File size: 5,657 Bytes
0ed9c4c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.3729974329471588,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.7782101167315175,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0311284046692607,
      "grad_norm": 52.70968246459961,
      "learning_rate": 5e-05,
      "loss": 8.0843,
      "step": 1
    },
    {
      "epoch": 0.0311284046692607,
      "eval_loss": 8.973531723022461,
      "eval_runtime": 1.5439,
      "eval_samples_per_second": 32.385,
      "eval_steps_per_second": 8.42,
      "step": 1
    },
    {
      "epoch": 0.0622568093385214,
      "grad_norm": 53.89131164550781,
      "learning_rate": 0.0001,
      "loss": 8.5925,
      "step": 2
    },
    {
      "epoch": 0.0933852140077821,
      "grad_norm": 37.69356155395508,
      "learning_rate": 9.990365154573717e-05,
      "loss": 8.0115,
      "step": 3
    },
    {
      "epoch": 0.1245136186770428,
      "grad_norm": 15.508984565734863,
      "learning_rate": 9.961501876182148e-05,
      "loss": 6.6474,
      "step": 4
    },
    {
      "epoch": 0.1556420233463035,
      "grad_norm": 22.018217086791992,
      "learning_rate": 9.913533761814537e-05,
      "loss": 6.004,
      "step": 5
    },
    {
      "epoch": 0.1867704280155642,
      "grad_norm": 12.03746509552002,
      "learning_rate": 9.846666218300807e-05,
      "loss": 5.3792,
      "step": 6
    },
    {
      "epoch": 0.2178988326848249,
      "grad_norm": 10.574116706848145,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.733,
      "step": 7
    },
    {
      "epoch": 0.2490272373540856,
      "grad_norm": 11.999857902526855,
      "learning_rate": 9.657457896300791e-05,
      "loss": 4.1143,
      "step": 8
    },
    {
      "epoch": 0.2801556420233463,
      "grad_norm": 13.117135047912598,
      "learning_rate": 9.535927336897098e-05,
      "loss": 4.1396,
      "step": 9
    },
    {
      "epoch": 0.311284046692607,
      "grad_norm": 11.065128326416016,
      "learning_rate": 9.397114317029975e-05,
      "loss": 3.5544,
      "step": 10
    },
    {
      "epoch": 0.3424124513618677,
      "grad_norm": 8.749752044677734,
      "learning_rate": 9.241613255361455e-05,
      "loss": 3.1875,
      "step": 11
    },
    {
      "epoch": 0.3735408560311284,
      "grad_norm": 16.695640563964844,
      "learning_rate": 9.070090031310558e-05,
      "loss": 2.7578,
      "step": 12
    },
    {
      "epoch": 0.4046692607003891,
      "grad_norm": 10.788463592529297,
      "learning_rate": 8.883279133655399e-05,
      "loss": 2.4173,
      "step": 13
    },
    {
      "epoch": 0.4357976653696498,
      "grad_norm": 9.146074295043945,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.9589,
      "step": 14
    },
    {
      "epoch": 0.4669260700389105,
      "grad_norm": 8.945752143859863,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.5098,
      "step": 15
    },
    {
      "epoch": 0.4980544747081712,
      "grad_norm": 10.399638175964355,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.1905,
      "step": 16
    },
    {
      "epoch": 0.5291828793774319,
      "grad_norm": 9.355493545532227,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.4249,
      "step": 17
    },
    {
      "epoch": 0.5603112840466926,
      "grad_norm": 8.332611083984375,
      "learning_rate": 7.75e-05,
      "loss": 1.3049,
      "step": 18
    },
    {
      "epoch": 0.5914396887159533,
      "grad_norm": 6.5103864669799805,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.9483,
      "step": 19
    },
    {
      "epoch": 0.622568093385214,
      "grad_norm": 5.166444301605225,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.748,
      "step": 20
    },
    {
      "epoch": 0.6536964980544747,
      "grad_norm": 3.8692352771759033,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.592,
      "step": 21
    },
    {
      "epoch": 0.6848249027237354,
      "grad_norm": 4.719802379608154,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.521,
      "step": 22
    },
    {
      "epoch": 0.7159533073929961,
      "grad_norm": 4.014556407928467,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.4679,
      "step": 23
    },
    {
      "epoch": 0.7470817120622568,
      "grad_norm": 5.582361698150635,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.4608,
      "step": 24
    },
    {
      "epoch": 0.7782101167315175,
      "grad_norm": 6.946940898895264,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.5128,
      "step": 25
    },
    {
      "epoch": 0.7782101167315175,
      "eval_loss": 0.3729974329471588,
      "eval_runtime": 1.0103,
      "eval_samples_per_second": 49.488,
      "eval_steps_per_second": 12.867,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 4.16708196040704e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}