.0293,
      "step": 24
    },
    {
      "epoch": 0.045625641610585146,
      "grad_norm": 1.3468083143234253,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.9982,
      "step": 25
    },
    {
      "epoch": 0.045625641610585146,
      "eval_loss": 0.7038731575012207,
      "eval_runtime": 2.0359,
      "eval_samples_per_second": 24.559,
      "eval_steps_per_second": 6.385,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 2.984041808658432e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}